3 Commits

Author SHA1 Message Date
Mathias Bergqvist
189ff89c34 feat(brain): add brain_answer and brain_classify MCP tools
All checks were successful
CI / Lint / Test / Vet (push) Successful in 11s
CI / Mirror to GitHub (push) Successful in 3s
Adds two new LLM-backed MCP tools to the ingestion service:

- brain_answer(query): BM25 retrieval + LLM synthesis → answer + sources
- brain_classify(text): classifies doc into type/title/tags via LLM

Adds llm.Router for primary→fallback routing (berget.ai → iguana).
Wired via BRAIN_LLM_PRIMARY_URL/BRAIN_LLM_FALLBACK_URL env vars;
no-op when unset so existing deployments are unaffected.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-12 11:06:17 +02:00
Mathias Bergqvist
3607920601 fix(lint): resolve all errcheck violations in ingestion module
All checks were successful
cd / Build and deploy (push) Successful in 10s
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s
2026-04-23 16:20:59 +02:00
Mathias Bergqvist
bf8a3fc11c feat(ingestion): add OpenAI-compatible LLM HTTP client with 429 retry 2026-04-22 22:29:24 +02:00