Phase 2 - AI Content Pipeline & Social Management:

== Backend Modules ==
- common/notification/: Notification engine (in-app, email, webhook, Slack, HMAC-signed)
- common/social/approval_gate.py: Editorial state machine (draft -> review -> approved -> published)
- common/social/post_queue.py: Post queue + calendar slot scheduling
- common/social/scheduler.py: Background publish engine (parallel, exponential backoff)
- common/media/image_processor.py: Media processor (Pillow resize, ffmpeg thumbnails)
- common/content_templates.py: 30+ fashion content templates + Vietnamese RSS feeds (ported from BrightBean builtin_templates.py 968L)

== API Routes ==
- api/notification_route.py: Notification CRUD + test endpoints
- api/content_approval_route.py: Approval workflow (approve/reject/submit)
- api/queue_route.py: Queue + calendar + posting slots
- api/media_route.py: Media library (upload/resize/delete)
- api/templates_route.py: Content templates + RSS feed catalog
- api/social_inbox_route.py: Unified social inbox (FB/IG/TikTok messages)

== Static Dashboards (zero-build) ==
- static/content-approval/index.html: Approval queue UI
- static/content-calendar/index.html: Weekly calendar + queue sidebar
- static/media-library/index.html: Drag-drop upload + asset grid + platform resize
- static/social-inbox/index.html: 3-column inbox (filters/list/detail) + reply/note composer
- static/content-composer/index.html: Post editor + templates + AI enhancement + schedule

== Server ==
- server.py: Registered all new routers + publish engine autostart + dashboard links in banner

fix(lead): Ensure Strict AI Selection via product_ids, Prevent search fallbacks and add proper Device ID logic

- Classifier (1 LLM call): classify stage via STAGE_JSON + call tools
- Stylist (1 LLM call): format response with optional stage context
- Removed _TOOL_STAGE_MAP hardcoded heuristic (stage is optional)
- Added re import for STAGE_JSON regex parsing
- Cleaned up debug logging

- New diagram agent: Planner generates Mermaid code, Responder explains
- FastAPI route: /api/diagram/chat + /clear with Redis session history
- Frontend: split-pane UI with canvas pan/zoom (scroll wheel + drag)
- Auto-fit diagram to view, grid background, PNG export
- Prompt enforces ASCII syntax labels for Mermaid compatibility
- Planner LLM max_tokens=4000 for complex diagram generation
- Supports: flowchart, sequence, class, ER, gantt, mindmap, pie chart

- HITL: Accept/Reject SQL before execution
- Chart.js: Auto-detect data shape -> render number cards/bar/doughnut/line
- Prompt: Verified StarRocks partition pruning rules (no DATE() on column)
- Summary: Agent provides 2-3 sentence Vietnamese explanation of results
- Fix: renderTraceDocument -> renderDataResults for history loading
- Auth: Login/admin pages, middleware, JWT auth
- Report Agent: Full report generation system
- New pages: stress-test, regression-test, user-simulator, competitor-research

- Add AI analytic dashboard (ai-analytic.html)
- Add report agent route and prompt
- Add langfuse analytics module
- Update middleware and server config

feat: add chat history analytics, product guide, experiment edit, docker network 10.101.10.x, workers=1