saravanakumardb1 229ce4f00f feat(backend): wire Ollama LLM for context messages (TODO-005) ... Dual-path LLM enrichment for AI context prep messages: 1. extraction-service (if EXTRACTION_SERVICE_URL set) 2. Ollama direct (if OLLAMA_URL set) — non-streaming /api/generate 3. Keyword rules fallback 4. Generic fallback New env vars: OLLAMA_URL, OLLAMA_MODEL (default: gemma3:4b) Both LLM paths use 5s timeout and null-return-on-error pattern. Feature-gated behind ai_context_messages.enabled flag.		2026-04-13 17:00:24 -07:00
..
src	feat(backend): wire Ollama LLM for context messages (TODO-005)	2026-04-13 17:00:24 -07:00
.env.example	fix(backend): harden Phase A endpoints — Zod validation, feature flag gate, state filtering	2026-03-31 23:56:35 -07:00
.gitignore	feat(backend): scaffold product-specific Fastify backend (port 4011)	2026-03-01 20:39:08 -08:00
Dockerfile	fix(docker): .docker-deps COPY + optional secret + .npmrc.docker simplification	2026-04-13 14:05:54 -07:00
eslint.config.js	chore(backend): add eslint config and lint script	2026-03-26 22:59:50 -07:00
package.json	feat(backend): add domain event bus + webhook dispatch	2026-04-13 11:28:38 -07:00
tsconfig.json	feat(backend): scaffold product-specific Fastify backend (port 4011)	2026-03-01 20:39:08 -08:00
vitest.config.ts	feat(backend): scaffold product-specific Fastify backend (port 4011)	2026-03-01 20:39:08 -08:00