fix(server): make synthetic CSI opt-in only (sibling fix to #937) (#979)

Background

Issue #937 in the cognitum-v0 appliance repo flagged that the
`cognitum-csi-capture` systemd unit shipped `--simulate` by default,
silently serving synthetic CSI tagged as production telemetry on
`/api/v1/sensor/stream`. That's a textbook trust-eroding pattern — the
single most-cited "where's the real data?" evidence external reviewers
(#943, #934) point at when they call the project AI-slop.

A grep across THIS tree surfaced the exact same anti-pattern in three
places:

  docker/docker-compose.yml:27        # auto (default) — probe ESP32, fall back to simulation
  docker/docker-entrypoint.sh:14      # CSI_SOURCE — data source: auto (default), ...
  main.rs:6435                        info!("No hardware detected, using simulation"); "simulate"

The sensing-server's `auto` source resolver at main.rs:6425-6440
silently fell back to synthetic with only an `info!` log line as the
signal. Downstream consumers calling `/api/v1/sensing/latest` or
`/ws/sensing` had no in-band way to know they were being served fake
data.

Fix

`auto` now refuses to fall back. When neither ESP32 UDP nor host WiFi
is detected, the server logs a clear `error!` explaining the situation
and exits 78 (EX_CONFIG). The error message names the two ways to
proceed: provision real hardware, or set `--source simulated` /
`CSI_SOURCE=simulated` explicitly. Existing operators who already use
`--source simulated` (or its legacy `simulate` alias) are unaffected —
the alias is preserved for back-compat.

Docker entrypoint comment, docker-compose comment, and the Tauri
desktop app's source-default path also updated to reflect the new
posture. The desktop app keeps its `simulated` default because it's
an explicit demo product — the value passed downstream is the
*explicit* `simulated`, not `auto`, so the server tags it correctly
and never lies about its data source.

Validation

  cargo build  -p wifi-densepose-sensing-server --no-default-features
  cargo test   -p wifi-densepose-sensing-server --no-default-features
  → 122 / 122 pass, build clean (existing pre-fix warnings unchanged).

Deployment

⚠ Breaking change for unattended deployments that relied on the
`auto → simulated` silent fallback. That is exactly the failure mode
this PR fixes: pretending to serve real sensing data when the source
is fake. Operators who genuinely want demo mode set
`CSI_SOURCE=simulated` explicitly; the error message and the
docker-compose comment both point them there.

.github/workflows/ci.yml

@@ -108,16 +108,18 @@ jobs:
     - name: Install Rust toolchain
       uses: dtolnay/rust-toolchain@stable
 
-    - name: Cache cargo
-      uses: actions/cache@v4
+    # Swatinem/rust-cache replaces a naive `actions/cache` of the whole
+    # `v2/target`. That manual cache of a 38-crate target dir (multi-GB) was an
+    # intermittent failure source — several CI runs this cycle died at the
+    # cache/setup step (after toolchain install, before "Run Rust tests"),
+    # needing a rerun. rust-cache is purpose-built for Rust: it caches the
+    # registry + git + a pruned target, evicts stale deps, and restores far more
+    # reliably (and faster) on large workspaces. `workspaces: v2` points it at
+    # the v2/ cargo workspace (keys on v2/Cargo.lock, caches v2/target).
+    - name: Cache cargo (Swatinem/rust-cache)
+      uses: Swatinem/rust-cache@v2
       with:
-        path: |
-          ~/.cargo/registry
-          ~/.cargo/git
-          v2/target
-        key: ${{ runner.os }}-cargo-${{ hashFiles('v2/Cargo.lock') }}
-        restore-keys: |
-          ${{ runner.os }}-cargo-
+        workspaces: v2
 
     - name: Run Rust tests
       working-directory: v2
@@ -265,23 +267,45 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install -r requirements.txt
-        pip install locust
+        pip install pytest   # the perf suite is pytest, not locust
 
-    - name: Start application
-      working-directory: archive/v1
-      run: |
-        uvicorn src.api.main:app --host 0.0.0.0 --port 8000 &
-        sleep 10
+    # No "Start application" step: the gated test (test_frame_budget.py) drives
+    # the CSIProcessor pipeline in-process and makes no HTTP calls, so the old
+    # uvicorn server + `sleep 10` were dead weight — they only existed for the
+    # now-excluded api_throughput/inference_speed tests, and on every run dumped
+    # ~50 misleading "router requires hardware setup" ERROR lines for a server
+    # no test touched. MOCK_POSE_DATA is server-only and unused here.
 
     - name: Run performance tests
+      working-directory: archive/v1
       run: |
-        locust -f tests/performance/locustfile.py --headless --users 50 --spawn-rate 5 --run-time 60s --host http://localhost:8000
+        # Gate only on the genuine, deterministic perf guard:
+        # test_frame_budget.py times the *real* CSIProcessor pipeline against
+        # the ADR 50 ms per-frame budget (single-frame, p95 over 100 frames,
+        # +Doppler) — a true regression signal.
+        #
+        # test_api_throughput.py / test_inference_speed.py are excluded: every
+        # test there is a TDD red-phase stub (suffix `_should_fail_initially`)
+        # that times a *mock that sleeps* — meaningless as a perf signal, with
+        # machine-dependent wall-clock asserts (e.g. `actual_rps >= 40`,
+        # `batch_time < individual_time`) that are inherently flaky on shared
+        # CI runners, plus a cross-class fixture-scope bug. Forcing them green
+        # would be manufacturing a false signal; they stay in-repo for local
+        # TDD but do not gate CI until the underlying features are implemented.
+        #
+        # `python -m pytest` (not the bare `pytest` script) puts the cwd
+        # (archive/v1) on sys.path so `from src.core...` resolves — the bare
+        # script omits cwd and raises ModuleNotFoundError: No module named 'src'.
+        # -o addopts="" drops the root pyproject's --cov/--cov-fail-under=100.
+        python -m pytest tests/performance/test_frame_budget.py \
+          -o addopts="" -v --junitxml=perf-junit.xml
 
     - name: Upload performance results
+      if: always()
       uses: actions/upload-artifact@v4
       with:
         name: performance-results
-        path: locust_report.html
+        path: archive/v1/perf-junit.xml
 
   # Docker Build and Test
   # NOTE: the canonical Docker build for the sensing-server is now
@@ -367,6 +391,8 @@ jobs:
     runs-on: ubuntu-latest
     needs: [docker-build]
     if: github.ref == 'refs/heads/main'
+    permissions:
+      contents: write   # gh-pages deploy needs write (GITHUB_TOKEN is read-only by default -> 403)
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
@@ -384,6 +410,8 @@ jobs:
 
     - name: Generate OpenAPI spec
       working-directory: archive/v1
+      env:
+        MOCK_POSE_DATA: "true"   # no CSI hardware in CI
       run: |
         python -c "
         from src.api.main import app
@@ -394,6 +422,7 @@ jobs:
 
     - name: Deploy to GitHub Pages
       uses: peaceiris/actions-gh-pages@v4
+      continue-on-error: true   # openapi generation above is the real validation; deploy is best-effort (Pages may be disabled)
       with:
         github_token: ${{ secrets.GITHUB_TOKEN }}
         publish_dir: ./docs

.github/workflows/security-scan.yml

@@ -46,7 +46,10 @@ jobs:
 
     - name: Run Bandit security scan
       run: |
-        bandit -r src/ -f sarif -o bandit-results.sarif
+        # The Python codebase lives under archive/v1/src (it moved there when
+        # the runtime was rewritten in Rust). Scanning `src/` matched nothing,
+        # so this SAST step was a silent no-op.
+        bandit -r archive/v1/src/ -f sarif -o bandit-results.sarif
       continue-on-error: true
 
     - name: Upload Bandit results to GitHub Security
@@ -57,22 +60,20 @@ jobs:
         sarif_file: bandit-results.sarif
         category: bandit
 
-    - name: Run Semgrep security scan
-      continue-on-error: true
-      uses: returntocorp/semgrep-action@v1
-      with:
-        config: >-
-          p/security-audit
-          p/secrets
-          p/python
-          p/docker
-          p/kubernetes
-      env:
-        SEMGREP_APP_TOKEN: ${{ secrets.SEMGREP_APP_TOKEN }}
-        
-    - name: Generate Semgrep SARIF
+    # Removed the deprecated `returntocorp/semgrep-action@v1` step: it was
+    # redundant (the pip `semgrep --sarif` below is what feeds GitHub Security;
+    # the action only pushed to the Semgrep cloud app via SEMGREP_APP_TOKEN) and
+    # it pulled `returntocorp/semgrep-agent:v1` from Docker Hub on every run,
+    # which intermittently timed out and turned this check red. The pip semgrep
+    # (installed above) needs no Docker pull. The action's `p/docker` +
+    # `p/kubernetes` rulesets are folded into the command below so coverage is
+    # preserved.
+    - name: Run Semgrep + generate SARIF
       run: |
-        semgrep --config=p/security-audit --config=p/secrets --config=p/python --sarif --output=semgrep.sarif src/
+        semgrep \
+          --config=p/security-audit --config=p/secrets --config=p/python \
+          --config=p/docker --config=p/kubernetes \
+          --sarif --output=semgrep.sarif archive/v1/src/
       continue-on-error: true
 
     - name: Upload Semgrep results to GitHub Security

CHANGELOG.md

@@ -8,8 +8,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Fixed
+- **Person count no longer leaks up to 10 in heuristic mode — addresses #894.** `field_bridge::occupancy_or_fallback` returned the eigenvalue-based `FieldModel::estimate_occupancy` count **unbounded** (its internal ceiling is 10), while the sibling estimators on the same single-link data — the perturbation-energy fallback right below it and `score_to_person_count` — both cap at 3 ("1-3 for single ESP32"). On noisy / under-calibrated CSI the eigenvalue count inflated, producing the "10 persons reported when 1 present" symptom (seen when `--model` fails to load and the server runs on heuristics). Bounded the eigenvalue path to the shared `MAX_SINGLE_LINK_OCCUPANCY` (3) so every estimator on one link agrees; genuine higher counts come from the multistatic fusion path, not a single-link covariance estimate.
+- **MQTT multi-node deployments now create one Home-Assistant device per node — closes #898.** After the #872 MQTT wiring landed, the JSON→`VitalsSnapshot` bridge hard-coded a single `node_id` (the MQTT client id) and the publisher used a single `OwnedDiscoveryBuilder`, so every physical node collapsed into one device (`identifiers:["wifi_densepose_wifi-densepose-1"]`), contradicting the "one device per node" docs. The bridge now emits one snapshot per node in the sensing update's `nodes[]` (each with its own `node_id` + RSSI, falling back to a single aggregate snapshot for wifi/simulate sources), and the publisher derives a per-node builder (`OwnedDiscoveryBuilder::for_node`) that publishes discovery + availability lazily on first sight of each `node_id` and routes state to per-node topics — yielding N distinct HA devices with per-node availability/LWT. Unit-tested (distinct nodes → distinct `wifi_densepose_<node>` identifiers); 71 MQTT tests pass.
 - **Person count no longer pinned to 1 — addresses #803.** The aggregate occupancy reported by the sensing server was derived from `smoothed_person_score`, an EMA-smoothed *activity* score (amplitude variance / motion / spectral energy). That score saturates near a single occupant — one moving person maxes it out — so it cannot discriminate occupancy *count* and stayed clamped at 1 across S3/C6 and the Python/Docker/Rust servers. Meanwhile the count-aware per-node estimates the ESP32 paths already compute (firmware `n_persons`, and the DynamicMinCut `corr_persons`) were stashed in `NodeState::prev_person_count` and then **discarded** by the aggregator (same dead-wiring class as #872). The aggregator now takes `max(activity_count, node_max)` via a unit-tested `aggregate_person_count` helper, so a node positively estimating 2–3 occupants is surfaced instead of overwritten. The fix can only ever *raise* the count when a node reports more people, so the single-occupant case is provably never inflated (regression-guarded by test). **Second half:** the pure-CSI per-node path itself clamped its own estimate — the DynamicMinCut occupancy (`estimate_persons_from_correlation`, 0–3) was mapped to a score via `corr_persons / 3.0`, putting 2 people at 0.667, *just under* the 0.70 up-threshold of `score_to_person_count`, so the per-node count never climbed past 1 (so `node_max` was also stuck at 1 for CSI-only nodes). Replaced it with a threshold-aligned `corr_persons_to_score` mapping (1→0.40, 2→0.74, 3→0.96) whose steady state round-trips back to the same count through the EMA + hysteresis, while still gating transient noise. A convergence test replays the exact EMA loop to prove min-cut=2 now reports 2 (and documents that the old `/3.0` mapping reported 1). Full multi-person accuracy still depends on the underlying estimator quality; this removes the two server-side clamps that masked it. 586 sensing-server tests pass.
 - **MQTT publisher now actually runs (`--mqtt`) — closes #872.** The `--mqtt*` flags were defined only in `cli::Args` (dead code, referenced nowhere) while the binary parses a *separate* `main::Args` with no mqtt fields, and `main.rs` never started the `mqtt::` publisher — so MQTT/Home-Assistant integration was completely unwired (`--mqtt` errored as an unexpected argument, and even with the Docker image's `--features mqtt` build the publisher never ran). Earlier attempts chased a Docker *rebuild*; the real cause was disconnected *code*. Extracted the flags into a shared `cli::MqttArgs` (`#[command(flatten)]` into both structs), spawn the publisher on `--mqtt`, and bridge the JSON sensing broadcast into the typed `VitalsSnapshot` stream with a defensive `serde_json::Value` mapping. Verified end-to-end against `mosquitto`: 20 HA auto-discovery entities + live state (presence/person-count/…). 577 (default) / 580 (`--features mqtt`) tests pass.
+- **Mass Casualty triage never reports a survivor with a heartbeat as Deceased (safety) — PR #926.** Both triage paths in `wifi-densepose-mat` — `TriageCalculator::calculate` (`combine_assessments(Absent, None) ⇒ Deceased`) and the detection path `EnsembleClassifier::determine_triage` (`!has_breathing && !has_movement ⇒ Deceased`) — ignored the `heartbeat` field. A survivor with a detectable **pulse** but no sensed breathing/movement (respiratory arrest — the most time-critical *savable* state, Immediate/Red) was therefore reported **Deceased (Black)** and deprioritized for rescue. The domain path was in fact only reachable *because* a heartbeat made `has_vitals()` true, so every "Deceased" was a live person. Both paths now escalate to **Immediate** when a heartbeat is present; total absence of breathing, movement *and* heartbeat is unchanged (domain → `Unknown`, ensemble → `Deceased`). 2 safety regression tests; full MAT suite (177) green.
+- **Per-node Home-Assistant devices now report each node's *own* presence/motion — PR #918.** After the one-device-per-node fan-out landed, the MQTT bridge still applied the *room-level aggregate* `classification` to every node, so in a multi-node deployment a node watching an empty corner inherited another node's "present" (and `motion_level: "absent"` was mis-mapped to full motion). Each node in the broadcast `nodes[]` already carries its own `classification`; the bridge now reads it per node (extracted into a testable `vitals_snapshots_from_sensing_json`), keeping vitals + person count room-level. 4 unit tests.
+- **`--model` gives an actionable diagnostic instead of a cryptic magic error — PR #919 (refs #894).** Passing a HuggingFace `ruvnet/wifi-densepose-pretrained` file (`model.safetensors` / `model-q4.bin` / `model.rvf.jsonl`) to `--model` produced `invalid magic at offset 0: … got 0x77455735`, then a silent fall back to heuristics. The load-failure path now detects the format (safetensors / quantized blob / JSONL manifest) and explains that those files are a different format **and** encoder architecture than the RVF binary container the progressive loader expects, pointing to #894. Pure `diagnose_model_load_error` + 4 tests.
+- **`--export-rvf` no longer silently produces a placeholder model — PR #920.** The `--export-rvf` handler ran *before* `--train`/`--pretrain` and unconditionally wrote placeholder sine-wave weights, so the documented `--train … --export-rvf <path>` workflow short-circuited to a fake model and never trained (while printing "exported successfully"). It now emits the placeholder **container-format demo** only standalone (with a clear warning), and falls through to real training when `--train`/`--pretrain` is set; docs point to `--save-rvf` for the real model. 3 guard tests.
 
 ### Added
 - **WiFi-CSI pose: efficiency frontier + per-room calibration service** (ADR-150 §3.2–3.6). Two beyond-SOTA results on the MM-Fi benchmark, plus the deployment mechanism that resolves real-world generalization:
@@ -31,6 +37,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Security
 - **ESP32 OTA upload now fails closed when no PSK is provisioned** (#596 audit finding — critical, **breaking change for unprovisioned nodes**). `ota_check_auth()` previously returned `true` when `s_ota_psk[0] == '\0'`, so a freshly-flashed node would accept attacker-controlled firmware over plain HTTP on port 8032 from any host on the WiFi. No Secure Boot V2, no signed-image verification — a single LAN call could brick or backdoor a node. The fix rejects every OTA upload until a PSK is written to NVS (the OTA HTTP server still starts so operators can run `provision.py --ota-psk <hex>` over USB-CDC without reflashing). **Operators affected**: any deployment that relied on the unauthenticated OTA endpoint working out of the box now needs to provision a PSK before subsequent OTA pushes will succeed. Boot-time `ESP_LOGW` makes the new posture visible.
+- **Bearer-token auth accepts the scheme case-insensitively (RFC 6750) — PR #929.** `require_bearer` parsed the `Authorization` header with a case-sensitive `strip_prefix("Bearer ")`, so a *correct* `RUVIEW_API_TOKEN` sent as `Authorization: bearer <token>` (or `BEARER`, or with extra whitespace) was rejected with a confusing 401 — needless friction when enabling auth. The scheme is now matched with `eq_ignore_ascii_case` (per RFC 6750 §2.1 / RFC 7235 §2.1); the token compare is unchanged — still exact and constant-time (`ct_eq`) — so a wrong token or a non-Bearer scheme (`Basic …`) still returns 401. Audited the surrounding code while here: `ct_eq` correctly rejects length mismatch (no prefix-auth bypass) and the middleware fails closed. New `accepts_case_insensitive_bearer_scheme` test.
 - **Path-traversal vulnerabilities patched in five sensing-server endpoints** (closes #615 — critical). New `wifi_densepose_sensing_server::path_safety::safe_id()` enforces `[A-Za-z0-9._-]` only (no leading `.`, max 64 chars) before any user-controlled identifier reaches a `format!()` building a filesystem path. Applied at:
   - `POST /api/v1/recording/start` (`recording.rs` — `session_name`)
   - `GET /api/v1/recording/download/:id` (`recording.rs` — `id`)
@@ -428,7 +435,7 @@ Model release (no new firmware binary). Firmware remains at v0.6.0-esp32.
 - Security fix merged via PR #310.
 
 ### Performance
-- Presence detection: 100% accuracy on 60,630 overnight samples.
+- Presence detection: 100% accuracy on 60,630 overnight samples. *(Retracted — that recording was single-class (one sleeping person, 6,062/6,063 frames "present"), so a constant "yes" scores ~99.98%. Superseded by the honest 82.3% held-out temporal-triplet metric; see [#882](https://github.com/ruvnet/RuView/issues/882). Kept here as the in-place public record.)*
 - Inference: 0.008 ms per sample, 164K embeddings/sec.
 - Contrastive self-supervised training: 51.6% improvement over baseline.
 

archive/v1/src/services/pose_service.py

@@ -107,16 +107,25 @@ class PoseService:
     async def _initialize_models(self):
         """Initialize neural network models."""
         try:
-            # Initialize DensePose model
+            # Initialize DensePose model. DensePoseHead requires a config
+            # dict — input_channels matches the modality translator's output
+            # (256), with the standard DensePose 24 body parts and 2 (U,V)
+            # coordinates. (Previously called with no args → TypeError at
+            # startup, which broke the API service.)
+            densepose_config = {
+                'input_channels': 256,
+                'num_body_parts': 24,
+                'num_uv_coordinates': 2,
+            }
             if self.settings.pose_model_path:
-                self.densepose_model = DensePoseHead()
+                self.densepose_model = DensePoseHead(densepose_config)
                 # Load model weights if path is provided
                 # model_state = torch.load(self.settings.pose_model_path)
                 # self.densepose_model.load_state_dict(model_state)
                 self.logger.info("DensePose model loaded")
             else:
                 self.logger.warning("No pose model path provided, using default model")
-                self.densepose_model = DensePoseHead()
+                self.densepose_model = DensePoseHead(densepose_config)
             
             # Initialize modality translation
             config = {

docker/docker-compose.yml

@@ -24,10 +24,13 @@ services:
     environment:
       - RUST_LOG=info
       # CSI_SOURCE controls the data source for the sensing server.
-      # Options: auto (default) — probe for ESP32 UDP then fall back to simulation
+      # Options: auto (default) — probe for ESP32 UDP then host WiFi; **fail
+      #                           hard with exit 78 if neither is detected**.
+      #                           Synthetic data is no longer a silent fallback
+      #                           (issue #937 fix) — operators must opt in.
       #          esp32          — receive real CSI frames from an ESP32 on UDP port 5005
       #          wifi           — use host Wi-Fi RSSI/scan data (Windows netsh)
-      #          simulated      — generate synthetic CSI data (no hardware required)
+      #          simulated      — explicitly generate synthetic CSI for demo mode
       - CSI_SOURCE=${CSI_SOURCE:-auto}
       # MODELS_DIR controls where the server scans for .rvf model files.
       # Mount a host directory and set this to make models visible:

docker/docker-entrypoint.sh

@@ -11,10 +11,65 @@
 #      docker run ruvnet/wifi-densepose:latest --model /app/models/my.rvf
 #
 # Environment variables:
-#   CSI_SOURCE   — data source: auto (default), esp32, wifi, simulated
+#   CSI_SOURCE   — data source. Valid values:
+#                    auto       — try ESP32 then Windows WiFi, **fail-loud if no
+#                                 real hardware is detected** (issue #937 fix:
+#                                 the server no longer silently falls back to
+#                                 synthetic data — that's now opt-in only).
+#                    esp32      — listen for UDP CSI on the configured port.
+#                    wifi       — Windows-native WiFi capture.
+#                    simulated  — explicit demo mode with synthetic CSI.
+#                  Default is `auto`. Set CSI_SOURCE=simulated when you want
+#                  fake data tagged as such; never set it implicitly.
 #   MODELS_DIR   — directory to scan for .rvf model files (default: data/models)
 set -e
 
+# ── Issue #864: fail-closed on default posture ───────────────────────────────
+# The pre-fix default was: empty RUVIEW_API_TOKEN (auth off) + --bind-addr
+# 0.0.0.0 + docker-compose publishing :3000/:3001/:5005 → an unauthenticated
+# attacker on any reachable network segment could read /api/v1/sensing/latest
+# and the /ws/sensing live stream. That posture is unsafe on guest WiFi,
+# untrusted LANs, accidentally-port-forwarded hosts, or any reverse-proxied
+# deployment. Refuse to start with this combination.
+#
+# Escape hatches (operator must opt in explicitly):
+#   * Set RUVIEW_API_TOKEN to a strong secret → auth enabled on /api/v1/*.
+#   * Set RUVIEW_ALLOW_UNAUTHENTICATED=1 → preserves the pre-fix behaviour;
+#     only safe on an isolated trust boundary.
+#   * Set RUVIEW_BIND_ADDR to a loopback / private interface → unauth is fine
+#     when the socket isn't reachable. The auto-bind nudges toward 127.0.0.1.
+#
+# This check runs only for the default sensing-server path (no args + flag-only
+# args). The `cog-ha-matter` / `homecore` routes below are excluded because
+# they own their own auth lifecycle.
+case "${1:-}" in
+    cog-ha-matter|ha-matter|homecore|homecore-server) ;;
+    *)
+        if [ -z "${RUVIEW_API_TOKEN:-}" ] && [ "${RUVIEW_ALLOW_UNAUTHENTICATED:-}" != "1" ]; then
+            # If the operator hasn't overridden the bind, refuse outright on
+            # the default 0.0.0.0. If they've nailed it to loopback (or a
+            # specific private address they trust), let it run.
+            __bind_default="${RUVIEW_BIND_ADDR:-0.0.0.0}"
+            case "$__bind_default" in
+                127.*|localhost|::1)
+                    : ;;  # loopback bind is safe even without a token
+                *)
+                    echo "[entrypoint] ERROR: refusing to start sensing-server with default" >&2
+                    echo "[entrypoint]        posture: RUVIEW_API_TOKEN is unset AND bind is" >&2
+                    echo "[entrypoint]        ${__bind_default}. /ws/sensing streams live sensing" >&2
+                    echo "[entrypoint]        frames; that data would be readable by anyone who" >&2
+                    echo "[entrypoint]        can reach this host. Pick one:" >&2
+                    echo "[entrypoint]          docker run -e RUVIEW_API_TOKEN=\$(openssl rand -hex 32) ..." >&2
+                    echo "[entrypoint]          docker run -e RUVIEW_BIND_ADDR=127.0.0.1 ..." >&2
+                    echo "[entrypoint]          docker run -e RUVIEW_ALLOW_UNAUTHENTICATED=1 ...   # only on trusted network" >&2
+                    echo "[entrypoint]        See https://github.com/ruvnet/RuView/issues/864" >&2
+                    exit 64
+                    ;;
+            esac
+        fi
+        ;;
+esac
+
 # Route to cog-ha-matter (ADR-116) when invoked as:
 #   docker run <image> cog-ha-matter [--flags]
 # or via the short alias `ha-matter`. Strips the keyword and execs the
@@ -48,7 +103,7 @@ if [ "${1#-}" != "$1" ] || [ -z "$1" ]; then
         --ui-path /app/ui \
         --http-port 3000 \
         --ws-port 3001 \
-        --bind-addr 0.0.0.0 \
+        --bind-addr "${RUVIEW_BIND_ADDR:-0.0.0.0}" \
         "$@"
 fi
 

docs/readme-details.md

@@ -122,7 +122,7 @@ node scripts/benchmark-ruvllm.js --model models/csi-ruvllm       # benchmark
 
 | What we measured | Result | Why it matters |
 |-----------------|--------|---------------|
-| **Presence detection** | **100% accuracy** | Never misses a person, never false alarms |
+| **CSI embedding quality** | **82.3% held-out temporal-triplet** | Honest label-free metric on the last 20% by time (v1's "100% presence" was a single-class recording — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) |
 | **Inference speed** | **0.008 ms** per embedding | 125,000x faster than real-time |
 | **Throughput** | **164,183 embeddings/sec** | One Mac Mini handles 1,600+ ESP32 nodes |
 | **Contrastive learning** | **51.6% improvement** | Strong pattern learning from real overnight data |
@@ -233,7 +233,7 @@ python firmware/esp32-csi-node/provision.py --port COM9 --hop-channels "1,6,11"
 | **kNN similarity search** | "Find the 10 most similar states to right now" — anomaly detection, fingerprinting | Cognitum Seed |
 | **Witness chain** | SHA-256 tamper-evident audit trail for every measurement (1,747 entries validated) | Cognitum Seed |
 | **Camera-free pose training** | 17 COCO keypoints from 10 sensor signals — PIR, RSSI triangulation, subcarrier asymmetry, vibration, BME280 | 2x ESP32 + Seed |
-| **Pre-trained model** | 82.8 KB (8 KB at 4-bit quantization), 100% presence accuracy, 0 skeleton violations | Download from release |
+| **Pre-trained model** | 82.8 KB (8 KB at 4-bit quantization), 82.3% held-out temporal-triplet accuracy (v1's "100% presence" was single-class — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) | Download from release |
 | **Sub-ms inference** | 0.012 ms latency, 171,472 embeddings/sec on M4 Pro | Any machine with Node.js |
 | **SONA adaptation** | Adapts to new rooms in <1ms without retraining | ruvllm runtime |
 | **LoRA room adapters** | Per-node fine-tuning with 2,048 parameters per adapter | Automatic |
@@ -262,7 +262,7 @@ node scripts/benchmark-ruvllm.js --model models/csi-ruvllm
 
 | What we measured | Result | Why it matters |
 |-----------------|--------|---------------|
-| **Presence detection** | **100% accuracy** | Never misses a person, never false alarms |
+| **CSI embedding quality** | **82.3% held-out temporal-triplet** | Honest label-free metric (v1's "100% presence" was single-class — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) |
 | **Person counting** | **24/24 correct** (MinCut) | Fixed the #1 user-reported issue |
 | **Inference speed** | **0.012 ms** per embedding | 83,000x faster than real-time |
 | **Throughput** | **171,472 embeddings/sec** | One Mac Mini handles 1,700+ ESP32 nodes |

docs/user-guide.md

@@ -1048,7 +1048,7 @@ The Rust sensing server binary accepts the following flags:
 | `--dataset` | (none) | Path to dataset directory (MM-Fi or Wi-Pose) |
 | `--dataset-type` | `mmfi` | Dataset format: `mmfi` or `wipose` |
 | `--epochs` | `100` | Training epochs |
-| `--export-rvf` | (none) | Export RVF model container and exit |
+| `--export-rvf` | (none) | Export a **placeholder** RVF container-format demo and exit — **not a trained model**. For a real model use `--train` (+ `--save-rvf`) or download a pretrained encoder. |
 | `--save-rvf` | (none) | Save model state to RVF on shutdown |
 | `--model` | (none) | Load a trained `.rvf` model for inference |
 | `--load-rvf` | (none) | Load model config from RVF container |
@@ -1119,7 +1119,7 @@ What it ships (and what it does not):
 
 | Capability | Status |
 |------------|--------|
-| Presence detection (occupied / empty) | ✅ Trained head — 100% accuracy on validation |
+| Presence detection (occupied / empty) | ✅ Trained head — v2 encoder reports 82.3% held-out temporal-triplet acc (v1's "100% on validation" was a single-class recording — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) |
 | 128-dim CSI embeddings (re-ID, similarity, downstream training) | ✅ Trained encoder |
 | Single-person breathing / heart-rate | ⚠️ Server still uses heuristic DSP — model does not replace this yet |
 | 17-keypoint full-body pose | 🔬 No keypoint weights shipped yet — pose pipeline runs but without a learned head |
@@ -1359,7 +1359,7 @@ docker run --rm \
   -v $(pwd)/output:/output \
   --entrypoint /app/sensing-server \
   ruvnet/wifi-densepose:latest \
-  --train --dataset /data --epochs 100 --export-rvf /output/model.rvf
+  --train --dataset /data --epochs 100 --save-rvf /output/model.rvf
 ```
 
 The pipeline runs 10 phases:
@@ -1824,7 +1824,7 @@ huggingface-cli download ruvnet/wifi-densepose-pretrained --local-dir models/pre
 #   model.safetensors    — 48 KB contrastive encoder
 #   model-q4.bin         — 8 KB quantized (recommended)
 #   model-q2.bin         — 4 KB ultra-compact (ESP32 edge)
-#   presence-head.json   — presence detection head (100% accuracy)
+#   presence-head.json   — presence detection head (v2 encoder: 82.3% held-out triplet acc)
 #   node-1.json          — LoRA adapter for room 1
 #   node-2.json          — LoRA adapter for room 2
 ```
@@ -1833,7 +1833,7 @@ huggingface-cli download ruvnet/wifi-densepose-pretrained --local-dir models/pre
 
 The pre-trained encoder converts 8-dim CSI feature vectors into 128-dim embeddings. These embeddings power all 17 sensing applications:
 
-- **Presence detection** — 100% accuracy, never misses, never false alarms
+- **Presence detection** — v2 encoder: 82.3% held-out temporal-triplet accuracy (v1's "100%" was a single-class recording — retracted, [#882](https://github.com/ruvnet/RuView/issues/882))
 - **Environment fingerprinting** — kNN search finds "states like this one"
 - **Anomaly detection** — embeddings that don't match known clusters = anomaly
 - **Activity classification** — different activities cluster in embedding space

firmware/esp32-csi-node/components/wasm3/CMakeLists.txt

@@ -65,6 +65,15 @@ target_compile_definitions(${COMPONENT_LIB} PUBLIC
     d_m3LogOutput=0                  # Disable WASM3 stdout logging (use ESP_LOG)
     d_m3FixedHeap=0                  # Use dynamic allocation (PSRAM-friendly)
     WASM3_AVAILABLE=1                # Flag for conditional compilation
+    # Issue #946: GCC 15.2.0 for Xtensa (ESP-IDF v6.0.1) rejects wasm3's
+    # `M3_MUSTTAIL` aggressive tail-call attribute with
+    # "cannot tail-call: machine description does not have a sibcall_epilogue
+    # instruction pattern". wasm3 falls back to a regular call sequence when
+    # M3_NO_MUSTTAIL is defined — slightly slower per opcode but functionally
+    # identical. Forcing it off unconditionally on Xtensa is fine because the
+    # tail-call optimisation was never reliable on this target anyway. Older
+    # IDF/GCC builds also accept the define (it just becomes a no-op).
+    M3_NO_MUSTTAIL=1
 )
 
 # Suppress warnings from third-party code.

firmware/esp32-csi-node/main/adaptive_controller.c

@@ -220,11 +220,20 @@ static void fast_loop_cb(TimerHandle_t t)
     adaptive_controller_decide(&s_cfg, s_state, &obs, &dec);
     apply_decision(&dec);
 
-    /* ADR-081 Layer 4/5: emit compact feature state on every fast tick
-     * (default 200 ms → 5 Hz, within the 1–10 Hz spec). Replaces raw
-     * ADR-018 CSI as the default upstream; raw remains available as a
-     * debug stream gated by the channel plan. */
-    emit_feature_state();
+    /* ADR-081 Layer 4/5: emit compact feature state at 1 Hz (the spec's
+     * 1–10 Hz floor). Was previously emitted on every fast tick (~5 Hz at
+     * the default 200 ms fast period), which combined with CSI promiscuous
+     * RX saturated the WiFi TX airtime — measured live on COM8 (S3) and
+     * COM9 (C6): every adaptive cycle showed `sendto ENOMEM — backing off
+     * for 100 ms`, and bumping LWIP/WiFi buffer pools to 4× had no effect
+     * on the rate because the bottleneck was radio TX time, not pool size.
+     * Dropping to 1 Hz (5× less feature_state traffic) frees the TX queue
+     * for CSI sends and lands well within the spec. */
+    static uint8_t s_emit_divider = 0;
+    if (++s_emit_divider >= 5) {
+        s_emit_divider = 0;
+        emit_feature_state();
+    }
 }
 
 static void medium_loop_cb(TimerHandle_t t)

firmware/esp32-csi-node/main/c6_sync_espnow.c

@@ -21,6 +21,7 @@
 #include "esp_wifi.h"
 #include "esp_mac.h"
 #include "esp_timer.h"
+#include "esp_idf_version.h"
 #include "freertos/FreeRTOS.h"
 #include "freertos/timers.h"
 #include <string.h>
@@ -144,11 +145,27 @@ static void on_recv(const uint8_t *src_mac, const uint8_t *data, int len)
     }
 }
 
+/* Issue #944: ESP-IDF v6.0 changed `esp_now_send_cb_t` from
+ *   void (*)(const uint8_t *mac, esp_now_send_status_t status)
+ * to
+ *   void (*)(const esp_now_send_info_t *tx_info, esp_now_send_status_t status)
+ * Both signatures ignore the address-side argument here — we only inspect
+ * `status` to bump the TX-fail counter — so the body is identical; only the
+ * function-pointer type differs. ESP_IDF_VERSION_MAJOR is the canonical guard.
+ */
+#if ESP_IDF_VERSION_MAJOR >= 6
+static void on_send(const esp_now_send_info_t *tx_info, esp_now_send_status_t status)
+{
+    (void)tx_info;
+    if (status != ESP_NOW_SEND_SUCCESS) s_tx_fail++;
+}
+#else
 static void on_send(const uint8_t *mac, esp_now_send_status_t status)
 {
     (void)mac;
     if (status != ESP_NOW_SEND_SUCCESS) s_tx_fail++;
 }
+#endif
 
 static void beacon_timer_cb(TimerHandle_t t)
 {

firmware/esp32-csi-node/main/csi_collector.c

@@ -637,6 +637,23 @@ static void hop_timer_cb(void *arg)
     csi_hop_next_channel();
 }
 
+void csi_collector_enable_data_capture(void)
+{
+    /* MGMT-only (RuView#396) starves the CSI callback on display-less boards
+     * (RuView#521/#893): beacons alone are sparse, yield collapses to 0 pps.
+     * Without a display there is no QSPI/SPI-flash cache contention with the
+     * DATA-frame interrupt load, so capture DATA frames too. */
+    wifi_promiscuous_filter_t filt = {
+        .filter_mask = WIFI_PROMIS_FILTER_MASK_MGMT | WIFI_PROMIS_FILTER_MASK_DATA,
+    };
+    esp_err_t err = esp_wifi_set_promiscuous_filter(&filt);
+    if (err == ESP_OK) {
+        ESP_LOGI(TAG, "CSI filter upgraded to MGMT+DATA (no display, RuView#893)");
+    } else {
+        ESP_LOGW(TAG, "Failed to enable DATA-frame CSI capture: %s", esp_err_to_name(err));
+    }
+}
+
 void csi_collector_start_hop_timer(void)
 {
     if (s_hop_count <= 1) {

firmware/esp32-csi-node/main/csi_collector.h

@@ -90,6 +90,19 @@ void csi_hop_next_channel(void);
  */
 void csi_collector_start_hop_timer(void);
 
+/**
+ * Upgrade the promiscuous filter to capture DATA frames in addition to MGMT
+ * (RuView#893/#521).
+ *
+ * Called on display-less boards: the MGMT-only filter (the #396 display-crash
+ * workaround set in csi_collector_init) only fires the CSI callback on sparse
+ * management frames, so yield collapses to 0 pps under real traffic and the
+ * node looks dead. A board with no AMOLED panel has no QSPI/SPI-flash cache
+ * contention, so it can safely capture DATA frames — restoring abundant CSI.
+ * Display boards keep MGMT-only to avoid the #396 crash.
+ */
+void csi_collector_enable_data_capture(void);
+
 /**
  * Inject an NDP (Null Data Packet) frame for sensing.
  *

firmware/esp32-csi-node/main/display_task.c

@@ -9,6 +9,14 @@
 #include "display_task.h"
 #include "sdkconfig.h"
 
+/* Set true once an AMOLED panel is detected and the display task starts.
+ * Defined outside the CONFIG_DISPLAY_ENABLE guard so display_is_active()
+ * exists on headless builds too (where it stays false → CSI captures DATA
+ * frames; see RuView#893). */
+static bool s_display_active = false;
+
+bool display_is_active(void) { return s_display_active; }
+
 #if CONFIG_DISPLAY_ENABLE
 
 #include <string.h>
@@ -162,6 +170,7 @@ esp_err_t display_task_start(void)
 
     ESP_LOGI(TAG, "Display task started (Core %d, priority %d, %d fps)",
              DISP_TASK_CORE, DISP_TASK_PRIORITY, DISP_FPS_LIMIT);
+    s_display_active = true;
     return ESP_OK;
 }
 

firmware/esp32-csi-node/main/display_task.h

@@ -7,6 +7,7 @@
 #define DISPLAY_TASK_H
 
 #include "esp_err.h"
+#include <stdbool.h>
 
 #ifdef __cplusplus
 extern "C" {
@@ -22,6 +23,15 @@ extern "C" {
  */
 esp_err_t display_task_start(void);
 
+/**
+ * @return true once an AMOLED panel has been detected and the display task
+ * is running; false on headless boards (no panel, or built without display
+ * support). Used to choose the CSI promiscuous filter (RuView#893): a board
+ * with no display has no QSPI/SPI-flash contention, so it can safely capture
+ * DATA frames for proper CSI yield instead of starving on MGMT-only.
+ */
+bool display_is_active(void);
+
 #ifdef __cplusplus
 }
 #endif

firmware/esp32-csi-node/main/main.c

@@ -410,6 +410,21 @@ void app_main(void)
     }
 #endif
 
+    /* RuView#893/#521: the MGMT-only promiscuous filter (set in
+     * csi_collector_init as the #396 display-crash workaround) starves the CSI
+     * callback on display-less boards — yield collapses to 0 pps and the node
+     * looks dead despite being on the network. Now that the display probe has
+     * run, boards with no AMOLED panel (no QSPI/SPI-flash cache contention)
+     * upgrade the filter to capture DATA frames too, restoring CSI yield. */
+#ifdef CONFIG_DISPLAY_ENABLE
+    bool has_display = display_is_active();   /* runtime panel probe result */
+#else
+    bool has_display = false;                 /* display support not compiled in */
+#endif
+    if (!has_display) {
+        csi_collector_enable_data_capture();
+    }
+
     ESP_LOGI(TAG, "CSI streaming active → %s:%d (edge_tier=%u, OTA=%s, WASM=%s, mmWave=%s, swarm=%s, adapt=%s)",
              g_nvs_config.target_ip, g_nvs_config.target_port,
              g_nvs_config.edge_tier,

firmware/esp32-csi-node/main/rv_feature_state.h

@@ -12,7 +12,8 @@
  *   0xC5110003 — ADR-069 feature vector (edge_processing.h)
  *   0xC5110004 — ADR-063 fused vitals   (edge_processing.h)
  *   0xC5110005 — ADR-039 compressed CSI (edge_processing.h)
- *   0xC5110006 — ADR-081 feature state  (this file) ← new
+ *   0xC5110006 — ADR-081 feature state  (this file)
+ *   0xC5110007 — ADR-040 WASM output    (wasm_runtime.h, reassigned per issue #928)
  */
 
 #ifndef RV_FEATURE_STATE_H

firmware/esp32-csi-node/main/swarm_bridge.c

@@ -23,7 +23,16 @@
 static const char *TAG = "swarm";
 
 /* ---- Task parameters ---- */
-#define SWARM_TASK_STACK   3072   /**< 3 KB stack — HTTP client uses ~2.5 KB. */
+/* Issue #949: 3 KB was sized for plain HTTP (~2.5 KB). The bug reporter
+ * configured `--seed-url https://…` which exercises TLS — mbedTLS handshake
+ * alone needs 4-6 KB on the stack (cipher suite + cert chain + ECDH), and on
+ * top of that esp_http_client adds another 1.5-2 KB. The task panicked with
+ * `0xa5a5a5a5` (FreeRTOS stack-fill sentinel) immediately after "bridge init
+ * OK". 8 KB comfortably fits TLS with margin for the cert chain + headers;
+ * confirmed against mbedTLS's stack analyser. Plain-HTTP deployments waste
+ * ~5 KB of headroom but that's <0.1 % of PSRAM, an acceptable cost for the
+ * bug class this prevents. */
+#define SWARM_TASK_STACK   8192   /**< 8 KB stack — fits mbedTLS handshake. */
 #define SWARM_TASK_PRIO    3
 #define SWARM_TASK_CORE    0
 #define SWARM_HTTP_TIMEOUT 3000  /**< HTTP timeout in ms (Seed responds <100ms on LAN). */

firmware/esp32-csi-node/main/wasm_runtime.h

@@ -43,7 +43,16 @@
 
 #define WASM_MAX_MODULE_SIZE (128 * 1024)  /**< Max .wasm binary size (128 KB). */
 #define WASM_STACK_SIZE      (8 * 1024)    /**< WASM execution stack (8 KB). */
-#define WASM_OUTPUT_MAGIC    0xC5110004    /**< WASM output packet magic. */
+/* Issue #928: WASM output was originally 0xC5110004, but that magic is
+ * canonically owned by ADR-063 fused vitals (edge_processing.h). Both packets
+ * were transmitted on the same magic, and the host parser only knew the WASM
+ * shape, so on the ESP32-C6 + MR60BHA2 mmWave config the 48-byte fused-vitals
+ * packet was being read as garbage WASM events. Reassigned to 0xC5110007 (next
+ * free slot in the registry — see rv_feature_state.h). Firmware older than
+ * this commit will silently lose its WASM event stream against an updated host
+ * — that's the deliberate "fail loud" choice over silent misparsing.
+ */
+#define WASM_OUTPUT_MAGIC    0xC5110007    /**< WASM output packet magic (post-#928). */
 #define WASM_MAX_EVENTS      16            /**< Max events per output packet. */
 
 /* ---- WASM Event (5 bytes: u8 type + f32 value) ---- */
@@ -54,7 +63,7 @@ typedef struct __attribute__((packed)) {
 
 /* ---- WASM Output Packet ---- */
 typedef struct __attribute__((packed)) {
-    uint32_t magic;         /**< WASM_OUTPUT_MAGIC = 0xC5110004. */
+    uint32_t magic;         /**< WASM_OUTPUT_MAGIC = 0xC5110007 (issue #928). */
     uint8_t  node_id;       /**< ESP32 node identifier. */
     uint8_t  module_id;     /**< Module slot index. */
     uint16_t event_count;   /**< Number of events in this packet. */

firmware/esp32-csi-node/release_bins/c6-adr110/SHA256SUMS.txt

@@ -1,4 +1,4 @@
-889715e9d698ad78f9978ad8b93b6af24a726b0494247201c8f0d920d9fc80ca *firmware/esp32-csi-node/release_bins/c6-adr110/bootloader.bin
-d8539e47c6f10a3344679118619e3fe01cfd66eb560ea8883268ca7c9a12efa4 *firmware/esp32-csi-node/release_bins/c6-adr110/esp32-csi-node.bin
+b0fb1f217a39c80bc95b5eb8208a0b8572ae64efa0f6d580b76caff4affe0f4d *firmware/esp32-csi-node/release_bins/c6-adr110/bootloader.bin
+4764c5b20a353895f70122816adc98f861ec20e9a8ea9b344dc0648b6341073c *firmware/esp32-csi-node/release_bins/c6-adr110/esp32-csi-node.bin
 7d2c7ac4888bfd75cd5f56e8d61f69595121183afc81556c876732fd3782c62f *firmware/esp32-csi-node/release_bins/c6-adr110/ota_data_initial.bin
 4c2cc4ffd52641e23b779bd57b3908014083ac3c1aab395756478c89e70d81f0 *firmware/esp32-csi-node/release_bins/c6-adr110/partition-table.bin

firmware/esp32-csi-node/release_bins/s3-adr110/SHA256SUMS.txt

@@ -1,3 +1,3 @@
-3c4905dd202ccabf4230cbabcc9320f250a60b1a7254eff7424780201bcb2072 *firmware/esp32-csi-node/release_bins/s3-adr110/bootloader.bin
-7a8bf9582c9031fed32f1ada44f5c41dd99bd07fadff8e5c86e07aa0f343e847 *firmware/esp32-csi-node/release_bins/s3-adr110/esp32-csi-node.bin
+b973d7eda65affb746adcfa63ceb18f779f206d240b76f01b8c9ae7485455660 *firmware/esp32-csi-node/release_bins/s3-adr110/bootloader.bin
+e21ef94aba779d534dc048c1b9da731c81e5dbe09d0645cfd70a05ad3642d3e9 *firmware/esp32-csi-node/release_bins/s3-adr110/esp32-csi-node.bin
 67222c257c0477501fd4002275638dc4262b34eb68235b8289fb1337054d322b *firmware/esp32-csi-node/release_bins/s3-adr110/partition-table.bin

firmware/esp32-csi-node/release_bins/version.txt

@@ -1,3 +1,4 @@
-0.6.6
-git-sha: cbcb389cb (pre-commit)
-built: 2026-05-21
+0.6.7
+git-sha: 8703ade9b
+built: 2026-06-02
+note: RuView#893 — display-less boards capture DATA frames (CSI yield 0pps fix); hardware-verified on ESP32-C6 (0->27 pps)

firmware/esp32-csi-node/sdkconfig.defaults

@@ -29,6 +29,30 @@ CONFIG_LOG_DEFAULT_LEVEL_INFO=y
 # LWIP: enable extended socket options for UDP multicast
 CONFIG_LWIP_SO_RCVBUF=y
 
+# Issue (sibling of #946/#949/#864 cluster): UDP `sendto` returned ENOMEM
+# in a tight loop on both ESP32-S3 (COM8) and ESP32-C6 (COM9) at the v0.7.0
+# CSI packet rate (CSI cb + status + sync + feature_state all sharing the
+# LWIP/WiFi pools). stream_sender.c has a cooldown path so the device
+# doesn't crash, but ~90 % of CSI frames were dropped before reaching the
+# host — boot trace showed `sendto ENOMEM — backing off 100 ms` repeating
+# every capture cycle. Stock IDF v5.4 defaults: UDP recv mbox=6, TCPIP
+# mbox=32, WiFi dynamic TX buffers=32 — too small once CSI promiscuous
+# mode is active. These bumps roughly quadruple the relevant pools at
+# ~3 KB extra heap cost, measured live on both targets Jun 8 2026.
+CONFIG_LWIP_UDP_RECVMBOX_SIZE=32
+CONFIG_LWIP_TCPIP_RECVMBOX_SIZE=64
+CONFIG_ESP_WIFI_DYNAMIC_TX_BUFFER_NUM=64
+# NOTE: Empirical 25 s measurements on the S3 at COM8 showed these bumps
+# eliminate the csi_collector.sendto failure path (`fail #1..5` →
+# `fail #0`) — real improvement — but do NOT eliminate the broader
+# `feature_state emit` ENOMEM at ~10/s. That residual is the WiFi
+# radio's TX airtime saturating under CSI promiscuous RX, and bigger
+# buffers cap out at the 100 ms backoff window regardless of size
+# (verified at WIFI_DYNAMIC_TX=128 + PBUF_POOL=32 — identical count).
+# The proper fix is rate-limiting adaptive_controller.c's emit cadence
+# from ~50 ms to the intended 1 Hz, which is a code refactor tracked
+# in a separate follow-up issue.
+
 # FreeRTOS: increase task stack for CSI processing
 CONFIG_ESP_MAIN_TASK_STACK_SIZE=8192
 

requirements.txt

@@ -36,3 +36,4 @@ scikit-learn>=1.2.0
 
 # Monitoring dependencies
 prometheus-client>=0.16.0
+psutil>=5.9.0  # system metrics — imported by health.py / metrics.py / status.py / monitoring.py

v2/crates/wifi-densepose-desktop/src/commands/server.rs

@@ -108,8 +108,14 @@ pub async fn start_server(
         cmd.args(["--log-level", log_level]);
     }
 
-    // Set data source (default to "simulate" if not specified for demo mode)
-    let source = config.source.as_deref().unwrap_or("simulate");
+    // Default to explicit "simulated" demo mode when the desktop user hasn't
+    // chosen a source — this is the *Tauri demo* app, not a production
+    // sensing endpoint, so the demo default is correct here. Critically, the
+    // value passed downstream is the **explicit** "simulated", not "auto",
+    // which means the sensing-server will tag the data as synthetic in its
+    // API responses rather than silently fall back (issue #937 fix in
+    // sensing-server's `auto` handler).
+    let source = config.source.as_deref().unwrap_or("simulated");
     cmd.args(["--source", source]);
 
     // Redirect stdout/stderr to pipes for monitoring
@@ -317,7 +323,7 @@ pub async fn restart_server(
             log_level: None,
             bind_address: None,
             server_path: None,
-            source: None, // Use default (simulate)
+            source: None, // Falls through to explicit "simulated" — Tauri demo default.
         }
     };
 

v2/crates/wifi-densepose-mat/src/detection/ensemble.rs

@@ -172,6 +172,14 @@ impl EnsembleClassifier {
         let has_movement = reading.movement.movement_type != MovementType::None;
 
         if !has_breathing && !has_movement {
+            // SAFETY: a detectable heartbeat means the survivor is ALIVE. No
+            // sensed breathing/movement *with* a pulse is respiratory arrest —
+            // the most time-critical savable state (Immediate), never Deceased.
+            // Only the total absence of breathing, movement AND heartbeat is
+            // reported Deceased.
+            if reading.heartbeat.is_some() {
+                return TriageStatus::Immediate;
+            }
             return TriageStatus::Deceased;
         }
 
@@ -295,6 +303,27 @@ mod tests {
         assert_eq!(result.recommended_triage, TriageStatus::Deceased);
     }
 
+    /// SAFETY regression: heartbeat present but no sensed breathing/movement is
+    /// respiratory arrest — Immediate, never Deceased. Only the *total* absence
+    /// of breathing, movement AND heartbeat (the test above) is Deceased.
+    #[test]
+    fn test_heartbeat_with_no_breathing_or_movement_is_immediate() {
+        // breathing: None, heartbeat: Some(72 bpm), movement: None
+        let reading = make_reading(None, Some(72.0), MovementType::None);
+
+        let classifier = EnsembleClassifier::new(EnsembleConfig {
+            min_ensemble_confidence: 0.0,
+            ..EnsembleConfig::default()
+        });
+
+        let result = classifier.classify(&reading);
+        assert_eq!(
+            result.recommended_triage,
+            TriageStatus::Immediate,
+            "a survivor with a pulse must never be triaged Deceased"
+        );
+    }
+
     #[test]
     fn test_ensemble_confidence_weighting() {
         let classifier = EnsembleClassifier::new(EnsembleConfig {

v2/crates/wifi-densepose-mat/src/domain/triage.rs

@@ -104,7 +104,20 @@ impl TriageCalculator {
         let movement_status = Self::assess_movement(vitals);
 
         // Step 4: Combine assessments
-        Self::combine_assessments(breathing_status, movement_status)
+        let status = Self::combine_assessments(breathing_status, movement_status);
+
+        // Step 5: SAFETY OVERRIDE — a detectable heartbeat means the survivor is
+        // ALIVE. `combine_assessments` only sees breathing + movement, so a
+        // person with a pulse but no *sensed* breathing/movement (respiratory
+        // arrest, or breathing too shallow for CSI to pick up) would otherwise
+        // be reported Deceased and deprioritized for rescue. No breathing + a
+        // pulse is the most time-critical *savable* state, so escalate to
+        // Immediate rather than ever calling a survivor with a heartbeat dead.
+        if status == TriageStatus::Deceased && vitals.heartbeat.is_some() {
+            return TriageStatus::Immediate;
+        }
+
+        status
     }
 
     /// Assess breathing status
@@ -217,7 +230,9 @@ enum MovementAssessment {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::domain::{BreathingPattern, ConfidenceScore, MovementProfile};
+    use crate::domain::{
+        BreathingPattern, ConfidenceScore, HeartbeatSignature, MovementProfile, SignalStrength,
+    };
     use chrono::Utc;
 
     fn create_vitals(
@@ -233,6 +248,29 @@ mod tests {
         }
     }
 
+    /// SAFETY regression: a survivor with a detectable heartbeat but no sensed
+    /// breathing or movement is in respiratory arrest — Immediate (Red), and
+    /// must NEVER be reported Deceased. (Before the fix, `combine_assessments`
+    /// ignored heartbeat and returned Deceased; that path was in fact only
+    /// reachable *because* a heartbeat made `has_vitals()` true.)
+    #[test]
+    fn heartbeat_with_no_breathing_or_movement_is_immediate_not_deceased() {
+        let vitals = VitalSignsReading {
+            breathing: None,
+            heartbeat: Some(HeartbeatSignature {
+                rate_bpm: 72.0,
+                variability: 0.1,
+                strength: SignalStrength::Moderate,
+            }),
+            movement: MovementProfile::default(),
+            timestamp: Utc::now(),
+            confidence: ConfidenceScore::new(0.8),
+        };
+        let status = TriageCalculator::calculate(&vitals);
+        assert_eq!(status, TriageStatus::Immediate, "pulse present ⇒ alive");
+        assert_ne!(status, TriageStatus::Deceased);
+    }
+
     #[test]
     fn test_no_vitals_is_unknown() {
         let vitals = create_vitals(None, MovementProfile::default());

v2/crates/wifi-densepose-sensing-server/src/bearer_auth.rs

@@ -100,7 +100,17 @@ pub async fn require_bearer(
         .headers()
         .get(AUTHORIZATION)
         .and_then(|v| v.to_str().ok())
-        .and_then(|s| s.strip_prefix("Bearer "));
+        // RFC 6750 §2.1 / RFC 7235 §2.1: the auth-scheme ("Bearer") is
+        // case-insensitive. Match it as such (and tolerate extra leading
+        // whitespace before the token) so a correct token isn't rejected
+        // just because a client sent `bearer`/`BEARER`. The token compare
+        // below stays exact + constant-time.
+        .and_then(|s| {
+            let (scheme, token) = s.split_once(' ')?;
+            scheme
+                .eq_ignore_ascii_case("Bearer")
+                .then(|| token.trim_start())
+        });
     let ok = supplied
         .map(|s| ct_eq(s.as_bytes(), expected.as_bytes()))
         .unwrap_or(false);
@@ -185,6 +195,31 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn accepts_case_insensitive_bearer_scheme() {
+        // RFC 6750 §2.1 / RFC 7235 §2.1: the auth-scheme is case-insensitive.
+        // A correct token must authenticate regardless of scheme casing or
+        // extra whitespace; a wrong token must still be rejected.
+        async fn req_status(auth_value: &str) -> StatusCode {
+            let r = wrap(AuthState::from_token("s3cr3t"));
+            let mut req = Request::builder()
+                .method("GET")
+                .uri("/api/v1/info")
+                .body(Body::empty())
+                .unwrap();
+            req.headers_mut()
+                .insert(AUTHORIZATION, auth_value.parse().unwrap());
+            r.oneshot(req).await.unwrap().status()
+        }
+        assert_eq!(req_status("Bearer s3cr3t").await, StatusCode::OK);
+        assert_eq!(req_status("bearer s3cr3t").await, StatusCode::OK);
+        assert_eq!(req_status("BEARER s3cr3t").await, StatusCode::OK);
+        assert_eq!(req_status("Bearer  s3cr3t").await, StatusCode::OK); // extra space
+        // Scheme leniency must NOT weaken the token check.
+        assert_eq!(req_status("bearer nope").await, StatusCode::UNAUTHORIZED);
+        assert_eq!(req_status("Basic s3cr3t").await, StatusCode::UNAUTHORIZED);
+    }
+
     #[tokio::test]
     async fn enabled_blocks_api_with_wrong_bearer() {
         let r = wrap(AuthState::from_token("s3cr3t"));

v2/crates/wifi-densepose-sensing-server/src/csi.rs

@@ -45,13 +45,14 @@ pub fn parse_esp32_vitals(buf: &[u8]) -> Option<Esp32VitalsPacket> {
     })
 }
 
-/// Parse a WASM output packet (magic 0xC511_0004).
+/// Parse a WASM output packet (magic 0xC511_0007 — reassigned per issue #928;
+/// the original 0xC511_0004 collided with ADR-063 fused vitals).
 pub fn parse_wasm_output(buf: &[u8]) -> Option<WasmOutputPacket> {
     if buf.len() < 8 {
         return None;
     }
     let magic = u32::from_le_bytes([buf[0], buf[1], buf[2], buf[3]]);
-    if magic != 0xC511_0004 {
+    if magic != 0xC511_0007 {
         return None;
     }
 

v2/crates/wifi-densepose-sensing-server/src/field_bridge.rs

@@ -21,6 +21,15 @@ const ENERGY_THRESH_2: f64 = 12.0;
 /// Perturbation energy threshold for detecting a third person.
 const ENERGY_THRESH_3: f64 = 25.0;
 
+/// Maximum occupancy a single ESP32 link can plausibly resolve (#894).
+/// The score heuristic (`score_to_person_count`) and the perturbation-energy
+/// fallback below both cap here; the eigenvalue path is bounded to match,
+/// rather than leaking its internal `min(10)` ceiling on noisy / under-
+/// calibrated CSI (the "10 persons reported when 1 present" symptom).
+/// Resolving more than this from one link's subcarrier covariance is not
+/// reliable — genuine higher counts come from the multistatic fusion path.
+const MAX_SINGLE_LINK_OCCUPANCY: usize = 3;
+
 /// Create a FieldModelConfig for single-link mode (one ESP32 node = one link).
 /// This avoids the DimensionMismatch error when feeding single-frame observations.
 pub fn single_link_config() -> FieldModelConfig {
@@ -55,9 +64,15 @@ pub fn occupancy_or_fallback(
                 return score_to_person_count(smoothed_score, prev_count);
             }
 
-            // Try eigenvalue-based occupancy first (best accuracy).
+            // Try eigenvalue-based occupancy first (best accuracy). Bound it to
+            // the same single-link maximum the sibling estimators use — the
+            // perturbation fallback below and score_to_person_count both cap at
+            // MAX_SINGLE_LINK_OCCUPANCY. Without this, estimate_occupancy's
+            // internal min(10) ceiling leaks up to 10 persons on noisy / under-
+            // calibrated CSI (#894), while every other path on the same data
+            // would report ≤3.
             if let Ok(count) = field.estimate_occupancy(&frames) {
-                return count;
+                return count.min(MAX_SINGLE_LINK_OCCUPANCY);
             } // else fall through to perturbation energy
 
             // Fallback: perturbation energy thresholds.

v2/crates/wifi-densepose-sensing-server/src/main.rs

@@ -1114,7 +1114,7 @@ fn parse_esp32_vitals(buf: &[u8]) -> Option<Esp32VitalsPacket> {
     })
 }
 
-// ── ADR-040: WASM Output Packet (magic 0xC511_0004) ───────────────────────────
+// ── ADR-040: WASM Output Packet (magic 0xC511_0007 — reassigned per #928) ─────
 
 /// Single WASM event (type + value).
 #[derive(Debug, Clone, Serialize)]
@@ -1131,13 +1131,14 @@ struct WasmOutputPacket {
     events: Vec<WasmEvent>,
 }
 
-/// Parse a WASM output packet (magic 0xC511_0004).
+/// Parse a WASM output packet (magic 0xC511_0007 — reassigned per issue #928;
+/// the original 0xC511_0004 was a collision with ADR-063 fused vitals).
 fn parse_wasm_output(buf: &[u8]) -> Option<WasmOutputPacket> {
     if buf.len() < 8 {
         return None;
     }
     let magic = u32::from_le_bytes([buf[0], buf[1], buf[2], buf[3]]);
-    if magic != 0xC511_0004 {
+    if magic != 0xC511_0007 {
         return None;
     }
 
@@ -1169,6 +1170,187 @@ fn parse_wasm_output(buf: &[u8]) -> Option<WasmOutputPacket> {
     })
 }
 
+// ── ADR-063: Edge Fused Vitals Packet (magic 0xC511_0004) ─────────────────────
+//
+// 48-byte packed struct emitted by the ESP32-C6 + MR60BHA2 mmWave config when
+// `mmwave_sensor_get_state().detected` is true. Byte layout from
+// `firmware/esp32-csi-node/main/edge_processing.h` line 129 — kept in lockstep
+// with the firmware's `_Static_assert(sizeof(edge_fused_vitals_pkt_t) == 48)`.
+// Issue #928 surfaced that this magic was being parsed as WASM output and the
+// fused vitals were silently lost. Adding the proper parser here.
+
+#[derive(Debug, Clone, Serialize)]
+struct EdgeFusedVitalsPacket {
+    node_id: u8,
+    /// Bit0=presence, Bit1=fall, Bit2=motion, Bit3=mmwave_present.
+    flags: u8,
+    /// Fused breathing rate in BPM (firmware sends BPM*100; we scale here).
+    breathing_rate_bpm: f32,
+    /// Fused heartrate in BPM (firmware sends BPM*10000; we scale here).
+    heartrate_bpm: f32,
+    rssi: i8,
+    n_persons: u8,
+    /// `mmwave_type_t` enum value from firmware.
+    mmwave_type: u8,
+    /// 0-100 fusion quality score.
+    fusion_confidence: u8,
+    motion_energy: f32,
+    presence_score: f32,
+    timestamp_ms: u32,
+    /// Raw mmWave heart rate (BPM).
+    mmwave_hr_bpm: f32,
+    /// Raw mmWave breathing rate (BPM).
+    mmwave_br_bpm: f32,
+    /// Distance to nearest target (cm).
+    mmwave_distance_cm: f32,
+    /// Target count from mmWave.
+    mmwave_targets: u8,
+    /// mmWave signal quality 0-100.
+    mmwave_confidence: u8,
+}
+
+/// Parse an ADR-063 edge fused vitals packet (magic 0xC511_0004, 48 bytes).
+fn parse_edge_fused_vitals(buf: &[u8]) -> Option<EdgeFusedVitalsPacket> {
+    if buf.len() < 48 {
+        return None;
+    }
+    let magic = u32::from_le_bytes([buf[0], buf[1], buf[2], buf[3]]);
+    if magic != 0xC511_0004 {
+        return None;
+    }
+
+    let node_id = buf[4];
+    let flags = buf[5];
+    let breathing_raw = u16::from_le_bytes([buf[6], buf[7]]);
+    let heartrate_raw = u32::from_le_bytes([buf[8], buf[9], buf[10], buf[11]]);
+    let rssi = buf[12] as i8;
+    let n_persons = buf[13];
+    let mmwave_type = buf[14];
+    let fusion_confidence = buf[15];
+    let motion_energy = f32::from_le_bytes([buf[16], buf[17], buf[18], buf[19]]);
+    let presence_score = f32::from_le_bytes([buf[20], buf[21], buf[22], buf[23]]);
+    let timestamp_ms = u32::from_le_bytes([buf[24], buf[25], buf[26], buf[27]]);
+    let mmwave_hr_bpm = f32::from_le_bytes([buf[28], buf[29], buf[30], buf[31]]);
+    let mmwave_br_bpm = f32::from_le_bytes([buf[32], buf[33], buf[34], buf[35]]);
+    let mmwave_distance_cm = f32::from_le_bytes([buf[36], buf[37], buf[38], buf[39]]);
+    let mmwave_targets = buf[40];
+    let mmwave_confidence = buf[41];
+    // buf[42..48] are firmware reserved fields (reserved3 u16 + reserved4 u32).
+
+    Some(EdgeFusedVitalsPacket {
+        node_id,
+        flags,
+        breathing_rate_bpm: breathing_raw as f32 / 100.0,
+        heartrate_bpm: heartrate_raw as f32 / 10000.0,
+        rssi,
+        n_persons,
+        mmwave_type,
+        fusion_confidence,
+        motion_energy,
+        presence_score,
+        timestamp_ms,
+        mmwave_hr_bpm,
+        mmwave_br_bpm,
+        mmwave_distance_cm,
+        mmwave_targets,
+        mmwave_confidence,
+    })
+}
+
+#[cfg(test)]
+mod issue_928_magic_collision_tests {
+    //! Issue #928 — `0xC511_0004` was being parsed as WASM output, eating the
+    //! C6+mmWave fused-vitals packets. After this fix, `0xC511_0004` routes to
+    //! `parse_edge_fused_vitals` and WASM output owns the freshly-allocated
+    //! `0xC511_0007` slot. Tests guard both halves of the swap.
+    use super::*;
+
+    /// Build a 48-byte synthetic fused-vitals packet matching the firmware's
+    /// `edge_fused_vitals_pkt_t` layout from `edge_processing.h:129`.
+    fn build_fused_vitals_packet() -> Vec<u8> {
+        let mut buf = vec![0u8; 48];
+        buf[0..4].copy_from_slice(&0xC511_0004u32.to_le_bytes());
+        buf[4] = 9;                                            // node_id
+        buf[5] = 0b0000_1001;                                   // flags: presence | mmwave_present
+        buf[6..8].copy_from_slice(&1600u16.to_le_bytes());      // breathing 16.00 BPM
+        buf[8..12].copy_from_slice(&720_000u32.to_le_bytes());  // heartrate 72.0 BPM
+        buf[12] = (-55i8) as u8;                                // rssi
+        buf[13] = 1;                                            // n_persons
+        buf[14] = 2;                                            // mmwave_type
+        buf[15] = 85;                                           // fusion_confidence
+        buf[16..20].copy_from_slice(&0.42f32.to_le_bytes());    // motion_energy
+        buf[20..24].copy_from_slice(&0.95f32.to_le_bytes());    // presence_score
+        buf[24..28].copy_from_slice(&1_234_567u32.to_le_bytes()); // timestamp_ms
+        buf[28..32].copy_from_slice(&71.5f32.to_le_bytes());    // mmwave_hr_bpm
+        buf[32..36].copy_from_slice(&15.8f32.to_le_bytes());    // mmwave_br_bpm
+        buf[36..40].copy_from_slice(&182.0f32.to_le_bytes());   // mmwave_distance_cm
+        buf[40] = 1;                                            // mmwave_targets
+        buf[41] = 90;                                           // mmwave_confidence
+        // bytes 42..48 — firmware reserved fields, left as zero
+        buf
+    }
+
+    #[test]
+    fn parse_edge_fused_vitals_extracts_fields_correctly() {
+        let buf = build_fused_vitals_packet();
+        let pkt = parse_edge_fused_vitals(&buf).expect("must parse a well-formed packet");
+        assert_eq!(pkt.node_id, 9);
+        assert_eq!(pkt.flags, 0b0000_1001);
+        assert!((pkt.breathing_rate_bpm - 16.0).abs() < 1e-3, "breathing scale 100");
+        assert!((pkt.heartrate_bpm - 72.0).abs() < 1e-3, "heartrate scale 10000");
+        assert_eq!(pkt.rssi, -55);
+        assert_eq!(pkt.n_persons, 1);
+        assert_eq!(pkt.mmwave_type, 2);
+        assert_eq!(pkt.fusion_confidence, 85);
+        assert!((pkt.motion_energy - 0.42).abs() < 1e-6);
+        assert!((pkt.presence_score - 0.95).abs() < 1e-6);
+        assert_eq!(pkt.timestamp_ms, 1_234_567);
+        assert!((pkt.mmwave_hr_bpm - 71.5).abs() < 1e-6);
+        assert!((pkt.mmwave_br_bpm - 15.8).abs() < 1e-3);
+        assert!((pkt.mmwave_distance_cm - 182.0).abs() < 1e-6);
+        assert_eq!(pkt.mmwave_targets, 1);
+        assert_eq!(pkt.mmwave_confidence, 90);
+    }
+
+    #[test]
+    fn parse_edge_fused_vitals_rejects_short_buffer() {
+        let buf = build_fused_vitals_packet();
+        // Truncate to 47 bytes — one short of the 48-byte minimum.
+        assert!(parse_edge_fused_vitals(&buf[..47]).is_none());
+    }
+
+    #[test]
+    fn parse_edge_fused_vitals_rejects_wrong_magic() {
+        let mut buf = build_fused_vitals_packet();
+        buf[0..4].copy_from_slice(&0xC511_0007u32.to_le_bytes()); // WASM magic, not fused
+        assert!(parse_edge_fused_vitals(&buf).is_none());
+    }
+
+    #[test]
+    fn parse_wasm_output_rejects_legacy_0004_magic() {
+        // The old WASM magic collided with fused vitals — must no longer be
+        // accepted. A real fused-vitals packet starts with 0xC511_0004 and
+        // would have been misparsed before this fix.
+        let buf = build_fused_vitals_packet();
+        assert!(parse_wasm_output(&buf).is_none(),
+                "issue #928: WASM parser must NOT accept 0xC511_0004");
+    }
+
+    #[test]
+    fn parse_wasm_output_accepts_new_0007_magic() {
+        // Build a tiny well-formed WASM output packet on the new magic.
+        let mut buf = vec![0u8; 8];
+        buf[0..4].copy_from_slice(&0xC511_0007u32.to_le_bytes());
+        buf[4] = 5;                                          // node_id
+        buf[5] = 1;                                          // module_id
+        buf[6..8].copy_from_slice(&0u16.to_le_bytes());      // event_count = 0
+        let pkt = parse_wasm_output(&buf).expect("0xC511_0007 must parse");
+        assert_eq!(pkt.node_id, 5);
+        assert_eq!(pkt.module_id, 1);
+        assert!(pkt.events.is_empty());
+    }
+}
+
 // ── ESP32 UDP frame parser ───────────────────────────────────────────────────
 
 fn parse_esp32_frame(buf: &[u8]) -> Option<Esp32Frame> {
@@ -4979,7 +5161,45 @@ async fn udp_receiver_task(state: SharedState, udp_port: u16) {
                     }
                 }
 
-                // ADR-040: Try WASM output packet (magic 0xC511_0004).
+                // ADR-063: Try edge fused vitals packet (magic 0xC511_0004).
+                // Must come BEFORE the WASM parser — issue #928: these two
+                // packet types shared a magic and the WASM parser was eating
+                // fused-vitals frames on the C6+mmWave config. The reassign of
+                // WASM_OUTPUT_MAGIC → 0xC511_0007 (firmware side) plus this
+                // dedicated parser resolve the collision.
+                if let Some(fused) = parse_edge_fused_vitals(&buf[..len]) {
+                    debug!(
+                        "Edge fused vitals from {src}: node={} br={:.1} hr={:.1} \
+                         mmwave_targets={} fusion_conf={}",
+                        fused.node_id, fused.breathing_rate_bpm, fused.heartrate_bpm,
+                        fused.mmwave_targets, fused.fusion_confidence,
+                    );
+                    let s = state.write().await;
+                    if let Ok(json) = serde_json::to_string(&serde_json::json!({
+                        "type": "edge_fused_vitals",
+                        "node_id": fused.node_id,
+                        "breathing_rate_bpm": fused.breathing_rate_bpm,
+                        "heartrate_bpm": fused.heartrate_bpm,
+                        "n_persons": fused.n_persons,
+                        "fusion_confidence": fused.fusion_confidence,
+                        "mmwave": {
+                            "hr_bpm": fused.mmwave_hr_bpm,
+                            "br_bpm": fused.mmwave_br_bpm,
+                            "distance_cm": fused.mmwave_distance_cm,
+                            "targets": fused.mmwave_targets,
+                            "confidence": fused.mmwave_confidence,
+                            "type": fused.mmwave_type,
+                        },
+                        "motion_energy": fused.motion_energy,
+                        "presence_score": fused.presence_score,
+                        "timestamp_ms": fused.timestamp_ms,
+                    })) {
+                        let _ = s.tx.send(json);
+                    }
+                    continue;
+                }
+
+                // ADR-040: Try WASM output packet (magic 0xC511_0007 post-#928).
                 if let Some(wasm_output) = parse_wasm_output(&buf[..len]) {
                     debug!(
                         "WASM output from {src}: node={} module={} events={}",
@@ -5476,6 +5696,159 @@ async fn broadcast_tick_task(state: SharedState, tick_ms: u64) {
     }
 }
 
+/// Map one sensing-broadcast JSON document into the `VitalsSnapshot`(s) to
+/// publish over MQTT (issues #872/#898).
+///
+/// Multi-node sources carry a `nodes` array where **each node has its own
+/// `classification`** (`motion_level`, `presence`, `confidence`) and RSSI — so
+/// each node must surface its *own* presence/motion, not the room-level
+/// aggregate. Previously the bridge applied the aggregate `classification` to
+/// every per-node Home-Assistant device, so a node in an empty corner inherited
+/// another node's "present" (and `motion_level: "absent"` was mis-mapped to full
+/// motion). Vitals (breathing / heart rate) and the person count are room-level
+/// and shared across the per-node devices. Falls back to a single aggregate
+/// snapshot when there is no per-node data (e.g. wifi / simulate sources).
+#[cfg(feature = "mqtt")]
+fn vitals_snapshots_from_sensing_json(
+    v: &serde_json::Value,
+    base_id: &str,
+) -> Vec<wifi_densepose_sensing_server::mqtt::state::VitalsSnapshot> {
+    use wifi_densepose_sensing_server::mqtt::state::VitalsSnapshot;
+
+    // motion_level string -> motion scalar. "absent"/"none"/"still"/"idle"/""
+    // are non-moving; anything else (walking, …) is motion. `fallback` is used
+    // when the field is absent so a partial per-node payload defers to the
+    // room aggregate rather than silently reading 0.
+    fn motion_of(level: Option<&str>, fallback: f64) -> f64 {
+        match level {
+            Some("none") | Some("still") | Some("idle") | Some("absent") | Some("") => 0.0,
+            Some(_) => 1.0,
+            None => fallback,
+        }
+    }
+
+    let ts = (v["timestamp"].as_f64().unwrap_or(0.0) * 1000.0) as i64;
+    let vit = &v["vital_signs"];
+    let breathing = vit["breathing_rate_bpm"].as_f64();
+    let hr = vit["heart_rate_bpm"].as_f64();
+    let n_persons = v["persons"]
+        .as_array()
+        .map(|a| a.len() as u32)
+        .or_else(|| v["estimated_persons"].as_u64().map(|x| x as u32))
+        .unwrap_or(0);
+
+    // Room-level aggregate: the no-nodes fallback, and the per-node default for
+    // any field a node omits.
+    let acls = &v["classification"];
+    let agg_presence = acls["presence"].as_bool().unwrap_or(false);
+    let agg_motion = motion_of(acls["motion_level"].as_str(), 0.0);
+    let agg_conf = acls["confidence"].as_f64().unwrap_or(0.0);
+
+    let mk = |node_id: String, presence: bool, motion: f64, conf: f64, rssi: Option<f64>| {
+        VitalsSnapshot {
+            node_id,
+            timestamp_ms: ts,
+            presence,
+            motion,
+            presence_score: if presence { conf.max(0.0) } else { 0.0 },
+            breathing_rate_bpm: breathing,
+            heartrate_bpm: hr,
+            n_persons,
+            rssi_dbm: rssi,
+            vital_confidence: conf,
+            ..Default::default()
+        }
+    };
+
+    match v["nodes"].as_array() {
+        Some(arr) if !arr.is_empty() => arr
+            .iter()
+            .map(|node| {
+                let n = node["node_id"].as_u64().unwrap_or(0);
+                // Each node carries its OWN classification — use it, deferring to
+                // the room aggregate only for fields the node omits.
+                let ncls = &node["classification"];
+                let presence = ncls["presence"].as_bool().unwrap_or(agg_presence);
+                let motion = motion_of(ncls["motion_level"].as_str(), agg_motion);
+                let conf = ncls["confidence"].as_f64().unwrap_or(agg_conf);
+                mk(
+                    format!("{base_id}-node{n}"),
+                    presence,
+                    motion,
+                    conf,
+                    node["rssi_dbm"].as_f64(),
+                )
+            })
+            .collect(),
+        _ => vec![mk(
+            base_id.to_string(),
+            agg_presence,
+            agg_motion,
+            agg_conf,
+            v["nodes"][0]["rssi_dbm"].as_f64(),
+        )],
+    }
+}
+
+/// Turn a `ProgressiveLoader::new` failure into an actionable diagnostic (#894).
+///
+/// The published HuggingFace `ruvnet/wifi-densepose-pretrained` files
+/// (`model.safetensors`, `model-q{2,4,8}.bin`, `model.rvf.jsonl`) are a
+/// different *format* — and a different encoder architecture — than the RVF
+/// binary container the `--model` progressive loader expects (`RVFS` magic
+/// `0x52564653`). Feeding one to `--model` produced a bare
+/// "invalid magic at offset 0 …" that left users stuck. Detect the common
+/// cases and explain plainly what's loadable instead.
+fn diagnose_model_load_error(path: &std::path::Path, data: &[u8], err: &str) -> String {
+    let name = path
+        .file_name()
+        .and_then(|n| n.to_str())
+        .unwrap_or("")
+        .to_ascii_lowercase();
+    let ext = path
+        .extension()
+        .and_then(|e| e.to_str())
+        .unwrap_or("")
+        .to_ascii_lowercase();
+
+    // safetensors: 8-byte LE header length, then a JSON object starting with '{'.
+    let looks_safetensors = ext == "safetensors" || (data.len() > 9 && data[8] == b'{');
+    // JSONL manifest: starts with '{' (or the well-known suffix).
+    let looks_jsonl =
+        ext == "jsonl" || name.ends_with(".rvf.jsonl") || data.first() == Some(&b'{');
+    // Quantized weight blob shipped on HF (model-q2/q4/q8.bin).
+    let looks_quant_bin = ext == "bin" || name.contains("-q");
+
+    let kind = if looks_safetensors {
+        "a safetensors weight file"
+    } else if looks_jsonl {
+        "a JSONL manifest, not the binary container"
+    } else if looks_quant_bin {
+        "a quantized weight blob (e.g. HuggingFace model-q4.bin)"
+    } else {
+        "not an RVF binary container"
+    };
+
+    format!(
+        "model `{}` could not be loaded: it is {kind}. The --model flag expects an \
+         RVF binary container (`RVFS` magic 0x52564653) produced by the \
+         wifi-densepose-train pipeline. The HuggingFace ruvnet/wifi-densepose-pretrained \
+         files are a different format and encoder architecture, so they do not load \
+         here directly (issue #894). Continuing with signal heuristics. (loader: {err})",
+        path.display()
+    )
+}
+
+/// Whether `--export-rvf` should emit the placeholder container-format demo.
+///
+/// It must only do so **standalone**. Combined with `--train`/`--pretrain` the
+/// real model is produced by the training pipeline, so short-circuiting here
+/// would silently skip training and write placeholder weights — the #894 bug
+/// where the documented `--train … --export-rvf` workflow produced a fake model.
+fn export_emits_placeholder_demo(export_set: bool, train: bool, pretrain: bool) -> bool {
+    export_set && !train && !pretrain
+}
+
 // ── Main ─────────────────────────────────────────────────────────────────────
 
 /// If `--ui-path` points nowhere (wrong cwd), try common repo layouts relative to cwd.
@@ -5519,9 +5892,24 @@ async fn main() {
         return;
     }
 
-    // Handle --export-rvf mode: build an RVF container package and exit
-    if let Some(ref rvf_path) = args.export_rvf {
-        eprintln!("Exporting RVF container package...");
+    // Handle --export-rvf: writes a CONTAINER-FORMAT DEMO with placeholder
+    // weights — it is NOT a trained model. Only short-circuit when standalone:
+    // combined with --train/--pretrain the real model is exported by the
+    // training pipeline, and short-circuiting here would silently skip training
+    // and write placeholder weights (#894 — the documented `--train …
+    // --export-rvf` workflow produced a placeholder and never trained).
+    if export_emits_placeholder_demo(args.export_rvf.is_some(), args.train, args.pretrain) {
+        let rvf_path = args
+            .export_rvf
+            .as_ref()
+            .expect("export_emits_placeholder_demo implies export_rvf is set");
+        eprintln!(
+            "WARNING: --export-rvf writes a CONTAINER-FORMAT DEMO with placeholder \
+             weights — it is NOT a trained model. Train one with \
+             `--train --dataset <DIR>` (which exports a calibrated .rvf to the \
+             models/ directory), or download a pretrained encoder. See issue #894."
+        );
+        eprintln!("Exporting RVF container package (placeholder weights)...");
         use rvf_pipeline::RvfModelBuilder;
 
         let mut builder = RvfModelBuilder::new("wifi-densepose", "1.0.0");
@@ -5570,6 +5958,13 @@ async fn main() {
             }
         }
         return;
+    } else if args.export_rvf.is_some() {
+        // --export-rvf alongside --train/--pretrain: don't emit a placeholder.
+        // Fall through so training runs; it exports the real calibrated model.
+        eprintln!(
+            "Note: --export-rvf is ignored in training mode — the trained model \
+             is exported by the training pipeline to the models/ directory."
+        );
     }
 
     // Handle --pretrain mode: self-supervised contrastive pretraining (ADR-024)
@@ -6026,7 +6421,17 @@ async fn main() {
     info!("  UI path:   {}", args.ui_path.display());
     info!("  Source:    {}", args.source);
 
-    // Auto-detect data source
+    // Auto-detect data source.
+    //
+    // Issue #937 / sibling fix: previously `auto` silently fell back to the
+    // synthetic data source when no ESP32 or Windows WiFi was reachable, with
+    // only an `info!` log line as the signal. Downstream API consumers
+    // (`/api/v1/sensing/latest`, `/ws/sensing`) had no in-band way to know they
+    // were being served fake CSI tagged as production telemetry. That is the
+    // exact "where's the real data?" pattern external reviewers (#943, #934)
+    // cited as the most damaging evidence of the project misrepresenting its
+    // posture. Synthetic-data is now opt-in only — operators who want demo
+    // mode must explicitly set `--source simulated` or `CSI_SOURCE=simulated`.
     let source = match args.source.as_str() {
         "auto" => {
             info!("Auto-detecting data source...");
@@ -6037,10 +6442,23 @@ async fn main() {
                 info!("  Windows WiFi detected");
                 "wifi"
             } else {
-                info!("  No hardware detected, using simulation");
-                "simulate"
+                error!(
+                    "No real CSI source detected. Auto-detection refuses to silently \
+                     fall back to synthetic data because that would expose downstream \
+                     consumers (/api/v1/sensing/latest, /ws/sensing) to fake telemetry \
+                     tagged as production. To run with synthetic data, set the source \
+                     explicitly: --source simulated (or CSI_SOURCE=simulated in Docker). \
+                     To use real hardware: provision an ESP32 to emit CSI on UDP :{} or \
+                     install the Windows WiFi capture driver. See \
+                     https://github.com/ruvnet/RuView/issues/937 for context.",
+                    args.udp_port
+                );
+                std::process::exit(78); // EX_CONFIG
             }
         }
+        // "simulate" is a synonym for "simulated" (back-compat alias kept so
+        // existing operators who already opted in don't get broken by this fix).
+        "simulate" => "simulated",
         other => other,
     };
 
@@ -6113,7 +6531,9 @@ async fn main() {
                         model_loaded = true;
                         progressive_loader = Some(loader);
                     }
-                    Err(e) => error!("Progressive loader init failed: {e}"),
+                    Err(e) => {
+                        error!("{}", diagnose_model_load_error(mp, &data, &e.to_string()))
+                    }
                 },
                 Err(e) => error!("Failed to read model file: {e}"),
             }
@@ -6200,37 +6620,14 @@ async fn main() {
                             let Ok(v) = serde_json::from_str::<serde_json::Value>(&json) else {
                                 continue;
                             };
-                            let cls = &v["classification"];
-                            let vit = &v["vital_signs"];
-                            let presence = cls["presence"].as_bool().unwrap_or(false);
-                            let n_persons = v["persons"]
-                                .as_array()
-                                .map(|a| a.len() as u32)
-                                .or_else(|| v["estimated_persons"].as_u64().map(|x| x as u32))
-                                .unwrap_or(0);
-                            let motion = match cls["motion_level"].as_str() {
-                                Some("none") | Some("still") | Some("idle") | Some("") => 0.0,
-                                Some(_) => 1.0,
-                                None => 0.0,
-                            };
-                            let snap = mqtt::state::VitalsSnapshot {
-                                node_id: node_id.clone(),
-                                timestamp_ms: (v["timestamp"].as_f64().unwrap_or(0.0) * 1000.0) as i64,
-                                presence,
-                                motion,
-                                presence_score: if presence {
-                                    cls["confidence"].as_f64().unwrap_or(1.0)
-                                } else {
-                                    0.0
-                                },
-                                breathing_rate_bpm: vit["breathing_rate_bpm"].as_f64(),
-                                heartrate_bpm: vit["heart_rate_bpm"].as_f64(),
-                                n_persons,
-                                rssi_dbm: v["nodes"][0]["rssi_dbm"].as_f64(),
-                                vital_confidence: cls["confidence"].as_f64().unwrap_or(0.0),
-                                ..Default::default()
-                            };
-                            let _ = vtx.send(snap);
+                            // #898/#872: emit one snapshot per physical node so
+                            // each surfaces as its own Home-Assistant device with
+                            // its *own* presence/motion/RSSI (see
+                            // vitals_snapshots_from_sensing_json). Falls back to a
+                            // single aggregate snapshot for per-node-less sources.
+                            for snap in vitals_snapshots_from_sensing_json(&v, &node_id) {
+                                let _ = vtx.send(snap);
+                            }
                         }
                     });
                     tracing::info!("MQTT publisher started -> {host}:{port}");
@@ -7048,3 +7445,169 @@ mod rolling_p95_tests {
         assert_eq!(p.len(), 1);
     }
 }
+
+#[cfg(all(test, feature = "mqtt"))]
+mod mqtt_bridge_tests {
+    use super::vitals_snapshots_from_sensing_json;
+    use serde_json::json;
+
+    /// Regression for the per-node presence bug (#872/#898): each node must
+    /// surface its OWN classification, not the room-level aggregate. Node 1 is
+    /// present+moving; node 2 is absent — node 2 must NOT inherit node 1's
+    /// "present".
+    #[test]
+    fn per_node_presence_uses_each_nodes_own_classification() {
+        let v = json!({
+            "timestamp": 1.0,
+            "classification": { "presence": true, "motion_level": "walking", "confidence": 0.9 },
+            "vital_signs": { "breathing_rate_bpm": 14.0, "heart_rate_bpm": 60.0 },
+            "persons": [{}, {}],
+            "nodes": [
+                { "node_id": 1, "rssi_dbm": -40.0,
+                  "classification": { "presence": true, "motion_level": "walking", "confidence": 0.8 } },
+                { "node_id": 2, "rssi_dbm": -70.0,
+                  "classification": { "presence": false, "motion_level": "absent", "confidence": 0.1 } }
+            ]
+        });
+        let snaps = vitals_snapshots_from_sensing_json(&v, "ruview");
+        assert_eq!(snaps.len(), 2, "one snapshot per node");
+
+        let n1 = snaps.iter().find(|s| s.node_id == "ruview-node1").unwrap();
+        let n2 = snaps.iter().find(|s| s.node_id == "ruview-node2").unwrap();
+
+        assert!(n1.presence && n1.motion > 0.0, "node1 present + moving");
+        assert!(
+            !n2.presence && n2.motion == 0.0,
+            "node2 must be absent — not inherit the room aggregate"
+        );
+        // Per-node RSSI preserved.
+        assert_eq!(n1.rssi_dbm, Some(-40.0));
+        assert_eq!(n2.rssi_dbm, Some(-70.0));
+        // Vitals + person count are room-level, shared across node devices.
+        assert_eq!(n1.n_persons, 2);
+        assert_eq!(n2.n_persons, 2);
+        assert_eq!(n1.breathing_rate_bpm, Some(14.0));
+        assert_eq!(n2.heartrate_bpm, Some(60.0));
+        // presence_score is gated on presence.
+        assert!(n1.presence_score > 0.0);
+        assert_eq!(n2.presence_score, 0.0);
+    }
+
+    /// A node that omits a classification field defers to the room aggregate
+    /// rather than silently reading false/0.
+    #[test]
+    fn per_node_missing_fields_fall_back_to_aggregate() {
+        let v = json!({
+            "timestamp": 1.0,
+            "classification": { "presence": true, "motion_level": "still", "confidence": 0.7 },
+            "vital_signs": {},
+            "nodes": [ { "node_id": 3, "rssi_dbm": -55.0 } ]  // no per-node classification
+        });
+        let snaps = vitals_snapshots_from_sensing_json(&v, "n");
+        assert_eq!(snaps.len(), 1);
+        assert_eq!(snaps[0].node_id, "n-node3");
+        assert!(snaps[0].presence, "defers to aggregate presence");
+        assert_eq!(snaps[0].motion, 0.0, "aggregate 'still' => no motion");
+    }
+
+    /// No `nodes` array (wifi / simulate sources): single aggregate snapshot
+    /// keyed by the base id.
+    #[test]
+    fn falls_back_to_single_aggregate_when_no_nodes() {
+        let v = json!({
+            "timestamp": 2.0,
+            "classification": { "presence": true, "motion_level": "idle", "confidence": 0.6 },
+            "vital_signs": { "breathing_rate_bpm": 12.0 },
+            "persons": [{}]
+        });
+        let snaps = vitals_snapshots_from_sensing_json(&v, "ruview");
+        assert_eq!(snaps.len(), 1);
+        assert_eq!(snaps[0].node_id, "ruview");
+        assert!(snaps[0].presence);
+        assert_eq!(snaps[0].motion, 0.0, "idle => no motion");
+        assert_eq!(snaps[0].n_persons, 1);
+    }
+
+    /// `motion_level: "absent"` must map to zero motion (the old aggregate
+    /// match fell through to `Some(_) => 1.0`, treating absent as full motion).
+    #[test]
+    fn absent_motion_level_is_zero_motion() {
+        let v = json!({
+            "timestamp": 0.0,
+            "classification": { "presence": false, "motion_level": "absent", "confidence": 0.0 },
+            "vital_signs": {}
+        });
+        let snaps = vitals_snapshots_from_sensing_json(&v, "x");
+        assert_eq!(snaps[0].motion, 0.0);
+        assert!(!snaps[0].presence);
+    }
+}
+
+#[cfg(test)]
+mod model_load_diagnostic_tests {
+    use super::diagnose_model_load_error;
+    use std::path::Path;
+
+    #[test]
+    fn safetensors_is_named_and_points_at_894() {
+        // 8-byte LE header length then '{' — the safetensors signature.
+        let data = [0x10, 0, 0, 0, 0, 0, 0, 0, b'{', b'"'];
+        let msg = diagnose_model_load_error(
+            Path::new("models/wifi-densepose-pretrained/model.safetensors"),
+            &data,
+            "invalid magic at offset 0",
+        );
+        assert!(msg.contains("safetensors"), "{msg}");
+        assert!(msg.contains("#894"), "{msg}");
+        assert!(msg.contains("signal heuristics"), "{msg}");
+    }
+
+    #[test]
+    fn quantized_bin_is_identified() {
+        let data = [0x35, 0x57, 0x45, 0x77]; // the 0x77455735 the loader reports
+        let msg = diagnose_model_load_error(Path::new("model-q4.bin"), &data, "bad magic");
+        assert!(msg.contains("quantized weight blob"), "{msg}");
+        assert!(msg.contains("RVFS") || msg.contains("0x52564653"), "{msg}");
+    }
+
+    #[test]
+    fn jsonl_manifest_is_identified() {
+        let data = *b"{\"seg\":0}";
+        let msg = diagnose_model_load_error(Path::new("model.rvf.jsonl"), &data, "x");
+        assert!(msg.contains("JSONL manifest"), "{msg}");
+    }
+
+    #[test]
+    fn unknown_format_still_gives_guidance() {
+        let data = [0u8, 1, 2, 3];
+        let msg = diagnose_model_load_error(Path::new("weird.dat"), &data, "x");
+        assert!(msg.contains("RVF binary container"), "{msg}");
+        assert!(msg.contains("wifi-densepose-train"), "{msg}");
+    }
+}
+
+#[cfg(test)]
+mod export_rvf_mode_tests {
+    use super::export_emits_placeholder_demo;
+
+    #[test]
+    fn standalone_export_emits_placeholder() {
+        // --export-rvf alone → the container-format demo (placeholder weights).
+        assert!(export_emits_placeholder_demo(true, false, false));
+    }
+
+    #[test]
+    fn export_with_train_does_not_short_circuit() {
+        // #894: `--train --export-rvf` must NOT emit a placeholder + skip
+        // training — it must fall through to the real training pipeline.
+        assert!(!export_emits_placeholder_demo(true, true, false));
+        assert!(!export_emits_placeholder_demo(true, false, true));
+        assert!(!export_emits_placeholder_demo(true, true, true));
+    }
+
+    #[test]
+    fn no_export_flag_never_emits() {
+        assert!(!export_emits_placeholder_demo(false, false, false));
+        assert!(!export_emits_placeholder_demo(false, true, false));
+    }
+}

v2/crates/wifi-densepose-sensing-server/src/mqtt/publisher.rs

@@ -117,6 +117,23 @@ impl OwnedDiscoveryBuilder {
             via_device: self.via_device.as_deref(),
         }
     }
+
+    /// Derive a per-node builder from this base (issue #898). Each physical
+    /// RuView node must surface as its own Home-Assistant device — the base
+    /// builder's `node_id` (the MQTT client id) is replaced with the actual
+    /// node id, giving a distinct `wifi_densepose_<node>` device identifier
+    /// and a per-node friendly name, instead of collapsing every node into a
+    /// single hard-coded device.
+    pub fn for_node(&self, node_id: &str) -> OwnedDiscoveryBuilder {
+        OwnedDiscoveryBuilder {
+            discovery_prefix: self.discovery_prefix.clone(),
+            node_id: node_id.to_string(),
+            node_friendly_name: Some(format!("RuView node {node_id}")),
+            sw_version: self.sw_version.clone(),
+            model: self.model.clone(),
+            via_device: self.via_device.clone(),
+        }
+    }
 }
 
 /// Core run loop. Pumps the broadcast channel + the MQTT event loop in
@@ -129,20 +146,19 @@ async fn run(
     let opts = build_mqtt_options(&cfg);
     let (client, mut eventloop): (AsyncClient, EventLoop) = AsyncClient::new(opts, 256);
 
-    let builder_borrowed = builder_owned.as_borrowed();
     let entities = DiscoveryBuilder::enabled_entities(
         cfg.privacy_mode,
         cfg.publish_pose,
         &[], // no_semantic — wire from cli::Args in P3.5
     );
 
-    if let Err(e) = publish_all_discovery(&client, &builder_borrowed, &entities).await {
-        warn!("[mqtt] initial discovery publish failed: {e}");
-    }
-    let avail = NodeAvailability::for_builder(&builder_borrowed, &entities);
-    if let Err(e) = publish_availability(&client, &avail, "online").await {
-        warn!("[mqtt] initial availability publish failed: {e}");
-    }
+    // #898: one Home-Assistant device per node. Discovery + availability are
+    // published lazily the first time a snapshot for a given node_id arrives;
+    // each node's builder + availability are retained here for heartbeats and
+    // the offline LWT. (Previously a single hard-coded builder collapsed every
+    // node into one device.)
+    let mut nodes: std::collections::HashMap<String, (OwnedDiscoveryBuilder, NodeAvailability)> =
+        std::collections::HashMap::new();
 
     let mut rate_limiter = RateLimiter::new();
     let mut last_heartbeat = Instant::now();
@@ -179,14 +195,20 @@ async fn run(
             // Periodic heartbeat / discovery refresh.
             _ = tokio::time::sleep(Duration::from_secs(1)) => {
                 if last_heartbeat.elapsed() >= AVAILABILITY_HEARTBEAT {
-                    if let Err(e) = publish_availability(&client, &avail, "online").await {
-                        warn!("[mqtt] heartbeat publish failed: {e}");
+                    for (_, na) in nodes.values() {
+                        if let Err(e) = publish_availability(&client, na, "online").await {
+                            warn!("[mqtt] heartbeat publish failed: {e}");
+                        }
                     }
                     last_heartbeat = Instant::now();
                 }
                 if last_refresh.elapsed() >= Duration::from_secs(cfg.refresh_secs) {
-                    if let Err(e) = publish_all_discovery(&client, &builder_borrowed, &entities).await {
-                        warn!("[mqtt] discovery refresh failed: {e}");
+                    for (nb, _) in nodes.values() {
+                        if let Err(e) =
+                            publish_all_discovery(&client, &nb.as_borrowed(), &entities).await
+                        {
+                            warn!("[mqtt] discovery refresh failed: {e}");
+                        }
                     }
                     last_refresh = Instant::now();
                 }
@@ -197,18 +219,39 @@ async fn run(
                 match recv {
                     Ok(snap) => {
                         let elapsed = start_instant.elapsed();
-                        publish_snapshot(&client, &builder_borrowed, &snap, &cfg, &mut rate_limiter, elapsed).await;
+                        // #898: on first sight of a node_id, publish that
+                        // node's discovery + availability; then route its
+                        // state to per-node topics.
+                        if !nodes.contains_key(&snap.node_id) {
+                            let nb = builder_owned.for_node(&snap.node_id);
+                            let borrowed = nb.as_borrowed();
+                            if let Err(e) =
+                                publish_all_discovery(&client, &borrowed, &entities).await
+                            {
+                                warn!("[mqtt] node {} discovery failed: {e}", snap.node_id);
+                            }
+                            let na = NodeAvailability::for_builder(&borrowed, &entities);
+                            if let Err(e) = publish_availability(&client, &na, "online").await {
+                                warn!("[mqtt] node {} availability failed: {e}", snap.node_id);
+                            }
+                            nodes.insert(snap.node_id.clone(), (nb, na));
+                        }
+                        let borrowed = nodes[&snap.node_id].0.as_borrowed();
+                        publish_snapshot(&client, &borrowed, &snap, &cfg, &mut rate_limiter, elapsed).await;
                     }
                     Err(broadcast::error::RecvError::Lagged(n)) => {
                         warn!("[mqtt] lagged behind broadcast by {n} messages — dropped");
                     }
                     Err(broadcast::error::RecvError::Closed) => {
                         info!("[mqtt] broadcast channel closed, draining");
-                        // Publish offline before exit.
-                        let _ = publish_availability(&client, &avail, "offline").await;
+                        // Publish offline for every known node before exit.
+                        for (_, na) in nodes.values() {
+                            let _ = publish_availability(&client, na, "offline").await;
+                        }
                         let _ = client.disconnect().await;
                         return;
                     }
+
                 }
             }
         }
@@ -296,3 +339,52 @@ async fn publish_state(client: &AsyncClient, m: &StateMessage) -> Result<(), Cli
     };
     client.publish(&m.topic, qos, m.retain, m.payload.clone()).await
 }
+
+#[cfg(test)]
+mod per_node_device_tests {
+    //! Issue #898 — each physical node must surface as its own Home-Assistant
+    //! device, not collapse into one hard-coded device.
+    use super::*;
+
+    fn base() -> OwnedDiscoveryBuilder {
+        OwnedDiscoveryBuilder {
+            discovery_prefix: "homeassistant".into(),
+            node_id: "wifi-densepose-1".into(),
+            node_friendly_name: Some("RuView".into()),
+            sw_version: "0.0.0".into(),
+            model: "test".into(),
+            via_device: None,
+        }
+    }
+
+    fn device_identifiers(b: &OwnedDiscoveryBuilder) -> Vec<String> {
+        b.as_borrowed().build(EntityKind::Presence).device.identifiers
+    }
+
+    #[test]
+    fn for_node_overrides_node_id_and_friendly_name() {
+        let n = base().for_node("node-A");
+        assert_eq!(n.node_id, "node-A");
+        assert_eq!(n.node_friendly_name.as_deref(), Some("RuView node node-A"));
+    }
+
+    #[test]
+    fn distinct_nodes_yield_distinct_ha_device_identifiers() {
+        let b = base();
+        let a = device_identifiers(&b.for_node("node-A"));
+        let c = device_identifiers(&b.for_node("node-B"));
+        assert_eq!(a, vec!["wifi_densepose_node-A".to_string()]);
+        assert_eq!(c, vec!["wifi_densepose_node-B".to_string()]);
+        assert_ne!(a, c, "#898: two nodes must not collapse into one device");
+    }
+
+    #[test]
+    fn single_node_keeps_a_stable_identity() {
+        // Two snapshots from the same node map to the same device.
+        let b = base();
+        assert_eq!(
+            device_identifiers(&b.for_node("node-7")),
+            device_identifiers(&b.for_node("node-7"))
+        );
+    }
+}

v2/crates/wifi-densepose-sensing-server/tests/mqtt_integration.rs

@@ -171,12 +171,28 @@ async fn discovery_topics_appear_on_broker() {
     // Spawn the publisher.
     let cfg = make_cfg(port, false, "discovery");
     let builder = make_builder("inttest1");
-    let (_tx, rx) = broadcast::channel::<VitalsSnapshot>(32);
+    let (tx, rx) = broadcast::channel::<VitalsSnapshot>(32);
     let _handle = spawn(cfg, builder, rx);
 
+    // #898: discovery is now published per-node the first time a snapshot for
+    // that node_id arrives (not eagerly at startup). Drive snapshots for
+    // "inttest1" throughout the window so its device's discovery lands — same
+    // pattern as state_messages_published_on_snapshot_broadcast.
+    let tx_bg = tx.clone();
+    let drive = tokio::spawn(async move {
+        for _ in 0..60 {
+            let _ = tx_bg.send(VitalsSnapshot {
+                node_id: "inttest1".into(),
+                ..Default::default()
+            });
+            tokio::time::sleep(Duration::from_millis(200)).await;
+        }
+    });
+
     // Drain the subscriber for up to 6 s — enough for initial discovery
     // + first availability publication.
     let msgs = collect_published(&mut sub_loop, Duration::from_secs(6)).await;
+    drive.abort();
     let _ = sub.disconnect().await;
 
     // Assertions: at least the presence + heart_rate + fall discovery
@@ -221,10 +237,23 @@ async fn privacy_mode_suppresses_biometric_discovery() {
 
     let cfg = make_cfg(port, /* privacy_mode = */ true, "privacy");
     let builder = make_builder("inttest2");
-    let (_tx, rx) = broadcast::channel::<VitalsSnapshot>(32);
+    let (tx, rx) = broadcast::channel::<VitalsSnapshot>(32);
     let _handle = spawn(cfg, builder, rx);
 
+    // #898: per-node discovery is triggered by a snapshot for that node_id.
+    let tx_bg = tx.clone();
+    let drive = tokio::spawn(async move {
+        for _ in 0..60 {
+            let _ = tx_bg.send(VitalsSnapshot {
+                node_id: "inttest2".into(),
+                ..Default::default()
+            });
+            tokio::time::sleep(Duration::from_millis(200)).await;
+        }
+    });
+
     let msgs = collect_published(&mut sub_loop, Duration::from_secs(6)).await;
+    drive.abort();
     let _ = sub.disconnect().await;
 
     let topics: Vec<&str> = msgs.iter().map(|(t, _, _)| t.as_str()).collect();

v2/crates/wifi-densepose-signal/src/ruvsense/field_model.rs

@@ -276,6 +276,13 @@ pub struct FieldNormalMode {
     pub geometry_hash: u64,
     /// Baseline eigenvalue count above Marcenko-Pastur threshold (empty-room).
     pub baseline_eigenvalue_count: usize,
+    /// Baseline noise variance estimate (median of bottom-half positive
+    /// eigenvalues from the calibration covariance). Persisted so that
+    /// `estimate_occupancy` can anchor its Marcenko-Pastur threshold to the
+    /// calibration noise floor instead of letting it drift with the
+    /// per-window sample size. Defaults to 0.0 in the diagonal-fallback path.
+    /// Issue #942.
+    pub baseline_noise_var: f64,
 }
 
 /// Body perturbation extracted from a CSI observation.
@@ -504,7 +511,11 @@ impl FieldModel {
         let baseline: Vec<Vec<f64>> = self.link_stats.iter().map(|ls| ls.mean_vector()).collect();
 
         // --- True eigenvalue decomposition (with diagonal fallback) ---
-        let (mode_energies, environmental_modes, baseline_eig_count) =
+        // Returns: (energies, modes, baseline_count, baseline_noise_var).
+        // The noise_var slot is 0.0 in the diagonal-fallback paths; the
+        // estimation hot path treats 0.0 as "no anchored noise floor" and
+        // falls back to per-window noise_var, preserving pre-#942 behavior.
+        let (mode_energies, environmental_modes, baseline_eig_count, baseline_noise_var) =
             if let Some(ref cov_sum) = self.covariance_sum {
                 if self.covariance_count > 1 {
                     // Compute sample covariance from raw outer products:
@@ -588,23 +599,28 @@ impl FieldModel {
                             let baseline_count =
                                 eigenvalues.iter().filter(|&&ev| ev > mp_threshold).count();
 
-                            (energies, modes, baseline_count)
+                            (energies, modes, baseline_count, noise_var)
                         }
                         Err(_) => {
                             // Fallback to diagonal approximation on SVD failure
-                            diagonal_fallback(&self.link_stats, n_sc, n_modes)
+                            let (e, m, b) =
+                                diagonal_fallback(&self.link_stats, n_sc, n_modes);
+                            (e, m, b, 0.0_f64)
                         }
                     }
                     // When eigenvalue feature is disabled, use diagonal fallback
                     #[cfg(not(feature = "eigenvalue"))]
                     {
-                        diagonal_fallback(&self.link_stats, n_sc, n_modes)
+                        let (e, m, b) = diagonal_fallback(&self.link_stats, n_sc, n_modes);
+                        (e, m, b, 0.0_f64)
                     }
                 } else {
-                    diagonal_fallback(&self.link_stats, n_sc, n_modes)
+                    let (e, m, b) = diagonal_fallback(&self.link_stats, n_sc, n_modes);
+                    (e, m, b, 0.0_f64)
                 }
             } else {
-                diagonal_fallback(&self.link_stats, n_sc, n_modes)
+                let (e, m, b) = diagonal_fallback(&self.link_stats, n_sc, n_modes);
+                (e, m, b, 0.0_f64)
             };
 
         // Compute variance explained using the same centered covariance as modes.
@@ -648,6 +664,7 @@ impl FieldModel {
             calibrated_at_us: timestamp_us,
             geometry_hash,
             baseline_eigenvalue_count: baseline_eig_count,
+            baseline_noise_var,
         };
 
         self.modes = Some(field_mode);
@@ -794,7 +811,7 @@ impl FieldModel {
         // Marcenko-Pastur noise estimate: median of POSITIVE eigenvalues
         // in the bottom half. Excludes zeros from rank-deficient matrices
         // (common when n_subcarriers > n_frames, e.g. 56 subcarriers / 50 frames).
-        let noise_var = {
+        let local_noise_var = {
             let mut positive: Vec<f64> =
                 eigenvalues.iter().copied().filter(|&e| e > 1e-10).collect();
             positive.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal));
@@ -807,6 +824,22 @@ impl FieldModel {
                 return Ok(0); // All zero eigenvalues — can't estimate
             }
         };
+
+        // Issue #942: anchor the noise floor to the calibration's noise_var
+        // when it's available. Per-window noise_var drifts with sample size —
+        // a short estimation window can produce a small local_noise_var that
+        // inflates `significant` and breaks the test_estimate_occupancy_noise_only
+        // invariant. The max of (calibration noise, local noise) keeps the
+        // threshold from collapsing on small windows while still letting the
+        // per-window noise dominate when it's the larger estimate. Falls back
+        // to local_noise_var when baseline_noise_var == 0 (diagonal-fallback
+        // calibration path, or pre-#942 stored modes).
+        let noise_var = if modes.baseline_noise_var > 0.0 {
+            local_noise_var.max(modes.baseline_noise_var)
+        } else {
+            local_noise_var
+        };
+
         let ratio = n as f64 / count as f64;
         let mp_threshold = noise_var * (1.0 + ratio.sqrt()).powi(2);