fix: add wifi_densepose package so from wifi_densepose import WiFiDensePose works (#314)

The README Quick Start tells users to `pip install wifi-densepose` and then
`from wifi_densepose import WiFiDensePose`, but no `wifi_densepose` Python
package existed — only `v1/src`. This adds a top-level `wifi_densepose/`
package with a WiFiDensePose facade class matching the documented API, and
updates pyproject.toml to include it in the distribution.

Closes #314

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

README.md

@@ -14,7 +14,7 @@
 
 Instead of relying on cameras or cloud models, it observes whatever signals exist in a space such as WiFi, radio waves across the spectrum, motion patterns, vibration, sound, or other sensory inputs and builds an understanding of what is happening locally.
 
-Built on top of [RuVector](https://github.com/ruvnet/ruvector/), the project became widely known for its implementation of WiFi DensePose — a sensing technique first explored in academic research such as Carnegie Mellon University's *DensePose From WiFi* work. That research demonstrated that WiFi signals can be used to reconstruct human pose.
+Built on top of [RuVector](https://github.com/ruvnet/ruvector/) Self Learning Vector Memory system and [Cognitum.One](https://Cognitum.One) , the project became widely known for its implementation of WiFi DensePose — a sensing technique first explored in academic research such as Carnegie Mellon University's *DensePose From WiFi* work. That research demonstrated that WiFi signals can be used to reconstruct human pose.
 
 RuView extends that concept into a practical edge system. By analyzing Channel State Information (CSI) disturbances caused by human movement, RuView reconstructs body position, breathing rate, heart rate, and presence in real time using physics-based signal processing and machine learning.
 

docs/adr/ADR-067-ruvector-v2.0.5-upgrade.md

@@ -0,0 +1,151 @@
+# ADR-067: RuVector v2.0.4 to v2.0.5 Upgrade + New Crate Adoption
+
+**Status:** Proposed
+**Date:** 2026-03-23
+**Deciders:** @ruvnet
+**Related:** ADR-016 (RuVector training pipeline integration), ADR-017 (RuVector signal + MAT integration), ADR-029 (RuvSense multistatic sensing)
+
+## Context
+
+RuView currently pins all five core RuVector crates at **v2.0.4** (from crates.io) plus a vendored `ruvector-crv` v0.1.1 and optional `ruvector-gnn` v2.0.5. The upstream RuVector workspace has moved to **v2.0.5** with meaningful improvements to the crates we depend on, and has introduced new crates that could benefit RuView's detection pipeline.
+
+### Current Integration Map
+
+| RuView Module | RuVector Crate | Current Version | Purpose |
+|---------------|----------------|-----------------|---------|
+| `signal/subcarrier.rs` | ruvector-mincut | 2.0.4 | Graph min-cut subcarrier partitioning |
+| `signal/spectrogram.rs` | ruvector-attn-mincut | 2.0.4 | Attention-gated spectrogram denoising |
+| `signal/bvp.rs` | ruvector-attention | 2.0.4 | Attention-weighted BVP aggregation |
+| `signal/fresnel.rs` | ruvector-solver | 2.0.4 | Fresnel geometry estimation |
+| `mat/triangulation.rs` | ruvector-solver | 2.0.4 | TDoA survivor localization |
+| `mat/breathing.rs` | ruvector-temporal-tensor | 2.0.4 | Tiered compressed breathing buffer |
+| `mat/heartbeat.rs` | ruvector-temporal-tensor | 2.0.4 | Tiered compressed heartbeat spectrogram |
+| `viewpoint/*` (4 files) | ruvector-attention | 2.0.4 | Cross-viewpoint fusion with geometric bias |
+| `crv/` (optional) | ruvector-crv | 0.1.1 (vendored) | CRV protocol integration |
+| `crv/` (optional) | ruvector-gnn | 2.0.5 | GNN graph topology |
+
+### What Changed Upstream (v2.0.4 → v2.0.5 → HEAD)
+
+**ruvector-mincut:**
+- Flat capacity matrix + allocation reuse — **10-30% faster** for all min-cut operations
+- Tier 2-3 Dynamic MinCut (ADR-124): Gomory-Hu tree construction for fast global min-cut, incremental edge insert/delete without full recomputation
+- Source-anchored canonical min-cut with SHA-256 witness hashing
+- Fixed: unsafe indexing removed, WASM Node.js panic from `std::time`
+
+**ruvector-attention / ruvector-attn-mincut:**
+- Migrated to workspace versioning (no API changes)
+- Documentation improvements
+
+**ruvector-temporal-tensor:**
+- Formatting fixes only (no API changes)
+
+**ruvector-gnn:**
+- Panic replaced with `Result` in `MultiHeadAttention` and `RuvectorLayer` constructors (breaking improvement — safer)
+- Bumped to v2.0.5
+
+**sona (new — Self-Optimizing Neural Architecture):**
+- v0.1.6 → v0.1.8: state persistence (`loadState`/`saveState`), trajectory counter fix
+- Micro-LoRA and Base-LoRA for instant and background learning
+- EWC++ (Elastic Weight Consolidation) to prevent catastrophic forgetting
+- ReasoningBank pattern extraction and similarity search
+- WASM support for edge devices
+
+**ruvector-coherence (new):**
+- Spectral coherence scoring for graph index health
+- Fiedler eigenvalue estimation, effective resistance sampling
+- HNSW health monitoring with alerts
+- Batch evaluation of attention mechanism quality
+
+**ruvector-core (new):**
+- ONNX embedding support for real semantic embeddings
+- HNSW index with SIMD-accelerated distance metrics
+- Quantization (4-32x memory reduction)
+- Arena allocator for cache-optimized operations
+
+## Decision
+
+### Phase 1: Version Bump (Low Risk)
+
+Bump the 5 core crates from v2.0.4 to v2.0.5 in the workspace `Cargo.toml`:
+
+```toml
+ruvector-mincut = "2.0.5"        # was 2.0.4 — 10-30% faster, safer
+ruvector-attn-mincut = "2.0.5"   # was 2.0.4 — workspace versioning
+ruvector-temporal-tensor = "2.0.5" # was 2.0.4 — fmt only
+ruvector-solver = "2.0.5"        # was 2.0.4 — workspace versioning
+ruvector-attention = "2.0.5"     # was 2.0.4 — workspace versioning
+```
+
+**Expected impact:** The mincut performance improvement directly benefits `signal/subcarrier.rs` which runs subcarrier graph partitioning every tick. 10-30% faster partitioning reduces per-frame CPU cost.
+
+### Phase 2: Add ruvector-coherence (Medium Value)
+
+Add `ruvector-coherence` with `spectral` feature to `wifi-densepose-ruvector`:
+
+**Use case:** Replace or augment the custom phase coherence logic in `viewpoint/coherence.rs` with spectral graph coherence scoring. The current implementation uses phasor magnitude for phase coherence — spectral Fiedler estimation would provide a more robust measure of multi-node CSI consistency, especially for detecting when a node's signal quality degrades.
+
+**Integration point:** `viewpoint/coherence.rs` — add `SpectralCoherenceScore` as a secondary coherence metric alongside existing phase phasor coherence. Use spectral gap estimation to detect structural changes in the multi-node CSI graph (e.g., a node dropping out or a new reflector appearing).
+
+### Phase 3: Add SONA for Adaptive Learning (High Value)
+
+Replace the logistic regression adaptive classifier in the sensing server with a SONA-backed learning engine:
+
+**Current state:** The sensing server's adaptive training (`POST /api/v1/adaptive/train`) uses a hand-rolled logistic regression on 15 CSI features. It requires explicit labeled recordings and provides no cross-session persistence.
+
+**Proposed improvement:** Use `sona::SonaEngine` to:
+1. **Learn from implicit feedback** — trajectory tracking on person-count decisions (was the count stable? did the user correct it?)
+2. **Persist across sessions** — `saveState()`/`loadState()` replaces the current `adaptive_model.json`
+3. **Pattern matching** — `find_patterns()` enables "this CSI signature looks like room X where we learned Y"
+4. **Prevent forgetting** — EWC++ ensures learning in a new room doesn't overwrite patterns from previous rooms
+
+**Integration point:** New `adaptive_sona.rs` module in `wifi-densepose-sensing-server`, behind a `sona` feature flag. The existing logistic regression remains the default.
+
+### Phase 4: Evaluate ruvector-core for CSI Embeddings (Exploratory)
+
+**Current state:** The person detection pipeline uses hand-crafted features (variance, change_points, motion_band_power, spectral_power) with fixed normalization ranges.
+
+**Potential:** Use `ruvector-core`'s ONNX embedding support to generate learned CSI embeddings that capture room geometry, person count, and activity patterns in a single vector. This would enable:
+- Similarity search: "is this CSI frame similar to known 2-person patterns?"
+- Transfer learning: embeddings learned in one room partially transfer to similar rooms
+- Quantized storage: 4-32x memory reduction for pattern databases
+
+**Status:** Exploratory — requires training data collection and embedding model design. Not a near-term target.
+
+## Consequences
+
+### Positive
+- **Phase 1:** Free 10-30% performance gain in subcarrier partitioning. Security fixes (unsafe indexing, WASM panic). Zero API changes required.
+- **Phase 2:** More robust multi-node coherence detection. Helps with the "flickering persons" issue (#292) by providing a second opinion on signal quality.
+- **Phase 3:** Fundamentally improves the adaptive learning pipeline. Users no longer need to manually record labeled data — the system learns from ongoing use.
+- **Phase 4:** Path toward real ML-based detection instead of heuristic thresholds.
+
+### Negative
+- **Phase 1:** Minimal risk — semver minor bump, no API breaks.
+- **Phase 2:** Adds a dependency. Spectral computation has O(n) cost per tick for Fiedler estimation (n = number of subcarriers, typically 56-128). Acceptable.
+- **Phase 3:** SONA adds ~200KB to the binary. The learning loop needs careful tuning to avoid adapting to noise.
+- **Phase 4:** Requires significant research and training data. Not guaranteed to outperform tuned heuristics for WiFi CSI.
+
+### Risks
+- `ruvector-gnn` v2.0.5 changed constructors from panic to `Result` — any existing `crv` feature users need to handle the `Result`. Our vendored `ruvector-crv` may need updates.
+- SONA's WASM support is experimental — keep it behind a feature flag until validated.
+
+## Implementation Plan
+
+| Phase | Scope | Effort | Priority |
+|-------|-------|--------|----------|
+| 1 | Bump 5 crates to v2.0.5 | 1 hour | High — free perf + security |
+| 2 | Add ruvector-coherence | 1 day | Medium — improves multi-node stability |
+| 3 | SONA adaptive learning | 3 days | Medium — replaces manual training workflow |
+| 4 | CSI embeddings via ruvector-core | 1-2 weeks | Low — exploratory research |
+
+## Vendor Submodule
+
+The `vendor/ruvector` git submodule has been updated from commit `f8f2c60` (v2.0.4 era) to `51a3557` (latest `origin/main`). This provides local reference for the full upstream source when developing Phases 2-4.
+
+## References
+
+- Upstream repo: https://github.com/ruvnet/ruvector
+- ADR-124 (Dynamic MinCut): `vendor/ruvector/docs/adr/ADR-124*.md`
+- SONA docs: `vendor/ruvector/crates/sona/src/lib.rs`
+- ruvector-coherence spectral: `vendor/ruvector/crates/ruvector-coherence/src/spectral.rs`
+- ruvector-core embeddings: `vendor/ruvector/crates/ruvector-core/src/embeddings.rs`

pyproject.toml

@@ -185,7 +185,7 @@ package-dir = {"" = "."}
 
 [tool.setuptools.packages.find]
 where = ["."]
-include = ["src*"]
+include = ["wifi_densepose*", "src*"]
 exclude = ["tests*", "docs*", "scripts*"]
 
 [tool.setuptools.package-data]

rust-port/wifi-densepose-rs/crates/wifi-densepose-sensing-server/src/main.rs

@@ -285,6 +285,8 @@ struct AppStateInner {
     frame_history: VecDeque<Vec<f64>>,
     tick: u64,
     source: String,
+    /// Instant of the last ESP32 UDP frame received (for offline detection).
+    last_esp32_frame: Option<std::time::Instant>,
     tx: broadcast::Sender<String>,
     total_detections: u64,
     start_time: std::time::Instant,
@@ -304,6 +306,8 @@ struct AppStateInner {
     model_loaded: bool,
     /// Smoothed person count (EMA) for hysteresis — prevents frame-to-frame jumping.
     smoothed_person_score: f64,
+    /// Previous person count for hysteresis (asymmetric up/down thresholds).
+    prev_person_count: usize,
     // ── Motion smoothing & adaptive baseline (ADR-047 tuning) ────────────
     /// EMA-smoothed motion score (alpha ~0.15 for ~10 FPS → ~1s time constant).
     smoothed_motion: f64,
@@ -362,6 +366,25 @@ struct AppStateInner {
     adaptive_model: Option<adaptive_classifier::AdaptiveModel>,
 }
 
+/// If no ESP32 frame arrives within this duration, source reverts to offline.
+const ESP32_OFFLINE_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(5);
+
+impl AppStateInner {
+    /// Return the effective data source, accounting for ESP32 frame timeout.
+    /// If the source is "esp32" but no frame has arrived in 5 seconds, returns
+    /// "esp32:offline" so the UI can distinguish active vs stale connections.
+    fn effective_source(&self) -> String {
+        if self.source == "esp32" {
+            if let Some(last) = self.last_esp32_frame {
+                if last.elapsed() > ESP32_OFFLINE_TIMEOUT {
+                    return "esp32:offline".to_string();
+                }
+            }
+        }
+        self.source.clone()
+    }
+}
+
 /// Number of frames retained in `frame_history` for temporal analysis.
 /// At 500 ms ticks this covers ~50 seconds; at 100 ms ticks ~10 seconds.
 const FRAME_HISTORY_CAPACITY: usize = 100;
@@ -1247,12 +1270,15 @@ async fn windows_wifi_task(state: SharedState, tick_ms: u64) {
 
         let feat_variance = features.variance;
 
-        // Multi-person estimation with temporal smoothing (EMA α=0.15).
+        // Multi-person estimation with temporal smoothing (EMA α=0.10).
         let raw_score = compute_person_score(&features);
-        s.smoothed_person_score = s.smoothed_person_score * 0.85 + raw_score * 0.15;
+        s.smoothed_person_score = s.smoothed_person_score * 0.90 + raw_score * 0.10;
         let est_persons = if classification.presence {
-            score_to_person_count(s.smoothed_person_score)
+            let count = score_to_person_count(s.smoothed_person_score, s.prev_person_count);
+            s.prev_person_count = count;
+            count
         } else {
+            s.prev_person_count = 0;
             0
         };
 
@@ -1377,12 +1403,15 @@ async fn windows_wifi_fallback_tick(state: &SharedState, seq: u32) {
 
     let feat_variance = features.variance;
 
-    // Multi-person estimation with temporal smoothing.
+    // Multi-person estimation with temporal smoothing (EMA α=0.10).
     let raw_score = compute_person_score(&features);
-    s.smoothed_person_score = s.smoothed_person_score * 0.85 + raw_score * 0.15;
+    s.smoothed_person_score = s.smoothed_person_score * 0.90 + raw_score * 0.10;
     let est_persons = if classification.presence {
-        score_to_person_count(s.smoothed_person_score)
+        let count = score_to_person_count(s.smoothed_person_score, s.prev_person_count);
+        s.prev_person_count = count;
+        count
     } else {
+        s.prev_person_count = 0;
         0
     };
 
@@ -1661,7 +1690,7 @@ async fn health(State(state): State<SharedState>) -> Json<serde_json::Value> {
     let s = state.read().await;
     Json(serde_json::json!({
         "status": "ok",
-        "source": s.source,
+        "source": s.effective_source(),
         "tick": s.tick,
         "clients": s.tx.receiver_count(),
     }))
@@ -1724,18 +1753,45 @@ fn compute_person_score(feat: &FeatureInfo) -> f64 {
 
 /// Convert smoothed person score to discrete count with hysteresis.
 ///
-/// Uses asymmetric thresholds: higher threshold to add a person, lower to remove.
-/// This prevents flickering at the boundary.
-fn score_to_person_count(smoothed_score: f64) -> usize {
-    // Thresholds chosen conservatively for single-ESP32 link:
-    //   score > 0.50 → 2 persons (needs sustained high variance + change points)
-    //   score > 0.80 → 3 persons (very high activity, rare with single link)
-    if smoothed_score > 0.80 {
-        3
-    } else if smoothed_score > 0.50 {
-        2
-    } else {
-        1
+/// Uses asymmetric thresholds: higher threshold to *add* a person, lower to
+/// *drop* one.  This prevents flickering when the score hovers near a boundary
+/// (the #1 user-reported issue — see #237, #249, #280, #292).
+fn score_to_person_count(smoothed_score: f64, prev_count: usize) -> usize {
+    // Up-thresholds (must exceed to increase count):
+    //   1→2: 0.65  (raised from 0.50 — multipath in small rooms hit 0.50 easily)
+    //   2→3: 0.85  (raised from 0.80 — 3 persons needs strong sustained signal)
+    // Down-thresholds (must drop below to decrease count):
+    //   2→1: 0.45  (hysteresis gap of 0.20)
+    //   3→2: 0.70  (hysteresis gap of 0.15)
+    match prev_count {
+        0 | 1 => {
+            if smoothed_score > 0.85 {
+                3
+            } else if smoothed_score > 0.65 {
+                2
+            } else {
+                1
+            }
+        }
+        2 => {
+            if smoothed_score > 0.85 {
+                3
+            } else if smoothed_score < 0.45 {
+                1
+            } else {
+                2 // hold — within hysteresis band
+            }
+        }
+        _ => {
+            // prev_count >= 3
+            if smoothed_score < 0.45 {
+                1
+            } else if smoothed_score < 0.70 {
+                2
+            } else {
+                3 // hold
+            }
+        }
     }
 }
 
@@ -1942,7 +1998,7 @@ async fn health_ready(State(state): State<SharedState>) -> Json<serde_json::Valu
     let s = state.read().await;
     Json(serde_json::json!({
         "status": "ready",
-        "source": s.source,
+        "source": s.effective_source(),
     }))
 }
 
@@ -1953,7 +2009,10 @@ async fn health_system(State(state): State<SharedState>) -> Json<serde_json::Val
         "status": "healthy",
         "components": {
             "api": { "status": "healthy", "message": "Rust Axum server" },
-            "hardware": { "status": "healthy", "message": format!("Source: {}", s.source) },
+            "hardware": {
+                "status": if s.effective_source().ends_with(":offline") { "degraded" } else { "healthy" },
+                "message": format!("Source: {}", s.effective_source())
+            },
             "pose": { "status": "healthy", "message": "WiFi-derived pose estimation" },
             "stream": { "status": if s.tx.receiver_count() > 0 { "healthy" } else { "idle" },
                         "message": format!("{} client(s)", s.tx.receiver_count()) },
@@ -1993,7 +2052,7 @@ async fn api_info(State(state): State<SharedState>) -> Json<serde_json::Value> {
         "version": env!("CARGO_PKG_VERSION"),
         "environment": "production",
         "backend": "rust",
-        "source": s.source,
+        "source": s.effective_source(),
         "features": {
             "wifi_sensing": true,
             "pose_estimation": true,
@@ -2014,7 +2073,7 @@ async fn pose_current(State(state): State<SharedState>) -> Json<serde_json::Valu
         "timestamp": chrono::Utc::now().timestamp_millis() as f64 / 1000.0,
         "persons": persons,
         "total_persons": persons.len(),
-        "source": s.source,
+        "source": s.effective_source(),
     }))
 }
 
@@ -2024,7 +2083,7 @@ async fn pose_stats(State(state): State<SharedState>) -> Json<serde_json::Value>
         "total_detections": s.total_detections,
         "average_confidence": 0.87,
         "frames_processed": s.tick,
-        "source": s.source,
+        "source": s.effective_source(),
     }))
 }
 
@@ -2048,7 +2107,7 @@ async fn stream_status(State(state): State<SharedState>) -> Json<serde_json::Val
         "active": true,
         "clients": s.tx.receiver_count(),
         "fps": if s.tick > 1 { 10u64 } else { 0u64 },
-        "source": s.source,
+        "source": s.effective_source(),
     }))
 }
 
@@ -2584,7 +2643,7 @@ async fn vital_signs_endpoint(State(state): State<SharedState>) -> Json<serde_js
             "heartbeat_samples": hb_len,
             "heartbeat_capacity": hb_cap,
         },
-        "source": s.source,
+        "source": s.effective_source(),
         "tick": s.tick,
     }))
 }
@@ -2790,6 +2849,7 @@ async fn udp_receiver_task(state: SharedState, udp_port: u16) {
 
                     let mut s = state.write().await;
                     s.source = "esp32".to_string();
+                    s.last_esp32_frame = Some(std::time::Instant::now());
 
                     // Append current amplitudes to history before extracting features so
                     // that temporal analysis includes the most recent frame.
@@ -2824,12 +2884,15 @@ async fn udp_receiver_task(state: SharedState, udp_port: u16) {
                     let vitals = smooth_vitals(&mut s, &raw_vitals);
                     s.latest_vitals = vitals.clone();
 
-                    // Multi-person estimation with temporal smoothing.
+                    // Multi-person estimation with temporal smoothing (EMA α=0.10).
                     let raw_score = compute_person_score(&features);
-                    s.smoothed_person_score = s.smoothed_person_score * 0.85 + raw_score * 0.15;
+                    s.smoothed_person_score = s.smoothed_person_score * 0.90 + raw_score * 0.10;
                     let est_persons = if classification.presence {
-                        score_to_person_count(s.smoothed_person_score)
+                        let count = score_to_person_count(s.smoothed_person_score, s.prev_person_count);
+                        s.prev_person_count = count;
+                        count
                     } else {
+                        s.prev_person_count = 0;
                         0
                     };
 
@@ -2929,12 +2992,15 @@ async fn simulated_data_task(state: SharedState, tick_ms: u64) {
         let frame_amplitudes = frame.amplitudes.clone();
         let frame_n_sub = frame.n_subcarriers;
 
-        // Multi-person estimation with temporal smoothing.
+        // Multi-person estimation with temporal smoothing (EMA α=0.10).
         let raw_score = compute_person_score(&features);
-        s.smoothed_person_score = s.smoothed_person_score * 0.85 + raw_score * 0.15;
+        s.smoothed_person_score = s.smoothed_person_score * 0.90 + raw_score * 0.10;
         let est_persons = if classification.presence {
-            score_to_person_count(s.smoothed_person_score)
+            let count = score_to_person_count(s.smoothed_person_score, s.prev_person_count);
+            s.prev_person_count = count;
+            count
         } else {
+            s.prev_person_count = 0;
             0
         };
 
@@ -3566,6 +3632,7 @@ async fn main() {
         frame_history: VecDeque::new(),
         tick: 0,
         source: source.into(),
+        last_esp32_frame: None,
         tx,
         total_detections: 0,
         start_time: std::time::Instant::now(),
@@ -3577,6 +3644,7 @@ async fn main() {
         active_sona_profile: None,
         model_loaded,
         smoothed_person_score: 0.0,
+        prev_person_count: 0,
         smoothed_motion: 0.0,
         current_motion_level: "absent".to_string(),
         debounce_counter: 0,
@@ -3739,7 +3807,7 @@ async fn main() {
             "WiFi DensePose sensing model state",
         );
         builder.add_metadata(&serde_json::json!({
-            "source": s.source,
+            "source": s.effective_source(),
             "total_ticks": s.tick,
             "total_detections": s.total_detections,
             "uptime_secs": s.start_time.elapsed().as_secs(),

wifi_densepose/__init__.py

@@ -0,0 +1,137 @@
+"""
+WiFi-DensePose — WiFi-based human pose estimation using CSI data.
+
+Usage:
+    from wifi_densepose import WiFiDensePose
+
+    system = WiFiDensePose()
+    system.start()
+    poses = system.get_latest_poses()
+    system.stop()
+"""
+
+__version__ = "1.2.0"
+
+import sys
+import os
+import logging
+
+logger = logging.getLogger(__name__)
+
+# Allow importing the v1 src package when installed from the repo
+_v1_src = os.path.join(os.path.dirname(os.path.dirname(__file__)), "v1")
+if os.path.isdir(_v1_src) and _v1_src not in sys.path:
+    sys.path.insert(0, _v1_src)
+
+
+class WiFiDensePose:
+    """High-level facade for the WiFi-DensePose sensing system.
+
+    This is the primary entry point documented in the README Quick Start.
+    It wraps the underlying ServiceOrchestrator and exposes a simple
+    start / get_latest_poses / stop interface.
+    """
+
+    def __init__(self, host: str = "0.0.0.0", port: int = 3000, **kwargs):
+        self.host = host
+        self.port = port
+        self._config = kwargs
+        self._orchestrator = None
+        self._server_task = None
+        self._poses = []
+        self._running = False
+
+    # ------------------------------------------------------------------
+    # Public API (matches README Quick Start)
+    # ------------------------------------------------------------------
+
+    def start(self):
+        """Start the sensing system (blocking until ready)."""
+        import asyncio
+
+        loop = _get_or_create_event_loop()
+        loop.run_until_complete(self._async_start())
+
+    async def _async_start(self):
+        try:
+            from src.config.settings import get_settings
+            from src.services.orchestrator import ServiceOrchestrator
+
+            settings = get_settings()
+            self._orchestrator = ServiceOrchestrator(settings)
+            await self._orchestrator.initialize()
+            await self._orchestrator.start()
+            self._running = True
+            logger.info("WiFiDensePose system started on %s:%s", self.host, self.port)
+        except ImportError:
+            raise ImportError(
+                "Core dependencies not found. Make sure you installed "
+                "from the repository root:\n"
+                "  cd wifi-densepose && pip install -e .\n"
+                "Or install the v1 package:\n"
+                "  cd wifi-densepose/v1 && pip install -e ."
+            )
+
+    def stop(self):
+        """Stop the sensing system."""
+        import asyncio
+
+        if self._orchestrator is not None:
+            loop = _get_or_create_event_loop()
+            loop.run_until_complete(self._orchestrator.shutdown())
+            self._running = False
+            logger.info("WiFiDensePose system stopped")
+
+    def get_latest_poses(self):
+        """Return the most recent list of detected pose dicts."""
+        if self._orchestrator is None:
+            return []
+        try:
+            import asyncio
+
+            loop = _get_or_create_event_loop()
+            return loop.run_until_complete(self._fetch_poses())
+        except Exception:
+            return []
+
+    async def _fetch_poses(self):
+        try:
+            pose_svc = self._orchestrator.pose_service
+            if pose_svc and hasattr(pose_svc, "get_latest"):
+                return await pose_svc.get_latest()
+        except Exception:
+            pass
+        return []
+
+    # ------------------------------------------------------------------
+    # Context-manager support
+    # ------------------------------------------------------------------
+
+    def __enter__(self):
+        self.start()
+        return self
+
+    def __exit__(self, *exc):
+        self.stop()
+
+    # ------------------------------------------------------------------
+    # Convenience re-exports
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def version():
+        return __version__
+
+
+def _get_or_create_event_loop():
+    import asyncio
+
+    try:
+        return asyncio.get_event_loop()
+    except RuntimeError:
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+        return loop
+
+
+__all__ = ["WiFiDensePose", "__version__"]