- Replace single-owner rating with per-user ratings stored in agent_ratings collection
- Any authenticated user can now rate any agent; average is computed and stored on agent doc
- Add GET /api/agents/{id}/my-rating endpoint for fetching user's own rating
- Add rating framework info modal showing 1-5 scale definitions and 4 performance areas
- Add "Pencil Agents" discipline with auto-tagging for agents with "pencil" in name
- Run Pencil migration on startup and auto-tag in collector API
- Remove star rating from edit modals (rating is now per-user, not admin-set)
- Add rating_count field to AiAgentResponse and CSV export
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add audit status filter (Audited/Not Audited) to agent management and admin dashboard
- Add token usage tracking: token_count per timeline entry, total_tokens on agents
- Token badge on agent cards, Total Tokens stat in usage modal, dual-axis chart
- Sort by Total Tokens option, total_tokens in CSV export
- Mailgun email notifications for high token usage (optional, non-blocking)
- Cooldown-based notification tracking in MongoDB token_notifications collection
- Add promote_admin.py utility script for user promotion
- Update CLAUDE.md documentation for all new features
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
