Carlos Garcia 564f1a9479 fix: raise Ollama timeout to 300s, add model pre-warming, improve health check ...

- OllamaBackend enforces _MIN_TIMEOUT=300s (overrides OLLAMA_TIMEOUT env var)
- warm_model() background task loads activeblue-chat into VRAM at startup
- health/detailed reports "warming" vs "ok" via Ollama ps() API
- README updated with May 2026 changes and test coverage details

2026-05-20 05:03:15 +00:00

..

__init__.py

feat(service): add FastAPI agent service with 5 routers and Docker setup

2026-04-12 17:54:28 -04:00

approval.py

feat(service): add FastAPI agent service with 5 routers and Docker setup

2026-04-12 17:54:28 -04:00

dispatch.py

fix: widen actions_taken to list[Any] and improve bot error replies

2026-05-16 16:31:45 -04:00

health.py

fix: raise Ollama timeout to 300s, add model pre-warming, improve health check

2026-05-20 05:03:15 +00:00

mcp_router.py

fix: resolve all 5 startup constructor errors + add DB retry

2026-04-24 16:48:23 -04:00

registry.py

fix: await get_all() in registry router and align get_all key names

2026-05-16 13:38:06 -04:00

sweep.py

feat(service): add FastAPI agent service with 5 routers and Docker setup

2026-04-12 17:54:28 -04:00

upload.py

refactor: remove scripted file intercept — LLM owns all responses

2026-05-19 21:05:38 -04:00