learning_ai_common_plat/services
saravanakumardb1 f542160784 feat(cowork-service): H.7 — wire @bytelyst/llm-router for multi-model routing
Added LLM routing module to cowork-service:
- lib/llm-router.ts — singleton LlmRouter with cloud + local Ollama support
- modules/llm/types.ts — Zod request schemas
- modules/llm/routes.ts — POST /api/llm/chat, GET /api/llm/providers, GET /api/llm/health
- All endpoints gated by llm_multi_model_enabled feature flag
- Best-effort init: service works without API keys (router stays uninitialized)
- 8 new tests (routes), server test updated for 3 route modules
- 57 total tests passing, typecheck clean
2026-04-02 23:10:07 -07:00
..
cowork-service feat(cowork-service): H.7 — wire @bytelyst/llm-router for multi-model routing 2026-04-02 23:10:07 -07:00
extraction-service feat(extraction): back product rate limits with valkey 2026-03-31 08:08:53 +00:00
mcp-server fix(mcp): align ChronoMind type enums with actual backend schema 2026-03-31 23:57:24 -07:00
monitoring feat(observability): add phase 2 monitoring and valkey services 2026-03-31 06:57:12 +00:00
platform-service feat(cowork-service): scaffold Fastify bridge + seed clawcowork feature flags (H.1 + H.2) 2026-04-02 20:39:22 -07:00