Commit Graph
8 Commits
Author SHA1 Message Date
manjunath22466 0343b4495e fix the remaining voice review gaps
keep analyst counts, speech, cards, cancellation, pointer capture, tool schema boundaries, and session lifetime consistent
add the exact Alps fallback and focused regression coverage
2026-10-05 04:37:28 +05:30
Bilawal Sidhu e7cb9b02b5 Merge main into feat/voice-core
Keeps the voice-core prompt rules and adds main's world-query and
vessels-vs-visuals rules; the tool catalog wraps the deixis-aware runner.

Also fixes two things the branch had before the merge:
- Live voice could not start: OpenAI rejects track_entity's top-level
  anyOf. Model-facing tools now omit top-level combinators; the runner
  and benchmark still require a query or a referent.
- The Contacts-centred analyst answer dropped the viewport coverage note.
2026-10-03 23:30:02 -07:00
Sameh Khamis 1a03e7483d feat: share the tool catalog with voice 2026-10-01 13:52:36 -07:00
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  follow-ups and never lets a superseded query replace follow-up memory.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
Sameh Khamis cc9a080f2d refactor(voice): separate Realtime state and resource owners 2026-09-15 12:05:01 -07:00
Sameh Khamis 57d7f9fc23 feat(search): compose Google and Photon through an explicit provider service 2026-09-12 15:38:43 -07:00
manjunath22466 5228ab9e40 fix: preserve keyboard focus and separate Space activation from voice
Keep focus visible across controls and stable during Contacts, Cockpit and mission roster updates. Preserve native short Space activation, and claim push-to-talk only after a 500 ms hold. Add panel Escape handling and keyboard-accessible attribution controls.

Retains the Map Source foundation contributed in https://github.com/bilawalsidhu/gods-eye-view/pull/171.
2026-09-10 23:48:12 -07:00
Bilawal Sidhu 880a672b5e Release God's Eye View as open source 2026-08-24 17:02:16 -05:00