Both stack parents (#837, #842) are on main, so the voice geometry branch
now builds on main directly. Conflict resolutions keep main's behaviour and
add the geometry work on top: osm_query gating on every provider, restored
admin identity for Nominatim outlines, merged analyst follow-up memory, and
the cancelled Globe View reset instruction ahead of the generic cancellation.
It reads the token, model, transcription model and tier for diagnostics and
cost accounting, so the credential is not opaque to it. Also lists requestToken's
authMode option in APPLICATION.md.
- turn named places and mapped landmarks into reusable bounded areas
- count loaded records inside resolved, drawn and annotated geometry
- find recent imagery for an area, the view or the pointer snapshot
- keep osm place search behind an operator-configured overpass endpoint
- preserve cancellation, ownership and follow-up memory across every action
- cover geometry, provider lifecycle, cache isolation and voice routing
- 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follow-ups and never lets a superseded query replace follow-up memory.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.
The ownership table lists every owner except the backend, though realtimeBackend.js owns the two requests, their separate transports, the abort/timeout scope around both, and client-secret expiry.
The method signatures are already documented with application construction, so link there rather than repeat them, and state only the ownership facts written nowhere: the connection is the backend's only consumer in the application, the resolved credential is opaque to it and is handed to negotiate whole, and client-secret expiry is refused inside the backend.
Manjunath