osm_query said "At least N" when the server capped its list, but handed
the places to the analyst engine with truncated:false, so "which of those
have emergency?" answered as if the list were whole. The handoff now
carries the cap and its caveat, and follow-ups (and their follow-ups)
stay incomplete with an unknown total.
From review: a row inside a large area pays a ray cast over every edge, so
20,000 rows against a 6,000-vertex outline made ~200 ms long tasks. The scan
now also yields once ~8 ms have passed, checked every 256 rows. An ambiguous
region refusal also tells the model the way back: resolve_area with the
picked candidateId, then analyst_query over that area.
osm_query handed its places to the analyst with no presentation, so "which of
those have emergency?" after "hospitals in Kathmandu" was answered as "anywhere
in the loaded data". The handoff now carries the scope the places were found
in ("inside Kathmandu" with its areaId, or "in view"), as an analyst count over
that area would.
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.
- 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
keep contacts counts, rows, scope and provenance on one retained snapshot
report capped cohorts as lower bounds
separate sibling tool cancellation from newer user turns
align track_entity validation across runtime and benchmark paths
- 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follow-ups and never lets a superseded query replace follow-up memory.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 Natural Earth and neighborhood packs were loaded with a JSON-attributed
import(). The Vite dev server answers that request with a JavaScript module,
which the browser rejects, so every analyst region scope failed and fell
through to a geocode lookup that could take 12-28 s.
- src/data/bundledJson.js fetches the pack from a new URL(..., import.meta.url)
asset in the browser; under Node the caller's attributed import runs.
- resolveRegionRingForQuery caps the geocode + admin-boundary rung at 3 s and
returns { error: 'region-timeout' }; the lookup keeps running and fills the
cache. The analyst query reports it as code 'region-timeout'. The Nepal
locator opts out of the budget.
- Unit tests for the loader, the timeout and the analyst error; the behavior
harness checks the Gulf of Mexico scope and retries Texas on region-timeout.
Co-authored-by: Bilawal Sidhu <[email protected]>
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