Track each ESP32 node independently instead of merging all CSI frames
into a single buffer. This enables per-node feature computation,
spatial awareness, and proper multi-node visualization.
Per-node CSI separation:
- Add NodeState struct with per-node frame_history, RSSI history,
features, classification, and smoothing state
- Compute features per-node using each node's own temporal history
- Add compute_fused_features() for backward-compatible aggregate
- Add smooth_and_classify_node() for per-node motion classification
- Add GET /api/v1/nodes endpoint for per-node health/status
- Add PerNodeFeatureInfo to WebSocket SensingUpdate messages
- Fix RSSI sign (use saturating_neg for correct negative dBm values)
- Node timeout: stale after 5s, removed after 30s
Dynamic classifier classes:
- Remove hardcoded CLASSES array and N_CLASSES constant
- Discover classes automatically from training data filenames
- Convention: train_<class>_<description>.jsonl
- Users can add any class by recording with appropriate filename
- Backward compatible with existing 4-class models via serde default
- AdaptiveModel now stores class_names as Vec<String>
UI changes:
- Dynamic node count display (was hardcoded "1 ESP32")
- Per-node status cards showing RSSI, variance, classification
- Color-coded node markers in 3D gaussian splat view
- Per-node RSSI history tracking in sensing service
- XSS-safe DOM element creation (no innerHTML with server data)
Addresses #237, #276, #51
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add Python WebSocket sensing server (ws_server.py) with ESP32 UDP CSI
and Windows RSSI auto-detect collectors on port 8765
- Add Three.js Gaussian splat renderer with custom GLSL shaders for
real-time WiFi signal field visualization (blue→green→red gradient)
- Add SensingTab component with RSSI sparkline, feature meters, and
motion classification badge
- Add sensing.service.js WebSocket client with reconnect and simulation fallback
- Implement sensing-only mode: suppress all DensePose API calls when
FastAPI backend (port 8000) is not running, clean console output
- ADR-019: Document sensing-only UI architecture and data flow
- ADR-020: Migrate AI/model inference to Rust with RuVector ONNX Runtime,
replacing ~2.7GB Python stack with ~50MB static binary
- Add ruvnet/ruvector as upstream remote for RuVector crate ecosystem
Co-Authored-By: claude-flow <ruv@ruv.net>
Taylor Dawson
ruv