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.
Voice hears audio directly, and "vessels" is easily heard as "visuals",
which the instructions route to visual styles, so asking for vessels turned
on other layers or a CRT style. The instructions now say a vessels request
without a style name means the ships layer, and a style needs its name.
The voice instructions recommended aircraft_in_area, vessels_in_area and
get_earthquakes, which voice no longer offers, and the docs said voice gets
nearly every query. The instructions now name tools voice has and send
aircraft, ship and hazard questions to analyst_query; a test keeps the
instructions to tools the voice session lists.
- 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follow-ups and never lets a superseded query replace follow-up memory.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.
Wind (NOAA GFS and ECMWF IFS: animated particles, colour field, a reading at map centre), observed weather (NOAA MRMS radar, GOES and NESDIS infrared clouds, lightning density) on one shared history timeline, NHC and CPHC cyclone advisories with tracks and cones, and a WEATHER panel in the right rail. On 3D Tiles the observed products render as raised shells with a sharper window around the view.
Co-authored-by: Gustavo Beneduzi <[email protected]>
Co-authored-by: Daniel Slay <[email protected]>
Co-authored-by: Rehaan Delmotra <[email protected]>
Co-authored-by: Cursor Agent <[email protected]>
Sameh Khamis