fix: WebSocket race condition, data source indicators, auto-start pose detection (#96)

* feat: RVF training pipeline & UI integration (ADR-036)

Implement full model training, management, and inference pipeline:

Backend (Rust):
- recording.rs: CSI recording API (start/stop/list/download/delete)
- model_manager.rs: RVF model loading, LoRA profile switching, model library
- training_api.rs: Training API with WebSocket progress streaming, simulated
  training mode with realistic loss curves, auto-RVF export on completion
- main.rs: Wire new modules, recording hooks in all CSI paths, data dirs

UI (new components):
- ModelPanel.js: Dark-mode model library with load/unload, LoRA dropdown
- TrainingPanel.js: Recording controls, training config, live Canvas charts
- model.service.js: Model REST API client with events
- training.service.js: Training + recording API client with WebSocket progress

UI (enhancements):
- LiveDemoTab: Model selector, LoRA profile switcher, A/B split view toggle,
  training quick-panel with 60s recording shortcut
- SettingsPanel: Full dark mode conversion (issue #92), model configuration
  (device, threads, auto-load), training configuration (epochs, LR, patience)
- PoseDetectionCanvas: 10-frame pose trail with ghost keypoints and motion
  trajectory lines, cyan trail toggle button
- pose.service.js: Model-inference confidence thresholds

UI (plumbing):
- index.html: Training tab (8th tab)
- app.js: Panel initialization and tab routing
- style.css: ~250 lines of training/model panel dark-mode styles

191 Rust tests pass, 0 failures. Closes #92.

Refs: ADR-036, #93

Co-Authored-By: claude-flow <ruv@ruv.net>

* fix: real RuVector training pipeline + UI service fixes

Training pipeline (training_api.rs):
- Replace simulated training with real signal-based training loop
- Load actual CSI data from .csi.jsonl recordings or live frame history
- Extract 180 features per frame: subcarrier amplitudes, temporal variance,
  Goertzel frequency analysis (9 bands), motion gradients, global stats
- Train calibrated linear CSI-to-pose mapping via mini-batch gradient descent
  with L2 regularization (ridge regression), Xavier init, cosine LR decay
- Self-supervised: teacher targets from derive_pose_from_sensing() heuristics
- Real validation metrics: MSE and PCK@0.2 on 80/20 train/val split
- Export trained .rvf with real weights, feature normalization stats, witness
- Add infer_pose_from_model() for live inference from trained model
- 16 new tests covering features, training, inference, serialization

UI fixes:
- Fix double-URL bug in model.service.js and training.service.js
  (buildApiUrl was called twice — once in service, once in apiService)
- Fix route paths to match Rust backend (/api/v1/train/*, /api/v1/recording/*)
- Fix request body formats (session_name, nested config object)
- Fix top-level await in LiveDemoTab.js blocking module graph
- Dynamic imports for ModelPanel/TrainingPanel in app.js
- Center nav tabs with flex-wrap for 8-tab layout

Co-Authored-By: claude-flow <ruv@ruv.net>

* fix: WebSocket onOpen race condition, data source indicators, auto-start pose detection

- Fix WebSocket onOpen race condition in websocket.service.js where
  setupEventHandlers replaced onopen after socket was already open,
  preventing pose service from receiving connection signal
- Add 4-state data source indicator (LIVE/SIMULATED/RECONNECTING/OFFLINE)
  across Dashboard, Sensing, and Live Demo tabs via sensing.service.js
- Add hot-plug ESP32 auto-detection in sensing server (auto mode runs
  both UDP listener and simulation, switches on ESP32_TIMEOUT)
- Auto-start pose detection when backend is reachable
- Hide duplicate PoseDetectionCanvas controls when enableControls=false
- Add standalone Demo button in LiveDemoTab for offline animated demo
- Add data source banner and status styling

Co-Authored-By: claude-flow <ruv@ruv.net>

ui/services/pose.service.js

@@ -21,13 +21,17 @@ export class PoseService {
     };
     this.validationErrors = [];
     this.logger = this.createLogger();
-    
+
+    // Model inference mode tracking
+    this.modelActive = false;
+
     // Configuration
     this.config = {
       enableValidation: true,
       enablePerformanceTracking: true,
       maxValidationErrors: 10,
       confidenceThreshold: 0.3,
+      confidenceThresholdModelInference: 0.15,
       maxPersons: 10,
       timeoutMs: 5000
     };
@@ -127,9 +131,14 @@ export class PoseService {
       throw new Error(`Invalid stream options: ${validationResult.errors.join(', ')}`);
     }
 
+    // Use a lower confidence threshold when model inference is active
+    const defaultThreshold = this.modelActive
+      ? this.config.confidenceThresholdModelInference
+      : this.config.confidenceThreshold;
+
     const params = {
       zone_ids: options.zoneIds?.join(','),
-      min_confidence: options.minConfidence || this.config.confidenceThreshold,
+      min_confidence: options.minConfidence || defaultThreshold,
       max_fps: options.maxFps || 30,
       token: options.token || apiService.authToken
     };
@@ -494,9 +503,18 @@ export class PoseService {
       };
     }
 
-    // Extract persons from zone data
-    const persons = zoneData.pose.persons || [];
-    console.log('👥 Extracted persons:', persons);
+    // Determine the pose source for this message
+    const poseSource = originalMessage.pose_source || zoneData.pose_source || null;
+
+    // Choose confidence threshold based on pose source
+    const threshold = (poseSource === 'model_inference' || this.modelActive)
+      ? this.config.confidenceThresholdModelInference
+      : this.config.confidenceThreshold;
+
+    // Extract persons from zone data, applying source-aware filtering
+    const rawPersons = zoneData.pose.persons || [];
+    const persons = rawPersons.filter(p => p.confidence === undefined || p.confidence >= threshold);
+    console.log('Extracted persons:', persons.length, '/', rawPersons.length, '(threshold:', threshold, ')');
     
     // Create zone summary
     const zoneSummary = {};
@@ -511,7 +529,7 @@ export class PoseService {
       persons: persons,
       zone_summary: zoneSummary,
       processing_time_ms: zoneData.metadata?.processing_time_ms || 0,
-      pose_source: originalMessage.pose_source || zoneData.pose_source || null,
+      pose_source: poseSource,
       metadata: {
         mock_data: false,
         source: 'websocket',
@@ -653,6 +671,14 @@ export class PoseService {
     this.logger.info('Configuration updated', { config: this.config });
   }
 
+  // Enable or disable model inference mode.
+  // When active, confidence thresholds are lowered because model inference
+  // produces more reliable detections than raw signal-derived heuristics.
+  setModelMode(active) {
+    this.modelActive = !!active;
+    this.logger.info('Model mode updated', { modelActive: this.modelActive });
+  }
+
   // Health check
   async healthCheck() {
     try {