docs(x): fix pointers the reorg docs pass got wrong or missed

The Phase B docs pass introduced two errors in VIDEO_MODE.md's prompt
catalog (composer still at the pre-move agents/ path; frame-context
pointed at legacy/engine.ts when convertFromMessages lives in
runtime/assembly/message-encoding.ts) and missed ANALYTICS.md entirely
(copilot_chat emit point still cited agents/runtime.ts:1313, file_parse
still cited the deleted builtin-tools.ts monolith).
turn-runtime-design.md referenced the repo-root AGENTS.md, which is not
committed — the carve-out is now stated inline. Also drops a leftover
debug comment in skills/index.ts.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Ramnique Singh 2026-07-10 17:57:03 +05:30
parent 1f0cdbd366
commit d7c19a9a38
4 changed files with 8 additions and 9 deletions

View file

@ -176,10 +176,10 @@ Push-to-talk is disabled while a call owns the mic.
| Prompt | Where |
|--------|-------|
| `# Video Mode (Live Camera)` system section — how to use webcam frames, coaching guidance, screen-share rules ("treat the screen as the primary subject", "last screen frame is current"), etiquette (never comment on appearance) | `packages/core/src/runtime/assembly/capabilities/modes.ts` (the `VIDEO_MODE` fragment of the `video-mode` capability, composed by `agents/compose-instructions.ts`) |
| `# Video Mode (Live Camera)` system section — how to use webcam frames, coaching guidance, screen-share rules ("treat the screen as the primary subject", "last screen frame is current"), etiquette (never comment on appearance) | `packages/core/src/runtime/assembly/capabilities/modes.ts` (the `VIDEO_MODE` fragment of the `video-mode` capability, composed by `runtime/assembly/compose-instructions.ts`) |
| `# Practice Session (Coach Mode)` system section — coaching persona: specific/actionable feedback after each take, one-sentence interjections mid-flow, structured debrief on wrap-up | `capabilities/modes.ts` (the `COACH_MODE` fragment, directly after the video capability) |
| "Driving the app" paragraph in the video-mode section — on calls, prefer app-navigation read-view/open-item (show while telling) over describing or squinting at frames | same `# Video Mode` section; full action docs in the `app-navigation` skill (`runtime/assembly/skills/app-navigation/skill.ts`) |
| Per-message frame context line `[Video mode: N live webcam frames … and M frames of the user's shared screen …]` + group labels | `packages/core/src/runtime/legacy/engine.ts` (`convertFromMessages`) |
| Per-message frame context line `[Video mode: N live webcam frames … and M frames of the user's shared screen …]` + group labels | `packages/core/src/runtime/assembly/message-encoding.ts` (`convertFromMessages`) |
| `videoMode` / `coachMode` composition overrides (session-sticky; flips bust prefix cache) | `packages/core/src/runtime/turns/bridges/real-agent-resolver.ts` (`CompositionOverrides`); set from `App.tsx` `sendConfig` |
Voice input/output prompt sections (`# Voice Input`, `# Voice Output`) are