- Replace broad service-level hiding with fine-grained operation-level gating
- PRIVACY_SENSITIVE_OPERATIONS config: hide specific operations across ALL services
- PRIVACY_SERVICES still works for broad service-level blocking (optional)
- Users without PRIVACY_SERVICE_ROLES:
* Don't see sensitive operations in /api/filter-options
* Can't query sensitive operations via /api/events or /api/ask
* Get 403 on /api/events/{id}/explain for sensitive events
- Exchange/Teams services remain visible; only privacy ops are hidden
- Update .env.example with new operation-level config docs
- Add AI_FEATURES_ENABLED config flag to gate AI/natural-language features
- Conditionally register /api/ask router based on AI_FEATURES_ENABLED
- Add GET /api/config/features endpoint for frontend feature detection
- Update frontend to hide Ask panel when AI features are disabled
- Implement standalone MCP server (backend/mcp_server.py) with tools:
* search_events, get_event, get_summary, ask
- Add mcp dependency to requirements.txt
- Update .env.example, AGENTS.md, and ROADMAP.md
- Bump VERSION to 1.3.0
- Bump LLM_MAX_EVENTS default from 50 to 200
- Add total_matched count to /api/ask response
- Include 'Showing X of Y total' header in LLM prompt so the model
knows when its view is a subset and avoids false certainty
- Update system prompt to instruct acknowledging scale when truncated
- Update test mocks to accept new total parameter
- Add LLM_API_VERSION config for Azure api-version query param
- Detect Azure endpoints and use api-key header instead of Bearer
- Handle base URLs that already include /chat/completions path
- Update .env.example with Azure OpenAI guidance
Features:
- Add /api/ask endpoint for plain-language audit log queries
- Regex-based time/entity extraction (no LLM required for parsing)
- LLM-powered narrative summarisation with OpenAI-compatible APIs
- Graceful fallback to structured bullet lists when LLM is unavailable
- Frontend ask panel with markdown rendering and cited events
Production:
- Harden Dockerfile: non-root user, gunicorn+uvicorn workers
- Add docker-compose.prod.yml with internal networks and health checks
- Add nginx reverse proxy with security headers
- MongoDB no longer exposed externally in production
Tests:
- 29 new tests for ask parsing, query building, and endpoint behaviour
- Fix conftest monkeypatch for routes.ask events collection
Bump version to 1.1.0
- Fix auth by using idToken fallback when accessToken audience mismatches
- Add PyJWT verification with audience-aware token selection in frontend
- Source health: track last_attempt_time and error status per source
- Frontend: fix modal outside x-data scope, add circular-safe JSON stringify
- Frontend: support multi-select service filter with All/None toggles
- Frontend: improve filter layout into organized rows
- Frontend: fix text overflow and result pill colors (success/succeeded)
- Intune: normalize application actors (auditActorType=Application)
- Add cache-control middleware for HTML/API responses
- Update tests for multi-service filtering and source health
- Migrate frontend to Alpine.js for reactive state management
- Add source health dashboard in UI and /api/source-health endpoint
- Add event tagging (PATCH /api/events/{id}/tags) and commenting (POST /api/events/{id}/comments)
- Add CSV/JSON export from the UI
- Add rule-based alerting engine (rules.py) with CRUD endpoints (/api/rules)
- Add SIEM export via webhook (siem.py)
- Add AOC audit trail middleware logging all mutations to aoc_audit collection
- Update config with SIEM_ENABLED, SIEM_WEBHOOK_URL, ALERTS_ENABLED
- Add tests for rules engine, tags, comments, and source health
