feat: M2 AI tips — LiteLLM gateway, context assembler, end-to-end generation pipeline

Issues closed: #86, #87, #88, #89, #90, #91, #79, #80, #82

infra:
- docker-compose `ai` profile: Ollama + LiteLLM services
- infra/litellm/litellm_config.yaml: tip-generator / embedder / judge aliases
- .env.example: LITELLM_URL, LITELLM_MASTER_KEY, OLLAMA_URL

ml/serving:
- POST /generate: calls LiteLLM tip-generator alias, returns TipCandidate[]
- JSON retry loop (2 retries with correction prompt on malformed response)
- _parse_llm_json strips markdown fences

ml/features:
- context.py: build_context() assembles user signals → PromptContext
  (sorts overdue/high-priority tasks first for LLM prompt quality)

shared-types:
- TipKind, TipSource, TipCandidate types
- Tip gains kind + rationale fields

services/api:
- recommender: 3-stage pipeline (assemble → score → serve)
  Stage 1: Todoist tasks + LLM candidates fetched in parallel
  Stage 2: egreedy bandit scores merged candidate pool
  Stage 3: serve + log with prompt_version, llm_model, tip_kind
- tip_scores: prompt_version, llm_model, tip_kind columns + migrations
- config: LITELLM_URL added
- integrations: surface token_status in /integrations response

tests:
- ml/serving/tests/test_generate.py: 13 tests (retry, 502/503, fence variants)
- ml/features/test_context.py: 9 tests (sorting, edge cases)
- services/api recommender.unit.test.ts: 16 pure-function tests (inferReward, dueAgeDays)
- services/api recommender.test.ts: 4 integration tests (tip_scores columns, LLM fallback)
- shared-types: TipCandidate, rationale, full TipFeedback action set

docs:
- ADR-0008: LiteLLM AI gateway decision
- overview.md: M2 pipeline description updated
- ml/README.md: serving + features roles updated

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

services/api/src/db/schema.ts

@@ -20,6 +20,7 @@ export const integrationTokens = sqliteTable('integration_tokens', {
   accessToken: text('access_token').notNull(),
   refreshToken: text('refresh_token'),
   expiresAt: text('expires_at'),
+  tokenStatus: text('token_status').notNull().default('active'), // 'active' | 'needs_reconnect'
   connectedAt: text('connected_at').notNull(),
 });
 
@@ -81,6 +82,9 @@ export const tipScores = sqliteTable('tip_scores', {
   candidateCount: integer('candidate_count'),
   latencyMs: integer('latency_ms'),
   servedAt: text('served_at').notNull(),
+  promptVersion: text('prompt_version'),             // e.g. 'v1' — tracks which prompt template generated this tip
+  llmModel: text('llm_model'),                       // e.g. 'tip-generator/qwen2.5:7b' — null for bandit-only tips
+  tipKind: text('tip_kind'),                         // 'task' | 'advice' | 'insight' | 'reminder'
 });
 
 // ── Simulation runs ──────────────────────────────────────────────────────────