Files
gods-eye-view/docs/VOICE-OWNERSHIP.md
T
Bilawal Sidhu a19897ad15 feat(voice): voice core — honest layer reach, spoken summary with on-screen card, narration, point-and-ask
- Voice layer manifest (src/voice/layerManifest.js) generates the layer enums,
  aliases and analyst field hints; a test fails when a catalog layer has no entry.
- analyst_query validates fields, operators, units, values and scopes, counts up
  to 250,000 loaded records per layer, reports complete/partial/unanswered, tells
  LAYER_OFF / NOT_READY / FEED_UNAVAILABLE apart from zero, refuses mismatched
  follow-ups and never lets a superseded query replace follow-up memory. Seven
  more layers expose analyst records.
- Tool results carry a code-built say line and a display card; the voice card in
  the mic control shows captions, plan steps and the result
  (src/voice/resultDisplay.js is the one adapter). Slow tools narrate their
  current step out of band; holding Space while the assistant talks cuts it off.
  Turn spans go to the debug log; caption transcription is metered; the log
  omits what was said unless GEV_VOICE_LOG_CONTENT=1.
- Point and ask: the Space-down pointer snapshot resolves "this", "that one" and
  "around here" through 'pointer' targets, and "the second one" through
  referent:n from the last numbered list.
- Prompt states each policy once (instructions + tools 48.5k -> 46.7k chars).
- Voice benchmark harness (scripts/qa-voice-bench.mjs, scripts/voice-bench/)
  shares its phrase table and grading with scripts/qa-voice-routing.mjs.
2026-09-28 21:19:23 -05:00

55 lines
3.5 KiB
Markdown

# Realtime voice ownership
`realtimeController.js` composes the session and owns its status, UI bindings and
overall lifetime. It coordinates startup and shutdown. `realtimeFacade.js`
preserves existing methods and properties by delegation, without copying state.
The session adapter, action runner and backend interfaces remain unchanged.
| Owner | State and responsibility |
| --- | --- |
| `realtimeConnection.js` | Start generation, request cancellation, peer/data channel, acquired microphone stream and playback element |
| `realtimeTurns.js` | Active and superseded responses, pending confirmations, deduplicated calls and action cancellation |
| `realtimeRadio.js` | Speaker ducking, prepared playback, stronger-action reservations and playback observers |
| `realtimeInput.js` | Physical Space gesture, microphone mute, input/output meters and their frame/listener lifetime |
| `realtimeCost.js` | Next-session preferences and the current session's model-bound meter |
| `realtimeViewport.js` | One retained image, bounded deletion identities and capture generation |
| `realtimeDiagnostics.js` | Bounded error history and sanitized optional diagnostics |
| `turnMetrics.js` | Per-turn latency and speech spans written to the debug log |
| `narration.js` | Progress lines and the earcon while tools run; spoken through the turns owner |
| `pointerContext.js` | Pointer position, dwell pick and the current turn's pointer snapshot (session-scoped) |
| `referents.js` | Numbered items from the latest result for `referent:n` (session-scoped) |
| `resultDisplay.js` | What the voice card shows for a result and which items it numbers (read by the card and `referents.js`) |
| `gevActions.js` runner | Analyst follow-up memory (session: `resetConversation()` on stop, `dispose()` on removal) |
Pure input policy, preferences and protocol-response policy have separate modules.
Owners receive named readers, operations or focused collaborators. Cross-owner
cancellation uses operations; response handling does not own Radio's reservations
or viewport deletion bookkeeping.
Shutdown first invalidates acquisition and action work, then closes transport,
stops audio analysis, releases media and clears conversation/input state. Full
removal also detaches UI, keyboard, annotation and Radio observers. Radio takeover
retains confirmed playback through that same shutdown path. A late offer, peer callback,
viewport capture or cancelled meter frame cannot enter a replacement session.
Action and post-capture continuations retain their conversation identity before
publishing output, queueing a response or changing status.
Behavioral invariants remain in force: a 500 ms Space hold claims push-to-talk;
short control taps and text entry remain native; a claimed hold while the assistant speaks interrupts it (never during a Radio handoff); a click-started session stays
open-mic. Every accepted or refused tool call receives its terminal output once.
New typed input supersedes old intent. Radio waits for the spoken confirmation and
verified muted playback. A live cost meter stays bound to its negotiated model,
even when the next-session preference changes.
Run the unit suite and both live recorded-audio modes against a configured local
server:
```sh
node scripts/qa-voice-wav.mjs http://localhost:4173
node scripts/qa-voice-wav.mjs http://localhost:4173 --push-to-talk
```
The second mode uses the actual Space shortcut, verifies microphone acquisition
and release, and checks the same globe/Radio outcome. Tracking and scene-control
acceptance exercise voice's shared application operations separately.