diff --git a/openadapt_flow/runtime/control_overlay.py b/openadapt_flow/runtime/control_overlay.py index 249b58ce..4b1ab90f 100644 --- a/openadapt_flow/runtime/control_overlay.py +++ b/openadapt_flow/runtime/control_overlay.py @@ -49,6 +49,9 @@ "ROLLED_BACK", ] OverlayFrameSink: TypeAlias = Callable[[ControlOverlayFrameV2], None] +OverlayObservationSink: TypeAlias = Callable[ + [ControlOverlayFrameV2, bytes | None], None +] MillisecondsClock: TypeAlias = Callable[[], int | float] ObservationKeyFactory: TypeAlias = Callable[[], bytes] @@ -86,12 +89,14 @@ def __init__( observation_key_factory: ObservationKeyFactory = lambda: secrets.token_bytes( 32 ), + observation_sink: OverlayObservationSink | None = None, ) -> None: self._sink = sink self._mode = ControlOverlayMode(mode) self._unix_ms_clock = unix_ms_clock self._monotonic_ms_clock = monotonic_ms_clock self._observation_key_factory = observation_key_factory + self._observation_sink = observation_sink self._observation_hmac_key: bytes | None = None self._profile: ControlOverlayProfile | None = None self._next_sequence = 0 @@ -121,6 +126,7 @@ def emit_phase( current_step: int | None = None, total_steps: int | None = None, target_tracking: ControlOverlayTargetTrackingV2 | None = None, + observation_png: bytes | None = None, ) -> ControlOverlayFrameV2: """Emit an exact runtime phase; all presentation strings are canonical.""" @@ -143,10 +149,16 @@ def emit_phase( current_step=current_step, total_steps=total_steps, target_tracking=target_tracking, + observation_png=observation_png, terminal=False, ) - def emit_terminal(self, outcome: ExecutionOutcome | str) -> ControlOverlayFrameV2: + def emit_terminal( + self, + outcome: ExecutionOutcome | str, + *, + observation_png: bytes | None = None, + ) -> ControlOverlayFrameV2: """Emit only an exact evidence-qualified ``RunReport.execution_outcome``. Generic success booleans and legacy strings such as ``SUCCESS`` are @@ -164,6 +176,7 @@ def emit_terminal(self, outcome: ExecutionOutcome | str) -> ControlOverlayFrameV current_step=None, total_steps=None, target_tracking=None, + observation_png=observation_png, terminal=True, ) @@ -254,6 +267,7 @@ def _emit( current_step: int | None, total_steps: int | None, target_tracking: ControlOverlayTargetTrackingV2 | None, + observation_png: bytes | None, terminal: bool, ) -> ControlOverlayFrameV2: if self._profile is None: @@ -292,6 +306,13 @@ def _emit( if terminal: self._terminal = True self._sink(frame) + if self._observation_sink is not None: + # Private presentation capture is deliberately out-of-band: the + # screenshot never enters the canonical event or an external + # transport. Exporters/viewers can retain the exact already-held + # observation without taking a new browser screenshot between + # final revalidation and one-shot actuation. + self._observation_sink(frame, observation_png) return frame diff --git a/openadapt_flow/runtime/replayer.py b/openadapt_flow/runtime/replayer.py index d5b55502..b5dcd5dd 100644 --- a/openadapt_flow/runtime/replayer.py +++ b/openadapt_flow/runtime/replayer.py @@ -522,6 +522,7 @@ def __init__( self.control_overlay = control_overlay self.control_overlay_error: Optional[str] = None self._control_overlay_disabled = False + self._control_overlay_last_observation_png: Optional[bytes] = None # -- public API ---------------------------------------------------------- @@ -911,6 +912,7 @@ def _begin_control_overlay(self, profile: Optional[str]) -> None: self.control_overlay_error = None self._control_overlay_disabled = False + self._control_overlay_last_observation_png = None if self.control_overlay is None: return try: @@ -934,6 +936,7 @@ def _emit_control_overlay_phase( current_step: Optional[int] = None, total_steps: Optional[int] = None, target_tracking: Optional[Any] = None, + observation_png: Optional[bytes] = None, ) -> None: if self.control_overlay is None or self._control_overlay_disabled: return @@ -943,7 +946,10 @@ def _emit_control_overlay_phase( current_step=current_step, total_steps=total_steps, target_tracking=target_tracking, + observation_png=observation_png, ) + if observation_png is not None: + self._control_overlay_last_observation_png = observation_png except Exception as exc: self.control_overlay_error = type(exc).__name__ self._control_overlay_disabled = True @@ -1012,7 +1018,10 @@ def _emit_control_overlay_terminal(self, outcome: Optional[str]) -> None: try: if outcome is None: raise ValueError("run report has no exact execution outcome") - self.control_overlay.emit_terminal(outcome) + self.control_overlay.emit_terminal( + outcome, + observation_png=self._control_overlay_last_observation_png, + ) except Exception as exc: self.control_overlay_error = type(exc).__name__ self._control_overlay_disabled = True @@ -2761,12 +2770,6 @@ def _run_step( overlay_current, overlay_total = self._control_overlay_progress( workflow, step_index, graph_ctx ) - self._emit_control_overlay_phase( - "observing", - current_step=overlay_current, - total_steps=overlay_total, - ) - # API/tool tier -- the TOP of the capability ladder. When the step # carries an api_binding and an ApiActuator is configured, PERFORM the # write via the API (deterministic, $0, no GUI), CONFIRM it with the @@ -2805,6 +2808,12 @@ def _run_step( ) result.before_png = self._save_step_png(run_dir, step.id, "before", before_png) last_frame = before_png + self._emit_control_overlay_phase( + "observing", + current_step=overlay_current, + total_steps=overlay_total, + observation_png=before_png, + ) # System-of-record pre-state, snapshotted just before the action when # the step declares effects (see the block guarding self._act below). effect_pre_state: Optional[EffectState] = None @@ -3038,6 +3047,7 @@ def _run_step( current_step=overlay_current, total_steps=overlay_total, target_tracking=overlay_target, + observation_png=before_png, ) try: error = self._act( @@ -3070,14 +3080,15 @@ def _run_step( result.safety_halt = True if error is None: - self._emit_control_overlay_phase( - "verifying", - current_step=overlay_current, - total_steps=overlay_total, - ) try: after_png = self.vision.wait_settled(self.backend) last_frame = after_png + self._emit_control_overlay_phase( + "verifying", + current_step=overlay_current, + total_steps=overlay_total, + observation_png=after_png, + ) postconditions_ok, last_frame, failed = self._check_postconditions( step, after_png, bundle_dir, start_state, result ) diff --git a/public-artifacts.json b/public-artifacts.json index b43b409d..ed6a8f1c 100644 --- a/public-artifacts.json +++ b/public-artifacts.json @@ -4,6 +4,7 @@ "artifact_suffixes": [ ".7z", ".arrow", + ".avi", ".bin", ".cfg", ".conf", @@ -21,6 +22,9 @@ ".json", ".jsonl", ".mjs", + ".mkv", + ".mov", + ".mp4", ".npy", ".npz", ".onnx", @@ -37,6 +41,7 @@ ".toml", ".tsv", ".wasm", + ".webm", ".webp", ".yaml", ".yml", @@ -1882,6 +1887,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-ambiguity/trial-01/events.jsonl", "sha256": "a91f85da34bf137e7fefbb1d5ec7baddd9a2256d931cfdbec238bdc52a7559d7" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-ambiguity/trial-01/halt.webm", + "sha256": "b2c811ff0b09a9581c34c1fa5524158b1eb3e204d5c63b3dab82d668d34a6576" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-ambiguity/trial-01/oracle.json", "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" @@ -1978,6 +1987,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-missing-effect/trial-01/events.jsonl", "sha256": "bfad48babc94d76a4cb369cb04df6c8e38278143f64536425e179f0344a15bf2" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-missing-effect/trial-01/halt.webm", + "sha256": "af085356dbfed4cfda483df07fd9da088c349bad28a9261234da5358732f7dff" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-missing-effect/trial-01/oracle.json", "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" @@ -2254,6 +2267,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-stale-identity/trial-01/events.jsonl", "sha256": "e9aac6e38059cefa2952765e3692ae2931da17c972ba8ef06fc57022c49bc224" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-stale-identity/trial-01/halt.webm", + "sha256": "6af5729a96f281f1ca386093850ababfcfe2dca053d0c58c2c56ce5d73052442" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-stale-identity/trial-01/oracle.json", "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" @@ -2350,6 +2367,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-weak-effect/trial-01/events.jsonl", "sha256": "633fb2c63f0a72462b11739edfd88dab2e8b22e39287379aac636df636d4dfc2" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-weak-effect/trial-01/halt.webm", + "sha256": "b1f1dd8d11429d3ffd53a488c1d5ad34628532a67fe1cf27918dd860ddc5024c" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-weak-effect/trial-01/oracle.json", "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" @@ -2626,6 +2647,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-wrong-identity/trial-01/events.jsonl", "sha256": "50acc12e737f2008cef9ec8d1f112606ee4c20e531d169ad07c240de022e7a84" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-wrong-identity/trial-01/halt.webm", + "sha256": "b15e927a6828e4154649d26d1ac1b4de6f11841f0eed94c5a4ae66097bef1197" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/fault-wrong-identity/trial-01/oracle.json", "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" @@ -2730,6 +2755,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/representative/trial-01/outcome.json", "sha256": "742e1fe45d5be237e069b31c48a85132c04fec1fd3384c8b4c9a0f896cd5d718" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/representative/trial-01/replay.webm", + "sha256": "bcf4e20e50134e84529b28312087b077ef3f0c1c3e519e9ac7a4d9e657bb6069" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json", "sha256": "8bedccacf1bb90a1d9d62a43ca8bb686d8482a6b4d43b3b2ddf692f471dbf58b" @@ -3002,6 +3031,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/compiled/program-graph.json", "sha256": "0c346b7bb23ad508d1731655c2c7e7947776fcd6256334b3b6fb2194b477e461" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/media/recording.webm", + "sha256": "f15bea447b26fd2c9f55c22d0e8e065aa4bf009af779a1b8e75be808491c908c" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v1/artifacts/qualification/project.json", "sha256": "a6819c3dcf91d99ecb325be3d44cca6404dae6cb134c2fd8187299f1a95490a7" @@ -3122,6 +3155,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-ambiguity/trial-01/events.jsonl", "sha256": "bca25dce7eec8d9317c4a7051aab40480c15ec12db5a3823041181e463043a40" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-ambiguity/trial-01/halt.webm", + "sha256": "79b525fc6a16982c3857165704b1391b0bf289957870efa9ed2781d2c7f6a5ea" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-ambiguity/trial-01/oracle.json", "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" @@ -3218,6 +3255,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-missing-effect/trial-01/events.jsonl", "sha256": "6ac475acf54bb53a66a1b2a044e318be7e130ded6a8b87e15aedf782d260c147" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-missing-effect/trial-01/halt.webm", + "sha256": "0d513a530baf60d04bf135197e5c5da83315d85c509969f8da3538d8dfa96c86" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-missing-effect/trial-01/oracle.json", "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" @@ -3494,6 +3535,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-stale-identity/trial-01/events.jsonl", "sha256": "96880fae22a6d690bb318baa57a694df8104ec7355e55b8e282ba4068c574e61" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-stale-identity/trial-01/halt.webm", + "sha256": "11047fca0880108a20f2f6465cde1270b223663a6dafc94cc0c94cb1dd8d6a3d" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-stale-identity/trial-01/oracle.json", "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" @@ -3590,6 +3635,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-weak-effect/trial-01/events.jsonl", "sha256": "806d8f76c5a5433b092a3f56e761a3cce0db18134fee3660553a8db9e97750f9" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-weak-effect/trial-01/halt.webm", + "sha256": "9304add04ad97d35dc2cb698f5e1340305d53e34bdef2e86743e26fab53201b8" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-weak-effect/trial-01/oracle.json", "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" @@ -3866,6 +3915,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-wrong-identity/trial-01/events.jsonl", "sha256": "d158dded31b9256c9c1454e880cb0bde935e297704d412c44ff73ad8f77a39a0" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-wrong-identity/trial-01/halt.webm", + "sha256": "2c72c7bcb44ca0cf274c280c890f7afce6620afa569f02a4db0d5f98c735b33b" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/fault-wrong-identity/trial-01/oracle.json", "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" @@ -3970,6 +4023,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/representative/trial-01/outcome.json", "sha256": "61c6ce5e1dbbe350f935e243461f864416f49b4d7bf8f2bb71386baac6ff1e29" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/representative/trial-01/replay.webm", + "sha256": "7e1bbe78f2573d18772504025701effcb91103d24b9cffdd8c6a1f029da46425" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json", "sha256": "58b2c45fb206cf769078d71e317c50be580fbc2d89c5da2f6be713252c2f6ccf" @@ -4242,6 +4299,10 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/compiled/program-graph.json", "sha256": "b3e6862e1c1e142858e4e5237a4af90af26c9515ce0e8cec194ba6998558d6b8" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/media/recording.webm", + "sha256": "5004a40404842d44b579622b838e406145d271ce93869c71f6827a18238087aa" + }, { "path": "public-demo/evidence-packs/mockmed-triage-v2/artifacts/qualification/project.json", "sha256": "eee3b764cb0d52a0fa4f7f3d801b32205d2002d0313d6562c6c4f9a18791c4c8" @@ -4310,13 +4371,1317 @@ "path": "public-demo/evidence-packs/mockmed-triage-v2/manifest.json", "sha256": "e6afc4b18bbff1f685dbf461e3496337f151a329c1c854c5d0b12393e3018051" }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/manifest.json", + "sha256": "8b304d279409ef6ae384d715274e3ad4bc35be49d2e6a12f918b61da31ba74f0" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000.png", + "sha256": "46a75b5d63ceaad4bee942ccf2a6ca3d2b4f6327509df7eff2cc7ddb2c9fd389" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000_expect.png", + "sha256": "337e403fec476cc955bcf5f1d96902119d9c2fadc03e201c0c2fbc2475d03646" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001.png", + "sha256": "9d17fc905b1902add82cad885c72fe446a23e0334fc4db58592d2369e85f26a5" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001_expect.png", + "sha256": "ccbbb335c8160188198df18beb48bd88082b7bb1e5c1cd987d6766afb62c0773" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002.png", + "sha256": "e6a0e0718b00c26280e32928b744217d00a7e010ab9825da27724e2debc9b805" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002_expect.png", + "sha256": "f66608f19f3acf0ba8d86a39ecdd04781eb320787885039ab1eefee3835c83de" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003.png", + "sha256": "2cb01de3e45c7c6cd6526f1b6f9c1a4f86bee1a5e4f8e3f6fbf7150470cf5f2c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003_expect.png", + "sha256": "68cd40d6bd0abdf81beb40dd4202bac784a4b55492f803cdd5fb1e7ab8f76941" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005.png", + "sha256": "5d8163520ba8355f44ffe0cd06a26be6bfe5d6660bcff1395dc82d4da3aa0ac1" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005_expect.png", + "sha256": "0919dca8fe883ad52eae6359f9da3494cb57c68e006ea4ba314d61e15787ea47" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.json", + "sha256": "1744b74833670792da00b02f61e89506b322864ffcbf31f6c002f456da0d7ace" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/events.jsonl", + "sha256": "a9dcbd93f5fb329c837a99aa38f53037c5289989859232e3e837e4773aee9181" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/halt.webm", + "sha256": "021e51c33ea6275b7013db0a727ffb2deb98fe8778bd3b529ebf97184f6c8247" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/outcome.json", + "sha256": "8cb4a9ee3f4e9a07c58dd162df3f71d0fe877b8e3e78658fba0b5181fad8dfb6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/checkpoints/_manifest.json", + "sha256": "8db2feee452506f7c1d8a21869a3544a0486339689b0e07bb59b524e6fa3fd57" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/pending_escalation.json", + "sha256": "c65459eb889f7c50887703cb567f7d09c6769b5224c16659f5f5921784af8cb8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/report.json", + "sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_after.png", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_before.png", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/events.jsonl", + "sha256": "01c775093f426afefc07258e38c2f6c54986a8856c1d271bef6102f35691f06d" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/outcome.json", + "sha256": "3493370d319101ec7dd1f9b8c0f28864f2ec66d3a240c42b4f5c1eb3f993ab63" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/checkpoints/_manifest.json", + "sha256": "13bbc582a5c0f955cfdf48095cb05750211094a81754f109156ed53b55375573" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/pending_escalation.json", + "sha256": "731847bdd955b40b0037672bf4b1e9b131aed6cea4aac3bb8a286d5546a598cc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/report.json", + "sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_after.png", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_before.png", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/events.jsonl", + "sha256": "754f8fb53a577102e7d788ca9dcff5eb3ad1e1259b6a838ffc418d40219d4daf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/outcome.json", + "sha256": "9a738876e3210993d1f6a6afc2fc8ac898a5230e2143b46180f93d1903db420f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/checkpoints/_manifest.json", + "sha256": "88682d8d15dd6a0160a9be8f6f0e5f1b33ed46b1f2b0cc253f85044a9700c90b" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/pending_escalation.json", + "sha256": "70d602353201bd5f9332284c63e87b057f4308cb948ba0791d44e2f21904ce93" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/report.json", + "sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_after.png", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_before.png", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/events.jsonl", + "sha256": "b06812e5d70d08f1e0541198384faeed2c6e761195378fc1914e7e7a16931d6b" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/halt.webm", + "sha256": "7eb3a32687049eae20bd4a114d3f7561be77e6c6d0678c38cac4d19d420b2317" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/oracle.json", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/outcome.json", + "sha256": "9200874f2a500208b57d4a139e38bfcbe2764ee453bc4d9698a88bbf0f258e14" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/_manifest.json", + "sha256": "48de396a45219641c6631b2fa2a02c573df2a585c85ea636a7373e95a7590146" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0000_step_000.json", + "sha256": "814decd92968bc3bcf806cd2054639c2309c237d53d0e3e3ed740ff7259d47b0" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0001_step_001.json", + "sha256": "2ba3c88fa8c8a6d36146d219eb7ac90f62ab005de25c97e9389e89410001cd9e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0002_step_002.json", + "sha256": "9a05ee6cc6df9b57bf39b22098ab83be01e738e481c2c03e6ad827bc2145528c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0003_step_003.json", + "sha256": "a5675e04a9b42af9d31c28c5434d88bf68cb03b49cacf0189a5da5addf7a9ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0004_step_004.json", + "sha256": "4ac68705abc17bb762716f1478f2a4dd8b13dc3f915cbb2dcf104c8931da6c81" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/pending_escalation.json", + "sha256": "7ecc0e49a256975f82c0a3071082d965343ba754927d39cd9c00140021c94498" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/report.json", + "sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_before.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/events.jsonl", + "sha256": "4d55ca68adf0f359fe0fa45b804b0e2b8a23a3b088de6412d39050b748285964" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/oracle.json", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/outcome.json", + "sha256": "d44ca70b9756bace314bb27a8964d3292079c0702e9448d2f4ba203dd0cceb4e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/_manifest.json", + "sha256": "51cbd0f8e3b7cb3270a09a2d6a6ffbb68a429b19de8291121ef41f68e46bba53" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0000_step_000.json", + "sha256": "e67952329148384eb8fa207297cb050a7af22b230db5d85f2118574d70aee4e7" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0001_step_001.json", + "sha256": "6693530faa7fe1ef09b0fafc5fff911af6cb6a64326f0a9d276e75cb3686136e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0002_step_002.json", + "sha256": "fcdcad265795c0d939e9de06dfcdcaec9c01ada20bcb22eb2ff44df51fa4cc6f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0003_step_003.json", + "sha256": "513042c8454f22289315a5dfc9b2e78632fbc9e908c72416810f6e14709c71b7" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0004_step_004.json", + "sha256": "c205aa56f8ee22b7d3e9252dfda2b48a86562bf6103cd1f8e1e0c08d3b3c2c2a" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/pending_escalation.json", + "sha256": "0dd76766cd687b0048595e1a302ae37c216e93a02ac1f54e8acce4ba6d395ed8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/report.json", + "sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_before.png", + "sha256": "d6c6c2d29da6ee4ab499388f4f66f05c39fa4d64bc39888c85bea76872c50a45" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_before.png", + "sha256": "9130e1d0c88efd3e3f6b4e8a80ece1e58ba2c1cb86a9cd8381f5753f3fe185ed" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_before.png", + "sha256": "019102af701afd1c0103fd3fefe8af7b88f0f1fae2d75e28b79875efee143e93" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/events.jsonl", + "sha256": "21a6e0b3080e32b46fe0d4b42f0a55038199828491cc317f4e4c25d6b7cfe469" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/oracle.json", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/outcome.json", + "sha256": "d11a823161311ad40d0d34774c087ed1cf90a60bca1baa7e5aaede75190ba171" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/_manifest.json", + "sha256": "2b7683f5845d18217037b701d32a360dc8442b7db6ea96ee3e08f531abfce881" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0000_step_000.json", + "sha256": "af72ba361b2e388b1c7dd40efe06ca410b886f2dfb4f0f055dd5c4c6a38c5cc5" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0001_step_001.json", + "sha256": "691219140254286808bba388b8bf26386d7d4482a95b5e40deb17d3797eddebd" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0002_step_002.json", + "sha256": "012f7406bdec2bcad62c1c80b27f9aa10eb89049cb9342ed1f4e852950d05b39" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0003_step_003.json", + "sha256": "57d3f431804993efc87e2f0886ca17e76ac8bf5d3ff0adf9de2422c887c633ba" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0004_step_004.json", + "sha256": "7588a898e3e183bc5534991bad677dddb8c29741e3063ef7eb714f62bd55bcb0" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/pending_escalation.json", + "sha256": "ec91d742252599fd03677a6d75ccc1a617a30c697b03731a96b27859949234bd" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/report.json", + "sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_before.png", + "sha256": "58f1714e31a3f511b5310539b433536169163c74f224402b7dafed32588d0c72" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/events.jsonl", + "sha256": "c8765f112880d5bdea2838f358bd8c008437c15667fe8740212607d112f6ba0e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/halt.webm", + "sha256": "bf4088606ca140b2ee1fe3fc57c693a1e9bb3b199de3e1c5ae9b27fc5739dca7" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/outcome.json", + "sha256": "c4ae9f7ecb4eaf95080f9f91f100a8fb97d5cb2bcda1efc0b6eb451919d88fdd" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/checkpoints/_manifest.json", + "sha256": "9bbddd29a6dc5953603fb1c75042e5f0e3aa87059de1e08b9fbebd3ac2a27a97" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/pending_escalation.json", + "sha256": "45282bbe8ea7b867ef0f9b764f9650b3136c7b7b61daf672fee34db7efb7582b" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/report.json", + "sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_after.png", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_before.png", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/events.jsonl", + "sha256": "d037138e6334a61804bf3230eb9d020bb745d7ecb7bbaee1c6f2c8d7639c7e5c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/outcome.json", + "sha256": "920cd25c90560c2961402a0f5710a47d1149a5e88ce63253a0705f627eed7ee8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/checkpoints/_manifest.json", + "sha256": "29d07aa793191a7c3d33834362cd5a560adee8bb5a5870bea90473e0c0612407" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/pending_escalation.json", + "sha256": "f2371b984668661d145f458dddab30b18596bd74ff6a51a324e9d5840e55daa3" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/report.json", + "sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_after.png", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_before.png", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/events.jsonl", + "sha256": "19aa64247e7bf1fc2fbd99f16f077cbf386c6a328185bfd3a4442dd30733e1ec" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/outcome.json", + "sha256": "f57c04fd555b86f6e6b2a0ae77125e0717670e62ea42df387df650798aaef6e0" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/checkpoints/_manifest.json", + "sha256": "f0cfcaf14c8bbb5cb79e5ca07c82548d09b2aca397c243827130046e976c3cdf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/pending_escalation.json", + "sha256": "058dc7684d0374b60dcf2a6e0d435caec50250117b0d6d65d5686d7f398d9346" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/report.json", + "sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_after.png", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_before.png", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/events.jsonl", + "sha256": "acb3bcc31a489bd719d098115e9b53305b87d8bff37be4109fc4d7ca69e7b857" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/halt.webm", + "sha256": "6f14e316ffeb24dcb8ce97febc045ae8f251df442680b90f0ff3407be49a0ccc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/oracle.json", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/outcome.json", + "sha256": "adb517d20498f540a459c2fb0193b732c740aa81b8a554a2cf08630de032cf73" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/_manifest.json", + "sha256": "3a0548c66e8ceb3017797ba60d001688ba4305e9af74c90fbedfbdb534029d76" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0000_step_000.json", + "sha256": "304f444e5a052ff8cba4bd53b2a80c66c10f810818d3eac462081f19c1f2d891" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0001_step_001.json", + "sha256": "42cd307f1681f42008963393f0b5c21d54ad147dab54c0491bd2268307e4d67d" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0002_step_002.json", + "sha256": "d6b1a792621c8c768c2d1f33396f2c3e15e7bc415ba691cd4017aa5887a32a4f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0003_step_003.json", + "sha256": "ea6aa97652382e7194265077277a259a7c0afe969f0b57857bdb01dca02aba44" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0004_step_004.json", + "sha256": "65a6f68a4e3218ff52b2a7adcbf898b3cb8c9c269d18668f93986f8f6c97f8d2" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/pending_escalation.json", + "sha256": "16e0d80c3338b20135c83c4ac84dca5187fae68088590dc8d4b7c9aa281fef16" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/report.json", + "sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_before.png", + "sha256": "d6c6c2d29da6ee4ab499388f4f66f05c39fa4d64bc39888c85bea76872c50a45" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_before.png", + "sha256": "1ffca11ead5fee98b4f8c11f330152a9765edcea3b2979c51c19f36b47229a4e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/events.jsonl", + "sha256": "ef206aae2902e32c4942fdd4a50cf08451a7704aee7cf48647bd7ab85d557dfa" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/oracle.json", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/outcome.json", + "sha256": "fddaee34409389259c1437e6f9ac3bae6fb1e5dfa0be48f9a6a44c9718eb8be3" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/_manifest.json", + "sha256": "57cb68b7364740aeefc56426784d9c555303e8c5504541fd4cd14ad7be2a1329" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0000_step_000.json", + "sha256": "e1037f598ed2086b6aea6c4fabd592238e7afce3e72947895bead6af6ed1546a" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0001_step_001.json", + "sha256": "5785e92cda87cabc21ba85ad6ba187f1bddd11340acff61c78f71f2e291afd1d" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0002_step_002.json", + "sha256": "8113812e60224cf302bf98d7428a249aca60b526959efccb0c7477a5d8935eb1" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0003_step_003.json", + "sha256": "2ee83b200195ed418dc7fe4167c86f3eefc71d3f44dd3eb08d739ed9de973ad6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0004_step_004.json", + "sha256": "8d9de578f018275cd31799b639f1c5d9040fa861f0f3073029e180737e3f56be" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/pending_escalation.json", + "sha256": "be7e4348be16a2f7e7b4901b979e16331b03c461a550c6d4a4ec4038556bcecd" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/report.json", + "sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_before.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/events.jsonl", + "sha256": "035ad252365df35c1575a353d530fdc321de8f9d6e969d4597f64a9044973175" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/oracle.json", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/outcome.json", + "sha256": "2b567a347febee7ff40b626e3379df0772ed2d79be6c4a7be44d81d8e36f6d1c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/_manifest.json", + "sha256": "b71e61fc56fe03b0720c878fbe1afa4dbe03cd0955eef97da1e2554e4af77ac7" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0000_step_000.json", + "sha256": "658bb9a4fe36fafb6e926a8aba781595707c7bab984bc9ad5db6d9cd5a9e38da" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0001_step_001.json", + "sha256": "04d1251cdd2798383230128572cb135c5f20ef922e0063fdd42559066a2bd025" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0002_step_002.json", + "sha256": "8ea2c34bd4a3bd3fd094901a08f0fd19b551b4ddd31f5fe9cb3339a4a512f874" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0003_step_003.json", + "sha256": "4cd8567fcba71da00bec11d78174fe14b3e9b5f573cb5d86fb0443e3443bf4f7" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0004_step_004.json", + "sha256": "00017a0bfefd2d6da17406d8c648670257b142eae21c18df990ec5899a67cb5a" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/pending_escalation.json", + "sha256": "72187b266e652899ef07acf05aacda19b9f5f6ac63444d3bcc298fcd849723b3" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/report.json", + "sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_before.png", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/events.jsonl", + "sha256": "17cb06e6e6c454cd5a646c09a3a2f84a6681ebb6615ac30c1320f4e6db7e26fb" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/halt.webm", + "sha256": "987ddf3f74b26102e6877de45b2ad4f558b643062253c5fa5058cb8b2490f146" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/outcome.json", + "sha256": "a1987aeb639d36a8b346e48e4762f4767ecc97d5c8fc5f164c83ed0d5ea6e951" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/checkpoints/_manifest.json", + "sha256": "4a7bfcb3583cd6ae7e74e02923527bb4bea4d1d600ab7cc32cd4f81f233be5ee" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/pending_escalation.json", + "sha256": "cfc412811b4dca04bb56499d2def2d972d4bfb1a8b47a25a074f9e68c7ff846c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/report.json", + "sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_after.png", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_before.png", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/events.jsonl", + "sha256": "ce5dbf2378ebee2bb99ad87cc405cf635e092321b09d954b71bf476dc4544dcf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/outcome.json", + "sha256": "98b0042e8cbbd25ee9632e5db57bb4206e38005b2420e357d0865db915f85512" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/checkpoints/_manifest.json", + "sha256": "af8bbff370e0512d4664e4c62b2bb9edf4e5f68cdd426624563d576faf7603ec" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/pending_escalation.json", + "sha256": "34c5aace35f54266009fa6a6664f348459500540d1d2dbd639c7396644e6735b" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/report.json", + "sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_after.png", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_before.png", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/events.jsonl", + "sha256": "ae6393fd33a83b3524fb55080dca38ed1fe7c853f61f5e7a89737e86d0f99921" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/outcome.json", + "sha256": "34d4cbd08fb746e62e765d53a39444403f676361917ce5006e449aca7cfab8aa" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/checkpoints/_manifest.json", + "sha256": "508dff905abe48b6fc24c5a4d21bfaf6184198f8c842c94df9bcd1ec009cdf68" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/pending_escalation.json", + "sha256": "248fca8ba29629384d18327ba565097aa7a714a49ec5b2c91cfb327ea3d0f258" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/report.json", + "sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_after.png", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_before.png", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/events.jsonl", + "sha256": "16c457b60fed99b9e8e77ac449f30e3d2c9bab20302bec9a094f5809bf935b68" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/oracle.json", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/outcome.json", + "sha256": "9fe5537806507fe364e32683b9fc39b17bfd996ffbaae221ff3ecacc37514a89" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/replay.webm", + "sha256": "b84184382c9cfeeb733776a2be72d242c7b21d5e6c2e4e7b249b897e5e5c73bd" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json", + "sha256": "1adb36cf8e55daf95f283486d6746554e37c5ea51433f57ac6a073c6757c5738" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0000_step_000.json", + "sha256": "35ce6b839a6ffb54f2766d7eb15c3b9b2ae8f25cead2f02c3e95eca2fa1cb19d" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0001_step_001.json", + "sha256": "b25134478eef367269c448ec99724196482e0de11a07a55937889761b84d7b6f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0002_step_002.json", + "sha256": "79cb1810e036fdbaa91a6bbe7eaa151a34fe1133358c7c00ec43dec80fcc4dd4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0003_step_003.json", + "sha256": "e8b1e7280c68307956ad9c6e0ec4360a4a4db959aba442adb0eec7d4c1ed4506" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0004_step_004.json", + "sha256": "391844051eca3c449e070711157ce910c65eebf902b9c2102a56791b4c01dd56" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0005_step_005.json", + "sha256": "ac60acd0ae5385aafd10d5846e06a948f4cc7c742da1b782fe8d189bc8c9a94f" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/report.json", + "sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_before.png", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_before.png", + "sha256": "58f1714e31a3f511b5310539b433536169163c74f224402b7dafed32588d0c72" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/events.jsonl", + "sha256": "911084d767b52fcb9955a9a3b52e64848aa2d444cd263b116e0b7636b263adf6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/oracle.json", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/outcome.json", + "sha256": "7e035ce556cbaa0b810d5e0d7164f8739956ab0b523803e87aea8920cbdc0643" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/_manifest.json", + "sha256": "cfbd75260c107f1dd37ff09f8973400eb408616599d7caf4a2a80d8f9e71ee84" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0000_step_000.json", + "sha256": "27342a30d986e092f15818f60b26dcf29cbadc1127e8ad12490f2f7138d71082" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0001_step_001.json", + "sha256": "f77f0e231054afe11778dcece240e92f9ac5df930d004261c3059d11aadbaedc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0002_step_002.json", + "sha256": "2f26cf6c608c501195dfd3f44d82e195e661f5d64632bb61da12cec1c0356681" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0003_step_003.json", + "sha256": "5d10cc81902b935eb2ce53d8f7e691701acb497a0f6580cdbe0aa1711d725eca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0004_step_004.json", + "sha256": "fad67f0751b96824ec423100de3a37336a3fde2ae2f9d279167ae96ae0af69a5" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0005_step_005.json", + "sha256": "9e80298ac69fed791a6f729418f6c00603550a1ef00092748c757a7d8d3959d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/report.json", + "sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_before.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_before.png", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/events.jsonl", + "sha256": "7204bc6d968bee2932fc83a8701ca763e32699c4547a8ab0cc88fd7741dd1dc8" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/oracle.json", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/outcome.json", + "sha256": "dd3e5b88e62166a75c11bbc91d0f0015b9bc489d078649a8e529a07ab134a5e1" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/_manifest.json", + "sha256": "cf19e5bda0e6731bb9b3da701740b64b96a84142d4301c32d5e8c4a3cf82fd43" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0000_step_000.json", + "sha256": "285cbed7c30d014dfa34b0ae6ba42ca6bae6209952970e455aeaa67fe5cc23c2" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0001_step_001.json", + "sha256": "436d7635b1731ee815993598bce7d552a3bf2381d299a13bafc0bbe3a2e4eec9" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0002_step_002.json", + "sha256": "49567d7332e299ce257ee9d3343da3f1ba10ae4d294bc68a6542496776ff0c5d" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0003_step_003.json", + "sha256": "be93b6229e20c4481fed797baac5d3820841718d78c5ba1166046948e7b46494" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0004_step_004.json", + "sha256": "a7664a09d18cb568bc212d99b3712b84e17609186e7ea00d12c94df71de67c5c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0005_step_005.json", + "sha256": "a648f8cb18385f7d416298037c7887f5712b59caa09b0bc964b2074c3d37db60" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/report.json", + "sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_after.png", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_after.png", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_before.png", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_after.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_before.png", + "sha256": "58f1714e31a3f511b5310539b433536169163c74f224402b7dafed32588d0c72" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_after.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_before.png", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_after.png", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_before.png", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_after.png", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_before.png", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.html", + "sha256": "15f97a7e127bbea3188f421ffd3b2bc8a18d6bffa0d61e117dabee43da355883" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.json", + "sha256": "016e509e71d6f649f8f3ff37e723f551ee0c32e081a1f1fc00713eab6ef3ebe3" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/media/recording.webm", + "sha256": "3ac77627340b5f3ef3adc37b9b8f05091bdc886e0d65d2ec2baac9ed591cc438" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.control-overlay.v2.json", + "sha256": "cfab1104ffaf3726eded86cf0378e5e5d3386802f5bab5b4179cf7a2ac2ead1d" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.frame-pts-us.json", + "sha256": "f6ed892ccc0a64a969ec12ec4a37f87d7cfcad5cafd5e002ff4871aabf626469" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.webm", + "sha256": "6a15175effc07fa737f3a1c020baa6a13e7548f382cf5f25d419e6ffb64b91bf" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.control-overlay.v2.json", + "sha256": "d97b7c13a0724989e292b45a4ea1435338db6889503f06f52e15421e0d3faa7c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.frame-pts-us.json", + "sha256": "64e5b69483ae0c70a2afb10eebe6e9917cacb2dd766bb672f94424a073240bb2" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.webm", + "sha256": "59cdce33ff0fbbf0aadc78ebe9eabe6cf189dc7f8aa2e9f2d1724d90cf8270f1" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.control-overlay.v2.json", + "sha256": "5742b18dc4532f6470f41ff9a21baf1dc637d5fab5d484defd36ba542ffd569c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.frame-pts-us.json", + "sha256": "821f6c48c2d5cfe00e86a44c886508e258678cb8f863a2dff26f5736dce71674" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.webm", + "sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/project.json", + "sha256": "d4a2db89a83f7aa7c28d233903228d82a323a4788b2bf5ea5e9a31a370cf4c78" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/report.json", + "sha256": "24f34c46f6feff7d2ac369416dda13a193b9487e360ffe7c00b36725474afa3c" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/events.jsonl", + "sha256": "c5ab16f16eacf2d81c060084c63ea3a29cc803a14ca4d7bcd5055fa8daadc9fb" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_after.png", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_before.png", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_after.png", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_before.png", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_after.png", + "sha256": "8d2d2d2a56a8d089b11f1e97926c06f0c1d7076e080d0ffbd70b0bf1691aeae3" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_before.png", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_after.png", + "sha256": "8a3c5f2a1a6d1816b42227a818afe24a0c1d7362791773cb6f18d1fcd1b314d9" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_before.png", + "sha256": "8d2d2d2a56a8d089b11f1e97926c06f0c1d7076e080d0ffbd70b0bf1691aeae3" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_after.png", + "sha256": "d4da8dbaf7fa257e89d78a08854ccd50c8277c3fcb12efe2614d3fa4508a3026" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_before.png", + "sha256": "8a3c5f2a1a6d1816b42227a818afe24a0c1d7362791773cb6f18d1fcd1b314d9" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_after.png", + "sha256": "09b63152f50688a01352cbab13a1ea33e2d837b36180c866849ec4cdfaeaa599" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_before.png", + "sha256": "d4da8dbaf7fa257e89d78a08854ccd50c8277c3fcb12efe2614d3fa4508a3026" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/meta.json", + "sha256": "17494cf94c54918f37e6237b2024809cc53160ec870b357e946149ea1e9183e1" + }, + { + "path": "public-demo/evidence-packs/mockmed-triage-v3/manifest.json", + "sha256": "a4c531de62d875355a359dce4655fe80963ab1be421c99c1be317d82cdccd49d" + }, { "path": "schemas/program-graph-v1.json", "sha256": "bc54c5df18ef47d2c54f7eb822847d12ce7613d545ac7f3b3f77872e3cf9e742" }, { "path": "schemas/public-demo-evidence-v1.json", - "sha256": "fe0b4b20a4338d8c4ea39a5d2e7b788dafa56e73639a084dd263f86f2a9f3baa" + "sha256": "fc7bca6e1ea0cfc9c70c11368d7b59d542f75f98f2dbaf4d869247225e53c1fd" }, { "path": "schemas/runtime-validation-attestation-v1.json", diff --git a/public-demo/README.md b/public-demo/README.md index 9c7555f7..e72339a7 100644 --- a/public-demo/README.md +++ b/public-demo/README.md @@ -7,23 +7,31 @@ and source-distribution artifacts. Generate a new version (never overwrite an existing pack): ```bash +pip install -e '.[dev,interop]' python -m scripts.export_public_demo_evidence \ --out public-demo/evidence-packs \ - --pack-id mockmed-triage-v2 + --pack-id mockmed-triage-v3 ``` +Generation also requires separately provisioned `ffmpeg` and `ffprobe`; neither +executable is embedded in OpenAdapt packages or the retained evidence pack. + Validate every retained byte and evidence binding: ```bash python -m scripts.export_public_demo_evidence \ - --validate public-demo/evidence-packs/mockmed-triage-v2 + --validate public-demo/evidence-packs/mockmed-triage-v3 ``` -`mockmed-triage-v1` remains retained as the immutable first export. The current -`v2` pack binds the finalized browser actuation guard and record-identity -semantics to a new source commit instead of rewriting prior evidence. +`mockmed-triage-v1` and `v2` remain retained as immutable prior exports. The +current `v3` pack adds fresh presentation derivatives bound to canonical +runtime-overlay events, exact decoded-frame indexes, and inventoried media/PTS +digests instead of retrofitting timing onto the older raw videos. The target data is first-party synthetic MockMed data. The recording, compiled bundle, program graph, qualification project/report, governed run reports, outcome envelopes, raw videos, frames, and source-of-record oracles are actual artifacts rather than fixture-shaped Cloud UI records. +The three `artifacts/presentation` WebMs are explicitly derived viewing media; +the raw recording and governed run videos remain unchanged and separately +inventory-bound. diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/manifest.json new file mode 100644 index 00000000..ad97df89 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/manifest.json @@ -0,0 +1,30 @@ +{ + "schema_version": 2, + "content_digest": "c3f3e82732db5dd186289f71ce9f24c13452fa07fddcdfbe8d5d61e4b5281542", + "file_hashes": { + "templates/step_000.png": "46a75b5d63ceaad4bee942ccf2a6ca3d2b4f6327509df7eff2cc7ddb2c9fd389", + "templates/step_000_expect.png": "337e403fec476cc955bcf5f1d96902119d9c2fadc03e201c0c2fbc2475d03646", + "templates/step_001.png": "9d17fc905b1902add82cad885c72fe446a23e0334fc4db58592d2369e85f26a5", + "templates/step_001_expect.png": "ccbbb335c8160188198df18beb48bd88082b7bb1e5c1cd987d6766afb62c0773", + "templates/step_002.png": "e6a0e0718b00c26280e32928b744217d00a7e010ab9825da27724e2debc9b805", + "templates/step_002_expect.png": "f66608f19f3acf0ba8d86a39ecdd04781eb320787885039ab1eefee3835c83de", + "templates/step_003.png": "2cb01de3e45c7c6cd6526f1b6f9c1a4f86bee1a5e4f8e3f6fbf7150470cf5f2c", + "templates/step_003_expect.png": "68cd40d6bd0abdf81beb40dd4202bac784a4b55492f803cdd5fb1e7ab8f76941", + "templates/step_005.png": "5d8163520ba8355f44ffe0cd06a26be6bfe5d6660bcff1395dc82d4da3aa0ac1", + "templates/step_005_expect.png": "0919dca8fe883ad52eae6359f9da3494cb57c68e006ea4ba314d61e15787ea47" + }, + "provenance": { + "compiler_version": "1.23.0", + "source_recording_sha256": null, + "compiler_config_sha256": "479f143ba6970af144553f82f66990463129ee6606852260478c9c2a79b7f91d", + "created_at": "2026-07-26T07:06:47.886463+00:00", + "policy_name": "clinical-write", + "certified": true, + "certification_status": "certified", + "certified_at": "2026-07-26T07:08:22.726707+00:00", + "expires_at": null, + "certification_invalidated_at": null, + "certification_invalidation_reason": null + }, + "encrypted": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000.png new file mode 100644 index 00000000..0331b6da Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000_expect.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000_expect.png new file mode 100644 index 00000000..3eeeecbb Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_000_expect.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001.png new file mode 100644 index 00000000..7556f803 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001_expect.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001_expect.png new file mode 100644 index 00000000..ff091516 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_001_expect.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002.png new file mode 100644 index 00000000..f0699083 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002_expect.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002_expect.png new file mode 100644 index 00000000..0d074dc0 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_002_expect.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003.png new file mode 100644 index 00000000..0ae38e7f Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003_expect.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003_expect.png new file mode 100644 index 00000000..ea7a2d31 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_003_expect.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005.png new file mode 100644 index 00000000..ec72ed50 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005_expect.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005_expect.png new file mode 100644 index 00000000..9a298828 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/templates/step_005_expect.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.json new file mode 100644 index 00000000..8628eae3 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.json @@ -0,0 +1,1355 @@ +{ + "schema_version": 2, + "name": "mockmed-triage", + "recording_id": "3290705d23254d978c7a335776e407ad", + "contains_phi": false, + "phi_scrubbed": false, + "encrypted": false, + "created_at": "2026-07-26T07:06:47.886221+00:00", + "viewport": [ + 1280, + 800 + ], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "param_specs": { + "note": { + "name": "note", + "type": "string", + "example": "Synthetic follow-up in two weeks", + "required": true, + "choices": [] + } + }, + "secret_params": [], + "steps": [ + { + "id": "step_000", + "intent": "click 'Open'", + "action": "click", + "anchor": { + "template": "templates/step_000.png", + "structural": { + "selector": "#open-p1", + "frame_path": null, + "role": "button", + "name": "Open", + "automation_id": null, + "window_name": null + }, + "region": [ + 695, + 154, + 160, + 64 + ], + "click_point": [ + 775, + 186 + ], + "ocr_text": "Open", + "context_text": null, + "structured_identity": null, + "identity_template": { + "schema_version": 1, + "salt": "c8887ea55d5a3781d3962e9dd6ef76d9", + "band_len": 30, + "tokens": [ + { + "c": "6ea091d5f9ee7cfe", + "r": "6ea091d5f9ee7cfe", + "n": 10, + "alpha": true, + "name": true, + "digit": false, + "idsh": false, + "glyph": false, + "gen": false + }, + { + "c": "2df90d28ac6dcd27", + "r": "2df90d28ac6dcd27", + "n": 4, + "alpha": true, + "name": true, + "digit": false, + "idsh": false, + "glyph": false, + "gen": false + }, + { + "c": "f2edf2308507962c", + "r": "29a63eedb29d1153", + "n": 4, + "alpha": true, + "name": true, + "digit": false, + "idsh": false, + "glyph": false, + "gen": false + }, + { + "c": "044b63bb729bddd4", + "r": "044b63bb729bddd4", + "n": 8, + "alpha": true, + "name": true, + "digit": false, + "idsh": false, + "glyph": false, + "gen": false + }, + { + "c": "3f52bc804134d00a", + "r": "aa748a391080ede9", + "n": 4, + "alpha": true, + "name": true, + "digit": false, + "idsh": false, + "glyph": false, + "gen": false + } + ], + "concats": [ + { + "i": 0, + "size": 2, + "c": "c47b03ec0c8a0d7e", + "r": "c47b03ec0c8a0d7e", + "digit": false, + "name": true, + "n": 14 + }, + { + "i": 0, + "size": 3, + "c": "11f5d4c43f93d95e", + "r": "b00bf35d2690abd3", + "digit": false, + "name": true, + "n": 18 + }, + { + "i": 0, + "size": 4, + "c": "aa06789d3d05b361", + "r": "4d17e4c7cac5fbd3", + "digit": false, + "name": true, + "n": 26 + }, + { + "i": 1, + "size": 2, + "c": "ca3513c757f4ced2", + "r": "834701f25ee7b09f", + "digit": false, + "name": true, + "n": 8 + }, + { + "i": 1, + "size": 3, + "c": "35eb5657b10f3ba0", + "r": "ea7820d360bfd89f", + "digit": false, + "name": true, + "n": 16 + }, + { + "i": 1, + "size": 4, + "c": "9e5ff3eed4ca9fa4", + "r": "6ace3fdb6b3fb235", + "digit": false, + "name": true, + "n": 20 + }, + { + "i": 2, + "size": 2, + "c": "879bca194b8f65b6", + "r": "a58edebd1fd7fe82", + "digit": false, + "name": true, + "n": 12 + }, + { + "i": 2, + "size": 3, + "c": "30505790b18a521f", + "r": "50b8da0b181f02f9", + "digit": false, + "name": true, + "n": 16 + }, + { + "i": 3, + "size": 2, + "c": "60caa1d8baeeb22d", + "r": "fe5efbea8109e8ea", + "digit": false, + "name": true, + "n": 12 + } + ], + "structured": "dde9db65d2c7c866", + "signal_hashes": { + "structured|exact|": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|unicode_nfkc": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|casefold": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|collapse_whitespace": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|strip_punctuation": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|unicode_nfkc,casefold": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|unicode_nfkc,collapse_whitespace": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|unicode_nfkc,strip_punctuation": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|casefold,collapse_whitespace": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|casefold,strip_punctuation": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|collapse_whitespace,strip_punctuation": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|unicode_nfkc,casefold,strip_punctuation": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|unicode_nfkc,collapse_whitespace,strip_punctuation": "5d864e6463d5eeb130a9093c4317f587e83557fd87a0cfa63938c41e53865f37", + "structured|normalized|casefold,collapse_whitespace,strip_punctuation": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace,strip_punctuation": "dde9db65d2c7c866fb6770b431537b34c8f4e1cfed0edbd6fb3cd0c7036f2977", + "captured_context|exact|": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|unicode_nfkc": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|casefold": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|collapse_whitespace": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|strip_punctuation": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|unicode_nfkc,casefold": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|unicode_nfkc,collapse_whitespace": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|unicode_nfkc,strip_punctuation": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|casefold,collapse_whitespace": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|casefold,strip_punctuation": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|collapse_whitespace,strip_punctuation": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|unicode_nfkc,casefold,collapse_whitespace": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|unicode_nfkc,casefold,strip_punctuation": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|unicode_nfkc,collapse_whitespace,strip_punctuation": "fcc4aadc296a76b5ced8f382c21f59bd765ceede824de377a71568a726bc9423", + "captured_context|normalized|casefold,collapse_whitespace,strip_punctuation": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781", + "captured_context|normalized|unicode_nfkc,casefold,collapse_whitespace,strip_punctuation": "ad5c86ac035fa66d1a0dde4c362fd78dc733688188a4d92134efd4943919c781" + }, + "param_token_indices": {}, + "rests_on_confusable_identifier": false + }, + "identifier_crop": null, + "identifier_region": null, + "landmarks": [ + { + "relation": "above", + "ocr_text": "Action", + "distance_px": 51, + "dx_px": 20, + "dy_px": 47 + }, + { + "relation": "below", + "ocr_text": "Open", + "distance_px": 58, + "dx_px": -2, + "dy_px": -58 + } + ], + "search_pad": 80 + }, + "text": null, + "param": null, + "secret": false, + "key": null, + "scroll_dx": null, + "scroll_dy": null, + "expect": [ + { + "kind": "region_stable", + "text": null, + "region": [ + 0, + 43, + 968, + 318 + ], + "phash": "f8e083ffbc08383c", + "phash_tolerance": 16, + "timeout_s": 5.0, + "template": "templates/step_000_expect.png" + }, + { + "kind": "text_present", + "text": "JaneSample—MRNP1—DOB1980-01-01", + "region": null, + "phash": null, + "phash_tolerance": 8, + "timeout_s": 5.0, + "template": null + } + ], + "effects": [], + "api_binding": null, + "risk": "reversible", + "wait_until": null, + "guard": null, + "timeout_s": 10.0, + "identity_armed": true, + "identity_unarmed_reason": null, + "identifier_crop_missing_reason": "structured identity (DOM/UIA/AX) owns this step's identity; no identifier pixels persisted at rest — mark the identifier field/region at record time (--identifier) to also arm the pixel tier for remote-display replays" + }, + { + "id": "step_001", + "intent": "click 'New Encounter'", + "action": "click", + "anchor": { + "template": "templates/step_001.png", + "structural": { + "selector": "#new-encounter", + "frame_path": null, + "role": "button", + "name": "New Encounter", + "automation_id": null, + "window_name": null + }, + "region": [ + 34, + 127, + 160, + 64 + ], + "click_point": [ + 114, + 159 + ], + "ocr_text": "New Encounter", + "context_text": null, + "structured_identity": null, + "identity_template": { + "schema_version": 1, + "salt": "c8887ea55d5a3781d3962e9dd6ef76d9", + "band_len": 0, + "tokens": [], + "concats": [], + "structured": "84fd8e01b2a61fc6", + "signal_hashes": { + "structured|exact|": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960" + }, + "param_token_indices": {}, + "rests_on_confusable_identifier": false + }, + "identifier_crop": null, + "identifier_region": null, + "landmarks": [ + { + "relation": "below", + "ocr_text": "Encounters", + "distance_px": 61, + "dx_px": 34, + "dy_px": -51 + }, + { + "relation": "below", + "ocr_text": "No encountersyet.", + "distance_px": 85, + "dx_px": 24, + "dy_px": -82 + } + ], + "search_pad": 80 + }, + "text": null, + "param": null, + "secret": false, + "key": null, + "scroll_dx": null, + "scroll_dy": null, + "expect": [ + { + "kind": "region_stable", + "text": null, + "region": [ + 0, + 101, + 696, + 350 + ], + "phash": "fae0c01e950fc78e", + "phash_tolerance": 16, + "timeout_s": 5.0, + "template": "templates/step_001_expect.png" + }, + { + "kind": "text_present", + "text": "EncounterType", + "region": null, + "phash": null, + "phash_tolerance": 8, + "timeout_s": 5.0, + "template": null + } + ], + "effects": [], + "api_binding": null, + "risk": "reversible", + "wait_until": null, + "guard": null, + "timeout_s": 10.0, + "identity_armed": true, + "identity_unarmed_reason": null, + "identifier_crop_missing_reason": "structured identity (DOM/UIA/AX) owns this step's identity; no identifier pixels persisted at rest — mark the identifier field/region at record time (--identifier) to also arm the pixel tier for remote-display replays" + }, + { + "id": "step_002", + "intent": "click 'Triage'", + "action": "click", + "anchor": { + "template": "templates/step_002.png", + "structural": { + "selector": "#type-triage", + "frame_path": null, + "role": "button", + "name": "Triage", + "automation_id": null, + "window_name": null + }, + "region": [ + 5, + 182, + 160, + 64 + ], + "click_point": [ + 85, + 214 + ], + "ocr_text": "Triage", + "context_text": null, + "structured_identity": null, + "identity_template": { + "schema_version": 1, + "salt": "c8887ea55d5a3781d3962e9dd6ef76d9", + "band_len": 0, + "tokens": [], + "concats": [], + "structured": "84fd8e01b2a61fc6", + "signal_hashes": { + "structured|exact|": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960" + }, + "param_token_indices": {}, + "rests_on_confusable_identifier": false + }, + "identifier_crop": null, + "identifier_region": null, + "landmarks": [ + { + "relation": "below", + "ocr_text": "Note", + "distance_px": 70, + "dx_px": 44, + "dy_px": -54 + }, + { + "relation": "above", + "ocr_text": "NewEncounter", + "distance_px": 77, + "dx_px": -26, + "dy_px": 72 + } + ], + "search_pad": 80 + }, + "text": null, + "param": null, + "secret": false, + "key": null, + "scroll_dx": null, + "scroll_dy": null, + "expect": [ + { + "kind": "region_stable", + "text": null, + "region": [ + 0, + 163, + 177, + 102 + ], + "phash": "88c2f2295d2da73d", + "phash_tolerance": 16, + "timeout_s": 5.0, + "template": "templates/step_002_expect.png" + } + ], + "effects": [], + "api_binding": null, + "risk": "reversible", + "wait_until": null, + "guard": null, + "timeout_s": 10.0, + "identity_armed": true, + "identity_unarmed_reason": null, + "identifier_crop_missing_reason": "structured identity (DOM/UIA/AX) owns this step's identity; no identifier pixels persisted at rest — mark the identifier field/region at record time (--identifier) to also arm the pixel tier for remote-display replays" + }, + { + "id": "step_003", + "intent": "click at (480, 268)", + "action": "click", + "anchor": { + "template": "templates/step_003.png", + "structural": { + "selector": "#note-label", + "frame_path": null, + "role": null, + "name": "Note", + "automation_id": null, + "window_name": null + }, + "region": [ + 400, + 236, + 160, + 64 + ], + "click_point": [ + 480, + 268 + ], + "ocr_text": null, + "context_text": null, + "structured_identity": null, + "identity_template": { + "schema_version": 1, + "salt": "c8887ea55d5a3781d3962e9dd6ef76d9", + "band_len": 0, + "tokens": [], + "concats": [], + "structured": "84fd8e01b2a61fc6", + "signal_hashes": { + "structured|exact|": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960" + }, + "param_token_indices": {}, + "rests_on_confusable_identifier": false + }, + "identifier_crop": null, + "identifier_region": null, + "landmarks": [ + { + "relation": "left_of", + "ocr_text": "Consult", + "distance_px": 279, + "dx_px": 274, + "dy_px": 54 + }, + { + "relation": "left_of", + "ocr_text": "JaneSample—MRNP1—DOB1980-01-01", + "distance_px": 319, + "dx_px": 270, + "dy_px": 170 + } + ], + "search_pad": 80 + }, + "text": null, + "param": null, + "secret": false, + "key": null, + "scroll_dx": null, + "scroll_dy": null, + "expect": [ + { + "kind": "region_stable", + "text": null, + "region": [ + 0, + 249, + 696, + 202 + ], + "phash": "ff3fd53f6a002a00", + "phash_tolerance": 16, + "timeout_s": 5.0, + "template": "templates/step_003_expect.png" + } + ], + "effects": [], + "api_binding": null, + "risk": "reversible", + "wait_until": null, + "guard": null, + "timeout_s": 10.0, + "identity_armed": true, + "identity_unarmed_reason": null, + "identifier_crop_missing_reason": "structured identity (DOM/UIA/AX) owns this step's identity; no identifier pixels persisted at rest — mark the identifier field/region at record time (--identifier) to also arm the pixel tier for remote-display replays" + }, + { + "id": "step_004", + "intent": "type ", + "action": "type", + "anchor": null, + "text": "Synthetic follow-up in two weeks", + "param": "note", + "secret": false, + "key": null, + "scroll_dx": null, + "scroll_dy": null, + "expect": [], + "effects": [], + "api_binding": null, + "risk": "reversible", + "wait_until": null, + "guard": null, + "timeout_s": 10.0, + "identity_armed": null, + "identity_unarmed_reason": null, + "identifier_crop_missing_reason": null + }, + { + "id": "step_005", + "intent": "click 'Save Encounter'", + "action": "click", + "anchor": { + "template": "templates/step_005.png", + "structural": { + "selector": "#save-encounter", + "frame_path": null, + "role": "button", + "name": "Save Encounter", + "automation_id": null, + "window_name": null + }, + "region": [ + 54, + 425, + 160, + 64 + ], + "click_point": [ + 134, + 457 + ], + "ocr_text": "Save Encounter", + "context_text": null, + "structured_identity": null, + "identity_template": { + "schema_version": 1, + "salt": "c8887ea55d5a3781d3962e9dd6ef76d9", + "band_len": 0, + "tokens": [], + "concats": [], + "structured": "84fd8e01b2a61fc6", + "signal_hashes": { + "structured|exact|": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,collapse_whitespace": "a96d2d91d99e56b48fe64448a9c4c81c3149044741ce8ecc50f53485f06a18f5", + "structured|normalized|unicode_nfkc,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace": "84fd8e01b2a61fc6f88d628a537f0d505b224e57a183b313bb3835ec9e0119ab", + "structured|normalized|unicode_nfkc,casefold,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,collapse_whitespace,strip_punctuation": "0c90cdae7be4d44b608e27c87798a6f135a8bbdb617b78bb6653cf800eff0e15", + "structured|normalized|casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960", + "structured|normalized|unicode_nfkc,casefold,collapse_whitespace,strip_punctuation": "c4b41bbaa931352a0585ea4400de10785f8fa138e2e0b713ec5c9b72c934d960" + }, + "param_token_indices": {}, + "rests_on_confusable_identifier": false + }, + "identifier_crop": null, + "identifier_region": null, + "landmarks": [ + { + "relation": "above", + "ocr_text": "Note", + "distance_px": 209, + "dx_px": 93, + "dy_px": 187 + }, + { + "relation": "above", + "ocr_text": "Triage", + "distance_px": 248, + "dx_px": 49, + "dy_px": 243 + } + ], + "search_pad": 80 + }, + "text": null, + "param": null, + "secret": false, + "key": null, + "scroll_dx": null, + "scroll_dy": null, + "expect": [ + { + "kind": "region_stable", + "text": null, + "region": [ + 0, + 228, + 696, + 223 + ], + "phash": "e0e0b83b1f87c7c2", + "phash_tolerance": 16, + "timeout_s": 5.0, + "template": "templates/step_005_expect.png" + }, + { + "kind": "text_present", + "text": "Encounters", + "region": null, + "phash": null, + "phash_tolerance": 8, + "timeout_s": 5.0, + "template": null + } + ], + "effects": [ + { + "kind": "record_written", + "match": { + "patient_id": { + "literal": "p1", + "param": null + }, + "type": { + "literal": "Triage", + "param": null + }, + "source": { + "literal": "replay", + "param": null + }, + "key": { + "literal": "mockmed-triage-p1-v1", + "param": null + } + }, + "field": null, + "value": null, + "expected_count": 1, + "idempotency_key": { + "literal": "mockmed-triage-p1-v1", + "param": null + }, + "key_field": "key", + "count_new_only": false, + "forbid_collateral_loss": true, + "risk": "irreversible", + "probe": "a record matching patient_id='p1', type='Triage', source='replay', key='mockmed-triage-p1-v1' exists exactly once (mined from the demonstration's system-of-record delta)", + "timeout_s": 5.0, + "needs_operator_confirmation": false, + "readback": null + }, + { + "kind": "field_equals", + "match": { + "patient_id": { + "literal": "p1", + "param": null + }, + "type": { + "literal": "Triage", + "param": null + }, + "source": { + "literal": "replay", + "param": null + }, + "key": { + "literal": "mockmed-triage-p1-v1", + "param": null + } + }, + "field": "note", + "value": { + "literal": "Synthetic follow-up in two weeks", + "param": null + }, + "expected_count": 1, + "idempotency_key": null, + "key_field": "key", + "count_new_only": false, + "forbid_collateral_loss": true, + "risk": "irreversible", + "probe": "field 'note' of the written record equals the demonstrated value (mined; the value is the recorded example — substitute the run's parameter if this field is parameterized)", + "timeout_s": 5.0, + "needs_operator_confirmation": false, + "readback": null + } + ], + "api_binding": null, + "risk": "irreversible", + "wait_until": null, + "guard": null, + "timeout_s": 10.0, + "identity_armed": true, + "identity_unarmed_reason": null, + "identifier_crop_missing_reason": "structured identity (DOM/UIA/AX) owns this step's identity; no identifier pixels persisted at rest — mark the identifier field/region at record time (--identifier) to also arm the pixel tier for remote-display replays" + } + ], + "interstitials": [], + "program": null, + "subflows": {}, + "data_sources": {}, + "qualification": { + "schema_version": "openadapt.qualification-project/v1", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "revision": 12, + "previous_revision_sha256": "bb4f26895f8d03914294e4ca03db90b852214834b03078a5c380028798a5f392", + "created_at": "2026-07-26T07:06:47.897989+00:00", + "updated_at": "2026-07-26T07:08:22.716689+00:00", + "environment": { + "target_kind": "web", + "application": "OpenAdapt MockMed synthetic reference", + "application_version": "sha256:1f4d59153fc6c797d626b27977fa6270ca8b2d9461b23171f9a2b2b571d2a0c1", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "required_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ] + }, + "minimum_effect_tier": 1, + "action_classifications": { + "step_000": { + "step_id": "step_000", + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true + }, + "step_001": { + "step_id": "step_001", + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true + }, + "step_002": { + "step_id": "step_002", + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true + }, + "step_003": { + "step_id": "step_003", + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true + }, + "step_004": { + "step_id": "step_004", + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true + }, + "step_005": { + "step_id": "step_005", + "classification": "irreversible", + "explanation": "compiler classified this as an irreversible system-of-record write", + "operator_confirmed": true + } + }, + "identity_policies": { + "step_005": { + "step_id": "step_005", + "enforcement": "canonical_ladder", + "signals": [], + "quorum": 0 + } + }, + "effect_policies": [ + { + "step_id": "step_005", + "effect_index": 0, + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "tier": 1 + }, + { + "step_id": "step_005", + "effect_index": 1, + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "tier": 1 + } + ], + "cases": [ + { + "id": "fault-ambiguity", + "kind": "ambiguity", + "description": "Deterministic ambiguity refusal case", + "input_ref": null, + "expected_outcome": "halted", + "required": true, + "results": [ + { + "case_id": "fault-ambiguity", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "runner_id": "openadapt-flow/public-demo-headless", + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "status": "passed", + "observed_outcome": "halted", + "evidence": [ + { + "kind": "run_report", + "sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e", + "relative_path": "artifacts/cases/fault-ambiguity/trial-01/run/report.json" + }, + { + "kind": "run_report", + "sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe", + "relative_path": "artifacts/cases/fault-ambiguity/trial-02/run/report.json" + }, + { + "kind": "run_report", + "sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5", + "relative_path": "artifacts/cases/fault-ambiguity/trial-03/run/report.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-ambiguity/trial-01/oracle.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-ambiguity/trial-02/oracle.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-ambiguity/trial-03/oracle.json" + } + ], + "detail_code": "fault-ambiguity.three-trial-contract", + "completed_at": "2026-07-26T07:07:09.351773+00:00", + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "3FxUdj1qDIf5M+v/u8dsoGhLqnAGTvlNwEKJtRNJAlbF0/nl7cG7/q4B+N8rdkbI+0UYyOMAJs1XBNze7QtJDA==" + } + ] + }, + { + "id": "fault-wrong-identity", + "kind": "wrong_identity", + "description": "Deterministic wrong identity refusal case", + "input_ref": null, + "expected_outcome": "halted", + "required": true, + "results": [ + { + "case_id": "fault-wrong-identity", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "runner_id": "openadapt-flow/public-demo-headless", + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "status": "passed", + "observed_outcome": "halted", + "evidence": [ + { + "kind": "run_report", + "sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-01/run/report.json" + }, + { + "kind": "run_report", + "sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-02/run/report.json" + }, + { + "kind": "run_report", + "sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-03/run/report.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-01/oracle.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-02/oracle.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-03/oracle.json" + } + ], + "detail_code": "fault-wrong-identity.three-trial-contract", + "completed_at": "2026-07-26T07:07:13.536333+00:00", + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "8fGOaHpgsPsyJCCjB2DYjAGfOcMKq/JAq4bfC98fqqZ672iDXprpUxDaQbv+x5kGK/9AGTpX33oUN+viE815BA==" + } + ] + }, + { + "id": "fault-stale-identity", + "kind": "stale_identity", + "description": "Deterministic stale identity refusal case", + "input_ref": null, + "expected_outcome": "halted", + "required": true, + "results": [ + { + "case_id": "fault-stale-identity", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "runner_id": "openadapt-flow/public-demo-headless", + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "status": "passed", + "observed_outcome": "halted", + "evidence": [ + { + "kind": "run_report", + "sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e", + "relative_path": "artifacts/cases/fault-stale-identity/trial-01/run/report.json" + }, + { + "kind": "run_report", + "sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047", + "relative_path": "artifacts/cases/fault-stale-identity/trial-02/run/report.json" + }, + { + "kind": "run_report", + "sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8", + "relative_path": "artifacts/cases/fault-stale-identity/trial-03/run/report.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-stale-identity/trial-01/oracle.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-stale-identity/trial-02/oracle.json" + }, + { + "kind": "effect", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f", + "relative_path": "artifacts/cases/fault-stale-identity/trial-03/oracle.json" + } + ], + "detail_code": "fault-stale-identity.three-trial-contract", + "completed_at": "2026-07-26T07:07:17.886852+00:00", + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "5PiFmo+xxxXZEmqc2pTfSqyJ3mN0cQ/RFZwJ+0eKcF0rZq4VrSlUbdYkZvsBvFg6hH618Tr8XN4UEJ81JNpCBA==" + } + ] + }, + { + "id": "fault-weak-effect", + "kind": "weak_effect", + "description": "Deterministic weak effect refusal case", + "input_ref": null, + "expected_outcome": "halted", + "required": true, + "results": [ + { + "case_id": "fault-weak-effect", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "runner_id": "openadapt-flow/public-demo-headless", + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "status": "passed", + "observed_outcome": "halted", + "evidence": [ + { + "kind": "run_report", + "sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa", + "relative_path": "artifacts/cases/fault-weak-effect/trial-01/run/report.json" + }, + { + "kind": "run_report", + "sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f", + "relative_path": "artifacts/cases/fault-weak-effect/trial-02/run/report.json" + }, + { + "kind": "run_report", + "sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee", + "relative_path": "artifacts/cases/fault-weak-effect/trial-03/run/report.json" + }, + { + "kind": "effect", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4", + "relative_path": "artifacts/cases/fault-weak-effect/trial-01/oracle.json" + }, + { + "kind": "effect", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4", + "relative_path": "artifacts/cases/fault-weak-effect/trial-02/oracle.json" + }, + { + "kind": "effect", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4", + "relative_path": "artifacts/cases/fault-weak-effect/trial-03/oracle.json" + } + ], + "detail_code": "fault-weak-effect.three-trial-contract", + "completed_at": "2026-07-26T07:07:50.021545+00:00", + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "9IcpvCPGR1iSQhJ4T/yd2b6ZkAixxK6Nh7FaHMJyGCE9hruAgKNA4oV+ipjqs/7Xi9EPwDARE93afyrOCjM7DQ==" + } + ] + }, + { + "id": "fault-missing-effect", + "kind": "missing_effect", + "description": "Deterministic missing effect refusal case", + "input_ref": null, + "expected_outcome": "halted", + "required": true, + "results": [ + { + "case_id": "fault-missing-effect", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "runner_id": "openadapt-flow/public-demo-headless", + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "status": "passed", + "observed_outcome": "halted", + "evidence": [ + { + "kind": "run_report", + "sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff", + "relative_path": "artifacts/cases/fault-missing-effect/trial-01/run/report.json" + }, + { + "kind": "run_report", + "sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626", + "relative_path": "artifacts/cases/fault-missing-effect/trial-02/run/report.json" + }, + { + "kind": "run_report", + "sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325", + "relative_path": "artifacts/cases/fault-missing-effect/trial-03/run/report.json" + }, + { + "kind": "effect", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad", + "relative_path": "artifacts/cases/fault-missing-effect/trial-01/oracle.json" + }, + { + "kind": "effect", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad", + "relative_path": "artifacts/cases/fault-missing-effect/trial-02/oracle.json" + }, + { + "kind": "effect", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad", + "relative_path": "artifacts/cases/fault-missing-effect/trial-03/oracle.json" + } + ], + "detail_code": "fault-missing-effect.three-trial-contract", + "completed_at": "2026-07-26T07:08:22.706051+00:00", + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "tXrlXALnWjNaOmiTvcXg+vYXhfAMYTwv61D9izyve9ou7rTNvXoDaNANxfziO+urVngZZHx+XDBO5dqSeTVqBQ==" + } + ] + }, + { + "id": "representative", + "kind": "representative", + "description": "Recorded workflow under its qualified application boundary", + "input_ref": null, + "expected_outcome": "verified", + "required": true, + "results": [ + { + "case_id": "representative", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "runtime_version": "1.23.0", + "runner_id": "openadapt-flow/public-demo-headless", + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "status": "passed", + "observed_outcome": "verified", + "evidence": [ + { + "kind": "run_report", + "sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf", + "relative_path": "artifacts/cases/representative/trial-01/run/report.json" + }, + { + "kind": "run_report", + "sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7", + "relative_path": "artifacts/cases/representative/trial-02/run/report.json" + }, + { + "kind": "run_report", + "sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c", + "relative_path": "artifacts/cases/representative/trial-03/run/report.json" + }, + { + "kind": "effect", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987", + "relative_path": "artifacts/cases/representative/trial-01/oracle.json" + }, + { + "kind": "effect", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987", + "relative_path": "artifacts/cases/representative/trial-02/oracle.json" + }, + { + "kind": "effect", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987", + "relative_path": "artifacts/cases/representative/trial-03/oracle.json" + } + ], + "detail_code": "representative.three-trial-contract", + "completed_at": "2026-07-26T07:07:04.683125+00:00", + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "4soLZkZwxanR4v+IOFpB+j4BYrACmiRw65IytqbXfrP90ep4ckbpH0lyuqxd6W0eR7O//V8bWyob48ai7q6WCw==" + } + ] + } + ], + "exclusions": [], + "requalification_conditions": [], + "trusted_runner_keys": { + "public-demo-headless-runner": "dmz7CT1Jv+6Gl7W3yJZs+65RzGz5ysq4bZ27Rr3DW58=" + }, + "last_certification": { + "project_revision": 12, + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "policy_name": "clinical-write", + "passed": true, + "report_sha256": "31b3f312109a6e9e8dd2cbffd318a4900433965434128ff6e869878b5eaf17f3", + "certified_at": "2026-07-26T07:08:22.726699+00:00" + } + }, + "manifest": { + "schema_version": 2, + "content_digest": "c3f3e82732db5dd186289f71ce9f24c13452fa07fddcdfbe8d5d61e4b5281542", + "file_hashes": { + "templates/step_000.png": "46a75b5d63ceaad4bee942ccf2a6ca3d2b4f6327509df7eff2cc7ddb2c9fd389", + "templates/step_000_expect.png": "337e403fec476cc955bcf5f1d96902119d9c2fadc03e201c0c2fbc2475d03646", + "templates/step_001.png": "9d17fc905b1902add82cad885c72fe446a23e0334fc4db58592d2369e85f26a5", + "templates/step_001_expect.png": "ccbbb335c8160188198df18beb48bd88082b7bb1e5c1cd987d6766afb62c0773", + "templates/step_002.png": "e6a0e0718b00c26280e32928b744217d00a7e010ab9825da27724e2debc9b805", + "templates/step_002_expect.png": "f66608f19f3acf0ba8d86a39ecdd04781eb320787885039ab1eefee3835c83de", + "templates/step_003.png": "2cb01de3e45c7c6cd6526f1b6f9c1a4f86bee1a5e4f8e3f6fbf7150470cf5f2c", + "templates/step_003_expect.png": "68cd40d6bd0abdf81beb40dd4202bac784a4b55492f803cdd5fb1e7ab8f76941", + "templates/step_005.png": "5d8163520ba8355f44ffe0cd06a26be6bfe5d6660bcff1395dc82d4da3aa0ac1", + "templates/step_005_expect.png": "0919dca8fe883ad52eae6359f9da3494cb57c68e006ea4ba314d61e15787ea47" + }, + "provenance": { + "compiler_version": "1.23.0", + "source_recording_sha256": null, + "compiler_config_sha256": "479f143ba6970af144553f82f66990463129ee6606852260478c9c2a79b7f91d", + "created_at": "2026-07-26T07:06:47.886463+00:00", + "policy_name": "clinical-write", + "certified": true, + "certification_status": "certified", + "certified_at": "2026-07-26T07:08:22.726707+00:00", + "expires_at": null, + "certification_invalidated_at": null, + "certification_invalidation_reason": null + }, + "encrypted": false + } +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.py b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.py new file mode 100644 index 00000000..a3d8aacf --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/bundle/workflow.py @@ -0,0 +1,52 @@ +"""Generated by openadapt-flow. Human-readable rendering of +workflow 'mockmed-triage' — for code review only; the replayer +executes workflow.json, not this file.""" + +WORKFLOW_NAME = 'mockmed-triage' +RECORDING_ID = '3290705d23254d978c7a335776e407ad' +PARAMS = {'note': 'Synthetic follow-up in two weeks'} # param -> example/default value + + +def run(flow, params=PARAMS): + # step_000: click 'Open' [reversible] + # landmark: 'Action' (above, 51px) + # landmark: 'Open' (below, 58px) + # identity: armed via PHI-free salted-hash template (5 band tokens, structured); no patient identifier stored + flow.click(template='templates/step_000.png', click_point=(775, 186), region=(695, 154, 160, 64), ocr_text='Open') + # expect region_stable region=(0, 43, 968, 318) phash='f8e083ffbc08383c' (tol 16) + # expect text_present text='JaneSample—MRNP1—DOB1980-01-01' + + # step_001: click 'New Encounter' [reversible] + # landmark: 'Encounters' (below, 61px) + # landmark: 'No encountersyet.' (below, 85px) + # identity: armed via PHI-free salted-hash template (0 band tokens, structured); no patient identifier stored + flow.click(template='templates/step_001.png', click_point=(114, 159), region=(34, 127, 160, 64), ocr_text='New Encounter') + # expect region_stable region=(0, 101, 696, 350) phash='fae0c01e950fc78e' (tol 16) + # expect text_present text='EncounterType' + + # step_002: click 'Triage' [reversible] + # landmark: 'Note' (below, 70px) + # landmark: 'NewEncounter' (above, 77px) + # identity: armed via PHI-free salted-hash template (0 band tokens, structured); no patient identifier stored + flow.click(template='templates/step_002.png', click_point=(85, 214), region=(5, 182, 160, 64), ocr_text='Triage') + # expect region_stable region=(0, 163, 177, 102) phash='88c2f2295d2da73d' (tol 16) + + # step_003: click at (480, 268) [reversible] + # landmark: 'Consult' (left_of, 279px) + # landmark: 'JaneSample—MRNP1—DOB1980-01-01' (left_of, 319px) + # identity: armed via PHI-free salted-hash template (0 band tokens, structured); no patient identifier stored + flow.click(template='templates/step_003.png', click_point=(480, 268), region=(400, 236, 160, 64)) + # expect region_stable region=(0, 249, 696, 202) phash='ff3fd53f6a002a00' (tol 16) + + # step_004: type [reversible] + flow.type_text(params['note']) + + # step_005: click 'Save Encounter' [irreversible] + # landmark: 'Note' (above, 209px) + # landmark: 'Triage' (above, 248px) + # identity: armed via PHI-free salted-hash template (0 band tokens, structured); no patient identifier stored + flow.click(template='templates/step_005.png', click_point=(134, 457), region=(54, 425, 160, 64), ocr_text='Save Encounter') + # expect region_stable region=(0, 228, 696, 223) phash='e0e0b83b1f87c7c2' (tol 16) + # expect text_present text='Encounters' + # effect record_written match={'patient_id': 'p1', 'type': 'Triage', 'source': 'replay', 'key': 'mockmed-triage-p1-v1'} count=1 idempotency_key='mockmed-triage-p1-v1' [irreversible] + # effect field_equals match={'patient_id': 'p1', 'type': 'Triage', 'source': 'replay', 'key': 'mockmed-triage-p1-v1'} field='note' value='Synthetic follow-up in two weeks' [irreversible] diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/events.jsonl new file mode 100644 index 00000000..dc95ef6a --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 152.94908406212926, "error": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 \u2014 no action was admitted", "exception_handled": false, "failure_category": "safety_halt", "heal": null, "identity": null, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": null, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/halt.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/halt.webm new file mode 100644 index 00000000..65fdc46e Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/halt.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/outcome.json new file mode 100644 index 00000000..47796497 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/outcome.json @@ -0,0 +1,49 @@ +{ + "browser_request_count": 3, + "case_id": "fault-ambiguity", + "duration_ms": 158.78204093314707, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/REPORT.md new file mode 100644 index 00000000..db8c2e8f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:05.070942+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `83809581eeb247aaae7bf7ca8a6e9e00` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | — | — | — | 153 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted + +**Rung** — (keyboard / wait step, no anchor) · **Gates** none on this step · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 159 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/checkpoints/_manifest.json new file mode 100644 index 00000000..6d6ce0a1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "83809581eeb247aaae7bf7ca8a6e9e00", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "83809581eeb247aaae7bf7ca8a6e9e00", + "created_at": "2026-07-26T07:07:05.070236+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:05.084240+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/pending_escalation.json new file mode 100644 index 00000000..61ebf2e1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "disambiguation", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "detail": [], + "proposed_options": [ + "Choose the intended target/entity for this step, then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:05.241351+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/report.json new file mode 100644 index 00000000..d72e0754 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/report.json @@ -0,0 +1,129 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:05.070942+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&drift=ambiguous&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "83809581eeb247aaae7bf7ca8a6e9e00", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:05.070236+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "safety_halt", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 152.94908406212926 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 158.78204093314707, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_after.png new file mode 100644 index 00000000..d8c492a7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_before.png new file mode 100644 index 00000000..d8c492a7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/events.jsonl new file mode 100644 index 00000000..9dc64b91 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 148.5437920782715, "error": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 \u2014 no action was admitted", "exception_handled": false, "failure_category": "safety_halt", "heal": null, "identity": null, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": null, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/outcome.json new file mode 100644 index 00000000..b8c3fbc5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/outcome.json @@ -0,0 +1,49 @@ +{ + "browser_request_count": 3, + "case_id": "fault-ambiguity", + "duration_ms": 154.73504201509058, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/REPORT.md new file mode 100644 index 00000000..6ba772a2 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:06.941734+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `eced022219e84378abdf26310f4f3cfa` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | — | — | — | 149 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted + +**Rung** — (keyboard / wait step, no anchor) · **Gates** none on this step · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 155 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/checkpoints/_manifest.json new file mode 100644 index 00000000..9942fffa --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "eced022219e84378abdf26310f4f3cfa", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "eced022219e84378abdf26310f4f3cfa", + "created_at": "2026-07-26T07:07:06.941057+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:06.943755+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/pending_escalation.json new file mode 100644 index 00000000..b0715bc9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "disambiguation", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "detail": [], + "proposed_options": [ + "Choose the intended target/entity for this step, then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:07.096765+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/report.json new file mode 100644 index 00000000..a40be2ef --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/report.json @@ -0,0 +1,129 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:06.941734+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&drift=ambiguous&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "eced022219e84378abdf26310f4f3cfa", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:06.941057+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "safety_halt", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 148.5437920782715 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 154.73504201509058, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_after.png new file mode 100644 index 00000000..d8c492a7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_before.png new file mode 100644 index 00000000..d8c492a7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/events.jsonl new file mode 100644 index 00000000..e9d0c286 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 174.98800018802285, "error": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 \u2014 no action was admitted", "exception_handled": false, "failure_category": "safety_halt", "heal": null, "identity": null, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": null, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/outcome.json new file mode 100644 index 00000000..663ad0be --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/outcome.json @@ -0,0 +1,49 @@ +{ + "browser_request_count": 3, + "case_id": "fault-ambiguity", + "duration_ms": 180.2768751513213, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/REPORT.md new file mode 100644 index 00000000..9e593876 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:08.328765+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `85e5c6858e6540b9bf86e269f4a0a2f8` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | — | — | — | 175 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted + +**Rung** — (keyboard / wait step, no anchor) · **Gates** none on this step · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 180 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/checkpoints/_manifest.json new file mode 100644 index 00000000..c864ba24 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "85e5c6858e6540b9bf86e269f4a0a2f8", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "85e5c6858e6540b9bf86e269f4a0a2f8", + "created_at": "2026-07-26T07:07:08.326749+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:08.333779+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/pending_escalation.json new file mode 100644 index 00000000..a0f714d7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "disambiguation", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "detail": [], + "proposed_options": [ + "Choose the intended target/entity for this step, then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:08.512754+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/report.json new file mode 100644 index 00000000..80608735 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/report.json @@ -0,0 +1,129 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:08.328765+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&drift=ambiguous&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "85e5c6858e6540b9bf86e269f4a0a2f8", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:08.326749+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "safety_halt", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 174.98800018802285 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 180.2768751513213, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_after.png new file mode 100644 index 00000000..d8c492a7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_before.png new file mode 100644 index 00000000..d8c492a7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/events.jsonl new file mode 100644 index 00000000..36be3305 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:50.773523+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-821686ca6324449aaff499015d79bd8f", "status": "delivered", "target_fingerprint": "362ef9aedad6caaa8c671e8284cb834375296d2f6fa582d47d9178f90263fd85"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 984.440749976784, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 40.292583871632814, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "362ef9aedad6caaa8c671e8284cb834375296d2f6fa582d47d9178f90263fd85"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:51.694179+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-ee6e161960e241c396d47f062678bd08", "status": "delivered", "target_fingerprint": "fd86ee2bf88e429633c6af84556e583ca462f6e1ad0c2d1b6ff21d279d8976e4"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 956.5690411254764, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 37.33066702261567, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "fd86ee2bf88e429633c6af84556e583ca462f6e1ad0c2d1b6ff21d279d8976e4"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:52.669037+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-28964e23f1e848c4a2ceaf7e28cd681c", "status": "delivered", "target_fingerprint": "15b3da3fa39ecc95627eb62998301ddee3d8b05f95f04d78b64b2da6544b5a3a"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 528.2623749226332, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 40.052459109574556, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "15b3da3fa39ecc95627eb62998301ddee3d8b05f95f04d78b64b2da6544b5a3a"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:53.160783+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-bdb8b7507168436ea35182eb7f5f694e", "status": "delivered", "target_fingerprint": "a5828149262543fc3c9d39c1c0a576bc96a5f70f89d3f1062ec42677ea5fb1c1"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 491.3847919087857, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 33.03429204970598, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "a5828149262543fc3c9d39c1c0a576bc96a5f70f89d3f1062ec42677ea5fb1c1"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 576.1481251101941, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:54.297801+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-fd291d76f54f4beaaf26c53a1ea61c05", "status": "delivered", "target_fingerprint": "9fe9e1de025e09a06b77f16150c8725455e81659e02e72997c91d9935b1535a9"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "refuted", "initial_verdict": "refuted", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: REFUTED \u2192 ESCALATED \u2014 no compensator available for an irreversible refuted effect -- durably halt and escalate"], "effect_verified": false, "elapsed_ms": 6087.340290891007, "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) \u2014 [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate \u2014 run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 40.33570806495845, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "9fe9e1de025e09a06b77f16150c8725455e81659e02e72997c91d9935b1535a9"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/halt.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/halt.webm new file mode 100644 index 00000000..6e59f83b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/halt.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/oracle.json new file mode 100644 index 00000000..3f352b36 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "rejected_write", + "oracle_kind": "rejected_write_detected", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 1 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/outcome.json new file mode 100644 index 00000000..bae91bfa --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/outcome.json @@ -0,0 +1,45 @@ +{ + "browser_request_count": 4, + "case_id": "fault-missing-effect", + "duration_ms": 9635.272833984345, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/REPORT.md new file mode 100644 index 00000000..109dbf58 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/REPORT.md @@ -0,0 +1,113 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:50.374242+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 0/2 +- **Evidence classes:** `authorization`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 5/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `a4c1dd116c8e4f42910e667f06ad9214` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 0 confirmed, 1 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 984 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 957 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 528 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 491 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 576 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✗ | 6087 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step, halted) + +> ❌ **Error:** System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 4 | ████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 9635 ms | +| Steps ok | 5/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/_manifest.json new file mode 100644 index 00000000..eef19d03 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "a4c1dd116c8e4f42910e667f06ad9214", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "created_at": "2026-07-26T07:07:50.373577+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:50.376226+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..7c3bb02c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 40.292583871632814, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "362ef9aedad6caaa8c671e8284cb834375296d2f6fa582d47d9178f90263fd85", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:51.361211+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..52a857a2 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 37.33066702261567, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "fd86ee2bf88e429633c6af84556e583ca462f6e1ad0c2d1b6ff21d279d8976e4", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:52.318215+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..40a812ee --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 40.052459109574556, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "15b3da3fa39ecc95627eb62998301ddee3d8b05f95f04d78b64b2da6544b5a3a", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:52.847006+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..d5b50180 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 33.03429204970598, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "a5828149262543fc3c9d39c1c0a576bc96a5f70f89d3f1062ec42677ea5fb1c1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:53.338924+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..5be62756 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:53.915502+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/pending_escalation.json new file mode 100644 index 00000000..a58dd51c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/pending_escalation.json @@ -0,0 +1,31 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "category": "effect_escalated", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "detail": [ + "[rest] record_written: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "proposed_options": [ + "Inspect the system of record and correct it (the automatic compensation could not safely undo the fault)", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 5, + "resume_from_step_id": "step_004", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:08:00.009874+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/report.json new file mode 100644 index 00000000..6911dc73 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/report.json @@ -0,0 +1,518 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:50.374242+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 0 + }, + "evidence_classes": [ + "authorization", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=optimistic&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "a4c1dd116c8e4f42910e667f06ad9214", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:50.373577+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 40.292583871632814, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "362ef9aedad6caaa8c671e8284cb834375296d2f6fa582d47d9178f90263fd85", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-821686ca6324449aaff499015d79bd8f", + "operation": "dom_click", + "native": false, + "target_fingerprint": "362ef9aedad6caaa8c671e8284cb834375296d2f6fa582d47d9178f90263fd85", + "delivered_at": "2026-07-26T07:07:50.773523+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 984.440749976784 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 37.33066702261567, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "fd86ee2bf88e429633c6af84556e583ca462f6e1ad0c2d1b6ff21d279d8976e4", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-ee6e161960e241c396d47f062678bd08", + "operation": "dom_click", + "native": false, + "target_fingerprint": "fd86ee2bf88e429633c6af84556e583ca462f6e1ad0c2d1b6ff21d279d8976e4", + "delivered_at": "2026-07-26T07:07:51.694179+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 956.5690411254764 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 40.052459109574556, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "15b3da3fa39ecc95627eb62998301ddee3d8b05f95f04d78b64b2da6544b5a3a", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-28964e23f1e848c4a2ceaf7e28cd681c", + "operation": "dom_click", + "native": false, + "target_fingerprint": "15b3da3fa39ecc95627eb62998301ddee3d8b05f95f04d78b64b2da6544b5a3a", + "delivered_at": "2026-07-26T07:07:52.669037+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 528.2623749226332 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 33.03429204970598, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "a5828149262543fc3c9d39c1c0a576bc96a5f70f89d3f1062ec42677ea5fb1c1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-bdb8b7507168436ea35182eb7f5f694e", + "operation": "dom_click", + "native": false, + "target_fingerprint": "a5828149262543fc3c9d39c1c0a576bc96a5f70f89d3f1062ec42677ea5fb1c1", + "delivered_at": "2026-07-26T07:07:53.160783+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 491.3847919087857 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 576.1481251101941 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 40.33570806495845, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "9fe9e1de025e09a06b77f16150c8725455e81659e02e72997c91d9935b1535a9", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": false, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [ + "[rest] record_written: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "refuted", + "final_verdict": "refuted", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": "governed_refusal", + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-fd291d76f54f4beaaf26c53a1ea61c05", + "operation": "dom_click", + "native": false, + "target_fingerprint": "9fe9e1de025e09a06b77f16150c8725455e81659e02e72997c91d9935b1535a9", + "delivered_at": "2026-07-26T07:07:54.297801+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 6087.340290891007 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_005", + "intent": "click 'Save Encounter'", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ] + }, + "rung_counts": { + "structural": 4 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 9635.272833984345, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_before.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/events.jsonl new file mode 100644 index 00000000..1df7148d --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:01.749639+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-36372955d7dd43b6bc403815c37152cd", "status": "delivered", "target_fingerprint": "fb235abacd578638389bec9324bccb8fb8e72dba99814ae0407d3c316d5222a6"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 950.2100001554936, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 32.478583976626396, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "fb235abacd578638389bec9324bccb8fb8e72dba99814ae0407d3c316d5222a6"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:02.644272+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-56dce832496f4031a08c9258f2bb406e", "status": "delivered", "target_fingerprint": "cf79c2426590e101038c5dcc362aeb7d868509c3ab48f5d8f7c9a02bccdf0df0"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 992.173541802913, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 36.10441600903869, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "cf79c2426590e101038c5dcc362aeb7d868509c3ab48f5d8f7c9a02bccdf0df0"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:03.693189+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-d3c5aa99d7d64565a3a14c423a3553cb", "status": "delivered", "target_fingerprint": "9e0bf616c22b45e369dd0ee348d77d3acc666f4fb69b70d94924e74c41285690"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 547.7649171371013, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 38.3332499768585, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "9e0bf616c22b45e369dd0ee348d77d3acc666f4fb69b70d94924e74c41285690"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:04.284691+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-b4b21007e0e54bb79a2b93885db156e9", "status": "delivered", "target_fingerprint": "f4c7d6f2dd59b304ecf5bbd0844708c2652044799ee49de9f119325cb7727cd8"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 598.3362500555813, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 25.51575005054474, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "f4c7d6f2dd59b304ecf5bbd0844708c2652044799ee49de9f119325cb7727cd8"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 549.9956659041345, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:05.388729+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-0c25a0e4872d4ac6ac57eb580a0b080b", "status": "delivered", "target_fingerprint": "fb8b3289588c17999c4ee5354ccf40e5acb9f4929c7c084468eb394beed30a59"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "refuted", "initial_verdict": "refuted", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: REFUTED \u2192 ESCALATED \u2014 no compensator available for an irreversible refuted effect -- durably halt and escalate"], "effect_verified": false, "elapsed_ms": 6054.953875020146, "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) \u2014 [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate \u2014 run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 41.47204104810953, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "fb8b3289588c17999c4ee5354ccf40e5acb9f4929c7c084468eb394beed30a59"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/oracle.json new file mode 100644 index 00000000..3f352b36 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "rejected_write", + "oracle_kind": "rejected_write_detected", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 1 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/outcome.json new file mode 100644 index 00000000..604cc901 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/outcome.json @@ -0,0 +1,45 @@ +{ + "browser_request_count": 4, + "case_id": "fault-missing-effect", + "duration_ms": 9710.82350006327, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/REPORT.md new file mode 100644 index 00000000..17739097 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/REPORT.md @@ -0,0 +1,113 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:08:01.374209+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 0/2 +- **Evidence classes:** `authorization`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 5/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `4631f6f7a7a84189a4e926f94b4a995a` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 0 confirmed, 1 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 950 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 992 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 548 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 598 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 550 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✗ | 6055 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step, halted) + +> ❌ **Error:** System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 4 | ████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 9711 ms | +| Steps ok | 5/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/_manifest.json new file mode 100644 index 00000000..98404eb3 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "4631f6f7a7a84189a4e926f94b4a995a", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "created_at": "2026-07-26T07:08:01.372476+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:08:01.376391+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..0dadf1f5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 32.478583976626396, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "fb235abacd578638389bec9324bccb8fb8e72dba99814ae0407d3c316d5222a6", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:02.327110+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..2e2190f5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 36.10441600903869, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "cf79c2426590e101038c5dcc362aeb7d868509c3ab48f5d8f7c9a02bccdf0df0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:03.319709+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..b9b4a81c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 38.3332499768585, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "9e0bf616c22b45e369dd0ee348d77d3acc666f4fb69b70d94924e74c41285690", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:03.867891+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..e816b134 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 25.51575005054474, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "f4c7d6f2dd59b304ecf5bbd0844708c2652044799ee49de9f119325cb7727cd8", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:04.466686+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..50508c05 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:05.017150+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/pending_escalation.json new file mode 100644 index 00000000..5685c0e1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/pending_escalation.json @@ -0,0 +1,31 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "category": "effect_escalated", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "detail": [ + "[rest] record_written: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "proposed_options": [ + "Inspect the system of record and correct it (the automatic compensation could not safely undo the fault)", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 5, + "resume_from_step_id": "step_004", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:08:11.085637+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/report.json new file mode 100644 index 00000000..6bf4cf38 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/report.json @@ -0,0 +1,518 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:08:01.374209+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 0 + }, + "evidence_classes": [ + "authorization", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=optimistic&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "4631f6f7a7a84189a4e926f94b4a995a", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:08:01.372476+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 32.478583976626396, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "fb235abacd578638389bec9324bccb8fb8e72dba99814ae0407d3c316d5222a6", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-36372955d7dd43b6bc403815c37152cd", + "operation": "dom_click", + "native": false, + "target_fingerprint": "fb235abacd578638389bec9324bccb8fb8e72dba99814ae0407d3c316d5222a6", + "delivered_at": "2026-07-26T07:08:01.749639+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 950.2100001554936 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 36.10441600903869, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "cf79c2426590e101038c5dcc362aeb7d868509c3ab48f5d8f7c9a02bccdf0df0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-56dce832496f4031a08c9258f2bb406e", + "operation": "dom_click", + "native": false, + "target_fingerprint": "cf79c2426590e101038c5dcc362aeb7d868509c3ab48f5d8f7c9a02bccdf0df0", + "delivered_at": "2026-07-26T07:08:02.644272+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 992.173541802913 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 38.3332499768585, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "9e0bf616c22b45e369dd0ee348d77d3acc666f4fb69b70d94924e74c41285690", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-d3c5aa99d7d64565a3a14c423a3553cb", + "operation": "dom_click", + "native": false, + "target_fingerprint": "9e0bf616c22b45e369dd0ee348d77d3acc666f4fb69b70d94924e74c41285690", + "delivered_at": "2026-07-26T07:08:03.693189+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 547.7649171371013 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 25.51575005054474, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "f4c7d6f2dd59b304ecf5bbd0844708c2652044799ee49de9f119325cb7727cd8", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-b4b21007e0e54bb79a2b93885db156e9", + "operation": "dom_click", + "native": false, + "target_fingerprint": "f4c7d6f2dd59b304ecf5bbd0844708c2652044799ee49de9f119325cb7727cd8", + "delivered_at": "2026-07-26T07:08:04.284691+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 598.3362500555813 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 549.9956659041345 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 41.47204104810953, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "fb8b3289588c17999c4ee5354ccf40e5acb9f4929c7c084468eb394beed30a59", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": false, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [ + "[rest] record_written: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "refuted", + "final_verdict": "refuted", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": "governed_refusal", + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-0c25a0e4872d4ac6ac57eb580a0b080b", + "operation": "dom_click", + "native": false, + "target_fingerprint": "fb8b3289588c17999c4ee5354ccf40e5acb9f4929c7c084468eb394beed30a59", + "delivered_at": "2026-07-26T07:08:05.388729+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 6054.953875020146 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_005", + "intent": "click 'Save Encounter'", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ] + }, + "rung_counts": { + "structural": 4 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 9710.82350006327, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_before.png new file mode 100644 index 00000000..437a4e28 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_before.png new file mode 100644 index 00000000..b34f57d7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_before.png new file mode 100644 index 00000000..44530e81 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/events.jsonl new file mode 100644 index 00000000..c746a219 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:12.536183+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-b2e1d854c89c48e88841e9af2dde043c", "status": "delivered", "target_fingerprint": "999102ecbec403eebe7d822985baf2ac0be06eedcd4496b5e55241aa8190265c"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 963.0870840046555, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 34.02324998751283, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "999102ecbec403eebe7d822985baf2ac0be06eedcd4496b5e55241aa8190265c"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:13.468117+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-9ac32d58b567470abeaaf4878a89af4d", "status": "delivered", "target_fingerprint": "a81f6f2a1fc7ad1980170271541f9f16a1dced43dd71adf12c7c688d6f3437b9"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 1109.6672920975834, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 35.284209065139294, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "a81f6f2a1fc7ad1980170271541f9f16a1dced43dd71adf12c7c688d6f3437b9"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:14.568216+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-68875cfd63434d61bab420aa6cae1de8", "status": "delivered", "target_fingerprint": "1fc5b7fad4faf089a1678e207b558f224178431741405c55c6623693c6b72fa6"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 533.6915410589427, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 37.34649997204542, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "1fc5b7fad4faf089a1678e207b558f224178431741405c55c6623693c6b72fa6"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:15.103070+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-5f4b92f606014b4f9c9fb8b8529865da", "status": "delivered", "target_fingerprint": "7b557cee5c68b46a97be50abf4beac6590b3d0765fca46aae085876b72988aff"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 542.9748331662267, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 41.29291605204344, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "7b557cee5c68b46a97be50abf4beac6590b3d0765fca46aae085876b72988aff"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 545.8195831160992, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:08:16.211611+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-91acb5295ec54021bc657e06b1657bd3", "status": "delivered", "target_fingerprint": "9e0f04248c738b1e4a623f4a89fbeedb9b888c5c3266ba7d96f1725201452054"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "refuted", "initial_verdict": "refuted", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: REFUTED \u2192 ESCALATED \u2014 no compensator available for an irreversible refuted effect -- durably halt and escalate"], "effect_verified": false, "elapsed_ms": 5990.614417009056, "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) \u2014 [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate \u2014 run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 36.404249956831336, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "9e0f04248c738b1e4a623f4a89fbeedb9b888c5c3266ba7d96f1725201452054"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/oracle.json new file mode 100644 index 00000000..3f352b36 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "rejected_write", + "oracle_kind": "rejected_write_detected", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 1 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/outcome.json new file mode 100644 index 00000000..a039efa7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/outcome.json @@ -0,0 +1,45 @@ +{ + "browser_request_count": 4, + "case_id": "fault-missing-effect", + "duration_ms": 9697.530041914433, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/REPORT.md new file mode 100644 index 00000000..32dcc104 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/REPORT.md @@ -0,0 +1,113 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:08:12.133946+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 0/2 +- **Evidence classes:** `authorization`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 5/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `df449cd7919c4675aadb955ffe6c92a5` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 0 confirmed, 1 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 963 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 1110 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 534 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 543 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 546 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✗ | 5991 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step, halted) + +> ❌ **Error:** System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 4 | ████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 9698 ms | +| Steps ok | 5/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/_manifest.json new file mode 100644 index 00000000..3936b047 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "df449cd7919c4675aadb955ffe6c92a5", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "created_at": "2026-07-26T07:08:12.133197+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:08:12.136594+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..3e999c84 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 34.02324998751283, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "999102ecbec403eebe7d822985baf2ac0be06eedcd4496b5e55241aa8190265c", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:13.100308+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..1575ebe4 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 35.284209065139294, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "a81f6f2a1fc7ad1980170271541f9f16a1dced43dd71adf12c7c688d6f3437b9", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:14.210421+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..86dfea99 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 37.34649997204542, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "1fc5b7fad4faf089a1678e207b558f224178431741405c55c6623693c6b72fa6", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:14.744528+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..704d3eb2 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 41.29291605204344, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "7b557cee5c68b46a97be50abf4beac6590b3d0765fca46aae085876b72988aff", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:15.287967+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..891ea53b --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:08:15.834227+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/pending_escalation.json new file mode 100644 index 00000000..80d008b4 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/pending_escalation.json @@ -0,0 +1,31 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "category": "effect_escalated", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "detail": [ + "[rest] record_written: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "proposed_options": [ + "Inspect the system of record and correct it (the automatic compensation could not safely undo the fault)", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 5, + "resume_from_step_id": "step_004", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:08:21.832587+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/report.json new file mode 100644 index 00000000..dffeb5df --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/report.json @@ -0,0 +1,518 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:08:12.133946+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 0 + }, + "evidence_classes": [ + "authorization", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=optimistic&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "df449cd7919c4675aadb955ffe6c92a5", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:08:12.133197+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 34.02324998751283, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "999102ecbec403eebe7d822985baf2ac0be06eedcd4496b5e55241aa8190265c", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-b2e1d854c89c48e88841e9af2dde043c", + "operation": "dom_click", + "native": false, + "target_fingerprint": "999102ecbec403eebe7d822985baf2ac0be06eedcd4496b5e55241aa8190265c", + "delivered_at": "2026-07-26T07:08:12.536183+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 963.0870840046555 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 35.284209065139294, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "a81f6f2a1fc7ad1980170271541f9f16a1dced43dd71adf12c7c688d6f3437b9", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-9ac32d58b567470abeaaf4878a89af4d", + "operation": "dom_click", + "native": false, + "target_fingerprint": "a81f6f2a1fc7ad1980170271541f9f16a1dced43dd71adf12c7c688d6f3437b9", + "delivered_at": "2026-07-26T07:08:13.468117+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 1109.6672920975834 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 37.34649997204542, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "1fc5b7fad4faf089a1678e207b558f224178431741405c55c6623693c6b72fa6", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-68875cfd63434d61bab420aa6cae1de8", + "operation": "dom_click", + "native": false, + "target_fingerprint": "1fc5b7fad4faf089a1678e207b558f224178431741405c55c6623693c6b72fa6", + "delivered_at": "2026-07-26T07:08:14.568216+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 533.6915410589427 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 41.29291605204344, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "7b557cee5c68b46a97be50abf4beac6590b3d0765fca46aae085876b72988aff", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-5f4b92f606014b4f9c9fb8b8529865da", + "operation": "dom_click", + "native": false, + "target_fingerprint": "7b557cee5c68b46a97be50abf4beac6590b3d0765fca46aae085876b72988aff", + "delivered_at": "2026-07-26T07:08:15.103070+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 542.9748331662267 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 545.8195831160992 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 36.404249956831336, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "9e0f04248c738b1e4a623f4a89fbeedb9b888c5c3266ba7d96f1725201452054", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": false, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [ + "[rest] record_written: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "refuted", + "final_verdict": "refuted", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": "governed_refusal", + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-91acb5295ec54021bc657e06b1657bd3", + "operation": "dom_click", + "native": false, + "target_fingerprint": "9e0f04248c738b1e4a623f4a89fbeedb9b888c5c3266ba7d96f1725201452054", + "delivered_at": "2026-07-26T07:08:16.211611+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 5990.614417009056 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_005", + "intent": "click 'Save Encounter'", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ] + }, + "rung_counts": { + "structural": 4 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 9697.530041914433, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_before.png new file mode 100644 index 00000000..38206281 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/events.jsonl new file mode 100644 index 00000000..cc9f53e8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 314.7491249255836, "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's \u2014 expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) \u2014 refusing to act; run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 0.0, "expected": "", "mode": "structured", "observed": "Changed IdentityKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "mismatch"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": {"confidence": 1.0, "elapsed_ms": 47.70233295857906, "point": [781, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [781, 186], "region": [736, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "ebfa1d0bc4a47a0d6b5d2f5ed423850b0e76c13d1138cf4d870bfbe87842b098"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/halt.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/halt.webm new file mode 100644 index 00000000..0ac6427d Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/halt.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/outcome.json new file mode 100644 index 00000000..529ea47e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/outcome.json @@ -0,0 +1,48 @@ +{ + "browser_request_count": 3, + "case_id": "fault-stale-identity", + "duration_ms": 320.0055421330035, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/REPORT.md new file mode 100644 index 00000000..5411ee66 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:13.914244+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `6bd545f7349e4d4aa3df9c80002897ca` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✗ | 315 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted + +**Rung** `structural` (conf 1.00, resolved (781, 186)) · **Gates** id ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 320 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/checkpoints/_manifest.json new file mode 100644 index 00000000..bb279e2f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "6bd545f7349e4d4aa3df9c80002897ca", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "6bd545f7349e4d4aa3df9c80002897ca", + "created_at": "2026-07-26T07:07:13.913349+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:13.919394+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/pending_escalation.json new file mode 100644 index 00000000..d5ea2fce --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "identity", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "detail": [], + "proposed_options": [ + "Confirm the resolved target is the intended entity (the identity band could not be certified), then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:14.237939+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/report.json new file mode 100644 index 00000000..a1855338 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/report.json @@ -0,0 +1,165 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:13.914244+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "6bd545f7349e4d4aa3df9c80002897ca", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:13.913349+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 781, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 47.70233295857906, + "structural_handle": { + "point": [ + 781, + 186 + ], + "confidence": 1.0, + "region": [ + 736, + 168, + 90, + 36 + ], + "target_fingerprint": "ebfa1d0bc4a47a0d6b5d2f5ed423850b0e76c13d1138cf4d870bfbe87842b098", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "mismatch", + "mode": "structured", + "coverage": 0.0, + "expected": "", + "observed": "Changed IdentityKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "governed_refusal", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 314.7491249255836 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 320.0055421330035, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_after.png new file mode 100644 index 00000000..32084d90 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_before.png new file mode 100644 index 00000000..32084d90 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/events.jsonl new file mode 100644 index 00000000..f5164691 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 301.51212494820356, "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's \u2014 expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) \u2014 refusing to act; run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 0.0, "expected": "", "mode": "structured", "observed": "Changed IdentityKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "mismatch"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": {"confidence": 1.0, "elapsed_ms": 37.499959114938974, "point": [781, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [781, 186], "region": [736, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "74b4985eda11b0b13d2aed4424cd5c57f309724bab71d7fb59ccebfd5d38ba76"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/outcome.json new file mode 100644 index 00000000..97b55c2c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/outcome.json @@ -0,0 +1,48 @@ +{ + "browser_request_count": 3, + "case_id": "fault-stale-identity", + "duration_ms": 305.9028328862041, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/REPORT.md new file mode 100644 index 00000000..ec3b2c09 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:15.440541+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `89eac5a6ce294635aee4cb27f601665d` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✗ | 302 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted + +**Rung** `structural` (conf 1.00, resolved (781, 186)) · **Gates** id ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 306 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/checkpoints/_manifest.json new file mode 100644 index 00000000..e97c75e3 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "89eac5a6ce294635aee4cb27f601665d", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "89eac5a6ce294635aee4cb27f601665d", + "created_at": "2026-07-26T07:07:15.438643+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:15.446586+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/pending_escalation.json new file mode 100644 index 00000000..33709c1b --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "identity", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "detail": [], + "proposed_options": [ + "Confirm the resolved target is the intended entity (the identity band could not be certified), then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:15.751322+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/report.json new file mode 100644 index 00000000..a874ace3 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/report.json @@ -0,0 +1,165 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:15.440541+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "89eac5a6ce294635aee4cb27f601665d", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:15.438643+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 781, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 37.499959114938974, + "structural_handle": { + "point": [ + 781, + 186 + ], + "confidence": 1.0, + "region": [ + 736, + 168, + 90, + 36 + ], + "target_fingerprint": "74b4985eda11b0b13d2aed4424cd5c57f309724bab71d7fb59ccebfd5d38ba76", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "mismatch", + "mode": "structured", + "coverage": 0.0, + "expected": "", + "observed": "Changed IdentityKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "governed_refusal", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 301.51212494820356 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 305.9028328862041, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_after.png new file mode 100644 index 00000000..32084d90 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_before.png new file mode 100644 index 00000000..32084d90 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/events.jsonl new file mode 100644 index 00000000..447f7bd7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 294.75320782512426, "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's \u2014 expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) \u2014 refusing to act; run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 0.0, "expected": "", "mode": "structured", "observed": "Changed IdentityKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "mismatch"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": {"confidence": 1.0, "elapsed_ms": 36.323499865829945, "point": [781, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [781, 186], "region": [736, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "d40946deca325be1aa495d87c139d4745cd5811b718f084cda67f0fba09ca93a"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/outcome.json new file mode 100644 index 00000000..4d59724e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/outcome.json @@ -0,0 +1,48 @@ +{ + "browser_request_count": 3, + "case_id": "fault-stale-identity", + "duration_ms": 299.26454089581966, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/REPORT.md new file mode 100644 index 00000000..c2d9d036 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:16.846963+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `2fc39b0674964b8d90fbc128881b895e` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✗ | 295 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted + +**Rung** `structural` (conf 1.00, resolved (781, 186)) · **Gates** id ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 299 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/checkpoints/_manifest.json new file mode 100644 index 00000000..b1bed677 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "2fc39b0674964b8d90fbc128881b895e", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "2fc39b0674964b8d90fbc128881b895e", + "created_at": "2026-07-26T07:07:16.846209+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:16.849041+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/pending_escalation.json new file mode 100644 index 00000000..ba768a59 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "identity", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "detail": [], + "proposed_options": [ + "Confirm the resolved target is the intended entity (the identity band could not be certified), then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:17.146009+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/report.json new file mode 100644 index 00000000..2470a2be --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/report.json @@ -0,0 +1,165 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:16.846963+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "2fc39b0674964b8d90fbc128881b895e", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:16.846209+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 781, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 36.323499865829945, + "structural_handle": { + "point": [ + 781, + 186 + ], + "confidence": 1.0, + "region": [ + 736, + 168, + 90, + 36 + ], + "target_fingerprint": "d40946deca325be1aa495d87c139d4745cd5811b718f084cda67f0fba09ca93a", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "mismatch", + "mode": "structured", + "coverage": 0.0, + "expected": "", + "observed": "Changed IdentityKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "governed_refusal", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 294.75320782512426 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 299.26454089581966, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_after.png new file mode 100644 index 00000000..32084d90 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_before.png new file mode 100644 index 00000000..32084d90 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/events.jsonl new file mode 100644 index 00000000..117a0d96 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:18.647432+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-16c9ef318ed14a55952fd5c5f1698942", "status": "delivered", "target_fingerprint": "064993739eaae34241e7903efd4eebf52806da3cd0b0c4905dc2e9dbec2835b7"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 983.4499580319971, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.725291930139065, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "064993739eaae34241e7903efd4eebf52806da3cd0b0c4905dc2e9dbec2835b7"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:19.593067+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-66cfcce97da64bcab710ca56ed0dfbd1", "status": "delivered", "target_fingerprint": "8e353f23599d19644732da7deecb904107e07b6b4548c4ddf29cca5ba74bac08"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 1075.9899590630084, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 40.83145805634558, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "8e353f23599d19644732da7deecb904107e07b6b4548c4ddf29cca5ba74bac08"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:20.659915+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-3431a373df954f0e947d6964153f29bf", "status": "delivered", "target_fingerprint": "b8781507fc92202f7d40f164271d77ae83b802e28f6041c3e279b44bd08b50d1"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 545.4657920636237, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 35.18629213795066, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "b8781507fc92202f7d40f164271d77ae83b802e28f6041c3e279b44bd08b50d1"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:21.209488+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-d81f95bab90847a8989db6441ddb7a83", "status": "delivered", "target_fingerprint": "a430f0b532a591aaa45455a9992ca4165953dbaadba5223904e3c2951cca5607"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 541.0749998409301, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 36.148458952084184, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "a430f0b532a591aaa45455a9992ca4165953dbaadba5223904e3c2951cca5607"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 519.7191659826785, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:22.262970+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-9c6e5eb3947d410b97d50c1e97cf8370", "status": "delivered", "target_fingerprint": "01b9812887265932c0fbd9214bd15286a2113b3f03028e4c8849307683f54f96"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}, {"effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", "final_verdict": "refuted", "initial_verdict": "refuted", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: CONFIRMED \u2014 exactly 1 record(s) match the target selector", "[rest] field_equals: REFUTED \u2192 ESCALATED \u2014 no compensator available for an irreversible refuted effect -- durably halt and escalate"], "effect_verified": false, "elapsed_ms": 6134.860750054941, "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) \u2014 [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate \u2014 run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 33.0356250051409, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "01b9812887265932c0fbd9214bd15286a2113b3f03028e4c8849307683f54f96"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/halt.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/halt.webm new file mode 100644 index 00000000..492354ce Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/halt.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/oracle.json new file mode 100644 index 00000000..3abc23f6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/oracle.json @@ -0,0 +1,23 @@ +{ + "observed": "partial_write", + "oracle_kind": "partial_write_detected", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [ + { + "id": 1, + "key": "mockmed-triage-p1-v1", + "note": "", + "patient_id": "p1", + "source": "replay", + "type": "Triage" + } + ], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/outcome.json new file mode 100644 index 00000000..7f80dc1c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/outcome.json @@ -0,0 +1,45 @@ +{ + "browser_request_count": 4, + "case_id": "fault-weak-effect", + "duration_ms": 9809.738958021626, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/REPORT.md new file mode 100644 index 00000000..807b27e6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/REPORT.md @@ -0,0 +1,113 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:18.234854+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 0/2 +- **Evidence classes:** `authorization`, `effect_tier_1`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 5/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `7efa1469d621449784f198fc520f4e52` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 0 confirmed, 1 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 983 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 1076 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 545 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 541 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 520 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✗ | 6135 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step, halted) + +> ❌ **Error:** System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 4 | ████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 9810 ms | +| Steps ok | 5/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/_manifest.json new file mode 100644 index 00000000..df39045c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "7efa1469d621449784f198fc520f4e52", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "7efa1469d621449784f198fc520f4e52", + "created_at": "2026-07-26T07:07:18.233988+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:18.237242+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..df21c752 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "7efa1469d621449784f198fc520f4e52", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 30.725291930139065, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "064993739eaae34241e7903efd4eebf52806da3cd0b0c4905dc2e9dbec2835b7", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:19.221225+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..68b221c8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "7efa1469d621449784f198fc520f4e52", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 40.83145805634558, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "8e353f23599d19644732da7deecb904107e07b6b4548c4ddf29cca5ba74bac08", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:20.297654+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..81b521b7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "7efa1469d621449784f198fc520f4e52", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 35.18629213795066, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "b8781507fc92202f7d40f164271d77ae83b802e28f6041c3e279b44bd08b50d1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:20.843508+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..67463ef1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "7efa1469d621449784f198fc520f4e52", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 36.148458952084184, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "a430f0b532a591aaa45455a9992ca4165953dbaadba5223904e3c2951cca5607", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:21.385023+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..e6475558 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "7efa1469d621449784f198fc520f4e52", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:21.905184+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/pending_escalation.json new file mode 100644 index 00000000..46f8a3b1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/pending_escalation.json @@ -0,0 +1,32 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "category": "effect_escalated", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "detail": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "proposed_options": [ + "Inspect the system of record and correct it (the automatic compensation could not safely undo the fault)", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 5, + "resume_from_step_id": "step_004", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:28.045992+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/report.json new file mode 100644 index 00000000..73a0fb4f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/report.json @@ -0,0 +1,530 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:18.234854+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 0 + }, + "evidence_classes": [ + "authorization", + "effect_tier_1", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=partial&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "7efa1469d621449784f198fc520f4e52", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:18.233988+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 30.725291930139065, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "064993739eaae34241e7903efd4eebf52806da3cd0b0c4905dc2e9dbec2835b7", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-16c9ef318ed14a55952fd5c5f1698942", + "operation": "dom_click", + "native": false, + "target_fingerprint": "064993739eaae34241e7903efd4eebf52806da3cd0b0c4905dc2e9dbec2835b7", + "delivered_at": "2026-07-26T07:07:18.647432+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 983.4499580319971 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 40.83145805634558, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "8e353f23599d19644732da7deecb904107e07b6b4548c4ddf29cca5ba74bac08", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-66cfcce97da64bcab710ca56ed0dfbd1", + "operation": "dom_click", + "native": false, + "target_fingerprint": "8e353f23599d19644732da7deecb904107e07b6b4548c4ddf29cca5ba74bac08", + "delivered_at": "2026-07-26T07:07:19.593067+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 1075.9899590630084 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 35.18629213795066, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "b8781507fc92202f7d40f164271d77ae83b802e28f6041c3e279b44bd08b50d1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-3431a373df954f0e947d6964153f29bf", + "operation": "dom_click", + "native": false, + "target_fingerprint": "b8781507fc92202f7d40f164271d77ae83b802e28f6041c3e279b44bd08b50d1", + "delivered_at": "2026-07-26T07:07:20.659915+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 545.4657920636237 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 36.148458952084184, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "a430f0b532a591aaa45455a9992ca4165953dbaadba5223904e3c2951cca5607", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-d81f95bab90847a8989db6441ddb7a83", + "operation": "dom_click", + "native": false, + "target_fingerprint": "a430f0b532a591aaa45455a9992ca4165953dbaadba5223904e3c2951cca5607", + "delivered_at": "2026-07-26T07:07:21.209488+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 541.0749998409301 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 519.7191659826785 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 33.0356250051409, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "01b9812887265932c0fbd9214bd15286a2113b3f03028e4c8849307683f54f96", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": false, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "refuted", + "final_verdict": "refuted", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": "governed_refusal", + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-9c6e5eb3947d410b97d50c1e97cf8370", + "operation": "dom_click", + "native": false, + "target_fingerprint": "01b9812887265932c0fbd9214bd15286a2113b3f03028e4c8849307683f54f96", + "delivered_at": "2026-07-26T07:07:22.262970+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 6134.860750054941 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_005", + "intent": "click 'Save Encounter'", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ] + }, + "rung_counts": { + "structural": 4 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 9809.738958021626, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_before.png new file mode 100644 index 00000000..437a4e28 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_before.png new file mode 100644 index 00000000..6ccd281f Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/events.jsonl new file mode 100644 index 00000000..cce33cfa --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:29.625202+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-82c3236bddb14eeab79557ee9e48e935", "status": "delivered", "target_fingerprint": "2910fff66d81522376a55ca7f11848bb70aba8ed74aa13f8484e533181119a66"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 928.3050000667572, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.969500076025724, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "2910fff66d81522376a55ca7f11848bb70aba8ed74aa13f8484e533181119a66"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:30.486688+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-c7230f760193480a964b0431cd0f4e73", "status": "delivered", "target_fingerprint": "97e0c24dba726abc4c55af80b50b8baf5eda812d66720b77513e892970b076a0"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 840.9424589481205, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 29.611208010464907, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "97e0c24dba726abc4c55af80b50b8baf5eda812d66720b77513e892970b076a0"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:31.367402+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-e57ebdd6a4e4492b91a148b99c3bda8f", "status": "delivered", "target_fingerprint": "b1d65d5fbece77bde75acd059445d5298482933b16f09e2e9b0cd5849c816aec"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 519.726708997041, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.53999994881451, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "b1d65d5fbece77bde75acd059445d5298482933b16f09e2e9b0cd5849c816aec"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:31.859639+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-9159c8db768c4e1c817df883dab5a004", "status": "delivered", "target_fingerprint": "eb158b367250dc84cc4774aebb228f54fe7d7983be022bfb385e1bdb8fed1539"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 508.75458284281194, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 32.12612518109381, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "eb158b367250dc84cc4774aebb228f54fe7d7983be022bfb385e1bdb8fed1539"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 528.7557078991085, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:32.928686+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-4d553db898064c1cab7b71328839f639", "status": "delivered", "target_fingerprint": "a4ab8b52025c5f3618ebcd58d2f47f055db887d947932cf14a0b2671e190eb81"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}, {"effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", "final_verdict": "refuted", "initial_verdict": "refuted", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: CONFIRMED \u2014 exactly 1 record(s) match the target selector", "[rest] field_equals: REFUTED \u2192 ESCALATED \u2014 no compensator available for an irreversible refuted effect -- durably halt and escalate"], "effect_verified": false, "elapsed_ms": 6127.1950409282, "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) \u2014 [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate \u2014 run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.567125184461474, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "a4ab8b52025c5f3618ebcd58d2f47f055db887d947932cf14a0b2671e190eb81"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/oracle.json new file mode 100644 index 00000000..3abc23f6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/oracle.json @@ -0,0 +1,23 @@ +{ + "observed": "partial_write", + "oracle_kind": "partial_write_detected", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [ + { + "id": 1, + "key": "mockmed-triage-p1-v1", + "note": "", + "patient_id": "p1", + "source": "replay", + "type": "Triage" + } + ], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/outcome.json new file mode 100644 index 00000000..730c90c1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/outcome.json @@ -0,0 +1,45 @@ +{ + "browser_request_count": 4, + "case_id": "fault-weak-effect", + "duration_ms": 9462.27787504904, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/REPORT.md new file mode 100644 index 00000000..b3be07d9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/REPORT.md @@ -0,0 +1,113 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:29.252408+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 0/2 +- **Evidence classes:** `authorization`, `effect_tier_1`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 5/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `a5fd7645b7174d93b3d7154e79e2f282` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 0 confirmed, 1 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 928 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 841 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 520 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 509 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 529 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✗ | 6127 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step, halted) + +> ❌ **Error:** System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 4 | ████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 9462 ms | +| Steps ok | 5/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/_manifest.json new file mode 100644 index 00000000..b29934b5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "a5fd7645b7174d93b3d7154e79e2f282", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "created_at": "2026-07-26T07:07:29.251725+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:29.254444+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..e73c9fd9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 30.969500076025724, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "2910fff66d81522376a55ca7f11848bb70aba8ed74aa13f8484e533181119a66", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:30.183331+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..ef8a3709 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 29.611208010464907, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "97e0c24dba726abc4c55af80b50b8baf5eda812d66720b77513e892970b076a0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:31.024998+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..87d617e8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 30.53999994881451, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "b1d65d5fbece77bde75acd059445d5298482933b16f09e2e9b0cd5849c816aec", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:31.545289+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..ca785939 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 32.12612518109381, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "eb158b367250dc84cc4774aebb228f54fe7d7983be022bfb385e1bdb8fed1539", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:32.054489+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..7841c8a2 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:32.583675+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/pending_escalation.json new file mode 100644 index 00000000..0fb91416 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/pending_escalation.json @@ -0,0 +1,32 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "category": "effect_escalated", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "detail": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "proposed_options": [ + "Inspect the system of record and correct it (the automatic compensation could not safely undo the fault)", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 5, + "resume_from_step_id": "step_004", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:38.715711+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/report.json new file mode 100644 index 00000000..327573a1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/report.json @@ -0,0 +1,530 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:29.252408+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 0 + }, + "evidence_classes": [ + "authorization", + "effect_tier_1", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=partial&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "a5fd7645b7174d93b3d7154e79e2f282", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:29.251725+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 30.969500076025724, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "2910fff66d81522376a55ca7f11848bb70aba8ed74aa13f8484e533181119a66", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-82c3236bddb14eeab79557ee9e48e935", + "operation": "dom_click", + "native": false, + "target_fingerprint": "2910fff66d81522376a55ca7f11848bb70aba8ed74aa13f8484e533181119a66", + "delivered_at": "2026-07-26T07:07:29.625202+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 928.3050000667572 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 29.611208010464907, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "97e0c24dba726abc4c55af80b50b8baf5eda812d66720b77513e892970b076a0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-c7230f760193480a964b0431cd0f4e73", + "operation": "dom_click", + "native": false, + "target_fingerprint": "97e0c24dba726abc4c55af80b50b8baf5eda812d66720b77513e892970b076a0", + "delivered_at": "2026-07-26T07:07:30.486688+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 840.9424589481205 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 30.53999994881451, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "b1d65d5fbece77bde75acd059445d5298482933b16f09e2e9b0cd5849c816aec", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-e57ebdd6a4e4492b91a148b99c3bda8f", + "operation": "dom_click", + "native": false, + "target_fingerprint": "b1d65d5fbece77bde75acd059445d5298482933b16f09e2e9b0cd5849c816aec", + "delivered_at": "2026-07-26T07:07:31.367402+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 519.726708997041 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 32.12612518109381, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "eb158b367250dc84cc4774aebb228f54fe7d7983be022bfb385e1bdb8fed1539", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-9159c8db768c4e1c817df883dab5a004", + "operation": "dom_click", + "native": false, + "target_fingerprint": "eb158b367250dc84cc4774aebb228f54fe7d7983be022bfb385e1bdb8fed1539", + "delivered_at": "2026-07-26T07:07:31.859639+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 508.75458284281194 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 528.7557078991085 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 30.567125184461474, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "a4ab8b52025c5f3618ebcd58d2f47f055db887d947932cf14a0b2671e190eb81", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": false, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "refuted", + "final_verdict": "refuted", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": "governed_refusal", + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-4d553db898064c1cab7b71328839f639", + "operation": "dom_click", + "native": false, + "target_fingerprint": "a4ab8b52025c5f3618ebcd58d2f47f055db887d947932cf14a0b2671e190eb81", + "delivered_at": "2026-07-26T07:07:32.928686+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 6127.1950409282 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_005", + "intent": "click 'Save Encounter'", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ] + }, + "rung_counts": { + "structural": 4 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 9462.27787504904, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_before.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/events.jsonl new file mode 100644 index 00000000..f95cea7d --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:40.130202+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-49261f4d7f264b6ab46702064b6686ef", "status": "delivered", "target_fingerprint": "6cd455a7f6e55ae55ddb49d204570b25b5d571db7235cc8e36fb3af090003a71"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 943.5510421171784, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 40.350459050387144, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "6cd455a7f6e55ae55ddb49d204570b25b5d571db7235cc8e36fb3af090003a71"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:41.053961+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-feca1256407d4ab9b6a71dda355f0521", "status": "delivered", "target_fingerprint": "7d866de5fd87c934051172a9ca3ab6c8df2c08046fbea1d58cc18d59890e9619"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 971.0973331239074, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 36.240207962691784, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "7d866de5fd87c934051172a9ca3ab6c8df2c08046fbea1d58cc18d59890e9619"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:42.018803+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-736c4d9d0a424e2b9bbbf72fbd38a2ff", "status": "delivered", "target_fingerprint": "af757b797cedce36ff0a48585dec15775f3e5243bec995d3f60581f9c1cb1dd9"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 527.0705830771476, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 31.014583073556423, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "af757b797cedce36ff0a48585dec15775f3e5243bec995d3f60581f9c1cb1dd9"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:42.567179+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-1e232ebc25864743ad1567ec63c26730", "status": "delivered", "target_fingerprint": "6288b470312690300104055b7328644d21b61299bc097604a76f34803db5c2b0"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 560.8661670703441, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 36.11699980683625, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "6288b470312690300104055b7328644d21b61299bc097604a76f34803db5c2b0"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 550.1984998118132, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:43.661424+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-53f2c72e11b64a20a05e2ad638c6c8f4", "status": "delivered", "target_fingerprint": "1126febdd3ff26b6fc2e491707c3b7f86c24c1a874a5dad6961c12e83f7733ec"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}, {"effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", "final_verdict": "refuted", "initial_verdict": "refuted", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: CONFIRMED \u2014 exactly 1 record(s) match the target selector", "[rest] field_equals: REFUTED \u2192 ESCALATED \u2014 no compensator available for an irreversible refuted effect -- durably halt and escalate"], "effect_verified": false, "elapsed_ms": 6019.042708911002, "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) \u2014 [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate \u2014 run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 34.47775007225573, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "1126febdd3ff26b6fc2e491707c3b7f86c24c1a874a5dad6961c12e83f7733ec"}}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/oracle.json new file mode 100644 index 00000000..3abc23f6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/oracle.json @@ -0,0 +1,23 @@ +{ + "observed": "partial_write", + "oracle_kind": "partial_write_detected", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [ + { + "id": 1, + "key": "mockmed-triage-p1-v1", + "note": "", + "patient_id": "p1", + "source": "replay", + "type": "Triage" + } + ], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/outcome.json new file mode 100644 index 00000000..3796c82e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/outcome.json @@ -0,0 +1,45 @@ +{ + "browser_request_count": 4, + "case_id": "fault-weak-effect", + "duration_ms": 9582.309165969491, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/REPORT.md new file mode 100644 index 00000000..d76a589f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/REPORT.md @@ -0,0 +1,113 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:39.751533+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 0/2 +- **Evidence classes:** `authorization`, `effect_tier_1`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 5/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `08a69e56a6674248b7130465e0316861` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 0 confirmed, 1 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 944 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 971 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 527 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 561 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 550 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✗ | 6019 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step, halted) + +> ❌ **Error:** System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 4 | ████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 9582 ms | +| Steps ok | 5/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/_manifest.json new file mode 100644 index 00000000..1bb95924 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "08a69e56a6674248b7130465e0316861", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "08a69e56a6674248b7130465e0316861", + "created_at": "2026-07-26T07:07:39.750852+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:39.753782+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..57982fe6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "08a69e56a6674248b7130465e0316861", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 40.350459050387144, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "6cd455a7f6e55ae55ddb49d204570b25b5d571db7235cc8e36fb3af090003a71", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:40.697827+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..66717845 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "08a69e56a6674248b7130465e0316861", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 36.240207962691784, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "7d866de5fd87c934051172a9ca3ab6c8df2c08046fbea1d58cc18d59890e9619", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:41.669349+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..c5062068 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "08a69e56a6674248b7130465e0316861", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 31.014583073556423, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "af757b797cedce36ff0a48585dec15775f3e5243bec995d3f60581f9c1cb1dd9", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:42.196869+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..f12b8a19 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "08a69e56a6674248b7130465e0316861", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 36.11699980683625, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "6288b470312690300104055b7328644d21b61299bc097604a76f34803db5c2b0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:42.758201+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..84d6f580 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "08a69e56a6674248b7130465e0316861", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:43.309078+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/pending_escalation.json new file mode 100644 index 00000000..93678dca --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/pending_escalation.json @@ -0,0 +1,32 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "category": "effect_escalated", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "detail": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "proposed_options": [ + "Inspect the system of record and correct it (the automatic compensation could not safely undo the fault)", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 5, + "resume_from_step_id": "step_004", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:49.334415+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/report.json new file mode 100644 index 00000000..a72d77d0 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/report.json @@ -0,0 +1,530 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:39.751533+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 0 + }, + "evidence_classes": [ + "authorization", + "effect_tier_1", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=partial&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "08a69e56a6674248b7130465e0316861", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:39.750852+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 40.350459050387144, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "6cd455a7f6e55ae55ddb49d204570b25b5d571db7235cc8e36fb3af090003a71", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-49261f4d7f264b6ab46702064b6686ef", + "operation": "dom_click", + "native": false, + "target_fingerprint": "6cd455a7f6e55ae55ddb49d204570b25b5d571db7235cc8e36fb3af090003a71", + "delivered_at": "2026-07-26T07:07:40.130202+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 943.5510421171784 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 36.240207962691784, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "7d866de5fd87c934051172a9ca3ab6c8df2c08046fbea1d58cc18d59890e9619", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-feca1256407d4ab9b6a71dda355f0521", + "operation": "dom_click", + "native": false, + "target_fingerprint": "7d866de5fd87c934051172a9ca3ab6c8df2c08046fbea1d58cc18d59890e9619", + "delivered_at": "2026-07-26T07:07:41.053961+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 971.0973331239074 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 31.014583073556423, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "af757b797cedce36ff0a48585dec15775f3e5243bec995d3f60581f9c1cb1dd9", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-736c4d9d0a424e2b9bbbf72fbd38a2ff", + "operation": "dom_click", + "native": false, + "target_fingerprint": "af757b797cedce36ff0a48585dec15775f3e5243bec995d3f60581f9c1cb1dd9", + "delivered_at": "2026-07-26T07:07:42.018803+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 527.0705830771476 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 36.11699980683625, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "6288b470312690300104055b7328644d21b61299bc097604a76f34803db5c2b0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-1e232ebc25864743ad1567ec63c26730", + "operation": "dom_click", + "native": false, + "target_fingerprint": "6288b470312690300104055b7328644d21b61299bc097604a76f34803db5c2b0", + "delivered_at": "2026-07-26T07:07:42.567179+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 560.8661670703441 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 550.1984998118132 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 34.47775007225573, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "1126febdd3ff26b6fc2e491707c3b7f86c24c1a874a5dad6961c12e83f7733ec", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": false, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: REFUTED → ESCALATED — no compensator available for an irreversible refuted effect -- durably halt and escalate" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "refuted", + "final_verdict": "refuted", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": "governed_refusal", + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-53f2c72e11b64a20a05e2ad638c6c8f4", + "operation": "dom_click", + "native": false, + "target_fingerprint": "1126febdd3ff26b6fc2e491707c3b7f86c24c1a874a5dad6961c12e83f7733ec", + "delivered_at": "2026-07-26T07:07:43.661424+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 6019.042708911002 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_005", + "intent": "click 'Save Encounter'", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ] + }, + "rung_counts": { + "structural": 4 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 9582.309165969491, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_before.png new file mode 100644 index 00000000..b151f9fc Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/events.jsonl new file mode 100644 index 00000000..3778f964 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 162.08275011740625, "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's \u2014 expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) \u2014 refusing to act; run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 0.0, "expected": "", "mode": "structured", "observed": "Taylor DuplicateKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "mismatch"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": {"confidence": 0.9979566335678101, "elapsed_ms": 15.029917005449533, "point": [777, 186], "rung": "template", "structural_handle": null}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/halt.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/halt.webm new file mode 100644 index 00000000..73acac88 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/halt.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/outcome.json new file mode 100644 index 00000000..55cbd23f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/outcome.json @@ -0,0 +1,50 @@ +{ + "browser_request_count": 3, + "case_id": "fault-wrong-identity", + "duration_ms": 167.76495892554522, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/REPORT.md new file mode 100644 index 00000000..27845a38 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:09.723096+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `dd51c9d6082b4997a421a321ae552d6d` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | template | 1.00 | id ✗ | 162 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted + +**Rung** `template` (conf 1.00, resolved (777, 186)) · **Gates** id ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 168 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/checkpoints/_manifest.json new file mode 100644 index 00000000..b0763a09 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "dd51c9d6082b4997a421a321ae552d6d", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "dd51c9d6082b4997a421a321ae552d6d", + "created_at": "2026-07-26T07:07:09.722343+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:09.725766+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/pending_escalation.json new file mode 100644 index 00000000..9c97d265 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "identity", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "detail": [], + "proposed_options": [ + "Confirm the resolved target is the intended entity (the identity band could not be certified), then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:09.891826+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/report.json new file mode 100644 index 00000000..fdc684f1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/report.json @@ -0,0 +1,149 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:09.723096+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&drift=lookalike&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "dd51c9d6082b4997a421a321ae552d6d", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:09.722343+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "template", + "point": [ + 777, + 186 + ], + "confidence": 0.9979566335678101, + "elapsed_ms": 15.029917005449533, + "structural_handle": null + }, + "identity": { + "status": "mismatch", + "mode": "structured", + "coverage": 0.0, + "expected": "", + "observed": "Taylor DuplicateKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "governed_refusal", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 162.08275011740625 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 167.76495892554522, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_after.png new file mode 100644 index 00000000..d88dec60 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_before.png new file mode 100644 index 00000000..d88dec60 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/events.jsonl new file mode 100644 index 00000000..67f6175b --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 180.47349993139505, "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's \u2014 expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) \u2014 refusing to act; run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 0.0, "expected": "", "mode": "structured", "observed": "Taylor DuplicateKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "mismatch"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": {"confidence": 0.9979566335678101, "elapsed_ms": 18.597082933411002, "point": [777, 186], "rung": "template", "structural_handle": null}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/outcome.json new file mode 100644 index 00000000..262d3a88 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/outcome.json @@ -0,0 +1,50 @@ +{ + "browser_request_count": 3, + "case_id": "fault-wrong-identity", + "duration_ms": 188.54504101909697, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/REPORT.md new file mode 100644 index 00000000..90977fb8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:11.136376+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `f8b96b5d0754447ea494cd44b5681088` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | template | 1.00 | id ✗ | 180 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted + +**Rung** `template` (conf 1.00, resolved (777, 186)) · **Gates** id ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 189 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/checkpoints/_manifest.json new file mode 100644 index 00000000..5cd0c9fb --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "f8b96b5d0754447ea494cd44b5681088", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "f8b96b5d0754447ea494cd44b5681088", + "created_at": "2026-07-26T07:07:11.135635+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:11.139398+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/pending_escalation.json new file mode 100644 index 00000000..e88370fa --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "identity", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "detail": [], + "proposed_options": [ + "Confirm the resolved target is the intended entity (the identity band could not be certified), then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:11.325140+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/report.json new file mode 100644 index 00000000..96915239 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/report.json @@ -0,0 +1,149 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:11.136376+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&drift=lookalike&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "f8b96b5d0754447ea494cd44b5681088", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:11.135635+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "template", + "point": [ + 777, + 186 + ], + "confidence": 0.9979566335678101, + "elapsed_ms": 18.597082933411002, + "structural_handle": null + }, + "identity": { + "status": "mismatch", + "mode": "structured", + "coverage": 0.0, + "expected": "", + "observed": "Taylor DuplicateKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "governed_refusal", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 180.47349993139505 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 188.54504101909697, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_after.png new file mode 100644 index 00000000..d88dec60 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_before.png new file mode 100644 index 00000000..d88dec60 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/events.jsonl new file mode 100644 index 00000000..014ad4ad --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/events.jsonl @@ -0,0 +1 @@ +{"actuation": null, "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 170.20112508907914, "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's \u2014 expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) \u2014 refusing to act; run aborted", "exception_handled": false, "failure_category": "governed_refusal", "heal": null, "identity": {"coverage": 0.0, "expected": "", "mode": "structured", "observed": "Taylor DuplicateKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "mismatch"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": false, "postcondition_drift_rescues": [], "postconditions_ok": null, "resolution": {"confidence": 0.9979566335678101, "elapsed_ms": 14.50908393599093, "point": [777, 186], "rung": "template", "structural_handle": null}, "safety_halt": true, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/oracle.json new file mode 100644 index 00000000..8e9eede9 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/oracle.json @@ -0,0 +1,14 @@ +{ + "observed": "no_mutation", + "oracle_kind": "no_mutation", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/outcome.json new file mode 100644 index 00000000..8983a88f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/outcome.json @@ -0,0 +1,50 @@ +{ + "browser_request_count": 3, + "case_id": "fault-wrong-identity", + "duration_ms": 174.04475016519427, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/REPORT.md new file mode 100644 index 00000000..ae3c2363 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/REPORT.md @@ -0,0 +1,67 @@ +# ❌ mockmed-triage — HALTED + +- **Started:** 2026-07-26T07:07:12.466000+00:00 +- **Execution profile:** `standard` (not production-eligible) +- **Required contracts passed:** authorization 1/1, identity 0/1, postcondition 0/2 +- **Evidence classes:** `authorization` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 0/1 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `13e73ceed35949a69000f91a40dbf3d1` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +_No executed step carried a system-of-record effect contract — every local step outcome used screen evidence only. Run `openadapt-flow lint` to see the bundle's consequential-step effect coverage._ + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | template | 1.00 | id ✗ | 170 | | ❌ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' (final step, halted) + +> ❌ **Error:** Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted + +**Rung** `template` (conf 1.00, resolved (777, 186)) · **Gates** id ✗ · **Heal** none · **Outcome** ❌ HALTED (governed refusal) + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 174 ms | +| Steps ok | 0/1 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/checkpoints/_manifest.json new file mode 100644 index 00000000..5fd8809c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "13e73ceed35949a69000f91a40dbf3d1", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "13e73ceed35949a69000f91a40dbf3d1", + "created_at": "2026-07-26T07:07:12.465301+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:07:12.467949+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/pending_escalation.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/pending_escalation.json new file mode 100644 index 00000000..7c522a32 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/pending_escalation.json @@ -0,0 +1,29 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "category": "identity", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "detail": [], + "proposed_options": [ + "Confirm the resolved target is the intended entity (the identity band could not be certified), then resume", + "Approve and RESUME from the last verified checkpoint (re-runs only this step onward; already-confirmed steps are not repeated)", + "Abort the run and discard the pending escalation" + ], + "resume_from_index": 0, + "resume_from_step_id": null, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "status": "pending", + "stale_after_s": 604800.0, + "program": false, + "program_frames": [], + "program_checkpoint_seq": 0, + "program_history_hash": "", + "delivery_uncertainty": null, + "created_at": "2026-07-26T07:07:12.640734+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/report.json new file mode 100644 index 00000000..65af2ef5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/report.json @@ -0,0 +1,149 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:07:12.466000+00:00", + "execution_profile": "standard", + "execution_outcome": "HALTED", + "production_eligible": false, + "execution_completed": false, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "HALTED", + "profile": "standard", + "production_eligible": false, + "execution_completed": false, + "required_contracts": { + "authorization": 1, + "identity": 1, + "postcondition": 2, + "effect": 0 + }, + "passed_contracts": { + "authorization": 1, + "identity": 0, + "postcondition": 0, + "effect": 0 + }, + "evidence_classes": [ + "authorization" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&drift=lookalike&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "13e73ceed35949a69000f91a40dbf3d1", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:07:12.465301+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": false, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "template", + "point": [ + 777, + 186 + ], + "confidence": 0.9979566335678101, + "elapsed_ms": 14.50908393599093, + "structural_handle": null + }, + "identity": { + "status": "mismatch", + "mode": "structured", + "coverage": 0.0, + "expected": "", + "observed": "Taylor DuplicateKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": null, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": true, + "effect_results": [], + "effect_evidence": [], + "failure_category": "governed_refusal", + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 170.20112508907914 + } + ], + "success": false, + "terminal_outcome": null, + "visited_states": [], + "halt": { + "state_id": "step_000", + "intent": "click 'Open'", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "outcome": "halt", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "completed_intents": [] + }, + "rung_counts": {}, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 174.04475016519427, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_after.png new file mode 100644 index 00000000..d88dec60 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_before.png new file mode 100644 index 00000000..d88dec60 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/events.jsonl new file mode 100644 index 00000000..8ca0243c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:48.810548+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-0f836ad65cdf46b7bb902bc8b61a19ab", "status": "delivered", "target_fingerprint": "f790e07b3a4e84ebc2ef91a38e8743d834c6d27ee7672873150057df366c8ea1"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 921.5095001272857, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 34.90704181604087, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "f790e07b3a4e84ebc2ef91a38e8743d834c6d27ee7672873150057df366c8ea1"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:49.692715+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-1afc295fe9274a189540a68bdb1f1d80", "status": "delivered", "target_fingerprint": "4d1f78b53357398753d4e7a9db205d3f8420b1633b0af04326d522b7e66bda96"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 1145.5764591228217, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 39.18520803563297, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "4d1f78b53357398753d4e7a9db205d3f8420b1633b0af04326d522b7e66bda96"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:50.818489+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-2831abd77d624ba68e4a74383e388c2f", "status": "delivered", "target_fingerprint": "69be686d8eb9b2a348da1b85be86ec36b8f54044eaad3fe2708afb23219438a6"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 527.8699579648674, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.22295911796391, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "69be686d8eb9b2a348da1b85be86ec36b8f54044eaad3fe2708afb23219438a6"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:51.326742+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-62a9a6f85d6f4f3e945ac898ef238e43", "status": "delivered", "target_fingerprint": "7de1b63a2855df928c5fa9a795cee16e2cf2efe66545138c7581a18cee17261c"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 504.9883748870343, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 28.679209062829614, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "7de1b63a2855df928c5fa9a795cee16e2cf2efe66545138c7581a18cee17261c"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 540.1995829306543, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:52.510169+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-36e997231f1347eba4ea2315e134dce7", "status": "delivered", "target_fingerprint": "cac6aeb9c74345a58c84d6854cfe35dc4893ca0d9e080fb64ea7f41456e85d0e"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}, {"effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: CONFIRMED \u2014 exactly 1 record(s) match the target selector", "[rest] field_equals: CONFIRMED \u2014 field 'note' equals the expected value"], "effect_verified": true, "elapsed_ms": 1176.8135000020266, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 31.852500047534704, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "cac6aeb9c74345a58c84d6854cfe35dc4893ca0d9e080fb64ea7f41456e85d0e"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/oracle.json new file mode 100644 index 00000000..18e3292d --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/oracle.json @@ -0,0 +1,23 @@ +{ + "observed": "exact_record", + "oracle_kind": "exact_record", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [ + { + "id": 1, + "key": "mockmed-triage-p1-v1", + "note": "Synthetic follow-up in two weeks", + "patient_id": "p1", + "source": "replay", + "type": "Triage" + } + ], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/outcome.json new file mode 100644 index 00000000..0173cbf7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/outcome.json @@ -0,0 +1,23 @@ +{ + "browser_request_count": 4, + "case_id": "representative", + "duration_ms": 4820.507416967303, + "execution_completed": true, + "execution_profile": "standard", + "expected_outcome": "VERIFIED", + "failed_step_id": null, + "halt": null, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "VERIFIED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": true, + "report_sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/replay.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/replay.webm new file mode 100644 index 00000000..f4cb944a Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/replay.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/REPORT.md new file mode 100644 index 00000000..90b772f3 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/REPORT.md @@ -0,0 +1,111 @@ +# ✅ mockmed-triage — VERIFIED + +- **Started:** 2026-07-26T07:06:48.383031+00:00 +- **Execution profile:** `standard` (production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 2/2 +- **Evidence classes:** `authorization`, `effect_tier_1`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 6/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `edbfec21795846338d3726f19d1a66c2` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 1 confirmed, 0 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 922 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 1146 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 528 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 505 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 540 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✓ | 1177 | | ✅ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step) + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 5 | █████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 4821 ms | +| Steps ok | 6/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json new file mode 100644 index 00000000..ec5813f4 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "edbfec21795846338d3726f19d1a66c2", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "edbfec21795846338d3726f19d1a66c2", + "created_at": "2026-07-26T07:06:48.381460+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:06:48.399724+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..dd840b2f --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 34.90704181604087, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "f790e07b3a4e84ebc2ef91a38e8743d834c6d27ee7672873150057df366c8ea1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:49.322002+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..7f0d9021 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 39.18520803563297, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "4d1f78b53357398753d4e7a9db205d3f8420b1633b0af04326d522b7e66bda96", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:50.468306+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..5652a75e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 30.22295911796391, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "69be686d8eb9b2a348da1b85be86ec36b8f54044eaad3fe2708afb23219438a6", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:50.996736+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..3676817e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 28.679209062829614, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "7de1b63a2855df928c5fa9a795cee16e2cf2efe66545138c7581a18cee17261c", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:51.502161+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..412ddbdf --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:52.042801+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0005_step_005.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0005_step_005.json new file mode 100644 index 00000000..45facfe8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/checkpoints/step_0005_step_005.json @@ -0,0 +1,86 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "next_step_index": 6, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": true, + "effect_approved_unverified": false, + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 31.852500047534704, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "cac6aeb9c74345a58c84d6854cfe35dc4893ca0d9e080fb64ea7f41456e85d0e", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:53.220029+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/report.json new file mode 100644 index 00000000..a52adaeb --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/report.json @@ -0,0 +1,508 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:06:48.383031+00:00", + "execution_profile": "standard", + "execution_outcome": "VERIFIED", + "production_eligible": true, + "execution_completed": true, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "VERIFIED", + "profile": "standard", + "production_eligible": true, + "execution_completed": true, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "evidence_classes": [ + "authorization", + "effect_tier_1", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "edbfec21795846338d3726f19d1a66c2", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:06:48.381460+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 34.90704181604087, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "f790e07b3a4e84ebc2ef91a38e8743d834c6d27ee7672873150057df366c8ea1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-0f836ad65cdf46b7bb902bc8b61a19ab", + "operation": "dom_click", + "native": false, + "target_fingerprint": "f790e07b3a4e84ebc2ef91a38e8743d834c6d27ee7672873150057df366c8ea1", + "delivered_at": "2026-07-26T07:06:48.810548+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 921.5095001272857 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 39.18520803563297, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "4d1f78b53357398753d4e7a9db205d3f8420b1633b0af04326d522b7e66bda96", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-1afc295fe9274a189540a68bdb1f1d80", + "operation": "dom_click", + "native": false, + "target_fingerprint": "4d1f78b53357398753d4e7a9db205d3f8420b1633b0af04326d522b7e66bda96", + "delivered_at": "2026-07-26T07:06:49.692715+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 1145.5764591228217 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 30.22295911796391, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "69be686d8eb9b2a348da1b85be86ec36b8f54044eaad3fe2708afb23219438a6", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-2831abd77d624ba68e4a74383e388c2f", + "operation": "dom_click", + "native": false, + "target_fingerprint": "69be686d8eb9b2a348da1b85be86ec36b8f54044eaad3fe2708afb23219438a6", + "delivered_at": "2026-07-26T07:06:50.818489+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 527.8699579648674 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 28.679209062829614, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "7de1b63a2855df928c5fa9a795cee16e2cf2efe66545138c7581a18cee17261c", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-62a9a6f85d6f4f3e945ac898ef238e43", + "operation": "dom_click", + "native": false, + "target_fingerprint": "7de1b63a2855df928c5fa9a795cee16e2cf2efe66545138c7581a18cee17261c", + "delivered_at": "2026-07-26T07:06:51.326742+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 504.9883748870343 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 540.1995829306543 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 31.852500047534704, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "cac6aeb9c74345a58c84d6854cfe35dc4893ca0d9e080fb64ea7f41456e85d0e", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": true, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: CONFIRMED — field 'note' equals the expected value" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": null, + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-36e997231f1347eba4ea2315e134dce7", + "operation": "dom_click", + "native": false, + "target_fingerprint": "cac6aeb9c74345a58c84d6854cfe35dc4893ca0d9e080fb64ea7f41456e85d0e", + "delivered_at": "2026-07-26T07:06:52.510169+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 1176.8135000020266 + } + ], + "success": true, + "terminal_outcome": null, + "visited_states": [], + "halt": null, + "rung_counts": { + "structural": 5 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 4820.507416967303, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_before.png new file mode 100644 index 00000000..fce3734e Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_before.png new file mode 100644 index 00000000..38206281 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-01/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/events.jsonl new file mode 100644 index 00000000..fc3a0b82 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:54.841703+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-3f0759c90ca74b9b882b6adb71b19cad", "status": "delivered", "target_fingerprint": "b76d4e76565f2854ee65c142b3ce98e2a306ab413501dceb73853b0b700d1530"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 948.7939579412341, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 33.2741669844836, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "b76d4e76565f2854ee65c142b3ce98e2a306ab413501dceb73853b0b700d1530"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:55.718404+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-66f90c151d05450eb2a7d536820a50b0", "status": "delivered", "target_fingerprint": "f8ffd614e005af2e96f81f56e2b2ae1ce8c30cd3f9d2dd038416b5ffb2817fd3"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 1017.7085839677602, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 34.51308305375278, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "f8ffd614e005af2e96f81f56e2b2ae1ce8c30cd3f9d2dd038416b5ffb2817fd3"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:56.776782+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-1cb440243707445c9aef49edab760ee8", "status": "delivered", "target_fingerprint": "aaf3a10b346371a1d519691e225dc7b4a0ee1bedbfd25eedd802b7fb55d60402"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 509.56866703927517, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.907042091712356, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "aaf3a10b346371a1d519691e225dc7b4a0ee1bedbfd25eedd802b7fb55d60402"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:57.291462+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-e7cefeddf44b4201a92e0e683240668c", "status": "delivered", "target_fingerprint": "b27f9b338296e099fb7c66868b943564a6ecdb5015b8879bc2e3834a1109cfad"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 524.6594999916852, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 39.38679210841656, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "b27f9b338296e099fb7c66868b943564a6ecdb5015b8879bc2e3834a1109cfad"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 546.6259999666363, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:06:58.334929+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-399e71af232c433ca660cef64d0c7ea3", "status": "delivered", "target_fingerprint": "8910826d1056d8c4a7e2021b98751c3958aa833a751cce31bfd88041d7c4082d"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}, {"effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: CONFIRMED \u2014 exactly 1 record(s) match the target selector", "[rest] field_equals: CONFIRMED \u2014 field 'note' equals the expected value"], "effect_verified": true, "elapsed_ms": 1156.0849589295685, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 29.901999980211258, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "8910826d1056d8c4a7e2021b98751c3958aa833a751cce31bfd88041d7c4082d"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/oracle.json new file mode 100644 index 00000000..18e3292d --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/oracle.json @@ -0,0 +1,23 @@ +{ + "observed": "exact_record", + "oracle_kind": "exact_record", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [ + { + "id": 1, + "key": "mockmed-triage-p1-v1", + "note": "Synthetic follow-up in two weeks", + "patient_id": "p1", + "source": "replay", + "type": "Triage" + } + ], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/outcome.json new file mode 100644 index 00000000..71ad591e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/outcome.json @@ -0,0 +1,23 @@ +{ + "browser_request_count": 4, + "case_id": "representative", + "duration_ms": 4706.6427080426365, + "execution_completed": true, + "execution_profile": "standard", + "expected_outcome": "VERIFIED", + "failed_step_id": null, + "halt": null, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "VERIFIED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": true, + "report_sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/REPORT.md new file mode 100644 index 00000000..36cf26c2 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/REPORT.md @@ -0,0 +1,111 @@ +# ✅ mockmed-triage — VERIFIED + +- **Started:** 2026-07-26T07:06:54.464498+00:00 +- **Execution profile:** `standard` (production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 2/2 +- **Evidence classes:** `authorization`, `effect_tier_1`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 6/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `b4c72d395a8e4340811bf3bd99563d4e` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 1 confirmed, 0 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 949 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 1018 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 510 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 525 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 547 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✓ | 1156 | | ✅ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step) + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 5 | █████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 4707 ms | +| Steps ok | 6/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/_manifest.json new file mode 100644 index 00000000..835d1ec8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "b4c72d395a8e4340811bf3bd99563d4e", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "created_at": "2026-07-26T07:06:54.463725+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:06:54.466667+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..4159ac29 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 33.2741669844836, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "b76d4e76565f2854ee65c142b3ce98e2a306ab413501dceb73853b0b700d1530", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:55.416009+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..268522fc --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 34.51308305375278, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "f8ffd614e005af2e96f81f56e2b2ae1ce8c30cd3f9d2dd038416b5ffb2817fd3", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:56.434137+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..48dfe831 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 30.907042091712356, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "aaf3a10b346371a1d519691e225dc7b4a0ee1bedbfd25eedd802b7fb55d60402", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:56.944156+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..4e5936e0 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 39.38679210841656, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "b27f9b338296e099fb7c66868b943564a6ecdb5015b8879bc2e3834a1109cfad", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:57.469344+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..e48c7269 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:58.016574+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0005_step_005.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0005_step_005.json new file mode 100644 index 00000000..dd89727a --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/checkpoints/step_0005_step_005.json @@ -0,0 +1,86 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "next_step_index": 6, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": true, + "effect_approved_unverified": false, + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 29.901999980211258, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "8910826d1056d8c4a7e2021b98751c3958aa833a751cce31bfd88041d7c4082d", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:06:59.173092+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/report.json new file mode 100644 index 00000000..3d7ee4a8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/report.json @@ -0,0 +1,508 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:06:54.464498+00:00", + "execution_profile": "standard", + "execution_outcome": "VERIFIED", + "production_eligible": true, + "execution_completed": true, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "VERIFIED", + "profile": "standard", + "production_eligible": true, + "execution_completed": true, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "evidence_classes": [ + "authorization", + "effect_tier_1", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "b4c72d395a8e4340811bf3bd99563d4e", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:06:54.463725+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 33.2741669844836, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "b76d4e76565f2854ee65c142b3ce98e2a306ab413501dceb73853b0b700d1530", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-3f0759c90ca74b9b882b6adb71b19cad", + "operation": "dom_click", + "native": false, + "target_fingerprint": "b76d4e76565f2854ee65c142b3ce98e2a306ab413501dceb73853b0b700d1530", + "delivered_at": "2026-07-26T07:06:54.841703+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 948.7939579412341 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 34.51308305375278, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "f8ffd614e005af2e96f81f56e2b2ae1ce8c30cd3f9d2dd038416b5ffb2817fd3", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-66f90c151d05450eb2a7d536820a50b0", + "operation": "dom_click", + "native": false, + "target_fingerprint": "f8ffd614e005af2e96f81f56e2b2ae1ce8c30cd3f9d2dd038416b5ffb2817fd3", + "delivered_at": "2026-07-26T07:06:55.718404+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 1017.7085839677602 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 30.907042091712356, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "aaf3a10b346371a1d519691e225dc7b4a0ee1bedbfd25eedd802b7fb55d60402", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-1cb440243707445c9aef49edab760ee8", + "operation": "dom_click", + "native": false, + "target_fingerprint": "aaf3a10b346371a1d519691e225dc7b4a0ee1bedbfd25eedd802b7fb55d60402", + "delivered_at": "2026-07-26T07:06:56.776782+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 509.56866703927517 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 39.38679210841656, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "b27f9b338296e099fb7c66868b943564a6ecdb5015b8879bc2e3834a1109cfad", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-e7cefeddf44b4201a92e0e683240668c", + "operation": "dom_click", + "native": false, + "target_fingerprint": "b27f9b338296e099fb7c66868b943564a6ecdb5015b8879bc2e3834a1109cfad", + "delivered_at": "2026-07-26T07:06:57.291462+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 524.6594999916852 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 546.6259999666363 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 29.901999980211258, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "8910826d1056d8c4a7e2021b98751c3958aa833a751cce31bfd88041d7c4082d", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": true, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: CONFIRMED — field 'note' equals the expected value" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": null, + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-399e71af232c433ca660cef64d0c7ea3", + "operation": "dom_click", + "native": false, + "target_fingerprint": "8910826d1056d8c4a7e2021b98751c3958aa833a751cce31bfd88041d7c4082d", + "delivered_at": "2026-07-26T07:06:58.334929+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 1156.0849589295685 + } + ], + "success": true, + "terminal_outcome": null, + "visited_states": [], + "halt": null, + "rung_counts": { + "structural": 5 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 4706.6427080426365, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_before.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_before.png new file mode 100644 index 00000000..b151f9fc Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-02/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/events.jsonl new file mode 100644 index 00000000..076b1ca6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/events.jsonl @@ -0,0 +1,6 @@ +{"actuation": "dom", "after_png": "steps/step_000_after.png", "before_png": "steps/step_000_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:00.132929+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-43bbd42cf4ec4112aafe8a7ea437439e", "status": "delivered", "target_fingerprint": "6d292b01ae1b623fdeddd0673d8c3fb085066c941955d687e87585a4c908ea93"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 1004.6848750207573, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane SampleKnee pain referralHigh", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 0, "input_retried": false, "input_verified": null, "intent": "click 'Open'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 38.53337489999831, "point": [776, 186], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [776, 186], "region": [731, 168, 90, 36], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "6d292b01ae1b623fdeddd0673d8c3fb085066c941955d687e87585a4c908ea93"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_000"} +{"actuation": "dom", "after_png": "steps/step_001_after.png", "before_png": "steps/step_001_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:01.077058+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-a237e6aea10547d2a1a15a6669408d43", "status": "delivered", "target_fingerprint": "ebf0b3ba1ecee8d23172318d2021f723d2e48ca78584b9f5ca35c94df7ff07d1"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 976.6885419376194, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 1, "input_retried": false, "input_verified": null, "intent": "click 'New Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 33.05812506005168, "point": [114, 159], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [114, 159], "region": [24, 139, 180, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "ebf0b3ba1ecee8d23172318d2021f723d2e48ca78584b9f5ca35c94df7ff07d1"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_001"} +{"actuation": "dom", "after_png": "steps/step_002_after.png", "before_png": "steps/step_002_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:02.083709+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-a1514aa3efb34a50b0042be5f8c8fb32", "status": "delivered", "target_fingerprint": "62ad985d106865db733806d57edba55417e29f24fac074b318afc49b37ce4a9d"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 520.2156249433756, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 2, "input_retried": false, "input_verified": null, "intent": "click 'Triage'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 40.41691683232784, "point": [85, 214], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [85, 214], "region": [25, 195, 120, 38], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "62ad985d106865db733806d57edba55417e29f24fac074b318afc49b37ce4a9d"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_002"} +{"actuation": "dom", "after_png": "steps/step_003_after.png", "before_png": "steps/step_003_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:02.570214+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-8147556fbc0e437a8afd9c14594503fa", "status": "delivered", "target_fingerprint": "5a6131e61d5decf9bf8d4da6f4b65937279a6f117e3e2e8005564e664078cfa0"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 505.71208307519555, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 3, "input_retried": false, "input_verified": null, "intent": "click at (480, 268)", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 26.378875132650137, "point": [480, 268], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [480, 268], "region": [24, 260, 912, 17], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "5a6131e61d5decf9bf8d4da6f4b65937279a6f117e3e2e8005564e664078cfa0"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_003"} +{"actuation": null, "after_png": "steps/step_004_after.png", "before_png": "steps/step_004_before.png", "delivery_receipt": null, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": [], "effect_evidence": [], "effect_results": [], "effect_verified": null, "elapsed_ms": 523.2460000552237, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": null, "index": 4, "input_retried": false, "input_verified": true, "intent": "type ", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": null, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_004"} +{"actuation": "dom", "after_png": "steps/step_005_after.png", "before_png": "steps/step_005_before.png", "delivery_receipt": {"delivered_at": "2026-07-26T07:07:03.614369+00:00", "native": false, "operation": "dom_click", "outcome_verified": false, "receipt_id": "playwright-5e143e9b834545e3b552454afc55ca36", "status": "delivered", "target_fingerprint": "e9d250f1586b9b1217a0f5dd97226dde586d795601d6fbd899a27a760e19ab1b"}, "delivery_uncertainty": null, "drift_oracle_calls": 0, "effect_approved_unverified": false, "effect_contract_hashes": ["sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053"], "effect_evidence": [{"effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}, {"effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", "final_verdict": "confirmed", "initial_verdict": "confirmed", "reconciliation_actions": 0, "reconciliation_completed": false, "substrate": "rest", "verification_tier": 1}], "effect_results": ["[rest] record_written: CONFIRMED \u2014 exactly 1 record(s) match the target selector", "[rest] field_equals: CONFIRMED \u2014 field 'note' equals the expected value"], "effect_verified": true, "elapsed_ms": 1162.1759592089802, "error": null, "exception_handled": false, "failure_category": null, "heal": null, "identity": {"coverage": 1.0, "expected": "", "mode": "structured", "observed": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "param": null, "quorum_required": null, "quorum_verified": null, "signal_evidence": [], "status": "verified"}, "index": 5, "input_retried": false, "input_verified": null, "intent": "click 'Save Encounter'", "interstitial_actions": [], "ok": true, "postcondition_drift_rescues": [], "postconditions_ok": true, "resolution": {"confidence": 1.0, "elapsed_ms": 30.784916132688522, "point": [134, 457], "rung": "structural", "structural_handle": {"candidate_count": 1, "confidence": 1.0, "point": [134, 457], "region": [24, 437, 220, 40], "supported_operations": ["dom_click", "dom_double_click"], "target_fingerprint": "e9d250f1586b9b1217a0f5dd97226dde586d795601d6fbd899a27a760e19ab1b"}}, "safety_halt": false, "schema_version": "openadapt.public-demo-run-event/v1", "skipped": false, "step_id": "step_005"} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/oracle.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/oracle.json new file mode 100644 index 00000000..18e3292d --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/oracle.json @@ -0,0 +1,23 @@ +{ + "observed": "exact_record", + "oracle_kind": "exact_record", + "passed": true, + "read_boundary": "independent from browser pixels and RunReport", + "read_path": "GET /api/db", + "schema_version": "openadapt.public-demo-oracle/v1", + "silent_incorrect_success": false, + "snapshot": { + "records": [ + { + "id": 1, + "key": "mockmed-triage-p1-v1", + "note": "Synthetic follow-up in two weeks", + "patient_id": "p1", + "source": "replay", + "type": "Triage" + } + ], + "rejected_writes": 0 + }, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/outcome.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/outcome.json new file mode 100644 index 00000000..2ed81732 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/outcome.json @@ -0,0 +1,23 @@ +{ + "browser_request_count": 4, + "case_id": "representative", + "duration_ms": 4697.135458001867, + "execution_completed": true, + "execution_profile": "standard", + "expected_outcome": "VERIFIED", + "failed_step_id": null, + "halt": null, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "VERIFIED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": true, + "report_sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/REPORT.md b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/REPORT.md new file mode 100644 index 00000000..6aeb1c44 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/REPORT.md @@ -0,0 +1,111 @@ +# ✅ mockmed-triage — VERIFIED + +- **Started:** 2026-07-26T07:06:59.747857+00:00 +- **Execution profile:** `standard` (production-eligible) +- **Required contracts passed:** authorization 1/1, identity 5/5, postcondition 8/8, effect 2/2 +- **Evidence classes:** `authorization`, `effect_tier_1`, `identity`, `postcondition` +- **Model calls:** 0 +- **External network calls:** `observed` +- **Steps:** 6/6 ok +- **Heals:** 0 +- **Screenshot egress:** none observed (zero screenshots left the box) +- **Governed authorization:** `1f532e2a67294d7ea6667fdbcbea91ba` (public-demo-qualified-campaign) +- **Admitted policy:** clinical-write; runtime inputs bound to `342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1` + +## Parameters + +| Param | Value | +| --- | --- | +| `note` | Synthetic follow-up in two weeks | + +## Identity protection coverage + +**5 of 5 click steps identity-armed.** Unarmed clicks proceed with **no identity verification** (see docs/LIMITS.md). + +## Effect verification (system of record) + +**1 of 6 executed step(s) carried a system-of-record effect contract** — 1 confirmed, 0 halted, 0 approved-unverified. Steps without a contract have only screen evidence for their local step outcome (run `openadapt-flow lint` for the bundle's per-consequential-step effect coverage). + +## Steps + +| # | Step | Intent | Rung | Confidence | Verified | ms | Healed | OK | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| 1 | `step_000` | click 'Open' | structural | 1.00 | id ✓ | 1005 | | ✅ | +| 2 | `step_001` | click 'New Encounter' | structural | 1.00 | id ✓ | 977 | | ✅ | +| 3 | `step_002` | click 'Triage' | structural | 1.00 | id ✓ | 520 | | ✅ | +| 4 | `step_003` | click at (480, 268) | structural | 1.00 | id ✓ | 506 | | ✅ | +| 5 | `step_004` | type | — | — | input ✓ | 523 | | ✅ | +| 6 | `step_005` | click 'Save Encounter' | structural | 1.00 | id ✓, effect ✓ | 1162 | | ✅ | + +## Per-step evidence + +Every step below shows the frame **before** and **after** the action next to the resolution rung, the identity-gate and effect-check verdicts, and whether the step healed or halted. The generator links only retained run artifacts and never synthesizes pixels. If image redaction was enabled when a frame was persisted, that redaction is already burned into its pixels; a frame the run did not retain is marked _not retained_. + +### 1. `step_000` — click 'Open' + +**Rung** `structural` (conf 1.00, resolved (776, 186)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_000 before](steps/step_000_before.png) | ![step_000 after](steps/step_000_after.png) | + +### 2. `step_001` — click 'New Encounter' + +**Rung** `structural` (conf 1.00, resolved (114, 159)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_001 before](steps/step_001_before.png) | ![step_001 after](steps/step_001_after.png) | + +### 3. `step_002` — click 'Triage' + +**Rung** `structural` (conf 1.00, resolved (85, 214)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_002 before](steps/step_002_before.png) | ![step_002 after](steps/step_002_after.png) | + +### 4. `step_003` — click at (480, 268) + +**Rung** `structural` (conf 1.00, resolved (480, 268)) · **Gates** id ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_003 before](steps/step_003_before.png) | ![step_003 after](steps/step_003_after.png) | + +### 5. `step_004` — type + +**Rung** — (keyboard / wait step, no anchor) · **Gates** input ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_004 before](steps/step_004_before.png) | ![step_004 after](steps/step_004_after.png) | + +### 6. `step_005` — click 'Save Encounter' (final step) + +**Rung** `structural` (conf 1.00, resolved (134, 457)) · **Gates** id ✓, effect ✓ · **Heal** none · **Outcome** ✅ ok + +| Before | After | +| --- | --- | +| ![step_005 before](steps/step_005_before.png) | ![step_005 after](steps/step_005_after.png) | + +## Rung histogram + +| Rung | Count | | +| --- | --- | --- | +| `template` | 0 | | +| `template_global` | 0 | | +| `ocr` | 0 | | +| `geometry` | 0 | | +| `grounder` | 0 | | +| `structural` | 5 | █████ | + +## Totals + +| Metric | Value | +| --- | --- | +| Total time | 4697 ms | +| Steps ok | 6/6 | +| Heals | 0 | +| model_calls | 0 | +| est_model_cost_usd | $0.0000 | diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/_manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/_manifest.json new file mode 100644 index 00000000..08bc4bf7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/_manifest.json @@ -0,0 +1,33 @@ +{ + "schema_version": 1, + "run_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "workflow_name": "mockmed-triage", + "bundle_dir": "/private/tmp/openadapt-flow-pr253-source/public-demo/evidence-packs/.mockmed-triage-v3.6o0oosjc/artifacts/bundle", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "worklists": {}, + "governed_authorization": { + "authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "created_at": "2026-07-26T07:06:59.747118+00:00", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "admitted_policy_name": "clinical-write", + "execution_profile": "standard", + "minimum_effect_tier": 1, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "unverified_write_approvals": [], + "approval_source": "public-demo-qualified-campaign" + }, + "screenshots_may_leave_box": false, + "model_calls": 0, + "external_network_calls": "observed", + "save_healed_to": null, + "created_at": "2026-07-26T07:06:59.749913+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0000_step_000.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0000_step_000.json new file mode 100644 index 00000000..79bb1eaf --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0000_step_000.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 0, + "step_id": "step_000", + "intent": "click 'Open'", + "state_id": null, + "next_step_index": 1, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 38.53337489999831, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "6d292b01ae1b623fdeddd0673d8c3fb085066c941955d687e87585a4c908ea93", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:00.755130+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0001_step_001.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0001_step_001.json new file mode 100644 index 00000000..0fb14166 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0001_step_001.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 1, + "step_id": "step_001", + "intent": "click 'New Encounter'", + "state_id": null, + "next_step_index": 2, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 33.05812506005168, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "ebf0b3ba1ecee8d23172318d2021f723d2e48ca78584b9f5ca35c94df7ff07d1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:01.732404+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0002_step_002.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0002_step_002.json new file mode 100644 index 00000000..6d3c3f83 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0002_step_002.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 2, + "step_id": "step_002", + "intent": "click 'Triage'", + "state_id": null, + "next_step_index": 3, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 40.41691683232784, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "62ad985d106865db733806d57edba55417e29f24fac074b318afc49b37ce4a9d", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:02.253601+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0003_step_003.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0003_step_003.json new file mode 100644 index 00000000..94313ab1 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0003_step_003.json @@ -0,0 +1,64 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 3, + "step_id": "step_003", + "intent": "click at (480, 268)", + "state_id": null, + "next_step_index": 4, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 26.378875132650137, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "5a6131e61d5decf9bf8d4da6f4b65937279a6f117e3e2e8005564e664078cfa0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:02.759779+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0004_step_004.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0004_step_004.json new file mode 100644 index 00000000..3a5ba5b4 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0004_step_004.json @@ -0,0 +1,27 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 4, + "step_id": "step_004", + "intent": "type ", + "state_id": null, + "next_step_index": 5, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": null, + "effect_approved_unverified": false, + "effect_contract_hashes": [], + "effect_evidence": [], + "identity": null, + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": null, + "delivery_uncertainty": null, + "resolution": null, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:03.283476+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0005_step_005.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0005_step_005.json new file mode 100644 index 00000000..2ea30cf8 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/checkpoints/step_0005_step_005.json @@ -0,0 +1,86 @@ +{ + "schema_version": 1, + "workflow_name": "mockmed-triage", + "step_index": 5, + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "state_id": null, + "next_step_index": 6, + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "effect_verified": true, + "effect_approved_unverified": false, + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "postconditions_ok": true, + "skipped": false, + "actuation": "dom", + "delivery_uncertainty": null, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 30.784916132688522, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "e9d250f1586b9b1217a0f5dd97226dde586d795601d6fbd899a27a760e19ab1b", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "drift_oracle_calls": 0, + "heal": null, + "created_at": "2026-07-26T07:07:04.446761+00:00" +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/report.json new file mode 100644 index 00000000..c01b841e --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/report.json @@ -0,0 +1,508 @@ +{ + "workflow_name": "mockmed-triage", + "started_at": "2026-07-26T07:06:59.747857+00:00", + "execution_profile": "standard", + "execution_outcome": "VERIFIED", + "production_eligible": true, + "execution_completed": true, + "outcome_envelope": { + "version": "openadapt.execution-outcome/v1", + "outcome": "VERIFIED", + "profile": "standard", + "production_eligible": true, + "execution_completed": true, + "required_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "passed_contracts": { + "authorization": 1, + "identity": 5, + "postcondition": 8, + "effect": 2 + }, + "evidence_classes": [ + "authorization", + "effect_tier_1", + "identity", + "postcondition" + ], + "model_calls": 0, + "external_network_calls": "observed", + "compensation_actions": 0 + }, + "execution_target_kind": "web", + "execution_origin": "http://127.0.0.1:63394/", + "execution_entry_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "bundle_content_digest": "5ed622b5568dac64e4202dae379835277f954c0b24fb2ead8108f32e1c1ce68e", + "source_recording_sha256": null, + "parameter_schema_sha256": "b9706e023d1b70651493a1b2b68bb1939f7173f74b5e574d4f9fa57acc89fc6d", + "governed_authorization_id": "1f532e2a67294d7ea6667fdbcbea91ba", + "governed_approval_source": "public-demo-qualified-campaign", + "governed_authorization_created_at": "2026-07-26T07:06:59.747118+00:00", + "governed_policy_name": "clinical-write", + "governed_minimum_effect_tier": 1, + "governed_runtime_inputs_digest": "342463e1dfa0e45e5a5dac4c34a3daf2f1499aeeb2fa7eefeb8f0a9a027b3ea1", + "governed_authorized_effect_contracts": {}, + "required_identity_step_ids": [ + "step_000", + "step_001", + "step_002", + "step_003", + "step_005" + ], + "approved_unverified_effect_step_ids": [], + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "results": [ + { + "step_id": "step_000", + "intent": "click 'Open'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "elapsed_ms": 38.53337489999831, + "structural_handle": { + "point": [ + 776, + 186 + ], + "confidence": 1.0, + "region": [ + 731, + 168, + 90, + 36 + ], + "target_fingerprint": "6d292b01ae1b623fdeddd0673d8c3fb085066c941955d687e87585a4c908ea93", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane SampleKnee pain referralHigh", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-43bbd42cf4ec4112aafe8a7ea437439e", + "operation": "dom_click", + "native": false, + "target_fingerprint": "6d292b01ae1b623fdeddd0673d8c3fb085066c941955d687e87585a4c908ea93", + "delivered_at": "2026-07-26T07:07:00.132929+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_000_before.png", + "after_png": "steps/step_000_after.png", + "elapsed_ms": 1004.6848750207573 + }, + { + "step_id": "step_001", + "intent": "click 'New Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "elapsed_ms": 33.05812506005168, + "structural_handle": { + "point": [ + 114, + 159 + ], + "confidence": 1.0, + "region": [ + 24, + 139, + 180, + 40 + ], + "target_fingerprint": "ebf0b3ba1ecee8d23172318d2021f723d2e48ca78584b9f5ca35c94df7ff07d1", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-a237e6aea10547d2a1a15a6669408d43", + "operation": "dom_click", + "native": false, + "target_fingerprint": "ebf0b3ba1ecee8d23172318d2021f723d2e48ca78584b9f5ca35c94df7ff07d1", + "delivered_at": "2026-07-26T07:07:01.077058+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_001_before.png", + "after_png": "steps/step_001_after.png", + "elapsed_ms": 976.6885419376194 + }, + { + "step_id": "step_002", + "intent": "click 'Triage'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "elapsed_ms": 40.41691683232784, + "structural_handle": { + "point": [ + 85, + 214 + ], + "confidence": 1.0, + "region": [ + 25, + 195, + 120, + 38 + ], + "target_fingerprint": "62ad985d106865db733806d57edba55417e29f24fac074b318afc49b37ce4a9d", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-a1514aa3efb34a50b0042be5f8c8fb32", + "operation": "dom_click", + "native": false, + "target_fingerprint": "62ad985d106865db733806d57edba55417e29f24fac074b318afc49b37ce4a9d", + "delivered_at": "2026-07-26T07:07:02.083709+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_002_before.png", + "after_png": "steps/step_002_after.png", + "elapsed_ms": 520.2156249433756 + }, + { + "step_id": "step_003", + "intent": "click at (480, 268)", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "elapsed_ms": 26.378875132650137, + "structural_handle": { + "point": [ + 480, + 268 + ], + "confidence": 1.0, + "region": [ + 24, + 260, + 912, + 17 + ], + "target_fingerprint": "5a6131e61d5decf9bf8d4da6f4b65937279a6f117e3e2e8005564e664078cfa0", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-8147556fbc0e437a8afd9c14594503fa", + "operation": "dom_click", + "native": false, + "target_fingerprint": "5a6131e61d5decf9bf8d4da6f4b65937279a6f117e3e2e8005564e664078cfa0", + "delivered_at": "2026-07-26T07:07:02.570214+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_003_before.png", + "after_png": "steps/step_003_after.png", + "elapsed_ms": 505.71208307519555 + }, + { + "step_id": "step_004", + "intent": "type ", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": null, + "identity": null, + "input_verified": true, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": null, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [], + "effect_evidence": [], + "failure_category": null, + "effect_contract_hashes": [], + "actuation": null, + "delivery_receipt": null, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_004_before.png", + "after_png": "steps/step_004_after.png", + "elapsed_ms": 523.2460000552237 + }, + { + "step_id": "step_005", + "intent": "click 'Save Encounter'", + "ok": true, + "skipped": false, + "exception_handled": false, + "resolution": { + "rung": "structural", + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "elapsed_ms": 30.784916132688522, + "structural_handle": { + "point": [ + 134, + 457 + ], + "confidence": 1.0, + "region": [ + 24, + 437, + 220, + 40 + ], + "target_fingerprint": "e9d250f1586b9b1217a0f5dd97226dde586d795601d6fbd899a27a760e19ab1b", + "candidate_count": 1, + "supported_operations": [ + "dom_click", + "dom_double_click" + ] + } + }, + "identity": { + "status": "verified", + "mode": "structured", + "coverage": 1.0, + "expected": "", + "observed": "Jane Sample — MRN P1 — DOB 1980-01-01", + "param": null, + "signal_evidence": [], + "quorum_required": null, + "quorum_verified": null + }, + "input_verified": null, + "input_retried": false, + "postconditions_ok": true, + "interstitial_actions": [], + "effect_verified": true, + "effect_approved_unverified": false, + "safety_halt": false, + "effect_results": [ + "[rest] record_written: CONFIRMED — exactly 1 record(s) match the target selector", + "[rest] field_equals: CONFIRMED — field 'note' equals the expected value" + ], + "effect_evidence": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "substrate": "rest", + "verification_tier": 1, + "initial_verdict": "confirmed", + "final_verdict": "confirmed", + "reconciliation_completed": false, + "reconciliation_actions": 0 + } + ], + "failure_category": null, + "effect_contract_hashes": [ + "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053" + ], + "actuation": "dom", + "delivery_receipt": { + "status": "delivered", + "receipt_id": "playwright-5e143e9b834545e3b552454afc55ca36", + "operation": "dom_click", + "native": false, + "target_fingerprint": "e9d250f1586b9b1217a0f5dd97226dde586d795601d6fbd899a27a760e19ab1b", + "delivered_at": "2026-07-26T07:07:03.614369+00:00", + "outcome_verified": false + }, + "delivery_uncertainty": null, + "postcondition_drift_rescues": [], + "drift_oracle_calls": 0, + "heal": null, + "error": null, + "before_png": "steps/step_005_before.png", + "after_png": "steps/step_005_after.png", + "elapsed_ms": 1162.1759592089802 + } + ], + "success": true, + "terminal_outcome": null, + "visited_states": [], + "halt": null, + "rung_counts": { + "structural": 5 + }, + "heal_count": 0, + "model_calls": 0, + "external_network_calls": "observed", + "est_model_cost_usd": 0.0, + "total_ms": 4697.135458001867, + "identity_applicable_steps": 5, + "identity_armed_steps": 5, + "identity_unarmed": [], + "screenshots_may_leave_box": false +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_after.png new file mode 100644 index 00000000..c6f8eff9 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_after.png new file mode 100644 index 00000000..a92388db Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_before.png new file mode 100644 index 00000000..fce3734e Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_after.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_before.png new file mode 100644 index 00000000..38206281 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_after.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_before.png new file mode 100644 index 00000000..098240bf Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_after.png new file mode 100644 index 00000000..cb83be08 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_before.png new file mode 100644 index 00000000..a2d2237b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_after.png new file mode 100644 index 00000000..b0feb003 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_before.png new file mode 100644 index 00000000..769d683b Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/cases/representative/trial-03/run/steps/step_005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.html b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.html new file mode 100644 index 00000000..229c0356 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.html @@ -0,0 +1,505 @@ + + + + + +Compiled program — mockmed-triage + + + +
+ + + + + diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.json new file mode 100644 index 00000000..b4c2ead6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/compiled/program-graph.json @@ -0,0 +1,509 @@ +{ + "bundle": { + "action_count": 6, + "api_binding_count": 0, + "contains_phi": false, + "created_at": "2026-07-26T07:06:47.886221+00:00", + "effect_count": 2, + "encrypted": false, + "halt_point_count": 1, + "identity_armed_count": 5, + "identity_unarmed_count": 0, + "irreversible_count": 1, + "is_program": false, + "name": "mockmed-triage", + "params": [ + { + "choices": [], + "example": "Synthetic follow-up in two weeks", + "name": "note", + "required": true, + "secret": false, + "type": "string" + } + ], + "phi_scrubbed": false, + "provenance": { + "certification_status": "certified", + "certified": true, + "compiler_version": "1.23.0", + "content_digest": "c3f3e82732db5dd186289f71ce9f24c13452fa07fddcdfbe8d5d61e4b5281542", + "expires_at": null, + "policy_name": "clinical-write", + "source_recording_sha256": null + }, + "schema_version": 2, + "step_count": 6, + "viewport": [ + 1280, + 800 + ] + }, + "edges": [ + { + "guard": null, + "kind": "sequence", + "label": "", + "source": "step_000", + "target": "step_001" + }, + { + "guard": null, + "kind": "sequence", + "label": "", + "source": "step_001", + "target": "step_002" + }, + { + "guard": null, + "kind": "sequence", + "label": "", + "source": "step_002", + "target": "step_003" + }, + { + "guard": null, + "kind": "sequence", + "label": "", + "source": "step_003", + "target": "step_004" + }, + { + "guard": null, + "kind": "sequence", + "label": "", + "source": "step_004", + "target": "step_005" + }, + { + "guard": null, + "kind": "sequence", + "label": "", + "source": "step_005", + "target": "__end__" + } + ], + "nodes": [ + { + "action": "click", + "api_summary": null, + "badges": [ + "identity gate" + ], + "effects": [], + "guard": null, + "guard_on_unmet": null, + "halts": [], + "has_api_binding": false, + "id": "step_000", + "identity": { + "applicable": true, + "armed": true, + "has_identifier_crop": false, + "has_structured": true, + "phi_free": true, + "reason": null + }, + "index": 0, + "key": null, + "kind": "action", + "outcome": null, + "param": null, + "postconditions": [ + "region_stable", + "text_present" + ], + "reason": "", + "resolution": { + "rungs": [ + { + "detail": "", + "label": "API / tool call", + "name": "api", + "present": false + }, + { + "detail": "#open-p1", + "label": "DOM / accessibility selector", + "name": "structural", + "present": true + }, + { + "detail": "templates/step_000.png", + "label": "Image template match", + "name": "template", + "present": true + }, + { + "detail": "Open", + "label": "OCR text match", + "name": "ocr", + "present": true + }, + { + "detail": "2 landmark(s)", + "label": "Nearby-landmark geometry", + "name": "landmarks", + "present": true + } + ], + "top_rung": "structural" + }, + "risk": "reversible", + "secret": false, + "title": "click 'Open'", + "wait_until": null + }, + { + "action": "click", + "api_summary": null, + "badges": [ + "identity gate" + ], + "effects": [], + "guard": null, + "guard_on_unmet": null, + "halts": [], + "has_api_binding": false, + "id": "step_001", + "identity": { + "applicable": true, + "armed": true, + "has_identifier_crop": false, + "has_structured": true, + "phi_free": true, + "reason": null + }, + "index": 1, + "key": null, + "kind": "action", + "outcome": null, + "param": null, + "postconditions": [ + "region_stable", + "text_present" + ], + "reason": "", + "resolution": { + "rungs": [ + { + "detail": "", + "label": "API / tool call", + "name": "api", + "present": false + }, + { + "detail": "#new-encounter", + "label": "DOM / accessibility selector", + "name": "structural", + "present": true + }, + { + "detail": "templates/step_001.png", + "label": "Image template match", + "name": "template", + "present": true + }, + { + "detail": "New Encounter", + "label": "OCR text match", + "name": "ocr", + "present": true + }, + { + "detail": "2 landmark(s)", + "label": "Nearby-landmark geometry", + "name": "landmarks", + "present": true + } + ], + "top_rung": "structural" + }, + "risk": "reversible", + "secret": false, + "title": "click 'New Encounter'", + "wait_until": null + }, + { + "action": "click", + "api_summary": null, + "badges": [ + "identity gate" + ], + "effects": [], + "guard": null, + "guard_on_unmet": null, + "halts": [], + "has_api_binding": false, + "id": "step_002", + "identity": { + "applicable": true, + "armed": true, + "has_identifier_crop": false, + "has_structured": true, + "phi_free": true, + "reason": null + }, + "index": 2, + "key": null, + "kind": "action", + "outcome": null, + "param": null, + "postconditions": [ + "region_stable" + ], + "reason": "", + "resolution": { + "rungs": [ + { + "detail": "", + "label": "API / tool call", + "name": "api", + "present": false + }, + { + "detail": "#type-triage", + "label": "DOM / accessibility selector", + "name": "structural", + "present": true + }, + { + "detail": "templates/step_002.png", + "label": "Image template match", + "name": "template", + "present": true + }, + { + "detail": "Triage", + "label": "OCR text match", + "name": "ocr", + "present": true + }, + { + "detail": "2 landmark(s)", + "label": "Nearby-landmark geometry", + "name": "landmarks", + "present": true + } + ], + "top_rung": "structural" + }, + "risk": "reversible", + "secret": false, + "title": "click 'Triage'", + "wait_until": null + }, + { + "action": "click", + "api_summary": null, + "badges": [ + "identity gate" + ], + "effects": [], + "guard": null, + "guard_on_unmet": null, + "halts": [], + "has_api_binding": false, + "id": "step_003", + "identity": { + "applicable": true, + "armed": true, + "has_identifier_crop": false, + "has_structured": true, + "phi_free": true, + "reason": null + }, + "index": 3, + "key": null, + "kind": "action", + "outcome": null, + "param": null, + "postconditions": [ + "region_stable" + ], + "reason": "", + "resolution": { + "rungs": [ + { + "detail": "", + "label": "API / tool call", + "name": "api", + "present": false + }, + { + "detail": "#note-label", + "label": "DOM / accessibility selector", + "name": "structural", + "present": true + }, + { + "detail": "templates/step_003.png", + "label": "Image template match", + "name": "template", + "present": true + }, + { + "detail": "", + "label": "OCR text match", + "name": "ocr", + "present": false + }, + { + "detail": "2 landmark(s)", + "label": "Nearby-landmark geometry", + "name": "landmarks", + "present": true + } + ], + "top_rung": "structural" + }, + "risk": "reversible", + "secret": false, + "title": "click target 'Note'", + "wait_until": null + }, + { + "action": "type", + "api_summary": null, + "badges": [], + "effects": [], + "guard": null, + "guard_on_unmet": null, + "halts": [], + "has_api_binding": false, + "id": "step_004", + "identity": { + "applicable": false, + "armed": null, + "has_identifier_crop": false, + "has_structured": false, + "phi_free": false, + "reason": null + }, + "index": 4, + "key": null, + "kind": "action", + "outcome": null, + "param": "note", + "postconditions": [], + "reason": "", + "resolution": null, + "risk": "reversible", + "secret": false, + "title": "type ", + "wait_until": null + }, + { + "action": "click", + "api_summary": null, + "badges": [ + "irreversible", + "identity gate", + "effect check" + ], + "effects": [ + { + "kind": "record_written", + "needs_operator_confirmation": false, + "risk": "irreversible", + "summary": "exactly 1 record(s) where patient_id=p1, type=Triage, source=replay, key=mockmed-triage-p1-v1" + }, + { + "kind": "field_equals", + "needs_operator_confirmation": false, + "risk": "irreversible", + "summary": "record field note == Synthetic follow-up in two weeks" + } + ], + "guard": null, + "guard_on_unmet": null, + "halts": [ + "halts if the system-of-record effect is not confirmed" + ], + "has_api_binding": false, + "id": "step_005", + "identity": { + "applicable": true, + "armed": true, + "has_identifier_crop": false, + "has_structured": true, + "phi_free": true, + "reason": null + }, + "index": 5, + "key": null, + "kind": "action", + "outcome": null, + "param": null, + "postconditions": [ + "region_stable", + "text_present" + ], + "reason": "", + "resolution": { + "rungs": [ + { + "detail": "", + "label": "API / tool call", + "name": "api", + "present": false + }, + { + "detail": "#save-encounter", + "label": "DOM / accessibility selector", + "name": "structural", + "present": true + }, + { + "detail": "templates/step_005.png", + "label": "Image template match", + "name": "template", + "present": true + }, + { + "detail": "Save Encounter", + "label": "OCR text match", + "name": "ocr", + "present": true + }, + { + "detail": "2 landmark(s)", + "label": "Nearby-landmark geometry", + "name": "landmarks", + "present": true + } + ], + "top_rung": "structural" + }, + "risk": "irreversible", + "secret": false, + "title": "click 'Save Encounter'", + "wait_until": null + }, + { + "action": null, + "api_summary": null, + "badges": [], + "effects": [], + "guard": null, + "guard_on_unmet": null, + "halts": [], + "has_api_binding": false, + "id": "__end__", + "identity": null, + "index": 6, + "key": null, + "kind": "terminal", + "outcome": "success", + "param": null, + "postconditions": [], + "reason": "", + "resolution": null, + "risk": null, + "secret": false, + "title": "Success", + "wait_until": null + } + ], + "spec_version": 1 +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/media/recording.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/media/recording.webm new file mode 100644 index 00000000..1e454e66 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/media/recording.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.control-overlay.v2.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.control-overlay.v2.json new file mode 100644 index 00000000..eacd94c6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.control-overlay.v2.json @@ -0,0 +1,206 @@ +{ + "data_classification": "synthetic", + "duration_ms": 3445, + "events": [ + { + "at_ms": 0, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 0, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278810950.969666, + "observed_at_unix_ms": 1785049598922, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 0 + }, + { + "at_ms": 287, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 1, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278811237.8695, + "observed_at_unix_ms": 1785049599209, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 1 + }, + { + "at_ms": 520, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 2, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278811471.058, + "observed_at_unix_ms": 1785049599442, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 2 + }, + { + "at_ms": 743, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 3, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278811693.916791, + "observed_at_unix_ms": 1785049599665, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 3 + }, + { + "at_ms": 978, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 4, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278811929.100041, + "observed_at_unix_ms": 1785049599900, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 4 + }, + { + "at_ms": 1202, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 5, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278812153.276166, + "observed_at_unix_ms": 1785049600124, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 5 + }, + { + "at_ms": 1695, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 6, + "mode": "demonstration", + "observed_at_monotonic_ms": 1278812645.606083, + "observed_at_unix_ms": 1785049600616, + "phase": "recording", + "presentation": true, + "profile": "demo", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:recording:demonstration:demo:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Watching your demonstration", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Workflow demonstration" + }, + "media_frame_index": 6 + } + ], + "evidence_pack_id": "mockmed-triage-v3", + "media_frame_count": 8, + "media_sha256": "6a15175effc07fa737f3a1c020baa6a13e7548f382cf5f25d419e6ffb64b91bf", + "schema_version": "openadapt.control-overlay-timeline/v2" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.frame-pts-us.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.frame-pts-us.json new file mode 100644 index 00000000..7243ec77 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.frame-pts-us.json @@ -0,0 +1,15 @@ +{ + "frame_count": 8, + "media_sha256": "6a15175effc07fa737f3a1c020baa6a13e7548f382cf5f25d419e6ffb64b91bf", + "presentation_times_us": [ + 0, + 287000, + 520000, + 743000, + 978000, + 1202000, + 1695000, + 3445000 + ], + "schema_version": "openadapt.media-frame-presentation-times/v1" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.webm new file mode 100644 index 00000000..2c12bec7 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/demonstration.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.control-overlay.v2.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.control-overlay.v2.json new file mode 100644 index 00000000..9ae75435 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.control-overlay.v2.json @@ -0,0 +1,66 @@ +{ + "data_classification": "synthetic", + "duration_ms": 2622, + "events": [ + { + "at_ms": 0, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 0, + "mode": "governed", + "observed_at_monotonic_ms": 1278837139.328958, + "observed_at_unix_ms": 1785049625110, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:1:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 1, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 0 + }, + { + "at_ms": 872, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 1, + "mode": "governed", + "observed_at_monotonic_ms": 1278838011.550833, + "observed_at_unix_ms": 1785049625982, + "phase": "halted", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:halted:governed:standard:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Halted instead of guessing", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 1 + } + ], + "evidence_pack_id": "mockmed-triage-v3", + "media_frame_count": 3, + "media_sha256": "59cdce33ff0fbbf0aadc78ebe9eabe6cf189dc7f8aa2e9f2d1724d90cf8270f1", + "schema_version": "openadapt.control-overlay-timeline/v2" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.frame-pts-us.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.frame-pts-us.json new file mode 100644 index 00000000..3f16d2d5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.frame-pts-us.json @@ -0,0 +1,10 @@ +{ + "frame_count": 3, + "media_sha256": "59cdce33ff0fbbf0aadc78ebe9eabe6cf189dc7f8aa2e9f2d1724d90cf8270f1", + "presentation_times_us": [ + 0, + 872000, + 2622000 + ], + "schema_version": "openadapt.media-frame-presentation-times/v1" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.webm new file mode 100644 index 00000000..31197491 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/halted.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.control-overlay.v2.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.control-overlay.v2.json new file mode 100644 index 00000000..1bc1477c --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.control-overlay.v2.json @@ -0,0 +1,637 @@ +{ + "data_classification": "synthetic", + "duration_ms": 6551, + "events": [ + { + "at_ms": 0, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 0, + "mode": "governed", + "observed_at_monotonic_ms": 1278820448.244916, + "observed_at_unix_ms": 1785049608419, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:1:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 1, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 0 + }, + { + "at_ms": 301, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 1, + "mode": "governed", + "observed_at_monotonic_ms": 1278820749.485416, + "observed_at_unix_ms": 1785049608720, + "phase": "executing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:executing:governed:standard:1:6:no-pause:no-resume:no-stop:target-5752cfa3ff1e352a", + "status": "Executing with verification gates", + "step": { + "current": 1, + "total": 6 + }, + "target_tracking": { + "action_kind": "click", + "binding": { + "frame_index": 1, + "kind": "media_frame", + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + "coordinate_space": "top_level_viewport_normalized", + "rect": { + "height": 0.045, + "width": 0.0703125, + "x": 0.57109375, + "y": 0.21 + }, + "source_viewport": { + "device_pixel_ratio": 1.0, + "height_css_px": 800, + "width_css_px": 1280 + } + }, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 1 + }, + { + "at_ms": 544, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 2, + "mode": "governed", + "observed_at_monotonic_ms": 1278820992.708791, + "observed_at_unix_ms": 1785049608963, + "phase": "verifying", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verifying:governed:standard:1:6:no-pause:no-resume:no-stop:no-target", + "status": "Verifying the intended result", + "step": { + "current": 1, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 2 + }, + { + "at_ms": 918, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 3, + "mode": "governed", + "observed_at_monotonic_ms": 1278821366.318333, + "observed_at_unix_ms": 1785049609337, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:2:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 2, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 3 + }, + { + "at_ms": 1204, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 4, + "mode": "governed", + "observed_at_monotonic_ms": 1278821652.634416, + "observed_at_unix_ms": 1785049609623, + "phase": "executing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:executing:governed:standard:2:6:no-pause:no-resume:no-stop:target-07ee8243f8cd5eb2", + "status": "Executing with verification gates", + "step": { + "current": 2, + "total": 6 + }, + "target_tracking": { + "action_kind": "click", + "binding": { + "frame_index": 4, + "kind": "media_frame", + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + "coordinate_space": "top_level_viewport_normalized", + "rect": { + "height": 0.05, + "width": 0.140625, + "x": 0.01875, + "y": 0.17375 + }, + "source_viewport": { + "device_pixel_ratio": 1.0, + "height_css_px": 800, + "width_css_px": 1280 + } + }, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 4 + }, + { + "at_ms": 1577, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 5, + "mode": "governed", + "observed_at_monotonic_ms": 1278822025.608791, + "observed_at_unix_ms": 1785049609996, + "phase": "verifying", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verifying:governed:standard:2:6:no-pause:no-resume:no-stop:no-target", + "status": "Verifying the intended result", + "step": { + "current": 2, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 5 + }, + { + "at_ms": 2074, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 6, + "mode": "governed", + "observed_at_monotonic_ms": 1278822522.579875, + "observed_at_unix_ms": 1785049610493, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:3:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 3, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 6 + }, + { + "at_ms": 2337, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 7, + "mode": "governed", + "observed_at_monotonic_ms": 1278822785.036375, + "observed_at_unix_ms": 1785049610756, + "phase": "executing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:executing:governed:standard:3:6:no-pause:no-resume:no-stop:target-95402457414f9392", + "status": "Executing with verification gates", + "step": { + "current": 3, + "total": 6 + }, + "target_tracking": { + "action_kind": "click", + "binding": { + "frame_index": 7, + "kind": "media_frame", + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + "coordinate_space": "top_level_viewport_normalized", + "rect": { + "height": 0.0475, + "width": 0.09375, + "x": 0.01953125, + "y": 0.24375 + }, + "source_viewport": { + "device_pixel_ratio": 1.0, + "height_css_px": 800, + "width_css_px": 1280 + } + }, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 7 + }, + { + "at_ms": 2566, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 8, + "mode": "governed", + "observed_at_monotonic_ms": 1278823013.956958, + "observed_at_unix_ms": 1785049610985, + "phase": "verifying", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verifying:governed:standard:3:6:no-pause:no-resume:no-stop:no-target", + "status": "Verifying the intended result", + "step": { + "current": 3, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 8 + }, + { + "at_ms": 2597, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 9, + "mode": "governed", + "observed_at_monotonic_ms": 1278823045.397, + "observed_at_unix_ms": 1785049611016, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:4:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 4, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 9 + }, + { + "at_ms": 2853, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 10, + "mode": "governed", + "observed_at_monotonic_ms": 1278823300.825416, + "observed_at_unix_ms": 1785049611272, + "phase": "executing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:executing:governed:standard:4:6:no-pause:no-resume:no-stop:target-d33280c638d0af00", + "status": "Executing with verification gates", + "step": { + "current": 4, + "total": 6 + }, + "target_tracking": { + "action_kind": "click", + "binding": { + "frame_index": 10, + "kind": "media_frame", + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + "coordinate_space": "top_level_viewport_normalized", + "rect": { + "height": 0.02125, + "width": 0.7125, + "x": 0.01875, + "y": 0.325 + }, + "source_viewport": { + "device_pixel_ratio": 1.0, + "height_css_px": 800, + "width_css_px": 1280 + } + }, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 10 + }, + { + "at_ms": 3063, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 11, + "mode": "governed", + "observed_at_monotonic_ms": 1278823511.56175, + "observed_at_unix_ms": 1785049611482, + "phase": "verifying", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verifying:governed:standard:4:6:no-pause:no-resume:no-stop:no-target", + "status": "Verifying the intended result", + "step": { + "current": 4, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 11 + }, + { + "at_ms": 3105, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 12, + "mode": "governed", + "observed_at_monotonic_ms": 1278823553.213166, + "observed_at_unix_ms": 1785049611524, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:5:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 5, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 12 + }, + { + "at_ms": 3217, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 13, + "mode": "governed", + "observed_at_monotonic_ms": 1278823664.748458, + "observed_at_unix_ms": 1785049611636, + "phase": "executing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:executing:governed:standard:5:6:no-pause:no-resume:no-stop:no-target", + "status": "Executing with verification gates", + "step": { + "current": 5, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 13 + }, + { + "at_ms": 3623, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 14, + "mode": "governed", + "observed_at_monotonic_ms": 1278824070.903125, + "observed_at_unix_ms": 1785049612042, + "phase": "verifying", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verifying:governed:standard:5:6:no-pause:no-resume:no-stop:no-target", + "status": "Verifying the intended result", + "step": { + "current": 5, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 14 + }, + { + "at_ms": 3648, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 15, + "mode": "governed", + "observed_at_monotonic_ms": 1278824095.954416, + "observed_at_unix_ms": 1785049612067, + "phase": "observing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:observing:governed:standard:6:6:no-pause:no-resume:no-stop:no-target", + "status": "Observing the application", + "step": { + "current": 6, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 15 + }, + { + "at_ms": 4031, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 16, + "mode": "governed", + "observed_at_monotonic_ms": 1278824479.138208, + "observed_at_unix_ms": 1785049612450, + "phase": "executing", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:executing:governed:standard:6:6:no-pause:no-resume:no-stop:target-43b7cb331c451f85", + "status": "Executing with verification gates", + "step": { + "current": 6, + "total": 6 + }, + "target_tracking": { + "action_kind": "click", + "binding": { + "frame_index": 16, + "kind": "media_frame", + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + "coordinate_space": "top_level_viewport_normalized", + "rect": { + "height": 0.05, + "width": 0.171875, + "x": 0.01875, + "y": 0.54625 + }, + "source_viewport": { + "device_pixel_ratio": 1.0, + "height_css_px": 800, + "width_css_px": 1280 + } + }, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 16 + }, + { + "at_ms": 4372, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 17, + "mode": "governed", + "observed_at_monotonic_ms": 1278824820.023, + "observed_at_unix_ms": 1785049612791, + "phase": "verifying", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verifying:governed:standard:6:6:no-pause:no-resume:no-stop:no-target", + "status": "Verifying the intended result", + "step": { + "current": 6, + "total": 6 + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 17 + }, + { + "at_ms": 4801, + "frame": { + "controls": { + "pause": false, + "resume": false, + "stop": false + }, + "event_sequence": 18, + "mode": "governed", + "observed_at_monotonic_ms": 1278825249.558833, + "observed_at_unix_ms": 1785049613220, + "phase": "verified", + "presentation": true, + "profile": "standard", + "schema_version": "openadapt.control-overlay-frame/v2", + "state_id": "visible:verified:governed:standard:no-step:no-total:no-pause:no-resume:no-stop:no-target", + "status": "Outcome verified", + "step": { + "current": null, + "total": null + }, + "target_tracking": null, + "visible": true, + "workflow_label": "Governed workflow" + }, + "media_frame_index": 18 + } + ], + "evidence_pack_id": "mockmed-triage-v3", + "media_frame_count": 20, + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087", + "schema_version": "openadapt.control-overlay-timeline/v2" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.frame-pts-us.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.frame-pts-us.json new file mode 100644 index 00000000..7a3d63cb --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.frame-pts-us.json @@ -0,0 +1,27 @@ +{ + "frame_count": 20, + "media_sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087", + "presentation_times_us": [ + 0, + 301000, + 544000, + 918000, + 1204000, + 1577000, + 2074000, + 2337000, + 2566000, + 2597000, + 2853000, + 3063000, + 3105000, + 3217000, + 3623000, + 3648000, + 4031000, + 4372000, + 4801000, + 6551000 + ], + "schema_version": "openadapt.media-frame-presentation-times/v1" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.webm b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.webm new file mode 100644 index 00000000..43502e4c Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/presentation/verified.webm differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/project.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/project.json new file mode 100644 index 00000000..cc91c3f6 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/project.json @@ -0,0 +1,482 @@ +{ + "action_classifications": { + "step_000": { + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true, + "step_id": "step_000" + }, + "step_001": { + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true, + "step_id": "step_001" + }, + "step_002": { + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true, + "step_id": "step_002" + }, + "step_003": { + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true, + "step_id": "step_003" + }, + "step_004": { + "classification": "read_only", + "explanation": "reviewed as workflow preparation/navigation with no business-record effect", + "operator_confirmed": true, + "step_id": "step_004" + }, + "step_005": { + "classification": "irreversible", + "explanation": "compiler classified this as an irreversible system-of-record write", + "operator_confirmed": true, + "step_id": "step_005" + } + }, + "cases": [ + { + "description": "Deterministic ambiguity refusal case", + "expected_outcome": "halted", + "id": "fault-ambiguity", + "input_ref": null, + "kind": "ambiguity", + "required": true, + "results": [ + { + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "3FxUdj1qDIf5M+v/u8dsoGhLqnAGTvlNwEKJtRNJAlbF0/nl7cG7/q4B+N8rdkbI+0UYyOMAJs1XBNze7QtJDA==", + "case_id": "fault-ambiguity", + "completed_at": "2026-07-26T07:07:09.351773+00:00", + "detail_code": "fault-ambiguity.three-trial-contract", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "evidence": [ + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-ambiguity/trial-01/run/report.json", + "sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-ambiguity/trial-02/run/report.json", + "sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-ambiguity/trial-03/run/report.json", + "sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-ambiguity/trial-01/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-ambiguity/trial-02/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-ambiguity/trial-03/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + } + ], + "observed_outcome": "halted", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runner_id": "openadapt-flow/public-demo-headless", + "runtime_version": "1.23.0", + "status": "passed", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + } + ] + }, + { + "description": "Deterministic wrong identity refusal case", + "expected_outcome": "halted", + "id": "fault-wrong-identity", + "input_ref": null, + "kind": "wrong_identity", + "required": true, + "results": [ + { + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "8fGOaHpgsPsyJCCjB2DYjAGfOcMKq/JAq4bfC98fqqZ672iDXprpUxDaQbv+x5kGK/9AGTpX33oUN+viE815BA==", + "case_id": "fault-wrong-identity", + "completed_at": "2026-07-26T07:07:13.536333+00:00", + "detail_code": "fault-wrong-identity.three-trial-contract", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "evidence": [ + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-01/run/report.json", + "sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-02/run/report.json", + "sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-03/run/report.json", + "sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-01/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-02/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-wrong-identity/trial-03/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + } + ], + "observed_outcome": "halted", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runner_id": "openadapt-flow/public-demo-headless", + "runtime_version": "1.23.0", + "status": "passed", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + } + ] + }, + { + "description": "Deterministic stale identity refusal case", + "expected_outcome": "halted", + "id": "fault-stale-identity", + "input_ref": null, + "kind": "stale_identity", + "required": true, + "results": [ + { + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "5PiFmo+xxxXZEmqc2pTfSqyJ3mN0cQ/RFZwJ+0eKcF0rZq4VrSlUbdYkZvsBvFg6hH618Tr8XN4UEJ81JNpCBA==", + "case_id": "fault-stale-identity", + "completed_at": "2026-07-26T07:07:17.886852+00:00", + "detail_code": "fault-stale-identity.three-trial-contract", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "evidence": [ + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-stale-identity/trial-01/run/report.json", + "sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-stale-identity/trial-02/run/report.json", + "sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-stale-identity/trial-03/run/report.json", + "sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-stale-identity/trial-01/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-stale-identity/trial-02/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-stale-identity/trial-03/oracle.json", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + } + ], + "observed_outcome": "halted", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runner_id": "openadapt-flow/public-demo-headless", + "runtime_version": "1.23.0", + "status": "passed", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + } + ] + }, + { + "description": "Deterministic weak effect refusal case", + "expected_outcome": "halted", + "id": "fault-weak-effect", + "input_ref": null, + "kind": "weak_effect", + "required": true, + "results": [ + { + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "9IcpvCPGR1iSQhJ4T/yd2b6ZkAixxK6Nh7FaHMJyGCE9hruAgKNA4oV+ipjqs/7Xi9EPwDARE93afyrOCjM7DQ==", + "case_id": "fault-weak-effect", + "completed_at": "2026-07-26T07:07:50.021545+00:00", + "detail_code": "fault-weak-effect.three-trial-contract", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "evidence": [ + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-weak-effect/trial-01/run/report.json", + "sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-weak-effect/trial-02/run/report.json", + "sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-weak-effect/trial-03/run/report.json", + "sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-weak-effect/trial-01/oracle.json", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-weak-effect/trial-02/oracle.json", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-weak-effect/trial-03/oracle.json", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + } + ], + "observed_outcome": "halted", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runner_id": "openadapt-flow/public-demo-headless", + "runtime_version": "1.23.0", + "status": "passed", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + } + ] + }, + { + "description": "Deterministic missing effect refusal case", + "expected_outcome": "halted", + "id": "fault-missing-effect", + "input_ref": null, + "kind": "missing_effect", + "required": true, + "results": [ + { + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "tXrlXALnWjNaOmiTvcXg+vYXhfAMYTwv61D9izyve9ou7rTNvXoDaNANxfziO+urVngZZHx+XDBO5dqSeTVqBQ==", + "case_id": "fault-missing-effect", + "completed_at": "2026-07-26T07:08:22.706051+00:00", + "detail_code": "fault-missing-effect.three-trial-contract", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "evidence": [ + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-missing-effect/trial-01/run/report.json", + "sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-missing-effect/trial-02/run/report.json", + "sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/fault-missing-effect/trial-03/run/report.json", + "sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-missing-effect/trial-01/oracle.json", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-missing-effect/trial-02/oracle.json", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/fault-missing-effect/trial-03/oracle.json", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + } + ], + "observed_outcome": "halted", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runner_id": "openadapt-flow/public-demo-headless", + "runtime_version": "1.23.0", + "status": "passed", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + } + ] + }, + { + "description": "Recorded workflow under its qualified application boundary", + "expected_outcome": "verified", + "id": "representative", + "input_ref": null, + "kind": "representative", + "required": true, + "results": [ + { + "attestation_key_id": "public-demo-headless-runner", + "attestation_signature": "4soLZkZwxanR4v+IOFpB+j4BYrACmiRw65IytqbXfrP90ep4ckbpH0lyuqxd6W0eR7O//V8bWyob48ai7q6WCw==", + "case_id": "representative", + "completed_at": "2026-07-26T07:07:04.683125+00:00", + "detail_code": "representative.three-trial-contract", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "evidence": [ + { + "kind": "run_report", + "relative_path": "artifacts/cases/representative/trial-01/run/report.json", + "sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/representative/trial-02/run/report.json", + "sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7" + }, + { + "kind": "run_report", + "relative_path": "artifacts/cases/representative/trial-03/run/report.json", + "sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/representative/trial-01/oracle.json", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/representative/trial-02/oracle.json", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "kind": "effect", + "relative_path": "artifacts/cases/representative/trial-03/oracle.json", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + } + ], + "observed_outcome": "verified", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "runner_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runner_id": "openadapt-flow/public-demo-headless", + "runtime_version": "1.23.0", + "status": "passed", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + } + ] + } + ], + "created_at": "2026-07-26T07:06:47.897989+00:00", + "effect_policies": [ + { + "effect_contract_hash": "sha256:de1ec3dd32c33b1683a590f55d45fea21a5a4290687eac7f350df7842e84815b", + "effect_index": 0, + "step_id": "step_005", + "tier": 1 + }, + { + "effect_contract_hash": "sha256:d267875f80a7e3d05ada9dbae3d761c300ed2c3526bb97266507ec8855d3c053", + "effect_index": 1, + "step_id": "step_005", + "tier": 1 + } + ], + "environment": { + "application": "OpenAdapt MockMed synthetic reference", + "application_version": "sha256:1f4d59153fc6c797d626b27977fa6270ca8b2d9461b23171f9a2b2b571d2a0c1", + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "required_capabilities": [ + "headless_chromium", + "independent_system_of_record", + "playwright_dom" + ], + "runtime_version": "1.23.0", + "target_kind": "web" + }, + "exclusions": [], + "identity_policies": { + "step_005": { + "enforcement": "canonical_ladder", + "quorum": 0, + "signals": [], + "step_id": "step_005" + } + }, + "last_certification": { + "certified_at": "2026-07-26T07:08:22.726699+00:00", + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "passed": true, + "policy_name": "clinical-write", + "project_contract_sha256": "4148d3653bf47bb06ce61bbdc1873a87e0805334576be41b534a430beb2e0abf", + "project_revision": 12, + "report_sha256": "31b3f312109a6e9e8dd2cbffd318a4900433965434128ff6e869878b5eaf17f3", + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c" + }, + "minimum_effect_tier": 1, + "previous_revision_sha256": "bb4f26895f8d03914294e4ca03db90b852214834b03078a5c380028798a5f392", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "requalification_conditions": [], + "revision": 12, + "schema_version": "openadapt.qualification-project/v1", + "trusted_runner_keys": { + "public-demo-headless-runner": "dmz7CT1Jv+6Gl7W3yJZs+65RzGz5ysq4bZ27Rr3DW58=" + }, + "updated_at": "2026-07-26T07:08:22.716689+00:00" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/report.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/report.json new file mode 100644 index 00000000..616cdc28 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/qualification/report.json @@ -0,0 +1,21 @@ +{ + "action_count": 6, + "case_count": 6, + "consequential_action_count": 1, + "effect_covered_action_count": 1, + "effect_required_action_count": 1, + "environment_contract_sha256": "b9625879c7aca502f246c91da64eed07ed08629f0e95a682831ae389f1282723", + "generated_at": "2026-07-26T07:08:22.726542+00:00", + "identity_covered_action_count": 1, + "minimum_effect_tier": 1, + "passed": true, + "passed_case_count": 6, + "policy_name": "clinical-write", + "project_id": "a7355d64-6635-4930-965e-fd1b975ececc", + "project_revision": 12, + "refusals": [], + "schema_version": "openadapt.qualification-report/v1", + "state_changing_action_count": 0, + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "workflow_name": "mockmed-triage" +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/events.jsonl b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/events.jsonl new file mode 100644 index 00000000..54d049df --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/events.jsonl @@ -0,0 +1,6 @@ +{"i": 0, "kind": "click", "x": 775, "y": 186, "structural": {"selector": "#open-p1", "role": "button", "name": "Open"}, "structured_identity": "Jane SampleKnee pain referralHigh", "url_before": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", "title_before": "MockMed", "pages_before": 1, "sor_before": [], "url_after": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#patient/p1", "title_after": "MockMed", "pages_after": 1, "sor_after": [], "t": 0.301} +{"i": 1, "kind": "click", "x": 114, "y": 159, "structural": {"selector": "#new-encounter", "role": "button", "name": "New Encounter"}, "structured_identity": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "url_before": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#patient/p1", "title_before": "MockMed", "pages_before": 1, "sor_before": [], "url_after": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_after": "MockMed", "pages_after": 1, "sor_after": [], "t": 0.531} +{"i": 2, "kind": "click", "x": 85, "y": 214, "structural": {"selector": "#type-triage", "role": "button", "name": "Triage"}, "structured_identity": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "url_before": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_before": "MockMed", "pages_before": 1, "sor_before": [], "url_after": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_after": "MockMed", "pages_after": 1, "sor_after": [], "t": 0.754} +{"i": 3, "kind": "click", "x": 480, "y": 268, "structural": {"selector": "#note-label", "name": "Note"}, "structured_identity": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "url_before": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_before": "MockMed", "pages_before": 1, "sor_before": [], "url_after": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_after": "MockMed", "pages_after": 1, "sor_after": [], "t": 0.982} +{"i": 4, "kind": "type", "text": "Synthetic follow-up in two weeks", "param": "note", "url_before": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_before": "MockMed", "pages_before": 1, "sor_before": [], "url_after": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_after": "MockMed", "pages_after": 1, "sor_after": [], "t": 1.205} +{"i": 5, "kind": "click", "x": 134, "y": 457, "structural": {"selector": "#save-encounter", "role": "button", "name": "Save Encounter"}, "structured_identity": "Jane Sample \u2014 MRN P1 \u2014 DOB 1980-01-01", "url_before": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#encounter", "title_before": "MockMed", "pages_before": 1, "sor_before": [], "url_after": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#patient/p1", "title_after": "MockMed", "pages_after": 1, "sor_after": [{"id": 1, "patient_id": "p1", "type": "Triage", "note": "Synthetic follow-up in two weeks", "source": "replay", "key": "mockmed-triage-p1-v1"}], "t": 1.439} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_after.png new file mode 100644 index 00000000..fce3734e Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_before.png new file mode 100644 index 00000000..6d0e1e85 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0000_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_after.png new file mode 100644 index 00000000..b151f9fc Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_before.png new file mode 100644 index 00000000..fce3734e Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0001_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_after.png new file mode 100644 index 00000000..4ce8f845 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_before.png new file mode 100644 index 00000000..b151f9fc Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0002_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_after.png new file mode 100644 index 00000000..a717f109 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_before.png new file mode 100644 index 00000000..4ce8f845 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0003_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_after.png new file mode 100644 index 00000000..ed5f5e2d Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_before.png new file mode 100644 index 00000000..a717f109 Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0004_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_after.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_after.png new file mode 100644 index 00000000..1bb1977f Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_after.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_before.png b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_before.png new file mode 100644 index 00000000..ed5f5e2d Binary files /dev/null and b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/frames/0005_before.png differ diff --git a/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/meta.json b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/meta.json new file mode 100644 index 00000000..99518ba7 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/artifacts/recording/meta.json @@ -0,0 +1,13 @@ +{ + "id": "3290705d23254d978c7a335776e407ad", + "created_at": "2026-07-26T07:06:40.616887+00:00", + "viewport": [ + 1280, + 800 + ], + "app_url": "http://127.0.0.1:63394/?fault=ok&idempotency=demo#tasks", + "params": { + "note": "Synthetic follow-up in two weeks" + }, + "secret_params": [] +} \ No newline at end of file diff --git a/public-demo/evidence-packs/mockmed-triage-v3/manifest.json b/public-demo/evidence-packs/mockmed-triage-v3/manifest.json new file mode 100644 index 00000000..62f82f81 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/manifest.json @@ -0,0 +1,4253 @@ +{ + "artifacts": { + "cases": [ + { + "case_id": "representative", + "events": [ + { + "bytes": 10080, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/representative/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "16c457b60fed99b9e8e77ac449f30e3d2c9bab20302bec9a094f5809bf935b68" + }, + { + "bytes": 10080, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/representative/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "911084d767b52fcb9955a9a3b52e64848aa2d444cd263b116e0b7636b263adf6" + }, + { + "bytes": 10081, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/representative/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "7204bc6d968bee2932fc83a8701ca763e32699c4547a8ab0cc88fd7741dd1dc8" + } + ], + "expected_outcome": "VERIFIED", + "kind": "representative", + "media": { + "bytes": 123995, + "media_type": "video/webm", + "path": "artifacts/cases/representative/trial-01/replay.webm", + "role": "media", + "sha256": "b84184382c9cfeeb733776a2be72d242c7b21d5e6c2e4e7b249b897e5e5c73bd" + }, + "oracles": [ + { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + } + ], + "outcome_envelopes": [ + { + "bytes": 743, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "9fe5537806507fe364e32683b9fc39b17bfd996ffbaae221ff3ecacc37514a89" + }, + { + "bytes": 744, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "7e035ce556cbaa0b810d5e0d7164f8739956ab0b523803e87aea8920cbdc0643" + }, + { + "bytes": 743, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "dd3e5b88e62166a75c11bbc91d0f0015b9bc489d078649a8e529a07ab134a5e1" + } + ], + "outcomes": [ + { + "browser_request_count": 4, + "case_id": "representative", + "duration_ms": 4820.507416967303, + "execution_completed": true, + "execution_profile": "standard", + "expected_outcome": "VERIFIED", + "failed_step_id": null, + "halt": null, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "VERIFIED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": true, + "report_sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false + }, + { + "browser_request_count": 4, + "case_id": "representative", + "duration_ms": 4706.6427080426365, + "execution_completed": true, + "execution_profile": "standard", + "expected_outcome": "VERIFIED", + "failed_step_id": null, + "halt": null, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "VERIFIED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": true, + "report_sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false + }, + { + "browser_request_count": 4, + "case_id": "representative", + "duration_ms": 4697.135458001867, + "execution_completed": true, + "execution_profile": "standard", + "expected_outcome": "VERIFIED", + "failed_step_id": null, + "halt": null, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "VERIFIED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": true, + "report_sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false + } + ], + "poster": { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + "reports": [ + { + "bytes": 15430, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf" + }, + { + "bytes": 15431, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7" + }, + { + "bytes": 15431, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c" + } + ] + }, + { + "case_id": "fault-ambiguity", + "events": [ + { + "bytes": 926, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-ambiguity/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "a9dcbd93f5fb329c837a99aa38f53037c5289989859232e3e837e4773aee9181" + }, + { + "bytes": 925, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-ambiguity/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "01c775093f426afefc07258e38c2f6c54986a8856c1d271bef6102f35691f06d" + }, + { + "bytes": 926, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-ambiguity/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "754f8fb53a577102e7d788ca9dcff5eb3ad1e1259b6a838ffc418d40219d4daf" + } + ], + "expected_outcome": "HALTED", + "kind": "ambiguity", + "media": { + "bytes": 38646, + "media_type": "video/webm", + "path": "artifacts/cases/fault-ambiguity/trial-01/halt.webm", + "role": "media", + "sha256": "021e51c33ea6275b7013db0a727ffb2deb98fe8778bd3b529ebf97184f6c8247" + }, + "oracles": [ + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + } + ], + "outcome_envelopes": [ + { + "bytes": 1423, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "8cb4a9ee3f4e9a07c58dd162df3f71d0fe877b8e3e78658fba0b5181fad8dfb6" + }, + { + "bytes": 1423, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "3493370d319101ec7dd1f9b8c0f28864f2ec66d3a240c42b4f5c1eb3f993ab63" + }, + { + "bytes": 1422, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "9a738876e3210993d1f6a6afc2fc8ac898a5230e2143b46180f93d1903db420f" + } + ], + "outcomes": [ + { + "browser_request_count": 3, + "case_id": "fault-ambiguity", + "duration_ms": 158.78204093314707, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false + }, + { + "browser_request_count": 3, + "case_id": "fault-ambiguity", + "duration_ms": 154.73504201509058, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false + }, + { + "browser_request_count": 3, + "case_id": "fault-ambiguity", + "duration_ms": 180.2768751513213, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "JaneSample", + "Knee painreferral", + "High", + "Open", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Structural safety refusal for step 'step_000' (click 'Open'): DOM locator is ambiguous: candidate_count=2 — no action was admitted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false + } + ], + "poster": { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + "reports": [ + { + "bytes": 4001, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e" + }, + { + "bytes": 4000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe" + }, + { + "bytes": 4000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5" + } + ] + }, + { + "case_id": "fault-wrong-identity", + "events": [ + { + "bytes": 1511, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-wrong-identity/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "17cb06e6e6c454cd5a646c09a3a2f84a6681ebb6615ac30c1320f4e6db7e26fb" + }, + { + "bytes": 1511, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-wrong-identity/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "ce5dbf2378ebee2bb99ad87cc405cf635e092321b09d954b71bf476dc4544dcf" + }, + { + "bytes": 1510, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-wrong-identity/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "ae6393fd33a83b3524fb55080dca38ed1fe7c853f61f5e7a89737e86d0f99921" + } + ], + "expected_outcome": "HALTED", + "kind": "wrong_identity", + "media": { + "bytes": 40123, + "media_type": "video/webm", + "path": "artifacts/cases/fault-wrong-identity/trial-01/halt.webm", + "role": "media", + "sha256": "987ddf3f74b26102e6877de45b2ad4f558b643062253c5fa5058cb8b2490f146" + }, + "oracles": [ + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + } + ], + "outcome_envelopes": [ + { + "bytes": 1653, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "a1987aeb639d36a8b346e48e4762f4767ecc97d5c8fc5f164c83ed0d5ea6e951" + }, + { + "bytes": 1653, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "98b0042e8cbbd25ee9632e5db57bb4206e38005b2420e357d0865db915f85512" + }, + { + "bytes": 1653, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "34d4cbd08fb746e62e765d53a39444403f676361917ce5006e449aca7cfab8aa" + } + ], + "outcomes": [ + { + "browser_request_count": 3, + "case_id": "fault-wrong-identity", + "duration_ms": 167.76495892554522, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false + }, + { + "browser_request_count": 3, + "case_id": "fault-wrong-identity", + "duration_ms": 188.54504101909697, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false + }, + { + "browser_request_count": 3, + "case_id": "fault-wrong-identity", + "duration_ms": 174.04475016519427, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Taylor Duplicate", + "Kneepainreferral", + "High", + "Open", + "JaneSample", + "Knee pain referral", + "AlexTestcase", + "Cardiologyfollow-up", + "Medium", + "Sam Specimen", + "Dermatologyconsult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'template', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Taylor DuplicateKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false + } + ], + "poster": { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + "reports": [ + { + "bytes": 4966, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e" + }, + { + "bytes": 4966, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd" + }, + { + "bytes": 4965, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238" + } + ] + }, + { + "case_id": "fault-stale-identity", + "events": [ + { + "bytes": 1735, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-stale-identity/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "c8765f112880d5bdea2838f358bd8c008437c15667fe8740212607d112f6ba0e" + }, + { + "bytes": 1737, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-stale-identity/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "d037138e6334a61804bf3230eb9d020bb745d7ecb7bbaee1c6f2c8d7639c7e5c" + }, + { + "bytes": 1737, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-stale-identity/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "19aa64247e7bf1fc2fbd99f16f077cbf386c6a328185bfd3a4442dd30733e1ec" + } + ], + "expected_outcome": "HALTED", + "kind": "stale_identity", + "media": { + "bytes": 42450, + "media_type": "video/webm", + "path": "artifacts/cases/fault-stale-identity/trial-01/halt.webm", + "role": "media", + "sha256": "bf4088606ca140b2ee1fe3fc57c693a1e9bb3b199de3e1c5ae9b27fc5739dca7" + }, + "oracles": [ + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + } + ], + "outcome_envelopes": [ + { + "bytes": 1610, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "c4ae9f7ecb4eaf95080f9f91f100a8fb97d5cb2bcda1efc0b6eb451919d88fdd" + }, + { + "bytes": 1610, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "920cd25c90560c2961402a0f5710a47d1149a5e88ce63253a0705f627eed7ee8" + }, + { + "bytes": 1611, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "f57c04fd555b86f6e6b2a0ae77125e0717670e62ea42df387df650798aaef6e0" + } + ], + "outcomes": [ + { + "browser_request_count": 3, + "case_id": "fault-stale-identity", + "duration_ms": 320.0055421330035, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false + }, + { + "browser_request_count": 3, + "case_id": "fault-stale-identity", + "duration_ms": 305.9028328862041, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false + }, + { + "browser_request_count": 3, + "case_id": "fault-stale-identity", + "duration_ms": 299.26454089581966, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_000", + "halt": { + "completed_intents": [], + "intent": "click 'Open'", + "observed_texts": [ + "MockMed", + "Clinical demo —all data is fake", + "Referral Tasks", + "Patient", + "Reason", + "Priority", + "Action", + "Changed Identity", + "Knee pain referral", + "High", + "Open", + "AlexTestcase", + "Cardiology follow-up", + "Medium", + "Sam Specimen", + "Dermatology consult", + "Low" + ], + "outcome": "halt", + "reason": "Identity check failed for step 'step_000' (click 'Open'): a target was found positionally (rung 'structural', confidence 1.00) but its surrounding text does not match the recorded target's — expected '', observed 'Changed IdentityKnee pain referralHigh' (coverage 0.00) — refusing to act; run aborted", + "state_id": "step_000" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false + } + ], + "poster": { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + "reports": [ + { + "bytes": 5333, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e" + }, + { + "bytes": 5335, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047" + }, + { + "bytes": 5336, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8" + } + ] + }, + { + "case_id": "fault-weak-effect", + "events": [ + { + "bytes": 10591, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-weak-effect/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "acb3bcc31a489bd719d098115e9b53305b87d8bff37be4109fc4d7ca69e7b857" + }, + { + "bytes": 10590, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-weak-effect/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "ef206aae2902e32c4942fdd4a50cf08451a7704aee7cf48647bd7ab85d557dfa" + }, + { + "bytes": 10592, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-weak-effect/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "035ad252365df35c1575a353d530fdc321de8f9d6e969d4597f64a9044973175" + } + ], + "expected_outcome": "HALTED", + "kind": "weak_effect", + "media": { + "bytes": 196611, + "media_type": "video/webm", + "path": "artifacts/cases/fault-weak-effect/trial-01/halt.webm", + "role": "media", + "sha256": "6f14e316ffeb24dcb8ce97febc045ae8f251df442680b90f0ff3407be49a0ccc" + }, + "oracles": [ + { + "bytes": 560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "bytes": 560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "bytes": 560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + } + ], + "outcome_envelopes": [ + { + "bytes": 1746, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "adb517d20498f540a459c2fb0193b732c740aa81b8a554a2cf08630de032cf73" + }, + { + "bytes": 1745, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "fddaee34409389259c1437e6f9ac3bae6fb1e5dfa0be48f9a6a44c9718eb8be3" + }, + { + "bytes": 1746, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "2b567a347febee7ff40b626e3379df0772ed2d79be6c4a7be44d81d8e36f6d1c" + } + ], + "outcomes": [ + { + "browser_request_count": 4, + "case_id": "fault-weak-effect", + "duration_ms": 9809.738958021626, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false + }, + { + "browser_request_count": 4, + "case_id": "fault-weak-effect", + "duration_ms": 9462.27787504904, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false + }, + { + "browser_request_count": 4, + "case_id": "fault-weak-effect", + "duration_ms": 9582.309165969491, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): field_equals refuted against the rest system of record and could not be reconciled (escalated) — [rest] field_equals: field 'note' is '', expected 'Synthetic follow-up in two weeks' (the system of record contradicts the declared outcome) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false + } + ], + "poster": { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + "reports": [ + { + "bytes": 16934, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa" + }, + { + "bytes": 16932, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f" + }, + { + "bytes": 16935, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee" + } + ] + }, + { + "case_id": "fault-missing-effect", + "events": [ + { + "bytes": 10175, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-missing-effect/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "b06812e5d70d08f1e0541198384faeed2c6e761195378fc1914e7e7a16931d6b" + }, + { + "bytes": 10173, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-missing-effect/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "4d55ca68adf0f359fe0fa45b804b0e2b8a23a3b088de6412d39050b748285964" + }, + { + "bytes": 10177, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-missing-effect/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "21a6e0b3080e32b46fe0d4b42f0a55038199828491cc317f4e4c25d6b7cfe469" + } + ], + "expected_outcome": "HALTED", + "kind": "missing_effect", + "media": { + "bytes": 196584, + "media_type": "video/webm", + "path": "artifacts/cases/fault-missing-effect/trial-01/halt.webm", + "role": "media", + "sha256": "7eb3a32687049eae20bd4a114d3f7561be77e6c6d0678c38cac4d19d420b2317" + }, + "oracles": [ + { + "bytes": 384, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "bytes": 384, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "bytes": 384, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + } + ], + "outcome_envelopes": [ + { + "bytes": 1768, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "9200874f2a500208b57d4a139e38bfcbe2764ee453bc4d9698a88bbf0f258e14" + }, + { + "bytes": 1767, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "d44ca70b9756bace314bb27a8964d3292079c0702e9448d2f4ba203dd0cceb4e" + }, + { + "bytes": 1768, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "d11a823161311ad40d0d34774c087ed1cf90a60bca1baa7e5aaede75190ba171" + } + ], + "outcomes": [ + { + "browser_request_count": 4, + "case_id": "fault-missing-effect", + "duration_ms": 9635.272833984345, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 1, + "wrong_target_action": false + }, + { + "browser_request_count": 4, + "case_id": "fault-missing-effect", + "duration_ms": 9710.82350006327, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 2, + "wrong_target_action": false + }, + { + "browser_request_count": 4, + "case_id": "fault-missing-effect", + "duration_ms": 9697.530041914433, + "execution_completed": false, + "execution_profile": "standard", + "expected_outcome": "HALTED", + "failed_step_id": "step_005", + "halt": { + "completed_intents": [ + "click 'Open'", + "click 'New Encounter'", + "click 'Triage'", + "click at (480, 268)", + "type " + ], + "intent": "click 'Save Encounter'", + "observed_texts": [ + "MockMed", + "Clinical demo — all data is fake", + "JaneSample—MRNP1—DOB1980-01-01", + "Encountersaved-", + "Syntheticfollow-upin twoweeks", + "NewEncounter", + "Encounters", + "·Triage—Synthetic follow-up in two weeks" + ], + "outcome": "halt", + "reason": "System-of-record effect verification HALTED step 'step_005' (click 'Save Encounter'): record_written refuted against the rest system of record and could not be reconciled (escalated) — [rest] record_written: 0 records match the target selector, expected 1 (missing / phantom / rejected write -- the screen may show success but nothing landed) -- no compensator available for an irreversible refuted effect -- durably halt and escalate — run aborted", + "state_id": "step_005" + }, + "matched_expectation": true, + "model_calls": 0, + "observed_outcome": "HALTED", + "off_box_or_third_party_egress_observed": false, + "oracle_passed": true, + "production_eligible": false, + "report_sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325", + "runtime_network_observation": "observed", + "schema_version": "openadapt.public-demo-outcome/v1", + "screenshots_may_leave_box": false, + "silent_incorrect_success": false, + "trial": 3, + "wrong_target_action": false + } + ], + "poster": { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + "reports": [ + { + "bytes": 16416, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff" + }, + { + "bytes": 16413, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626" + }, + { + "bytes": 16418, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325" + } + ] + } + ], + "compiled": { + "content_digest": "c3f3e82732db5dd186289f71ce9f24c13452fa07fddcdfbe8d5d61e4b5281542", + "program_graph": { + "bytes": 12223, + "media_type": "application/json", + "path": "artifacts/compiled/program-graph.json", + "role": "program_graph", + "sha256": "016e509e71d6f649f8f3ff37e723f551ee0c32e081a1f1fc00713eab6ef3ebe3" + }, + "program_graph_html": { + "bytes": 24900, + "media_type": "text/html", + "path": "artifacts/compiled/program-graph.html", + "role": "program_graph", + "sha256": "15f97a7e127bbea3188f421ffd3b2bc8a18d6bffa0d61e117dabee43da355883" + }, + "workflow": { + "bytes": 57464, + "media_type": "application/json", + "path": "artifacts/bundle/workflow.json", + "role": "compiled_bundle", + "sha256": "1744b74833670792da00b02f61e89506b322864ffcbf31f6c002f456da0d7ace" + }, + "workflow_contract_sha256": "1b94cfe9d2c90e373ad152f14cb9ebc0768a9ce2344d7f99d0f5f7bcb66bb50c", + "workflow_source": { + "bytes": 3268, + "media_type": "text/x-python", + "path": "artifacts/bundle/workflow.py", + "role": "compiled_bundle", + "sha256": "4a90b12d9833ad42d083af10ee889835ecc28ae1558acf7107774a7c4cd57a31" + } + }, + "crop_bindings": [ + { + "crop_path": "artifacts/bundle/templates/step_000.png", + "crop_sha256": "46a75b5d63ceaad4bee942ccf2a6ca3d2b4f6327509df7eff2cc7ddb2c9fd389", + "region": [ + 695, + 154, + 160, + 64 + ], + "source_frame_path": "artifacts/recording/frames/0000_before.png", + "source_frame_sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe", + "step_id": "step_000" + }, + { + "crop_path": "artifacts/bundle/templates/step_001.png", + "crop_sha256": "9d17fc905b1902add82cad885c72fe446a23e0334fc4db58592d2369e85f26a5", + "region": [ + 34, + 127, + 160, + 64 + ], + "source_frame_path": "artifacts/recording/frames/0001_before.png", + "source_frame_sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870", + "step_id": "step_001" + }, + { + "crop_path": "artifacts/bundle/templates/step_002.png", + "crop_sha256": "e6a0e0718b00c26280e32928b744217d00a7e010ab9825da27724e2debc9b805", + "region": [ + 5, + 182, + 160, + 64 + ], + "source_frame_path": "artifacts/recording/frames/0002_before.png", + "source_frame_sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc", + "step_id": "step_002" + }, + { + "crop_path": "artifacts/bundle/templates/step_003.png", + "crop_sha256": "2cb01de3e45c7c6cd6526f1b6f9c1a4f86bee1a5e4f8e3f6fbf7150470cf5f2c", + "region": [ + 400, + 236, + 160, + 64 + ], + "source_frame_path": "artifacts/recording/frames/0003_before.png", + "source_frame_sha256": "8d2d2d2a56a8d089b11f1e97926c06f0c1d7076e080d0ffbd70b0bf1691aeae3", + "step_id": "step_003" + }, + { + "crop_path": "artifacts/bundle/templates/step_005.png", + "crop_sha256": "5d8163520ba8355f44ffe0cd06a26be6bfe5d6660bcff1395dc82d4da3aa0ac1", + "region": [ + 54, + 425, + 160, + 64 + ], + "source_frame_path": "artifacts/recording/frames/0005_before.png", + "source_frame_sha256": "d4da8dbaf7fa257e89d78a08854ccd50c8277c3fcb12efe2614d3fa4508a3026", + "step_id": "step_005" + } + ], + "presentation": { + "demonstration": { + "frame_pts": { + "bytes": 303, + "media_type": "application/json", + "path": "artifacts/presentation/demonstration.frame-pts-us.json", + "role": "evidence", + "sha256": "f6ed892ccc0a64a969ec12ec4a37f87d7cfcad5cafd5e002ff4871aabf626469" + }, + "media": { + "bytes": 77376, + "media_type": "video/webm", + "path": "artifacts/presentation/demonstration.webm", + "role": "media", + "sha256": "6a15175effc07fa737f3a1c020baa6a13e7548f382cf5f25d419e6ffb64b91bf" + }, + "raw_media": { + "bytes": 116411, + "media_type": "video/webm", + "path": "artifacts/media/recording.webm", + "role": "media", + "sha256": "3ac77627340b5f3ef3adc37b9b8f05091bdc886e0d65d2ec2baac9ed591cc438" + }, + "source_kind": "source_recording", + "timeline": { + "bytes": 6341, + "media_type": "application/json", + "path": "artifacts/presentation/demonstration.control-overlay.v2.json", + "role": "evidence", + "sha256": "cfab1104ffaf3726eded86cf0378e5e5d3386802f5bab5b4179cf7a2ac2ead1d" + } + }, + "halted": { + "case_id": "fault-ambiguity", + "frame_pts": { + "bytes": 241, + "media_type": "application/json", + "path": "artifacts/presentation/halted.frame-pts-us.json", + "role": "evidence", + "sha256": "64e5b69483ae0c70a2afb10eebe6e9917cacb2dd766bb672f94424a073240bb2" + }, + "media": { + "bytes": 32237, + "media_type": "video/webm", + "path": "artifacts/presentation/halted.webm", + "role": "media", + "sha256": "59cdce33ff0fbbf0aadc78ebe9eabe6cf189dc7f8aa2e9f2d1724d90cf8270f1" + }, + "oracle": { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + "outcome": { + "bytes": 1423, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "8cb4a9ee3f4e9a07c58dd162df3f71d0fe877b8e3e78658fba0b5181fad8dfb6" + }, + "raw_media": { + "bytes": 38646, + "media_type": "video/webm", + "path": "artifacts/cases/fault-ambiguity/trial-01/halt.webm", + "role": "media", + "sha256": "021e51c33ea6275b7013db0a727ffb2deb98fe8778bd3b529ebf97184f6c8247" + }, + "report": { + "bytes": 4001, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e" + }, + "source_kind": "run", + "timeline": { + "bytes": 1982, + "media_type": "application/json", + "path": "artifacts/presentation/halted.control-overlay.v2.json", + "role": "evidence", + "sha256": "d97b7c13a0724989e292b45a4ea1435338db6889503f06f52e15421e0d3faa7c" + }, + "trial": 1 + }, + "verified": { + "case_id": "representative", + "frame_pts": { + "bytes": 461, + "media_type": "application/json", + "path": "artifacts/presentation/verified.frame-pts-us.json", + "role": "evidence", + "sha256": "821f6c48c2d5cfe00e86a44c886508e258678cb8f863a2dff26f5736dce71674" + }, + "media": { + "bytes": 78310, + "media_type": "video/webm", + "path": "artifacts/presentation/verified.webm", + "role": "media", + "sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + "oracle": { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + "outcome": { + "bytes": 743, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "9fe5537806507fe364e32683b9fc39b17bfd996ffbaae221ff3ecacc37514a89" + }, + "raw_media": { + "bytes": 123995, + "media_type": "video/webm", + "path": "artifacts/cases/representative/trial-01/replay.webm", + "role": "media", + "sha256": "b84184382c9cfeeb733776a2be72d242c7b21d5e6c2e4e7b249b897e5e5c73bd" + }, + "report": { + "bytes": 15430, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf" + }, + "source_kind": "run", + "timeline": { + "bytes": 19324, + "media_type": "application/json", + "path": "artifacts/presentation/verified.control-overlay.v2.json", + "role": "evidence", + "sha256": "5742b18dc4532f6470f41ff9a21baf1dc637d5fab5d484defd36ba542ffd569c" + }, + "trial": 1 + } + }, + "qualification": { + "minimum_effect_tier": 1, + "passed": true, + "project": { + "bytes": 21462, + "media_type": "application/json", + "path": "artifacts/qualification/project.json", + "role": "qualification", + "sha256": "d4a2db89a83f7aa7c28d233903228d82a323a4788b2bf5ea5e9a31a370cf4c78" + }, + "report": { + "bytes": 779, + "media_type": "application/json", + "path": "artifacts/qualification/report.json", + "role": "qualification", + "sha256": "24f34c46f6feff7d2ac369416dda13a193b9487e360ffe7c00b36725474afa3c" + } + }, + "source_recording": { + "events": { + "bytes": 2945, + "media_type": "application/x-ndjson", + "path": "artifacts/recording/events.jsonl", + "role": "source_recording", + "sha256": "c5ab16f16eacf2d81c060084c63ea3a29cc803a14ca4d7bcd5055fa8daadc9fb" + }, + "frame_count": 12, + "media": { + "bytes": 116411, + "media_type": "video/webm", + "path": "artifacts/media/recording.webm", + "role": "media", + "sha256": "3ac77627340b5f3ef3adc37b9b8f05091bdc886e0d65d2ec2baac9ed591cc438" + }, + "meta": { + "bytes": 298, + "media_type": "application/json", + "path": "artifacts/recording/meta.json", + "role": "source_recording", + "sha256": "17494cf94c54918f37e6237b2024809cc53160ec870b357e946149ea1e9183e1" + } + } + }, + "evaluation": { + "browser_request_count": 63, + "case_count": 6, + "caveats": [ + "First-party synthetic MockMed task; not customer production evidence.", + "Bound to the exact app, browser, viewport, runtime, and source commit in this pack.", + "The runtime conservatively records network activity as observed. Every configured and browser-observed destination in this isolated campaign was loopback; no off-box or third-party egress was observed.", + "Three trials per required condition establish this bounded campaign only.", + "The synthetic reference app exposes a stable demo-mode idempotency key so the compiler can retain and verify a real at-most-once contract." + ], + "environment_digest": "bbc33b0e8a54d33979f8ee271758685f907f8f81f5a7f0206d04e421e8a0ce82", + "minimum_effect_tier": 1, + "model_calls": 0, + "off_box_or_third_party_egress_observed": false, + "oracle": { + "kind": "independent_system_of_record", + "summary": "GET /api/db is independent of browser pixels and the runtime report; target state is held in the local MockMed fault server.", + "verification_tier": 1, + "verifier": "openadapt_flow.runtime.effects.rest.RestRecordVerifier" + }, + "outcome_counts": { + "HALTED": 15, + "VERIFIED": 3 + }, + "over_halts": 0, + "passed_contracts": 6, + "qualification_passed": true, + "required_case_kinds": [ + "ambiguity", + "missing_effect", + "representative", + "stale_identity", + "weak_effect", + "wrong_identity" + ], + "required_contracts": 6, + "run_count": 18, + "runtime_network_observation_counts": { + "observed": 18 + }, + "screenshots_may_leave_box": false, + "silent_incorrect_successes": 0, + "total_duration_ms": 74071.55958213843, + "trials_per_case": 3, + "wrong_target_actions": 0 + }, + "files": [ + { + "bytes": 1688, + "media_type": "application/json", + "path": "artifacts/bundle/manifest.json", + "role": "compiled_bundle", + "sha256": "8b304d279409ef6ae384d715274e3ad4bc35be49d2e6a12f918b61da31ba74f0" + }, + { + "bytes": 2505, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_000.png", + "role": "compiled_bundle", + "sha256": "46a75b5d63ceaad4bee942ccf2a6ca3d2b4f6327509df7eff2cc7ddb2c9fd389" + }, + { + "bytes": 21930, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_000_expect.png", + "role": "compiled_bundle", + "sha256": "337e403fec476cc955bcf5f1d96902119d9c2fadc03e201c0c2fbc2475d03646" + }, + { + "bytes": 3116, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_001.png", + "role": "compiled_bundle", + "sha256": "9d17fc905b1902add82cad885c72fe446a23e0334fc4db58592d2369e85f26a5" + }, + { + "bytes": 18546, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_001_expect.png", + "role": "compiled_bundle", + "sha256": "ccbbb335c8160188198df18beb48bd88082b7bb1e5c1cd987d6766afb62c0773" + }, + { + "bytes": 3573, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_002.png", + "role": "compiled_bundle", + "sha256": "e6a0e0718b00c26280e32928b744217d00a7e010ab9825da27724e2debc9b805" + }, + { + "bytes": 5009, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_002_expect.png", + "role": "compiled_bundle", + "sha256": "f66608f19f3acf0ba8d86a39ecdd04781eb320787885039ab1eefee3835c83de" + }, + { + "bytes": 317, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_003.png", + "role": "compiled_bundle", + "sha256": "2cb01de3e45c7c6cd6526f1b6f9c1a4f86bee1a5e4f8e3f6fbf7150470cf5f2c" + }, + { + "bytes": 5686, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_003_expect.png", + "role": "compiled_bundle", + "sha256": "68cd40d6bd0abdf81beb40dd4202bac784a4b55492f803cdd5fb1e7ab8f76941" + }, + { + "bytes": 3250, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_005.png", + "role": "compiled_bundle", + "sha256": "5d8163520ba8355f44ffe0cd06a26be6bfe5d6660bcff1395dc82d4da3aa0ac1" + }, + { + "bytes": 11751, + "media_type": "image/png", + "path": "artifacts/bundle/templates/step_005_expect.png", + "role": "compiled_bundle", + "sha256": "0919dca8fe883ad52eae6359f9da3494cb57c68e006ea4ba314d61e15787ea47" + }, + { + "bytes": 57464, + "media_type": "application/json", + "path": "artifacts/bundle/workflow.json", + "role": "compiled_bundle", + "sha256": "1744b74833670792da00b02f61e89506b322864ffcbf31f6c002f456da0d7ace" + }, + { + "bytes": 3268, + "media_type": "text/x-python", + "path": "artifacts/bundle/workflow.py", + "role": "compiled_bundle", + "sha256": "4a90b12d9833ad42d083af10ee889835ecc28ae1558acf7107774a7c4cd57a31" + }, + { + "bytes": 926, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-ambiguity/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "a9dcbd93f5fb329c837a99aa38f53037c5289989859232e3e837e4773aee9181" + }, + { + "bytes": 38646, + "media_type": "video/webm", + "path": "artifacts/cases/fault-ambiguity/trial-01/halt.webm", + "role": "media", + "sha256": "021e51c33ea6275b7013db0a727ffb2deb98fe8778bd3b529ebf97184f6c8247" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1423, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "8cb4a9ee3f4e9a07c58dd162df3f71d0fe877b8e3e78658fba0b5181fad8dfb6" + }, + { + "bytes": 2629, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/REPORT.md", + "role": "case_evidence", + "sha256": "1adea9bca3e3a5b6aef5842513f0c2355452066161b2cbae6febd752952262fc" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "8db2feee452506f7c1d8a21869a3544a0486339689b0e07bb59b524e6fa3fd57" + }, + { + "bytes": 1000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "c65459eb889f7c50887703cb567f7d09c6769b5224c16659f5f5921784af8cb8" + }, + { + "bytes": 4001, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "0199fd3396cb1f38707f20bd1df878cccc6faaf73a362c95d022fca4cd9e504e" + }, + { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-01/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "bytes": 925, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-ambiguity/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "01c775093f426afefc07258e38c2f6c54986a8856c1d271bef6102f35691f06d" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1423, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "3493370d319101ec7dd1f9b8c0f28864f2ec66d3a240c42b4f5c1eb3f993ab63" + }, + { + "bytes": 2629, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/REPORT.md", + "role": "case_evidence", + "sha256": "add65f6fdd62e6b0a3dabd66544066419bc832fa335d84e01f9451bc0c69a7ef" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "13bbc582a5c0f955cfdf48095cb05750211094a81754f109156ed53b55375573" + }, + { + "bytes": 1000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "731847bdd955b40b0037672bf4b1e9b131aed6cea4aac3bb8a286d5546a598cc" + }, + { + "bytes": 4000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "a0b46dadd309c371099e0173c3e95e6c64783c6803c9236d29ad74670b6cc9fe" + }, + { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-02/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "bytes": 926, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-ambiguity/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "754f8fb53a577102e7d788ca9dcff5eb3ad1e1259b6a838ffc418d40219d4daf" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1422, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "9a738876e3210993d1f6a6afc2fc8ac898a5230e2143b46180f93d1903db420f" + }, + { + "bytes": 2629, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/REPORT.md", + "role": "case_evidence", + "sha256": "ed7ffa6d35250ad7b231d066941a3b28826c4a550fdd9f1c58c6459cc4756103" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "88682d8d15dd6a0160a9be8f6f0e5f1b33ed46b1f2b0cc253f85044a9700c90b" + }, + { + "bytes": 1000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "70d602353201bd5f9332284c63e87b057f4308cb948ba0791d44e2f21904ce93" + }, + { + "bytes": 4000, + "media_type": "application/json", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "389d3890f2e06e6dab6479e6edd960fa3a7fbbcf475131e9eb804de9e2ff8ba5" + }, + { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "bytes": 39758, + "media_type": "image/png", + "path": "artifacts/cases/fault-ambiguity/trial-03/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "395adf2a20b0b258343d77b521240dc0adf8229ac9957661aa6855e3d8d4148f" + }, + { + "bytes": 10175, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-missing-effect/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "b06812e5d70d08f1e0541198384faeed2c6e761195378fc1914e7e7a16931d6b" + }, + { + "bytes": 196584, + "media_type": "video/webm", + "path": "artifacts/cases/fault-missing-effect/trial-01/halt.webm", + "role": "media", + "sha256": "7eb3a32687049eae20bd4a114d3f7561be77e6c6d0678c38cac4d19d420b2317" + }, + { + "bytes": 384, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "bytes": 1768, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "9200874f2a500208b57d4a139e38bfcbe2764ee453bc4d9698a88bbf0f258e14" + }, + { + "bytes": 4980, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/REPORT.md", + "role": "case_evidence", + "sha256": "36e218b5020300de9cc0679bb077d7568d49a8421c068ea1643a520b9a3b9885" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "48de396a45219641c6631b2fa2a02c573df2a585c85ea636a7373e95a7590146" + }, + { + "bytes": 1546, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "814decd92968bc3bcf806cd2054639c2309c237d53d0e3e3ed740ff7259d47b0" + }, + { + "bytes": 1562, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "2ba3c88fa8c8a6d36146d219eb7ac90f62ab005de25c97e9389e89410001cd9e" + }, + { + "bytes": 1554, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "9a05ee6cc6df9b57bf39b22098ab83be01e738e481c2c03e6ad827bc2145528c" + }, + { + "bytes": 1560, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "a5675e04a9b42af9d31c28c5434d88bf68cb03b49cacf0189a5da5addf7a9ebe" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "4ac68705abc17bb762716f1478f2a4dd8b13dc3f915cbb2dcf104c8931da6c81" + }, + { + "bytes": 1529, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "7ecc0e49a256975f82c0a3071082d965343ba754927d39cd9c00140021c94498" + }, + { + "bytes": 16416, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "9888ec067b7f7c05d4e67e638a29493b6e5e2f764d6f2eab363a6c607488b0ff" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-01/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 10173, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-missing-effect/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "4d55ca68adf0f359fe0fa45b804b0e2b8a23a3b088de6412d39050b748285964" + }, + { + "bytes": 384, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "bytes": 1767, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "d44ca70b9756bace314bb27a8964d3292079c0702e9448d2f4ba203dd0cceb4e" + }, + { + "bytes": 4980, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/REPORT.md", + "role": "case_evidence", + "sha256": "b5b445985cf5f1a9d97e76c0cffcb0cc395b7141d9de8f4fe0db65f76746f53b" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "51cbd0f8e3b7cb3270a09a2d6a6ffbb68a429b19de8291121ef41f68e46bba53" + }, + { + "bytes": 1546, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "e67952329148384eb8fa207297cb050a7af22b230db5d85f2118574d70aee4e7" + }, + { + "bytes": 1562, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "6693530faa7fe1ef09b0fafc5fff911af6cb6a64326f0a9d276e75cb3686136e" + }, + { + "bytes": 1552, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "fcdcad265795c0d939e9de06dfcdcaec9c01ada20bcb22eb2ff44df51fa4cc6f" + }, + { + "bytes": 1560, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "513042c8454f22289315a5dfc9b2e78632fbc9e908c72416810f6e14709c71b7" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "c205aa56f8ee22b7d3e9252dfda2b48a86562bf6103cd1f8e1e0c08d3b3c2c2a" + }, + { + "bytes": 1529, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "0dd76766cd687b0048595e1a302ae37c216e93a02ac1f54e8acce4ba6d395ed8" + }, + { + "bytes": 16413, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "eef8a4cb4c6efa841c5649d3328866f29265937aba3eab8306ab11d2e0b21626" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27354, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "d6c6c2d29da6ee4ab499388f4f66f05c39fa4d64bc39888c85bea76872c50a45" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27387, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "9130e1d0c88efd3e3f6b4e8a80ece1e58ba2c1cb86a9cd8381f5753f3fe185ed" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31494, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-02/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "019102af701afd1c0103fd3fefe8af7b88f0f1fae2d75e28b79875efee143e93" + }, + { + "bytes": 10177, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-missing-effect/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "21a6e0b3080e32b46fe0d4b42f0a55038199828491cc317f4e4c25d6b7cfe469" + }, + { + "bytes": 384, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "3a55ea754f1fd03b3393a6a3abf9570a7ebd0bd90c0a9fe8f92a5e7689b132ad" + }, + { + "bytes": 1768, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "d11a823161311ad40d0d34774c087ed1cf90a60bca1baa7e5aaede75190ba171" + }, + { + "bytes": 4981, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/REPORT.md", + "role": "case_evidence", + "sha256": "ab7847e71773c98ac24784511db42f8ded646aa0c4f97348e72fafb29c1270a5" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "2b7683f5845d18217037b701d32a360dc8442b7db6ea96ee3e08f531abfce881" + }, + { + "bytes": 1545, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "af72ba361b2e388b1c7dd40efe06ca410b886f2dfb4f0f055dd5c4c6a38c5cc5" + }, + { + "bytes": 1563, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "691219140254286808bba388b8bf26386d7d4482a95b5e40deb17d3797eddebd" + }, + { + "bytes": 1553, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "012f7406bdec2bcad62c1c80b27f9aa10eb89049cb9342ed1f4e852950d05b39" + }, + { + "bytes": 1560, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "57d3f431804993efc87e2f0886ca17e76ac8bf5d3ff0adf9de2422c887c633ba" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "7588a898e3e183bc5534991bad677dddb8c29741e3063ef7eb714f62bd55bcb0" + }, + { + "bytes": 1529, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "ec91d742252599fd03677a6d75ccc1a617a30c697b03731a96b27859949234bd" + }, + { + "bytes": 16418, + "media_type": "application/json", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "2a550f53de9c8c2a24e492574705fecf0cc5183718ebebada1f9e6333876a325" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27344, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "58f1714e31a3f511b5310539b433536169163c74f224402b7dafed32588d0c72" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/fault-missing-effect/trial-03/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 1735, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-stale-identity/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "c8765f112880d5bdea2838f358bd8c008437c15667fe8740212607d112f6ba0e" + }, + { + "bytes": 42450, + "media_type": "video/webm", + "path": "artifacts/cases/fault-stale-identity/trial-01/halt.webm", + "role": "media", + "sha256": "bf4088606ca140b2ee1fe3fc57c693a1e9bb3b199de3e1c5ae9b27fc5739dca7" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1610, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "c4ae9f7ecb4eaf95080f9f91f100a8fb97d5cb2bcda1efc0b6eb451919d88fdd" + }, + { + "bytes": 2823, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/REPORT.md", + "role": "case_evidence", + "sha256": "c326274d36cca12f7a5ec0dc47eaeb8e2976fc4bf2a978f02e69ce2be5369ccd" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "9bbddd29a6dc5953603fb1c75042e5f0e3aa87059de1e08b9fbebd3ac2a27a97" + }, + { + "bytes": 1242, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "45282bbe8ea7b867ef0f9b764f9650b3136c7b7b61daf672fee34db7efb7582b" + }, + { + "bytes": 5333, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "dca15bf16fe0195f5c3dc68873365c16fa09f45f9ca8ebf1e60dab82c284530e" + }, + { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-01/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "bytes": 1737, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-stale-identity/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "d037138e6334a61804bf3230eb9d020bb745d7ecb7bbaee1c6f2c8d7639c7e5c" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1610, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "920cd25c90560c2961402a0f5710a47d1149a5e88ce63253a0705f627eed7ee8" + }, + { + "bytes": 2823, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/REPORT.md", + "role": "case_evidence", + "sha256": "11168960729a77378a318acb34d4ad530a4aeec96697d084392c72d2d89f0a4f" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "29d07aa793191a7c3d33834362cd5a560adee8bb5a5870bea90473e0c0612407" + }, + { + "bytes": 1242, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "f2371b984668661d145f458dddab30b18596bd74ff6a51a324e9d5840e55daa3" + }, + { + "bytes": 5335, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "ee7aae31e2484417c9c0a2f14825e03373676e12e62300b839acbe45f2f66047" + }, + { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-02/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "bytes": 1737, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-stale-identity/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "19aa64247e7bf1fc2fbd99f16f077cbf386c6a328185bfd3a4442dd30733e1ec" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1611, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "f57c04fd555b86f6e6b2a0ae77125e0717670e62ea42df387df650798aaef6e0" + }, + { + "bytes": 2823, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/REPORT.md", + "role": "case_evidence", + "sha256": "cf818b98410e9a97234621e2749eafae34536b7a1ef35f33259deea746491e5c" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "f0cfcaf14c8bbb5cb79e5ca07c82548d09b2aca397c243827130046e976c3cdf" + }, + { + "bytes": 1242, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "058dc7684d0374b60dcf2a6e0d435caec50250117b0d6d65d5686d7f398d9346" + }, + { + "bytes": 5336, + "media_type": "application/json", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "631ff5e1da6d7e8378a57de74cefb99f1f69b355d1fd32bda2cbdc1c33b641a8" + }, + { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "bytes": 35632, + "media_type": "image/png", + "path": "artifacts/cases/fault-stale-identity/trial-03/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "00dcb835d496c495f07e56390ee635114243f8643f287fb17c092ef59cc72cf8" + }, + { + "bytes": 10591, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-weak-effect/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "acb3bcc31a489bd719d098115e9b53305b87d8bff37be4109fc4d7ca69e7b857" + }, + { + "bytes": 196611, + "media_type": "video/webm", + "path": "artifacts/cases/fault-weak-effect/trial-01/halt.webm", + "role": "media", + "sha256": "6f14e316ffeb24dcb8ce97febc045ae8f251df442680b90f0ff3407be49a0ccc" + }, + { + "bytes": 560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "bytes": 1746, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "adb517d20498f540a459c2fb0193b732c740aa81b8a554a2cf08630de032cf73" + }, + { + "bytes": 4979, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/REPORT.md", + "role": "case_evidence", + "sha256": "26680c82621fb40f65d1d0216f9c7f3cf98e35b978299ac3f6fe497d7582fb49" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "3a0548c66e8ceb3017797ba60d001688ba4305e9af74c90fbedfbdb534029d76" + }, + { + "bytes": 1546, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "304f444e5a052ff8cba4bd53b2a80c66c10f810818d3eac462081f19c1f2d891" + }, + { + "bytes": 1562, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "42cd307f1681f42008963393f0b5c21d54ad147dab54c0491bd2268307e4d67d" + }, + { + "bytes": 1553, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "d6b1a792621c8c768c2d1f33396f2c3e15e7bc415ba691cd4017aa5887a32a4f" + }, + { + "bytes": 1561, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "ea6aa97652382e7194265077277a259a7c0afe969f0b57857bdb01dca02aba44" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "65a6f68a4e3218ff52b2a7adcbf898b3cb8c9c269d18668f93986f8f6c97f8d2" + }, + { + "bytes": 1598, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "16e0d80c3338b20135c83c4ac84dca5187fae68088590dc8d4b7c9aa281fef16" + }, + { + "bytes": 16934, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "b4d5b9c01abc0d902f7a57afd89b32cae6574d42851372f6a4f4cad6f7807afa" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27354, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "d6c6c2d29da6ee4ab499388f4f66f05c39fa4d64bc39888c85bea76872c50a45" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27395, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "1ffca11ead5fee98b4f8c11f330152a9765edcea3b2979c51c19f36b47229a4e" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-01/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 10590, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-weak-effect/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "ef206aae2902e32c4942fdd4a50cf08451a7704aee7cf48647bd7ab85d557dfa" + }, + { + "bytes": 560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "bytes": 1745, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "fddaee34409389259c1437e6f9ac3bae6fb1e5dfa0be48f9a6a44c9718eb8be3" + }, + { + "bytes": 4978, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/REPORT.md", + "role": "case_evidence", + "sha256": "e8c4f30281cc1e9d794ce174ace88da5934e3155cd2b445564b0eecd68d1e2d4" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "57cb68b7364740aeefc56426784d9c555303e8c5504541fd4cd14ad7be2a1329" + }, + { + "bytes": 1546, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "e1037f598ed2086b6aea6c4fabd592238e7afce3e72947895bead6af6ed1546a" + }, + { + "bytes": 1563, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "5785e92cda87cabc21ba85ad6ba187f1bddd11340acff61c78f71f2e291afd1d" + }, + { + "bytes": 1553, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "8113812e60224cf302bf98d7428a249aca60b526959efccb0c7477a5d8935eb1" + }, + { + "bytes": 1560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "2ee83b200195ed418dc7fe4167c86f3eefc71d3f44dd3eb08d739ed9de973ad6" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "8d9de578f018275cd31799b639f1c5d9040fa861f0f3073029e180737e3f56be" + }, + { + "bytes": 1598, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "be7e4348be16a2f7e7b4901b979e16331b03c461a550c6d4a4ec4038556bcecd" + }, + { + "bytes": 16932, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "8143ef2f20bd6b42a00a8cd63827bf18ca99940745b7c435878e512cb2c8bf3f" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-02/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 10592, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-weak-effect/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "035ad252365df35c1575a353d530fdc321de8f9d6e969d4597f64a9044973175" + }, + { + "bytes": 560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "25ea4b0ab9a8225cef1a40b1b8fbec4a40b24e13303f2a44efa8848ebfc55af4" + }, + { + "bytes": 1746, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "2b567a347febee7ff40b626e3379df0772ed2d79be6c4a7be44d81d8e36f6d1c" + }, + { + "bytes": 4978, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/REPORT.md", + "role": "case_evidence", + "sha256": "0a25c150bde7bca40ff42bc0ae08bc4fe038ec46769e32e85af889a7d0912f35" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "b71e61fc56fe03b0720c878fbe1afa4dbe03cd0955eef97da1e2554e4af77ac7" + }, + { + "bytes": 1546, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "658bb9a4fe36fafb6e926a8aba781595707c7bab984bc9ad5db6d9cd5a9e38da" + }, + { + "bytes": 1563, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "04d1251cdd2798383230128572cb135c5f20ef922e0063fdd42559066a2bd025" + }, + { + "bytes": 1554, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "8ea2c34bd4a3bd3fd094901a08f0fd19b551b4ddd31f5fe9cb3339a4a512f874" + }, + { + "bytes": 1560, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "4cd8567fcba71da00bec11d78174fe14b3e9b5f573cb5d86fb0443e3443bf4f7" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "00017a0bfefd2d6da17406d8c648670257b142eae21c18df990ec5899a67cb5a" + }, + { + "bytes": 1598, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "72187b266e652899ef07acf05aacda19b9f5f6ac63444d3bcc298fcd849723b3" + }, + { + "bytes": 16935, + "media_type": "application/json", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "217acca2cdf139ff7e8b53cf8b69f7d704abe8da170e8d880adf6200b9c0d5ee" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27347, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/fault-weak-effect/trial-03/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 1511, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-wrong-identity/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "17cb06e6e6c454cd5a646c09a3a2f84a6681ebb6615ac30c1320f4e6db7e26fb" + }, + { + "bytes": 40123, + "media_type": "video/webm", + "path": "artifacts/cases/fault-wrong-identity/trial-01/halt.webm", + "role": "media", + "sha256": "987ddf3f74b26102e6877de45b2ad4f558b643062253c5fa5058cb8b2490f146" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1653, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "a1987aeb639d36a8b346e48e4762f4767ecc97d5c8fc5f164c83ed0d5ea6e951" + }, + { + "bytes": 2817, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/REPORT.md", + "role": "case_evidence", + "sha256": "ead387e4679c3a3141fcde82a877178cef30e558f251fac1d5f3ffd32265ab4f" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "4a7bfcb3583cd6ae7e74e02923527bb4bea4d1d600ab7cc32cd4f81f233be5ee" + }, + { + "bytes": 1240, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "cfc412811b4dca04bb56499d2def2d972d4bfb1a8b47a25a074f9e68c7ff846c" + }, + { + "bytes": 4966, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "e1c742fac9cde46d9ae25d950005f40af0e2b5957d0fce13f4cb26bc20a7ff9e" + }, + { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-01/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "bytes": 1511, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-wrong-identity/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "ce5dbf2378ebee2bb99ad87cc405cf635e092321b09d954b71bf476dc4544dcf" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1653, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "98b0042e8cbbd25ee9632e5db57bb4206e38005b2420e357d0865db915f85512" + }, + { + "bytes": 2817, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/REPORT.md", + "role": "case_evidence", + "sha256": "b5e8fda99f5eaee6e486a4ead6e956be1f4ec3b62847279bd43240f040d35ef4" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "af8bbff370e0512d4664e4c62b2bb9edf4e5f68cdd426624563d576faf7603ec" + }, + { + "bytes": 1240, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "34c5aace35f54266009fa6a6664f348459500540d1d2dbd639c7396644e6735b" + }, + { + "bytes": 4966, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "7ae08bb375505df852fee3594884bc27326f1eeafcdc2b48824bc6cc7e5934cd" + }, + { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-02/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "bytes": 1510, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/fault-wrong-identity/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "ae6393fd33a83b3524fb55080dca38ed1fe7c853f61f5e7a89737e86d0f99921" + }, + { + "bytes": 369, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "53505ae34f1d494855f9d1ce5fb12561c36a86884834255270d973d57945bd1f" + }, + { + "bytes": 1653, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "34d4cbd08fb746e62e765d53a39444403f676361917ce5006e449aca7cfab8aa" + }, + { + "bytes": 2817, + "media_type": "text/markdown", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/REPORT.md", + "role": "case_evidence", + "sha256": "8da2741861fb693e0f96f0377f65e88e9798ad57e67deb1f2b0722b7933abccf" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "508dff905abe48b6fc24c5a4d21bfaf6184198f8c842c94df9bcd1ec009cdf68" + }, + { + "bytes": 1240, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/pending_escalation.json", + "role": "case_evidence", + "sha256": "248fca8ba29629384d18327ba565097aa7a714a49ec5b2c91cfb327ea3d0f258" + }, + { + "bytes": 4965, + "media_type": "application/json", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "f9f73d20c1c98fa7d03fef19e70089a0231a49cb06bb1cf764cc66c10e01c238" + }, + { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "bytes": 39941, + "media_type": "image/png", + "path": "artifacts/cases/fault-wrong-identity/trial-03/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "d99076ca95354216c80ea82a3be00908b680b998879ac0bdd97f435d12bbdecf" + }, + { + "bytes": 10080, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/representative/trial-01/events.jsonl", + "role": "case_evidence", + "sha256": "16c457b60fed99b9e8e77ac449f30e3d2c9bab20302bec9a094f5809bf935b68" + }, + { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "bytes": 743, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/outcome.json", + "role": "case_evidence", + "sha256": "9fe5537806507fe364e32683b9fc39b17bfd996ffbaae221ff3ecacc37514a89" + }, + { + "bytes": 123995, + "media_type": "video/webm", + "path": "artifacts/cases/representative/trial-01/replay.webm", + "role": "media", + "sha256": "b84184382c9cfeeb733776a2be72d242c7b21d5e6c2e4e7b249b897e5e5c73bd" + }, + { + "bytes": 4497, + "media_type": "text/markdown", + "path": "artifacts/cases/representative/trial-01/run/REPORT.md", + "role": "case_evidence", + "sha256": "61300e9be731260f9b58069dbf3e0e54bb1e997b24331fb4d1a1db6cc7c80b77" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "1adb36cf8e55daf95f283486d6746554e37c5ea51433f57ac6a073c6757c5738" + }, + { + "bytes": 1545, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "35ce6b839a6ffb54f2766d7eb15c3b9b2ae8f25cead2f02c3e95eca2fa1cb19d" + }, + { + "bytes": 1562, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "b25134478eef367269c448ec99724196482e0de11a07a55937889761b84d7b6f" + }, + { + "bytes": 1553, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "79cb1810e036fdbaa91a6bbe7eaa151a34fe1133358c7c00ec43dec80fcc4dd4" + }, + { + "bytes": 1561, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "e8b1e7280c68307956ad9c6e0ec4360a4a4db959aba442adb0eec7d4c1ed4506" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "391844051eca3c449e070711157ce910c65eebf902b9c2102a56791b4c01dd56" + }, + { + "bytes": 2374, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/checkpoints/step_0005_step_005.json", + "role": "case_evidence", + "sha256": "ac60acd0ae5385aafd10d5846e06a948f4cc7c742da1b782fe8d189bc8c9a94f" + }, + { + "bytes": 15430, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-01/run/report.json", + "role": "case_evidence", + "sha256": "10d7e85225617c5ee98a357f5b2b9098b451373f6f0e367d7f84185c46806fcf" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23522, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27344, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "58f1714e31a3f511b5310539b433536169163c74f224402b7dafed32588d0c72" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-01/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 10080, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/representative/trial-02/events.jsonl", + "role": "case_evidence", + "sha256": "911084d767b52fcb9955a9a3b52e64848aa2d444cd263b116e0b7636b263adf6" + }, + { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "bytes": 744, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/outcome.json", + "role": "case_evidence", + "sha256": "7e035ce556cbaa0b810d5e0d7164f8739956ab0b523803e87aea8920cbdc0643" + }, + { + "bytes": 4497, + "media_type": "text/markdown", + "path": "artifacts/cases/representative/trial-02/run/REPORT.md", + "role": "case_evidence", + "sha256": "76176805c74945965e0dfaa4be64d70b707a80bb2edfdd14749ccf060d902933" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "cfbd75260c107f1dd37ff09f8973400eb408616599d7caf4a2a80d8f9e71ee84" + }, + { + "bytes": 1544, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "27342a30d986e092f15818f60b26dcf29cbadc1127e8ad12490f2f7138d71082" + }, + { + "bytes": 1562, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "f77f0e231054afe11778dcece240e92f9ac5df930d004261c3059d11aadbaedc" + }, + { + "bytes": 1554, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "2f26cf6c608c501195dfd3f44d82e195e661f5d64632bb61da12cec1c0356681" + }, + { + "bytes": 1560, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "5d10cc81902b935eb2ce53d8f7e691701acb497a0f6580cdbe0aa1711d725eca" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "fad67f0751b96824ec423100de3a37336a3fde2ae2f9d279167ae96ae0af69a5" + }, + { + "bytes": 2374, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/checkpoints/step_0005_step_005.json", + "role": "case_evidence", + "sha256": "9e80298ac69fed791a6f729418f6c00603550a1ef00092748c757a7d8d3959d4" + }, + { + "bytes": 15431, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-02/run/report.json", + "role": "case_evidence", + "sha256": "74571ea3f509a07e570a3628325501e503e684a452bd14713121dd77bd7da5b7" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27347, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-02/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 10081, + "media_type": "application/x-ndjson", + "path": "artifacts/cases/representative/trial-03/events.jsonl", + "role": "case_evidence", + "sha256": "7204bc6d968bee2932fc83a8701ca763e32699c4547a8ab0cc88fd7741dd1dc8" + }, + { + "bytes": 581, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/oracle.json", + "role": "case_evidence", + "sha256": "788c60eeecab7de31d5e90c0784d7eee1ac34a84862ec138f18a3178caa8f987" + }, + { + "bytes": 743, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/outcome.json", + "role": "case_evidence", + "sha256": "dd3e5b88e62166a75c11bbc91d0f0015b9bc489d078649a8e529a07ab134a5e1" + }, + { + "bytes": 4497, + "media_type": "text/markdown", + "path": "artifacts/cases/representative/trial-03/run/REPORT.md", + "role": "case_evidence", + "sha256": "ca619e1f30405a7b1ccb148d8edb9a0f194902ed0a961d7cc36aae355ed6878d" + }, + { + "bytes": 1185, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/_manifest.json", + "role": "case_evidence", + "sha256": "cf19e5bda0e6731bb9b3da701740b64b96a84142d4301c32d5e8c4a3cf82fd43" + }, + { + "bytes": 1545, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/step_0000_step_000.json", + "role": "case_evidence", + "sha256": "285cbed7c30d014dfa34b0ae6ba42ca6bae6209952970e455aeaa67fe5cc23c2" + }, + { + "bytes": 1562, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/step_0001_step_001.json", + "role": "case_evidence", + "sha256": "436d7635b1731ee815993598bce7d552a3bf2381d299a13bafc0bbe3a2e4eec9" + }, + { + "bytes": 1553, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/step_0002_step_002.json", + "role": "case_evidence", + "sha256": "49567d7332e299ce257ee9d3343da3f1ba10ae4d294bc68a6542496776ff0c5d" + }, + { + "bytes": 1561, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/step_0003_step_003.json", + "role": "case_evidence", + "sha256": "be93b6229e20c4481fed797baac5d3820841718d78c5ba1166046948e7b46494" + }, + { + "bytes": 736, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/step_0004_step_004.json", + "role": "case_evidence", + "sha256": "a7664a09d18cb568bc212d99b3712b84e17609186e7ea00d12c94df71de67c5c" + }, + { + "bytes": 2374, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/checkpoints/step_0005_step_005.json", + "role": "case_evidence", + "sha256": "a648f8cb18385f7d416298037c7887f5712b59caa09b0bc964b2074c3d37db60" + }, + { + "bytes": 15431, + "media_type": "application/json", + "path": "artifacts/cases/representative/trial-03/run/report.json", + "role": "case_evidence", + "sha256": "c2a3606345c3baffc881f4fcb5ff76d209278476787dbf65c6e92a2ff00bc68c" + }, + { + "bytes": 23523, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_000_after.png", + "role": "case_evidence", + "sha256": "bc5ecdd6b0b6becdf72fd736840f9ceb3a8f5c28a94b7ca93d18ac47b113e3b6" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_000_before.png", + "role": "case_evidence", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27348, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_001_after.png", + "role": "case_evidence", + "sha256": "c93494363bb067164bd0da1d4f48ee33acde619800f66f2b91b297477336c4ca" + }, + { + "bytes": 23522, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_001_before.png", + "role": "case_evidence", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_002_after.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 27344, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_002_before.png", + "role": "case_evidence", + "sha256": "58f1714e31a3f511b5310539b433536169163c74f224402b7dafed32588d0c72" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_003_after.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 27400, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_003_before.png", + "role": "case_evidence", + "sha256": "5b0d35f3b6f60ac321573c3a6ce36c096dc0abe44dbe6c756ba344b3eec820ca" + }, + { + "bytes": 31501, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_004_after.png", + "role": "case_evidence", + "sha256": "d47fd457fc12221ca37db9aab4a098d754fbb086f4e5f6607c12b5090d4bf97c" + }, + { + "bytes": 27618, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_004_before.png", + "role": "case_evidence", + "sha256": "7f6806cac79efad47ed1472e525954cb5f65b1a18943f785bf13c336cabda03c" + }, + { + "bytes": 31599, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_005_after.png", + "role": "case_evidence", + "sha256": "ba6033fa67a091fd53200f591cab85e4b8e1759f38d4f11def4f3ab8f989b2d4" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/cases/representative/trial-03/run/steps/step_005_before.png", + "role": "case_evidence", + "sha256": "a8201e29326123adbf2662cbce74d9de7e636210904b41038ae84e17bce8fa23" + }, + { + "bytes": 24900, + "media_type": "text/html", + "path": "artifacts/compiled/program-graph.html", + "role": "program_graph", + "sha256": "15f97a7e127bbea3188f421ffd3b2bc8a18d6bffa0d61e117dabee43da355883" + }, + { + "bytes": 12223, + "media_type": "application/json", + "path": "artifacts/compiled/program-graph.json", + "role": "program_graph", + "sha256": "016e509e71d6f649f8f3ff37e723f551ee0c32e081a1f1fc00713eab6ef3ebe3" + }, + { + "bytes": 116411, + "media_type": "video/webm", + "path": "artifacts/media/recording.webm", + "role": "media", + "sha256": "3ac77627340b5f3ef3adc37b9b8f05091bdc886e0d65d2ec2baac9ed591cc438" + }, + { + "bytes": 6341, + "media_type": "application/json", + "path": "artifacts/presentation/demonstration.control-overlay.v2.json", + "role": "evidence", + "sha256": "cfab1104ffaf3726eded86cf0378e5e5d3386802f5bab5b4179cf7a2ac2ead1d" + }, + { + "bytes": 303, + "media_type": "application/json", + "path": "artifacts/presentation/demonstration.frame-pts-us.json", + "role": "evidence", + "sha256": "f6ed892ccc0a64a969ec12ec4a37f87d7cfcad5cafd5e002ff4871aabf626469" + }, + { + "bytes": 77376, + "media_type": "video/webm", + "path": "artifacts/presentation/demonstration.webm", + "role": "media", + "sha256": "6a15175effc07fa737f3a1c020baa6a13e7548f382cf5f25d419e6ffb64b91bf" + }, + { + "bytes": 1982, + "media_type": "application/json", + "path": "artifacts/presentation/halted.control-overlay.v2.json", + "role": "evidence", + "sha256": "d97b7c13a0724989e292b45a4ea1435338db6889503f06f52e15421e0d3faa7c" + }, + { + "bytes": 241, + "media_type": "application/json", + "path": "artifacts/presentation/halted.frame-pts-us.json", + "role": "evidence", + "sha256": "64e5b69483ae0c70a2afb10eebe6e9917cacb2dd766bb672f94424a073240bb2" + }, + { + "bytes": 32237, + "media_type": "video/webm", + "path": "artifacts/presentation/halted.webm", + "role": "media", + "sha256": "59cdce33ff0fbbf0aadc78ebe9eabe6cf189dc7f8aa2e9f2d1724d90cf8270f1" + }, + { + "bytes": 19324, + "media_type": "application/json", + "path": "artifacts/presentation/verified.control-overlay.v2.json", + "role": "evidence", + "sha256": "5742b18dc4532f6470f41ff9a21baf1dc637d5fab5d484defd36ba542ffd569c" + }, + { + "bytes": 461, + "media_type": "application/json", + "path": "artifacts/presentation/verified.frame-pts-us.json", + "role": "evidence", + "sha256": "821f6c48c2d5cfe00e86a44c886508e258678cb8f863a2dff26f5736dce71674" + }, + { + "bytes": 78310, + "media_type": "video/webm", + "path": "artifacts/presentation/verified.webm", + "role": "media", + "sha256": "41b3d412220827678696d8c06a111c79118f201ebb3a48be459ae4126892d087" + }, + { + "bytes": 21462, + "media_type": "application/json", + "path": "artifacts/qualification/project.json", + "role": "qualification", + "sha256": "d4a2db89a83f7aa7c28d233903228d82a323a4788b2bf5ea5e9a31a370cf4c78" + }, + { + "bytes": 779, + "media_type": "application/json", + "path": "artifacts/qualification/report.json", + "role": "qualification", + "sha256": "24f34c46f6feff7d2ac369416dda13a193b9487e360ffe7c00b36725474afa3c" + }, + { + "bytes": 2945, + "media_type": "application/x-ndjson", + "path": "artifacts/recording/events.jsonl", + "role": "source_recording", + "sha256": "c5ab16f16eacf2d81c060084c63ea3a29cc803a14ca4d7bcd5055fa8daadc9fb" + }, + { + "bytes": 23522, + "media_type": "image/png", + "path": "artifacts/recording/frames/0000_after.png", + "role": "source_recording", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "bytes": 35249, + "media_type": "image/png", + "path": "artifacts/recording/frames/0000_before.png", + "role": "source_recording", + "sha256": "44ec36e83492639eeb90ec6a8888be4242e85de3a508cea28a2906bcb12e2ebe" + }, + { + "bytes": 27347, + "media_type": "image/png", + "path": "artifacts/recording/frames/0001_after.png", + "role": "source_recording", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "bytes": 23522, + "media_type": "image/png", + "path": "artifacts/recording/frames/0001_before.png", + "role": "source_recording", + "sha256": "95f240328c3e7e5b8ba9fbb3adebe48891c378a5b9ecc5aa4de55c613189b870" + }, + { + "bytes": 27393, + "media_type": "image/png", + "path": "artifacts/recording/frames/0002_after.png", + "role": "source_recording", + "sha256": "8d2d2d2a56a8d089b11f1e97926c06f0c1d7076e080d0ffbd70b0bf1691aeae3" + }, + { + "bytes": 27347, + "media_type": "image/png", + "path": "artifacts/recording/frames/0002_before.png", + "role": "source_recording", + "sha256": "c9a35595904c645af4664987a5f94d6665c0cbf6efb74c3bf69920ca8ad950dc" + }, + { + "bytes": 27616, + "media_type": "image/png", + "path": "artifacts/recording/frames/0003_after.png", + "role": "source_recording", + "sha256": "8a3c5f2a1a6d1816b42227a818afe24a0c1d7362791773cb6f18d1fcd1b314d9" + }, + { + "bytes": 27393, + "media_type": "image/png", + "path": "artifacts/recording/frames/0003_before.png", + "role": "source_recording", + "sha256": "8d2d2d2a56a8d089b11f1e97926c06f0c1d7076e080d0ffbd70b0bf1691aeae3" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/recording/frames/0004_after.png", + "role": "source_recording", + "sha256": "d4da8dbaf7fa257e89d78a08854ccd50c8277c3fcb12efe2614d3fa4508a3026" + }, + { + "bytes": 27616, + "media_type": "image/png", + "path": "artifacts/recording/frames/0004_before.png", + "role": "source_recording", + "sha256": "8a3c5f2a1a6d1816b42227a818afe24a0c1d7362791773cb6f18d1fcd1b314d9" + }, + { + "bytes": 31598, + "media_type": "image/png", + "path": "artifacts/recording/frames/0005_after.png", + "role": "source_recording", + "sha256": "09b63152f50688a01352cbab13a1ea33e2d837b36180c866849ec4cdfaeaa599" + }, + { + "bytes": 31499, + "media_type": "image/png", + "path": "artifacts/recording/frames/0005_before.png", + "role": "source_recording", + "sha256": "d4da8dbaf7fa257e89d78a08854ccd50c8277c3fcb12efe2614d3fa4508a3026" + }, + { + "bytes": 298, + "media_type": "application/json", + "path": "artifacts/recording/meta.json", + "role": "source_recording", + "sha256": "17494cf94c54918f37e6237b2024809cc53160ec870b357e946149ea1e9183e1" + } + ], + "pack": { + "generated_at": "2026-07-26T07:08:22.800022+00:00", + "id": "mockmed-triage-v3", + "immutable": true, + "version": 1 + }, + "provenance": { + "application": { + "license": "MIT", + "name": "OpenAdapt MockMed synthetic reference", + "source_path": "openadapt_flow/mockmed", + "source_sha256": "1f4d59153fc6c797d626b27977fa6270ca8b2d9461b23171f9a2b2b571d2a0c1", + "synthetic_data_only": true, + "version": "sha256:1f4d59153fc6c797d626b27977fa6270ca8b2d9461b23171f9a2b2b571d2a0c1" + }, + "data_classification": "synthetic_sample", + "exporter": "scripts/export_public_demo_evidence.py", + "license": "MIT", + "openadapt_flow_version": "1.23.0", + "repository": "https://github.com/OpenAdaptAI/openadapt-flow", + "runtime": { + "browser": "chromium", + "browser_version": "149.0.7827.55", + "device_scale_factor": 1, + "headless": true, + "platform": "macOS-15.7.3-arm64-arm-64bit", + "python": "3.11.9", + "user_agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) HeadlessChrome/149.0.7827.55 Safari/537.36", + "viewport": [ + 1280, + 800 + ] + }, + "source_commit": "7cc518ee0b83dd571c0902423134a5525635e6b2", + "source_tree_clean": true + }, + "schema_version": "openadapt.public-demo-evidence/v1", + "task": { + "parameter_names": [ + "note" + ], + "program_graph_ref": { + "bytes": 12223, + "media_type": "application/json", + "path": "artifacts/compiled/program-graph.json", + "role": "program_graph", + "sha256": "016e509e71d6f649f8f3ff37e723f551ee0c32e081a1f1fc00713eab6ef3ebe3" + }, + "target_kind": "web", + "workflow_name": "mockmed-triage" + } +} diff --git a/public-demo/evidence-packs/mockmed-triage-v3/manifest.sha256 b/public-demo/evidence-packs/mockmed-triage-v3/manifest.sha256 new file mode 100644 index 00000000..93468eb5 --- /dev/null +++ b/public-demo/evidence-packs/mockmed-triage-v3/manifest.sha256 @@ -0,0 +1 @@ +a4c531de62d875355a359dce4655fe80963ab1be421c99c1be317d82cdccd49d manifest.json diff --git a/schemas/public-demo-evidence-v1.json b/schemas/public-demo-evidence-v1.json index 3f7947bb..d54e9360 100644 --- a/schemas/public-demo-evidence-v1.json +++ b/schemas/public-demo-evidence-v1.json @@ -125,7 +125,6 @@ "required_case_kinds", "outcome_counts", "model_calls", - "external_network_calls", "screenshots_may_leave_box", "wrong_target_actions", "silent_incorrect_successes", @@ -138,6 +137,18 @@ "qualification_passed", "caveats" ], + "oneOf": [ + { + "required": ["external_network_calls"] + }, + { + "required": [ + "runtime_network_observation_counts", + "browser_request_count", + "off_box_or_third_party_egress_observed" + ] + } + ], "properties": { "environment_digest": { "$ref": "#/$defs/sha256" @@ -152,6 +163,22 @@ "external_network_calls": { "const": 0 }, + "runtime_network_observation_counts": { + "type": "object", + "additionalProperties": false, + "properties": { + "none": {"type": "integer", "minimum": 0}, + "observed": {"type": "integer", "minimum": 0}, + "unknown": {"type": "integer", "minimum": 0} + } + }, + "browser_request_count": { + "type": "integer", + "minimum": 1 + }, + "off_box_or_third_party_egress_observed": { + "const": false + }, "screenshots_may_leave_box": { "const": false }, @@ -209,6 +236,22 @@ "minimum_effect_tier" ] }, + "presentation": { + "type": "object", + "additionalProperties": false, + "required": ["demonstration", "verified", "halted"], + "properties": { + "demonstration": { + "$ref": "#/$defs/presentationRecording" + }, + "verified": { + "$ref": "#/$defs/presentationRun" + }, + "halted": { + "$ref": "#/$defs/presentationRun" + } + } + }, "cases": { "type": "array", "minItems": 6, @@ -265,6 +308,52 @@ } } }, + "presentationRecording": { + "type": "object", + "additionalProperties": false, + "required": [ + "source_kind", + "raw_media", + "media", + "timeline", + "frame_pts" + ], + "properties": { + "source_kind": {"const": "source_recording"}, + "raw_media": {"$ref": "#/$defs/fileRef"}, + "media": {"$ref": "#/$defs/fileRef"}, + "timeline": {"$ref": "#/$defs/fileRef"}, + "frame_pts": {"$ref": "#/$defs/fileRef"} + } + }, + "presentationRun": { + "type": "object", + "additionalProperties": false, + "required": [ + "source_kind", + "case_id", + "trial", + "report", + "outcome", + "oracle", + "raw_media", + "media", + "timeline", + "frame_pts" + ], + "properties": { + "source_kind": {"const": "run"}, + "case_id": {"type": "string", "minLength": 1}, + "trial": {"type": "integer", "minimum": 1}, + "report": {"$ref": "#/$defs/fileRef"}, + "outcome": {"$ref": "#/$defs/fileRef"}, + "oracle": {"$ref": "#/$defs/fileRef"}, + "raw_media": {"$ref": "#/$defs/fileRef"}, + "media": {"$ref": "#/$defs/fileRef"}, + "timeline": {"$ref": "#/$defs/fileRef"}, + "frame_pts": {"$ref": "#/$defs/fileRef"} + } + }, "cropBinding": { "type": "object", "additionalProperties": false, diff --git a/scripts/check_release_consistency.py b/scripts/check_release_consistency.py index bdfd90dd..ae47a8d2 100644 --- a/scripts/check_release_consistency.py +++ b/scripts/check_release_consistency.py @@ -10,6 +10,7 @@ import os import re import stat +import subprocess import tarfile import zipfile from email.parser import BytesParser @@ -182,6 +183,7 @@ { ".7z", ".arrow", + ".avi", ".bin", ".cfg", ".conf", @@ -199,6 +201,9 @@ ".json", ".jsonl", ".mjs", + ".mkv", + ".mov", + ".mp4", ".npy", ".npz", ".onnx", @@ -216,6 +221,7 @@ ".tsv", ".wasm", ".webp", + ".webm", ".yaml", ".yml", ".zip", @@ -600,6 +606,27 @@ def _validate_public_artifact_inventory( "public artifact inventory hash mismatch; explicitly regenerate and " f"review it: {changed}" ) + git_marker = root / ".git" + if git_marker.exists(): + tracked_result = subprocess.run( + ["git", "-C", str(root), "ls-files", "-z"], + check=False, + capture_output=True, + ) + if tracked_result.returncode != 0: + raise ValueError( + "could not verify that public artifact inventory paths are tracked " + "by git" + ) + tracked = { + path.decode("utf-8") for path in tracked_result.stdout.split(b"\0") if path + } + untracked = sorted(expected - tracked) + if untracked: + raise ValueError( + "public artifact inventory contains files that are not tracked by " + f"git: {untracked}" + ) return inventory diff --git a/scripts/export_public_demo_evidence.py b/scripts/export_public_demo_evidence.py index 9b1a914b..584e001f 100644 --- a/scripts/export_public_demo_evidence.py +++ b/scripts/export_public_demo_evidence.py @@ -16,7 +16,7 @@ python -m scripts.export_public_demo_evidence \ --out public-demo/evidence-packs \ - --pack-id mockmed-triage-v2 + --pack-id mockmed-triage-v3 The pack directory is created atomically and is never overwritten. Run ``--validate `` to re-check every retained byte, crop binding, case @@ -28,7 +28,9 @@ import argparse import base64 import hashlib +import ipaddress import json +import math import os import platform import shutil @@ -36,8 +38,10 @@ import tempfile from collections import Counter from datetime import datetime, timezone +from decimal import Decimal from pathlib import Path, PurePosixPath -from typing import Any, Callable, Iterable, Optional +from typing import Any, Callable, Iterable, Literal, Optional +from urllib.parse import urlsplit from urllib.request import Request, urlopen from jsonschema import Draft202012Validator @@ -92,6 +96,8 @@ OUTCOME_SCHEMA_VERSION = "openadapt.public-demo-outcome/v1" PACK_VERSION = 1 TRIALS_PER_CASE = 3 +PRESENTATION_TERMINAL_HOLD_MS = 1_750 +PRESENTATION_PTS_SCHEMA_VERSION = "openadapt.media-frame-presentation-times/v1" NOTE = "Synthetic follow-up in two weeks" WORKFLOW_NAME = "mockmed-triage" RUNNER_KEY_ID = "public-demo-headless-runner" @@ -240,10 +246,283 @@ def _finish_video(video_dir: Path, target: Path) -> Path: return target +class _PresentationCapture: + """Retain exact runtime frames with the screenshot displayed at each sink call. + + This capture is a presentation derivative, not execution evidence. The + target page is never modified. Browser target geometry survives only when + the runtime's already-held observation proves its run-scoped binding; + otherwise the status frame remains and the rectangle is omitted. The sink + never takes a browser screenshot between final revalidation and actuation. + """ + + def __init__(self, *, mode: str) -> None: + from openadapt_types import ControlOverlayMode + + from openadapt_flow.runtime.control_overlay import ( + RuntimeControlOverlayEmitter, + ) + + self.frames: list[Any] = [] + self.screenshots: list[bytes] = [] + self.emitter = RuntimeControlOverlayEmitter( + lambda _frame: None, + mode=ControlOverlayMode(mode), + observation_sink=self._accept, + ) + + def _accept(self, frame: Any, observation_png: Optional[bytes]) -> None: + screenshot = observation_png or ( + self.screenshots[-1] if self.screenshots else None + ) + if screenshot is None: + raise EvidencePackError( + "presentation event has no exact retained runtime observation" + ) + if frame.target_tracking is not None: + observation_binding = self.emitter.observation_hmac_sha256( + screenshot, + event_sequence=frame.event_sequence, + ) + if frame.tracking_for_observation(observation_binding) is None: + frame = frame.model_copy(update={"target_tracking": None}) + self.frames.append(frame) + self.screenshots.append(screenshot) + + +def _presentation_tools() -> tuple[str, str]: + ffmpeg = shutil.which("ffmpeg") + ffprobe = shutil.which("ffprobe") + if ffmpeg is None or ffprobe is None: + raise EvidencePackError( + "public presentation export requires separately provisioned " + "ffmpeg and ffprobe executables" + ) + return ffmpeg, ffprobe + + +def _probe_frame_presentation_times_us( + ffprobe: str, + media_path: Path, +) -> list[int]: + result = subprocess.run( + [ + ffprobe, + "-v", + "error", + "-select_streams", + "v:0", + "-show_entries", + "frame=best_effort_timestamp_time", + "-of", + "json", + str(media_path), + ], + check=True, + capture_output=True, + text=True, + ) + payload = json.loads(result.stdout) + raw_frames = payload.get("frames") if isinstance(payload, dict) else None + if not isinstance(raw_frames, list) or not raw_frames: + raise EvidencePackError(f"ffprobe found no decoded frames in {media_path}") + presentation_times_us: list[int] = [] + for item in raw_frames: + value = ( + item.get("best_effort_timestamp_time") if isinstance(item, dict) else None + ) + if not isinstance(value, str): + raise EvidencePackError( + f"ffprobe omitted a decoded-frame timestamp in {media_path}" + ) + microseconds = Decimal(value) * Decimal(1_000_000) + if microseconds != microseconds.to_integral_value(): + raise EvidencePackError( + f"ffprobe returned a sub-microsecond timestamp in {media_path}" + ) + presentation_times_us.append(int(microseconds)) + if presentation_times_us[0] != 0 or any( + current <= previous + for previous, current in zip( + presentation_times_us, + presentation_times_us[1:], + ) + ): + raise EvidencePackError( + f"decoded-frame timestamps are not zero-based and strictly increasing: " + f"{media_path}" + ) + return presentation_times_us + + +def _write_presentation_clip( + *, + capture: _PresentationCapture, + pack_id: str, + clip_id: str, + presentation_dir: Path, +) -> None: + """Encode one fresh exact-frame derivative and its canonical V2 timeline.""" + + from openadapt_types import ControlOverlayDataClassification + + from openadapt_flow.runtime.control_overlay import ( + build_runtime_control_overlay_timeline_v2, + ) + + if not capture.frames or len(capture.frames) != len(capture.screenshots): + raise EvidencePackError(f"{clip_id} presentation capture is incomplete") + if [frame.event_sequence for frame in capture.frames] != list( + range(len(capture.frames)) + ): + raise EvidencePackError( + f"{clip_id} presentation events are not one exact sequence" + ) + media_started_monotonic_ms = capture.frames[0].observed_at_monotonic_ms + event_offsets_ms = [ + int( + math.floor( + frame.observed_at_monotonic_ms - media_started_monotonic_ms + 0.5 + ) + ) + for frame in capture.frames + ] + if event_offsets_ms[0] != 0 or any( + current <= previous + for previous, current in zip(event_offsets_ms, event_offsets_ms[1:]) + ): + raise EvidencePackError( + f"{clip_id} presentation events do not map to distinct media milliseconds" + ) + + ffmpeg, ffprobe = _presentation_tools() + presentation_dir.mkdir(parents=True, exist_ok=True) + media_path = presentation_dir / f"{clip_id}.webm" + timeline_path = presentation_dir / f"{clip_id}.control-overlay.v2.json" + pts_path = presentation_dir / f"{clip_id}.frame-pts-us.json" + with tempfile.TemporaryDirectory( + prefix=f".{clip_id}-frames.", + dir=str(presentation_dir), + ) as staging_raw: + staging = Path(staging_raw) + frame_paths: list[Path] = [] + for index, screenshot in enumerate(capture.screenshots): + frame_path = staging / f"{index:04d}.png" + frame_path.write_bytes(screenshot) + frame_paths.append(frame_path) + concat_lines = ["ffconcat version 1.0"] + for index, frame_path in enumerate(frame_paths): + absolute = frame_path.resolve().as_posix() + if "'" in absolute or "\n" in absolute: + raise EvidencePackError("unsafe presentation staging path") + duration_ms = ( + event_offsets_ms[index + 1] - event_offsets_ms[index] + if index + 1 < len(event_offsets_ms) + else PRESENTATION_TERMINAL_HOLD_MS + ) + concat_lines.extend( + [ + f"file '{absolute}'", + "option framerate 1000", + f"duration {duration_ms / 1000:.3f}", + ] + ) + # The concat demuxer needs the final image repeated for its duration to + # be honored. This adds one target-free terminal/recording hold frame; + # it does not invent another runtime event. + concat_lines.extend( + [ + f"file '{frame_paths[-1].resolve().as_posix()}'", + "option framerate 1000", + ] + ) + concat_path = staging / "frames.ffconcat" + concat_path.write_text("\n".join(concat_lines) + "\n", encoding="utf-8") + subprocess.run( + [ + ffmpeg, + "-nostdin", + "-loglevel", + "error", + "-y", + "-f", + "concat", + "-safe", + "0", + "-i", + str(concat_path), + "-an", + "-fps_mode", + "vfr", + "-c:v", + "libvpx-vp9", + "-lossless", + "1", + "-deadline", + "good", + "-cpu-used", + "2", + "-pix_fmt", + "yuv420p", + str(media_path), + ], + check=True, + ) + + presentation_times_us = _probe_frame_presentation_times_us(ffprobe, media_path) + if len(presentation_times_us) < len(capture.frames) + 1: + raise EvidencePackError( + f"{clip_id} encoder dropped a retained presentation frame" + ) + for event_offset_ms, presentation_time_us in zip( + event_offsets_ms, + presentation_times_us[: len(capture.frames)], + strict=True, + ): + if presentation_time_us != event_offset_ms * 1_000: + raise EvidencePackError( + f"{clip_id} runtime event does not have an exact decoded frame" + ) + terminal_hold_us = ( + presentation_times_us[len(capture.frames)] + - presentation_times_us[len(capture.frames) - 1] + ) + if terminal_hold_us != PRESENTATION_TERMINAL_HOLD_MS * 1_000: + raise EvidencePackError( + f"{clip_id} terminal presentation hold was not retained exactly" + ) + + media_sha256 = _sha256(media_path) + duration_ms = presentation_times_us[-1] // 1_000 + timeline = build_runtime_control_overlay_timeline_v2( + capture.frames, + data_classification=ControlOverlayDataClassification.SYNTHETIC, + evidence_pack_id=pack_id, + media_sha256=media_sha256, + media_frame_count=len(presentation_times_us), + media_frame_indexes=list(range(len(capture.frames))), + duration_ms=duration_ms, + media_started_monotonic_ms=media_started_monotonic_ms, + ) + _write_json(timeline_path, timeline.model_dump(mode="json")) + _write_json( + pts_path, + { + "schema_version": PRESENTATION_PTS_SCHEMA_VERSION, + "media_sha256": media_sha256, + "frame_count": len(presentation_times_us), + "presentation_times_us": presentation_times_us, + }, + ) + + def _record( base_url: str, recording_dir: Path, media_dir: Path, + presentation_dir: Path, + *, + pack_id: str, ) -> dict[str, Any]: """Drive the real Recorder with a read-only source-of-record observer.""" @@ -256,12 +535,17 @@ def _record( headless=True, record_video_dir=str(video_tmp), ) + presentation = _PresentationCapture(mode="demonstration") + presentation.emitter.begin(profile="demo") environment: dict[str, Any] = {} try: page = backend.page + browser = page.context.browser + if browser is None: + raise EvidencePackError("recording page has no owning browser") environment = { "browser": "chromium", - "browser_version": page.context.browser.version, + "browser_version": browser.version, "user_agent": page.evaluate("navigator.userAgent"), "viewport": list(backend.viewport), "device_scale_factor": 1, @@ -275,18 +559,46 @@ def _record( app_url=entry_url, system_of_record_reader=_records_reader(base_url), ) + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.click(*_center(page, ".open-btn")) + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.click(*_center(page, "#new-encounter")) + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.click(*_center(page, "#type-triage")) + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.click(*_center(page, "#note-label")) + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.type_text(NOTE, param="note") + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.click(*_center(page, "#save-encounter")) page.wait_for_selector("#saved-banner", state="visible") page.wait_for_timeout(250) + presentation.emitter.emit_phase( + "recording", observation_png=backend.screenshot() + ) recorder.finish() + _browser_network_observation(page, base_url=base_url) finally: close() _finish_video(video_tmp, media_dir / "recording.webm") + _write_presentation_clip( + capture=presentation, + pack_id=pack_id, + clip_id="demonstration", + presentation_dir=presentation_dir, + ) return environment @@ -439,6 +751,57 @@ def _origin(url: str) -> str: return url.rstrip("/").split("?", 1)[0] +def _require_loopback_url(url: str) -> None: + """Reject any configured or browser-observed off-box destination.""" + + parsed = urlsplit(url) + if ( + parsed.scheme not in {"http", "https"} + or parsed.username is not None + or parsed.password is not None + or parsed.hostname is None + ): + raise EvidencePackError(f"invalid public-demo network destination: {url!r}") + try: + loopback = ipaddress.ip_address(parsed.hostname).is_loopback + except ValueError: + loopback = parsed.hostname.lower() == "localhost" + if not loopback: + raise EvidencePackError( + f"public-demo observed an off-box network destination: {url!r}" + ) + + +def _browser_network_observation(page: Any, *, base_url: str) -> dict[str, Any]: + """Summarize actual browser destinations without publishing their URLs. + + The synthetic exporter configures only the loopback MockMed app/verifier. + Navigation and resource timing entries provide a second, browser-observed + check. This proves the bounded off-box/third-party boundary; it does not + pretend that loopback HTTP means zero network calls. + """ + + _require_loopback_url(base_url) + raw_urls = page.evaluate( + """() => [ + ...performance.getEntriesByType('navigation'), + ...performance.getEntriesByType('resource'), + ].map((entry) => entry.name)""" + ) + if not isinstance(raw_urls, list) or not raw_urls: + raise EvidencePackError("browser exposed no navigation/resource observations") + urls: list[str] = [] + for value in raw_urls: + if not isinstance(value, str) or not value: + raise EvidencePackError("browser returned an invalid network observation") + _require_loopback_url(value) + urls.append(value) + return { + "browser_request_count": len(urls), + "off_box_or_third_party_egress_observed": False, + } + + def _case_plan() -> list[dict[str, Any]]: """Machine conditions keyed to the canonical qualification case ids.""" @@ -564,6 +927,7 @@ def _outcome_envelope( report: RunReport, report_path: Path, oracle: dict[str, Any], + network_observation: dict[str, Any], ) -> dict[str, Any]: if report.execution_outcome is None: raise EvidencePackError("run report has no precise execution outcome") @@ -580,7 +944,11 @@ def _outcome_envelope( "execution_completed": report.execution_completed, "report_sha256": _sha256(report_path), "model_calls": report.model_calls, - "external_network_calls": 0, + "runtime_network_observation": report.external_network_calls, + "browser_request_count": network_observation["browser_request_count"], + "off_box_or_third_party_egress_observed": network_observation[ + "off_box_or_third_party_egress_observed" + ], "screenshots_may_leave_box": report.screenshots_may_leave_box, "duration_ms": report.total_ms, "wrong_target_action": oracle["wrong_target_action"], @@ -622,6 +990,8 @@ def _run_case_trial( case: dict[str, Any], trial: int, case_dir: Path, + presentation_dir: Path, + pack_id: str, ) -> tuple[RunReport, dict[str, Any], dict[str, Any]]: _http_json(f"{base_url}api/reset", method="POST", body={}) trial_dir = case_dir / f"trial-{trial:02d}" @@ -639,6 +1009,17 @@ def _run_case_trial( active_backend: PlaywrightBackend = backend if case.get("backend") == "stale_identity": active_backend = _StaleIdentityBackend(backend.page) + clip_id = ( + "verified" + if trial == 1 and case["case_id"] == "representative" + else "halted" + if trial == 1 and case["case_id"] == "fault-ambiguity" + else None + ) + presentation = ( + _PresentationCapture(mode="governed") if clip_id is not None else None + ) + network_observation: dict[str, Any] | None = None try: verifier = RestRecordVerifier( base_url, @@ -671,6 +1052,9 @@ def _run_case_trial( durable=True, require_settled=True, use_structural=bool(case["use_structural"]), + control_overlay=( + presentation.emitter if presentation is not None else None + ), ).run( workflow.model_copy(deep=True), params={"note": NOTE}, @@ -681,14 +1065,27 @@ def _run_case_trial( execution_entry_url=entry_url, ) backend.page.wait_for_timeout(200) + network_observation = _browser_network_observation( + backend.page, + base_url=base_url, + ) finally: close() + if network_observation is None: + raise EvidencePackError("run retained no browser network observation") if record_video: _finish_video( media_tmp, trial_dir / ("replay.webm" if case["expected"] == "VERIFIED" else "halt.webm"), ) + if presentation is not None and clip_id is not None: + _write_presentation_clip( + capture=presentation, + pack_id=pack_id, + clip_id=clip_id, + presentation_dir=presentation_dir, + ) report_path = run_dir / "report.json" render_run_report(run_dir) @@ -710,12 +1107,17 @@ def _run_case_trial( report=report, report_path=report_path, oracle=oracle, + network_observation=network_observation, ) _write_json(trial_dir / "outcome.json", envelope) if report.execution_outcome != case["expected"]: + failures = [ + result.error for result in report.results if not result.ok and result.error + ] raise EvidencePackError( f"{case['case_id']} trial {trial} observed " - f"{report.execution_outcome}, expected {case['expected']}" + f"{report.execution_outcome}, expected {case['expected']}; " + f"failures={failures}" ) if report.model_calls != 0 or report.screenshots_may_leave_box: raise EvidencePackError( @@ -728,7 +1130,11 @@ def _run_case_trial( return report, oracle, envelope -def _evidence_ref(root: Path, path: Path, kind: str) -> EvidenceRef: +def _evidence_ref( + root: Path, + path: Path, + kind: Literal["run_report", "identity", "effect", "fault_campaign", "other"], +) -> EvidenceRef: return EvidenceRef( kind=kind, sha256=_sha256(path), @@ -796,8 +1202,11 @@ def _copy_binding( with Image.open(source) as raw_image, Image.open(crop) as crop_image: x, y, width, height = step.anchor.region expected = raw_image.convert("RGB").crop((x, y, x + width, y + height)) - actual = crop_image.convert("RGB") - if expected.size != actual.size or expected.tobytes() != actual.tobytes(): + actual_image = crop_image.convert("RGB") + if ( + expected.size != actual_image.size + or expected.tobytes() != actual_image.tobytes() + ): raise EvidencePackError( f"compiled template pixels do not match raw frame region for {step.id}" ) @@ -929,6 +1338,46 @@ def _assemble_manifest( recording = root / "artifacts" / "recording" bundle = root / "artifacts" / "bundle" qualification = root / "artifacts" / "qualification" + presentation = root / "artifacts" / "presentation" + case_by_id = {str(case["case_id"]): case for case in cases} + if len(case_by_id) != len(cases): + raise EvidencePackError("public-demo case ids are not unique") + + def presentation_media(clip_id: str) -> dict[str, Any]: + return { + "media": _ref_for(root, presentation / f"{clip_id}.webm"), + "timeline": _ref_for( + root, presentation / f"{clip_id}.control-overlay.v2.json" + ), + "frame_pts": _ref_for(root, presentation / f"{clip_id}.frame-pts-us.json"), + } + + def run_presentation(clip_id: str, case_id: str) -> dict[str, Any]: + case = case_by_id.get(case_id) + if case is None: + raise EvidencePackError(f"presentation source case is missing: {case_id}") + return { + "source_kind": "run", + "case_id": case_id, + "trial": 1, + "report": case["reports"][0], + "outcome": case["outcome_envelopes"][0], + "oracle": case["oracles"][0], + "raw_media": case["media"], + **presentation_media(clip_id), + } + + network_observations = Counter(report.external_network_calls for report in reports) + browser_request_count = sum( + int(envelope["browser_request_count"]) + for case in cases + for envelope in case["outcomes"] + ) + off_box_egress_observed = any( + bool(envelope["off_box_or_third_party_egress_observed"]) + for case in cases + for envelope in case["outcomes"] + ) return { "schema_version": SCHEMA_VERSION, "pack": { @@ -965,7 +1414,11 @@ def _assemble_manifest( ), "outcome_counts": dict(sorted(outcomes.items())), "model_calls": sum(report.model_calls for report in reports), - "external_network_calls": 0, + "runtime_network_observation_counts": dict( + sorted(network_observations.items()) + ), + "browser_request_count": browser_request_count, + "off_box_or_third_party_egress_observed": off_box_egress_observed, "screenshots_may_leave_box": any( report.screenshots_may_leave_box for report in reports ), @@ -994,7 +1447,7 @@ def _assemble_manifest( "caveats": [ "First-party synthetic MockMed task; not customer production evidence.", "Bound to the exact app, browser, viewport, runtime, and source commit in this pack.", - "Loopback HTTP is used for the local app and independent read-back; no external service is contacted.", + "The runtime conservatively records network activity as observed. Every configured and browser-observed destination in this isolated campaign was loopback; no off-box or third-party egress was observed.", "Three trials per required condition establish this bounded campaign only.", "The synthetic reference app exposes a stable demo-mode idempotency key so the compiler can retain and verify a real at-most-once contract.", ], @@ -1024,6 +1477,17 @@ def _assemble_manifest( "passed": qualification_report["passed"], "minimum_effect_tier": int(project.minimum_effect_tier), }, + "presentation": { + "demonstration": { + "source_kind": "source_recording", + "raw_media": _ref_for( + root, root / "artifacts" / "media" / "recording.webm" + ), + **presentation_media("demonstration"), + }, + "verified": run_presentation("verified", "representative"), + "halted": run_presentation("halted", "fault-ambiguity"), + }, "cases": cases, "crop_bindings": crop_bindings, }, @@ -1105,11 +1569,18 @@ def export_pack( recording_dir = artifacts / "recording" bundle_dir = artifacts / "bundle" media_dir = artifacts / "media" + presentation_dir = artifacts / "presentation" qualification_dir = artifacts / "qualification" media_dir.mkdir(parents=True) base_url, _db, stop = serve() - environment = _record(base_url, recording_dir, media_dir) + environment = _record( + base_url, + recording_dir, + media_dir, + presentation_dir, + pack_id=pack_id, + ) workflow = compile_recording( recording_dir, bundle_dir, @@ -1147,6 +1618,8 @@ def export_pack( case=case, trial=trial, case_dir=case_dir, + presentation_dir=presentation_dir, + pack_id=pack_id, ) reports.append(report) trial_dir = case_dir / f"trial-{trial:02d}" @@ -1263,6 +1736,227 @@ def _safe_file(root: Path, relative: str) -> Path: return resolved +def _validate_presentation_artifacts( + root: Path, + *, + inventory: dict[str, dict[str, Any]], + pack_id: str, + artifacts: dict[str, Any], +) -> None: + presentation = artifacts["presentation"] + cases = {str(case["case_id"]): case for case in artifacts["cases"]} + if len(cases) != len(artifacts["cases"]): + raise EvidencePackError("public-demo case ids are not unique") + for clip_id in ("demonstration", "verified", "halted"): + clip = presentation[clip_id] + media_relative = str(clip["media"]["path"]) + timeline_relative = str(clip["timeline"]["path"]) + pts_relative = str(clip["frame_pts"]["path"]) + expected_prefix = f"artifacts/presentation/{clip_id}" + if ( + media_relative != f"{expected_prefix}.webm" + or timeline_relative != f"{expected_prefix}.control-overlay.v2.json" + or pts_relative != f"{expected_prefix}.frame-pts-us.json" + ): + raise EvidencePackError( + f"presentation mapping uses non-canonical paths: {clip_id}" + ) + for ref in (clip["media"], clip["timeline"], clip["frame_pts"]): + relative = str(ref["path"]) + if relative not in inventory: + raise EvidencePackError( + f"public presentation artifact is not inventoried: {relative}" + ) + media_path = _safe_file(root, media_relative) + media_sha256 = _sha256(media_path) + timeline = json.loads( + _safe_file(root, timeline_relative).read_text(encoding="utf-8") + ) + pts = json.loads(_safe_file(root, pts_relative).read_text(encoding="utf-8")) + if ( + set(pts) + != { + "schema_version", + "media_sha256", + "frame_count", + "presentation_times_us", + } + or pts.get("schema_version") != PRESENTATION_PTS_SCHEMA_VERSION + ): + raise EvidencePackError(f"invalid exact-PTS sidecar: {pts_relative}") + presentation_times_us = pts.get("presentation_times_us") + if ( + pts.get("media_sha256") != media_sha256 + or not isinstance(presentation_times_us, list) + or not presentation_times_us + or pts.get("frame_count") != len(presentation_times_us) + or presentation_times_us[0] != 0 + or any( + isinstance(value, bool) or not isinstance(value, int) or value < 0 + for value in presentation_times_us + ) + or any( + current <= previous + for previous, current in zip( + presentation_times_us, + presentation_times_us[1:], + ) + ) + ): + raise EvidencePackError( + f"exact-PTS sidecar does not bind decoded media: {pts_relative}" + ) + if ( + timeline.get("schema_version") != "openadapt.control-overlay-timeline/v2" + or timeline.get("data_classification") != "synthetic" + or timeline.get("evidence_pack_id") != pack_id + or timeline.get("media_sha256") != media_sha256 + or timeline.get("media_frame_count") != len(presentation_times_us) + or timeline.get("duration_ms") != presentation_times_us[-1] // 1_000 + ): + raise EvidencePackError( + f"control-overlay timeline does not bind media: {timeline_relative}" + ) + events = timeline.get("events") + if not isinstance(events, list) or not events: + raise EvidencePackError( + f"empty control-overlay timeline: {timeline_relative}" + ) + if len(presentation_times_us) != len(events) + 1: + raise EvidencePackError( + f"presentation media must add exactly one terminal hold frame: " + f"{media_relative}" + ) + expected_sequences = list(range(len(events))) + if [event.get("media_frame_index") for event in events] != expected_sequences: + raise EvidencePackError( + f"control-overlay frames are not one exact decoded sequence: " + f"{timeline_relative}" + ) + at_ms = [event.get("at_ms") for event in events] + if ( + at_ms[0] != 0 + or any( + isinstance(value, bool) or not isinstance(value, int) for value in at_ms + ) + or any(current <= previous for previous, current in zip(at_ms, at_ms[1:])) + ): + raise EvidencePackError( + f"control-overlay offsets are not zero-based and strict: " + f"{timeline_relative}" + ) + for event, expected_sequence in zip(events, expected_sequences, strict=True): + frame_index = event["media_frame_index"] + if event["at_ms"] * 1_000 != presentation_times_us[frame_index]: + raise EvidencePackError( + f"control-overlay event lacks an exact decoded-frame PTS: " + f"{timeline_relative}" + ) + frame = event.get("frame") + if ( + not isinstance(frame, dict) + or frame.get("event_sequence") != expected_sequence + or frame.get("presentation") is not True + ): + raise EvidencePackError( + f"invalid canonical overlay frame: {timeline_relative}" + ) + target = frame.get("target_tracking") + if target is not None: + binding = target.get("binding") if isinstance(target, dict) else None + if binding != { + "kind": "media_frame", + "media_sha256": media_sha256, + "frame_index": frame_index, + }: + raise EvidencePackError( + f"target geometry is not bound to its exact decoded frame: " + f"{timeline_relative}" + ) + frames = [event["frame"] for event in events] + if clip_id == "demonstration": + if ( + clip["source_kind"] != "source_recording" + or clip["raw_media"] != artifacts["source_recording"]["media"] + ): + raise EvidencePackError( + "demonstration presentation is not bound to the source recording" + ) + if any( + frame.get("mode") != "demonstration" + or frame.get("profile") != "demo" + or frame.get("phase") != "recording" + or frame.get("target_tracking") is not None + for frame in frames + ): + raise EvidencePackError( + "demonstration presentation must remain recording-only " + "and carry no execution proof" + ) + else: + case = cases.get(str(clip["case_id"])) + trial_index = int(clip["trial"]) - 1 + if ( + clip["source_kind"] != "run" + or case is None + or trial_index < 0 + or trial_index >= len(case["reports"]) + or clip["report"] != case["reports"][trial_index] + or clip["outcome"] != case["outcome_envelopes"][trial_index] + or clip["oracle"] != case["oracles"][trial_index] + or clip["raw_media"] != case["media"] + ): + raise EvidencePackError( + f"{clip_id} presentation source mapping does not match its case" + ) + report_path = _safe_file(root, str(clip["report"]["path"])) + report = RunReport.model_validate_json( + report_path.read_text(encoding="utf-8") + ) + outcome = json.loads( + _safe_file(root, str(clip["outcome"]["path"])).read_text( + encoding="utf-8" + ) + ) + oracle = json.loads( + _safe_file(root, str(clip["oracle"]["path"])).read_text( + encoding="utf-8" + ) + ) + expected_outcome = "VERIFIED" if clip_id == "verified" else "HALTED" + expected_terminal = expected_outcome.lower() + if ( + report.execution_outcome != expected_outcome + or report.execution_profile != "standard" + or outcome.get("report_sha256") != _sha256(report_path) + or outcome.get("observed_outcome") != expected_outcome + or outcome.get("expected_outcome") != expected_outcome + or outcome.get("matched_expectation") is not True + or oracle.get("passed") is not True + or any( + frame.get("mode") != "governed" + or frame.get("profile") != "standard" + for frame in frames + ) + or frames[-1].get("phase") != expected_terminal + ): + raise EvidencePackError( + f"{clip_id} presentation is not an exact governed outcome" + ) + if clip_id == "verified" and not any( + frame.get("target_tracking") is not None for frame in frames + ): + raise EvidencePackError( + "verified presentation retained no exact target geometry" + ) + terminal_hold_us = presentation_times_us[-1] - presentation_times_us[-2] + if terminal_hold_us != PRESENTATION_TERMINAL_HOLD_MS * 1_000: + raise EvidencePackError( + f"{clip_id} presentation terminal state is not retained for " + f"{PRESENTATION_TERMINAL_HOLD_MS}ms" + ) + + def validate_pack(pack_dir: Path | str) -> dict[str, Any]: root = Path(pack_dir).resolve(strict=True) manifest_path = _safe_file(root, "manifest.json") @@ -1325,6 +2019,20 @@ def validate_refs(value: Any) -> None: validate_refs(manifest["artifacts"]) artifacts = manifest["artifacts"] + exact_network_boundary = ( + "runtime_network_observation_counts" in manifest["evaluation"] + ) + if exact_network_boundary and "presentation" not in artifacts: + raise EvidencePackError( + "exact-bound public-demo pack is missing presentation provenance" + ) + if "presentation" in artifacts: + _validate_presentation_artifacts( + root, + inventory=inventory, + pack_id=str(manifest["pack"]["id"]), + artifacts=artifacts, + ) for binding in artifacts["crop_bindings"]: crop = _safe_file(root, binding["crop_path"]) source = _safe_file(root, binding["source_frame_path"]) @@ -1337,8 +2045,11 @@ def validate_refs(value: Any) -> None: with Image.open(source) as raw_image, Image.open(crop) as crop_image: x, y, width, height = binding["region"] expected = raw_image.convert("RGB").crop((x, y, x + width, y + height)) - actual = crop_image.convert("RGB") - if expected.size != actual.size or expected.tobytes() != actual.tobytes(): + actual_image = crop_image.convert("RGB") + if ( + expected.size != actual_image.size + or expected.tobytes() != actual_image.tobytes() + ): raise EvidencePackError( f"crop pixels are not bound to source frame: {binding['crop_path']}" ) @@ -1348,15 +2059,41 @@ def validate_refs(value: Any) -> None: silent_wrong = 0 wrong_target = 0 over_halts = 0 + report_count = 0 + total_duration_ms = 0.0 + runtime_network_observations: Counter[str] = Counter() + browser_request_count = 0 + off_box_egress_observed = False + screenshots_may_leave_box = False + case_ids: set[str] = set() + case_kinds: list[str] = [] + trials_per_case: set[int] = set() + evaluation = manifest["evaluation"] for case in artifacts["cases"]: + case_id = str(case["case_id"]) + if case_id in case_ids: + raise EvidencePackError(f"duplicate public-demo case id: {case_id}") + case_ids.add(case_id) + case_kinds.append(str(case["kind"])) expected = case["expected_outcome"] - if len(case["reports"]) < 3: - raise EvidencePackError(f"{case['case_id']} has fewer than 3 trials") - for report_ref, outcome_ref, oracle_ref in zip( - case["reports"], - case["outcome_envelopes"], - case["oracles"], - strict=True, + trial_count = len(case["reports"]) + trials_per_case.add(trial_count) + if trial_count < 3 or any( + len(case[key]) != trial_count + for key in ("outcome_envelopes", "outcomes", "oracles", "events") + ): + raise EvidencePackError( + f"{case_id} does not retain one complete artifact set per trial" + ) + for trial, (report_ref, outcome_ref, inline_outcome, oracle_ref) in enumerate( + zip( + case["reports"], + case["outcome_envelopes"], + case["outcomes"], + case["oracles"], + strict=True, + ), + start=1, ): report_path = _safe_file(root, report_ref["path"]) report = RunReport.model_validate_json( @@ -1369,34 +2106,98 @@ def validate_refs(value: Any) -> None: _safe_file(root, oracle_ref["path"]).read_text(encoding="utf-8") ) if ( - outcome["report_sha256"] != _sha256(report_path) + inline_outcome != outcome + or outcome["report_sha256"] != _sha256(report_path) or outcome["observed_outcome"] != report.execution_outcome or outcome["expected_outcome"] != expected + or outcome.get("case_id") != case_id + or outcome.get("trial") != trial or not outcome["matched_expectation"] or not oracle["passed"] + or outcome.get("screenshots_may_leave_box") + != report.screenshots_may_leave_box + or ( + exact_network_boundary + and ( + outcome.get("runtime_network_observation") + != report.external_network_calls + or not isinstance(outcome.get("browser_request_count"), int) + or isinstance(outcome.get("browser_request_count"), bool) + or outcome["browser_request_count"] < 1 + or outcome.get("off_box_or_third_party_egress_observed") + is not False + ) + ) ): raise EvidencePackError( f"case outcome/report/oracle mismatch: {case['case_id']}" ) outcomes[report.execution_outcome or ""] += 1 + report_count += 1 model_calls += report.model_calls + total_duration_ms += report.total_ms + runtime_network_observations[report.external_network_calls] += 1 + if exact_network_boundary: + browser_request_count += outcome["browser_request_count"] + off_box_egress_observed = off_box_egress_observed or bool( + outcome["off_box_or_third_party_egress_observed"] + ) + screenshots_may_leave_box = ( + screenshots_may_leave_box or report.screenshots_may_leave_box + ) silent_wrong += int(oracle["silent_incorrect_success"]) wrong_target += int(oracle["wrong_target_action"]) over_halts += int( report.execution_outcome == "HALTED" and expected != "HALTED" ) - evaluation = manifest["evaluation"] + qualification_report = json.loads( + _safe_file(root, artifacts["qualification"]["report"]["path"]).read_text( + encoding="utf-8" + ) + ) if ( dict(sorted(outcomes.items())) != evaluation["outcome_counts"] + or evaluation["case_count"] != len(case_ids) + or len(trials_per_case) != 1 + or evaluation["trials_per_case"] != next(iter(trials_per_case)) + or evaluation["run_count"] != report_count + or evaluation["run_count"] + != evaluation["case_count"] * evaluation["trials_per_case"] + or sorted(evaluation["required_case_kinds"]) != sorted(case_kinds) or model_calls != evaluation["model_calls"] + or ( + exact_network_boundary + and ( + dict(sorted(runtime_network_observations.items())) + != evaluation["runtime_network_observation_counts"] + or browser_request_count != evaluation["browser_request_count"] + or off_box_egress_observed + != evaluation["off_box_or_third_party_egress_observed"] + ) + ) + or not math.isclose( + total_duration_ms, + float(evaluation["total_duration_ms"]), + rel_tol=0.0, + abs_tol=1e-9, + ) or silent_wrong != evaluation["silent_incorrect_successes"] or wrong_target != evaluation["wrong_target_actions"] or over_halts != evaluation["over_halts"] or model_calls != 0 or silent_wrong != 0 or wrong_target != 0 - or evaluation["external_network_calls"] != 0 + or (exact_network_boundary and off_box_egress_observed) + or ( + not exact_network_boundary and evaluation.get("external_network_calls") != 0 + ) + or screenshots_may_leave_box != evaluation["screenshots_may_leave_box"] or evaluation["screenshots_may_leave_box"] is not False + or evaluation["required_contracts"] != qualification_report["case_count"] + or evaluation["passed_contracts"] != qualification_report["passed_case_count"] + or artifacts["qualification"]["passed"] != qualification_report["passed"] + or evaluation["minimum_effect_tier"] + != artifacts["qualification"]["minimum_effect_tier"] or evaluation["qualification_passed"] is not True ): raise EvidencePackError("evaluation aggregate does not match case evidence") @@ -1413,7 +2214,7 @@ def _parser() -> argparse.ArgumentParser: default=REPO_ROOT / "public-demo" / "evidence-packs", help="parent directory for the immutable pack", ) - parser.add_argument("--pack-id", default="mockmed-triage-v2") + parser.add_argument("--pack-id", default="mockmed-triage-v3") parser.add_argument("--trials", type=int, default=TRIALS_PER_CASE) parser.add_argument( "--allow-dirty", diff --git a/tests/test_public_demo_evidence.py b/tests/test_public_demo_evidence.py new file mode 100644 index 00000000..d89323a9 --- /dev/null +++ b/tests/test_public_demo_evidence.py @@ -0,0 +1,19 @@ +"""Retained public-demo packs remain independently verifiable.""" + +from pathlib import Path + +import pytest + +from scripts.export_public_demo_evidence import validate_pack + +REPO_ROOT = Path(__file__).resolve().parents[1] + + +@pytest.mark.parametrize( + "pack_id", + ["mockmed-triage-v1", "mockmed-triage-v2", "mockmed-triage-v3"], +) +def test_retained_public_demo_pack_validates(pack_id: str) -> None: + manifest = validate_pack(REPO_ROOT / "public-demo" / "evidence-packs" / pack_id) + + assert manifest["pack"]["id"] == pack_id diff --git a/tests/test_runtime_control_overlay.py b/tests/test_runtime_control_overlay.py index da3952c4..e4e5076e 100644 --- a/tests/test_runtime_control_overlay.py +++ b/tests/test_runtime_control_overlay.py @@ -231,6 +231,24 @@ def test_each_begin_rotates_private_observation_binding() -> None: assert first != second +def test_private_observation_sink_receives_bytes_outside_canonical_frame() -> None: + public_frames = [] + private_observations = [] + emitter = RuntimeControlOverlayEmitter( + public_frames.append, + observation_sink=lambda frame, png: private_observations.append( + (frame.event_sequence, png) + ), + unix_ms_clock=_clock([1_000]), + monotonic_ms_clock=_clock([50.0]), + ) + emitter.begin(profile="demo") + emitter.emit_phase("observing", observation_png=b"private-screen") + + assert private_observations == [(0, b"private-screen")] + assert "private-screen" not in public_frames[0].model_dump_json() + + class _Backend: viewport = (20, 20)