Rebuilds the agent registration form into 7 governance sections (Identity,
Classification, Autonomy, IP, Tech Stack, Data Safety, Performance, Declarations)
and introduces a completion flow for agents that come in via the LibreChat
collector without the new required fields.
- New form fields: business_entity, client_scope, agent_classification,
autonomy_level, ip_ownership, foundation_model, validated_by/date, evals_method,
plus nested safety / pii / declarations objects and a registration_complete flag.
- registration_complete defaults to true for form-submitted agents and false for
collector-created ones; existing agents are grandfathered via a startup migration.
- Owner-by-email lookup so LibreChat-synced agents surface in the user's "My Agents"
view with an Incomplete badge and Complete CTA. Submitting the completion form
reassigns created_by from the collector marker to the user.
- Daily APScheduler job sends a digest reminder email per owner with a 7-day
cooldown and 4-nudge cap (configurable). Manual trigger via
POST /api/admin/completion-reminders/send.
- Admin banner + modal for collector agents whose contact email doesn't match an
active user, with one-click reassignment.
- Gemini audit extended to also return agent_classification and an autonomy hint;
applied to agents on next batch run alongside discipline/department.
- New filter dimensions on agent management + admin dashboard: Business Entity,
Agent Type, Autonomy, plus a Compliance Risks quick toggle.
- CSV export/import gains 21 columns covering all governance fields.
- Discipline 'Optimization' renamed to 'Optimisation' with idempotent startup
migration; Gemini system prompt and template dropdowns updated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds Gemini-powered agent classification system that analyzes agent instructions
to determine category, risk level, discipline, and client detection. Includes
admin Prompt Audit tab, audit review workflow, and auto-classification on sync.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Three-tier role system: user, admin, readonly_admin with dashboard gating
- Client field (Yes/No) on registration with conditional Client Name and Studio Name
- Auto-tag client agents as "needs_verification" with Verification tab on admin dashboard
- Client agent email notification via Mailgun to configured recipients
- Daily agent digest email scheduled via APScheduler (configurable hour)
- Manual digest trigger endpoint: POST /api/admin/digest/send
- Role dropdown replaces is_admin checkbox in user edit modal
- Registration form reordered: Name, Description, Purpose, Client, Client Name, Studio, Tool
- Stat card CSS fix for text truncation on admin dashboard
- Updated CLAUDE.md documentation and PLAN file
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Supports the token breakdown (prompt/completion) now sent by agent-sync
from LibreChat's transactions collection. Updates models, collector
endpoint, usage stats, CSV export, and agent card/modal display.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 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 discipline (business category) and rating (1-5 stars) fields to agent models
- Discipline dropdown on registration form (required) and edit modals (both user and admin)
- Interactive star rating widget with immediate save via PUT /api/agents/{id}/rating
- Discipline filter and rating sort on agent management dashboard
- Purple discipline badge and gold star badge on agent cards
- CSV export/import support for discipline, rating, and total_tokens
- Initialize total_tokens on manually-created agents for consistent CSV exports
- Search agents by discipline field
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>
- Show both Microsoft SSO and local login options on login page
- Add admin user management: create local users with password
- Add admin password reset for local users only
- Add self-service password change on profile page for local users
- Display auth provider (Local/SSO) in admin user table
- New API endpoints: POST /api/admin/users, POST /api/admin/users/{email}/reset-password, POST /api/users/change-password
- SSO and local auth remain separate (no dual-auth)
- Minimum 8 character password requirement
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
