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

..

agents

Add comprehensive unit tests for all agent service components

2026-05-20 04:00:45 +00:00

llm

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

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

logging_utils

feat(infra): add sweep coordinator, structured logging, test suite, and README

2026-04-12 18:08:11 -04:00

mcp

feat(mcp): add MCP gateway — 14 tools over SSE, all agent calls forced local

2026-04-15 16:45:49 -04:00

memory

feat: OCR via tesseract, dedup, category selection for expense receipts

2026-05-16 01:40:32 -04:00

migrations

fix: MemoryManager kwarg 'llm' -> 'llm_router'; fix alembic script_location

2026-04-24 17:43:03 -04:00

prompts

refactor: remove scripted file intercept — LLM owns all responses

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

routers

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

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

tools

feat: elearning_agent — reduce tools 14 → 8 so it registers at startup

2026-05-19 23:02:51 -04:00

app_state.py

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

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

config.py

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

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

main.py

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

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