Detects when user changes same config setting 3+ times within 24 hours.
Shows non-intrusive prompt offering help with guided calibration flow.
Guided calibration features:
- Test for false positives (walk around room)
- Test for missed motion (sit still)
- Suggest optimal value based on diurnal baseline SNR and link health
- Apply suggested value button
Files:
- dashboard/js/proactive.js: Complete implementation with localStorage tracking
Acceptance:
- Help prompt fires after 3+ changes in 24h
- Calibration flow tests both directions
- Suggests value based on system data
- Apply button works
AnomalyDetector initialized in main() with periodic model updates.
Anomaly events broadcast to dashboard WS as 'alert' messages via
BroadcastAlert. GET /api/anomalies?since=24h lists recent events.
POST /api/security/arm and /api/security/disarm manage security mode.
GET /api/security/status returns armed state, learning progress, and
24h anomaly count. Arm/disarm state persisted to learning_state table
and restored on restart.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add explainability.js module with sidebar panel, X-ray overlay, Fresnel zone rendering
- Add explainability handler with /api/explain/{blobID} endpoint
- Fix viz3d.js CONFIG reference by adding FRESNEL_CONFIG constant
- Integrate explainability into fusion engine and ingestion server
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
