83b0ab7cd3
Scope auxiliary LLM endpoints by owner ( #2996 )
...
* fix(auth): scope auxiliary llm endpoints by owner
* fix(auth): scope auxiliary llm fallbacks by owner
2026-06-07 14:47:44 +02:00
a3cb15d0a1
fix(agent): enforce guide-only tool policy ( #3088 )
2026-06-06 18:48:24 -06:00
6ccd4500d7
fix(chat): show requested and actual reply models
...
Show requested and actual reply models in chat labels when fallback or provider routing changes the responding model.
2026-06-06 04:30:16 -06:00
545e692565
fix(auth): distinguish empty model allowlists ( #2938 )
...
Co-authored-by: ghreprimand <203024559+ghreprimand@users.noreply.github.com >
2026-06-05 20:27:10 +02:00
c12c2aa233
fix: normalize Gemma 4 thought-channel output ( #2224 )
2026-06-04 19:26:58 +02:00
ec3b8b42ae
fix: auto-naming for 24h time format ( #1374 )
...
* fix: auto-naming for 24h time format
needs_auto_name() required AM/PM suffix for default
frontend-generated names like 'deepseek-v4-flash 17:46:02'.
Frontend uses toLocaleTimeString() which outputs 24h
format in most locales — so the regex never matched and
auto-naming silently skipped.
Made AM/PM optional and added re.IGNORECASE for 'am'/'pm'.
* test: add regression tests for needs_auto_name (24h + 12h + custom)
---------
Co-authored-by: Calculator Dev <dev@calculator.local >
2026-06-03 14:14:34 +09:00
4771d80eb2
Harden session endpoint owner scope ( #1308 )
2026-06-03 02:40:22 +09:00
fd89d098a1
Chat: use cached endpoint model ids before probing
2026-06-02 21:00:58 +09:00
c3228f8b59
Background tasks: respect active session model fallback
2026-06-02 20:57:42 +09:00
2c4b8b57dd
feat(ai): add OpenRouter and Ollama Cloud providers ( #231 )
...
Co-authored-by: Alex Kenley <Alex.Kenley@threatvectorsecurity.com >
2026-06-01 14:26:10 +09:00
e5c99a5eee
Odysseus v1.0
2026-05-31 23:58:26 +09:00
Vykos