Commit Graph
2 Commits
Author SHA1 Message Date
Sameh Khamis 8480abf41c Read the voice actions' camera and picks through the renderer ports and take them off the Cesium list
The voice actions now take the camera pose, view target picks and screen
projection from the camera and query ports, and do their ellipsoid and
bounding-sphere maths with the geo modules. The HUD hands its own camera
port to the basemap label lookup. The only scene object still read is the
canvas, for its size.
2026-11-07 15:10:19 -08:00
Sameh Khamis c1f60cb7e7 Cut the Google requests the HUD summary makes on its own
The HUD builds place context for its AI summary whenever the camera
settles, and each build paid for up to four reverse geocodes plus a Nearby
Places search, even when no OpenAI key was configured to use them.

- Ask GET /api/openai/hud-summary/status once; with no summary configured,
  or after an unconfigured reply, make no place lookups for the page.
- Reverse-geocode at most two points: the view center and one viewport
  point.
- Reuse a lookup until the view center moves a quarter of the visible
  width, the camera's distance to it doubles or halves, or the camera
  crosses a lookup height. The reused points are asked again, so only a
  timeout, failure or empty answer spends.
- Repaint the last AI reply when a small pan leaves the context unchanged.

Cached-only hosts and voice context lookups are unchanged.
2026-10-28 14:59:33 -07:00