- 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
- Add keyword-based intent extraction: 'device' → Intune, 'user' → Directory, etc.
- Broad questions without intent auto-exclude noisy services (Exchange, SharePoint)
- Smart stratified sampling: failures always included, high-value services prioritised
- Fetch up to 1000 events from MongoDB, then curate best 200 for the LLM
- Excluded services noted in LLM prompt and query_info so the admin knows the scope
- Add GET /api/version endpoint that reads VERSION file
- Frontend fetches version on init and displays it as a badge in the header
- Add version-badge CSS styling
- Update docker-compose.yml comment to v1.2.5
When a query matches >50 events, the LLM now receives:
- Aggregated counts by service, operation, result, and actor
- A list of failures (up to 10)
- The 50 most recent raw events as samples
This scales to thousands of events without blowing the token budget
or losing signal. The LLM gets a bird's-eye view plus concrete examples.
Also updates the system prompt to handle both individual event lists
and aggregated overviews correctly.
- 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
- AskRequest now accepts optional filter fields: services, actor, operation,
result, start, end, include_tags, exclude_tags
- ask_question merges NL-extracted constraints with explicit UI filters
- Frontend sends active filter state with every ask request
- Show filter hint below ask input when filters are active
- Add tests for service+result filtering and actor filtering in /api/ask
Bump version to 1.2.0
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
- Add VERSION file (1.0.0)
- Add GitHub Actions release workflow to build and push Docker images to ghcr.io
- Update docker-compose.yml to pull ghcr.io/cqrenet/aoc-backend:v1.0.0 by default
