feat: natural language query + production hardening

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

backend/tests/conftest.py

@@ -24,6 +24,7 @@ def client(mock_events_collection, mock_watermarks_collection, monkeypatch):
     monkeypatch.setattr("database.events_collection", mock_events_collection)
     monkeypatch.setattr("routes.fetch.events_collection", mock_events_collection)
     monkeypatch.setattr("routes.events.events_collection", mock_events_collection)
+    monkeypatch.setattr("routes.ask.events_collection", mock_events_collection)
     monkeypatch.setattr("watermark.watermarks_collection", mock_watermarks_collection)
     monkeypatch.setattr("routes.health.watermarks_collection", mock_watermarks_collection)
     monkeypatch.setattr("routes.fetch.get_watermark", lambda source: None)