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.
This commit is contained in:
Bilawal Sidhu committed 2026-10-03 23:30:02 -07:00
commit e7cb9b02b5
191 files changed
+20005 -1450

No files matched your search

+2
View File
@@ -12,6 +12,7 @@
@import './src/ui/styles/bhote-koshi.css';
@import './src/ui/styles/recent-imagery.css';
@import './src/ui/styles/recording.css';
@import './src/ui/styles/embed.css';
@import './src/ui/styles/responsive.css';
@import './src/ui/styles/command-dock.css';
@import './src/ui/styles/command-dock-compact.css';
@@ -23,4 +24,5 @@
@import './src/ui/styles/provider-settings.css';
@import './src/ui/styles/weather.css';
@import './src/ui/styles/panel-surfaces.css';
@import './src/ui/styles/cyber.css';