test: update reliability regressions

Author: elkaix

tests/core/test_default_agent.py

@@ -97,7 +97,8 @@ async def test_default_agent(runtime: Runtime):
 - No "flexibility" or "configurability" that wasn't requested.
 - No error handling for impossible scenarios; validate at boundaries only.
 - If a 200-line draft could be 50 lines, rewrite it before showing it.
-- Self-check: *"Would a senior engineer call this overcomplicated?"* If yes, simplify.
+- Over-fragmentation is overcomplication too: don't scatter logic across many tiny files or extra abstraction layers to satisfy a design pattern. Match the codebase's existing granularity.
+- Self-check: *"Would a senior engineer call this overcomplicated or over-engineered?"* If yes, simplify.
 
 **3. Goal-driven execution — define success criteria, then loop until verified.**
 - Transform vague tasks into verifiable goals before writing code:

tests/telemetry/test_instrumentation.py

@@ -416,6 +416,22 @@ def test_queue_overflow_preserves_newest(self):
 # ---------------------------------------------------------------------------
 
 
+def _mock_store_for(runtime: Any) -> MagicMock:
+    """A mock BackgroundTaskStore whose ``update_runtime`` runs the callback and
+    returns the (mutated) runtime, mirroring the real read-modify-write store so
+    the manager's ``_transition_status`` path is actually exercised."""
+    store = MagicMock()
+    store.read_runtime.return_value = runtime
+
+    def _update(task_id: str, update_fn: Any) -> Any:
+        rt = store.read_runtime(task_id)
+        update_fn(rt)
+        return rt
+
+    store.update_runtime.side_effect = _update
+    return store
+
+
 class TestEventPropertyCorrectness:
     """Verify specific events carry the right property types and values."""
 
@@ -608,8 +624,7 @@ def test_background_task_no_event_without_start_time(self):
         from pythinker_code.background.models import TaskRuntime
 
         runtime = TaskRuntime(status="running", started_at=None)
-        mock_store = MagicMock()
-        mock_store.read_runtime.return_value = runtime
+        mock_store = _mock_store_for(runtime)
 
         manager = object.__new__(BackgroundTaskManager)
         manager._store = mock_store
@@ -626,8 +641,7 @@ def test_mark_task_killed_emits_completed_event(self):
 
         runtime = TaskRuntime(status="running", started_at=1000.0)
 
-        mock_store = MagicMock()
-        mock_store.read_runtime.return_value = runtime
+        mock_store = _mock_store_for(runtime)
 
         manager = object.__new__(BackgroundTaskManager)
         manager._store = mock_store
@@ -647,8 +661,7 @@ def test_mark_task_killed_no_event_without_start_time(self):
         from pythinker_code.background.models import TaskRuntime
 
         runtime = TaskRuntime(status="running", started_at=None)
-        mock_store = MagicMock()
-        mock_store.read_runtime.return_value = runtime
+        mock_store = _mock_store_for(runtime)
 
         manager = object.__new__(BackgroundTaskManager)
         manager._store = mock_store

tests/test_release_update_pipeline.py

@@ -36,7 +36,7 @@ def test_release_is_promoted_only_after_update_assets_are_ready() -> None:
     # Promotion clears prerelease AND marks latest, and only after the wait.
     assert "-F prerelease=false" in promote_workflow
     assert "-f make_latest=true" in promote_workflow
-    assert promote_workflow.index("Wait for all release assets") < promote_workflow.index(
+    assert promote_workflow.index("Wait for install-channel readiness") < promote_workflow.index(
         "-F prerelease=false"
     )
 
@@ -67,15 +67,22 @@ def test_install_scripts_gate_on_asset_readiness() -> None:
 def test_release_asset_wait_covers_all_updater_channels() -> None:
     promote_workflow = (WORKFLOWS / "promote-release.yml").read_text()
 
-    for expected_asset_fragment in (
-        "PythinkerSetup-",
-        "_amd64.deb",
-        "_arm64.deb",
-        ".x86_64.rpm",
-        ".aarch64.rpm",
-        "x86_64-unknown-linux-gnu.tar.gz",
-        "aarch64-unknown-linux-gnu.tar.gz",
-        "aarch64-apple-darwin.tar.gz",
-        "x86_64-apple-darwin.tar.gz",
+    for expected_readiness_marker in (
+        "PythinkerSetup-${version}.exe.sha256",
+        "pythinker-code_${version}_amd64.deb.sha256",
+        "pythinker-code_${version}_arm64.deb.sha256",
+        "pythinker-code-${version}.x86_64.rpm.sha256",
+        "pythinker-code-${version}.aarch64.rpm.sha256",
+        "pythinker-${version}-x86_64-unknown-linux-gnu.tar.gz.sha256",
+        "pythinker-${version}-aarch64-unknown-linux-gnu.tar.gz.sha256",
+        "pythinker-${version}-aarch64-apple-darwin.tar.gz.sha256",
+        "pythinker-${version}-x86_64-apple-darwin.tar.gz.sha256",
+        "pythinker-${version}-x86_64-unknown-linux-gnu-onedir.tar.gz.sha256",
+        "pythinker-${version}-aarch64-unknown-linux-gnu-onedir.tar.gz.sha256",
+        "pythinker-${version}-aarch64-apple-darwin-onedir.tar.gz.sha256",
+        "pythinker-${version}-x86_64-apple-darwin-onedir.tar.gz.sha256",
+        "https://pypi.org/pypi/pythinker-code/${version}/json",
+        "raw.githubusercontent.com/TechMatrix-labs/homebrew-pythinker",
+        'version \\"${version}\\"',
     ):
-        assert expected_asset_fragment in promote_workflow
+        assert expected_readiness_marker in promote_workflow