chore: retire src/eval.ts and npm run eval (#24)

`src/eval.ts` and the `npm run eval` script have been dead-code-walking
since Stack E shipped `npm run sim` (improvements.md #16, resolved
2026-04-30). The two runners coexisting under similar names actively
misled engineers and customer forks.

This change deletes the legacy runner and scrubs all doc references.
The Vapi `/eval` REST endpoint, the `evals` resource type, the
`/eval/simulation/*` simulation API, and `docs/learnings/simulations.md`
are all unaffected — only the local CLI runner is gone.

If customer-fork automation still invokes `npm run eval`, swap to
`npm run sim -- <org> --suite <name> --target <name>`.

Author: dhruva-reddy

AGENTS.md

@@ -775,8 +775,6 @@ npm run rollback -- <org> --list                   # List available snapshots
 # Testing
 npm run call -- <org> -a <assistant-name>          # Call an assistant via WebSocket
 npm run call -- <org> -s <squad-name>              # Call a squad via WebSocket
-npm run eval -- <org> -s <squad-name>              # Run evals against a squad
-npm run eval -- <org> -a <assistant-name>          # Run evals against an assistant
 
 # Maintenance
 npm run cleanup -- <org>                           # Dry-run: show orphaned remote resources

README.md

@@ -76,7 +76,6 @@ Every command works in two modes:
 | `npm run apply` | ✅ | `npm run apply -- <org> [--force]` | Pull → Merge → Push in one shot |
 | `npm run call` | ✅ | `npm run call -- <org> -a <name>` | Start a WebSocket call |
 | `npm run cleanup` | ✅ | `npm run cleanup -- <org> [--force --confirm <org>]` | Delete orphaned remote resources (destructive run requires `--confirm <org>`) |
-| `npm run eval` | — | `npm run eval -- <org> -s <squad>` | Run evals against an assistant/squad |
 | `npm run build` | — | — | Type-check the codebase |
 | `npm test` | — | — | Run regression tests (`node:test`) |
 
@@ -142,10 +141,6 @@ npm run call -- my-org -a my-assistant
 
 # Call a squad
 npm run call -- my-org -s my-squad
-
-# Run evals
-npm run eval -- my-org -s my-squad
-npm run eval -- my-org -a my-assistant --filter booking
 ```
 
 ---
@@ -282,29 +277,6 @@ Squad push
   └─ all references resolved → create the squad ✓
 ```
 
-### Running Evals
-
-Evals run mock conversations against an assistant or squad and check assertions.
-
-```bash
-# Run all evals against a squad (transient — loaded from local files)
-npm run eval -- my-org -s my-squad
-
-# Run a specific eval by name filter
-npm run eval -- my-org -a my-assistant --filter booking
-
-# Use stored assistant/squad IDs from state (already pushed)
-npm run eval -- my-org -s my-squad --stored
-
-# Load assistant from a specific file path
-npm run eval -- my-org -a resources/my-org/assistants/qa-tester.md
-
-# Provide variable overrides
-npm run eval -- my-org -s my-squad -v eval-variables.json
-```
-
-Evals must be pushed first (`npm run push -- my-org evals`). Eval definitions live in `resources/<org>/evals/*.yml`.
-
 ---
 
 ## File Formats
@@ -536,7 +508,6 @@ vapi-gitops/
 │   ├── push.ts                 # Push local state to platform
 │   ├── apply.ts                # Orchestrator: pull → merge → push
 │   ├── call.ts                 # WebSocket call script
-│   ├── eval.ts                 # Eval runner
 │   ├── cleanup.ts              # Orphan cleanup
 │   ├── pull-cmd.ts             # Entry point: interactive or direct pull
 │   ├── push-cmd.ts             # Entry point: interactive or direct push

package.json

@@ -12,7 +12,6 @@
     "pull": "tsx src/pull-cmd.ts",
     "call": "bash -c 'exec tsx src/call-cmd.ts \"$@\" 2> >(grep --line-buffered -v \"buffer underflow\" >&2)' --",
     "cleanup": "tsx src/cleanup-cmd.ts",
-    "eval": "tsx src/eval.ts",
     "validate": "tsx src/validate-cmd.ts",
     "sim": "tsx src/sim-cmd.ts",
     "rollback": "tsx src/rollback-cmd.ts",