chore: version-bump and republish 10 of 12 documented crates to crates.io (#1439 )

Published: wifi-densepose-core 0.3.2, -vitals 0.3.2, -wifiscan 0.3.2, -hardware 0.3.2, -signal 0.3.6, -nn 0.3.2, -ruvector 0.3.3, -train 0.3.3, -mat 0.3.2, -wasm 0.3.1. Not published (blocked, needs a decision): wifi-densepose-sensing-server and wifi-densepose-cli both path-depend on ruview-auth, which is publish = false. Version bumps reserved (0.3.5, 0.3.2) but not published.
feat(ruview-unified): Unified RF spatial world model — ADR-273..282 (#1437 )
2026-10-19 13:20:07 -05:00 · 2026-07-26 15:44:24 -07:00 · 2026-07-26 14:37:56 -07:00 · 2026-07-24 09:10:52 -07:00 · 2026-07-24 08:57:36 -07:00 · 2026-07-24 16:01:06 +02:00
1002 changed files with 112394 additions and 44088 deletions
@@ -33,6 +33,8 @@ jobs:
        working-directory: v2
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Install Rust toolchain
        run: rustup show && rustc --version
@@ -0,0 +1,199 @@
+name: Bench Regression Guard
+
+# Sub-deliverable 8.3 of the benchmark/optimization milestone.
+#
+# HONEST SCOPE (read this before assuming this gates on timing):
+#   * The `bench-compile` job is a REAL, HARD-FAILING regression gate. It runs
+#     `cargo bench --no-default-features --no-run`, which type-checks and links
+#     EVERY criterion bench in the v2/ workspace without running a single
+#     measurement. Benches are not part of `cargo test`, so they silently
+#     bit-rot when a public API they call changes — this job catches that the
+#     moment it happens. This is the part of this workflow that can fail a PR.
+#
+#   * The `bench-fast-run` job runs a small, curated subset of pure-CPU benches
+#     in criterion "quick mode" (short warm-up / measurement / 10 samples) and
+#     is INFORMATIONAL ONLY (`continue-on-error: true`). It does NOT gate on
+#     timing. Wall-clock timings on shared GitHub-hosted runners vary by
+#     2-3x run-to-run (noisy neighbours, CPU throttling, no pinned frequency),
+#     so a hard ">X ms" threshold here would flake constantly and teach
+#     everyone to ignore it. We deliberately do not pretend to do timing
+#     regression-gating we cannot deliver reliably. The numbers are surfaced in
+#     the job log + uploaded as an artifact for humans to eyeball trends.
+#
+# WHY NO criterion --baseline COMPARE GATE:
+#   criterion's `--save-baseline` / `--baseline` compare is the textbook
+#   regression mechanism, but it only produces a trustworthy verdict when the
+#   baseline and the candidate were measured on the SAME hardware under the SAME
+#   conditions. GitHub-hosted runners give neither (the baseline commit and the
+#   PR commit land on different physical machines). Committing a baseline JSON
+#   measured on one runner and comparing a different runner against it would
+#   manufacture false regressions. If/when these benches run on a dedicated,
+#   frequency-pinned self-hosted runner, a `--baseline` compare with a generous
+#   (>2x) noise floor becomes honest and can be added then. Until then,
+#   compile-verify + informational-run is the honest gate.
+
+on:
+  push:
+    branches: [ main, develop, 'feat/*' ]
+    paths:
+      - 'v2/crates/**/benches/**'
+      - 'v2/crates/**/Cargo.toml'
+      - 'v2/crates/**/src/**'
+      - 'v2/Cargo.toml'
+      - 'v2/Cargo.lock'
+      - '.github/workflows/bench-regression.yml'
+  pull_request:
+    paths:
+      - 'v2/crates/**/benches/**'
+      - 'v2/crates/**/Cargo.toml'
+      - 'v2/crates/**/src/**'
+      - 'v2/Cargo.toml'
+      - 'v2/Cargo.lock'
+      - '.github/workflows/bench-regression.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  CARGO_TERM_COLOR: always
+  # Debuginfo is useless in CI and the 38-crate workspace target dir otherwise
+  # exhausts the runner disk (mirrors ci.yml's rust-tests job). The bench
+  # profile inherits release + debug = true (v2/Cargo.toml [profile.bench]);
+  # force it off so the link step does not run out of space.
+  CARGO_PROFILE_BENCH_DEBUG: "0"
+  CARGO_PROFILE_RELEASE_DEBUG: "0"
+
+jobs:
+  # ── HARD GATE: every bench must still compile + link ─────────────────────
+  bench-compile:
+    name: bench compile-verify (--no-run)
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout (recursive — wifi-densepose-rufield path-deps vendor/rufield)
+        uses: actions/checkout@v4
+        with:
+          # The workspace includes `wifi-densepose-rufield`, which path-deps the
+          # `vendor/rufield` submodule crates. Without a recursive checkout the
+          # whole workspace fails to resolve before any bench is built.
+          submodules: recursive
+
+      # The workspace pulls in `wifi-densepose-desktop` (Tauri v2) whose -sys
+      # crates need the GTK/WebKit/serial dev libraries via pkg-config, exactly
+      # as ci.yml's rust-tests job documents. A `--workspace` bench build links
+      # the whole graph, so these are required here too.
+      - name: Install Tauri / GTK / serial system dev libraries
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            libglib2.0-dev \
+            libgtk-3-dev \
+            libsoup-3.0-dev \
+            libjavascriptcoregtk-4.1-dev \
+            libwebkit2gtk-4.1-dev \
+            libayatana-appindicator3-dev \
+            librsvg2-dev \
+            libxdo-dev \
+            libudev-dev \
+            libdbus-1-dev \
+            libssl-dev \
+            pkg-config
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache cargo (Swatinem/rust-cache)
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: v2
+          # Distinct cache scope from ci.yml's rust-tests so the bench profile
+          # artifacts (release+opt) do not evict the test profile cache.
+          key: bench-regression
+
+      # The core regression guard. `--no-run` compiles + links every bench
+      # target in the workspace's DEFAULT feature set but runs no measurement,
+      # so it is deterministic and fast-ish (build only). A bench that no longer
+      # compiles — because a type/signature it calls changed and nobody updated
+      # the bench — fails the build here. `--no-default-features` is the
+      # workspace's standard gate flag (openblas/tch/ort/onnx stay opt-out).
+      - name: Compile all workspace benches (default features)
+        working-directory: v2
+        run: cargo bench --workspace --no-default-features --no-run
+
+      # Feature-gated benches are skipped by the default build above because
+      # their `[[bench]]` entries carry `required-features`. Compile the ones we
+      # can guard so they are also covered against bit-rot.
+      #   * cir → wifi-densepose-signal/benches/cir_bench.rs (ADR-134). The
+      #     `cir` feature is pure-Rust (`cir = []`), so it builds on the stock
+      #     runner and is a real, hard-failing guard like the step above.
+      #
+      # NOT guarded here (honest scope):
+      #   * crv → wifi-densepose-ruvector/benches/crv_bench.rs. The `crv` feature
+      #     pulls the crates.io dependency `ruvector-crv 0.1.1`, which currently
+      #     FAILS to compile on stable (E0308 type mismatch in its own
+      #     `stage_iii.rs` — an UPSTREAM bug, unrelated to bench bit-rot).
+      #     Adding a hard `--features crv` compile step would make this workflow
+      #     red for a reason this gate is not meant to police. Re-add this step
+      #     once `ruvector-crv` ships a fixed release. (mqtt/onnx benches are
+      #     likewise left to their own crate workflows.)
+      - name: Compile feature-gated benches (cir)
+        working-directory: v2
+        run: cargo bench -p wifi-densepose-signal --no-default-features --features cir --bench cir_bench --no-run
+
+  # ── INFORMATIONAL: run a curated fast subset (never gates) ───────────────
+  bench-fast-run:
+    name: bench fast-run (informational, non-gating)
+    runs-on: ubuntu-latest
+    # NEVER fail the workflow on this job — timings are noise-prone on shared
+    # runners (see header). It exists to surface trends for humans, not to gate.
+    continue-on-error: true
+    needs: [bench-compile]
+    steps:
+      - name: Checkout (recursive)
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache cargo (Swatinem/rust-cache)
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: v2
+          key: bench-regression
+
+      # Curated subset = pure-CPU, fast, dependency-light criterion benches that
+      # finish in seconds under quick-mode flags. Each is targeted by `--bench`
+      # (NOT a bare `cargo bench -p`) because the crates' lib targets use the
+      # libtest harness, which rejects criterion's CLI flags (--warm-up-time
+      # etc.) and aborts the run. Quick-mode: 1s warm-up, 2s measure, 10 samples.
+      - name: nvsim pipeline_throughput (quick)
+        working-directory: v2
+        run: |
+          mkdir -p ../bench-out
+          cargo bench -p nvsim --no-default-features --bench pipeline_throughput -- \
+            --warm-up-time 1 --measurement-time 2 --sample-size 10 \
+            | tee ../bench-out/nvsim_pipeline_throughput.txt
+
+      - name: ruvector sketch_bench (quick)
+        working-directory: v2
+        run: |
+          cargo bench -p wifi-densepose-ruvector --no-default-features --bench sketch_bench -- \
+            --warm-up-time 1 --measurement-time 2 --sample-size 10 \
+            | tee ../bench-out/ruvector_sketch_bench.txt
+
+      - name: ruvector fusion_bench (quick)
+        working-directory: v2
+        run: |
+          cargo bench -p wifi-densepose-ruvector --no-default-features --bench fusion_bench -- \
+            --warm-up-time 1 --measurement-time 2 --sample-size 10 \
+            | tee ../bench-out/ruvector_fusion_bench.txt
+
+      - name: Upload informational bench logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: bench-fast-run-logs
+          path: bench-out/
+          if-no-files-found: warn
@@ -53,6 +53,8 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Install Rust toolchain
        uses: dtolnay/rust-toolchain@stable
@@ -1,14 +1,10 @@
 name: Continuous Deployment

 on:
-  push:
-    branches: [ main ]
-    tags: [ 'v*' ]
  workflow_run:
-    workflows: ["Continuous Integration"]
+    workflows: ["wifi-densepose sensing-server → Docker Hub + ghcr.io"]
    types:
      - completed
-    branches: [ main ]
  workflow_dispatch:
    inputs:
      environment:
@@ -19,6 +15,11 @@ on:
        options:
        - staging
        - production
+      image_tag:
+        description: 'Existing ghcr.io/ruvnet/wifi-densepose tag to deploy'
+        required: true
+        default: 'latest'
+        type: string
      force_deploy:
        description: 'Force deployment (skip checks)'
        required: false
@@ -27,7 +28,7 @@ on:

 env:
  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
+  IMAGE_NAME: ruvnet/wifi-densepose
  KUBE_CONFIG_DATA: ${{ secrets.KUBE_CONFIG_DATA }}

 jobs:
@@ -35,27 +36,30 @@ jobs:
  pre-deployment:
    name: Pre-deployment Checks
    runs-on: ubuntu-latest
-    if: github.event.workflow_run.conclusion == 'success' || github.event_name == 'workflow_dispatch'
+    if: |
+      (github.event_name == 'workflow_run' && github.event.workflow_run.conclusion == 'success') ||
+      github.event_name == 'workflow_dispatch'
    outputs:
      deploy_env: ${{ steps.determine-env.outputs.environment }}
      image_tag: ${{ steps.determine-tag.outputs.tag }}
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.event.workflow_run.head_sha || github.sha }}
+        submodules: recursive

    - name: Determine deployment environment
      id: determine-env
      env:
        # Use environment variable to prevent shell injection
        GITHUB_EVENT_NAME: ${{ github.event_name }}
-        GITHUB_REF: ${{ github.ref }}
+        PUBLISHED_REF: ${{ github.event.workflow_run.head_branch }}
        GITHUB_INPUT_ENVIRONMENT: ${{ github.event.inputs.environment }}
      run: |
        if [[ "$GITHUB_EVENT_NAME" == "workflow_dispatch" ]]; then
          echo "environment=$GITHUB_INPUT_ENVIRONMENT" >> $GITHUB_OUTPUT
-        elif [[ "$GITHUB_REF" == "refs/heads/main" ]]; then
-          echo "environment=staging" >> $GITHUB_OUTPUT
-        elif [[ "$GITHUB_REF" == refs/tags/v* ]]; then
+        elif [[ "$PUBLISHED_REF" == v* ]]; then
          echo "environment=production" >> $GITHUB_OUTPUT
        else
          echo "environment=staging" >> $GITHUB_OUTPUT
@@ -63,16 +67,23 @@ jobs:

    - name: Determine image tag
      id: determine-tag
+      env:
+        GITHUB_EVENT_NAME: ${{ github.event_name }}
+        PUBLISHED_REF: ${{ github.event.workflow_run.head_branch }}
+        PUBLISHED_SHA: ${{ github.event.workflow_run.head_sha }}
+        INPUT_IMAGE_TAG: ${{ github.event.inputs.image_tag }}
      run: |
-        if [[ "${{ github.ref }}" == refs/tags/v* ]]; then
-          echo "tag=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+        if [[ "$GITHUB_EVENT_NAME" == "workflow_dispatch" ]]; then
+          echo "tag=$INPUT_IMAGE_TAG" >> $GITHUB_OUTPUT
+        elif [[ "$PUBLISHED_REF" == v* ]]; then
+          echo "tag=$PUBLISHED_REF" >> $GITHUB_OUTPUT
        else
-          echo "tag=${{ github.sha }}" >> $GITHUB_OUTPUT
+          echo "tag=sha-${PUBLISHED_SHA:0:7}" >> $GITHUB_OUTPUT
        fi

    - name: Verify image exists
      run: |
-        docker manifest inspect ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.determine-tag.outputs.tag }}
+        docker manifest inspect "${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.determine-tag.outputs.tag }}"

  # Deploy to staging
  deploy-staging:
@@ -86,6 +97,8 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up kubectl
      uses: azure/setup-kubectl@v3
@@ -125,13 +138,18 @@ jobs:
    name: Deploy to Production
    runs-on: ubuntu-latest
    needs: [pre-deployment, deploy-staging]
-    if: needs.pre-deployment.outputs.deploy_env == 'production' || (github.ref == 'refs/tags/v*' && needs.deploy-staging.result == 'success')
+    if: |
+      always() &&
+      needs.pre-deployment.result == 'success' &&
+      needs.pre-deployment.outputs.deploy_env == 'production'
    environment:
      name: production
      url: https://wifi-densepose.com
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up kubectl
      uses: azure/setup-kubectl@v3
@@ -204,7 +222,7 @@ jobs:
        # kubectl scale rs -n wifi-densepose -l app=wifi-densepose,version!=green --replicas=0

    - name: Upload deployment artifacts
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
      with:
        name: production-deployment-${{ github.run_number }}
        path: |
@@ -254,7 +272,7 @@ jobs:
  post-deployment:
    name: Post-deployment Monitoring
    runs-on: ubuntu-latest
-    needs: [deploy-staging, deploy-production]
+    needs: [pre-deployment, deploy-staging, deploy-production]
    if: always() && (needs.deploy-staging.result == 'success' || needs.deploy-production.result == 'success')
    steps:
    - name: Monitor deployment health
@@ -275,7 +293,7 @@ jobs:
        done

    - name: Update deployment status
-      uses: actions/github-script@v6
+      uses: actions/github-script@v7
      with:
        script: |
          const deployEnv = '${{ needs.pre-deployment.outputs.deploy_env }}';
@@ -294,7 +312,7 @@ jobs:
  notify:
    name: Notify Deployment Status
    runs-on: ubuntu-latest
-    needs: [deploy-staging, deploy-production, post-deployment]
+    needs: [pre-deployment, deploy-staging, deploy-production, post-deployment]
    if: always()
    steps:
    - name: Notify Slack on success
@@ -326,7 +344,7 @@ jobs:

    - name: Create deployment issue on failure
      if: needs.deploy-production.result == 'failure'
-      uses: actions/github-script@v6
+      uses: actions/github-script@v7
      with:
        script: |
          github.rest.issues.create({
@@ -349,4 +367,4 @@ jobs:
            **Logs:** Check the workflow run for detailed error messages.
            `,
            labels: ['deployment', 'production', 'urgent']
-          })
+          })
@@ -9,7 +9,7 @@ on:

 env:
  PYTHON_VERSION: '3.11'
-  NODE_VERSION: '18'
+  NODE_VERSION: '20' # ADR-265: all Node packages in this repo declare engines >= 20
  REGISTRY: ghcr.io
  IMAGE_NAME: ${{ github.repository }}

@@ -29,6 +29,7 @@ jobs:
      continue-on-error: true
      uses: actions/checkout@v4
      with:
+        submodules: recursive
        fetch-depth: 0

    - name: Set up Python
@@ -82,6 +83,11 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+      # ADR-262 P1: `wifi-densepose-rufield` path-deps the `vendor/rufield`
+      # submodule. Without a recursive checkout the workspace build fails to
+      # resolve those path deps in CI even though it passes locally.

    # `wifi-densepose-desktop` is a Tauri v2 app — `glib-sys`, `gtk-sys`,
    # `webkit2gtk-sys`, etc. need the Linux dev libraries via pkg-config or the
@@ -108,24 +114,40 @@ 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

+    # The 38-crate workspace debug build exhausts the runner's disk when built
+    # with full debuginfo (observed: "final link failed: No space left on
+    # device" once the engine/benchmark crates landed; the same tree's local
+    # debug target measured 151 GB). Debuginfo is useless in CI — tests either
+    # pass or print their failure — so build without it; target shrinks ~5-10x.
    - name: Run Rust tests
      working-directory: v2
+      env:
+        CARGO_PROFILE_DEV_DEBUG: "0"
+        CARGO_PROFILE_TEST_DEBUG: "0"
      run: cargo test --workspace --no-default-features

    - name: Run ADR-147 worldmodel tests
      working-directory: v2
-      run: cargo test -p wifi-densepose-worldmodel --no-default-features
+      env:
+        CARGO_PROFILE_DEV_DEBUG: "0"
+        CARGO_PROFILE_TEST_DEBUG: "0"
+      run: >-
+        cargo test
+        --manifest-path crates/worldgraph/wifi-densepose-worldmodel/Cargo.toml
+        --no-default-features

    # ADR-134 CIR tests are behind the `cir` feature so the bench dependency
    # (Criterion) only pulls when actually exercised. Run them as a separate
@@ -149,6 +171,41 @@ jobs:
    - name: ADR-135 calibration witness proof (determinism guard)
      run: bash scripts/verify-calibration-proof.sh

+    # The workspace runs with --no-default-features, which switches OFF
+    # ruview-auth's `login` and `pkce` features. That silently excluded 40 of
+    # its 87 tests — the whole interactive sign-in path: credential storage,
+    # single-flight refresh, the advisory file lock, the loopback callback, and
+    # PKCE generation. They were green locally and never executed here.
+    # Measured: 47 tests with --no-default-features, 87 with --all-features.
+    - name: Run ruview-auth tests with all features (ADR-271 login path)
+      working-directory: v2
+      env:
+        CARGO_PROFILE_DEV_DEBUG: "0"
+        CARGO_PROFILE_TEST_DEBUG: "0"
+      run: cargo test -p ruview-auth --all-features
+
+  # Browser-facing JavaScript.
+  #
+  # These run the dashboard's own modules in Node with stubbed browser globals.
+  # They exist because the Rust suite cannot see them at all: two ADR-271/272
+  # defects (a service worker caching /oauth/status, and the WebSocket ticket
+  # helper) lived entirely in `ui/` and were invisible to a fully green
+  # workspace. Blocking, and fast — no browser, no install step.
+  ui-tests:
+    name: UI JavaScript Tests
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Node
+      uses: actions/setup-node@v4
+      with:
+        node-version: '22'
+
+    - name: Run UI unit tests
+      run: node --test ui/sw.test.mjs ui/services/ws-ticket.test.mjs
+
  # Unit and Integration Tests
  # Python pytest matrix — runs against the archived v1 Python tree.
  # `continue-on-error: true` for the same reason as code-quality above:
@@ -189,6 +246,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Python ${{ matrix.python-version }}
      continue-on-error: true
@@ -226,7 +285,7 @@ jobs:
      continue-on-error: true
      uses: codecov/codecov-action@v6
      with:
-        file: ./coverage.xml
+        files: ./coverage.xml
        flags: unittests
        name: codecov-umbrella

@@ -254,6 +313,8 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Python
      uses: actions/setup-python@v6
@@ -322,6 +383,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Docker Buildx
      continue-on-error: true
@@ -394,6 +457,8 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Python
      uses: actions/setup-python@v6
@@ -471,4 +536,4 @@ jobs:
          **Docker Image:**
          `${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}`
        draft: false
-        prerelease: false
+        prerelease: false
@@ -35,6 +35,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Fetch /traffic/clones + /traffic/views from GitHub
        env:
@@ -28,6 +28,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Setup Rust
        uses: dtolnay/rust-toolchain@stable
@@ -78,6 +80,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Setup Rust
        uses: dtolnay/rust-toolchain@stable
@@ -145,6 +149,8 @@ jobs:
      vars.HAS_GCP_CREDENTIALS == 'true'
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Download x86_64 artifact
        uses: actions/download-artifact@v4
@@ -20,6 +20,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - uses: dtolnay/rust-toolchain@stable
        with: { targets: wasm32-unknown-unknown }
@@ -26,6 +26,8 @@ jobs:
    steps:
      - name: Checkout main
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Install Rust + wasm32 target
        uses: dtolnay/rust-toolchain@stable
@@ -28,6 +28,8 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Setup Node.js
        uses: actions/setup-node@v6
@@ -83,6 +85,8 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Setup Node.js
        uses: actions/setup-node@v6
@@ -131,6 +135,8 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Download all artifacts
        uses: actions/download-artifact@v4
@@ -22,6 +22,8 @@ jobs:
    if: github.ref_type == 'tag'
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      - name: Check firmware version.txt == tag
        run: |
          # Tag form: vX.Y.Z-esp32  →  expect version.txt to contain X.Y.Z
@@ -50,14 +52,16 @@ jobs:
            target: esp32s3
            sdkconfig: sdkconfig.defaults
            partition_table_name: partitions_display.csv
-            size_limit_kb: 1100
+            size_warn_kb: 1100
+            size_limit_kb: 1152
            artifact_app: esp32-csi-node.bin
            artifact_pt: partition-table.bin
          - variant: 4mb
            target: esp32s3
            sdkconfig: sdkconfig.defaults.4mb
            partition_table_name: partitions_4mb.csv
-            size_limit_kb: 1100
+            size_warn_kb: 1100
+            size_limit_kb: 1152
            artifact_app: esp32-csi-node-4mb.bin
            artifact_pt: partition-table-4mb.bin
          # ADR-110: ESP32-C6 research target (Wi-Fi 6 / 802.15.4 / TWT / LP-core)
@@ -65,12 +69,15 @@ jobs:
            target: esp32c6
            sdkconfig: sdkconfig.defaults
            partition_table_name: partitions_4mb.csv
-            size_limit_kb: 1100
+            size_warn_kb: 1100
+            size_limit_kb: 1152
            artifact_app: esp32-csi-node-c6.bin
            artifact_pt: partition-table-c6.bin

    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Build firmware (${{ matrix.variant }})
        working-directory: firmware/esp32-csi-node
@@ -92,18 +99,23 @@ jobs:
          make test_adr110
          ./test_adr110

-      - name: Verify binary size (< ${{ matrix.size_limit_kb }} KB gate)
+      - name: Verify binary size budget
        working-directory: firmware/esp32-csi-node
        run: |
          BIN=build/esp32-csi-node.bin
          SIZE=$(stat -c%s "$BIN")
          MAX=$((${{ matrix.size_limit_kb }} * 1024))
+          WARN=$((${{ matrix.size_warn_kb }} * 1024))
          echo "Binary size: $SIZE bytes ($(( SIZE / 1024 )) KB)"
+          echo "Warning at:  $WARN bytes (${{ matrix.size_warn_kb }} KB)"
          echo "Size limit:  $MAX bytes (${{ matrix.size_limit_kb }} KB)"
          if [ "$SIZE" -gt "$MAX" ]; then
            echo "::error::Firmware binary exceeds ${{ matrix.size_limit_kb }} KB size gate ($SIZE > $MAX)"
            exit 1
          fi
+          if [ "$SIZE" -gt "$WARN" ]; then
+            echo "::warning::Firmware binary exceeds the ${{ matrix.size_warn_kb }} KB soft budget ($SIZE > $WARN); hard limit is ${{ matrix.size_limit_kb }} KB"
+          fi
          echo "Binary size OK: $SIZE <= $MAX"

      - name: Verify flash image integrity
@@ -100,6 +100,8 @@ jobs:

    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Download QEMU artifact
        uses: actions/download-artifact@v4
@@ -214,6 +216,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Install clang
        run: |
@@ -263,6 +267,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Install NVS generator
        run: pip install esp-idf-nvs-partition-gen
@@ -317,6 +323,8 @@ jobs:

    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Download QEMU artifact
        uses: actions/download-artifact@v4
@@ -22,6 +22,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - uses: actions/setup-python@v6
        with:
@@ -41,6 +41,8 @@ jobs:

    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Install mosquitto + clients and start with allow_anonymous
        run: |
@@ -0,0 +1,148 @@
+# ADR-265 D1 — the npm-package gate.
+#
+# Every Node package in this repo (published or private) gets: install, build,
+# tests, a version-literal gate (D3 — package.json is the only place a version
+# lives), a pack-content gate (no source maps, unpacked-size budget), a
+# tarball-install smoke test (would have caught ADR-264 F1's broken `require`
+# export), and the claim-check honesty lint on the README (D4).
+
+name: npm packages
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'harness/ruview/**'
+      - 'tools/ruview-mcp/**'
+      - 'tools/ruview-cli/**'
+      - '.github/workflows/npm-packages.yml'
+  pull_request:
+    paths:
+      - 'harness/ruview/**'
+      - 'tools/ruview-mcp/**'
+      - 'tools/ruview-cli/**'
+      - '.github/workflows/npm-packages.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  gate:
+    name: ${{ matrix.package.dir }} (node ${{ matrix.node }})
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        node: ['20', '22']
+        package:
+          - dir: harness/ruview
+            build: false
+            publishable: true
+            # ADR-263: dependency-free harness; budget guards against dep creep.
+            unpacked_budget: 65536
+          - dir: tools/ruview-mcp
+            build: true
+            publishable: true
+            # ADR-264 O2: map-free tarball (was 188 kB with maps).
+            unpacked_budget: 140000
+          - dir: tools/ruview-cli
+            build: true
+            publishable: false
+            unpacked_budget: 0
+    defaults:
+      run:
+        working-directory: ${{ matrix.package.dir }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node }}
+
+      # Repo policy gitignores lockfiles under harness/ (the harness is
+      # dependency-free anyway); the TS packages commit theirs.
+      - name: Install
+        run: |
+          if [ -f package-lock.json ]; then npm ci; else npm install --no-fund --no-audit; fi
+
+      - name: Build
+        if: ${{ matrix.package.build }}
+        run: npm run build
+
+      - name: Test
+        run: npm test --if-present
+
+      # ADR-265 D3 — package.json is the only place a version string lives.
+      - name: Version-literal gate
+        run: |
+          set -euo pipefail
+          hits=""
+          for d in src bin; do
+            if [ -d "$d" ]; then
+              hits+=$(grep -rEn '\b[0-9]+\.[0-9]+\.[0-9]+\b' "$d" | grep -vE '127\.0\.0\.1|0\.0\.0\.0' || true)
+            fi
+          done
+          if [ -n "$hits" ]; then
+            echo "Hardcoded version-like literals found (read package.json instead — ADR-265 D3):"
+            echo "$hits"
+            exit 1
+          fi
+
+      # ADR-265 D1.3 — pack-content gate: no maps, size budget enforced.
+      - name: Pack gate
+        if: ${{ matrix.package.publishable }}
+        run: |
+          npm pack --dry-run --json 2>/dev/null | node -e "
+            const [info] = JSON.parse(require('fs').readFileSync(0, 'utf8'));
+            const budget = Number(process.env.UNPACKED_BUDGET);
+            const maps = info.files.filter((f) => f.path.endsWith('.map'));
+            if (maps.length > 0) {
+              console.error('Tarball contains source maps (ADR-264 F2):', maps.map((m) => m.path));
+              process.exit(1);
+            }
+            if (info.unpackedSize > budget) {
+              console.error(\`Unpacked size \${info.unpackedSize} B exceeds budget \${budget} B\`);
+              process.exit(1);
+            }
+            console.log(\`pack gate OK: \${info.files.length} files, \${info.unpackedSize} B unpacked (budget \${budget} B), 0 maps\`);
+          "
+        env:
+          UNPACKED_BUDGET: ${{ matrix.package.unpacked_budget }}
+
+      # ADR-265 D1.4 — install the real tarball and drive each bin/export.
+      - name: Tarball smoke test
+        if: ${{ matrix.package.publishable }}
+        run: |
+          set -euo pipefail
+          TGZ="$PWD/$(npm pack --silent 2>/dev/null | tail -1)"
+          SMOKE="$(mktemp -d)"
+          cd "$SMOKE"
+          npm init -y > /dev/null
+          npm i --no-fund --no-audit "$TGZ"
+          case "${{ matrix.package.dir }}" in
+            harness/ruview)
+              ./node_modules/.bin/ruview --version
+              ./node_modules/.bin/ruview doctor
+              # the honesty gate must fail closed on empty input (ADR-263 F1)
+              if ./node_modules/.bin/ruview claim-check; then
+                echo 'claim-check passed with no input — fail-open regression'; exit 1
+              fi
+              node --input-type=module -e "const m = await import('@ruvnet/ruview'); if (!m.TOOLS) process.exit(1);"
+              ;;
+            tools/ruview-mcp)
+              # initialize over stdio; server must answer and exit 0 on EOF
+              printf '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"ci","version":"0"}}}\n' \
+                | timeout 30 ./node_modules/.bin/rvagent | grep -q '"serverInfo"'
+              # the ESM export must resolve from the installed tarball (ADR-264 F1)
+              timeout 30 node --input-type=module -e "await import('@ruvnet/rvagent');" < /dev/null
+              ;;
+          esac
+
+      # ADR-265 D4 — package READMEs must pass the project's own honesty lint.
+      - name: Claim-check README
+        run: |
+          if [ -f README.md ]; then
+            node "$GITHUB_WORKSPACE/harness/ruview/bin/cli.js" claim-check --file README.md
+          else
+            echo "no README.md — skipping"
+          fi
@@ -26,6 +26,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - uses: docker/setup-buildx-action@v3

@@ -13,14 +13,29 @@
 #   1. cut tag `v1.99.0-pip`  → publishes the tombstone wheel first
 #   2. cut tag `v2.0.0-pip`   → publishes the PyO3 v2 wheel matrix
 #
-# Publishes via the `PYPI_API_TOKEN` GitHub Actions secret. The
-# token-refresh runbook (GCP Secret Manager → gh secret set) lives in
-# docs/integrations/pypi-release.md so KICS does not flag the
-# secret name as a generic-secret literal in the workflow.
+# Publishes via the `PYPI_API_TOKEN` GitHub Actions secret (API-token
+# auth). This is the ACTIVE, working publish path — the token is sourced
+# fresh from GCP Secret Manager per the runbook in
+# docs/integrations/pypi-release.md (GCP Secret Manager → gh secret set),
+# which also keeps KICS from flagging the secret name as a generic-secret
+# literal here.
 #
-# Q3 (witness hash v2 — open in ADR-117 §11.3) MUST be resolved
-# before the first v2.0.0 publish. When v2 lands, add a parallel
-# step that verifies the v2 hash against the Rust pipeline.
+# TODO(ADR-184 P1b): migrate to PyPI OIDC Trusted Publishing to remove
+# this rotatable/expire-able credential. That switch is GATED on a manual
+# pypi.org step no CLI/agent can perform: the repo owner must register a
+# Trusted Publisher on pypi.org for owner=ruvnet / repo=RuView /
+# workflow=pip-release.yml (BOTH the wifi-densepose and ruview projects;
+# ruview as a pending publisher) — see docs/adr/ADR-184-*.md. Do NOT grant
+# the OIDC id-token write permission before that registration exists, or
+# publishing fails with "no trusted publisher configured" — a silent
+# regression the `Verify fix markers` guard `RuView#786-pypi-token-auth`
+# exists to catch (it forbids that permission string in this file). When
+# the owner confirms both entries are live, do the OIDC switch as a
+# dedicated follow-up commit (drop `password:`, add the OIDC id-token
+# permission + `environment: pypi`) so there is no capability gap between.
+#
+# Production publishing fails closed until the ADR-117 §11.3 v2 witness
+# hash exists. TestPyPI remains usable to validate release artifacts.

 name: pip-release

@@ -67,7 +82,7 @@ jobs:
            arch: x86_64
          - os: ubuntu-latest
            arch: aarch64
-          - os: macos-13          # x86_64 runner
+          - os: macos-15-intel    # x86_64 runner
            arch: x86_64
          - os: macos-14          # arm64 runner
            arch: arm64
@@ -76,6 +91,8 @@ jobs:
    runs-on: ${{ matrix.os }}
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive

      # Linux aarch64 needs QEMU for cross-build on x86_64 runners.
      - name: Set up QEMU
@@ -121,6 +138,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      - name: Install maturin
        run: pip install maturin>=1.7
      - name: Build sdist
@@ -132,6 +151,46 @@ jobs:
          path: sdist/*.tar.gz
          if-no-files-found: error

+  build-ruview:
+    name: Build ruview meta-package
+    if: |
+      github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
+      startsWith(github.ref, 'refs/tags/v2.')
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v6
+        with:
+          python-version: '3.12'
+      - name: Verify lock-step package versions
+        shell: python
+        run: |
+          import pathlib
+          import tomllib
+
+          root = pathlib.Path("python")
+          core = tomllib.loads((root / "pyproject.toml").read_text(encoding="utf-8"))
+          meta = tomllib.loads((root / "ruview-meta" / "pyproject.toml").read_text(encoding="utf-8"))
+          core_version = core["project"]["version"]
+          meta_version = meta["project"]["version"]
+          expected_dependency = f"wifi-densepose=={core_version}"
+          if meta_version != core_version:
+              raise SystemExit(
+                  f"package versions differ: wifi-densepose={core_version}, ruview={meta_version}"
+              )
+          if expected_dependency not in meta["project"]["dependencies"]:
+              raise SystemExit(f"ruview must depend on {expected_dependency}")
+          print(f"lock-step version: {core_version}")
+      - name: Build ruview wheel and sdist
+        run: |
+          python -m pip install --upgrade pip build
+          python -m build python/ruview-meta --outdir ruview-dist
+      - uses: actions/upload-artifact@v4
+        with:
+          name: ruview
+          path: ruview-dist/*
+          if-no-files-found: error
+
  # ────────────────────────────────────────────────────────────────
  # v1.99.0 — tombstone wheel (pure Python, single sdist + wheel)
  # ────────────────────────────────────────────────────────────────
@@ -144,6 +203,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'
@@ -214,18 +275,29 @@ jobs:
  # ────────────────────────────────────────────────────────────────

  publish-v2:
-    name: Publish v2 wheels
-    needs: [build-wheels, build-sdist]
+    name: Publish wifi-densepose + ruview
+    needs: [build-wheels, build-sdist, build-ruview]
    if: |
      always() &&
      needs.build-wheels.result == 'success' &&
      needs.build-sdist.result == 'success' &&
+      needs.build-ruview.result == 'success' &&
      (
        github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
        startsWith(github.ref, 'refs/tags/v2.')
      )
    runs-on: ubuntu-latest
    steps:
+      - uses: actions/checkout@v4
+      - name: Enforce production witness gate
+        if: |
+          startsWith(github.ref, 'refs/tags/v2.') ||
+          (github.event_name == 'workflow_dispatch' && inputs.publish_to == 'pypi')
+        run: |
+          test -s archive/v1/data/proof/expected_features_v2.sha256 || {
+            echo "::error::ADR-117 §11.3 release gate is incomplete: archive/v1/data/proof/expected_features_v2.sha256 is missing or empty"
+            exit 1
+          }
      - name: Gather all artifacts into dist/
        uses: actions/download-artifact@v4
        with:
@@ -235,12 +307,14 @@ jobs:
          mkdir -p dist
          find dist-staging -type f \( -name '*.whl' -o -name '*.tar.gz' \) -exec cp -v {} dist/ \;
          ls -lh dist/
+      # API-token auth (active path). See TODO(ADR-184 P1b) in the header
+      # before replacing `password:` with the OIDC id-token permission.
      - name: Publish to TestPyPI (dry-run target)
        if: github.event_name == 'workflow_dispatch' && inputs.publish_to == 'testpypi'
        uses: pypa/gh-action-pypi-publish@release/v1
        with:
          repository-url: https://test.pypi.org/legacy/
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.TESTPYPI_API_TOKEN }}
          packages-dir: dist
          skip-existing: true
      - name: Publish to PyPI
@@ -251,6 +325,7 @@ jobs:
        with:
          password: ${{ secrets.PYPI_API_TOKEN }}
          packages-dir: dist
+          verbose: true

  publish-tombstone:
    name: Publish v1.99 tombstone
@@ -268,12 +343,14 @@ jobs:
        with:
          name: tombstone
          path: dist
+      # API-token auth (active path). See TODO(ADR-184 P1b) in the header
+      # before replacing `password:` with the OIDC id-token permission.
      - name: Publish to TestPyPI (dry-run target)
        if: github.event_name == 'workflow_dispatch' && inputs.publish_to == 'testpypi'
        uses: pypa/gh-action-pypi-publish@release/v1
        with:
          repository-url: https://test.pypi.org/legacy/
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.TESTPYPI_API_TOKEN }}
          packages-dir: dist
          skip-existing: true
      - name: Publish to PyPI
@@ -29,6 +29,8 @@ jobs:
    steps:
      - name: Checkout main
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Stage viewer for Pages
        run: |
@@ -0,0 +1,170 @@
+# Python Package CI — gates the `python/` PyO3+maturin wheel (`wifi-densepose`).
+#
+# ADR-117 (pip modernization) + ADR-185 (SOTA extras). Unlike the frozen
+# `archive/v1/` Python app — which is `continue-on-error: true` in ci.yml
+# because it is reference-only — the `python/` package is an actively-shipped
+# PyPI wheel (published by pip-release.yml). Before this workflow, `python/`
+# had ZERO per-PR coverage: pip-release.yml only fires on release triggers
+# (tags / dispatch), so a PR could break the wheel build, break a native-Rust
+# parity test, or blow the wheel-size budget and nothing in the normal gating
+# CI would notice until release day. This workflow closes that gap.
+#
+# Path-scoped as a DEDICATED workflow rather than a job inside ci.yml. That is
+# this repo's own convention for component-scoped CI (cf. firmware-ci.yml,
+# sensing-server-docker.yml, bfld-mqtt-integration.yml — all separate files
+# with `paths:` triggers). GitHub only supports workflow-level `paths:`, not
+# per-job path filters, and no workflow in this repo uses a change-detection
+# action (dorny/paths-filter, tj-actions/changed-files) — so the idiomatic,
+# no-new-dependency way to scope to `python/**` is a standalone workflow. It
+# simply does not run on unrelated PRs.
+
+name: Python Package CI
+
+on:
+  push:
+    branches:
+      - '**'
+    # NOTE: kept in sync with the pull_request paths below. GitHub Actions
+    # does not reliably support YAML anchors in workflow files, so the two
+    # lists are duplicated deliberately rather than aliased.
+    paths:
+      - 'python/**'
+      - 'v2/crates/wifi-densepose-core/**'
+      - 'v2/crates/wifi-densepose-vitals/**'
+      - 'v2/crates/wifi-densepose-bfld/**'
+      - 'v2/crates/wifi-densepose-aether/**'
+      - 'v2/crates/wifi-densepose-mat/**'
+      - 'v2/crates/wifi-densepose-train/**'
+      - 'v2/crates/wifi-densepose-signal/**'
+      - '.github/workflows/python-ci.yml'
+  pull_request:
+    paths:
+      - 'python/**'
+      - 'v2/crates/wifi-densepose-core/**'
+      - 'v2/crates/wifi-densepose-vitals/**'
+      - 'v2/crates/wifi-densepose-bfld/**'
+      - 'v2/crates/wifi-densepose-aether/**'
+      - 'v2/crates/wifi-densepose-mat/**'
+      - 'v2/crates/wifi-densepose-train/**'
+      - 'v2/crates/wifi-densepose-signal/**'
+      - '.github/workflows/python-ci.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: python-ci-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  # Build the wheel with ALL SOTA features and run the full parity suite.
+  # `--features sota` = aether + meridian + mat, so the compiled feature
+  # submodules (wifi_densepose.aether / .meridian / .mat) exist and their
+  # SHA-256 parity tests against the native-Rust reference actually run
+  # (test_aether.py / test_meridian.py / test_mat.py import those submodules
+  # at collection time — without the features they would error, not skip).
+  parity-tests:
+    name: Wheel + parity tests (features=sota)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          # The python/ crate path-deps v2/crates/* and (transitively via
+          # train) the vendored ruvector submodule — recursive checkout keeps
+          # those path deps resolvable, matching the rust-tests job in ci.yml.
+          submodules: recursive
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.11'
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache cargo (Swatinem/rust-cache)
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: |
+            v2
+            python
+
+      # Fast-fail with per-crate attribution BEFORE the heavier maturin build,
+      # so a break in a binding-backing crate is reported as "this crate failed
+      # to build" rather than buried in a maturin link error. These are the
+      # crates the [aether]/[mat]/[meridian] compiled extras link.
+      - name: Build binding-backing crates
+        working-directory: v2
+        env:
+          CARGO_PROFILE_DEV_DEBUG: "0"
+        run: cargo build -p wifi-densepose-aether -p wifi-densepose-mat -p wifi-densepose-train
+
+      # maturin develop needs an active virtualenv; create one and expose it
+      # to the later steps via GITHUB_PATH so `maturin` / `pytest` resolve to
+      # it. Test deps: pytest-asyncio (client tests are async, asyncio_mode
+      # auto), numpy (test_bfld), websockets + paho-mqtt (the [client] extra
+      # used by test_client_*).
+      - name: Create venv + install maturin and test deps
+        run: |
+          python -m venv .venv
+          . .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install "maturin>=1.7,<2.0" pytest pytest-asyncio numpy websockets paho-mqtt
+          echo "VIRTUAL_ENV=$PWD/.venv" >> "$GITHUB_ENV"
+          echo "$PWD/.venv/bin" >> "$GITHUB_PATH"
+
+      - name: Build + install wheel (maturin develop --features sota)
+        working-directory: python
+        env:
+          CARGO_PROFILE_DEV_DEBUG: "0"
+        run: maturin develop --features sota
+
+      - name: Run parity + binding tests
+        run: pytest python/tests/ -q
+
+  # Numeric enforcement of the ADR-117 §5.4 default-wheel budget. A fix-marker
+  # can guard the CONFIG that keeps the wheel small (empty default features,
+  # optional SOTA deps, strip=true — see RuView#1387-default-wheel-budget-config
+  # in scripts/fix-markers.json) but it cannot measure bytes. This job builds
+  # the DEFAULT (no-features) wheel and fails if it exceeds the budget — the
+  # real guard against a dependency silently ballooning the shipped wheel.
+  wheel-size-budget:
+    name: Default wheel <= 5 MiB (ADR-117 §5.4)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.11'
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache cargo (Swatinem/rust-cache)
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: python
+
+      - name: Install maturin
+        run: python -m pip install --upgrade pip "maturin>=1.7,<2.0"
+
+      - name: Build default wheel and assert size budget
+        working-directory: python
+        run: |
+          set -euo pipefail
+          maturin build --release --out dist
+          whl="$(ls dist/*.whl | head -1)"
+          bytes="$(stat -c%s "$whl")"
+          limit=$((5 * 1024 * 1024))   # ADR-117 §5.4: 5 MiB
+          printf 'Default wheel: %s = %s bytes (%s MiB); budget = %s bytes\n' \
+            "$whl" "$bytes" "$((bytes / 1024 / 1024))" "$limit"
+          if [ "$bytes" -gt "$limit" ]; then
+            echo "::error::default wheel is $bytes bytes, over the ADR-117 §5.4 $limit-byte (5 MiB) budget"
+            exit 1
+          fi
+          echo "Default wheel is within the 5 MiB budget."
@@ -0,0 +1,137 @@
+# ADR-265 D2 — publish only from CI, with provenance.
+#
+# Manual `npm publish` from laptops stops: this workflow re-runs the ADR-265 D1
+# gate for the selected package and then publishes with npm provenance
+# attestations (OIDC), tying every published version to a public commit +
+# workflow run — the npm-side analogue of the ADR-028 witness bundle.
+#
+# Requires: NPM_TOKEN repo secret (an npm automation token), or npm Trusted
+# Publishing configured for the package (in which case the token is unused).
+
+name: ruview npm release
+
+on:
+  workflow_dispatch:
+    inputs:
+      package:
+        description: 'Package directory to publish'
+        required: true
+        type: choice
+        options:
+          - harness/ruview
+          - tools/ruview-mcp
+      dist_tag:
+        description: 'npm dist-tag'
+        required: false
+        default: 'latest'
+        type: string
+
+permissions:
+  contents: read
+  id-token: write # npm --provenance
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ${{ inputs.package }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          registry-url: 'https://registry.npmjs.org'
+
+      - name: Install
+        run: |
+          if [ -f package-lock.json ]; then npm ci; else npm install --no-fund --no-audit; fi
+
+      - name: Build (if present)
+        run: npm run build --if-present
+
+      - name: Test
+        run: npm test --if-present
+
+      # ADR-265 D3 — package.json is the only place a version string lives.
+      - name: Version-literal gate
+        run: |
+          set -euo pipefail
+          hits=""
+          for d in src bin; do
+            if [ -d "$d" ]; then
+              hits+=$(grep -rEn '\b[0-9]+\.[0-9]+\.[0-9]+\b' "$d" | grep -vE '127\.0\.0\.1|0\.0\.0\.0' || true)
+            fi
+          done
+          if [ -n "$hits" ]; then
+            echo "Hardcoded version-like literals found (read package.json instead — ADR-265 D3):"
+            echo "$hits"
+            exit 1
+          fi
+
+      # ADR-265 D1.3 — pack-content gate: no maps AND the per-package
+      # unpacked-size budget (the budgets that npm-packages.yml enforces).
+      - name: Pack gate (no maps + size budget)
+        run: |
+          set -euo pipefail
+          case "${{ inputs.package }}" in
+            # ADR-263: dependency-free harness; budget guards against dep creep.
+            harness/ruview) export UNPACKED_BUDGET=65536 ;;
+            # ADR-264 O2: map-free tarball (was 188 kB with maps).
+            tools/ruview-mcp) export UNPACKED_BUDGET=140000 ;;
+            *) echo "Unknown package '${{ inputs.package }}' — no budget defined"; exit 1 ;;
+          esac
+          npm pack --dry-run --json 2>/dev/null | node -e "
+            const [info] = JSON.parse(require('fs').readFileSync(0, 'utf8'));
+            const budget = Number(process.env.UNPACKED_BUDGET);
+            const maps = info.files.filter((f) => f.path.endsWith('.map'));
+            if (maps.length > 0) {
+              console.error('Tarball contains source maps (ADR-264 F2):', maps.map((m) => m.path));
+              process.exit(1);
+            }
+            if (info.unpackedSize > budget) {
+              console.error(\`Unpacked size \${info.unpackedSize} B exceeds budget \${budget} B\`);
+              process.exit(1);
+            }
+            console.log(\`pack gate OK: \${info.files.length} files, \${info.unpackedSize} B unpacked (budget \${budget} B), 0 maps\`);
+          "
+
+      # ADR-265 D1.4 — install the real tarball and drive each bin/export.
+      - name: Tarball smoke test
+        run: |
+          set -euo pipefail
+          TGZ="$PWD/$(npm pack --silent 2>/dev/null | tail -1)"
+          SMOKE="$(mktemp -d)"
+          cd "$SMOKE"
+          npm init -y > /dev/null
+          npm i --no-fund --no-audit "$TGZ"
+          case "${{ inputs.package }}" in
+            harness/ruview)
+              ./node_modules/.bin/ruview --version
+              ./node_modules/.bin/ruview doctor
+              # the honesty gate must fail closed on empty input (ADR-263 F1)
+              if ./node_modules/.bin/ruview claim-check; then
+                echo 'claim-check passed with no input — fail-open regression'; exit 1
+              fi
+              node --input-type=module -e "const m = await import('@ruvnet/ruview'); if (!m.TOOLS) process.exit(1);"
+              ;;
+            tools/ruview-mcp)
+              # initialize over stdio; server must answer and exit 0 on EOF
+              printf '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"ci","version":"0"}}}\n' \
+                | timeout 30 ./node_modules/.bin/rvagent | grep -q '"serverInfo"'
+              # the ESM export must resolve from the installed tarball (ADR-264 F1)
+              timeout 30 node --input-type=module -e "await import('@ruvnet/rvagent');" < /dev/null
+              ;;
+          esac
+
+      - name: Claim-check README
+        run: |
+          if [ -f README.md ]; then
+            node "$GITHUB_WORKSPACE/harness/ruview/bin/cli.js" claim-check --file README.md
+          fi
+
+      - name: Publish (with provenance)
+        run: npm publish --provenance --access public --tag "${{ inputs.dist_tag }}"
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
@@ -36,10 +36,12 @@ jobs:
        features:
          - { label: 'default',          flags: '--no-default-features' }
          - { label: 'train',            flags: '--features train' }
-          - { label: 'ruflo+itar',       flags: '--features ruflo,itar-unrestricted' }
+          - { label: 'ruflo',            flags: '--features ruflo' }
          - { label: 'full+train',       flags: '--features full,train' }
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      - uses: dtolnay/rust-toolchain@stable
      - name: Cache cargo
        uses: actions/cache@v4
@@ -60,6 +62,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      # v2/rust-toolchain.toml pins channel "1.89" with profile "minimal" (no
      # clippy). dtolnay@stable installs clippy on the floating "stable"
      # toolchain, but the override makes cargo use the separate "1.89"
@@ -93,6 +97,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      - uses: dtolnay/rust-toolchain@stable
      - name: Cache cargo
        uses: actions/cache@v4
@@ -127,6 +133,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
      - name: publish = false is present (no accidental crates.io publish)
        run: |
          CARGO=v2/crates/ruview-swarm/Cargo.toml
@@ -28,6 +28,7 @@ jobs:
      continue-on-error: true
      uses: actions/checkout@v4
      with:
+        submodules: recursive
        fetch-depth: 0

    - name: Set up Python
@@ -46,7 +47,10 @@ 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 +61,20 @@ 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
@@ -96,6 +98,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Python
      continue-on-error: true
@@ -163,6 +167,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Docker Buildx
      continue-on-error: true
@@ -244,6 +250,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Run Checkov IaC scan
      continue-on-error: true
@@ -306,6 +314,7 @@ jobs:
      continue-on-error: true
      uses: actions/checkout@v4
      with:
+        submodules: recursive
        fetch-depth: 0

    - name: Run TruffleHog secret scan
@@ -340,6 +349,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Set up Python
      continue-on-error: true
@@ -377,6 +388,8 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
+      with:
+        submodules: recursive

    - name: Check security policy files
      continue-on-error: true
@@ -115,7 +115,7 @@ jobs:
      #      RUN guard catches missing ones at build time, this re-checks the
      #      pushed artifact post-hoc as belt-and-braces).
      #   2. /health is up.
-      #   3. /api/v1/info returns 200 with no auth (LAN-mode default).
+      #   3. /api/v1/info returns 200 with the explicit trusted-LAN opt-in.
      #   4. With RUVIEW_API_TOKEN set, /api/v1/info returns 401 without a
      #      Bearer header, 200 with the correct one (the #443 auth middleware).
      # ---------------------------------------------------------------------
@@ -124,11 +124,14 @@ jobs:
          set -euo pipefail
          IMAGE="ghcr.io/ruvnet/wifi-densepose:sha-${GITHUB_SHA::7}"
          docker pull "$IMAGE"
-          docker run --rm "$IMAGE" sh -c \
+          docker run --rm --entrypoint sh "$IMAGE" -c \
            'ls /app/ui/observatory.html /app/ui/pose-fusion.html /app/ui/index.html /app/ui/viz.html >/dev/null'
-          docker run --rm "$IMAGE" sh -c 'ls -d /app/ui/observatory /app/ui/pose-fusion >/dev/null'
+          docker run --rm --entrypoint sh "$IMAGE" -c 'ls -d /app/ui/observatory /app/ui/pose-fusion >/dev/null'

-          docker run -d --name sm -p 3000:3000 -e CSI_SOURCE=simulated "$IMAGE"
+          docker run -d --name sm -p 3000:3000 \
+            -e CSI_SOURCE=simulated \
+            -e RUVIEW_ALLOW_UNAUTHENTICATED=1 \
+            "$IMAGE"
          # Wait up to 30 s for /health.
          for _ in $(seq 1 30); do
            if curl -fsS http://127.0.0.1:3000/health >/dev/null 2>&1; then break; fi
@@ -30,6 +30,8 @@ jobs:
    steps:
      - name: Checkout main
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Stage demos for Pages
        run: |
@@ -30,6 +30,8 @@ jobs:
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
+        with:
+          submodules: recursive

      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v6
@@ -16,6 +16,15 @@ firmware/esp32-csi-node/sdkconfig.defaults.bak
 # ESP-IDF set-target backup (local only)
 firmware/esp32-hello-world/sdkconfig.old

+# Host-built firmware test binaries (compiled from test/*.c, not source)
+firmware/esp32-csi-node/test/test_adr110
+firmware/esp32-csi-node/test/test_vitals
+firmware/esp32-csi-node/test/fuzz_serialize
+firmware/esp32-csi-node/test/fuzz_edge
+firmware/esp32-csi-node/test/fuzz_nvs
+firmware/esp32-csi-node/test/*.exe
+firmware/esp32-csi-node/test/*.obj
+
 # Claude Flow swarm runtime state
 .swarm/

@@ -268,3 +277,22 @@ aether-arena/staging/
 # MM-Fi benchmark dataset archives — large data, fetch separately, never commit
 assets/MM-Fi/E0*.zip
 assets/MM-Fi/*.zip
+
+# through-wall demo: regenerable trained model artifact
+examples/through-wall/model/
+
+# RuView harness (npx ruview) build artifacts — ADR-182
+harness/**/node_modules/
+harness/**/*.tgz
+harness/**/package-lock.json
+harness/**/.claude-flow/
+harness/**/ruvector.db
+
+# ruvector runtime/hook DB — never tracked (any depth)
+ruvector.db
+**/ruvector.db
+
+# sensing-server runtime artifacts written by its test suite (trained model
+# snapshots + the generated session-secret) — never tracked
+v2/crates/wifi-densepose-sensing-server/data/
+*.proptest-regressions
@@ -14,3 +14,18 @@
 	path = vendor/rvcsi
 	url = https://github.com/ruvnet/rvcsi
 	branch = main
+[submodule "v2/crates/ruv-neural"]
+	path = v2/crates/ruv-neural
+	url = https://github.com/ruvnet/ruv-neural.git
+	branch = main
+[submodule "vendor/rufield"]
+	path = vendor/rufield
+	url = https://github.com/ruvnet/rufield
+[submodule "v2/crates/ruview-swarm"]
+	path = v2/crates/ruview-swarm
+	url = https://github.com/ruvnet/ruv-drone.git
+	branch = main
+[submodule "v2/crates/worldgraph"]
+	path = v2/crates/worldgraph
+	url = https://github.com/ruvnet/worldgraph.git
+	branch = main
@@ -7,13 +7,170 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ## [Unreleased]

+### Added
+- **`ruview-unified` increment 3 — Gaussian update-loop completion, separable delay-Doppler, and property-tested boundary hardening.** (1) `GaussianMap::merge_overlapping` (ADR-275 step 5: mutual-Mahalanobis + semantic-compatibility dedup catching drift the insert-time gate misses) and lifetime-aware decay (`τ_eff = τ·(1+ln(1+lifetime/τ))` — confirmed structures outlive transients at equal nominal τ). (2) `delay_doppler_map` reimplemented separably (`O(B²S+S²B)`), proven equivalent to the direct reference to <1e-10 and **measured 8.3× faster** (520 µs vs 4.34 ms at 56×8). (3) `tests/security_boundaries.rs` — 8 `proptest` properties over the boundary surfaces (arbitrary values incl. NaN/±inf via `f64::from_bits`) that found and fixed three input-controlled defects: a BLE-CS phase-unwrap infinite loop on non-finite phases and an ~1e299-iteration loop on finite-huge phases (now O(1) modular unwrap + plausibility bound), and a subnormal Gaussian scale overflowing `1/σ²` to NaN density (now physical σ/occupancy bounds). (4) New criterion benches for all increment-2 hot paths (`to_canonical` 38 µs, `ble_cs_range` 481 ns, AoI planner 647 ns/200 regions, coherent fusion 1.5 µs/32 members, factorized pose 521 ns). ruview-unified now 98 tests (87 lib + 3 acceptance + 8 security), 0 failed, clippy-clean.
+- **`ruview-unified` increment 2 — native frame contract + programmable perception (ADR-279..282).** (1) `RfFrameV2` becomes the authoritative RF record: native complex IQ with explicit validity masks, declared `PhaseState`, TX/RX poses + antenna geometry in one building frame, calibration/quality state, and a provenance rule enforced at construction — `Synthetic ⇒ L0Simulation` and `Measured ⇒ ≥ L1CapturedReplay` can never alias (the public L0–L5 evidence ladder is now a type); the 56-bin canonical tensor is demoted to a derived compatibility view (`to_canonical`, mask-aware gap-filling through the same normalization path as every adapter; native samples proven byte-untouched). (2) Active sensing control plane (`control.rs`): ETSI-ISAC-vocabulary `SensingTask` admission (raw export always refused; identity requires consent), `SensingAction`/`InformationGoal`, an age-of-information `ActiveSensingPlanner` (priority = uncertainty × change rate × criticality ÷ cost; **measured 95% sensing-traffic reduction** vs uniform refresh on a 20-region scenario), fail-closed `CoherentSensorGroup` fusion gates (time/phase/geometry bounds; five denial paths tested), policy-authorized RIS/movable-antenna actuation receipts, and purpose-scoped `TaskSufficientRepresentation` leakage validation. (3) New modality surfaces: BLE Channel Sounding adapter + `ble_cs_range` treating phase-slope and RTT as **separate cross-validated evidence** (exact distance recovery on synthetic tones; relay-style divergence flagged, never averaged), delay-Doppler-native `FieldAxis` + `delay_doppler_map` (unit-peak tone test), IEEE P3162 synthetic-aperture import profile. (4) RePos-factorized pose head (relative skeleton on the content representation, root on the geometry-conditioned one, calibrated per-joint uncertainties): held-out-room MPJPE 0.0003 m vs 0.2534 m for the monolithic baseline in the room-shortcut leakage experiment; ≤2% structured-adapter budget (740 params). (5) Age gate input now `log(1+age_ms)` per the age-aware-CSI recipe (gradient check re-proven); Gaussian primitives gained `first_seen_ns`/`doppler_variance`/bounded `source_receipts` lineage; `PartitionKey` gained a `session` dimension and `SplitManifest` certifies disjointness across all seven dimensions. 87 tests, 0 failed; crate clippy-clean. Docker images unaffected (no shipped binary consumes the crate yet); Python proof re-verified PASS.
+- **`ruview-unified` — unified RF spatial world model, P1 (ADR-273..278).** New v2 workspace leaf crate implementing the five-pillar architecture: (1) canonical `RfTensor` (`links × 56 bins × 8 snapshots`, complex, validated at the boundary) plus a fail-closed hardware adapter registry with reference adapters for 802.11 CSI (consumes `wifi-densepose-core::CsiFrame`), FMCW radar cubes (fast-time DFT), UWB CIR, and 5G SRS (comb de-interleave); (2) a universal RF foundation encoder — window-median + CFO-aligned tokenizer, masked-reconstruction pretraining with a hand-derived backward pass verified against central finite differences (174 params sampled, max rel err 1.31e-5), the ADR-273 fusion contract `z = Enc(CSI) ⊙ σ(AgeEnc) + GeomEnc(pose)`, and ≤1% task adapters (presence 129 / activity 268 / localization 387 / anomaly 2 vs a 40,856-param backbone); (3) an RF-aware Gaussian spatial memory — anisotropic primitives with per-band×angle reflectivity, confidence-weighted fusion, exponential decay, spatial-hash + semantic queries, closed-form (erf) Beer–Lambert channel-gain queries that degrade to exact Friis on an empty map, inverse gain updates that learn an unseen 6 dB obstruction to <0.5 dB in 20 link observations, and a JITOMA-style task-gated scene graph; (4) a physics-guided synthetic RF world generator — Allen–Berkley image method (order ≤2), complex-permittivity Fresnel materials, bistatic person scattering with *emergent* Doppler (proven against the analytic phase rate), seeded ChaCha20 domain randomization of physics + hardware nuisances (gain/CFO/phase noise/packet loss/interference); (5) an edge sensing control plane — 802.11bf/ETSI-ISAC-aligned purposes and zones, fail-closed authorization, a double-gated identity purpose, retention bounds, and a `BoundedEvent`-only trust boundary that makes raw RF export unrepresentable. Anti-leakage evaluation (`StrictSplit` by room/day/person/chipset/firmware/layout with an independent disjointness verifier, ECE, selective risk, degradation) plus an end-to-end acceptance pipeline: presence F1 1.00 on held-out rooms *and* held-out chipset, degradation 0.0, ECE 0.012, p95 tokenize+encode 2.0 ms debug / 105 µs release — **all SYNTHETIC** (honest labeling propagates from `RfModality::Synthetic` through `Provenance.synthetic`). Criterion benches with an optimization pass: segment-corridor candidate search took `channel_gain` from 139 µs → 27 µs (O(1) in map size; hash/linear crossover at ~4k Gaussians reported honestly), `observe_link` 305 µs → 74 µs, precomputed DFT twiddles 4.9×. 66 unit + 3 acceptance tests, 0 failed.
+
+### Changed
+- **crates.io release batch — 10 of the 12 documented crates republished at their next patch version.** `wifi-densepose-core` 0.3.2, `-vitals` 0.3.2, `-wifiscan` 0.3.2, `-hardware` 0.3.2 (picks up the ADR-273..282 review-fix commit's clippy fixes), `-signal` 0.3.6, `-nn` 0.3.2, `-ruvector` 0.3.3, `-train` 0.3.3, `-mat` 0.3.2, `-wasm` 0.3.1 — all published and verified live on crates.io. **`wifi-densepose-sensing-server` and `wifi-densepose-cli` were bumped locally (0.3.5, 0.3.2) but NOT published**: both now path-depend on `ruview-auth`, which is deliberately `publish = false` and not on crates.io — `cargo publish` correctly refuses to publish a crate with an unversioned/unpublishable path dependency. This is a pre-existing gap (the dependency predates this batch); resolving it is a deliberate call for whoever owns whether `ruview-auth` becomes public, not something to route around silently.
+- **`wifi-densepose` promoted to `2.0.0` stable; `ruview` `2.0.0` prepared for its first stable publish (ADR-184 P2).** Dropped the `a1` alpha suffix on both sibling packages (`python/pyproject.toml`, `python/ruview-meta/pyproject.toml`) and flipped their trove classifier `Development Status :: 3 - Alpha` → `5 - Production/Stable`; the `ruview` meta-package's `wifi-densepose==2.0.0a1` dependency pins (base + `[client]`) were repointed to `==2.0.0`. **Version-metadata prep only — nothing is published by this change**: the actual PyPI upload remains gated on the ADR-117 v2 witness hash. Justified as "stable": the default (no-extras) wheel builds at 279 KB (`maturin build --release --strip`) and the base non-SOTA suite is green — `pytest python/tests/` (excluding the `[aether]`/`[meridian]`/`[mat]` extra modules) = **185 passed, 0 failed** (smoke / keypoint / pose / vitals / bfld / security / WS+MQTT client).
+- **CI (ADR-184): `pip-release.yml` keeps token-based PyPI authentication until Trusted Publishing is registered.** An OIDC migration was attempted in `cc153e8b5` and reverted in `82d5c7339` so releases would not enter a half-configured state. Production currently uses `PYPI_API_TOKEN`; TestPyPI uses its independent `TESTPYPI_API_TOKEN`. The workflow now builds and publishes `wifi-densepose` and `ruview` together, verifies their versions and dependency pin match, and fails closed before production upload when `expected_features_v2.sha256` is absent.
+- **`@ruvnet/rvagent` startup optimization — stdio time-to-first-response ~242 ms → ~189 ms (−22%; MEASURED, median of repeated `initialize` round-trips against `dist/index.js`, this container, reproduce with a piped-stdin timer).** Two changes: (1) `./http-transport.js` is now imported **lazily** inside the `RVAGENT_HTTP_PORT` branch — it chain-loads the MCP SDK's `streamableHttp` module (~48 ms MEASURED via per-module `import()` timing), which the default stdio path never uses; (2) the advertised JSON Schemas generated from the Zod sources are memoized per tool instead of re-walking the Zod tree on every `tools/list` (matters under the session-per-server HTTP model where each session lists tools). No behavior change: 99/99 jest tests, HTTP session flow re-smoke-tested through the lazy path. The `@ruvnet/ruview` harness CLI was profiled too and left alone — 50 ms vs the ~29 ms bare `node -e ''` floor on the same box (MEASURED), i.e. already near the interpreter floor with zero dependencies.
+
+### Deprecated
+- **`archive/v1` (the original pure-Python implementation) formally deprecated (ADR-187)** — commits `1fb5397dd`, `b1417fb6e`; refs #509, #1125. Added `archive/v1/DEPRECATED.md` (a loud tombstone) and a `> ⚠️ DEPRECATED` notice atop `archive/v1/README.md`, both pointing at the maintained `v2/` workspace and the `wifi-densepose 2.x` / `ruview` pip wheel (ADR-117). Records the honest fact behind #509: `archive/v1`'s `DensePoseHead` is **architecture-only** — random `kaiming_normal_` init with **zero committed checkpoints** under `archive/v1/` (MEASURED by Glob over `**/*.{pth,onnx,safetensors,pt,ckpt,bin}`). The ADR-028 deterministic proof `archive/v1/data/proof/verify.py` stays live and is explicitly out of scope. The same effort added a **"Model weights: what's real, what's not" three-tier table** to `README.md` + `docs/user-guide.md`, separating real-and-validated checkpoints (presence 82.3% held-out temporal-triplet, MM-Fi pose 82.69% torso-PCK@20, `count_v1`) from the real-but-weak on-device `pose_v1` (PCK@20 = 3.0%, runtime `confidence=0` stub, below the ADR-079 ≥35% target) from the architecture-only `archive/v1` head — and caveated every live single-ESP32 17-keypoint advertisement accordingly. Docs/labeling only; no code or model behavior changed.
+
 ### Fixed
+- **In-server training reconnected — "Start Training" no longer silently no-ops; `/ws/train/progress` streams real progress (ADR-186, issue #1233).** The dashboard's Start Training button POSTed a config, got `success:true`, and nothing happened: `/api/v1/train/start` was a stub that flipped a status string and logged one line, and `/ws/train/progress` 404'd. The full pure-Rust trainer in `training_api.rs` (loads recorded CSI, gradient-descent, exports a `.rvf`) already existed but was **orphaned** — never declared as a module (no `mod training_api;`), so it wasn't compiled at all. Fix (`wifi-densepose-sensing-server`): declared the module, reconciled `AppStateInner` (replaced the `training_status`/`training_config` stub fields with a shared `TrainingState` status handle + cooperative cancel flag + a `training_progress_tx` broadcast), deleted the stub handlers, and merged the real `training_api::routes()` (so `/api/v1/train/{start,stop,status,pretrain,lora}` and `/ws/train/progress` resolve under the existing `/api/v1/*` bearer gate). The training core was decoupled from the ~60-field server state so it is unit-testable. **P5 honesty guarantee:** with `RUVIEW_DISABLE_SERVER_TRAINING` set, start returns a structured `{enabled:false, cli:"wifi-densepose train-room"}` HTTP 409 — never a silent success — and the dashboard disables the Start buttons with a CLI tooltip (enablement is surfaced on `/api/v1/train/status`). Pinned by 8 new tests incl. a **live-socket** test that completes a genuine 101 WebSocket handshake and receives a real progress frame after a POST start, a full POST→poll-status→`.rvf`-exists round-trip, a path-traversal rejection, cancellation, and the disabled-409 path. `cargo test -p wifi-densepose-sensing-server -p wifi-densepose-train --no-default-features` — 0 failed.
+- **FastAPI health/metrics endpoints event-loop starvation.** Calling `psutil.cpu_percent(interval=1)` blocked the single-threaded async event loop for 1.0 second on every health check or metrics collection tick, stalling all incoming requests and WebSocket operations. Fixed by changing `cpu_percent` to use non-blocking `interval=None` and offloading all blocking OS metrics gathering to background thread pools via `asyncio.to_thread`. Verified event loop responsiveness via concurrency regression tests.
+- **EngineBridge now honors `WDP_GUARD_INTERVAL_US`/`WDP_SOFT_GUARD_US`/`WDP_TDM_SLOTS`+`WDP_TDM_SLOT_US`** (#1309, PR #1312, @erichkusuki). The governed trust path previously built its multistatic fuser from a hardcoded `MultistaticConfig::default()` (60 ms guard), so multi-node deployments with WiFi/ESP-NOW time sync (10–150 ms drift) failed every governed cycle regardless of configuration — while the startup log claimed the override took effect. New `StreamingEngine::set_multistatic_config()`; `EngineBridge::new()` takes an `Option<MultistaticConfig>` threaded from the same env-derived config as `AppState.multistatic_fuser`. Hardware-verified on a live 2-node ESP32-S3 setup (90 s window, 0 fusion errors; previously every cycle failed).
+- **`/api/v1/stream/pose` WebSocket reachable with `RUVIEW_API_TOKEN` set + dashboard bearer-token field** (#1310, PR #1313, @erichkusuki). Browsers cannot attach an `Authorization` header to a WS upgrade, so the Live Demo pose stream always failed when auth was on; the path is now on a narrow exact-match exemption list (mirrors `/ws/sensing`), with a regression test pinning that the exemption doesn't leak to other `/api/v1/*` paths. The QuickSettings panel gains an "API Access" field storing the bearer token in `localStorage`; the token is applied at `api.service.js` module load so the very first request carries it.
+- **Display-less DevKitC-1 boards: `sdkconfig.defaults.devkitc` build overlay** (#1308, PR #1311, @erichkusuki). The ADR-045 runtime display probe false-positives on stock ESP32-S3-DevKitC-1 (floating QSPI pins), which silently skipped the RuView#893 MGMT+DATA CSI upgrade and collapsed CSI yield to 0 pps. The overlay compiles display support out (`has_display` constant-false). Also fixes stale `espressif/idf:v5.2` README references to v5.4 (source requires `esp_driver_uart`, IDF ≥5.3). Hardware-verified on 2× DevKitC-1-N16R8 (0 → 40–45 pps).
+- **ADR-263/264/265 implemented — the RuView npm surface fixed end-to-end (`@ruvnet/ruview@0.2.0`, `@ruvnet/rvagent@0.2.0`, `@ruv/ruview-cli`).** Harness (ADR-263 O1–O9): `claim-check` now **fails closed** on empty input (CLI exit 2 + `empty_text` tool error); the MCP stdio server dispatches `tools/call` asynchronously over promise-based `spawn` — `ping` answers while a long `verify`/`calibrate` runs (pinned by a new e2e test that runs a 3 s fake proof and asserts sub-second ping); the two `optionalDependencies` are gone so a cold `npx` installs exactly 1 package (MEASURED: was 4 packages / 620 kB / 71 files, `npm i` in a clean prefix); child output is captured as bounded rolling tails (no more 1 MiB `maxBuffer` kills); `node_monitor` passes the port via `sys.argv` instead of splicing it into `python -c` source; the MCP `serverInfo.version` reads package.json; `.claude/skills/*/SKILL.md` are generated from `skills/*.md` by a `prepack` sync script (byte-equality pinned by test); `which()` is a memoized dep-free PATH scan; tools are underscore-canonical (`ruview_claim_check`, …) with the dotted names accepted as call-time aliases, plus `resources/list`/`prompts/list` stubs; the guardrail's `METRIC_TERMS` matching is precision-fixed (word-boundary `map`/`f1`/`auc`/`iou`, code-span + label scrubbing, quantitative-claims-only) — ADR-263/264/265 and both package READMEs now PASS `claim-check` while real untagged claims still flag. 30/30 tests (MEASURED, `node --test`). rvagent (ADR-264 O1–O9): `exports` fixed (types-first, the never-built `dist/index.cjs` `require` target removed — verified broken in the published 0.1.0 tarball); tarball is map-free (127,704 B unpacked / 46 files / 0 maps — MEASURED, `npm pack --dry-run`, down from 188 kB with 44 maps); the Streamable HTTP transport is **actually wired** behind `RVAGENT_HTTP_PORT` with one transport + one MCP server per session (`mcp-session-id` routing), a 1 MiB body cap (413), and a port-aware localhost origin gate — the "dual-transport" description is now true; tools renamed to underscore-canonical with dotted router aliases; ONE Zod validation gate per call with the advertised JSON Schema generated from the same Zod source (`zod-to-json-schema`); `train_count` closes its log fds (was leaking 2/job) and persists job records to `<jobsDir>/<id>.json` so `job_status` survives restarts, with bounded log-tail reads; `detectCogBinary` actually probes its candidate paths; version reads package.json; `@types/express` dropped, `@types/jest` aligned to jest 29; README rewritten to match reality (no phantom `stdio`/`http`/`policy grant` subcommands; unimplemented ADR-124 catalog tools labeled roadmap). 99/99 jest tests (MEASURED); stdio handshake + HTTP session flow + 403/400/404/413 gates smoke-tested live. CLI: bin renamed `ruview-cli` (the `ruview` bin belongs to `@ruvnet/ruview`, ADR-265 D4), version single-sourced. Distribution (ADR-265 D1–D4): new `npm-packages.yml` (3-package × Node 20/22 matrix: tests, version-literal grep gate, pack-content/size gate, tarball-install smoke test incl. the fail-closed claim-check and an ESM-import probe that would have caught the broken `require` export, README claim-check) and `ruview-npm-release.yml` (publish from CI only, `npm publish --provenance`); `ci.yml` NODE_VERSION 18→20.
+- **Empty-room field-model calibration collected nothing on real HT40 nodes — raw 128-wide frames rejected by the 56-tone model (follow-up to the deadlock fix below).** Once the status-gate deadlock was fixed, `maybe_feed_calibration` reached `feed_calibration`, but a real ESP32 HT40 node streams 128-wide amplitude vectors while the single-link `FieldModel` is the canonical 56-tone grid — so `LinkStats::update` returned `DimensionMismatch`, `feed_calibration` bubbled the error, and `maybe_feed_calibration` swallowed it at `debug` level. Net effect: `frame_count` stayed pinned at 0 on live hardware even though presence/motion/vitals (which read the global history) worked fine. Fixed by resampling each frame onto the model's canonical 56-tone grid via `HardwareNormalizer::resample_to_canonical` before feeding — the same length-only canonicalization the multistatic fusion path uses (#1170). Pinned by `field_bridge::maybe_feed_calibration_resamples_wide_frames_and_accumulates` (128-wide frame → Collecting + count 1; fails on old code). Verified live on the ESP32-S3 deployment.
+- **Empty-room field-model calibration could never start — `/api/v1/calibration/*` was a dead endpoint (frame count pinned at 0).** `POST /calibration/start` creates the `FieldModel` in `Uncalibrated`, but the per-frame server feed `field_bridge::maybe_feed_calibration` only fed observations while the model was **already** `Collecting` — and the *only* thing that sets `Collecting` is `feed_calibration` itself (on its first fed frame). The two gates deadlocked: nothing ever fed the first frame, so `calibration_frame_count` stayed 0, `status` never left `Uncalibrated`, and the SVD room eigenstructure (eigenvalue-based person counting / localization) could never calibrate — observed live as `{"status":"Uncalibrated","frame_count":0}` never advancing on a streaming ESP32 node. Fixed the guard to feed while `Uncalibrated | Collecting` so the first frame flips the model to `Collecting` and the count advances. Also made `calibration_stop` return a structured `{success:false, frame_count, frames_needed}` (with a new `FieldModel::min_calibration_frames()` accessor) instead of an opaque 500 when finalized before enough empty-room frames accumulate. Pinned by `field_bridge::maybe_feed_calibration_advances_uncalibrated_to_collecting` (asserts `Uncalibrated → Collecting` + count 0 → 1 → 2; fails on old code). Presence/motion/vitals were unaffected — they use the separate auto rolling baseline, not the field model.
+- **Multistatic fusion never ran on a mixed-mode ESP32 mesh — live bridge fed raw, un-canonicalized per-node CSI to the fuser (#1170).** `node_frame_from_state` (`multistatic_bridge.rs`) wrapped each node's **raw** amplitude vector (HT20 ≈ 64 bins, HT40 ≈ 128/192) into a struct *named* `CanonicalCsiFrame` without ever resampling, so `MultistaticFuser::fuse` tripped `DimensionMismatch` on every cycle, silently fell back to per-node sum/dedup, and spun `total_engine_errors` unbounded. Added `HardwareNormalizer::resample_to_canonical` (resample-only, **no z-score** — preserves the amplitude scale the person-score's `variance/mean²` relies on) and run every node frame through it onto the canonical 56-tone grid before fusion. Heterogeneous meshes now fuse instead of erroring. Pinned by `heterogeneous_node_counts_canonicalize_and_fuse` (mixed 64/192 → fuses), `resample_to_canonical_is_length_only_no_zscore`, and an updated `test_node_frame_conversion`; the pre-existing `engine_bridge::observe_cycle_counts_engine_errors` was retargeted to force a `TimestampMismatch` (its old 56-vs-30 setup now canonicalizes cleanly). `wifi-densepose-signal` 501 / `wifi-densepose-sensing-server` 677 tests, 0 failed.
+- **`csi_fps_ema` reported the CSI frame rate 40–840× too high under bursty UDP delivery (#1180).** `update_csi_fps_ema` only rejected deltas `≤ 0` or `≥ 1 s`, so a 36 µs intra-burst arrival delta yielded `1/dt ≈ 27 kHz` straight into the EMA — the metric measured server arrival jitter, not the node's ~40 fps production rate. Added a `MIN_PLAUSIBLE_CSI_DT_SEC = 0.005` floor (derived from the firmware's 50 fps `CSI_MIN_SEND_INTERVAL_US` ceiling, ×4 slack) and made `observe_csi_frame_arrival` keep its anchor across sub-floor bursts so the next genuine inter-frame gap measures true cadence. Pinned by `subms_burst_delta_rejected`, `burst_interleaved_with_nominal_stays_in_band`, and `observe_csi_frame_arrival_ignores_subms_bursts`.
+- **`stream_sender` ENOMEM backoff starved low-rate control packets under a weak uplink (#1183, follow-up to #1135/#1159).** The global `s_backoff_until_us` gate (triggered by the 50 Hz CSI flood at weak RSSI) also suppressed the ≤48 B, ≤1 Hz `feature_state` / mesh `HEALTH` / sync packets that contribute negligible buffer pressure, so telemetry failed essentially every cycle. Added `stream_sender_send_priority()` — bypasses the backoff gate, reports ENOMEM quietly, and never extends/resets the global streak — and routed `feature_state`, HEALTH/anomaly (`rv_mesh_send`), and sync packets through it. Also fixed the misleading `"HEALTH sent"` log that printed unconditionally even when `rv_mesh_send` returned `ESP_FAIL` (now prints `sent`/`FAILED` from the actual return). Firmware builds clean (ESP-IDF v5.4).
+- **Multistatic fusion guard interval is now operator-configurable — fixes permanent trust demotion with WiFi-synced ESP32 nodes (#1049).** Two independently-clocked ESP32-S3 boards on ESP-NOW sync drift 10–150 ms (typ. ~70 ms) — the 100 ms beacon + WiFi-MAC jitter cannot hold them within the published 60 ms default guard, so the governed-trust cycle permanently demoted to `Restricted`, suppressed all pose output, and spun the error counter to 200k+ with **no escape hatch but a container restart**. Added a **direct `WDP_GUARD_INTERVAL_US` override** (+ optional `WDP_SOFT_GUARD_US`) to `multistatic_guard_config_from_env`, so a deployment can lift the hard guard past its measured spread (e.g. `WDP_GUARD_INTERVAL_US=200000`) without having to know its exact TDM schedule. Precedence is most-specific-wins: a direct override beats the existing `WDP_TDM_SLOTS`+`WDP_TDM_SLOT_US` schedule-derived guard, which beats the 60 ms/20 ms default; the override is applied on top of whichever base is selected, the soft band is always clamped strictly below the hard guard, and a malformed/zero value is ignored (falls back to the base rather than breaking fusion). The effective guard is now logged at startup. Pinned by 6 new tests (`multistatic_guard_config_tests`): direct-override-wins / beats-TDM-derived / soft-clamped-below-hard / lowering-hard-pulls-soft-down / malformed-or-zero-falls-back / default-when-unset. `wifi-densepose-sensing-server` bin tests **449 → 455**, 0 failed; Python proof VERDICT PASS, hash unchanged (off the signal proof path).
+
+### Security
+- **`wifi-densepose-occworld-candle` — beyond-SOTA security + correctness review (Milestone #9, crate 4/4).** (1) **HIGH (MEASURED) — checkpoint-load crash on any int32 tensor** (`model.rs::safetensor_dtype_to_candle`). `safetensors::Dtype::I32` was mapped to `candle_core::DType::I64` and the raw int32 byte buffer (4 bytes/elem) was then handed to `Tensor::from_raw_buffer(.., I64, shape, ..)`. Candle derives `elem_count = data.len() / dtype.size_in_bytes()`, so the I64 path halved the element count while keeping the *original* shape — yielding a tensor whose declared shape claims twice as many elements as its backing storage holds. Reading it **panics** (`range end index 6 out of range for slice of length 3` — slice OOB inside candle-core) on any attacker-supplied or PyTorch-exported checkpoint containing an int32 tensor (common: index/buffer tensors). Fixed by mapping `I32 → DType::I32` (and `I16 → DType::I16`), both first-class candle dtypes. Reproduction recorded on old code; pinned by `tests/checkpoint_loading.rs::int32_tensor_loads_with_consistent_shape_and_values` (panics on old, passes on new) plus F32/I64/corrupt-file control cases. (2) **LOW (MEASURED) — `predict()` lacked frame/batch validation at the input boundary** (`inference.rs`). It validated H/W/D but not the externally-supplied frame count; an `f_in > num_frames*2` over-indexed the temporal positional embedding deep in the transformer and surfaced as a cryptic candle "gather" `InvalidIndex` (returned error, not a panic — candle bounds-checks), and a zero frame/batch dim fed a zero-element tensor into the pipeline. Now rejected at the boundary with a clear `ShapeMismatch`. Pinned by `predict_rejects_zero_frames` / `predict_rejects_too_many_frames` / `predict_accepts_frame_count_at_capacity`. (3) **LOW (MEASURED) — divide-by-zero panic on a degenerate input to the public `VQCodebook::encode`** (`vqvae.rs`): a rank-0 / empty-last-dim tensor made `last == 0` and panicked on `elem_count() / last`. Now fails closed with a clear error. Pinned by `encode_rejects_scalar_without_panicking`. **Dimensions confirmed CLEAN with evidence:** panic surface — zero `unwrap()`/`expect()`/`panic!`/`unreachable!` in production code paths (grep evidence; all error handling via `?`/`map_err`); NaN-state-poisoning — N/A (engine is stateless between `predict` calls, input is `u8` class indices so non-finite input is structurally impossible, no persistent world-model buffer to latch into); unbounded-alloc / shape-data mismatch from malformed weights — defended upstream by `safetensors::validate()` (overflow-checked `nelements*dtype.size()` vs declared byte range, rejected before reaching candle); secrets — none (grep clean, only `token_h`/`token_w` config fields match). `unsafe_code = forbid` in the crate manifest. **Build/validation status (MEASURED on Windows):** crate builds and tests under `cargo test -p wifi-densepose-occworld-candle --no-default-features` — **29/29 pass** (20 unit + 4 checkpoint_loading + 3 predict_honesty + 2 doc) after fixes; `cargo test --workspace --no-default-features` = 0 failed across all crates (lone `wifi-densepose-desktop` `api_integration` failure was a Windows "Access is denied (os error 5)" file-lock flake — re-ran in isolation **21/21 pass**); Python proof VERDICT PASS, hash `f8e76f21…446f7a` unchanged. *Warrants ADR slot 179 (parent to author).*
+- **`wifi-densepose-wasm-edge` beyond-SOTA closing review — boundary NaN-state-poisoning guard + clean-with-evidence attestation (ADR-040 edge crate, ~70 modules).** Closing pass of the security campaign over the last untouched sizeable crate. **One real finding fixed (LOW / source-analysis + reproduced):** the two WASM↔host frame boundaries (`lib.rs::on_frame`/`on_timer` and `bin/ghost_hunter.rs::on_frame`) read raw IEEE-754 `f32` from the `csi_get_phase`/`csi_get_amplitude`/`csi_get_variance`/`csi_get_motion_energy` host imports **without any finiteness check** — the entire crate had **zero** `is_finite`/`is_nan` guards, and the in-crate `clamp` helpers propagate NaN (`NaN < lo` and `NaN > hi` are both false). A single non-finite value (firmware DSP bug, uninitialised buffer, or hostile host) latches NaN into the long-lived per-module accumulators (EMA, Welford, phasor sums, anomaly baselines); once latched, every downstream comparison evaluates `false`, so detectors fail **degraded** (stuck gate state, silently-disabled anomaly checks) — silent corruption, not a crash (WASM `panic=abort` is *not* tripped: no indexing/`unwrap` on the poisoned value). Threat model is a **semi-trusted** boundary (the Tier-2 DSP firmware supplies the imports, not direct network/JS), hence LOW severity / defense-in-depth. **Fix:** added `sanitize_host_f32()` (maps non-finite→`0.0`, `core`-only so it holds in `no_std`) applied at every `host_get_*` float read — a single chokepoint covering all ~70 downstream modules, mirroring the existing M-01 negative-`n_subcarriers` boundary clamp. **Pinned by** `boundary_tests::{sanitize_passes_finite_values_through, sanitize_maps_non_finite_to_zero, coherence_monitor_nan_latches_without_sanitize_but_not_with}` — the last asserts on the *current* `CoherenceMonitor` that a raw NaN frame latches the smoothed score (documents the hazard) while the boundary-sanitized path stays finite. **Dimensions attested CLEAN with evidence (source-analysis):** (a) **panic-on-input** — every non-test `unwrap()`/`expect()` is either `#[cfg(test)]` or in the `std`-gated RVF *builder* host tool writing to an in-memory `Vec` (infallible); no `panic!`/`unreachable!`/`todo!`/`get_unchecked` in any hot path. (b) **shape/bounds** — all frame-buffer access is `min()`-clamped (`MAX_SC=32`, `DTW_MAX_LEN`, `LCS_WINDOW`, `PATTERN_LEN`), all index-by-cast sites (`feature_id as usize`, `conclusion_id`, `minute_counter`, `plan_step`) are either compile-time-const-bounded or `if idx <`/`%`-guarded; negative `n_subcarriers` already mapped to 0 (M-01). (c) **memory/leak** — no `move ||` closures, no `mem::forget`/`Box::leak`/`.leak()`; the only `Box::new` is in the `std`-gated `skill_registry` (one-time init, bounded). (d) **secrets** — none (grep clean). **MEASURED build/test evidence:** host `cargo test --features std,medical-experimental` = **672 passed / 0 failed** (was 669 pre-fix; +3 new tests); the real deployment artifacts all build clean on the actual target — `cargo build --target wasm32-unknown-unknown --release` (no_std/panic=abort default lib), `--bin ghost_hunter --no-default-features --features standalone-bin`, and `--features medical-experimental` (toolchain 1.89 per `rust-toolchain.toml`). No ADR slot needed — a single LOW defense-in-depth boundary fix; CHANGELOG attestation suffices.
+- **ADR-131 HOMECORE-UI BFF gateway — public-PR review fixes (PR #1082).** (1) **HIGH — path-traversal / confused-deputy SSRF closed in the `/api/cal/*` reverse-proxy** (`homecore-server/src/gateway.rs`). The wildcard proxy path was interpolated straight into the upstream URL while `proxy()` attaches the server-side calibration bearer, so `/api/cal/v1/../../x` (and percent-encoded `..%2f`, `%2e%2e`, leading `/`, backslash, double-encoded `%252e`) could escape the `…/api/` scope **with the privileged token**. Now `validate_proxy_path()` decode-then-checks and rejects absolute/backslash/dot-segment/encoded-traversal paths with a typed **400 BEFORE the URL is built** (applies to GET **and** POST); legit `v1/...` paths still pass. Pinned by `cal_proxy_rejects_traversal_with_400_before_upstream` (fails on old code) + `validate_proxy_path_rejects_traversal_variants`. (2) **CORS + request-tracing now cover the gateway routes.** `/api/homecore/*` and `/api/cal/*` were `.merge()`d **outside** the layers `homecore-api::router()` applies, leaving them with no CORS allowlist and untraced; the audited `build_cors_layer()` (HC-05) + `TraceLayer` are now applied to the whole merged surface in `main.rs`. Pinned by `gateway_routes_are_cors_covered_after_merge` (Vite-dev-origin preflight succeeds on a gateway route). (3) **Fabricated-data honesty (§6 invariant 3):** the gateway no longer injects a hardcoded `anomaly.threshold: 0.5` — it passes through the REAL upstream threshold or emits `null` (withheld); the dashboard renders a not-available `—` instead of `"null%"`/`"null°C"` for null appliance metrics; the COG panel's Hailo-worker pill reflects the real appliance probe instead of a hardcoded `"connected"`; `rooms.js` treats a null anomaly threshold as withheld, not a fake `0.8` default. (4) **Robustness:** a forwarded `hef` that is a string (not an array) no longer throws in the COG panel; the calibration wizard guards `frames/target` against `NaN%`/`Infinity%` and clears its baseline poll timer on Restart / panel teardown (leaked `setTimeout` loop fixed). (5) **Perf:** per-bank RoomState fetches and the appliance service probes now run concurrently (`futures::join_all`; async `tokio::net::TcpStream` + `timeout` replaces the blocking `connect_timeout` that parked a worker per probe); the mock fixture module is now a dynamic `import()` gated on demo mode so production never bundles it. **Note (workspace-wide, not fixed here):** `homecore-server` requests `reqwest`'s `rustls-tls` only, but cargo feature-unification means a sibling crate enabling the default `native-tls` re-introduces OpenSSL into the final binary regardless — a true "no OpenSSL on the appliance" guarantee requires aligning every reqwest-pulling crate on rustls-only. **Note (pre-existing, out of scope):** DEV-mode `allow_any_non_empty()` bearer auth when `HOMECORE_TOKENS` is unset on `0.0.0.0` is unchanged; the loud `warn!` at boot is retained — provision real tokens before network exposure. **Verified:** `cargo test -p homecore-server --no-default-features` = **18/18 pass**, `cargo build -p homecore-server` clean, UI suite (`node tests`) all green, Python proof VERDICT PASS (hash unchanged).
+- **`wifi-densepose-desktop` (Tauri v2 desktop app) beyond-SOTA security review (needs ADR slot 178) — one real IPC serial-command-injection fix + one over-broad shell-capability removal, each MEASURED on Windows; remaining IPC/path/secret dimensions confirmed clean with evidence.** Beyond-SOTA review of the Tauri desktop crate (the real attack surface is the webview→Rust IPC boundary + the capability allowlist). The crate **builds + tests on this Windows box** (`cargo check`/`cargo test -p wifi-densepose-desktop --no-default-features` — Tauri 2.10 + GTK-less Windows webview2 path), so both findings are **MEASURED**, not source-analysis. **WDP-DESK-01 (serial command injection via `configure_esp32_wifi`, MODERATE) — FIXED.** The `#[tauri::command] configure_esp32_wifi(port, ssid, password)` handler took `ssid`/`password` straight from the webview and concatenated them into newline-terminated serial commands (`format!("wifi_config {} {}\r\n", ssid, password)`, `set ssid {}\r\n`, …) with **zero validation** before writing them to the ESP32 over the line-oriented serial protocol. A `\r\n` embedded in either field lets a malicious/compromised webview **terminate the command line early and inject an arbitrary follow-up firmware command** (`reboot`, `erase_nvs`, etc.) — a command-injection-into-device-protocol crossing the IPC trust boundary. Ironic note: the crate already shipped `test_wifi_credentials_validation` documenting the WPA2 length bounds, but the handler never enforced them. **Fix:** a new `validate_wifi_credentials(ssid, password)` rejects out-of-range lengths (SSID 1-32, password 8-63 — WPA2 PSK bounds) **and any control character** (`char::is_control()` catches `\r`/`\n`/NUL), called at the top of the handler before any serial write — fail-closed (`Err` → no bytes sent). Pinned fails-on-old / passes-on-new by `test_validate_wifi_credentials_rejects_injection` (`"net\r\nreboot"`, `"net\ninjected"`, `"pass\r\nerase_nvs"`, embedded NUL — all rejected; would splice into the command stream pre-fix), `test_validate_wifi_credentials_rejects_out_of_range`, and `test_validate_wifi_credentials_accepts_valid` (boundary 32-char SSID / 8- and 63-char passwords still accepted). **WDP-DESK-02 (over-broad shell capability, MODERATE) — REMOVED.** `capabilities/default.json` granted the webview `shell:allow-execute` + `shell:allow-open`, but the Rust backend spawns every process via `std::process::Command` directly (espflash/which/sensing-server — which **bypasses** the Tauri allowlist entirely) and the React UI only ever calls `dialog.open` (file picker) — verified by grep: `tauri_plugin_shell` is `init()`-ed but its `Command`/`open` API is **never invoked from Rust or TS**. The two `shell:` permissions were therefore unused privilege: a webview compromise (e.g. XSS in a UI dep) would have gained **arbitrary host command execution** via `shell.execute` with no scope restriction (no `shell` scope object was even defined). **Fix:** removed both `shell:` permissions from the capability (kept `core:default` + the two `dialog:` perms the UI actually uses). MEASURED: the build-regenerated `gen/schemas/capabilities.json` now reads `"permissions":["core:default","dialog:allow-open","dialog:allow-save"]` (shell perms gone), and the crate still builds + all tests pass — confirming nothing depended on the granted shell scope. (Plugin `init()` + the npm dep left in place to keep the blast radius minimal and avoid touching the off-limits generated ACL manifests; with no permission granted the plugin is inert.) **Dimensions confirmed clean (with evidence):** (1) **No directory-traversal / arbitrary-file primitive crossing the boundary** — the path-taking commands (`flash_firmware`/`verify_firmware`/`ota_update`/`wasm_upload`/`provision_*`) pass the webview-supplied path to `std::fs`/`espflash` to **read a firmware/wasm blob the local user themselves selected via the `dialog.open` native picker**; there is no command that *writes* to or *reads back* an arbitrary attacker-named path to the webview — `settings` read/write is confined to `app_data_dir().join("settings.json")` (fixed filename, no user path component), so no traversal sink exists. (2) **No shell-string interpolation** — every subprocess uses `Command::new(prog).args([...])` (argv vector, no shell), so the `port`/`source`/`chip`/`baud` args cannot inject a second command even though they are unvalidated (the `source` value flows only as a single `--source <value>` argv element). (3) **No SSRF-to-secret** — the `node_ip`-built URLs (`http://{ip}:8032/...`) target the local ESP32 mesh and return only device status; no credential is returned to the webview. (4) **Panic-on-input** — handlers use `.map_err(|e| e.to_string())?` throughout; the one `srv.pid.expect(...)` in `server_status` is guarded by an explicit `is_none()` early-return on the line above (unreachable), and the discovery/provision deserializers bounds-check before everyLine truncated
+- **`ruview-swarm` beyond-SOTA security + correctness review (ADR-148 drone swarm control plane; needs ADR slot 176) — 4 real fail-open / DoS bugs fixed in the NaN-state-poisoning class, each pinned fails-on-old / passes-on-new; 5 dimensions confirmed clean with evidence.** The shared theme is **IEEE-754 NaN/Inf silently defeating a safety comparison** on data that crosses the untrusted swarm-comm trust boundary (`SwarmOrchestrator::receive_peer_state` / `receive_peer_detection` accept full `DroneState`/`CsiDetection` whose f64/f32 fields deserialize with no finite-check; the integer-encoded MAVLink wire formats in `mavlink_messages.rs` cannot carry NaN, but the serde struct path can). **(1) HIGH — `failsafe::FailSafeMachine::tick` collision-avoidance + battery fail-open** (`failsafe/mod.rs:51,75`). `nearest_neighbor_dist < collision_dist_m` and `battery_pct <= rth_pct` both evaluate `false` for a NaN operand, so a poisoned peer position (→ NaN `nearest_peer_distance` via `Position3D::distance_to`) **silently disabled collision avoidance** and a NaN battery reading kept a drone Nominal — the worst failure for a physical airframe. Fixed to fail CLOSED (`!is_finite() ||` → `EmergencyDiverge` / `ReturnToHome`). MEASURED fails-on-old: `test_nan_neighbor_distance_fails_closed_to_diverge` / `test_nan_battery_fails_closed_to_rth` both returned `Nominal` pre-fix. **(2) MEDIUM — `security::geofence::Geofence::check` NaN-altitude bypass** (`security/geofence.rs:33`). A NaN `z` (altitude) with valid x/y skipped the altitude breach (`NaN < min || NaN > max` = `false`) and returned **`Safe`** through the point-in-polygon path — a silent geofence bypass. Fixed with a leading non-finite-coordinate → `HardBreach` guard. MEASURED fails-on-old: `test_nan_altitude_fails_closed` returned `Safe` pre-fix. **(3) MEDIUM/DoS — `security::antijamming::FhssRadio` `% 0` panic on empty `channels_mhz`** (`security/antijamming.rs:65,71,102`). `FhssConfig` is `Deserialize`; an empty channel list (malformed/hostile config) made `next_hop`/`current_channel_mhz`/`evasive_hop`/`tick` panic with `remainder with a divisor of zero`, crashing the radio task. Fixed with `len == 0` early-returns (benign `0.0` sentinel). MEASURED fails-on-old: `test_empty_channels_does_not_panic` **panicked** (`divisor of zero`) pre-fix. **(4) LOW — `sensing::multiview::MultiViewFusion::fuse` NaN victim-position propagation** (`sensing/multiview.rs:70`). A NaN `victim_position` passed the `is_some()` filter and propagated through the confidence-weighted average into the fused "confirmed victim" location dispatched to the swarm. Fixed by requiring finite `confidence` + finite position components (fail-closed drop). MEASURED fails-on-old: `test_nan_victim_position_dropped_from_fusion` produced a non-finite fused position pre-fix. **Dimensions confirmed clean (with evidence):** (a) **MAVLink decode panic-safety** — `SwarmNodeState::decode(&[u8;20])` `try_into().unwrap()`s are over fixed const ranges of a fixed-size array (provably infallible; no arbitrary-length `&[u8]` path exists). (b) **UWB GPS anti-spoofing is NaN-safe** — `(gps_dist - uwb_dist).abs() <= tol` already fails CLOSED on a NaN range/position (counts as inconsistent → spoof rejected), verified by reasoning + existing `test_spoofed_gps_invalid`. (c) **Bounded grid / no allocation-from-length-field** — `ProbabilityGrid::update_bayesian`/`mark_scanned` bounds-check `cx >= width || cy >= height`; `pos_to_cell` uses saturating `as u32` (Rust `as` saturates, no UB). (d) **Mesh `nearest_k` NaN-safe sort** — `partial_cmp(..).unwrap_or(Equal)` cannot panic on NaN distances. (e) **No hardcoded secrets** — `MavlinkSigner` key is constructor-injected (`[u8;32]`), nothing embedded. **Documented-not-fixed (for ADR-176, not churned to avoid test-rewrite risk):** (i) **Raft `AppendEntries` lacks the Log-Matching consistency check** (`topology/raft.rs:187`) — a follower appends leader entries on `term >= current_term` without validating `prev_log_index`/`prev_log_term`, so a malformed/byzantine leader can corrupt a follower's log (a genuine consensus-safety gap; vote tallying is also delegated to the caller per the existing `handle_message` comment). (ii) **`MavlinkSigner::verify` uses a non-constant-time tag `==` and has no replay/timestamp-window rejection** (`security/mavlink_signing.rs:64`) — the doc comment already flags the replay limitation as a known demo/test simplification. `cargo test -p ruview-swarm --no-default-features`: **117 → 123 passed, 0 failed** (+6 pins). Workspace green; Python deterministic proof unchanged (`f8e76f21a0f9852b70b6d9dd5318239f6b20cbcb4cdd995863263cecdc446f7a`, bit-exact — `ruview-swarm` is off the signal proof path).
+- **`nvsim` (ADR-089 NV-diamond magnetometer simulator) beyond-SOTA security review — two real degenerate-input findings fixed (config-induced panic/DoS + NaN-state-poisoning silent-corruption), each pinned by a fails-on-old test; determinism integrity, panic-free deserialisation, and RNG-seeding confirmed clean with evidence. Needs ADR slot 177.** Beyond-SOTA review of the standalone WASM-ready forward-only pipeline (`scene → source → propagation → NV ensemble → digitiser → MagFrame + SHA-256 witness`). The real risk surface is degenerate physical-parameter input (the scene + config are the external boundary, especially via the WASM `config_json`/`scene_json` entry points). **Finding 1 — NVSIM-DT-01 (config-induced panic / DoS, MEDIUM; `pipeline.rs:58,95`).** `dt` was derived as `config.dt_s.unwrap_or(1.0 / f_s_hz)`; an externally-supplied `f_s_hz == 0.0` makes `dt == +Inf`, `(dt*1e6) as u64` saturates to `u64::MAX`, and `(sample as u64) * dt_us` then **panics `attempt to multiply with overflow`** for `sample >= 2` (MEASURED: probe panicked at `pipeline.rs:95:30` under the debug/test profile; in `panic=abort` WASM this aborts the module, in release it silently wraps `t_us` to garbage). **Fixed** by sanitising `dt` (non-finite/non-positive → 1 µs fallback), capping the `u64` cast at `u64::MAX`, and using `saturating_mul` for the timestamp so no config can ever overflow it. **Finding 2 — NVSIM-NAN-01 (NaN-state-poisoning silent corruption, MEDIUM; funnel at `digitiser.rs::adc_quantise`).** A non-finite scene parameter (e.g. a `NaN`/`Inf` dipole **position**, `Inf` **moment**, or `NaN` loop **radius**) flows through `scene_field_at` and **bypasses the near-field clamp** — `NaN < R_MIN_M` is `false`, so the `1/r³` path is taken and produces a `NaN`/`Inf` field (MEASURED: `b=[NaN,NaN,NaN], sat=false`). At the ADC that non-finite value hit the `else` branch and **`NaN as i32 == 0`** (Rust saturating cast), emitting a frame with `b_pt=[0,0,0]` and **the `ADC_SATURATED` flag CLEAR** — a frame *indistinguishable from a legitimate zero-field reading* (MEASURED: `b_pt=[0.0,0.0,0.0] flags=0b0000`). This is the same NaN-poisoning class flagged across the calibration/vitals crates; the `propagation` module already guards its NaN paths, but the source→ADC path did not. **Fixed** at the single funnel point: `adc_quantise` now treats any non-finite input as out-of-range → clamps to code `0` **and raises the saturation flag**, so the corruption is visible downstream (the pipeline's existing `adc_sat` OR-reduction propagates `ADC_SATURATED` onto the frame). **Dimensions confirmed clean (with evidence):** (1) **Determinism integrity — clean.** The only RNG is `ChaCha20Rng::seed_from_u64(seed)` fully seeded from the caller's `u64` (grep: one `seed_from_u64`, zero `thread_rng`/`getrandom`/`SystemTime`/`Instant`/`HashMap`); Cargo.toml pins `rand`/`rand_chacha` with `default-features=false` (no OS-entropy path). Box–Muller draws from `gen_range(f64::EPSILON..=1.0)` (avoids `ln(0) = -Inf` by construction). Frame serialisation is fixed little-endian; source summation order is fixed by `Vec` order. The published cross-machine witness `cc8de9b0…93b4` (`proof::tests::proof_witness_publishes_a_known_value`) **still passes unchanged** after both fixes — the happy-path output is byte-identical, confirming the guards only affect degenerate inputs. (Attested caveat, not a finding: libm `cos`/`ln`/`sqrt` *could* differ x86↔wasm; witness is documented as x86_64-captured.) (2) **Panic-free deserialisation — clean.** `MagFrame::from_bytes` validates `len`/magic/version, then the per-field `buf[a..b].try_into().expect(...)` calls are over **fixed sub-ranges of an already-length-checked 60-byte buffer** → provably infallible, not reachable panic vectors. No `unsafe`, no `panic!`/`unreachable!` in production code; every other `unwrap`/`expect` is `#[cfg(test)]`. (3) **Div-by-zero — clean.** `dipole_field`/`current_loop_field` clamp `r_norm < R_MIN_M` (1 mm) before the `1/r³`/`1/r²` divide (finite inputs); `shot_noise_floor` guards `denom <= 0.0 → f64::INFINITY`; `vec3_normalise` guards `n < 1e-20`. (The only gap was the NaN case that *bypasses* the `r_norm` clamp — fixed at the ADC funnel above.) **Pinning tests (fails-on-old / passes-on-new, MEASURED):** `pipeline::degenerate_zero_sample_rate_does_not_panic` (panicked on old code; now finite frames), `pipeline::non_finite_scene_input_flags_frame_instead_of_silently_zeroing` (old: `flags=0b0000`; now `ADC_SATURATED` set, `b_pt` finite), `digitiser::adc_quantise_flags_non_finite_as_saturated` (old: `(0,false)` for NaN; now `(0,true)`). `cargo test -p nvsim --no-default-features`: **50 → 53 passed, 0 failed**. Workspace green; Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — nvsim is off the signal proof path). Needs ADR slot 177.
+- **`wifi-densepose-core` + `wifi-densepose-cli` beyond-SOTA security review (ADR-127 note; CLI needs ADR slot) — NaN-state-poisoning bug class does NOT originate in core (verdict: no + evidence); both crates confirmed clean on all reviewed dimensions; 4 regression pins added locking in two real DoS guards.** **Load-bearing question — verdict NO (with evidence, MEASURED).** The NaN-state-poisoning class that hit `wifi-densepose-calibration`/`-vitals`/`-geo` (a non-finite input latching into a persistent IIR/Welford/von-Mises/voxel accumulator → silent permanent feature failure) does **not** live in a shared `wifi-densepose-core` primitive: core exposes **no stateful accumulator at all** — no Welford/running-mean, no von-Mises/circular-mean, no IIR/biquad filter state, no voxel grid. Grep over `core/src` for `welford|von_mises|biquad|y1|y2|running_mean|accumulat|voxel|self.*+=` matched only the `InvalidState` *error* enum, "reset state" doc comments, and a test-only LCG — zero stateful logic (MEASURED). Each downstream crate rolls its own accumulator, so each fix is correctly local; corroborated by `wifi-densepose-calibration::Features::from_series`, which **already** filters non-finite samples and returns `Features::ZERO` (the downstream re-implementation of the fix). The only float math in core's hot path is construction-time projection (`CsiFrame::new` → `amplitude`/`phase` via `mapv`) and pure stateless `utils` functions — none persists state across frames. **Dimensions confirmed clean (with evidence):** (1) **panic-on-adversarial-input = 0** — `CsiFrame::from_canonical_bytes` (the replay/forward deserialisation boundary) returns a typed `CanonicalDecodeError` for every malformed input (truncation, bad discriminant, non-UTF-8 device id, nonzero reserved bytes, shape/payload mismatch, trailing bytes); the CLI UDP parser `parse_csi_packet` (the widest CLI attack surface — bound to `0.0.0.0` by default) returns `None` on any malformed datagram. Both proven panic-free over deterministic-LCG fuzz sweeps (new pins). (2) **`Confidence::new` rejects NaN** (`!(0.0..=1.0).contains(&NaN)` ⇒ `true` ⇒ `Err`); `compute_bounding_box`/`to_flat_array` are NaN-tolerant (f32 `min`/`max` ignore NaN). (3) **`amplitude_variance`/`mean_amplitude` panic-free on empty frames** — ndarray 0.17 `var(0.0)`/`mean()` return finite/`None` (handled), not a panic (MEASURED via throwaway probe). (4) **Unbounded-memory DoS bounded** in both deserialisers: `from_canonical_bytes` guards the `Vec::with_capacity(rows*cols)` with `rows.saturating_mul(cols).saturating_mul(16) <= bytes.len()`; `parse_csi_packet` guards `Array2::zeros` with `buf.len() < 20 + n_pairs*2` — a header lying about an enormous `rows×cols` / `n_antennas×n_subcarriers` is rejected before allocation. (5) **CLI path-traversal** in `calibrate-serve` already defended by `sanitize_room_id` (keeps `[A-Za-z0-9_-]`, caps 64 chars, with tests) on every client-supplied `room_id`/`bank`/`baseline` name that reaches a file path; bearer-auth gate + non-loopback-bind warning present. (6) **No hardcoded secrets** (`--token` read from `CALIBRATE_TOKEN` env, never embedded). **Regression pins added (fails-on-old / passes-on-new):** core `canonical_decode_oversized_shape_is_bounded_not_allocated` (MEASURED: with the saturating guard removed it panics `capacity overflow` at `types.rs:801`; passes with the guard) and `canonical_decode_never_panics_on_arbitrary_bytes`; CLI `test_parse_csi_packet_oversized_claim_is_rejected_not_allocated` (a 255×65535-pair claim ≈ 33 MB in a 2 KB datagram → `None`, never OOMs) and `test_parse_csi_packet_never_panics_on_arbitrary_bytes`. `cargo test -p wifi-densepose-core`: **35 → 37** lib tests, 0 failed; `cargo test -p wifi-densepose-cli --no-default-features`: **24 → 26**, 0 failed. Workspace green; Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — core/cli are off the signal proof path). No production code changed — review is clean-with-evidence plus pins.
+- **`homecore` foundational state-machine review (ADR-127) — one real concurrency bug fixed (state-set TOCTOU dropping/reordering `state_changed` events) + two hardening fixes (entity_id memory-DoS, service-handler panic isolation), each pinned by a fails-on-old test; event-bus lag & lock discipline confirmed clean with evidence.** Beyond-SOTA security+concurrency review of the crate every other HOMECORE module builds on (state store `state.rs`, event bus `bus.rs`, service/entity registries, the `HomeCore` coordinator), un-covered by the ADR-154–159 sweep — a bug here is high-blast-radius. **HC-RACE-01 (state-set TOCTOU, the crux — race/lost-event).** `StateMachine::set` did `get()` (releasing the DashMap shard lock) → compute the next snapshot + the no-op/`last_changed` decision → `insert()` (re-acquiring the lock) → `send()`; the read-modify-write was **not atomic** w.r.t. a concurrent writer on the same entity, contradicting ADR-127 §2.1's promise that "the writer atomically replaces the map entry." A writer that read a **stale `old`** could mis-classify a genuine transition as a no-op and **silently drop its `state_changed` event** (a missed automation trigger) or fire an event whose `new_state` duplicated the previously delivered one (a spurious trigger for any automation keyed on `old_state != new_state`). **Fixed** by holding the shard write-lock across the whole read→decide→insert→fire sequence via `entry()`/`insert_entry()` — `tx.send` is non-blocking, non-async, and never re-enters the map, so firing under the shard lock cannot deadlock and keeps global event order in lock-step with global commit order. Pinned by `concurrent_set_fires_no_duplicate_adjacent_events` (4 writers toggling one entity A/B; asserts no two consecutive fired events carry an identical `new_state` — impossible under correct serialisation; an instrumented probe observed ~93k such duplicate-adjacent events across 200 trials on the racy code, **zero** on the fix; the test fails reliably on the first trial pre-fix). **HC-EID-LEN-01 (unbounded `entity_id`, memory-DoS).** `homecore-api/src/rest.rs` parses untrusted REST path segments straight through `EntityId::parse`; with no length cap an otherwise-valid id (`a.` + many MB of `[a-z0-9_]`) was accepted, and a `POST /api/states/<giant>` would persist it into the DashMap state store (permanent growth across distinct ids). **Fixed** by rejecting ids longer than `MAX_ENTITY_ID_LEN` (255, HA-compatible) up front in `parse()`, before any per-char scan, with a new `EntityIdError::TooLong` — fail-closed at the boundary type protects every caller (REST, registry deserialize, automation). Pinned by `entity_id_length_boundary` (exactly-MAX accepted; MAX+1 and a 4 MiB id rejected — oversized parses `Ok` on old code). **HC-SVC-PANIC-01 (service-handler panic not isolated).** `ServiceRegistry::call` already ran handlers **outside** the registry lock (the `Arc<dyn ServiceHandler>` is cloned out of the read guard first → no `RwLock` poisoning, no blocking of other callers — clean), but a panicking handler unwound through `call()` into the caller's task (the task driving the engine). **Hardened** by wrapping the handler future in `AssertUnwindSafe` + `catch_unwind`, converting a panic to `ServiceError::HandlerPanicked`; the registry stays fully usable (a sibling healthy service still returns, the bad service stays registered). Pinned by `panicking_handler_is_isolated_and_registry_survives` (unwinds through `call` on old code). **Dimensions confirmed clean (with evidence, no invented issues):** (1) **event-bus bounds / lag** (the homecore-api WS lag-DoS class) — both `StateMachine` and `EventBus` use **bounded** `tokio::sync::broadcast` (capacity 4,096); a slow subscriber gets a recoverable `Lagged(n)` (drop-oldest + re-sync) while `fire_*` is non-blocking and never waits on slow receivers, so a lagging subscriber **cannot block the publisher, grow the channel without bound, or kill a fast subscriber** (evidenced by `slow_subscriber_does_not_block_publisher_or_kill_the_bus` — fire 3× capacity at an idle subscriber, publisher unblocked, bus stays live, fresh fast subscriber receives, lagged one recovers); (2) **lock ordering / lock-across-await** (deadlock) — no code path holds two of `{state DashMap, registry RwLock, service RwLock}` simultaneously, so no inconsistent-ordering deadlock can exist; every `tokio::sync::RwLock` guard in `registry.rs`/`service.rs` is used in one synchronous statement and dropped before any `.await` (`call` explicitly scopes the read guard out before awaiting the handler); the only guard held across a send is the DashMap shard lock in `set`, across a **synchronous** broadcast send — safe; (3) **panic-on-input** — no reachable `unwrap`/`expect`/index in non-test code beyond the safe `send().unwrap_or(0)` and the dead-but-harmless `split_once(...).unwrap_or(...)` fallbacks on already-validated ids. `cargo test -p homecore --no-dLine truncated
+- **`homecore-migrate` security review (ADR-165 surfaces) — one real secret-leak fix; traversal / data-loss / panic / injection dimensions confirmed clean with evidence.** Beyond-SOTA review of the Home-Assistant `.storage`/`secrets.yaml`/`automations.yaml` migrator, the two sharp surfaces being secret handling (`secrets.rs`) and untrusted-file parsing. **Finding + fix (secret-leak, `secrets.rs`):** a malformed `secrets.yaml` whose offending scalar fails a typed-tag coercion (e.g. `port: !!int <value>`) produced a `serde_yaml` error whose message **embeds the scalar verbatim** — `invalid value: string "<the-secret-value>"`. The old code wrapped that message into `MigrateError::YamlParse { source }`; the error propagates out of `read_secrets`, is `?`-returned by the `InspectSecrets` CLI path in `main.rs`, and printed to stderr by `anyhow` — **leaking a secret value despite the CLI's deliberate `<redacted>` design** (`main.rs` only ever prints keys as `<key> = <redacted>`). Fix: `secrets.yaml` parse failures now map to a dedicated redacting variant `MigrateError::SecretsParse { path, line, column }` carrying only the file path + a coarse location (from `serde_yaml::Error::location()`), never the scalar; other (non-secret) YAML files keep `YamlParse`. **Pinned** by `secrets::tests::malformed_secrets_error_never_contains_secret_value`, which asserts the rendered error **and its full `#[source]` chain** never contain the secret value and that the error is still the structured `SecretsParse` (fail-closed) — it **fails on the old `YamlParse` path** (observed leak: `... invalid value: string "s3cr3t_TOKEN_VALUE" ...`) and passes on the fix; plus `malformed_secrets_error_reports_location` (still locatable). **Confirmed clean with evidence:** *secret leakage elsewhere* — the only secret sink is the value map; `main.rs` redacts values, and the `MissingField`/`Io` paths surface only the path, never content. *Source mutation / data-loss* — **structurally impossible**: there is no `fs::write`/`fs::remove`/`fs::create`/`File::create`/`OpenOptions` anywhere in the crate; P1 reads source and writes nothing (`import-entities` is in-memory only), so re-runs are trivially idempotent and the HA source is never touched. *Path traversal* — CLI takes a `--config-dir`/`--storage` dir and joins **fixed** filenames (`secrets.yaml`, `core.entity_registry`, …); no user-controlled path component, no `..`/absolute escape beyond the user's own privileges. *Panic-on-input* — probed duplicate-key, bad-indent, tab/control-char, multi-doc, non-mapping-root, unterminated-flow, `!input` blueprint tags, deep nesting, anchors: **every** malformed/typed/truncated input **errors, never panics** (all production code is panic-free; every `unwrap`/`expect` is `#[cfg(test)]`). *Fail-closed versioning* — unknown storage `minor_version` hard-errors (no silent fallback to an older parser). *Injection* — no SQL/shell/path interpolation; the tool emits diagnostics only and persists nothing in P1. `homecore-migrate` **19 → 21** tests (`--no-default-features`), 0 failed. Behaviour otherwise unchanged; Python deterministic proof PASS, hash unchanged (`homecore-migrate` is off the signal proof path).
+- **`homecore-recorder` security review (ADR-132 surfaces) — two real bounding fixes; SQL-injection & NaN-index dimensions confirmed clean with evidence.** Beyond-SOTA review of the HA-compat state recorder (DB persistence + history + ruvector semantic search), the crux being its DB-backed SQL-injection surface. **Findings + fixes:** (1) **Memory-DoS — unbounded `get_state_history`.** The history query carried no `LIMIT`, so a wide `[since, until]` window over a high-frequency entity (a per-second sensor ≈ 86k rows/day) would load an unbounded row set into a single in-memory `Vec`. Added a hard `LIMIT MAX_HISTORY_ROWS` (1,000,000 — generous enough never to truncate a realistic history graph, bounded enough to cap the worst case); the sibling search paths were already `k`-bounded. (2) **Disk-DoS / documented-but-missing `purge`.** The README + HA-compat table advertised `Recorder::purge(older_than)` as a capability, but **no such method existed** — i.e. no retention path at all → unbounded disk growth. Implemented a **transactional** `purge` that deletes `states` + `events` strictly **older than** the cutoff (**exclusive** boundary — idempotent, no off-by-one; a row at the cutoff instant is kept) and **garbage-collects** orphaned `state_attributes` blobs (a dedup-shared blob is dropped only once its last referencing state is gone); all three deletes run in one transaction so a mid-purge failure rolls back cleanly (no states-deleted-but-events-kept corruption). **Confirmed clean with evidence:** SQL injection — **every** query in `db.rs` uses bound `?` parameters (no `format!`/string-concat of user data into SQL); the lone `format!` builds the LIKE *pattern*, which is itself bound as a parameter with `ESCAPE '\\'` and metacharacter escaping. Pinned: a state value `'; DROP TABLE states; --` is stored/queried **literally** (table survives), and a `%`/`_` in a search query matches **literally**, not as a wildcard. NaN-index poisoning (the calibration/vitals/geo class) — **structurally impossible** here: embeddings are SHA-256 → `i32` → `f32` (an `i32` cast to `f32` is always finite, never NaN/Inf), with an all-zero-digest norm guard; probed empty-index search, empty-string query, and `k=0` — all return `Ok(0)`, **no panic**. Fail-closed write path — a removal event yields `Ok(None)`, semantic-index failure is logged not propagated (best-effort, never blocks the durable SQLite write), and `EntityId` parsing failures fall back rather than panic. **6 new pinning tests** (SQL-injection literal-storage, LIKE-metacharacter literalness, history `LIMIT`, purge exclusive-boundary, purge attribute-GC-keeps-shared, purge old-events): `homecore-recorder` **19 → 25** (`--no-default-features`) / **25 → 31** (`--features ruvector`), 0 failed; the purge-boundary test is a true pin (fails deleting 2 rows under an inclusive cutoff, passes deleting 1 under the exclusive cutoff). Behaviour otherwise unchanged; Python deterministic proof unchanged (recorder is off the signal proof path).
+
+### Added
+- **ADR-184 / ADR-185 / ADR-186 / ADR-187 decision records added under `docs/adr/`** (indexed in the ADR README, count corrected to 193 — commit `cca5bd811`). **ADR-184** (PyPI Trusted Publishing, completes ADR-117) — Proposed; its CI migration has landed but is pending pypi.org registration (see Changed). **ADR-185** (P6 Python bindings for AETHER/MERIDIAN/MAT) and **ADR-186** (training progress API, refs #1233) are **Proposed only** — decision records for work not yet implemented on this branch. **ADR-187** (archive/v1 deprecation + model-weights honest labeling) — Accepted and implemented (see Deprecated).
+- **ADR-263/264/265: deep review of the RuView npm surface (`@ruvnet/ruview`, `@ruvnet/rvagent`, `@ruv/ruview-cli`) with optimization strategies recorded as ADRs.** ADR-263 reviews the published `@ruvnet/ruview@0.1.0` harness: fail-open `claim-check` on empty input (HIGH), `spawnSync` head-of-line blocking of the MCP stdio server during long `verify`/`calibrate` runs (HIGH), optionalDependencies tripling the cold `npx` install for a code path that never uses them (MEASURED, `npm i` in a clean prefix: 4 packages / 620 kB / 71 files default vs 1 package / 172 kB / 22 files with `--omit=optional`), 1 MiB `maxBuffer` truncation risk, `python -c` port-interpolation surface in `node_monitor`, hardcoded MCP server version, duplicated skill payload — optimizations O1–O8. ADR-264 reviews `@ruvnet/rvagent@0.1.0` + the private CLI **against the published registry tarball**: `exports.require` → nonexistent `dist/index.cjs` (HIGH, every CJS consumer breaks), 44 dead source-map files = 62,698 B of the 188 kB unpacked payload pointing at unshipped `../src` (MEASURED), stdio-only server described as "dual-transport" (CLAIMED capability), mixed dot/underscore tool naming, double Zod validation + hand-duplicated advertised schemas, 2-fd leak per training job, unbounded request body in the unwired HTTP scaffold, dead `detectCogBinary` candidate list, `ruview` bin-name collision — optimizations O1–O9. ADR-265 adds the cross-cutting distribution layer: an `npm-packages.yml` CI matrix (tests + pack-content/size gate + tarball-install smoke test — none of the three packages currently has any CI, and `ci.yml` pins Node 18 against `engines >= 20`), publish-from-CI-only with `npm publish --provenance`, version single-sourcing from package.json, bin/namespace ownership (the `ruview` bin belongs to `@ruvnet/ruview`), and claim-check enforcement on package READMEs/descriptions. Docs only — no runtime code changed; the findings are the work orders for the follow-up PRs.
+- **ADR-131 §11–§12: HOMECORE-UI wired to a real backend — single-origin BFF gateway + production front-end (no mock in prod).** Implements the §11 wiring decision so the dashboard stops rendering fabricated data. **Front-end (DONE + verified under Node):** `api.js` rewritten so every data accessor is async and calls the §11.2 gateway routes; the in-browser mock is demoted to a **dev-only fixture** reachable only via `?demo=1`/`HOMECORE_UI_DEMO` (§2.2); all ten panels now `await` and render a **typed empty/error state** on upstream failure (no mock fallback in production) — 3 panels converted by hand, 7 via a parallel agent swarm. **New `homecore-server` BFF gateway (`src/gateway.rs`, compile-pending — no Rust toolchain in the authoring env):** promotes `homecore-server` to the single origin (§2.1); adds `/api/homecore/*` + `/api/cal/*` merged into `build_app`, with `reqwest` + CLI/env flags (`--calibration-url`/`--calibration-token`/`--apps-dir`/`--gateway-timeout-ms`). Real handlers: calibration **reverse-proxy** (W2), `GET /api/homecore/rooms` with the §11.3 **RoomState adapter** (`breathing`→`breathing_bpm`, `heartbeat`→`heart_bpm`, `None`→`null` preserving not-trained-vs-withheld, injected `anomaly.threshold`/`room_id`), **COG supervisor** over `/var/lib/cognitum/apps/` (W4), and **appliance metrics** from `/proc` + TCP service probes (W6); SEED-device/appliance routes (seeds/federation/witness/privacy/settings/automations/events-history/hailo/tokens — W3/W5) return a typed `503 upstream_unavailable` and the UI shows error states. **Tests:** front-end **5 files green** — import-graph, boot, render-smoke (22), interaction (3), and a **new prod-errors suite (13)** that runs with demo OFF + gateway unreachable and proves every panel renders an error state, never mock, never throws (it caught + fixed a real unhandled-rejection in the events automation builder). **Gateway compiled, tested, and run on Rust 1.89:** `cargo test -p homecore-server --no-default-features` = **12/12 pass** (6 gateway + 6 UI mount); the binary was **run live** — `GET /api/homecore/appliance` returns real `/proc` metrics + TCP service probes, unauth → `401`, `cogs` → `[]` (no apps dir), SEED-tier → typed `503`, and against a mock calibration upstream the `/api/cal/*` proxy passes through (`200`) and `GET /api/homecore/rooms` adapts `RoomState` to the UI shape (`breathing`→`breathing_bpm`, `heartbeat:null`→`heart_bpm:null`, injected `anomaly.threshold`/`room_id`). **Live testing caught + fixed a real bug** — a double-`v1` segment in the `/api/cal/*` proxy URL. **Remaining (intrinsic, not an env limit):** W3/W5/W6-Hailo/federation depend on services/hardware **not in this repo** (recorder/automation HTTP wrappers, real SEED nodes, Hailo stat source), so they return honest `503`s rather than fabricate data; W1/W2/W4/W6-appliance are functional now. ADR-131 §10/§12.1 updated with per-wave status.
+- **ADR-131: HOMECORE-UI — the complete operational dashboard for the two-tier Cognitum stack, served by `homecore-server` at `/homecore`.** A zero-dependency, no-build-step vanilla TS/JS + CSS frontend (the `rufield-viewer` "Axum + vanilla-JS" pattern) that extends the Cognitum Appliance shell as a first-class nav section (Framework | Guide | Cog Store | **HOMECORE** | Status). **Complete, not a scaffold** (per the ADR's revised §2/§7): all **10 panels** ship fully built and rendered — §4.1 System Dashboard (v0 Appliance health strip + SEED fleet grid + ESP32 summary + COG status row + event-bus sparkline), §4.2 SEED Detail (vector store / witness chain / 5 onboard sensors / reflex rules / cognitive-fragility / ingest packet-type), §4.3 SEED Fleet Map (Appliance→SEED→ESP32 hierarchy, ESP-NOW mesh, cross-SEED fusion badges, ADR-105 federation), §4.4 Entity & State Browser (domain-grouped, **live WebSocket `subscribe_events` patching — never polls**, first-class provenance badges, keyword filter, context-causality slide-over), §4.5 RoomState/Sensing (mixture-of-specialists), §4.6 COG Management + App Registry, §4.7 Calibration Wizard (5-step baseline→enroll→train→verify), §4.8 Event Bus + Automation builder, §4.9 Witness/Audit log (two-tier SHA-256 + Ed25519 timeline, privacy-mode banner, pagination, export), §4.10 Settings. **Design system is the exact production Cognitum palette** (`tokens.css` carries `--cyan #4ecdc4` … `--r 10px` verbatim, §3.1) so there is no visual seam with the Cog Store (§3.3 invariant). **§6 UX invariants enforced in code and pinned by tests:** tier-origin provenance is always-visible (never collapsed); `stale`/`vetoed` flags and the kNN fragility score are prominent (amber/red tint + banners, never grey-on-grey); a `null` specialist renders "Not trained / calibrate to enable" **visually distinct from** veto-`withheld` (rendered as explicitly withheld, never zero) **distinct from** an error; all IDs/hashes/endpoints/payloads use `--mono`; Hailo-sourced COGs (`arch: hailo10`) are visually distinguished from CPU-only (`arch: arm`). **Wiring:** `homecore-server` gains a `--ui-dir`/`HOMECORE_UI_DIR` flag and mounts the assets via `tower-http` `ServeDir` at `/homecore` alongside the unchanged HA-compat `/api` surface (new testable `build_app()`), with **5 Rust integration tests** (`#[cfg(test)] mod ui_tests`, `tower::oneshot`) asserting index / design tokens / all-10-panels are served, the API coexists, and an empty `--ui-dir` disables the mount. **JS test + benchmark suite (`ui/`, runs under plain `node`, no npm install): 24 checks / 0 failed** — an import/export graph verifier (15 modules consistent), a DOM-shim render-smoke that *executes every panel* (21 checks: ui helpers + mock contracts + all 10 panels render without throwing), and an interaction suite (3 checks: live WS state-patch, ws.js handshake/parse, calibration backend contract). **Benchmark:** total bundle **136.8 KB uncompressed across 18 files — ~37× smaller than HA's ~5 MB Lit bundle** (the ADR-126 §1.1 foil), slowest panel **1.5 ms/cold-render**. **Honest scope (§7.1):** the live HOMECORE REST API (`/api/config|states|services`) and the WebSocket `subscribe_events` feed are driven for real; panels whose backing service is **not** in this binary (SEED HTTPS API, calibration ADR-151, ADR-105 federation) render against a **contract-conformant mock layer flagged with a DEMO banner** and swap to live the moment those endpoints land — no mock data is ever presented as real. **Not verified in this environment:** the Rust crate was edited and the integration tests written but **not compiled/run here** (no Rust toolchain present); `cargo test -p homecore-server` + `cargo build` must be run on a Rust host before merge.
+- **ADR-175: int8 quantization of the WiFlow-STD "half" pose model — MEASURED fp32-vs-int8 accuracy/size trade-off (honest negative).** Sub-deliverable 8.2 of the benchmark/optimization milestone, and the reading of the SOTA brief's "one untested edge lever" (QAT-int8 on the 843,834-param half model that strictly dominates the published 2.23M model). A new committed script `v2/crates/wifi-densepose-train/scripts/quantize_half_int8.py` quantizes `half_best.pth` to int8 two ways and scores both with the **same** upstream `calculate_pck`/`calculate_mpjpe` that produced the fp32 sweep numbers, under **one locked normalization** (ADR-173 torso-diameter PCK — neck idx2→pelvis idx12, `use_torso_norm=True`, the standard MM-Fi/GraphPose-Fi convention), on the **same** seed-42 file-level 70/15/15 test split (52,560 NaN-free / 54,000 full windows). **MEASURED on ruvultra (RTX 5080, torch 2.11.0+cu128, fbgemm; clean test, torso-PCK):** fp32 = 96.62% PCK@20 / 99.47% PCK@50 / 0.008981 MPJPE / 3.351 MB (fp32-CPU reproduces fp32-GPU to 4 dp, so the int8 deltas are pure quantization, not CPU/GPU drift); **int8 static PTQ = 40.98% PCK@20 (−55.64 pp), 1.046 MB** — naive static QDQ **collapses** on this model (the brief's 2.23M "sweet spot" does NOT transfer to the 843k half model at the tight @20 threshold); **int8 QAT (3-epoch FX fake-quant fine-tune from half_best) = 67.48% PCK@20 (−29.15 pp) / 98.69% PCK@50 (−0.78 pp), 1.043 MB.** **Verdict (honest no):** int8 is **not a win** at the strict PCK@20 edge target — QAT recovers a large share of the PTQ collapse and is near-lossless at the loose PCK@50 (coarse localization survives int8, fine does not), but a **3.2× size win at −29 pp PCK@20** is a bad trade when the half model already fits edge flash at fp32 → **keep fp32/fp16 on the edge for now.** **Disclosed gap:** the QAT *fake-quant* val PCK@20 reached 83.45% but the *converted* int8 model scores 67.48% — a real ~16 pp `convert_fx` gap (fbgemm int8 kernels ≠ straight-through estimate, esp. the axial-attention einsum/softmax); we report the converted-int8 number, not the fake-quant proxy. **MEASURED:** every table number + the PTQ collapse + the QAT partial recovery + the conversion gap. **CLAIMED/not done:** ONNX/TFLite export, on-edge-SoC latency/energy (int8 measured on x86 fbgemm — size transfers, latency does NOT), mixed-precision keeping attention fp32, longer/better-tuned QAT. **Honest limitations:** single in-domain eval split (no cross-environment split), x86-int8 not edge-SoC-int8, lightly-tuned QAT. Additive only — no production Rust or signal-pipeline change; Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — off the signal proof path).
+- **Metric-locked PCK/MPJPE accuracy harness — resolves the PCK-definition ambiguity (`wifi-densepose-train`, needs ADR slot 173).** The SOTA brief (`docs/research/sota-nn-train-benchmark-brief.md` §1, §3.1, §4) found the single biggest threat to any "beyond-SOTA" claim is **metric ambiguity**: three PCK@20 figures (96.09% WiFlow-STD image-normalized, 81.63% AetherArena torso-PCK, 61.1% GraphPose-Fi standard PCK) cannot be lined up because each silently uses a different normalization — the project was retracted twice over this (a withdrawn "92.9%" used *absolute* pixels, not torso). New `src/accuracy.rs` makes the normalizer **explicit, selectable, and carried with every reported number**: a `PckNormalization` enum (`TorsoDiameter` = standard MM-Fi/GraphPose-Fi hip↔hip; `BoundingBoxDiagonal` = looser WiFlow-STD image-normalized; `AbsolutePixels(threshold)` = the retracted convention, included so historical numbers are reproducible and clearly labeled non-comparable); one canonical `pck_at(pred, gt, vis, k, normalization)` reusing the `metrics_core` geometric primitives (hip distance, bbox diagonal — no duplicate kernel); `mpjpe(pred, gt, vis)` (2D/3D, mm); and a self-describing `PoseAccuracy { pck_at: BTreeMap<u8,f32>, mpjpe, normalization, n_keypoints, n_frames }` returned by `accuracy_report(frames, ks, normalization)` so an **unlabeled PCK number is structurally impossible**. **17 hand-computed deterministic tests** (no GPU, no datasets) prove the harness arithmetic: perfect→PCK=1.0/MPJPE=0; all-just-outside→0.0; half-in-half-out→0.5; the **key proof** that identical predictions score 0.50 (torso) / 1.00 (bbox) / 0.75 (abs) under the three normalizations (the ambiguity is real and the definitions are distinct); MPJPE 2D/3D fixtures; and graceful degenerate handling (zero torso, empty frames, NaN coords — no panic, never a false-perfect). **This is measurement infrastructure, not an accuracy claim** — the tests prove the harness is correct, not that any model is good. `wifi-densepose-train` lib 191→206, `test_metrics` 12→14, 0 failed. Python deterministic proof unchanged (off the signal proof path).
+- **CI bench-regression guard (`.github/workflows/bench-regression.yml`) — wires the v2/ criterion benches into CI as a real, hard-failing COMPILE-VERIFY gate + an informational fast-run; caught + fixed one already-bit-rotted bench (benchmark/optimization milestone sub-deliverable 8.3; needs ADR slot 174).** The v2/ workspace ships **26 criterion benches across 18 crates** (e.g. `nvsim/pipeline_throughput`, `wifi-densepose-ruvector/{ann,sketch,fusion}_bench`, `wifi-densepose-signal/{signal,dsp_perf,features,calibration,aether_prefilter,cir}_bench`, `wifi-densepose-mat/detection_bench`, `wifi-densepose-nn/{inference,native_conv,onnx}_bench`, `wifi-densepose-engine/engine_cycle`, …) but, because benches are **not** part of `cargo test`, nothing in CI compiled them — so they silently rot when a public API they call changes. **Proof this matters (MEASURED):** running the new gate on the current tree immediately caught `wifi-densepose-mat/detection_bench` failing to compile (`E0063: missing field last_rssi in initializer of SensorPosition` — the struct gained a field, the bench was never updated); fixed in this change (`last_rssi: None`, the simulated-zone convention) and re-verified (`cargo bench -p wifi-densepose-mat --no-default-features --bench detection_bench --no-run` → `Finished`, Executable produced). **HONEST SCOPE — what gates vs what is informational:** (1) `bench-compile` (HARD GATE) runs `cargo bench --workspace --no-default-features --no-run` (compile + link every default-feature bench, no measurement) plus a `--features cir` compile of the gated `cir_bench` — a deterministic, real regression guard against bench bit-rot; (2) `bench-fast-run` (INFORMATIONAL, `continue-on-error: true`, NEVER gates) runs a curated pure-CPU subset (`nvsim/pipeline_throughput`, `ruvector/{sketch,fusion}_bench`) in criterion quick-mode (1s warm-up / 2s measure / 10 samples), targeted per-`--bench` (the crates' libtest lib targets reject criterion flags), and uploads the logs as an artifact. **No timing-regression gate, by design and stated in the workflow header:** wall-clock on shared GitHub runners varies 2-3x run-to-run, so a hard threshold or a cross-runner `criterion --baseline` compare would manufacture false failures; that becomes honest only on a frequency-pinned self-hosted runner (documented as the re-add condition). The `crv`-gated `ruvector/crv_bench` is deliberately NOT compiled by the gate because its crates.io dep `ruvector-crv 0.1.1` currently fails to build on stable (upstream E0308 in its own `stage_iii.rs`) — noted in-workflow with the re-add condition. Checkout is `submodules: recursive` (the workspace path-deps `vendor/rufield`) and installs the Tauri/GTK dev libs like `ci.yml`'s rust-tests job (a `--workspace` bench link pulls the whole graph). **MEASURED locally (Windows, `--no-default-features`):** `nvsim`, `wifi-densepose-ruvector` (sketch/fusion/ann), `wifi-densepose-signal/cir_bench`, `wifi-densepose-mat/detection_bench` (post-fix), `wifi-densepose-vitals/vitals_bench`, and `ruview-swarm/swarm_bench` all compile + the fast subset runs (sample baseline: `nvsim pipeline_run/d1/256` ≈ 55 µs, `d16/1024` ≈ 315 µs; `ruvector sketch_hamming` ≈ 3-7 ns vs `float_l2` ≈ 63-371 ns). The full `--workspace` `--no-run` could **not** be fully validated on Windows (Tauri-`desktop` needs GTK, `candle-core` fails on MSVC, `swarm_bench` LTO-links OOM under parallel pressure) — those are Windows-env artifacts that build in the Linux CI runner (each affected bench was confirmed to compile standalone here). No baseline JSON is committed (a cross-runner baseline would be dishonest). Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — off the signal proof path).
+- **RuField `rufield-viewer` live-ingest mode — closes the RuView↔RuField visual loop (ADR-262 surfaces).** The dashboard gains `--source live --upstream <RuView-URL>`: it consumes RuView's `/ws/field` SSE (falling back to polling `/api/field`), **verifies every event's ed25519 provenance receipt on ingest** (`is_fusable`) — forged/tampered events are flagged ✗ and **never fused** into trusted inferences — and renders real RuView `FieldEvent`s through the same room-state/privacy-badge/fusion-graph/receipt path the synthetic mode uses (wire-compatible by construction: both sides use `rufield_core::FieldEvent` serde). **Strict banner honesty:** a single `BannerState` shows `SYNTHETIC` / `LIVE — <upstream>` / `DISCONNECTED — <upstream> unreachable`, mutually exclusive — never SYNTHETIC while showing live data or vice versa; live mode returns **409** on `/api/run` rather than fabricate a synthetic run, and starts DISCONNECTED until first verified contact. Default stays synthetic. 26 tests / 0 failed. `ruvnet/rufield` `crates/rufield-viewer`; `vendor/rufield` submodule bumped.
+- **ADR-262 P3 — live RuField surface: RuView's running sensing-server now speaks RuField on `/api/field` + `/ws/field`.** Wires the P1 `wifi-densepose-rufield` bridge into the live `wifi-densepose-sensing-server` (the bridge is the only added coupling, ADR-262 §5.4). A new `src/rufield_surface.rs` module (kept out of the 8k-line `main.rs`) holds a `FieldSurface` with a **dedicated ed25519 `Signer`**, a bounded ring buffer of recent signed events (`FIELD_RING_CAPACITY = 64`), and the `/ws/field` broadcast topic; it exposes `GET /api/field` (latest signed `FieldEvent`s + signer pubkey + a `dev_signing_key` flag) and `GET /ws/field` (per-cycle stream, mirroring `/ws/sensing`), plus a standalone `router()` for isolated testing. **Tap:** at the ESP32 governed-trust cycle (`main.rs` `observe_cycle` ~`:5886` / `SensingUpdate` build ~`:5938`), `emit_rufield_event` joins the cycle's real `SensingUpdate` (features/classification/signal_field) with the engine's recorded `effective_class`/`demoted` trust state into a `SensingSnapshot` and surfaces a signed `FieldEvent` — **existing endpoints (`/ws/sensing` etc.) are unchanged; this is purely additive.** **Signer (defers the P2 key decision, §8 Q1):** a **standalone dev/sensing key** from `WDP_RUFIELD_SIGNING_SEED` (64-hex or ≥32-byte value), else a deterministic dev default with a logged `WARN` — reusing the `cog-ha-matter` Ed25519 key is the deferred P2 call, so P3 does not pre-empt it. **Egress privacy (fail-closed):** `network_egress_allowed` is *stricter* than `DefaultPrivacyGuard` for an unattended live surface — only **P1/P2** leave the box; P0 (raw) and P3/P4/P5 are held edge-local, so a `Derived → P4/P5` cycle **never** surfaces; no-presence cycles emit **no phantom event**. **P3 acceptance gates (`tests/rufield_surface_test.rs`, 4 integration via `tower::oneshot` + 4 module unit, 0 failed):** a well-formed **signed** event (`Modality::WifiCsi`, P2 not P1, `is_fusable` ed25519-verified, real timestamp); empty cycle → no phantom; **privacy-safety** — an injected `Derived` trust never surfaces; a mixed stream surfaces only egress-safe events. **Honest scope (ADR-262 §0/§6):** real plumbing on a **live endpoint**, **NOT accuracy** — single-link CSI with its existing caveats (no validated room-coordinate accuracy — `field_localize`), a dedicated dev signing key pending the P2 ownership decision, no accuracy claim. The win is narrowly: "RuView's live sensing now speaks RuField on `/ws/field`."
+- **ADR-262 P1 — `wifi-densepose-rufield` anti-corruption bridge: RuView WiFi-CSI sensing → signed RuField `FieldEvent`s.** A new v2 workspace member (the *single coupling point* between RuView and the standalone RuField MFS spec, ADR-262 §5.4) that **path-deps** the `vendor/rufield` submodule crates (`rufield-core`/`-provenance`/`-privacy`/`-fusion` — pure-Rust, `--no-default-features`-buildable: serde/sha2/ed25519/toml only, no tch/openblas/ndarray/candle) and **no** RuView internal crate. The bridge takes owned primitives — `SensingSnapshot` mirrors the `/ws/sensing` `SensingUpdate` (features + classification + signal_field) joined with the `TrustedOutput` trust state (`trust_class`/`demoted`/`identity_bound`) — and `snapshot_to_field_event()` emits one **signed** `FieldEvent` (`Modality::WifiCsi`, axis `[Frequency]`): a real `FieldTensor` from the feature scalars with the real `timestamp_ns`; an `Observation` whose `range_m`/`motion_vector`/`space_cell` are derived from the strongest **signal-field peak** when present (else `None` — coordinates are **never fabricated**, per the `field_localize` caveat) and `confidence` from the classification; a real `ProvenanceRef` (sha256 over the tensor bytes, `synthetic=false`) **ed25519-signed** so `rufield_provenance::is_fusable` passes. **The §3.3 privacy mapping is the critical correctness item**, implemented as `map_privacy()` mapping RuView's class onto RuField P0–P5 **by information content, NEVER by byte value** and **fail-closed**: RuView `Derived` (byte `1`, which sorts *below* `Anonymous` byte `2`) carries an identity embedding → maps to **P4** (or **P5** if identity-bound), **never P1** (the single most dangerous mapping mistake); `Raw → P0`, `Anonymous → P2`, `Restricted → P2`; a governed-engine `demoted` cycle floors the egress class to ≥ P2 with raw suppressed. **P1 acceptance gates (15 tests / 0 failed — 5 unit + 9 integration + 1 doc):** round-trip (`SensingSnapshot → FieldEvent →` serde `→` equal), `is_fusable` (verified ed25519 receipt), `RuFieldFusion::ingest` accept + `infer()` runs, **privacy-safety** (`gate_privacy_safety_derived_never_maps_to_low_privacy` — `Derived → P4/P5`, never P1; a table test over every RuView class; fail-closed demotion), and determinism (same snapshot + same signer seed → byte-identical event). **Honest scope:** this is **P1 plumbing** — a tested conversion + a safe privacy mapping. It is **not** wired into the live server (that is P3) and makes **no accuracy claim** (RuField v0.1 is synthetic; RuView's single-link CSI carries its own caveats). CI: the `rust-tests` workflow checkout gains `submodules: recursive` so the path-deps resolve. Python deterministic proof unchanged (off the signal proof path).
+- **ADR-262 (Proposed): RuField MFS ↔ RuView integration — a live `SensingServerAdapter`, a privacy/provenance bridge, MAPPED not papered-over.** Researched integration design for wiring RuField into RuView. Recommends: a thin **`wifi-densepose-rufield` bridge crate** (anti-corruption layer, path-deps on the `vendor/rufield` submodule — the `vendor/rvcsi` pattern, since rufield crates are unpublished); a **live `SensingServerAdapter`** that taps the real `SensingUpdate` emit site joined with `TrustedOutput` trust state and emits one signed `FieldEvent`/cycle (the file-based `CsiReplayAdapter` stays for offline replay); **vertical fusion composition** (ruvsense fuses *within* WiFi → one `wifi_csi` event → rufield-fusion graph fuses *across* modalities above it); and **one canonical privacy/provenance model** (RuView `effective_class` is source-of-truth, mapped to RuField P0–P5 at egress; reuse the existing `cog-ha-matter` SHA-256+Ed25519 chain for the `ProvenanceReceipt`). **Key honest finding:** RuView has **two privacy enums + three witness mechanisms across two hash algorithms** that do not map 1:1 onto P0–P5, and a real trap — RuView's `Derived` privacy byte (`1`) sorts *below* `Anonymous` (`2`) yet carries identity embeddings, so the bridge must map by **information content** (`Derived → P4/P5`), never by byte value, or it would leak identity as low-privacy P1. 4 independently-shippable phases, each with a test gate (round-trip / `is_fusable` / privacy-monotonicity / ed25519-verify). Honest scope: this is **plumbing architecture, not accuracy** — RuField v0.1 is synthetic and RuView's only real-CSI path is unlabeled replay; the ADR claims only architecture, gated by round-trip/monotonicity/signature tests.
+- **RuField `CsiReplayAdapter` — first real (non-synthetic) WiFi-CSI adapter (ADR-260 §17).** RuField now ingests **real captured WiFi CSI** instead of only the synthetic simulator. New `rufield-adapters::csi_replay` parses RuView's `.csi.jsonl` recording format (`{timestamp, subcarriers[]}`), normalizes each frame to a `FieldTensor` (`WifiCsi`, real amplitudes + real `timestamp_ns`), establishes a per-subcarrier Welford **empty-room baseline** via `calibrate()`, derives a **physically-grounded CSI-variance motion/presence proxy** (normalized MAD vs baseline → P2 motion/presence, else P1), and emits `FieldEvent`s with a **real sha256 + ed25519 provenance receipt** (`synthetic=false`). **Measured on 199 real captured frames:** 184 presence-proxy / 69 motion-proxy → fed through `RuFieldFusion` → **182 fused inferences (115 breathing, 67 person_present) from real signal.** 12 tests (9 unit + 3 integration over real-CSI fixtures), deterministic (byte-identical stream per file). **Honest caveats (stated everywhere):** it's **replay from file, not live hardware**; recordings are **unlabeled**, so the motion/presence output is a **proxy, NOT validated accuracy** (no pose, no accuracy numbers); live streaming + labeled validation remain roadmap; mmWave/thermal stay synthetic. The win is "RuField ingests real WiFi CSI and produces fused events from it." [`ruvnet/rufield`](https://github.com/ruvnet/rufield) `crates/rufield-adapters`; `vendor/rufield` submodule bumped.
+- **RuField `rufield-viewer` web dashboard — completes ADR-260 §27.9 (all §27 criteria 1–10 now PASS).** A read-only Axum + vanilla-JS dashboard (no build step — `cargo run -p rufield-viewer`) that streams the deterministic SyntheticSim→fusion camera-free room-intelligence demo: live room-state inferences with confidence, a scrolling event log where every event carries its modality + a colour-coded **P0–P5 privacy badge**, the fusion graph (supporting=green / contradicting=red per inference), and a click-to-open **provenance-receipt modal** (sha256 + ed25519 signer + verified ✓ / fusable ✓) — behind a permanent, undismissable `SYNTHETIC — simulated sensors, no hardware` banner. Endpoints `/` · `/app.js` · `/health` · `/api/run` (full deterministic JSON) · `/events` (SSE). 12 new tests. Honest scope: a read-only SYNTHETIC demo viewer, **not** a device-management console — fleet/real-adapter management is a separate later milestone. Lives in [`ruvnet/rufield`](https://github.com/ruvnet/rufield) (`crates/rufield-viewer`, repo now 7 crates / 72 tests); `vendor/rufield` submodule bumped to include it.
+- **ADR-261: RuVector graph-ANN index — a real HNSW baseline + a SymphonyQG-style quantized variant, MEASURED (honest negative).** Closes the [ADR-156 §5 #1](docs/adr/ADR-156-ruvector-fusion-beyond-sota.md) gap: the SymphonyQG (SIGMOD 2025) **3.5–17× QPS-over-HNSW** claim was CLAIMED-only because **no HNSW baseline existed to compare against**. This adds one. New pure-Rust, `--no-default-features`-buildable modules in `wifi-densepose-ruvector`: `hnsw.rs` (a correct float HNSW — Malkov & Yashunin: multi-layer NSW graph, `ef_construction`/`ef_search`, Algorithm-4 neighbour selection, **seeded-deterministic** level assignment via SplitMix64, L2 + cosine, full degenerate-case guards), `hnsw_quantized.rs` (the SymphonyQG-style variant — the **same** graph traversed by a cheap **1-bit Hamming** score over the RaBitQ Pass-2 rotated sign code, then **exact-float rerank**), `ann_measure.rs` + `benches/ann_bench.rs` (one shared deterministic planted-cluster fixture; the `ann_bench_report` test is the source of truth). **MEASURED (dim=128, N=10k, K=10, `--release`):** float HNSW = **~25× QPS over linear scan at recall ≥0.99** (the baseline this gap needed; recall@10 correctness gate ≥0.95 holds, L2 + cosine). **Honest negative:** the 1-bit quantized traversal is **too coarse to beat float HNSW at equal recall at this scale** — its best recall is **0.738**, never reaching the ≥0.90 equal-recall point, so there is **no QPS win** over float HNSW; the 3.5–17× is **not reproduced** by our 1-bit construction here. The recall gate also **caught a real index-out-of-bounds bug** in the insert path (disclosed in ADR-261 §4). Caveat: this is **our** HNSW + **our** 1-bit quant, not SymphonyQG's exact system — it tests the *direction* of the claim, with the expected crossover at large N + a multi-bit traversal code. **We did not tune to manufacture a speedup.** +20 tests (ruvector lib 131→151, 0 failed). ADR-156 §5 #1 / §8 backlog: CLAIMED → **MEASURED-direction-tested**. Python deterministic proof unchanged (off the signal proof path).
+- **ADR-261 Milestone-2: multi-bit quantized HNSW traversal + large-N scaling study — MEASURED (honest negative).** Extends ADR-261's quantized index from 1-bit to **`b`-bit-per-dimension** (`b ∈ {1,2,4}`, 16/32/64 B/node) over the Pass-2 rotated coordinates, and runs a deterministic scaling study (N ∈ {10k, 100k, 250k}) to test M1's *prediction* of a large-N crossover. **Result: no crossover at any measured (N, b), and the trend refutes the prediction.** At N=10k more bits lift the equal-recall QPS ratio (0.19×→0.46×→0.48×) and let b≥2 reach the 0.90 recall bar 1-bit missed — but quant stays slower than float HNSW at equal recall; at N=100k/250k quant recall *collapses* (b=4: 1.000→0.788→0.624, never ≥0.90) while float holds ≥0.92 (denser graph → low-bit codes can't separate near-neighbours, beam goes off-path faster than the float-distance saving repays). Caveat: our HNSW + our per-node multi-bit code, not SymphonyQG's RaBitQ-fused graph — refutes the *direction* at ≤250k, not their million-scale numbers. ruvector lib **151→156** (+5 tests; `scaling_report` `#[ignore]` produced the table). A published negative with the mechanism explained. ADR-261 §11.
+- **ADR-260: RuField MFS — the open specification for camera-free multimodal field sensing.** A common event / tensor / calibration / privacy / provenance model that sits *above* WiFi CSI/CIR/BFLD, UWB, BLE Channel Sounding, mmWave radar, ultrasound, subsonic, infrared, and future quantum sensors (each modality emits a normalized `FieldEvent` → `FieldTensor` → `FusionGraph` → `PrivacyClass` → `ProvenanceReceipt`). Published as a **standalone repo** [`ruvnet/rufield`](https://github.com/ruvnet/rufield) and vendored here as the `vendor/rufield` submodule (the `vendor/rvcsi` pattern — not a `v2/` workspace member). The v0.1 reference stack is a self-contained 6-crate Rust workspace (`rufield-core`, `-provenance` [sha256 + ed25519], `-privacy` [P0–P5 guard], `-adapters` [deterministic `SyntheticSim` across wifi_csi/mmwave_radar/infrared_thermal], `-fusion` [graph + TOML weighted-Bayes rules → 7 room-state inferences], `-bench` [deterministic runner + the §31 acceptance test]). **60 tests / 0 failed, clippy-clean.** §27 acceptance criteria 1–8 and 10 PASS; the live dashboard (9) is deferred. **All benchmark metrics are SYNTHETIC** (scored against the simulator's own ground truth — presence/breathing/bed_exit/room_transition F1 = 1.000, nocturnal_scratch 0.923 reported honestly, p95 latency ~0.01 ms, provenance coverage 100%, 0 privacy violations) — they prove the pipeline recovers known truth, **not** field accuracy; real hardware adapters (ESP32 CSI, mmWave, thermal IR) are a documented roadmap item, none validated in v0.1. The Python deterministic proof is unchanged (rufield is off the signal-processing proof path).
+
+### Security
+- **`homecore-assist` voice/intent pipeline security review — one real unbounded-utterance DoS fixed (fail-closed length bound), pinned by fails-on-old tests; command-injection / ReDoS / NaN-poisoning / intent-confusion dimensions confirmed clean with evidence (ADR-133).** Beyond-SOTA review of the HA-compat Assist pipeline (utterance → recognizer → intent → handler → action, plus the `RufloRunner`) — the untrusted-input → action path, un-covered by the ADR-154–159 sweep. **One real finding fixed.** **HC-ASSIST-01 (unbounded-utterance DoS, LOW):** both `RegexIntentRecognizer::recognize` and the semantic `recognize_scored` accepted utterances of unbounded length from untrusted callers (voice transcripts / the WebSocket `assist` command) and ran `to_lowercase()` (a full clone) + a per-registered-pattern scan (and, in the semantic path, full tokenisation + feature-hash embedding) before any bound — an allocation/CPU amplification on attacker-controlled input. The `regex` crate is **linear-time** (no catastrophic backtracking), so this was a throughput/memory DoS, not a hang. **Fixed** by a named `MAX_UTTERANCE_BYTES = 4096` (far above any real spoken command) checked at both recognizer boundaries **before** any allocation/scan; an over-length utterance **fails closed** to `Ok(None)` (no intent, no action), identical to an unrecognised phrase, so it can never be coerced into firing a handler. Legitimate commands unaffected. Pinned by `over_length_utterance_fails_closed` (an over-length utterance that *contains* a valid command resolves to `None` — would have matched on old code) and `over_length_utterance_fails_closed_semantic`. **Dimensions confirmed clean (with evidence, no invented issues):** (1) **command/argument injection** — there is **no subprocess surface**: the `RufloRunner` has exactly two impls, `NoopRunner` (no process) and `LocalRunner` (runs the local recognizer, no process); no `std::process`/`tokio::process`/`Command`/`.spawn()` on any process exists in the crate (`spawn` is a `started: bool` lifecycle flag), and `RufloRunnerOpts.{script_path,env}` are inert data **never consumed** — the live `node ruflo-agent.js` runner is genuinely data-gated/future per the doc-comments. Additionally the `entity_id` capture class `[a-z_][a-z0-9_ .]*` **excludes every shell/SQL metacharacter**, so even when an injection-shaped utterance resolves (the regex is not exact-anchored) the captured slot is a clean token — sanitisation by construction (pinned by `shell_metachars_never_survive_into_a_resolved_slot`, `runner_opts_are_inert_no_process_spawned`, `pipeline_injection_shaped_utterance_carries_no_metachars_to_service`). (2) **ReDoS** — `regex 1.12.3` (no `fancy-regex` in the tree) is a linear-time finite automaton; a classic `(a+)+$` shape on adversarial input completes in bounded time (`pathological_backtracking_pattern_completes_in_bounded_time`). (3) **NaN-poisoning** — embeddings are **structurally finite** (FNV feature-hash + guarded L2 normalise, no external float input, no unguarded division), so a crafted utterance cannot inject NaN/Inf into the cosine k-NN; cosine vs the zero vector is a finite `0.0`; empty-index `max_by` returns `None` (no panic); the NaN-safe `partial_cmp().unwrap_or(Equal)` is already in place (`embeddings_are_structurally_finite`, `cosine_with_zero_vector_is_finite_not_nan`, `empty_utterance_against_empty_index_no_panic_no_match`). (4) **intent confusion / fail-closed** — an unrecognised utterance returns `not_understood()` (no service call), a recognised intent with no registered handler also returns `not_understood()`, semantic below-threshold/empty-index falls back to regex; no default high-privilege intent, no fail-open (`pipeline_injection_shaped_utterance_fires_no_handler` evidence + existing pipeline tests). (5) **panic-on-input** — no `unwrap`/`expect`/index reachable from a crafted utterance (the one `exemplars[id]` index uses an `id` from `enumerate()` over the append-only Vec). `cargo test -p homecore-assist --no-default-features`: **29→36 passed, 0 failed** (+7); default/`semantic`: **39→48, 0 failed** (+9). Workspace green; Python deterministic proof unchanged (homecore-assist is off the signal proof path). Review notes appended to ADR-133.
+- **`homecore-automation` security review — two real DoS findings fixed (template unbounded-expansion + delay panic-on-config), each pinned by a fails-on-old test; condition-bypass / fail-closed / action-authz dimensions confirmed clean (ADR-129 §8a).** Beyond-SOTA review of the HA-compat automation engine (the execution/eval surface: triggers → conditions → actions, with user-config Jinja2 templates), un-covered by the ADR-154–159 sweep. **HC-SEC-01 (template DoS, HIGH):** a `template:` condition / `value_template` is user config and was rendered with MiniJinja's defaults — **no instruction budget, no output cap**. A single nested-loop condition rendered a **100 MB string in ~11 s on one render call** (measured) — the bfld-class unbounded expansion (MiniJinja's per-call `range()` 10k cap does **not** stop nesting). **Fixed** by enabling MiniJinja's `fuel` feature + `set_fuel(Some(1_000_000))` (the attack now fails fast ~90 ms with "engine ran out of fuel") and a 64 KiB source-length cap; legitimate templates unaffected. **HC-SEC-02 (panic-on-config DoS, MEDIUM):** `Action::Delay`/`WaitForTrigger` fed the user float straight into `Duration::from_secs_f64`, which **panics** on negative/NaN/inf/overflow — all reachable from a crafted or typo'd YAML (`delay: {seconds: -1}`, `.nan`, `.inf`, `1e308`), aborting the spawned run task (measured panic). **Fixed** by a `safe_duration_from_secs` guard that saturates (NaN/±inf/negative → `0`, matching HA's lenient "non-positive delay = no delay"; huge → clamped to ~100 yr). **Dimensions probed clean (evidence in ADR-129 §8a):** condition eval is **fail-closed** (template-render error → `false`; un-parseable `choose` branch condition → branch skipped, never silently passing); run-modes are **bounded** (Single/Restart/Queued/`max:N` — a self-triggering automation does not livelock, ADR-162 tests); templates are **read-only sandboxed** (no service-call/state-set global exposed to template scope, so a template cannot escalate to an action); no `unwrap`/`expect`/index panic reachable from a crafted config in the eval/exec path beyond the fixed `from_secs_f64`. Fails-on-old verified by reverting each fix in isolation (delay tests panic; template nested-loop test runs unbounded >60 s; oversized-source test fails). `cargo test -p homecore-automation --no-default-features`: **40 → 54 passed, 0 failed** (+14: 4 template-DoS, 1 no-regression render, 5 delay/wait + safe-duration unit). Workspace green; Python deterministic proof unchanged (homecore-automation is off the signal proof path).
+- **`cog-ha-matter` witness/manifest crypto review — engine-class signed-digest collision confirmed ABSENT (length-prefixing already correct); domain-separation tag ADDED + `verify_strict` HARDENED; key-handling & verify-before-trust confirmed clean (ADR-116 §2.2).** Beyond-SOTA crypto+security review of the Cognitum/HA-Matter bridge's SHA-256 + Ed25519 witness chain — the exact signing chain ADR-262 P2 proposes to reuse — un-covered by the ADR-154–159 sweep. **Top-priority check: the sibling `wifi-densepose-engine` bug class (unframed boundary-to-boundary concatenation of operator-influenceable strings into a signed/hashed digest).** Result reported honestly: **that bug class is ABSENT here** — `witness::canonical_bytes` already length-prefixes the two variable-length operator-influenceable fields (`kind_len:u32-be ‖ kind`, `payload_len:u32-be ‖ payload`) over fixed-width `prev_hash[32] ‖ seq:u64-be ‖ ts:u64-be`, an injective encoding (proven pre-existing by `canonical_bytes_length_prefixing_prevents_ambiguity`), and `witness_signing::sign_event`/`verify_signature` sign/verify the **identical** bytes the hash chain commits to (no separate unframed concatenation). The manifest `binary_signature` (Ed25519 over the fixed 64-hex-char `binary_sha256`) is signed **at build time by the Makefile**, not in-crate, and over a single fixed-length value — no in-crate manifest-signing concatenation surface. **Two real hardening gaps fixed, the first pinned by fails-on-old tests:**
+  - **CHM-WIT-01 (missing domain-separation tag, LOW) — ADDED.** The engine review's prescribed fix is "domain-tag **+** length-prefix"; the length-prefix half was present, the **domain tag was absent**. The witness SHA-256 preimage / Ed25519 message carried no tag distinguishing it from any other signing context that shares key infrastructure — notably the manifest `binary_signature`, the very chain ADR-262 P2 reuses. **Fix:** prepend a versioned, NUL-terminated `WITNESS_DOMAIN_TAG = b"cog-ha-matter/witness-event/v1\x00"` to `canonical_bytes` (the doc-comment already anticipated a leading version migration). Cross-protocol separation now holds: a witness signature can never be replayed as a message for another Ed25519 context. **Witness-bytes change by design** (prior on-disk witness hashes/signatures invalidated, like the engine fix) — verified safe: **no in-repo crate consumes cog-ha-matter's witness bytes/signatures programmatically** (all references are doc-comment mentions; the crate is self-contained, no `use cog_ha_matter::` anywhere). Pinned by `canonical_bytes_is_domain_separated`, `canonical_bytes_starts_with_domain_tag_then_prev_hash`, `witness_preimage_cannot_collide_with_a_bare_manifest_digest` (witness.rs) and `signature_commits_to_domain_tag_not_bare_fields` (witness_signing.rs — a signature over the **un-tagged** field concatenation must NOT verify); the domain-separation guard **FAILED on the reverted un-tagged encoding** ("canonical message is not domain-separated").
+  - **CHM-WIT-02 (permissive Ed25519 verification, LOW) — HARDENED to `verify_strict`.** For a tamper-evident **audit** chain the signature is the attestation, so `verify_signature` now uses `VerifyingKey::verify_strict` (rejects non-canonical encodings + small-order public keys per RFC 8032) instead of the permissive `Verifier::verify` — giving auditors the "one canonical signature per event" property they rely on when comparing/deduplicating signed records. Not a forgery fix (the public key is caller-pinned, never parsed from the event), reported at true LOW severity. Guarded by `verify_uses_strict_path_and_pins_caller_key`.
+  - **Dimensions confirmed clean (with evidence, no invented issues):** (1) **verify-before-trust + key-pinning** — `verify_signature` takes the verifying key as a **caller-supplied parameter** (the Seed's known key), never reads a key from the event/manifest, so a forged event carrying its own key cannot self-attest; `WitnessChain::read_jsonl` re-derives and re-checks every `this_hash` on load (tampered bundle → `HashMismatch`) and runs a chain-level `verify()` catching reordered/spliced events (existing `verify_rejects_*`, `jsonl_parser_rejects_tampered_payload`, `read_jsonl_chain_verify_catches_reordered_events`). (2) **key handling** — the crate **never generates, stores, logs, or serializes** a signing key: `sign_event` takes `&SigningKey` by reference, the manifest struct has no key field, and the only key material in-crate is the **test-only** fixed seed (clearly documented "DO NOT use in production"); production keys come from the Seed's secure key store (out of scope, ADR-116 §key-management). No hardcoded/default/predictable production key, no key in the manifest, no world-readable key path (the crate does no key file I/O). (3) **determinism/canonicalization** — `canonical_bytes` is pure positional bytes (no HashMap iteration, no float formatting); Ed25519 is deterministic (pinned by `signature_is_deterministic_for_same_event_and_key`); the JSONL wire form is hand-rolled with **alphabetically-locked** field order (`jsonl_field_order_is_alphabetical_for_byte_stability`) and the mdns TXT records are `sort()`-ed for byte-stable advertisement — no iteration-order or float-format nondeterminism feeds any hash/signature. (4) **fail-closed parsing / DoS** — `from_jsonl_line`/`from_hex`/`hex_decode` return structured errors (never panic) on wrong length, non-hex, missing field, odd-length payload, or hash mismatch (`jsonl_parser_rejects_non_hex_hash`, `hex_decode_rejects_odd_length`, …); `main.rs` reads no untrusted files/paths (clap args only; `--print-manifest` emits a static template) — no path/injection surface. (5) **de-magic** — the witness/signing byte layout is already expressed as named widths; no bare security-relevant literals worth extracting beyond the new named `WITNESS_DOMAIN_TAG`. `cog-ha-matter --no-default-features`: **64→68 tests**, 0 failed (+3 domain-tag witness, +1 signing-layer domain-commit, +1 strict-verify key-pin; one pre-existing test renamed to assert the tag). Workspace green; Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — cog-ha-matter is off the signal proof path). Review notes appended to ADR-116 §2.2.
+- **`homecore-api` (HA-wire-compat REST + WebSocket) beyond-SOTA security review — `GET /api/` auth-gate gap FIXED + WS event-stream lag-DoS robustness FIXED; auth/traversal/injection/info-leak dimensions confirmed clean (ADR-161 / ADR-130).** Network-facing review of the HA-wire-compat API layer (remote attack surface), not covered by the ADR-154–159 sweep — same scrutiny the sibling `wifi-densepose-engine` and `-bfld` reviews got. **Two real bugs fixed, each pinned by a fails-on-old test.**
+  - **HC-API-AUTH-01 (auth-gate gap, LOW) — `GET /api/` was unauthenticated; FIXED.** Every sibling REST route (`/api/config`, `/api/states`, `/api/services`, …) calls `BearerAuth::from_headers` first, but `rest::api_root` took no headers and unconditionally returned `200 {"message":"API running."}`. HA's `APIStatusView` inherits `requires_auth = True`, so an unauthenticated/wrong-token request to `/api/` must be **401** — HA clients use this status route as a token-validation probe, and a 200 both told a bad-token client its token was good and let an unauthenticated party confirm a live endpoint. Severity is LOW (the body is a static string — no entity/state data leaks), reported at true severity, not inflated. **Fix:** `api_root` now validates the bearer like its siblings. Pinned by `api_root_rejects_missing_bearer` + `api_root_rejects_wrong_bearer` (both 200→assert-401 on old code) and guarded by `api_root_accepts_correct_bearer`.
+  - **HC-WS-LAG-01 (DoS-adjacent silent failure, LOW) — `subscribe_events` killed the event stream on a broadcast lag; FIXED.** The per-subscription task matched `Err(_) => break` on both `broadcast::Receiver::recv()` arms, but `Lagged(n)` (a slow consumer falling >4,096 events — `EVENT_CHANNEL_CAPACITY` — behind) is **recoverable**: the bus doc itself says "Lagged receivers must re-sync", and HA's WS contract keeps the subscription alive across a lag. The old code treated the first lag as fatal, so after an event burst the client's stream went **permanently silent** with no error frame — a self-inflicted event-delivery DoS under load. **Fix:** `Lagged(_) => continue` (skip the dropped window, re-sync), `Closed => break`, on both the system and domain arms. Pinned by `subscription_survives_broadcast_lag` (subscribes, floods 6,000 filtered events past the 4,096 capacity to force a `Lagged`, then asserts a subsequent subscribed event is still delivered — 5s-timeout panic on old code).
+  - **Dimensions confirmed clean (with evidence, no invented issues):** (1) **AuthN/AuthZ** — all 7 other REST handlers (`get_config`/`get_states`/`get_state`/`set_state`/`delete_state`/`get_services`/`call_service`) gate on `BearerAuth::from_headers` → `LongLivedTokenStore::is_valid` before any work; the WS handshake validates the `auth` token against the **same** store before entering the command loop and the privileged commands are unreachable pre-`auth_ok` (HC-WS-01, already fixed). Token compare is a `HashSet::contains` (content-independent timing, not the byte-`==` oracle ADR-157 §B4 fixed in hardware) — no timing-oracle finding. No route skips the gate, no result-ignored check, no default/empty token accepted (`is_valid` rejects empty internally; `from_env` is non-dev). (2) **Path traversal** — **no route maps user input to a filesystem path** (state lives in an in-memory `DashMap`); `:entity_id` is funneled through `EntityId::parse`, a strict `[a-z0-9_]+\.[a-z0-9_]+` ASCII allowlist that rejects `..`, `/`, `\`, and absolute paths. No traversal surface exists. (3) **Injection** — no SQL, no shell/subprocess, no `format!`-into-response; `call_service`/`set_state` bodies are typed `serde_json::Value` passed to the in-process service registry (matches HA). (4) **Info-leak** — `ApiError` maps to fixed status + a `{message}` derived only from typed variants; `call_service`'s `ServiceError::HandlerFailed(String)` is integration-controlled (mirrors HA surfacing the handler error), not framework internals/paths/stack-traces (no ADR-080-class leak). (5) **CORS** is an explicit allowlist (`allow_credentials(false)`, HC-05 already fixed), not `permissive()`. (6) **De-magic** — no bare security-relevant literals in this crate worth extracting (`EVENT_CHANNEL_CAPACITY` already named in `homecore`; CORS dev-default ports are documented). `homecore-api --no-default-features`: **25→29 tests**, 0 failed (+2 api-root auth, +1 api-root accept-guard, +1 WS lag-survival); workspace green; Python deterministic proof unchanged (homecore-api is off the signal proof path). Review notes appended to ADR-161.
+- **`wifi-densepose-calibration` per-room calibration review — NaN-poisoning fail-closed gap FIXED + file/path & receipt surfaces confirmed clean (ADR-151).** Beyond-SOTA correctness+security review of the ADR-151 `baseline → enroll → extract → train → bank` pipeline (the appliance-deployed per-room specialist core), un-covered by the ADR-154–159 sweep. **One real numerical-robustness bug fixed.** `Features::from_series` — the live-inference *and* training feature path — computed `mean`/`variance`/`motion` over the raw scalar series with **no non-finite guard**, so a single `NaN`/`±inf` sample (a corrupt CSI frame) produced `mean=NaN, variance=NaN` and an all-`NaN` prototype embedding. Baked into a persisted `PresenceSpecialist::threshold`/`empty_mean` at train time, that `NaN` **silently disabled presence detection** for the life of the bank (every `f.variance > NaN` and `|mean − NaN|` comparison is false → presence always reads *absent*, confidence 0), with **no error raised** — the exact "produce NaN that poisons a specialist / silently accept garbage" failure, and an asymmetry vs the meticulously NaN-guarded `geometry_embedding.rs`. **Fix at the production boundary:** filter non-finite samples before any statistic (a corrupt frame counts as no frame); a wholly-non-finite series degrades to the new `Features::ZERO`, exactly like the empty series. **Value-identical for all-finite input** — `full_loop.rs` and every existing `extract` test pass unchanged. Pinned by two fails-on-old tests (`non_finite_samples_do_not_poison_features`, `all_non_finite_series_is_zero`, both FAILED pre-fix). **Dimensions confirmed clean (with evidence, no invented issues):** (1) **file/path handling** — the crate does **zero** file/path I/O (no `std::fs`/`Path`/`File`/`read`/`write` anywhere in `src/`; only in-memory `serde_json`), so path-traversal / unbounded-read / artifact-path concerns do not exist at the crate boundary — they live in the `wifi-densepose-cli` consumer (`room.rs`), out of this crate's scope; (2) **untrusted-load** — `SpecialistBank::from_json` parse-validates shape via serde (malformed → `CalibrationError::Serde`), and per ADR-151 invariant (B) banks are local-first, never network-received; (3) **receipt/hash integrity** — the crate emits **no** hash/receipt/witness/signature (no `CalibrationReceipt` analogue), so the engine's unframed-concatenation bug class is structurally absent — nothing to mis-frame; (4) **other numerical paths already robust** — `geometry_embedding.rs` sanitizes every input + sweeps to finite (verified by its `adversarial_inputs_never_produce_nan` test); presence/restlessness/anomaly divisions are all `.max(1e-3)`-guarded; `autocorr_dominant` guards `r0 ≤ 1e-6`, `n < 16`, empty bands; `SpecialistBank::train` rejects empty anchors; anomaly requires ≥2 anchors. De-magicked the bare specialist threshold literals (breathing 0.25 / heartbeat 0.3 default min-scores, anomaly 2.0× spread / >0.5 label cutoff) into named documented consts, value-identical, pinned by `default_min_score_constants_match_prior_literals` + `anomaly_constants_match_prior_literals`. `wifi-densepose-calibration --no-default-features`: **58→62 unit tests** (+2 NaN fail-closed, +2 de-magic pins) + 1 full-loop integration, 0 failed. Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — calibration is off the signal proof path). Review notes appended to ADR-151 §6.
+- **`wifi-densepose-engine` governed-trust review — witness domain-separation gap FIXED + privacy monotonicity confirmed clean (ADR-137 / ADR-141 / ADR-032).** Beyond-SOTA correctness+security review of the security-critical composition root (the cycle enforcing RuView's privacy guarantees), not covered by the ADR-154–159 sweep. **One real witness-integrity bug fixed.** `witness_of` concatenated `model_version`, `calibration_version`, and `privacy_decision` boundary-to-boundary and left the variable-length evidence list without a count, so a string straddling a field boundary collided with a *different* trust decision — e.g. a per-room adapter id (ADR-150 §3.4, operator-influenceable) absorbing the leading bytes of the calibration epoch (`model="…cal:00a"`,`cal="b"`) yields the same witness as `model="…"`,`cal="cal:00ab"`. Two distinct privacy-relevant input tuples → one witness defeats the ADR-137 §2.7 "any privacy-relevant delta → different witness" tamper/drift audit. **Fix:** domain-tag the BLAKE3 hash (`ruview.engine.witness.v1`), write an explicit evidence count, and **length-prefix every field** (8-byte LE length ‖ bytes) — unambiguous framing regardless of contents. Witness-layout change by design (prior witness bytes invalidated); downstream consumers (`engine_bridge`, rufield) assert only witness *relationships* (`assert_ne`/`assert_eq` across runs), never absolute bytes, so nothing breaks. Pinned by two fails-on-old tests: `witness_distinguishes_model_calibration_boundary`, `witness_distinguishes_evidence_model_boundary`. **Dimensions confirmed clean (with evidence, no invented issues):** (1) **privacy monotonicity** — `effective_class` is recomputed each cycle from the active mode's floor with at most a single-step `demote_one` (clamped at `Restricted`), no cross-cycle state, proven over **all 5 modes** by `forced_contradiction_never_relaxes_class` (forced contradiction only ever raises the class byte; clean cycle == base); (2) **fail-closed** — empty cycle errors with no degenerate output (`empty_cycle_fails_closed`), single-node boundary characterized (`single_node_cycle_is_well_formed`), NaN coupling → `max(0.0)`→absent edge→at-risk (more restrictive); (3) **witness determinism** — no HashMap iteration / float formatting feeds the hash; (4) **mesh_guard** (ADR-032) — partition-risk → demotion path verified, thresholds already named documented fields. De-magicked the engine-construction literals (coherence accept gate, ADR-143 SLAM discovery + static-anchor thresholds) into named documented consts, value-identical, pinned by `engine_constants_match_prior_values`. `wifi-densepose-engine --no-default-features`: **27→33 tests**, 0 failed (+2 witness, +1 monotonicity property, +2 fail-closed boundary, +1 de-magic pin). Python deterministic proof unchanged (`f8e76f21…46f7a`, bit-exact — the engine is off the signal proof path). Review notes appended to ADR-137 (witness) and ADR-141 (monotonicity).
+- **ADR-141 BFLD privacy-bypass closed — `process_to_frame` now routes the payload through `PrivacyGate` (`wifi-densepose-bfld`).** `BfldPipeline::process_to_frame` stamped the emitted `BfldFrame` header with the active `PrivacyClass` but serialized the caller-supplied `BfldPayload` **unchanged** via `BfldFrame::from_payload`. A frame labeled `Anonymous`(2) or `Restricted`(3) therefore carried the full identity-leaky `compressed_angle_matrix` (the beamforming-angle identity surface) + amplitude/phase proxies + `csi_delta` — exactly the sections `PrivacyGate::demote` is documented and tested (`privacy_gate_demote.rs`) to strip at those classes. Because a `NetworkSink` accepts class ≥ `Derived`(1), such a frame would publish the identity surface across the node boundary despite its restrictive class byte; the class byte lied about payload content. **Fix:** after building the frame at the active class, apply `PrivacyGate::demote` to the same class — a no-op class transition that strips the sections that class forbids (research classes `Raw`/`Derived` keep the full payload). Pinned by three fails-on-old tests in `pipeline_to_frame.rs` (`…_at_anonymous_strips_identity_leaky_sections`, `…_in_privacy_mode_strips_amplitude_and_phase` — both FAILED pre-fix; `…_at_derived_preserves_full_payload` guards against over-stripping). Grade: privacy-bypass FIXED + regression-pinned.
+- **ADR-157 Milestone-1 B4 - constant-time HMAC sync-beacon tag compare (`wifi-densepose-hardware`).** `AuthenticatedBeacon::verify` compared the 8-byte HMAC-SHA256 tag with `self.hmac_tag == expected`, which short-circuits on the first differing byte and leaks, through verification latency, how many leading bytes an attacker's forged tag matched - a byte-by-byte tag-recovery oracle (~256*N trials instead of 256^N). Replaced with a hand-rolled branch-free `constant_time_tag_eq` (XOR-accumulate every byte difference into a single `u8`, no early exit, `#[inline(never)]` + `core::hint::black_box` to stop the optimizer reintroducing a short-circuit or a non-constant-time `memcmp`). **No new dependency** - ADR-157 had deferred this only to avoid adding the `subtle` crate; a fixed 8-byte compare needs none. Grade MEASURED (constant-time *construction*; micro-timing on a noisy host is a smoke check only, gated `#[ignore]`). Pinned by `tag_compare_is_constant_time_shape` (equal/first-differ/last-differ/all-differ/length-mismatch + an end-to-end `verify()` last-byte tamper), proven to fail on a last-byte-skipping constant-time bug. ADR-157 §8 B4 -> RESOLVED.
+- **ADR-080 open HIGH findings closed on the Rust `wifi-densepose-sensing-server` boundary (ADR-164 G11).** The QE sweep's three HIGH findings — XFF-spoofing bypass, leaked stack traces, JWT-in-URL (CWE-598) — were logged against the Python v1 API and never re-verified against the shipped Rust sensing-server; the HOMECORE/M7 sweep (ADR-161) covered `homecore-server`, not this crate.
+  - **#2 leaked internal errors (the one live exposure) — FIXED.** Six handlers in `main.rs` serialized the internal error `Display` straight into the JSON response body: `edge_registry_endpoint` returned a panicked `spawn_blocking` `JoinError` (`"task … panicked"`) in a `500`, plus the raw upstream error in a `503`; `delete_model`/`delete_recording`/`start_recording` returned `std::io::Error` strings (OS detail / path); `calibration_start`/`calibration_stop` returned the `FieldModel` error chain. New `error_response` module logs the full detail **server-side only** (with a correlation id) and returns a generic body (`{"error":"internal_error","correlation_id":…}`) — no `panicked`, no file paths, no Debug chain. 5 module tests (a leak-substring guard proven to fail on the reverted old body) + the existing handler suite.
+  - **#1 XFF-spoofing bypass — VERIFIED ABSENT, regression-pinned.** The sensing-server has no XFF-trusting control to bypass: there is no IP-based rate-limiter or IP-allowlist, and neither `bearer_auth` (token-only) nor `host_validation` (Host-header only) reads `X-Forwarded-For`/`X-Forwarded-Host` (no `forwarded`/`peer_addr`/`client_ip` anywhere in the crate). Added regression tests proving a spoofed `X-Forwarded-For` never flips an auth decision and a spoofed `X-Forwarded-Host` never bypasses the Host allowlist.
+  - **#3 JWT-in-URL (CWE-598) — VERIFIED ABSENT, regression-pinned.** `require_bearer` reads the token only from the `Authorization` header; the WebSocket handlers take no token query param and the sole `Query` extractor (`EdgeRegistryParams`) is a non-secret `refresh` flag. Added a regression proving `?token=`/`?access_token=` in the URL never authenticates while the header path still does.
+
+### Fixed
+- **`wifi-densepose-geo` numerical-robustness audit — `parse_hgt` degenerate-input panic FIXED + `haversine` antipodal NaN FIXED; pole-singularity & pointcloud NaN-state-poisoning confirmed clean (ADR-154-class sweep).** Targeted numerical-robustness audit of `wifi-densepose-geo` + `wifi-densepose-pointcloud`, hunting the proven non-finite-input-poisons-persistent-state class. **Two real bugs in `geo`, each pinned by a fails-on-old test.** (1) **`terrain.rs::parse_hgt` usize-underflow panic** — `side = sqrt(n_samples)`; for an empty / sub-2x2 buffer `side ≤ 1`, so `1.0 / (side - 1)` underflows `usize` (panic "attempt to subtract with overflow" in debug; wraps to a huge value in release → garbage/inf `cell_size_deg` that then poisons every `ElevationGrid::get` lookup). A truncated SRTM download, a 404 HTML body, or an empty response all reach `parse_hgt` — now `bail!`s with a clear error when `side < 2`. Pinned by `parse_hgt_empty_data_errors_not_panics` (panicked pre-fix) + `parse_hgt_single_sample_errors` (returned inf pre-fix) + a `parse_hgt_minimal_2x2_is_finite` guard. (2) **`coord.rs::haversine` asin-domain → NaN** — for (near-)antipodal points floating rounding can push `h.sqrt()` to `1.0 + ~4e-16`, and `asin(>1)` is NaN, silently breaking every downstream `<`/`>` distance comparison (verified: pair `(-44.4994,-178.95722)→(44.49939999,1.04278001)` yields `h=1.0000000000000004`). Fixed by clamping into `[0,1]` before `asin`. Pinned by `haversine_near_antipodal_is_finite_not_nan` (NaN pre-fix). The ±90° pole-singularity (`cos(lat)=0` division in the ENU transforms) is pinned as no-panic without changing the transform (value-identical for valid inputs). **`wifi-densepose-pointcloud` is confirmed-robust — no bug, no manufactured finding:** the only persistent auto-accumulating state (`occupancy` EMA, vitals) is fed exclusively from the integer-rssi/`sqrt`/`atan2` parser, which can only emit finite values, and the persistent state is provably self-healing even under an adversarial hand-built `CsiFrame` carrying NaN/inf amplitudes+phases (`motion_score=(NaN/100).min(1.0)→1.0`; breathing path `→0→clamp(5,40)→5.0`; tomography EMA uses only integer rssi). Pinned by `nonfinite_frame_does_not_poison_persistent_state` (injects 40 poisoned frames, asserts occupancy/vitals stay finite + the pipeline recovers) and three degenerate-voxel-fusion no-panic tests (empty/single/all-coincident). `wifi-densepose-geo --no-default-features`: 9→15 lib (+6), 8 integration unchanged; `wifi-densepose-pointcloud`: 18→22 (+4); 0 failed; workspace green; Python proof unchanged (`f8e76f21…46f7a`, bit-exact — both crates off the signal proof path).
+- **Vitals IIR filters self-heal after a non-finite CSI frame — a single NaN/inf no longer permanently kills breathing & heart-rate extraction (`wifi-densepose-vitals`, safety; ADR-021 / ADR-158 §A1).** The 2nd-order resonator in `breathing::BreathingExtractor::bandpass_filter` and `heartrate::HeartRateExtractor::bandpass_filter` latches each output `y[n]` into the filter state (`y1`/`y2`). A non-finite input — one NaN/inf amplitude residual from a corrupt CSI frame — produced a NaN `output` that was written into the state. The existing `extract()` `is_finite()` guard correctly dropped that single sample from history, **but never sanitized the poisoned filter state**, so every subsequent output stayed NaN, was rejected too, and the sliding-window history *never refilled*: the extractor went silently dead (returning `None` forever) until `reset()`. On the vitals alert path this is a safety-relevant denial of service — one bad frame and breathing **and** heart-rate monitoring stop, with no error surfaced. Fix: when `bandpass_filter` computes a non-finite `output` it now resets the IIR state to default and returns `0.0`, so the resonator recovers on the next clean frame (the `0.0` is still dropped by the caller's finite-check — no spurious sample enters history). Same class as the calibration NaN bug (ADR-154 §3) and the firmware vitals fixes (#998/#996/#987): the prior hardening guarded the *history boundary* but not the *filter-state boundary*. Pinned by `breathing::tests::nan_frame_does_not_permanently_poison_filter`, `breathing::tests::inf_mid_stream_does_not_freeze_history`, and `heartrate::tests::nan_frame_does_not_permanently_poison_filter` (all three FAIL on the pre-fix code, verified by reverting). Also de-magicked the safety-critical HR physiological plausibility band into named `HR_PLAUSIBLE_MIN_BPM`/`HR_PLAUSIBLE_MAX_BPM` consts (value-identical 40/180 BPM, pinned by `plausibility_band_constants_pinned`) and added a fabricated-vital negative (`pure_noise_is_never_reported_valid` — broadband noise never yields a clinically `Valid` HR). `wifi-densepose-vitals --no-default-features`: 55→60 lib tests, 0 failed; workspace green; Python proof unchanged (vitals is off the deterministic proof's signal path).
+- **BFLD MQTT `zone_activity` payload now JSON-escapes the zone name (`wifi-densepose-bfld`).** `mqtt_topics::render_events` emitted the zone payload as `format!("\"{zone}\"")` with no escaping, while `ha_discovery.rs` already escapes operator-controlled strings. A zone name containing a `"` or `\` produced malformed/injectable JSON on the Home-Assistant state topic (e.g. zone `a"b` → payload `"a"b"`). Added a `json_string_literal` escaper mirroring `ha_discovery::push_str_field` and applied it to the zone payload — value-identical for normal zone names (`living_room`, …). Pinned by `zone_payload_escapes_json_metacharacters` (FAILED pre-fix; round-trips through `serde_json`); the existing `zone_payload_is_json_string_with_quotes` still passes unchanged.
+- **ESP32 vitals: `n_persons` over-counted (reported 4 for one person) + presence flag flickered at close range (#998, #996).** Two firmware logic bugs in `firmware/esp32-csi-node/main/edge_processing.c`, both robustness/logic fixes — **not** validated-accuracy claims (true count/PCK vs labelled ground truth stays hardware/data-gated on the COM9 ESP32-S3).
+  - **#998 over-count — root cause + fix.** `update_multi_person_vitals()` split the top-K subcarriers into `top_k_count/2` groups and marked **every** group `active` unconditionally, so one body's multipath always reported the full `EDGE_MAX_PERSONS` (=4). New pure, host-testable `count_distinct_persons()` gates each candidate group: (1) **energy gate** — a group's phase variance must be ≥ `EDGE_PERSON_MIN_ENERGY_RATIO` (0.35) × the strongest group's, so weak multipath echoes don't count; (2) **spatial dedup** — groups whose representative subcarriers sit within `EDGE_PERSON_MIN_SC_SEP` (4) of each other are the same body. A `person_count_debounce()` then requires the gated count to hold `EDGE_PERSON_PERSIST_FRAMES` (3) consecutive frames before it's emitted, so a single noisy frame can't promote a phantom. The strongest group always counts (a present body yields ≥1). All thresholds are named, documented constants in `edge_processing.h`.
+  - **#996 presence flicker — root cause + fix.** Presence was a bare `score > threshold` compare on a noisy `presence_score` (field-observed 2.6–26.7 frame-to-frame for one stationary person), so the boolean chattered at the boundary while the score clearly indicated a person. New pure `presence_flag_update()` is a Schmitt trigger + clear-debounce: assert above `threshold`, **hold** in the dead band down to `threshold × EDGE_PRESENCE_HYST_RATIO` (0.5), and only clear after the score stays below the low threshold for `EDGE_PRESENCE_CLEAR_FRAMES` (5) consecutive frames. The score itself is unchanged (and still emitted at packet offset 20 for consumer-side thresholding). Constants named/documented in `edge_processing.h`.
+  - **Tests:** `firmware/esp32-csi-node/test/test_vitals_count_presence.c` (host C99, `make run_vitals`) — 13 cases / 22 assertions, all passing under gcc 13 `-Wall -Wextra`. Pins: single-strong-signature + multipath → count==1; two well-separated → count==2; two strong-but-adjacent → 1 (dedup); transient count spike rejected; sustained change accepted; dithering presence trace → stable flag (no flicker); genuine departure → clears within hold window. The named tuning constants are `#include`d from the real header so the test and firmware can't disagree. **Hardware-gated caveat:** these pin the decision *logic*; the exact energy/separation/hysteresis values that best match a real room vs labelled occupancy remain on-device tuning (COM9 ESP32-S3 + ground truth).
+- **Observatory 3D figure never animated — `/ws/sensing` omitted per-person `position`/`motion_score`/`pose` (#1050).** The `sensing_update` frame shipped `nodes`/`features`/`classification`/`signal_field` and a `persons[]` carrying only image-space `keypoints`/`bbox`/`zone`; the Observatory's `FigurePool`/`PoseSystem` (and `demo-data.js`'s own contract) animate each figure from `persons[i].position` (room-world `[x,y,z]`), `persons[i].motion_score` (0..100), and `persons[i].pose`, none of which the live stream emitted — so the figure sat static while signal metrics updated. **Honest scope (Case 2 — no calibrated per-person localizer exists):** a single ESP32 link does not produce calibrated room-coordinate localization or per-person skeletal pose, so the fix emits only what is *truthfully derivable*. New `field_localize` module reads the **strongest peak(s)** out of the frame's real `signal_field` grid (already built from measured subcarrier variances × measured motion-band power) and maps the peak cell to Observatory world coordinates with the **exact** `_buildSignalField` transform (`x=(ix−nx/2)·0.6`, `z=(iz−nz/2)·0.5`, `y=0`), so the figure lands on the field hotspot it stands on. `motion_score` is the measured `motion_band_power` passed through (clamped 0..100); `pose` is set **only** from a real aggregate `posture` estimate when one exists, else `None` (never a fabricated skeleton — per-person pose keypoints in room coordinates stay gated on the pose model + ADR-079 paired data). An empty / below-threshold field yields `persons: []` (no phantom person); a present person on a field with no resolvable peak keeps `position=[0,0,0]` (not invented coords) while `motion_score` stays real. `attach_field_positions` runs after the tracker step at all five broadcast sites. **No UI change required** — the Observatory already reads these fields and defaults `pose`→`'standing'` when absent. New `PersonDetection.position`/`motion_score`/`pose` fields added to both the `main.rs`-local and `types.rs` structs. Pinned by 10 tests: `field_localize` peak-extraction/coordinate-mapping/empty-field/separation unit tests + `observatory_persons_field_position_tests` (`sensing_update_emits_persons_with_field_derived_position` feeds a synthetic field with a known peak at cell (15,4) and asserts the emitted `position` = `[3.0, 0, −3.0]` within tolerance; `empty_room_yields_no_phantom_person`; `pose_is_real_when_posture_present_and_absent_otherwise`; `present_but_below_threshold_field_keeps_position_at_origin_not_fabricated`). `wifi-densepose-sensing-server --no-default-features`: bin **441→451**, 0 failed; workspace green; Python proof unchanged (off the deterministic proof path).
+- **ADR-155 Milestone-1b — metric-definition unification, the §8 backlog subset (Goals A/B/C).** Closed the two §8 metric-integrity items; every change pinned by a test, graded MEASURED. The audit (Goal A) also surfaced findings the §1 table under-counted — recorded honestly in ADR-155 §8.1, not hidden. Workspace stays green; Python proof unchanged (metrics are not on the deterministic proof's signal path).
+  - **Goal B — `test_metrics.rs` now validates the production metric, not a reimplementation.** The integration test previously asserted properties of its OWN local `compute_pck`/`compute_oks` (a test that can't catch a canonical-impl bug — both could be wrong the same way). Hoisted the canonical core (`pck_canonical`/`oks_canonical`/`canonical_torso_size`/sigmas/`bounding_box_diagonal`) into a new **un-gated** `metrics_core` module so the single definition is reachable under `cargo test --no-default-features` (the `metrics` module is `tch-backend`-gated); `metrics` re-exports it → still exactly ONE implementation. Rewrote the test to assert the production `pck_canonical`/`oks_canonical` equal **hand-computed** fixtures (`canonical_pck_matches_hand_computed_fixture` = 3/4 correct ⇒ 0.75; hip↔hip normalizer pin; zero-visible⇒0.0; OKS perfect⇒1.0; fake-Gold pin) plus a differential cross-check (`test_kernel_agrees_with_canonical`: an independent raw-threshold kernel must AGREE with canonical where torso==1.0). `wifi-densepose-train --no-default-features`: test_metrics **10→12**, 0 failed.
+  - **Goal C — divergent live-server PCK/OKS relabelled so they're never conflated with canonical.** Goal C named `training_api.rs:804` (torso-HEIGHT PCK); the audit found that file is an **orphan (not `mod`-declared, does not compile)** and the **real** live `best_pck`/`best_oks` come from `trainer.rs` — a **raw, unnormalized** `pck_at_threshold` and an **`area=1.0` fake-Gold** `oks_map` (both MISSED by ADR-155 §1, both on the claim-inflating side, both serialized as bare "PCK@0.2"/"OKS"). Torso-height/raw math is load-bearing (pixel-space, different scale axis, no `ndarray`/train dep), so the honest fix is **relabel, not force-unify**: `training_api.rs` `compute_pck` → `compute_pck_torso_height` + field/log docs; `trainer.rs` kernels documented raw/fake-Gold; `main.rs` prints `pck_raw@0.2` / `oks_map(area=1.0 proxy)`. No wire-format field or `pub`-fn renames (no silent API break). Pinned by `torso_pck_is_labelled_distinctly_from_canonical` + `pck_at_threshold_is_raw_unnormalized_not_canonical`. `wifi-densepose-sensing-server --no-default-features`: lib **450→451**, 0 failed. True unification onto `pck_canonical`/`oks_canonical` remains a tracked ADR-155 §8 item.
+- **Pre-existing `SketchBank::topk` heap inversion returned the FARTHEST sketches (found during ADR-156 §8 Pass-2 work).** The `n > k` partial-sort path in `wifi-densepose-ruvector/src/sketch.rs` used `BinaryHeap<Reverse<(dist,id)>>` (a min-heap) but its eviction logic treated the peek as the max, so it kept the k *farthest* sketches and returned them as "nearest." The shipped unit tests only exercised the `n ≤ k` fast path (≤ 3 entries), so the inversion shipped silently in ADR-084. Fixed to a plain max-heap. Pinned by `topk_heap_path_returns_nearest` (farthest-first insertion exposes it) and `tight_clusters_give_high_coverage_with_overfetch` (**measured 0.072 coverage on the old code** — effectively random — vs >0.99 fixed). Every ADR-084 top-K coverage number depends on the fixed path. MEASURED, not a no-op.
+- **ADR-154 Milestone-1 — cleared the P1 deferred backlog in `wifi-densepose-signal` (§7.4 #1, #10; partial #9, #13).** Each fix pinned by a regression test that fails on the old behaviour; every claim graded MEASURED / DATA-GATED; no fabricated thresholds. Python proof unchanged (`f8e76f21…46f7a`, bit-exact — the CIR ghost-tap guard is not on the deterministic proof path).
+  - **#1 (MEASURED metric / DATA-GATED threshold): circular phase variance.** `cir.rs::phase_variance` computed a *linear* sample variance over phase angles that wrap at ±π, so a tightly-clustered set straddling the branch cut reported spuriously HIGH dispersion — false-tripping the `> TAU` ghost-tap **guard** on real, tightly-clustered CIR taps. Replaced with Mardia's **circular variance** V = 1 − R̄, bounded **[0,1]** and invariant to where the cluster sits on the circle. The old TAU-scaled threshold is meaningless on [0,1]; re-derived against a named const `GHOST_TAP_CIRCULAR_VARIANCE_MAX = 0.99` (fires only when R̄ ≤ 0.01 — essentially uniform phase). The **metric is MEASURED**; the **threshold value is DATA-GATED** (a clean single-path ramp also sweeps the circle, so V alone can't separate clean from unsanitized without labelled frames — the default is deliberately conservative, strictly more permissive at the wrap boundary than the buggy linear guard). Fails-on-old: `phase_variance_circular_not_fooled_by_branch_cut` (old linear variance > TAU on wrap-straddling phases while circular V≈0, guard no longer trips) + `phase_variance_circular_is_bounded_and_extremal` (V∈[0,1], V≈0 identical, V≈1 uniform).
+  - **#10 (MEASURED): Welford n=0/n=1 finiteness guard pinned.** The shared `WelfordStats` (`field_model.rs`) `count < 2` guards keep `variance`/`sample_variance`/`std_dev`/`z_score` finite at the boundaries, but the n=0 case was untested (same family as the §4 divide-by-(n−1) trio). Added `welford_finite_at_n0_and_n1` — finite + documented-sentinel (0.0) at n=0/n=1. Fails-on-old proof: removing the `sample_variance` guard makes the test panic with "attempt to subtract with overflow" at the `(count − 1)` underflow (guard restored).
+  - **#9, #13 (DATA-GATED): de-magicked thresholds + boundary tests (values UNCHANGED).** Lifted the bare detection literals in `adversarial.rs` (`check`/`check_consistency`: Gini 0.8, energy ratios 2.0/0.1, consistency 0.1·mean, score weights), `coherence.rs::classify_drift` (0.85, 10) and `coherence_gate.rs` defaults (0.85/0.5/200/3.0) into named, documented consts marked EMPIRICAL DEFAULT pending labelled calibration. Added characterization/boundary tests pinning each decision at/just-below/just-above its threshold (`energy_ratio_high_boundary`, `energy_ratio_low_boundary`, `field_model_gini_boundary`, `consistency_active_fraction_boundary`, `classify_drift_*_boundary`, `*_consts_unchanged_from_literals`) so a future labelled-data retune is a visible, tested change. The operating **values were not changed**; the de-magicking + tests are MEASURED, the values stay DATA-GATED.
+- **Multistatic fusion guard was too tight for real TDM hardware (#1031).** `MultistaticConfig::default().guard_interval_us` was 5,000 µs (5 ms) with a comment claiming "well within the 50 ms TDMA cycle" — but on a real N-slot TDM schedule node `k` transmits in slot `k`, so two nodes are separated by the *slot offset*, not clock jitter. A real 2-node mesh (slots 0/1) measured an **18,194 µs** spread, so every real frame set exceeded the 5 ms guard and `fuse()` silently fell back to per-node sum/dedup — multistatic fusion never actually ran on hardware. Raised the default hard guard to **60 ms** (a full 50 ms TDMA cycle + 20% jitter headroom, derived from the slot model and documented in the field doc) and the soft guard to **20 ms** (just above the observed 18.2 ms 2-slot spread, so a normal cycle fuses cleanly with no privacy demotion). Added `MultistaticConfig::for_tdm_schedule(total_slots, slot_duration_us)` to derive the guard from a deployment's exact schedule, and a `WDP_TDM_SLOTS`+`WDP_TDM_SLOT_US` env seam in sensing-server. The honest per-node fallback remains for genuinely-mismatched frames — now the exception, not the default. Pinned by `fuse_real_tdm_spread_18194us_fuses_with_default_guard` (fails on the old 5 ms default) + `configurable_guard_rejects_too_large_spread` (guard still rejects a spread beyond one cycle).
+- **Published HuggingFace model was unloadable — RVF format mismatch (#894).** The `ProgressiveLoader` rejected the published `ruvnet/wifi-densepose-pretrained` model with the opaque `invalid magic at offset 0: expected 0x52564653 (RVFS), got 0x77455735`, then silently fell back to signal heuristics (the "10 persons for 1" garbage reporters saw). The HF repo ships `model.safetensors`, `model-q{2,4,8}.bin` (magic `0x77455735` = "5WEw"), and `model.rvf.jsonl` — none carry the binary-RVF magic. New `model_format` module **auto-detects** RVFS / safetensors / HF-quant-bin / JSONL by magic+name, returns a **typed actionable** `ModelLoadError` (lists accepted formats + the one-command convert path — never the opaque magic), and **converts** `model.safetensors` / `model.rvf.jsonl` → RVF in-memory so the published full-precision model now loads via `--model`. A `--convert-model <in> --convert-out <out>` CLI subcommand gives a one-command offline path; the silent heuristics fallback is now a loud, actionable error. **Honest scope:** the converter wires the format/load path (safetensors F32 tensors → RVF weight segment, manifest written, Layer A/B/C all succeed, weights round-trip) — it does **not** claim end-to-end pose accuracy, since the HF pose-decoder architecture differs from this crate's inference head (still data-gated in #894). Quantized `.bin` blobs are rejected with a typed error pointing at the safetensors path. Pinned by `safetensors_converts_and_loads` + `hf_quant_classifies_to_actionable_error` (both fail on the old opaque-magic path).
+
+### Changed
+- **ADR-157 Milestone-1 §5 #4 - native `wlanapi.dll` multi-BSSID throughput MEASURED on real hardware (`wifi-densepose-wifiscan`).** The ADR's prior status ("asserted but NOT implemented; live scanner is the ~2 Hz netsh shim") is now stale: `wlanapi_native.rs` already implements the real `WlanOpenHandle` -> `WlanEnumInterfaces` -> `WlanGetNetworkBssList` -> `WlanFreeMemory`/`WlanCloseHandle` FFI and `WlanApiScanner` already wires it native-first with a netsh fallback. This milestone **measured it on this box** (Intel Wi-Fi 7 BE201 320MHz, 2026-06-13): a new `benchmark_backend(backend, window)` drives each backend over the same fixed 10 s wall-clock window so netsh is timed independently (the prior `benchmark()` picked native-first and never measured netsh on a Windows box where native works). **MEASURED: native 21.42 Hz vs netsh 3.84 Hz = 5.57x** (mean 5.0 BSSIDs/scan, both paths); a separate native-only run measured 18.0 Hz. Native genuinely beats netsh - this is a real positive result, not a fabricated "10x". 50 back-to-back native scans completed 50/50 with no handle leak/degradation. Live-WLAN tests (`measure_native_vs_netsh_throughput`, `native_scans_dont_leak_handles`, `measure_native_scan_rate`) are `#[ignore]` for CI but were RUN here; `native_scan_runs_real_ffi_on_windows` is a non-ignored schema-valid pin. ADR-157 §5 #4 + §8 -> MEASURED (was ACCEPTED-FUTURE / CLAIMED-unmeasured).
+- **Mesh partition risk now demotes the privacy class and is witnessed (ADR-032).** The dynamic min-cut guard's `at_risk` signal was advisory-only (it fed the recalibration advisor). It now also contributes to the ADR-141 privacy demotion alongside fusion- and array-level contradictions: a mesh close to partitioning makes the fused belief less trustworthy, so the cycle emits at a more restricted class (monotonic — information only removed). Because `effective_class` feeds the BLAKE3 witness, a fragmenting array now shifts the witness — partition risk is auditable, not just logged. The mesh computation moved ahead of the demotion step in `process_cycle`; new `mesh_guard_mut()` exposes risk-threshold tuning. Test proves a forced-risk 3-node cycle demotes PrivateHome Anonymous→Restricted and shifts the witness vs a clean *same-topology* baseline (the only delta between the two cycles is the forced risk).
+
+### Added
+- **ADR-155 Milestone-2 — cleared the host-verifiable subset of the §8 P3 backlog in `wifi-densepose-train` (+ the pure-Rust `rf_encoder.rs`/`densepose.rs` the §3/§4 items named).** Mirrors the ADR-154 M3 cleanup discipline. **Honest enumeration first (grep, not the ADR's "~40" estimate):** the actual non-tch train/nn surface is smaller — **7 de-magicked (const + `*_consts_unchanged_from_literals` pin == prior literal), 9 boundary/characterization tests, 1 added input guard (`rf_encoder::LinearHead::try_new`) + test, 2 doc-only fixes, 1 perf item bench-first → MEASURED-INCONCLUSIVE (not shipped)**. **This is cleanup — no operating value or behaviour changed:** each lifted literal is bit-identical to its prior value, each boundary test pins CURRENT behaviour. De-magicked: `metrics_core.rs` (`VISIBILITY_THRESHOLD`/`MIN_REFERENCE_EXTENT`/`OKS_FALLBACK_SIGMA`), `ruview_metrics.rs` (`NUM_KEYPOINTS`/`VISIBILITY_THRESHOLD`/`PCK_THRESHOLD`/`MIN_BBOX_DIAG`/`MIN_DURATION_MINUTES`), `subcarrier.rs` (6 `SPARSE_*` consts), `eval.rs` (`MIN_POSITIVE_MPJPE`), `domain.rs` (`LAYER_NORM_EPS`), `virtual_aug.rs` (`BOX_MULLER_U1_FLOOR`/`MIN_ROOM_SCALE`), `rf_encoder.rs` (`SOFTPLUS_LINEAR_THRESHOLD`). **§3 `rf_encoder.rs`:** added a pure-Rust fallible `LinearHead::try_new` → typed `RfHeadError` so untrusted/deserialized checkpoint weights can be shape-validated without the `new()` panic (`new` unchanged; additive). **§4 native-conv:** `densepose.rs::apply_conv_layer` (pure-Rust naive loop) was benched (committed `benches/native_conv_bench.rs`); a bit-identical range-clamped rewrite measured ~35% faster on padding-heavy small-channel maps but ~3% *slower* on channel-heavy maps, all inside a ±20% host-noise floor — **MEASURED-INCONCLUSIVE, so NOT shipped** (no fabricated number), characterized by `native_conv_matches_reference` and honestly deferred. **Skipped honestly (not-real / already-handled):** `ablation.rs` (NaN-sort + boundaries already fixed/tested in M1), `signal_features.rs` (consts already named, n=0 tested), `mae.rs` (no bare guard literals). `wifi-densepose-train --no-default-features`: **303 passed** (was 288, +15), 0 failed; `wifi-densepose-nn --no-default-features` lib: **38** (was 35, +3). Workspace `--no-default-features`: GREEN (single clean run). Python proof **VERDICT: PASS**, hash **`f8e76f21…46f7a` UNCHANGED, bit-exact** (asserted — the metrics path is off the deterministic signal proof path). **Remaining §8 backlog stays deferred-not-dropped:** GraphPose-Fi / ONNX-INT4 / CSI-JEPA (data/model-gated), ONNX read-lock (upstream `ort`-gated), tch-gated panic sites in `proof.rs`/`trainer.rs`/`model.rs` + `metrics.rs` `*_v2` dead-code (tch-gated — need a libtorch host). **The non-tch-verifiable subset of §8 is now cleared.**
+- **ADR-154 Milestone-3 — cleared the §7.4 row #21–45 P3 backlog in `wifi-densepose-signal` (the lumped "remaining clarity/doc/magic-constant/missing-boundary-test findings across `ruvsense/*`, `features.rs`, `motion.rs`").** Honest enumeration first (grep, not the ADR's estimate): the lumped row was **~25 findings → 22 real, de-magicked across 11 modules; 6 boundary/characterization tests added; ~4 doc-only; the rest were already-handled or not-real and are reported as such** (the "row #21–45" count was an estimate — there were not 25 *distinct* magic constants left after M0–M2). **This is cleanup — no operating value or behaviour changed:** every de-magicked literal becomes a named, documented EMPIRICAL-DEFAULT const that **equals the prior literal exactly** (each module ships a `*_consts_unchanged_from_literals` pin test), and every boundary test pins **current** behaviour so a future retune is a visible, tested change. Modules touched: `motion.rs` (#18, fusion weights/normalization/adaptive-threshold consts + 5 tests), `gesture.rs` (#12, `euclidean_distance` length-mismatch `debug_assert` documenting the silent-truncation contract + DTW n=0/m=0 boundary), `longitudinal.rs` (drift thresholds 7-day/2σ/3-day/7-day/EMA + day-6/7 + zero-vector cosine), `cross_room.rs`/`multiband.rs`/`intention.rs`/`hampel.rs` (division-guard epsilons + zero-norm/zero-variance/zero-MAD boundary + `half_window==0` error path), `rf_slam.rs` (`NS_PER_DAY` + fixed-map defaults + zero-span guard), `attractor_drift.rs` (buffer/recent-window consts + documented the implicit `recent.len()≥1` divide-safety + `min_observations` off-by-one boundary), `coherence.rs` (#9 completion — variance-floor + default-decay), `calibration.rs` (#2 — `DEFAULT_MIN_FRAMES` deduped across 4 tier constructors + motion/subtract thresholds), `fusion_quality.rs` (contradiction penalty/bounds + n=0 identity), `temporal_gesture.rs` (confidence epsilon + quantization scale). **A "magic" the agents flagged that was NOT real:** an `attractor_drift.rs:301` "divide-by-zero" is unreachable (the `count < min_observations` guard guarantees `recent.len()≥1`) — documented + boundary-tested rather than guarded, per the no-behaviour-change rule. Signal crate lib `--no-default-features`: **476 passed, 0 failed, 1 ignored**; `--no-default-features --features cir`: **476 passed, 0 failed** (plain `--features cir` is unbuildable on this Windows host — the default `eigenvalue` feature pulls `openblas-src`, the same BLAS gate documented in M2 #8). Workspace `--no-default-features`: **3,275 / 0 failed** (single clean run). Python proof **VERDICT: PASS**, hash **`f8e76f21…46f7a` UNCHANGED, bit-exact** (asserted explicitly — these modules are off the deterministic PSD/Doppler proof path, and the de-magicked consts are bit-identical regardless). **This clears ADR-154's §7.4 deferred backlog to zero across M0–M3.**
+- **ADR-154 Milestone-2 — bench-first P2 perf subset + missing boundary tests (`wifi-densepose-signal`, §7.4 #5/#6/#7/#8/#14/#16/#19/#20).** PROOF discipline (ADR-154 §0): every perf item was **benched before being touched** (new committed `benches/dsp_perf_bench.rs`, criterion, this Windows box); only the one item the bench proved hot was optimized, the rest are committed MEASURED-NULLs — a benched null is the proof the micro-opt was unnecessary, the §5.1 "already amortized" pattern. Every behaviour-changing edit is pinned bit-identical (or documented-tolerance). Signal crate lib `--no-default-features`: **447 passed, 0 failed, 1 ignored**; `--features cir`: **447 passed, 0 failed**.
+  - **#20 MEASURED-HOT, optimized (bit-identical).** `compute_multi_subcarrier_spectrogram` re-planned a fresh `FftPlanner` for *every* subcarrier (via `compute_spectrogram`). Hoisted the plan + window out of the per-subcarrier loop (new `compute_spectrogram_with_plan` core; `compute_spectrogram` delegates, unchanged). **56-subcarrier: 467.88 µs → 254.75 µs = 1.84×** (window 128); **627.27 µs → 448.39 µs = 1.40×** (window 256). Bit-identical via `multi_subcarrier_hoisted_plan_bit_identical` (`f64::to_bits` of every value across all 4 window functions × {power,magnitude}). The §7.4 intro's predicted "most likely real win" — confirmed.
+  - **#5 / #6 / #7 MEASURED-NULL, left as-is.** `node_attention_weights` 181 ns (2 nodes)…848 ns (8) — sub-µs, no hot-path alloc. `tomography reconstruct` (full 50-iter ISTA, 256 voxels) 47.5 µs (16 links) / 60.4 µs (32) — the 2 voxel buffers are already alloc-once + `.fill`-reused, negligible vs O(iters·links·voxels). `pose_tracker` Kalman cycle 150 ns (17 keypoints) / 2.82 µs (170) — the "gain matrices" are fixed-size **stack** arrays, zero heap to reuse. No rewrite shipped; the committed benches prove each is not hot.
+  - **#8 MEASUREMENT-ONLY, BLAS-gated (number deferred, not fabricated).** Correction to the finding: `extract_perturbation` does **not** recompute the SVD (it projects against cached `finalize_calibration` modes); the real per-call eigendecomposition is the `eigenvalue`-feature `estimate_occupancy` (`cov.eigh()` on a 56×56 covariance). The `eig` bench is committed but `openblas-src` won't build on this Windows host ("Non-vcpkg builds are not supported on Windows" — the exact reason the project gate runs `--no-default-features`), so its µs cost must come from a Linux/BLAS box. Recorded, not estimated. Incremental SVD stays a sized future item.
+  - **#14 / #16 / #19 RESOLVED — tests added (no behaviour change).** `fft_operator_within_tolerance_of_dense_canonical56` pins the full `Cir` output of the opt-in FFT path within a documented relative tolerance of the dense path on the production canonical-56 config (τ ∈ {20,50,90} ns) — it changes the witness hash, so it must be provably *close*, not silently divergent. `refinement_terminates_at_iteration_cap_when_not_converging` (+ convergent companion) proves the LO-offset refinement terminates at exactly `max_iterations` on a non-converging input (cap, not convergence, bounds the loop; internal `…_counted` refactor returns the identical offsets). `ratio_finite_at_and_below_1e_12_epsilon` pins that the conjugate-product CSI-ratio (no division → no `1e-12` divide-guard needed) is finite + bit-exact at/below the epsilon boundary and at exact zero (where a naive `H_i/H_j` ratio is ±inf/NaN).
+- **ADR-156 §11 Milestone-2: RaBitQ unbiased distance estimator — IMPLEMENTED & MEASURED (RESOLVED-NEGATIVE on the strict-K bar).** Closes the §10.5 / §8 backlog "full RaBitQ residual-distance estimator (not just a uniform scalar code)" item — the **real** Gao & Long (SIGMOD 2024) contribution, not just sign bits. New `wifi-densepose-ruvector/src/estimator.rs`: `EstimatorSketch` carries the Pass-2 sign code (over the padded FHT length `D = next_pow2(dim)`) **plus 8 B/vec side info** (`residual_norm` + `x_dot_o = ⟨x̄, o'⟩`, 2× f32); `DistanceEstimator` computes the **unbiased** estimate `⟨o',q'⟩ ≈ ⟨x̄,q'⟩ / x_dot_o` (the random rotation makes the 1-bit code's quantization error orthogonal-in-expectation to the query, paper `O(1/√D)` bound); `EstimatorBank::topk_estimated_cosine` reranks the candidate set by the estimate instead of raw Hamming. **Zero-centroid simplification (`c = 0`) stated honestly** — the paper-faithful per-cluster centroid path (`from_embedding_centred` / `EstimatorBank::with_centroid`) is also built so the simplification is a measured choice (no centroid coverage number is reported against the cosine ground truth, because cosine-of-residual ≠ cosine-of-raw would be a metric mismatch). **Purely additive + backward-compatible** — new types only; Pass-1 `Sketch` / Pass-2 `SketchBank` / `WireSketch` wire format unchanged; all external callers (`event_log.rs`, `signal/longitudinal.rs`, `sensing-server`) use Pass-1 and are unaffected. **MEASURED strict-K coverage** (same fixture/seeds as §10: dim=128 N=2048 K=8, 64 clusters, noise=0.35, 128 queries, cosine ground truth): the estimator lifts the strict `candidate_k=K` bar **46.39% (Pass-2 sign) → 49.71% (estimator, cosine rerank)** — a real **+3.3 pp** lift, **still ~40 pp short of the ADR-084 ≥90% strict bar.** At over-fetch the estimator beats sign (candidate_k=24: **95.12%** vs 91.60%). **Honest verdict — RESOLVED-NEGATIVE: the unbiased estimator does NOT clear the strict-K 90% bar on this distribution** (the binding constraint is the 1-bit code's information ceiling, not estimator variance); the bar is still met only via the over-fetch "candidate set" pattern ADR-084 specifies, though the estimator **reduces the over-fetch factor** needed. A published negative, reported as such — no benchmark tuned to manufacture a pass. Unbiasedness pinned by `estimator_unbiased_on_fixture` (Monte-Carlo mean over 4000 rotation seeds → true inner product within tolerance); not-worse-than-sign pinned by `estimator_rerank_not_worse_than_sign`; determinism by `estimator_is_deterministic`. +12 tests in the crate (119→131). Workspace **3,228 / 0 failed** (`cargo test --workspace --no-default-features`, 162 test binaries, single clean run), Python proof **VERDICT: PASS** (`f8e76f21…46f7a`, unchanged — estimator is not on the proof's signal path). Full numbers + reproduce commands in ADR-156 §11 / ADR-084 "Pass 2b".
+- **ADR-156 §8 Milestone-1: RaBitQ Pass-2 randomized rotation + multi-bit experiment — IMPLEMENTED & MEASURED (RESOLVED-PARTIAL).** Closes the §8 "Multi-bit / Extended RaBitQ" backlog item. New `wifi-densepose-ruvector/src/rotation.rs`: a deterministic randomized orthogonal rotation `R = H·D` — **Fast Hadamard Transform** (`O(d log d)`, in-place, `1/√m`-normalized so norm-preserving) + seeded ±1 sign flips (SplitMix64 from a stored `u64` seed; identical at index + query time). Chosen over a dense `d×d` matrix (`O(d²)`, infeasible at the 65,535-d the wire format provisions for); pads to `next_pow2(d)`. Additive, backward-compatible API (`Sketch::from_embedding_rotated`, `SketchBank::with_rotation` + `insert_embedding`/`topk_embedding`/`novelty_embedding`); Pass-1 and the wire format are byte-for-byte unchanged. New `coverage.rs` single-source-of-truth top-K coverage harness (anisotropic planted-cluster fixture, cosine ground truth) backs both a `#[test]` report and the `sketch_bench` coverage table. **MEASURED (dim=128 N=2048 K=8, 64 clusters, noise=0.35, 128 queries, seeded):** at the strict `candidate_k=K` bar, rotation lifts coverage **36.13% → 46.39%**; Pass-2 reaches the **ADR-084 ≥90% bar at candidate_k=24 (~3× over-fetch)**; multi-bit Pass-3 reaches 54%/67%/74% at 2/3/4-bit (strict bar). **Honest verdict: neither rotation nor ≤4-bit multi-bit clears the strict-K 90% bar on this distribution — the bar is met only via the over-fetch "candidate set" pattern ADR-084 specifies.** No benchmark was tuned to manufacture a pass; the strict-bar gap is documented (ADR-156 §10, ADR-084 "Pass 2" section). +19 tests in the crate (100→119), workspace **3,225 / 0 failed**, Python proof VERDICT: PASS (`f8e76f21…`, unchanged — sketch is not on the proof's signal path).
+- **Beyond-SOTA `v2/crates/` sweep (ADR-154–158) + full stub-implementation push — every claim MEASURED or graded.** A 5-milestone review/optimize/secure/benchmark/validate sweep, then a verified-audit-driven push to replace every production stub with real, tested logic (no labels, no placeholders). Each fix is pinned by a test that fails on the old code; every number ships with a reproduce command. Workspace: **3,122 tests / 0 failed** (`cargo test --workspace --no-default-features`), Python proof **VERDICT: PASS** (bit-exact).
+  - **ADR-154 Signal/DSP** — revived a dead ADR-134 CIR coherence gate (canonical-56 vs ht20 mismatch meant it never ran in production: 8/8 Err → 8/8 Ok); NaN-bypass + window div0 guards; PSD FFT-planner cache (**2.0–3.1×**) + honored DTW band (**2.4–4.1×**).
+  - **ADR-155 NN/Training** — unified 7 divergent PCK/OKS metric definitions into one canonical torso-normalized source (fixed two claim-inflating bugs: zero-visible PCK 1.0→0.0, OKS fake-Gold); leak-free subject-disjoint MM-Fi split + injected-leak detector; rapid_adapt replaced fake gradients with real finite-difference; proof.rs gained a min-decrease margin + committed-hash requirement; zero-copy ORT input (**1.48×**).
+  - **ADR-156 RuVector/Fusion** — closed crafted-input DoS panics (triangulation/heartbeat); honest dimensionless GDOP = √(trace(G⁻¹)) replacing an RMSE mislabel; canonical wrapped angular distance; fuse() double-clone removed (**~2.17×** marshalling). SOTA graded: SymphonyQG (CLAIMED), multi-bit RaBitQ (near-term), GraphPose-Fi (data-gated).
+  - **ADR-157 Hardware/Sensing** — `Vec::remove(0)` O(n²) sliding windows → `VecDeque`; breathing partial-weight renormalization; IIR low-sample-rate divergence clamp. Centerpiece: a MEASURED **negative-results** audit showing the layer (802.11bf model, parsers, calibration) was already hardened — cited file:line, NO-ACTION.
+  - **ADR-158 MAT/world-model** — **unified two divergent triage engines** (the confidence-gated result was computed then discarded; gate==record now); **killed survivor count-inflation** (real RSSI localization + vitals-signature dedup, MEASURED 3→1); real ESP32/UDP/PCAP CSI ingest with honest typed `HardwareUnavailable`/`UnsupportedAdapter` errors for hardware-gated adapters (Intel5300/Atheros/PicoScenes — never fabricated CSI); real parabolic peak interpolation; real GDOP.
+  - **Soul Signature §3.6 matcher made real (`wifi-densepose-bfld`, issue #1021).** An external audit correctly found person-identification was spec-only behind a no-op `NullOracle`. Now a real per-channel weighted-cosine matcher + `EnrolledMatcher: SoulMatchOracle` (364 tests). MEASURED: same-person 1.0000 vs cross-person 0.8088; and the audit's own claim proven — on WiFi-only cardiac+respiratory channels alone two people are **not separable** (gap 0.0005). Named identity is honestly **data-gated** on the AETHER/body-resonance channel being fed by a real enrollment; no working-named-identity claim is made.
+  - **OccWorld real forward pass** — replaced `Tensor::randn` encoder/decoder stubs (which emitted trajectory priors from pure noise) with a real deterministic conv VQ-VAE forward pass (input-dependent, proven by tests that fail on the old randn) + a `weights_trained` honesty flag (false until a real checkpoint loads); pointcloud `to_gaussian_splats` 9→2 passes (**1.24×** MEASURED).
+  - **Native multi-BSSID `wlanapi.dll` FFI** (`wifi-densepose-wifiscan`) — real `WlanOpenHandle`/`WlanEnumInterfaces`/`WlanGetNetworkBssList`, **MEASURED 9.74 Hz** on Windows (vs netsh ~2 Hz; no fabricated "10×"), typed `Unsupported` off-Windows. Real Matter 1.3 manual-pairing-code field-packing (canonical 34970112332, lossless decode) replacing a lossy-modulo placeholder.
+  - **HOMECORE assistant** — real `LocalRunner` response path, real semantic intent recognizer (exact in-memory cosine k-NN; MEASURED 0.855 match / 0.106 no-match), real SQL state text-search — three always-empty stubs removed.
+- **ADR-152 WiFi-Pose SOTA 2026 intake — verified external benchmark + four Rust integrations.** A 22-source adversarially-verified survey of the 2025–2026 WiFi-sensing SOTA, with every adopted number reproduced or graded before integration:
+  - **WiFlow-STD (DY2434) reproduction (`benchmarks/wiflow-std/`)** — the external "97.25% PCK@20, 2.23M params" claim audited end-to-end: the **shipped checkpoint is REFUTED** (0.08% PCK@20 — wrong keypoint normalization, predates the published code), the released code does not run as published (6 documented defects, incl. an import that fails and an unreachable test phase), and the released dataset's final 13 files are corrupted (9,072 windows of NaN + float32-max garbage that NaN-poisons fp16 BatchNorm training). After repairing both, retraining with upstream defaults on an RTX 5080 reproduced **96.09% PCK@20 (full test) / 96.61% (corruption-free)** — claims graded MEASURED-EQUIVALENT; params (2,225,042) and FLOPs (~0.055 G) verified exactly. Full forensics in `benchmarks/wiflow-std/RESULTS.md`.
+  - **`GeometryEmbedding` (ADR-152 §2.1.2, `wifi-densepose-calibration`)** — 32-slot permutation-invariant, NaN-proof featurization of the §2.1.1 `NodeGeometry` records (centroid/spread, measured-first pairwise distances, circular azimuth stats, covariance-eigenvalue geometric diversity, per-node flags), schema-versioned for the ADR-151 P6 LoRA heads; derived `SpecialistBank::geometry_embedding()` accessor. The PerceptAlign "coordinate overfitting" defense, transplanted to per-room banks.
+  - **MAE pretraining recipe (ADR-152 §2.3, `wifi-densepose-train/src/mae.rs`)** — `MaePretrainConfig` pinning the UNSW-measured recipe (80% masking, (30,3) patches) with pure-Rust patchify/random-mask (exact counts, seed-deterministic, error-not-truncate divisibility, NaN rejection), property-tested; the consumption seam for the future ADR-150 ViT-Small encoder.
+  - **`WiFlowStdModel` Rust port (`wifi-densepose-train/src/wiflow_std/`)** — tch-gated idiomatic port of the verified spatio-temporal-decoupled architecture (grouped causal TCN → asymmetric conv stack → dual axial attention); ungated param formula asserted equal to the reference 2,225,042; 15/17-keypoint variants share weights (enables the ADR-152 §2.2(b) ESP32 fine-tune).
+  - **RuVector vendor sync + §2.6 opportunity survey** — vendor at `a083bd77f`; graded ADOPT/EVALUATE/WATCH table; crates.io bumps applied (mincut/solver 2.0.6, attention 2.1.0, gnn 2.2.0; RUSTSEC #504 audit: no pinned crate affected); top WATCH: unpublished `ruvector-graph-condense` differentiable min-cut for trainable subcarrier grouping.
+- **ADR-153 IEEE 802.11bf-2025 forward-compatibility protocol model (`wifi-densepose-hardware/src/ieee80211bf/`)** — typed WLAN-sensing procedures (measurement setup/instance/report, SBP, termination) with `SpecProfile` version gates, `SensingCapabilities` negotiation, and **required** `ConsentMode` governance metadata on every setup; deterministic session FSM with rejection/timeout paths; `SensingTransport` seam with `SimTransport` and an `OpportunisticCsiBridge` mapping live ESP32 CSI batches into standardized report shape (a future chipset adapter replaces the bridge without touching RuvSense consumers). Not a certified implementation — simulation-tested protocol surface; OTA binding lands when silicon does. 19 acceptance tests.
+- **Dynamic min-cut mesh partition guard in the streaming engine (`mesh_guard`).** Maintains a `ruvector-mincut` exact min-cut over the live mesh coupling graph (nodes = sensing nodes, coupling = product of fusion attention weights), surfacing per cycle: the global **cut value** (how close the array is to splitting — a structural measure per-node heuristics miss), the **weak side** (which specific nodes would partition: failure/jamming triage feeding ADR-032 posture), and an **at-risk flag** that counts as a structural event for the drift→recalibration advisor. Surfaced as `TrustedOutput::mesh`. **Measured cost policy** (criterion, 12-node mesh): weights are quantized (1/64; a *nonzero* coupling below one quantum saturates to quantum 1 so quantization never erases a live coupling — without the floor, balanced meshes of ≥ 65 nodes had every ~1/n coupling erased and sat permanently "at risk") and updates change-gated, so the steady-state cycle does zero graph work (~7.3 µs, ~23× cheaper than building); on any real change a full exact rebuild (~171 µs) is used because one `DynamicMinCut` delete+insert measured ~240 µs — the incremental machinery's overhead targets much larger graphs, so rebuild-on-change is the measured optimum at mesh scale (one-edge case −28% after the policy switch). Degenerate cases fail toward risk: a node with zero coupling is reported as already partitioned (cut 0). 9 mesh-guard tests + an engine-level wiring test; full `process_cycle` with the guard: ~33 µs for 4 nodes (50 ms budget).
+- **Opt-in FFT operator for the CIR ISTA solver (8–14× measured).** Φ is a sub-DFT, so each ISTA mat-vec can run as one length-G FFT (O(G log G)) instead of a dense O(K·G) product. New `CirConfig::fft_operator` (default **false** — the dense path stays the bit-exact witness default; the FFT evaluates the same sums in a different order, so enabling it shifts float results and requires regenerating any pinned witness). `FftOperator` (rustfft, planned once at construction, scratch reused across the ISTA loop) dispatches inside `ista_solve`; warm-start/Lipschitz stay dense at construction. Measured (criterion, same run): ht20 2.22 ms → 265 µs (**8.4×**), ht40 10.26 ms → 717 µs (**14.3×**); the real HE40 grid (K=484, G=1452) scales further. 3 new tests: FFT↔dense matvec equivalence to float tolerance (ht20 + he40 grids), end-to-end dominant-tap agreement on a single-path frame, and all default configs keep FFT off. New `cir_estimate_fft` bench group.
+- **Per-room adapter provenance + drift→recalibration advisor in the streaming engine.** Closes the trust-chain gap where an ~11 KB per-room LoRA adapter (ADR-150 §3.4) could silently change inference without the witness noticing. `StreamingEngine::set_room_adapter(AdapterInfo)` pins the adapter's content-derived id into provenance `model_version` (`rfenc-v1+adapter:<id>`) — and therefore into the BLAKE3 witness — so swapping or clearing adapter weights always shifts the witness (engine test proves base → adapter → other-adapter → cleared all witness differently, and cleared == base). New `RecalibrationAdvisor` recommends re-running the ADR-135 baseline / refitting the adapter on sustained low fusion coherence (streak threshold, default 60 cycles ≈ 3 s at 20 Hz) or an ADR-142 change-point; surfaced as `TrustedOutput::recalibration_recommended` and recorded on the sensing-server's `EngineBridge` alongside the witness. Bridge plumbing: `EngineBridge::{set_room_adapter, clear_room_adapter}` + live-path test that the adapter id flows into the live witness. *Scope note: this is the deployable provenance/trigger half of the "retrained model" roadmap item — fitting the adapter itself runs in the existing external calibration service (`aether-arena/calibration/`), and a trained RF-encoder checkpoint still does not exist in-tree.*
+- **RuView beyond-SOTA research series** (`docs/research/ruview-beyond-sota/`, 6 docs) — research-swarm output defining the beyond-SOTA bar and the path to it: system capability audit (role→crate maturity matrix, gap analysis, risk register), web-verified 2026 SOTA landscape per capability axis (incl. ratified IEEE 802.11bf-2025), 8-pillar target architecture on the ADR-136 contract spine (no rewrite), 6-layer benchmark/validation methodology (all 15 criterion bench targets inventoried; ADR-171 statistical protocol), and a determinism-safe optimization roadmap. Includes session validation evidence: 2,797 workspace tests / 0 failed, Python proof PASS (bit-exact), paired pre/post criterion runs.
+
+### Performance
+- **CIR estimator warm-start precompute** — the diagonal Tikhonov preconditioner `diag(Φ^H Φ)+λI` and its CSR matrix were rebuilt every frame although they depend only on Φ and λ (fixed at `CirEstimator::new`); now precomputed at construction (`ruvsense/cir.rs`). Bit-identical floats (summation order unchanged, witness chain unaffected). Measured: `cir_estimate/he40` −3.9% (p<0.01), multiband groups −1.2/−1.4%; smaller configs within container noise.
+- **RF tomography solver hoisting** — ISTA gradient buffer no longer allocated inside the 100-iteration loop, and the Frobenius Lipschitz bound moved from per-`reconstruct` to construction (`ruvsense/tomography.rs`). Bit-identical results.
+
+### Added
+- **Falsifiable occupancy benchmark (`wifi-densepose-train::occupancy_bench`).** Makes the presence/person-count "beyond SOTA" claim falsifiable in code instead of aspirational (the unfalsifiability gap from the beyond-SOTA system review). Grades predictions vs ground truth and gates a SOTA claim behind one `claim_allowed` invariant requiring all of: `DataProvenance::Measured` (synthetic/mock is scorable but **never claimable** — anti-mock-contamination per the CLAUDE.md Kconfig-bug lesson), a leak-free `EvalSplit` (refuses any split where a subject *or* environment id appears in both train and test — subject leakage / per-environment overfitting), `n_test ≥ min`, a **non-degenerate test set** (both truth classes represented: present-rate ≥ `min_positive_rate` and ≥ 1 absent sample — an all-absent set plus an always-absent predictor cannot release a claim; vacuous F1 scores 0.0, never 1.0), presence-F1 **bootstrap-CI lower bound** (deterministic seeded splitmix64) clearing the threshold, and count MAE within threshold. The claim string is unreadable except through the gate (`NO_CLAIM` otherwise). What remains is data, not method: a frozen, SHA-pinned, subject/environment-disjoint measured replay set turns the claim into a passing/failing test. 12 tests cover each refusal path, including the point-above/CI-below case (claim withheld on the CI lower bound even when the point estimate clears the threshold).
+- **Live trust path: sensing-server routes real frames through the governed `StreamingEngine` (parallel governed path with partial output gating).** Previously the live server ran only the *bare* `MultistaticFuser` (fused amplitudes, no trust control plane), while the privacy/provenance/witness engine (ADR-135..146) ran only on synthetic in-test frames — the gap called out in ADR-136 §8 and the beyond-SOTA system review. New `engine_bridge` module drives `StreamingEngine::process_cycle` from the server's live `NodeState` map (reusing the existing `NodeState → MultiBandCsiFrame` conversion), lazily wiring each node as a WorldGraph sensor and bounding belief growth via the retention cap; every *governed belief* carries evidence + model + calibration + privacy decision and a deterministic witness. **Honest scope:** the engine runs alongside (not instead of) the bare fusion path that feeds the live `SensingUpdate`. What its decision gates on the wire today: a cycle emitted at class `Restricted` (base mode or contradiction/mesh-risk demotion) suppresses the per-node raw amplitude vectors from the live publish — the same field mapping `wifi-densepose-bfld`'s privacy gate applies at `Restricted`; gating the remaining derived outputs (person count, classification, signal field) is tracked as a follow-up. Trust state is no longer write-only: the latest witness, effective privacy class, demotion flag, recalibration recommendation, and an engine-error counter are readable on `GET /api/v1/status`, and engine errors are counted + rate-limit logged instead of silently swallowed (`EngineBridge::observe_cycle`). Adds `wifi-densepose-engine/-worldgraph/-bfld/-geo` deps. Bridge tests cover witnessed belief with provenance, determinism, idempotent node registration, retention bound, privacy-mode propagation, trust-state recording, the error-counter path, and Restricted-class raw-output suppression.
+
+### Fixed
+- **Real HE20 CSI no longer silently dropped or replaced with simulated data (fixes #1009, #1004).** Two ingest bugs caused real ESP32-C6 HE20 frames to be discarded or never received — the exact "real data silently lost" failure class the project fights. Each fix is pinned by a test that fails on the old code.
+  - **#1009 §1b — HE20 baseline recorder trimmed 256 → 242 bins by sequential index (`wifi-densepose-signal/src/ruvsense/calibration.rs`).** ESP-IDF v5.5.2 delivers all 256 FFT bins for an HE20 frame; `CalibrationConfig::he20()` carried `num_active: 242`, so the recorder (which has no HE20 tone map — `extract_first_stream` takes the first `num_active` columns *sequentially*) kept bins 0..242 of the 256-bin grid. Those are the lower guard band + DC, **not** the 242 active tones, silently corrupting the empty-room baseline. Now `num_active: 256` records every delivered bin, staying aligned 1:1 with the live `deviation()` path. The exact-242 tone map deliberately stays only in `cir.rs` (`HE20_ACTIVE`), where the Φ sensing matrix genuinely needs it. Test `he20_records_all_256_bins_not_trimmed_to_242` asserts the finalized baseline covers all 256 bins (was 242). HE20 synthetic/bench fixtures updated to feed 256-bin frames (the real wire format).
+  - **#1009 §1a/§1c — already-fixed u8→u16 `n_subcarriers` truncation, now regression-pinned.** The ADR-018 wire format carries `n_subcarriers` as u16 LE at bytes 6–7. A 256-bin HE20 frame (byte6=0x00, byte7=0x01) read as a single byte decodes to **0 subcarriers** → every frame skipped (invisible until HE20: ESP32-S3's ≤192 bins fit in one byte). The CLI parser (`wifi-densepose-cli/calibrate.rs`) and the sensing-server template parser (`wifi-densepose-sensing-server` `parse_esp32_frame`) were already corrected to u16 under #1005/ADR-110; added regression tests (`parse_esp32_frame_he20_256_bins_not_truncated`, CLI `test_parse_csi_packet_he_su_256_bins`) that fail on the old single-byte read so the truncation cannot silently return.
+  - **#1004 — `--source auto` latched on `simulate` forever, never binding UDP :5005 (`wifi-densepose-sensing-server/src/main.rs`).** A one-shot boot probe resolved the source once; with no CSI flowing at boot (the normal firmware/server startup race) it served simulated poses for the whole process and ignored real CSI that arrived seconds later (the prior #937 fix hard-exited instead — equally wrong, the server could never pick up late-starting CSI). New `plan_source()` state machine: in `auto` mode **always bind the UDP receiver** and serve simulated data only until the first real frame, at which point `udp_receiver_task` promotes `source` → `esp32` (mirroring the existing `esp32 → esp32:offline` reversion in `effective_source()`); `simulated_data_task` self-suspends once promoted so it never clobbers live CSI. Explicit `--source simulated` stays a hard, UDP-free override for offline demos. 6 unit tests pin the resolution/promotion machine (`auto_with_no_boot_source_still_binds_udp_and_simulates`, etc.); the auto-binds-UDP assertion fails on the old behavior.
+- **`wifi-densepose-mat` standalone `--no-default-features` build (101 errors → 0).** `pub mod api` was unconditional while its only dependency, serde, is optional behind the `api` feature — so any build without default features failed with unresolved serde imports (masked in `--workspace` runs by feature unification). The `api` module and its `create_router`/`AppState` re-export are now `#[cfg(feature = "api")]`-gated (with docsrs annotations). All feature combos compile: bare `--no-default-features`, `--no-default-features --features api`, and full default (177 tests pass).
+- **WorldGraph no longer grows unboundedly under the live loop.** `StreamingEngine::process_cycle` appended one `SemanticState` belief per cycle with no eviction — ~1.7M nodes/day at 20 Hz (identified in `docs/research/ruview-beyond-sota/04-optimization-roadmap.md`). Added `WorldGraph::prune_semantic_states(max)` — deterministic eviction of the oldest beliefs by `(valid_from_unix_ms, id)`, structural nodes (rooms/zones/sensors/anchors/tracks/events) never eligible — and wired it into the engine after each belief append (`StreamingEngine::DEFAULT_SEMANTIC_RETENTION` = 7,200 ≈ 6 min at 20 Hz; tunable via `set_semantic_retention`). The WorldGraph holds *current* beliefs; durable history is the recorder's job, so no audit data is lost. 3 new tests (bounded growth end-to-end, oldest-only eviction, deterministic tie-break).
+- **ESP32 edge heart rate no longer stuck at ~45 BPM / dropping wildly — #987.** The on-device HR estimator (`edge_processing.c`, `0xC5110002`) reported ~45 BPM regardless of true heart rate (Apple-Watch ground truth 87 BPM read as ~45) and swung frame-to-frame. Two root causes: (1) a hardcoded `sample_rate = 10.0f` that became wrong after #985's self-ping raised the CSI callback rate to a variable ~13–19 Hz — BPM scales as `assumed/actual × true`, so 87 read ~45 and the reading swung as CSI yield fluctuated; (2) the zero-crossing estimator locked onto a breathing harmonic (a 0.25 Hz breathing fundamental puts its 3rd harmonic at ~0.74 Hz ≈ 44 BPM inside the HR band). Fix: measure the real sample rate from inter-frame timestamps (used for BPM conversion + biquad re-tuning on >15% drift); replace the HR zero-crossing with an autocorrelation estimator that rejects breathing harmonics (driven by a robust autocorr breathing period); median-13 smooth the output. Hardware A/B (fixed vs unmodified control board, both `edge_tier=2`): control pegged 40–49 BPM; fixed reaches the true 88–91 BPM (vs 87 GT) and holds a stable physiological value (spread 59→0 for a steady subject). Known limitation: heavy subject motion still degrades the estimate (motion gating is a follow-up).
 - **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
+- **ADR-151 per-room calibration & specialist training — full `baseline → enroll → extract → train` pipeline (new `wifi-densepose-calibration` crate).** "Teach the room before you teach the model": a local-first pipeline that turns a few minutes of clean human anchors — layered on the ADR-135 empty-room baseline — into a versioned bank of small, room-calibrated specialists for **presence, posture, breathing, heartbeat, restlessness, and anomaly**. Stages: guided enrollment with an adaptive quality gate (event-sourced `EnrollmentSession`, re-prompts bad anchors); feature extraction (autocorrelation periodicity in breathing/HR bands + variance/motion); six small specialists (learned threshold / nearest-prototype / band-limited periodicity / novelty); a `SpecialistBank` with baseline-drift **STALE** invalidation; and a `MixtureOfSpecialists` runtime with presence short-circuit + anomaly veto + confidence gating. Specialists are statistical heads today (runnable + hardware-validated); the frozen ADR-150 HF RF Foundation Encoder backbone is the documented upgrade path.
+  - **CLI:** `enroll` / `train-room` / `room-status` / `room-watch`, plus the Stage-1 `calibrate-serve` HTTP API (CORS-enabled: `POST /start`, `GET /status`, `POST /stop`, `GET /result`, `GET /baselines`, `GET /health`) and a firewall-free `scripts/csi-udp-relay.py` for local Windows ESP32 testing without admin.
+  - **Multistatic fusion (ADR-029):** `MultiNodeMixture` fuses several co-located nodes (each with its own room-calibrated bank) into one room state — presence OR'd across nodes, posture/breathing/heartbeat from the highest-confidence node, a single implausible node vetoes the room's vitals. Driven via `room-watch --node-bank N:path` (repeatable), which groups live frames by `node_id` and fuses. Same-room only; cross-room is federation (ADR-105).
+  - **Validated on live ESP32-S3 (COM8, `edge_tier=0` raw CSI):** baseline capture (120 frames → 52-subcarrier baseline); the real parser → feature-extraction → mixture runtime detecting breathing (~16–31 BPM); and the multistatic ingest grouping/fusing by node-id end-to-end. Full multi-anchor enrollment accuracy requires the operator to perform the poses; true 2-node fusion + phase-based breathing + RVF/HNSW storage are noted follow-ups. 54 tests pass (35 calibration + 19 CLI).
 - **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:
  - **Efficiency frontier** — a **75 K-param model beats published SOTA** (74.3% vs MultiFormer 72.25% torso-PCK@20); every config from `micro` up is Pareto-dominant (smaller *and* more accurate than prior work). Shipped a deployable **int4 edge model (~20 KB, verified 74.08%, 0.135 ms single-thread CPU)** — published at [`ruvnet/wifi-densepose-mmfi-pose/edge`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose). See [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](docs/benchmarks/wifi-pose-efficiency-frontier.md).
  - **Generalization solved by few-shot calibration** — zero-shot cross-subject (~64%) and cross-environment (~10%) are *not* closeable by algorithms (CORAL, DANN, instance-norm, contrastive foundation-pretraining all tested, all failed) or by more training subjects (saturates ~64%). But **~100–200 labeled in-room samples recover SOTA-level pose**: cross-subject 64→76%, **cross-environment 10→73% (60% from just 5 samples)** — deployable as a **~11 KB per-room LoRA adapter** on a frozen shared base. Full empirical chain in ADR-150 §3.2–3.6.
@@ -26,13 +183,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `ruview-swarm` benchmarks (criterion, release): MARL actor inference 3.3 µs, RRT-APF planning 0.043 ms, multi-view CSI fusion 58.5 ns, 3-view localization 1.732 m (beats Wi2SAR 5 m SOTA baseline), 4-drone SAR coverage 223 s for 400×400 m (under 240 s target).

 ### Added
- **ADR-147 — OccWorld world model integration** (`wifi-densepose-worldmodel` v0.3.0 published to crates.io). 15-frame trajectory prediction at 209 ms / 3.37 GB VRAM on RTX 5080. Phase 3 domain adapter `scripts/ruview_occ_dataset.py` (`RuViewOccDataset`) converts WorldGraph snapshots to OccWorld tensors with indoor class remapping + zero ego-poses (validated). Phase 5 retraining pipeline `scripts/occworld_retrain.py` — VQVAE + transformer fine-tuning on RuView occupancy snapshots. See [ADR-147](docs/adr/ADR-147-nvidia-cosmos-world-foundation-model-integration.md) · [benchmark proof](docs/adr/ADR-147-benchmark-proof.md).
+- **ADR-147 — OccWorld world model integration** (`wifi-densepose-worldmodel` v0.3.0 published to crates.io). 15-frame trajectory prediction at 209 ms / 3.37 GB VRAM on RTX 5080. Phase 3 domain adapter `scripts/ruview_occ_dataset.py` (`RuViewOccDataset`) converts WorldGraph snapshots to OccWorld tensors with indoor class remapping + zero ego-poses (validated). Phase 5 retraining pipeline `scripts/occworld_retrain.py` — VQVAE + transformer fine-tuning on RuView occupancy snapshots. See [ADR-147](docs/adr/ADR-147-nvidia-cosmos-world-foundation-model-integration.md) · [benchmark proof](docs/adr/ADR-168-benchmark-proof.md).

 ### Added
 - **ADR-125 (APPLE-FABRIC) — RuView ↔ Apple Home native HAP bridge proposal + reference impl** (issue #796). New ADR-125 lays out a three-phase plan to expose RuView as a discoverable HomeKit accessory on the LAN so a HomePod (as Home Hub) sees presence / vitals / BFLD-derived events natively — zero Home-Assistant intermediary. Two architectural decisions resolved in the ADR per design review: (1) **one HAP bridge with N child accessories** (single pairing, matches Hue/Eve pattern), and (2) **identity-risk mapping is semantic, not probabilistic** — `identity_risk_score` and Soul-Signature match probability never cross the HAP boundary; instead three thresholded events are exposed (`Unknown Presence`, `Unexpected Occupancy`, `Unrecognized Activity Pattern`) so RuView reads as calm-tech ambient awareness, not surveillance UX. ADR-125 §2.1.a reference impl ships now: `scripts/hap-test-sensor.py` (HAP-1.1 bridge advertised over mDNS, paired with operator's iPhone) + `scripts/c6-presence-watcher.py` (parses ESP32 `RV_FEATURE_STATE_MAGIC = 0xC5110006` UDP packets with IEEE CRC32 validation, hysteresis, and a Python port of `wifi-densepose-bfld::PrivacyClass` that enforces ADR-125 §2.1.d invariant I1 at the HomeKit edge — only `Anonymous` (2) and `Restricted` (3) frames may cross; `Raw`/`Derived` are refused with exit code 2 and the cited ADR clause). Validated end-to-end on real hardware (no mocks): ESP32-C6 on `ruv.net` → UDP/5005 → mac-mini watcher → BFLD gate → HAP bridge → iPhone Home app shows `Unknown Presence` live characteristic flip. **Empirical**: 50-51 valid CRC-passing feature_state packets per 10 s window from the live C6; zero CRC errors. P2 (Rust-native HAP via the `hap` crate, replaces the Python sidecar) and P3 (Matter Controller once `matter-rs` stabilizes) follow.

 ### 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`)
@@ -10,18 +10,22 @@ Dual codebase: Python v1 (`v1/`) and Rust port (`v2/`).
 | `wifi-densepose-core` | Core types, traits, error types, CSI frame primitives |
 | `wifi-densepose-signal` | SOTA signal processing + RuvSense multistatic sensing (16 modules) |
 | `wifi-densepose-nn` | Neural network inference (ONNX, PyTorch, Candle backends) |
-| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics |
+| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics; MAE pretraining recipe (`mae.rs`, ADR-152 §2.3) + WiFlow-STD port (`wiflow_std/`, tch-gated) |
 | `wifi-densepose-mat` | Mass Casualty Assessment Tool — disaster survivor detection |
-| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware |
+| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware; `ieee80211bf/` 802.11bf forward-compat protocol model (ADR-153) |
 | `wifi-densepose-ruvector` | RuVector v2.0.4 integration + cross-viewpoint fusion (5 modules) |
 | `wifi-densepose-wasm` | WebAssembly bindings for browser deployment |
-| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) |
+| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) — `calibrate`/`calibrate-serve`/`enroll`/`train-room`/`room-watch` + MAT (MAT gated behind the `mat` feature; build `--no-default-features` for the aarch64/appliance calibration binary) |
+| `wifi-densepose-calibration` | ADR-151 per-room calibration & specialist training — `baseline → enroll → extract → train` → bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly) + multistatic fusion; pure Rust, edge-deployable |
 | `wifi-densepose-sensing-server` | Lightweight Axum server for WiFi sensing UI |
 | `wifi-densepose-wifiscan` | Multi-BSSID WiFi scanning (ADR-022) |
 | `wifi-densepose-vitals` | ESP32 CSI-grade vital sign extraction (ADR-021) |
 | `nvsim` | Deterministic NV-diamond magnetometer pipeline simulator (ADR-089) — standalone leaf, WASM-ready |
 | `vendor/rvcsi` (submodule) | **rvCSI** — edge RF sensing runtime (ADR-095/096): 9 crates (`rvcsi-core`/`-dsp`/`-events`/`-adapter-file`/`-adapter-nexmon`/`-ruvector`/`-runtime`/`-node`/`-cli`). Lives in its own repo ([github.com/ruvnet/rvcsi](https://github.com/ruvnet/rvcsi)), vendored here under `vendor/rvcsi`, published to crates.io as `rvcsi-* 0.3.x` and to npm as `@ruv/rvcsi`. Not a `v2/` workspace member — depend on the published crates (or the submodule's `crates/rvcsi-*` paths). Normalized `CsiFrame`/`CsiWindow`/`CsiEvent` schema, validate-before-FFI, reusable DSP, typed confidence-scored events, the napi-c Nexmon shim (real nexmon_csi `.pcap` from a Raspberry Pi 5 / 4 / 3B+ — BCM43455c0), the napi-rs SDK, the `rvcsi` CLI, a Claude Code plugin. |
+| `vendor/rufield` (submodule) | **RuField MFS** — the open spec for camera-free multimodal field sensing (ADR-260). A common `FieldEvent`/`FieldTensor`/`FusionGraph`/`PrivacyClass`/`ProvenanceReceipt` model *above* WiFi CSI/CIR/BFLD, UWB, BLE Channel Sounding, mmWave radar, ultrasound, subsonic, infrared, and quantum sensors. Lives in its own repo ([github.com/ruvnet/rufield](https://github.com/ruvnet/rufield)), vendored here under `vendor/rufield`. Not a `v2/` workspace member. v0.1 reference stack = 7 crates (`rufield-core`/`-provenance`/`-privacy`/`-adapters`/`-fusion`/`-bench`/`-viewer`), 72 tests/0 failed; `rufield-viewer` is an Axum + vanilla-JS read-only dashboard (`cargo run -p rufield-viewer`) completing ADR-260 §27.9. The WiFi-CSI modality is now **real-replay-backed** via `CsiReplayAdapter` (ingests real captured `.csi.jsonl` → fused presence/breathing inferences; replay-from-file, unlabeled CSI-variance proxy, not validated accuracy); mmWave/thermal + all synthetic-bench F1 numbers remain **SYNTHETIC** (no live hardware — live streaming + labeled accuracy are roadmap). |
+| `wifi-densepose-rufield` | ADR-262 P1 **anti-corruption bridge** — converts RuView WiFi-CSI sensing output (`SensingSnapshot` mirroring `SensingUpdate` + `TrustedOutput`, owned primitives, no dep on `wifi-densepose-sensing-server`) into **signed RuField `FieldEvent`s** (`Modality::WifiCsi`, real `timestamp_ns`, sha256 + ed25519 provenance, `synthetic=false`). The single coupling point between RuView and the standalone RuField MFS spec (§5.4); path-deps the `vendor/rufield` submodule crates (`rufield-core`/`-provenance`/`-privacy`/`-fusion`). **Critical §3.3 privacy mapping** (`map_privacy`): maps RuView class → RuField P0–P5 by **information content, never byte value**, fail-closed (`Derived → P4/P5`, never P1; `demoted` floors to ≥ P2). 15 tests / 0 failed (round-trip / `is_fusable` / fusion-ingest / privacy-safety / determinism). P1 plumbing — not wired into the live server (P3), no accuracy claim. |
 | `ruview-swarm` | Drone swarm control system (ADR-148) — hierarchical-mesh topology, Raft consensus, MARL, CSI sensing payload, MAVLink/PX4 compat, Ruflo AI-agent integration |
+| `ruview-unified` | ADR-273..282 **unified RF spatial world model**: authoritative native `RfFrameV2` frame contract (native IQ never overwritten, phase-state/evidence-ladder/provenance invariants) with the canonical `RfTensor` as a derived view; fail-closed hardware adapter registry (WiFi CSI / FMCW cube / UWB CIR / 5G SRS / BLE Channel Sounding with phase-vs-RTT cross-validated ranging); universal RF foundation encoder (masked-reconstruction pretraining with finite-difference-verified backprop, `z = Enc ⊙ σ(AgeEnc(log age)) + Geom` fusion, ≤1% scalar / <2% structured task adapters incl. RePos-factorized pose); RF-aware Gaussian spatial memory (fusion/decay/channel-gain queries + inverse updates, lineage receipts, task-gated scene graph); physics-guided synthetic RF world generator (image-method multipath, Fresnel materials, emergent Doppler, seeded domain randomization); edge sensing control plane (802.11bf/ETSI-ISAC purposes/zones/tasks, AoI active-sensing planner, fail-closed coherent-aperture fusion, governed RIS actuation; raw RF structurally unexportable); delay-Doppler-native transforms. Pure Rust leaf; all accuracy numbers SYNTHETIC (evidence level L0) until real-data validation. |

 ### RuvSense Modules (`signal/src/ruvsense/`)
 | Module | Purpose |
@@ -59,7 +63,7 @@ All 5 ruvector crates integrated in workspace:
 - `ruvector-attention` → `model.rs` (apply_spatial_attention) + `bvp.rs`

 ### Architecture Decisions
-43 ADRs in `docs/adr/` (ADR-001 through ADR-043). Key ones:
+205 ADRs in `docs/adr/` (numbered ADR-001 through ADR-282, with gaps). Key ones:
 - ADR-014: SOTA signal processing (Accepted)
 - ADR-015: MM-Fi + Wi-Pose training datasets (Accepted)
 - ADR-016: RuVector training pipeline integration (Accepted — complete)
@@ -72,6 +76,22 @@ All 5 ruvector crates integrated in workspace:
 - ADR-031: RuView sensing-first RF mode (Proposed)
 - ADR-032: Multistatic mesh security hardening (Proposed)
 - ADR-148: Drone swarm control system / `ruview-swarm` (In Progress)
+- ADR-152: WiFi-Pose SOTA 2026 intake — geometry conditioning, WiFlow-STD benchmark (measurement (a) complete: claims MEASURED-EQUIVALENT at ~96% PCK@20), MAE recipe (Proposed; §2.1–2.3, 2.6 implemented)
+- ADR-153: IEEE 802.11bf-2025 forward-compatibility protocol model (Accepted — amends ADR-152 §2.4)
+- ADR-182: `npx ruview` harness minted via MetaHarness (Accepted — P1+P2 shipped as `@ruvnet/ruview`)
+- ADR-263: `@ruvnet/ruview` npm harness deep review + optimization strategy (Proposed)
+- ADR-264: `@ruvnet/rvagent` MCP server + `@ruv/ruview-cli` deep review + optimization strategy (Proposed)
+- ADR-265: RuView npm distribution strategy — CI gate, provenance, version single-sourcing (Proposed)
+- ADR-273: Unified RF spatial world model — umbrella + anti-leakage evaluation protocol + acceptance gates (Accepted — P1 implemented in `ruview-unified`)
+- ADR-274: Universal RF foundation encoder + hardware adapter registry (Accepted — P1 implemented)
+- ADR-275: RF-aware Gaussian spatial memory — fusion, decay, channel-gain queries, inverse updates, task-gated scene graph (Accepted — P1 implemented)
+- ADR-276: Physics-guided synthetic RF world generator — randomize physics, not textures (Accepted — P1 implemented)
+- ADR-277: Edge sensing control plane — purposes/zones/retention/identity double-gate; raw RF unexportable (Accepted — P1 implemented)
+- ADR-278: Radar inverse rendering + differentiable RF SLAM research program — RISE/DiffRadar/GeRaF reproduction gates (Proposed)
+- ADR-279: Native RF frame contract — `RfFrameV2` authoritative, canonical tensor demoted to derived view; 7 invariants; split manifest with session dimension (Accepted — implemented)
+- ADR-280: Active sensing & programmable perception — sensing tasks/actions, AoI freshness scheduler (95% traffic reduction measured), fail-closed coherent-aperture fusion, governed RIS actuation, task-sufficient representations (Accepted — implemented)
+- ADR-281: BLE Channel Sounding (phase vs RTT cross-validated ranging), delay-Doppler-native tensors, IEEE P3162 import profile, RePos factorized pose (Accepted — implemented)
+- ADR-282: Ecosystem positioning — RuView as edge RF perception runtime; RuField/RuVector/MetaHarness layering; mandatory L0–L5 evidence ladder (Accepted)

 ### Supported Hardware

@@ -84,6 +104,8 @@ All 5 ruvector crates integrated in workspace:

 **Not supported:** ESP32 (original), ESP32-C3 — single-core, can't run CSI DSP pipeline.

+**⚠️ Compact boards (SuperMini, ESP32-S3-Zero, other coin-sized clones) run hot:** the firmware keeps the WiFi radio on continuously (`WIFI_PS_NONE`) and runs a full DSP pipeline (`edge_tier=2`), which is sustained high current draw. Full-size dev boards handle this fine; coin-sized clones with minimal PCB copper and budget regulators can run uncomfortably hot and, per at least one field report, have failed to power on again after a hot session. Give them airflow and check by touch during the first few minutes. See `firmware/esp32-csi-node/README.md` for details.
+
 ### Build & Test Commands (this repo)
 ```bash
 # Rust — full workspace tests (1,031+ tests, ~2 min)
@@ -51,26 +51,26 @@ verify-audit:

 # ─── Rust Builds ─────────────────────────────────────────────
 build-rust:
-	cd rust-port/wifi-densepose-rs && cargo build --release
+	cd v2 && cargo build --release

 build-wasm:
-	cd rust-port/wifi-densepose-rs && wasm-pack build crates/wifi-densepose-wasm --target web --release
+	cd v2 && wasm-pack build crates/wifi-densepose-wasm --target web --release

 build-wasm-mat:
-	cd rust-port/wifi-densepose-rs && wasm-pack build crates/wifi-densepose-wasm --target web --release -- --features mat
+	cd v2 && wasm-pack build crates/wifi-densepose-wasm --target web --release -- --features mat

 test-rust:
-	cd rust-port/wifi-densepose-rs && cargo test --workspace
+	cd v2 && cargo test --workspace --no-default-features

 bench:
-	cd rust-port/wifi-densepose-rs && cargo bench --package wifi-densepose-signal
+	cd v2 && cargo bench --package wifi-densepose-signal

 # ─── Run ─────────────────────────────────────────────────────
 run-api:
-	uvicorn v1.src.api.main:app --host 0.0.0.0 --port 8000
+	uvicorn archive.v1.src.api.main:app --host 0.0.0.0 --port 8000

 run-api-dev:
-	uvicorn v1.src.api.main:app --host 0.0.0.0 --port 8000 --reload
+	uvicorn archive.v1.src.api.main:app --host 0.0.0.0 --port 8000 --reload

 run-viz:
 	python3 -m http.server 3000 --directory ui
@@ -81,7 +81,7 @@ run-docker:
 # ─── Clean ───────────────────────────────────────────────────
 clean:
 	rm -f .install.log
-	cd rust-port/wifi-densepose-rs && cargo clean 2>/dev/null || true
+	cd v2 && cargo clean 2>/dev/null || true

 # ─── Help ────────────────────────────────────────────────────
 help:
@@ -0,0 +1,78 @@
+# PROOF — reproduce every claim, or find the one we can't yet
+
+This project (RuView / wifi-densepose) has been publicly called "AI slop" and
+"fake." This document is the answer: **a skeptic can clone the repo, run one
+script, and have every headline claim either verified on their own machine or
+shown — explicitly — as "CLAIMED, not yet reproduced (here's exactly what it
+needs)."** Nothing below is asserted without a command you can run.
+
+```bash
+git clone https://github.com/ruvnet/RuView && cd RuView
+bash scripts/prove.sh          # core gate + the anti-slop assertion tests
+bash scripts/prove.sh --full   # also attempt the feature-gated subset
+```
+
+`prove.sh` exits 0 only if every **non-gated** claim passes. Gated claims never
+fail the run; they print the prerequisite (a GPU, a dataset, real hardware, a
+trained checkpoint) so you can reproduce them yourself.
+
+## Grading
+
+- **MEASURED** — reproduced on our hardware, with the exact command recorded, and
+  pinned by a test that *fails on the pre-fix code*. `prove.sh` re-runs these.
+- **CLAIMED** — cited from a source, or measured by the source, but not
+  reproduced in this repo's automated harness.
+- **DATA-GATED / HARDWARE-GATED** — the *code path* is real and tested, but the
+  *accuracy/throughput claim* needs data or hardware we don't ship. We never
+  fabricate the number; the code carries a typed error or a `weights_trained`/
+  provenance flag instead.
+
+## The hard gate (run on any machine with Rust + Python)
+
+| Claim | Grade | Reproduce |
+|---|---|---|
+| Rust workspace: 3,128 tests, 0 failed | **MEASURED** | `cd v2 && cargo test --workspace --no-default-features` |
+| Deterministic CSI pipeline proof (bit-exact SHA-256) | **MEASURED** | `python archive/v1/data/proof/verify.py` → `VERDICT: PASS` |
+
+## Anti-slop assertion tests (each fails on the pre-fix code)
+
+| Claim | Grade | Test (run via `cargo test -p <crate> <name>`) |
+|---|---|---|
+| Fusion crafted-input DoS panics are closed (ADR-156 §2.2) | **MEASURED** | `wifi-densepose-ruvector :: triangulation_out_of_range_index_returns_none_no_panic` |
+| **The "Soul Signature" identity claim, honestly bounded:** on WiFi-only cardiac+respiratory channels two people are **not separable** (gap ≈ 0.0005) | **MEASURED** | `wifi-densepose-bfld :: cardiac_alone_cannot_separate_identity_matches_audit` |
+| OccWorld `predict()` is real (input-dependent), not random noise | **MEASURED** | `wifi-densepose-occworld-candle :: predict_is_deterministic_for_same_input` |
+| Pose runtime emits frames under its own default config (ADR-159 A1) | **MEASURED** | `cog-pose-estimation :: default_config_emits_frames_with_real_model` |
+| Person-count flags untrained classes — no count inflation (ADR-159 A2) | **MEASURED** | `cog-person-count :: untrained_class_argmax_is_flagged_low_confidence` |
+| Medical edge skills carry a "not a medical device" disclaimer (ADR-160 A1) | **MEASURED** | `wifi-densepose-wasm-edge :: a1_med_modules_have_clinical_disclaimer` (`--features std`) |
+| Survivor dedup 3→1, count-inflation killed (ADR-158 §2) | **MEASURED** | `wifi-densepose-mat :: test_identical_vitals_no_location_dedup_to_one` (`--features mat`) |
+
+## Measured performance (criterion; reproduce on your machine)
+
+| Claim | Grade | Reproduce |
+|---|---|---|
+| PSD FFT-planner cache 2.0–3.1×, DTW band 2.4–4.1× (ADR-154) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-signal` |
+| fuse() double-clone removed ~2.17× marshalling (ADR-156) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-ruvector --bench fusion_bench` |
+| zero-copy ORT input ~1.48× (ADR-155) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-nn --features onnx --bench onnx_bench` |
+| pointcloud splats 9→2 passes ~1.24× (ADR-160 research) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-pointcloud --bench splats_bench` |
+| native wlanapi multi-BSSID scan 9.74 Hz (vs netsh ~2 Hz) | **MEASURED (Windows)** | `cd v2 && cargo test -p wifi-densepose-wifiscan -- --ignored measure_native_scan_rate` |
+| wasm-edge `process_frame` hot-path latency (host proxy, ADR-163) | **MEASURED-on-host** (NOT the ESP32/WASM3 budget — needs hardware) | `cd v2/crates/wifi-densepose-wasm-edge && cargo bench --features std` |
+| cog steady-state CPU infer latency ~305 µs (ADR-163; NOT the manifest cold-start) | **MEASURED-on-host** | `cd v2 && cargo bench -p cog-person-count -p cog-pose-estimation --no-default-features --bench infer_bench` |
+
+## What we do NOT claim (the honest negatives — the strongest anti-slop signal)
+
+| Capability | Status |
+|---|---|
+| **Named person-identity from WiFi** | **NOT achieved, and measured why.** The §3.6 matcher is real, but identity does not lock on WiFi-only channels (gap 0.0005). DATA-GATED on a real enrollment feeding the AETHER/body-resonance channel — never done. No named-identity claim is made. |
+| WiFlow-STD ~96% PCK@20 | **CLAIMED-reproduced** on our RTX 5080 (`benchmarks/wiflow-std/RESULTS.md`); HARDWARE-GATED for you (needs an NVIDIA GPU + the MM-Fi dataset). The upstream *shipped checkpoint* was **REFUTED** (0.08% PCK) — we publish that. |
+| OccWorld trajectory accuracy | DATA-GATED on a trained checkpoint; `predict()` carries `weights_trained=false` until one is loaded — never silently faked. |
+| Edge-skill detection accuracy (seizure, weapon, affect, …) | UNVALIDATED — every such module is now disclaimer-gated as experimental/research; the DSP is real, the accuracy is not claimed. |
+| 802.11bf-2025 OTA conformance | No commodity silicon ships a conformant interface as of 2026; ours is a simulation-tested forward-compat protocol model, not a certified implementation. |
+
+## Provenance
+
+Every claim above traces to a committed ADR (`docs/adr/ADR-154`…`ADR-163`), a
+test, a criterion bench, `benchmarks/wiflow-std/RESULTS.md`, or
+`benchmarks/edge-latency/RESULTS.md`. The history
+includes published **retractions** (the 92.9% PCK retraction; the WiFlow-STD
+shipped-checkpoint refutation; the NV-diamond BOM reality check) — a faker hides
+failures; we commit them.
@@ -6,8 +6,8 @@
  </a>
 </p>
 <p align="center">
-  <a href="https://cognitum.one/seed">
-    <img src="assets/seed.png" alt="Cognitum Seed" width="100%">
+  <a href="https://cognitum.one/marketplace/musica">
+    <img src="assets/musica-promo.png" alt="Cognitum Musica" width="100%">
  </a>
 </p>

@@ -58,7 +58,7 @@ RuView turns ordinary WiFi into a contactless sensor. A $9 ESP32 board reads the
 > | 💓 **Heart rate** | Bandpass 0.8–2.0 Hz, zero-crossing BPM | 40–120 BPM, real-time |
 > | 👤 **Presence detection** | Trained head on Hugging Face ([`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained); v2 encoder = 82.3% held-out temporal-triplet acc, honestly re-benchmarked) + a phase-variance fallback that needs no model | < 1 ms, ~30 s ambient calibration |
 > | 🧬 **CSI embeddings** | 128-dim contrastive encoder shipped on Hugging Face, 4-bit quantised variant fits in 8 KB | **164,183 emb/s** on M4 Pro |
-> | 🦴 **17-keypoint pose estimation** | `cog-pose-estimation` Cog v0.0.1 — signed aarch64 + x86_64 binaries on GCS, loads `pose_v1.safetensors` via Candle. Train your own from paired data in 2.1 s on an RTX 5080 ([ADR-101](docs/adr/ADR-101-pose-estimation-cog.md), [benchmarks](docs/benchmarks/pose-estimation-cog.md)). **SOTA on MM-Fi:** [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) hits **82.69% torso-PCK@20** (ensemble 83.59%), beating MultiFormer (72.25%) and CSI2Pose (68.41%) on the matched MM-Fi `random_split` protocol — self-corrected and auditable on [AetherArena](https://huggingface.co/spaces/ruvnet/aether-arena) | 8.4 ms cold-start on a Pi 5 |
+> | 🦴 **17-keypoint pose estimation** | `cog-pose-estimation` Cog v0.0.1 — signed aarch64 + x86_64 binaries on GCS, loads `pose_v1.safetensors` via Candle (the committed `pose_v1` is a **first-cut** on-device model: PCK@20 = 3.0%, below the ADR-079 ≥35% target, and its runtime path is still a `confidence=0` stub — see [Model weights: what's real, what's not](#model-weights-whats-real-whats-not); the **82.69%** figure below is the separate published MM-Fi benchmark, not this live cog). Train your own from paired data in 2.1 s on an RTX 5080 ([ADR-101](docs/adr/ADR-101-pose-estimation-cog.md), [benchmarks](docs/benchmarks/pose-estimation-cog.md)). **SOTA on MM-Fi:** [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) hits **82.69% torso-PCK@20** (ensemble 83.59%), beating MultiFormer (72.25%) and CSI2Pose (68.41%) on the matched MM-Fi `random_split` protocol — self-corrected and auditable on [AetherArena](https://huggingface.co/spaces/ruvnet/aether-arena) | 8.4 ms cold-start on a Pi 5 |
 > | 🚶 **Motion / activity** | Motion-band power + phase acceleration | Real-time |
 > | 🤸 **Fall detection** | Phase-acceleration threshold + 3-frame debounce + 5 s cooldown ([#263](https://github.com/ruvnet/RuView/issues/263)) | < 200 ms |
 > | 🧮 **Multi-person count** | Adaptive P95 normalisation + runtime-tunable dedup factor (`/api/v1/config/dedup-factor`, [#491](https://github.com/ruvnet/RuView/pull/491)). Six specialised learned counters available as Cogs: `occupancy-zones`, `elevator-count`, `queue-length`, `customer-flow`, `clean-room`, `person-matching` | Real-time, self-calibrating |
@@ -128,10 +128,12 @@ pip install "ruview[client]"              # or: pip install "wifi-densepose[clie
 >
 > | Option | Hardware | Cost | Full CSI | Capabilities |
 > |--------|----------|------|----------|-------------|
-> | **ESP32 + Cognitum Seed** (recommended) | ESP32-S3 + [Cognitum Seed](https://cognitum.one) | ~$140 | Yes | Presence, motion, breathing, heart rate, fall detection, multi-person counting, 17-keypoint pose (signed Cog binary), 105-cog catalog, persistent vector store, kNN search, witness chain, MCP proxy |
+> | **ESP32 + Cognitum Seed** (recommended) | ESP32-S3 + [Cognitum Seed](https://cognitum.one) | ~$140 | Yes | Presence, motion, breathing, heart rate, fall detection, multi-person counting, 17-keypoint pose (signed Cog binary — first-cut on-device model, see [Model weights: what's real, what's not](#model-weights-whats-real-whats-not)), 105-cog catalog, persistent vector store, kNN search, witness chain, MCP proxy |
 > | **ESP32 Mesh** | 3-6× ESP32-S3 + WiFi router | ~$54 | Yes | Same capabilities as above without the persistent-memory features |
 > | **ESP32-C6 research node** ([ADR-110](docs/adr/ADR-110-esp32-c6-firmware-extension.md), [witness](docs/WITNESS-LOG-110.md), [reviewer guide](docs/ADR-110-REVIEW-GUIDE.md), [firmware v0.7.0](https://github.com/ruvnet/RuView/releases/tag/v0.7.0-esp32)) | ESP32-C6-DevKit ($6–10) | ~$10 | Yes (Wi-Fi 6 capable) | Same CSI pipeline as S3 with the dual-target firmware. **Firmware-side ADR-110 substrate now closed** (v0.7.0): ESP-NOW cross-board mesh quantified at **99.56 % match / 104 µs smoothed offset stdev / 3.95× EMA suppression** over a 5-min two-board soak (witness §A0.10), 32-byte UDP sync packet with operator-tunable cadence (§A0.12), ADR-018 byte 19 bit 4 wire-fix sourced from the working ESP-NOW path (§A0.13). Wire format ready for HE-LTF PPDU tagging in ADR-018 bytes 18-19 (firmware encoder + Rust + Python decoders verified end-to-end across 23 unit tests). LP-core motion-gate RISC-V program and Wi-Fi 6 soft-AP with TWT Responder both ship as opt-in code paths (default off). **Hardware-gated for measurement**: HE-LTF live subcarrier capture needs an 11ax AP (IDF v5.4 doesn't expose AP-side HE config — §A0.6); ~5 µA LP-core hibernation needs an INA meter to capture; 802.15.4 raw RX is broken in IDF v5.4 (workaround: ESP-NOW transport, shipped + measured). See witness log for the empirical / claimed split. |
 > | **Research NIC** | Intel 5300 / Atheros AR9580 | ~$50-100 | Yes | Full CSI with 3x3 MIMO |
+> | **Qualcomm CSI beta** ([ADR-268](docs/adr/ADR-268-qualcomm-atheros-csi-platform.md)) | QCA9300 now; QCN9074/QCN9274 experimental | ~$30-200 | Simulator now; hardware adapter gated | Rust `QCS1` codec, deterministic replay, UDP/API integration; modern ath11k/ath12k profiles do not claim public CSI export |
+> | **Vendor provider beta** ([ADR-270](docs/adr/ADR-270-vendor-rf-sensing-integration-program.md)) | Origin, Plume, Mist, NETGEAR, Electric Imp, RF Solutions, Luma, Nest, Linksys, Wifigarden | Varies | Capability-dependent | Bounded Rust adapters and deterministic fixtures; telemetry/network-only/unsupported states cannot masquerade as CSI |
 > | **Any WiFi** | Windows, macOS, or Linux laptop | $0 | No | RSSI-only: coarse presence and motion (see [tutorial #36](https://github.com/ruvnet/RuView/issues/36)) |
 >
 > No hardware? Verify the signal processing pipeline with the deterministic reference signal: `python archive/v1/data/proof/verify.py`
@@ -143,7 +145,7 @@ pip install "ruview[client]"              # or: pip install "wifi-densepose[clie
    <img src="assets/v2-screen.png" alt="WiFi DensePose — Live pose detection with setup guide" width="800">
  </a>
  <br>
-  <em>Real-time pose skeleton from WiFi CSI signals — no cameras, no wearables</em>
+  <em>Real-time pose skeleton from WiFi CSI signals — no cameras, no wearables (demo visualization; the live CSI-only single-ESP32 17-keypoint model is still first-cut — see <a href="#model-weights-whats-real-whats-not">Model weights: what's real, what's not</a>)</em>
  <br><br>
  <a href="https://ruvnet.github.io/RuView/"><strong>▶ Live Observatory Demo</strong></a>
  &nbsp;|&nbsp;
@@ -155,7 +157,7 @@ pip install "ruview[client]"              # or: pip install "wifi-densepose[clie

 > The [server](#-quick-start) is optional for visualization and aggregation — the ESP32 [runs independently](#esp32-s3-hardware-pipeline) for presence detection, vital signs, and fall alerts.
 >
-> **Live ESP32 pipeline**: Connect an ESP32-S3 node → run the [sensing server](#sensing-server) → open the [pose fusion demo](https://ruvnet.github.io/RuView/pose-fusion.html) for real-time dual-modal pose estimation (webcam + WiFi CSI). See [ADR-059](docs/adr/ADR-059-live-esp32-csi-pipeline.md).
+> **Live ESP32 pipeline**: Connect an ESP32-S3 node → run the [sensing server](#sensing-server) → open the [pose fusion demo](https://ruvnet.github.io/RuView/pose-fusion.html) for real-time dual-modal pose estimation (webcam + WiFi CSI). See [ADR-059](docs/adr/ADR-059-live-esp32-csi-pipeline.md). (The webcam supplies ground-truth pose in this dual-modal demo; the CSI-only on-device 17-keypoint model is still first-cut — see [Model weights: what's real, what's not](#model-weights-whats-real-whats-not).)
 >
 > **three.js scene gallery** at [`/three.js/`](https://ruvnet.github.io/RuView/three.js/) — five progressively richer ADR-097 demos: helpers, cinematic, GLTF skinned, FBX skinned, and a live MediaPipe→Mixamo retargeting feed driven by ESP32 CSI. Demos 04 and 05 require a local Mixamo `X Bot.fbx` (license boundary — not redistributed).

@@ -194,7 +196,7 @@ The separate **17-keypoint pose-estimation model** is now published at [`ruvnet/
 | **Efficiency frontier** | [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](docs/benchmarks/wifi-pose-efficiency-frontier.md) | SOTA-beating WiFi pose in a 20 KB int4 edge model |
 | **Pretrained encoder** | [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) | 82.3% held-out temporal-triplet, 8 KB int4 |
 | **Reproducible proof (Trust Kill Switch)** | [`archive/v1/data/proof/verify.py`](archive/v1/data/proof/verify.py) + [`expected_features.sha256`](archive/v1/data/proof/expected_features.sha256) | one-command deterministic pipeline replay (SHA-256 of output vs published hash) |
-| **Benchmark-proof ADR** | [ADR-147](docs/adr/ADR-147-benchmark-proof.md) | how the numbers are produced and verified |
+| **Benchmark-proof ADR** | [ADR-168](docs/adr/ADR-168-benchmark-proof.md) | how the numbers are produced and verified |
 | **Witness attestation** | [`docs/WITNESS-LOG-028.md`](docs/WITNESS-LOG-028.md) | 33-row capability attestation matrix with per-claim evidence |

 ```bash
@@ -202,7 +204,26 @@ The separate **17-keypoint pose-estimation model** is now published at [`ruvnet/
 python archive/v1/data/proof/verify.py
 ```

-Tracked in [#509](https://github.com/ruvnet/RuView/issues/509); see [ADR-079](docs/adr/ADR-079-camera-supervised-pose-finetune.md) phases P7–P9 for the camera-supervised fine-tune path.
+Tracked in [#509](https://github.com/ruvnet/RuView/issues/509); see [ADR-079](docs/adr/ADR-079-camera-ground-truth-training.md) phases P7–P9 for the camera-supervised fine-tune path.
+
+### Model weights: what's real, what's not
+
+"WiFi → pose" means three different things in this repo, at three different maturity
+levels. Read the label, not the headline ([ADR-187](docs/adr/ADR-187-archive-v1-deprecation-honest-labeling.md)):
+
+| Tier | Checkpoint(s) | Honest status |
+|------|---------------|---------------|
+| **Real & validated** | [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) (CSI encoder + presence head) · [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) (17-keypoint pose) · `cog-person-count/count_v1` | **MEASURED / published.** Presence = 82.3% held-out temporal-triplet accuracy (the old "100% presence" figure was retracted); MM-Fi pose = 82.69% torso-PCK@20 on the `random_split` protocol. These are the pose/presence numbers the project stands behind today. |
+| **Real but weak (honestly labeled)** | committed `v2/crates/cog-pose-estimation/cog/artifacts/pose_v1.safetensors` | First-cut on-device model. **PCK@20 = 3.0% / PCK@50 = 18.5%** on a 217-sample holdout — **below the ADR-079 target of ≥ 35%.** Learns coarse structure (`r_hip` 77% PCK@50); distal/face joints near-random. Its runtime path in `cog-pose-estimation/src/inference.rs` is still a centred-skeleton **stub returning `confidence=0`** — the weights are not yet wired in. Full disclosure in the [cog README](v2/crates/cog-pose-estimation/cog/README.md). |
+| **Architecture only, no weights** | `archive/v1` `DensePoseHead` | Random `kaiming_normal_` init, **no checkpoint of any kind** (zero `.pth`/`.onnx`/`.safetensors` files under `archive/v1/`). Deprecated and superseded — see [`archive/v1/DEPRECATED.md`](archive/v1/DEPRECATED.md). Do not expect real pose output from it. |
+
+**On the ESP32-SISO question ([#509](https://github.com/ruvnet/RuView/issues/509)):** a
+single-antenna, 56-subcarrier CSI stream at a 20-frame window does *not* carry the
+fine-grained spatial information the multi-antenna NIC research relies on — the cog
+measurements above show distal/face joints near-random. The shippable pose accuracy the
+project can stand behind today is the **MM-Fi benchmark number**, not a live single-ESP32
+number. The path to a first *reproducible* on-device baseline (PCK@20 ≥ 35%) is tracked in
+[ADR-079](docs/adr/ADR-079-camera-ground-truth-training.md) / [#645](https://github.com/ruvnet/RuView/issues/645) — do not advertise the live single-ESP32 17-keypoint feature without the "first-cut, below-target, runtime-stub" caveat until that baseline is measured.


 ## 🧩 Edge Module Catalog
@@ -501,7 +522,7 @@ Every WiFi signal that passes through a room creates a unique fingerprint of tha
 **What it does in plain terms:**
 - Turns any WiFi signal into a 128-number "fingerprint" that uniquely describes what's happening in a room
 - Learns entirely on its own from raw WiFi data — no cameras, no labeling, no human supervision needed
- Recognizes rooms, detects intruders, identifies people, and classifies activities using only WiFi
+- Recognizes rooms, detects intruders, and classifies activities using only WiFi (named person-identity is an experimental, data-gated research capability — see below, not a shipped feature)
 - Runs on an $8 ESP32 chip (the entire model fits in 55 KB of memory)
 - Produces both body pose tracking AND environment fingerprints in a single computation

@@ -512,7 +533,7 @@ Every WiFi signal that passes through a room creates a unique fingerprint of tha
 | **Self-supervised learning** | The model watches WiFi signals and teaches itself what "similar" and "different" look like, without any human-labeled data | Deploy anywhere — just plug in a WiFi sensor and wait 10 minutes |
 | **Room identification** | Each room produces a distinct WiFi fingerprint pattern | Know which room someone is in without GPS or beacons |
 | **Anomaly detection** | An unexpected person or event creates a fingerprint that doesn't match anything seen before | Automatic intrusion and fall detection as a free byproduct |
-| **Person re-identification** | Each person disturbs WiFi in a slightly different way, creating a personal signature | Track individuals across sessions without cameras |
+| **Person re-identification** *(experimental, research)* | A real per-channel similarity matcher (Soul Signature §3.6, `wifi-densepose-bfld`); **measured** result: on WiFi-only cardiac+respiratory channels alone two people are *not* separable (gap ~0.0005) | Honest research capability — **named identity is not claimed** and is data-gated on enrollment with the decisive AETHER/body-resonance channel. See [#1021](https://github.com/ruvnet/RuView/issues/1021) |
 | **Environment adaptation** | MicroLoRA adapters (1,792 parameters per room) fine-tune the model for each new space | Adapts to a new room with minimal data — 93% less than retraining from scratch |
 | **Memory preservation** | EWC++ regularization remembers what was learned during pretraining | Switching to a new task doesn't erase prior knowledge |
 | **Hard-negative mining** | Training focuses on the most confusing examples to learn faster | Better accuracy with the same amount of training data |
@@ -601,6 +622,8 @@ claude --plugin-dir ./plugins/ruview

 Verify the plugin structure: `bash plugins/ruview/scripts/smoke.sh`. Full details: [`plugins/ruview/README.md`](plugins/ruview/README.md).

+**Portable harness — `npx @ruvnet/ruview`:** a lighter, host-portable companion to the in-repo plugin, minted via [MetaHarness](https://www.npmjs.com/package/metaharness) and hardened per [ADR-182](docs/adr/ADR-182-npx-ruview-harness-via-metaharness.md). It runs **without cloning this repo** and on more hosts (Claude Code, Codex, Copilot, opencode, …), exposing the RuView operator tools (`onboard`, `verify`, `node_monitor`, `calibrate`, `node_flash`) over an MCP server — plus the project's **MEASURED-vs-CLAIMED honesty guardrail enforced in code** (`ruview.claim_check` flags untagged or retracted-"100%" accuracy claims). v0.1: the onboarding/verify/claim-check paths are tested (17/17, `verify.py` → PASS); the hardware tools are fail-closed wrappers. Try `npx @ruvnet/ruview` to onboard, or `npx @ruvnet/ruview claim-check --text "…"`. Source: [`harness/ruview/`](harness/ruview/README.md).
+
 ---

 ## 📖 Documentation
@@ -610,15 +633,17 @@ Verify the plugin structure: `bash plugins/ruview/scripts/smoke.sh`. Full detail
 | [User Guide](docs/user-guide.md) | Step-by-step guide: installation, first run, API usage, hardware setup, training |
 | [Build Guide](docs/build-guide.md) | Building from source (Rust and Python) |
 | [**Home Assistant + Matter Integration**](docs/integrations/home-assistant.md) | **Works with Home Assistant** via MQTT auto-discovery + **Works with Matter** (Apple Home / Google Home / Alexa / SmartThings) — full entity catalog, 3 starter blueprints, Lovelace dashboards, privacy mode, threshold tuning ([ADR-115](docs/adr/ADR-115-home-assistant-integration.md)). |
-| [**BFLD — Beamforming Feedback Layer for Detection**](v2/crates/wifi-densepose-bfld/README.md) | New privacy-gated WiFi sensing layer that measures + structurally prevents identity leakage from 802.11ac/ax Beamforming Feedback Information. Three type-enforced invariants (raw BFI never exits node, identity embedding is in-RAM-only, cross-site correlation cryptographically impossible via per-site BLAKE3 keyed hash + daily rotation). Ships full operator surface (`BfldPipeline`, `BfldPipelineHandle`, Soul Signature `SoulMatchOracle` integration), MQTT topic router + HA-DISCO + availability + LWT, 3 operator HA blueprints, two runnable examples, eclipse-mosquitto:2 CI service container. 327+ tests. [ADR-118](docs/adr/ADR-118-bfld-beamforming-feedback-layer-for-detection.md) umbrella + sub-ADRs [119](docs/adr/ADR-119-bfld-frame-format-and-wire-protocol.md)/[120](docs/adr/ADR-120-bfld-privacy-class-and-hash-rotation.md)/[121](docs/adr/ADR-121-bfld-identity-risk-scoring.md)/[122](docs/adr/ADR-122-bfld-ruview-ha-matter-exposure.md)/[123](docs/adr/ADR-123-bfld-capture-path-nexmon-and-esp32.md). Research dossier: [`docs/research/BFLD/`](docs/research/BFLD/) (11 files, 13,544 words). |
+| [**BFLD — Beamforming Feedback Layer for Detection**](v2/crates/wifi-densepose-bfld/README.md) | New privacy-gated WiFi sensing layer that measures + structurally prevents identity leakage from 802.11ac/ax Beamforming Feedback Information. Three type-enforced invariants (raw BFI never exits node, identity embedding is in-RAM-only, cross-site correlation cryptographically impossible via per-site BLAKE3 keyed hash + daily rotation). Ships full operator surface (`BfldPipeline`, `BfldPipelineHandle`, the Soul Signature §3.6 per-channel matcher `EnrolledMatcher`/`SoulMatchOracle` — experimental; named identity is data-gated, **measured** as not-separable on WiFi-only channels alone), MQTT topic router + HA-DISCO + availability + LWT, 3 operator HA blueprints, two runnable examples, eclipse-mosquitto:2 CI service container. 327+ tests. [ADR-118](docs/adr/ADR-118-bfld-beamforming-feedback-layer-for-detection.md) umbrella + sub-ADRs [119](docs/adr/ADR-119-bfld-frame-format-and-wire-protocol.md)/[120](docs/adr/ADR-120-bfld-privacy-class-and-hash-rotation.md)/[121](docs/adr/ADR-121-bfld-identity-risk-scoring.md)/[122](docs/adr/ADR-122-bfld-ruview-ha-matter-exposure.md)/[123](docs/adr/ADR-123-bfld-capture-path-nexmon-and-esp32.md). Research dossier: [`docs/research/BFLD/`](docs/research/BFLD/) (11 files, 13,544 words). |
 | [**SENSE-BRIDGE — rvagent MCP server**](tools/ruview-mcp/README.md) | Dual-transport MCP server (`@ruvnet/rvagent`) bridging the RuView sensing stack to AI agents (Claude Code, Cursor, ruflo swarms). 6 tools wired: `ruview.presence.now`, `ruview.vitals.get_{breathing,heart_rate,all}`, `ruview.bfld.last_scan`, `ruview.bfld.subscribe`. stdio + Streamable HTTP (`POST /mcp`, Origin-validated, bearer-token auth, `127.0.0.1` bind). Full 20-tool Zod schema barrel + 5 RUVIEW-POLICY governance tools. 93 tests. [ADR-124](docs/adr/ADR-124-rvagent-mcp-ruvector-npm-integration.md). Try: `npx @ruvnet/rvagent stdio`. |
 | [Semantic Primitives — Precision/Recall](docs/integrations/semantic-primitives-metrics.md) | Per-primitive F1 on the held-out paired-capture set: someone-sleeping, possible-distress, room-active, elderly-inactivity-anomaly, meeting, bathroom, fall-risk, bed-exit, no-movement, multi-room. |
 | [Claude Code / Codex Plugin](plugins/ruview/README.md) | The `ruview` plugin + marketplace — skills, `/ruview-*` commands, agents, and the Codex prompt mirror |
-| [Architecture Decisions](docs/adr/README.md) | 96 ADRs — why each technical choice was made, organized by domain (hardware, signal processing, ML, platform, infrastructure) |
+| [Portable harness — `npx @ruvnet/ruview`](harness/ruview/README.md) | MetaHarness-minted, host-portable RuView operator harness — `ruview.*` MCP tools + the MEASURED-vs-CLAIMED honesty guardrail enforced in code ([ADR-182](docs/adr/ADR-182-npx-ruview-harness-via-metaharness.md)). A lighter, multi-host companion to the in-repo plugin. |
+| [Architecture Decisions](docs/adr/README.md) | 205 ADRs — why each technical choice was made, organized by domain (hardware, signal processing, ML, platform, infrastructure) |
 | [Domain Models](docs/ddd/README.md) | 8 DDD models (RuvSense, Signal Processing, Training Pipeline, Hardware Platform, Sensing Server, WiFi-Mat, CHCI, rvCSI) — bounded contexts, aggregates, domain events, and ubiquitous language |
 | [rvCSI — edge RF sensing runtime](https://github.com/ruvnet/rvcsi) | Rust-first / TypeScript-accessible / hardware-abstracted CSI runtime: multi-source ingestion (incl. real nexmon_csi `.pcap` from a **Raspberry Pi 5** / Pi 4 / Pi 3B+ — CYW43455 / BCM43455c0) → validation → DSP → typed events → RuVector RF memory ([ADR-095](docs/adr/ADR-095-rvcsi-edge-rf-sensing-platform.md), [ADR-096](docs/adr/ADR-096-rvcsi-ffi-crate-layout.md), [domain model](docs/ddd/rvcsi-domain-model.md)). Now its own repo — [`ruvnet/rvcsi`](https://github.com/ruvnet/rvcsi) — vendored here under `vendor/rvcsi`; 9 `rvcsi-*` crates on crates.io, `@ruv/rvcsi` on npm, plus a Claude Code plugin. |
 | [Desktop App](v2/crates/wifi-densepose-desktop/README.md) | **WIP** — Tauri v2 desktop app for node management, OTA updates, WASM deployment, and mesh visualization |
 | `ruview-swarm` | Drone swarm control system (ADR-148) — hierarchical-mesh topology, Raft consensus, MARL, CSI sensing payload, MAVLink/PX4/ArduPilot compatibility, Ruflo AI-agent integration |
+| `ruview-unified` | Unified RF spatial world model ([ADR-273](docs/adr/ADR-273-unified-rf-spatial-world-model.md)..[277](docs/adr/ADR-277-edge-sensing-control-plane.md)) — canonical RF tensor + hardware adapters (WiFi CSI / FMCW radar / UWB / 5G SRS), universal RF foundation encoder with ≤1% task adapters, RF-aware Gaussian spatial memory with channel-gain queries + inverse updates, physics-guided synthetic RF worlds, and an 802.11bf/ETSI-ISAC-aligned sensing policy plane (raw RF structurally unexportable). All accuracy numbers SYNTHETIC until real-data validation. |
 | [Medical Examples](examples/medical/README.md) | Contactless blood pressure, heart rate, breathing rate via 60 GHz mmWave radar — $15 hardware, no wearable |
 | [Extended Documentation](docs/readme-details.md) | Latest additions, key features, installation, quick start, signal processing, training, CLI, testing, deployment, and changelog |

@@ -0,0 +1,49 @@
+# ⚠️ DEPRECATED — `archive/v1` is unmaintained and superseded
+
+**Do not build new work on this tree.** `archive/v1` is the original pure-Python
+implementation of WiFi-DensePose. It is kept only as a research archive
+(per [ADR-117 §1.3](../../docs/adr/ADR-117-pip-wifi-densepose-modernization.md)) and
+as the host of one still-live deterministic proof (see "What still lives here" below).
+Everything else in this directory is frozen and receives no fixes, reviews, or support.
+
+Governed by [ADR-187](../../docs/adr/ADR-187-archive-v1-deprecation-honest-labeling.md).
+
+## The one honest fact that trips people up
+
+`archive/v1/src/models/densepose_head.py` defines a `DensePoseHead` neural-network
+architecture (segmentation + UV-regression heads). **It ships no trained weights.** Its
+`_initialize_weights()` uses `kaiming_normal_` **random initialization only** — there is
+no checkpoint-loading path in the class, and there are **zero** `.pth` / `.onnx` /
+`.safetensors` / `.pt` / `.ckpt` / `.bin` files anywhere under `archive/v1/`.
+
+So: the architecture is *defined*, but it is **architecture-only**. Running it produces
+random output, not real pose accuracy. This matches the technical review in
+[#509](https://github.com/ruvnet/RuView/issues/509) — for *this tree*, the "network
+defined, no pre-trained weights" observation is TRUE.
+
+Real, trained, benchmarked weights **do** exist — just not here. They live in the
+maintained `v2/` workspace and on Hugging Face (see next section).
+
+## Use the maintained path instead
+
+| You want… | Go here |
+|-----------|---------|
+| The maintained implementation | The **`v2/` Rust workspace** (repo root `../../v2/`) |
+| A pip install | `pip install ruview` **or** `pip install wifi-densepose` (2.x) — the compiled PyO3 wheel ([ADR-117](../../docs/adr/ADR-117-pip-wifi-densepose-modernization.md)). The `wifi-densepose` **1.x** line is tombstoned on PyPI: `1.99.0` raises an `ImportError` telling you to migrate. |
+| Real trained presence/encoder weights | [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) — 82.3% held-out temporal-triplet accuracy |
+| A real 17-keypoint pose model | [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) — 82.69% torso-PCK@20 on MM-Fi `random_split` |
+| The honest three-tier weights picture | The "Model weights: what's real, what's not" table in the root [`README.md`](../../README.md) and [`docs/user-guide.md`](../../docs/user-guide.md) |
+
+## What still lives here (intentionally)
+
+Only one thing under `archive/v1/` is still a live, cited signal: the deterministic
+reference-pipeline proof —
+
+```bash
+python archive/v1/data/proof/verify.py   # must print VERDICT: PASS
+```
+
+This is the ADR-028 "Trust Kill Switch": it feeds a fixed reference signal through the
+signal-processing pipeline and checks the SHA-256 of the output against a published hash.
+It is a legitimate reproducibility witness and is **not** deprecated. Everything else in
+this tree is.
@@ -1,3 +1,19 @@
+> ## ⚠️ DEPRECATED — unmaintained and superseded
+>
+> This tree is the **original pure-Python implementation** and is kept only as a research
+> archive. It receives no fixes, reviews, or support. **Read [`DEPRECATED.md`](DEPRECATED.md) before using anything below.**
+>
+> - Its `DensePoseHead` is **architecture-only with random-initialized weights and ships no
+>   trained checkpoint** — running it produces random output, not real pose accuracy.
+> - The maintained path is the **`v2/` Rust workspace** and the `wifi-densepose 2.x` / `ruview`
+>   pip wheel ([ADR-117](../../docs/adr/ADR-117-pip-wifi-densepose-modernization.md)). The
+>   `wifi-densepose` 1.x line is tombstoned on PyPI (1.99.0 raises `ImportError`).
+> - Real trained weights live elsewhere: [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained)
+>   (presence, 82.3%) and [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose)
+>   (17-keypoint pose, 82.69% torso-PCK@20).
+> - The only still-live artifact here is the deterministic proof `data/proof/verify.py`
+>   (ADR-028), which stays. See [ADR-187](../../docs/adr/ADR-187-archive-v1-deprecation-honest-labeling.md).
+
 # WiFi-DensePose v1 (Python Implementation)

 This directory contains the original Python implementation of WiFi-DensePose.
@@ -2,6 +2,7 @@
 Health check API endpoints
 """

+import asyncio
 import logging
 import psutil
 from typing import Dict, Any, Optional
@@ -168,7 +169,7 @@ async def health_check(request: Request):
            overall_status = "degraded"
        
        # Get system metrics
-        system_metrics = get_system_metrics()
+        system_metrics = await asyncio.to_thread(get_system_metrics)
        
        uptime_seconds = (datetime.now() - _APP_START_TIME).total_seconds()
        
@@ -263,11 +264,12 @@ async def get_health_metrics(
 ):
    """Get detailed system metrics."""
    try:
-        metrics = get_system_metrics()
+        metrics = await asyncio.to_thread(get_system_metrics)
        
        # Add additional metrics if authenticated
        if current_user:
-            metrics.update(get_detailed_metrics())
+            detailed = await asyncio.to_thread(get_detailed_metrics)
+            metrics.update(detailed)
        
        return {
            "timestamp": datetime.utcnow().isoformat(),
@@ -300,7 +302,7 @@ def get_system_metrics() -> Dict[str, Any]:
    """Get basic system metrics."""
    try:
        # CPU metrics
-        cpu_percent = psutil.cpu_percent(interval=1)
+        cpu_percent = psutil.cpu_percent(interval=None)
        cpu_count = psutil.cpu_count()
        
        # Memory metrics
@@ -221,11 +221,15 @@ class ESP32BinaryParser:

        snr = float(rssi - noise_floor)
        frequency = float(freq_mhz) * 1e6
-        bandwidth = 20e6  # default; could infer from n_subcarriers

-        if n_subcarriers <= 56:
+        # Bandwidth inference (issue #1005): HE-LTF uses a 4x denser tone
+        # grid than HT-LTF on the same channel width — an HE-SU frame with
+        # 256 bins (242 active HE20 tones) is a *20 MHz* capture, not 160.
+        if ppdu_byte in (1, 2, 3):  # HE-SU / HE-MU / HE-TB
+            bandwidth = 40e6 if (flags_byte & 0x01) or n_subcarriers > 256 else 20e6
+        elif n_subcarriers <= 64:  # ESP32 HT20 delivers the full 64-bin FFT
            bandwidth = 20e6
-        elif n_subcarriers <= 114:
+        elif n_subcarriers <= 128:
            bandwidth = 40e6
        elif n_subcarriers <= 242:
            bandwidth = 80e6
@@ -180,21 +180,24 @@ class MetricsService:
    async def _collect_system_metrics(self):
        """Collect system-level metrics."""
        try:
-            # CPU usage
-            cpu_percent = psutil.cpu_percent(interval=1)
+            # Query OS metrics in a background thread to prevent blocking the event loop
+            def gather_metrics():
+                return (
+                    psutil.cpu_percent(interval=None),
+                    psutil.virtual_memory().percent,
+                    psutil.disk_usage('/'),
+                    psutil.net_io_counters()
+                )
+            
+            cpu_percent, mem_percent, disk, network = await asyncio.to_thread(gather_metrics)
+            
+            # Record metrics on the main loop
            self._metrics["system_cpu_usage"].add_point(cpu_percent)
+            self._metrics["system_memory_usage"].add_point(mem_percent)
            
-            # Memory usage
-            memory = psutil.virtual_memory()
-            self._metrics["system_memory_usage"].add_point(memory.percent)
-            
-            # Disk usage
-            disk = psutil.disk_usage('/')
            disk_percent = (disk.used / disk.total) * 100
            self._metrics["system_disk_usage"].add_point(disk_percent)
            
-            # Network I/O
-            network = psutil.net_io_counters()
            self._metrics["system_network_bytes_sent"].add_point(network.bytes_sent)
            self._metrics["system_network_bytes_recv"].add_point(network.bytes_recv)
            
@@ -0,0 +1,59 @@
+import asyncio
+import time
+import os
+import sys
+
+import pytest
+
+# Add project root and archive/v1 to sys.path so we can import src modules
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../../")))
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from archive.v1.src.api.routers.health import get_system_metrics
+
+async def ticker():
+    """Asynchronous background ticker to measure event loop latency/freezes."""
+    ticks = []
+    for _ in range(15):
+        ticks.append(time.time())
+        await asyncio.sleep(0.1)
+    return ticks
+
+async def run_test():
+    print("Starting concurrency verification test...")
+    
+    # Start the ticker background task
+    ticker_task = asyncio.create_task(ticker())
+    
+    # Let ticker run for a few ticks
+    await asyncio.sleep(0.3)
+    
+    print("Calling get_system_metrics offloaded to background thread...")
+    start_time = time.time()
+    
+    # Query system metrics using to_thread (simulating FastAPI request)
+    metrics = await asyncio.to_thread(get_system_metrics)
+    
+    duration = time.time() - start_time
+    print(f"get_system_metrics took: {duration:.4f}s")
+    
+    # Wait for the ticker to complete
+    ticks = await ticker_task
+    
+    # Calculate gaps between consecutive ticks to check for event loop freezes
+    gaps = [ticks[i+1] - ticks[i] for i in range(len(ticks)-1)]
+    max_gap = max(gaps)
+    
+    print(f"All tick gaps: {[round(g, 3) for g in gaps]}")
+    print(f"Max event loop freeze: {max_gap:.4f}s")
+    
+    # In pre-fix code, psutil.cpu_percent(interval=1) blocks for 1.0s,
+    # causing a gap of >1.0s. With our fix, it should be close to 0.1s.
+    return max_gap, duration
+
+@pytest.mark.asyncio
+async def test_get_system_metrics_does_not_starve_event_loop():
+    max_gap, duration = await run_test()
+    # ticker sleeps 0.1s; allow slack for CI, but we should not see ~1s gaps
+    assert max_gap < 0.6
+    assert duration < 0.6
@@ -0,0 +1,137 @@
+# Edge-Latency Benchmark Results — ADR-163
+
+Converting **CLAIMED** edge latency budgets into **MEASURED-on-host** numbers,
+closing the measurement debt flagged by Milestones 5/6 (ADR-159 / ADR-160).
+Benches + docs only — **no production-code behavior changed**.
+
+## The honest caveat, up front (read before citing any number)
+
+Two distinct gaps separate every number below from the figure it is converting:
+
+1. **Host ≠ ESP32.** The wasm-edge skill modules document budgets *"on ESP32-S3
+   WASM3"* (e.g. `exo_time_crystal`: "H (<10 ms)"). These benches run **native
+   x86_64 on a development laptop**, not the Xtensa/WASM3 target. A native host
+   median is an **upper bound on the algorithm's work**, not the ESP32 number.
+   WASM3 interpretation on a ~240 MHz Xtensa core is typically 1–2 orders of
+   magnitude slower than native `-O` host code, so a host median far under the
+   budget **does NOT prove the ESP32 meets it.** *The ESP32 figure is NOT
+   reproduced here — it needs hardware.*
+
+2. **Bench ≠ the doc-claimed measurement.** For the cogs, the manifest cites a
+   **cold-start** number (`cold_start_ms_avg`, weight-load included); these
+   benches measure **steady-state** per-frame `infer` (warm, weights resident).
+   Different measurements; we report both, labelled.
+
+Grades (per `benchmarks/wiflow-std/RESULTS.md` / ADR-152 vocabulary):
+- **MEASURED-on-host** — reproduced in this repo on the machine below, exact
+  command recorded. NOT the ESP32 / NOT the cold-start figure.
+- **CLAIMED (ESP32)** — the doc budget; UNMEASURED on hardware here.
+
+## Machine
+
+| | |
+|---|---|
+| Host | `ruvzen` (Windows 11, this dev box) |
+| CPU | Intel Core Ultra 9 285H |
+| Toolchain | `cargo 1.91.1`, `--release` (opt-level per crate profile) |
+| Bench harness | criterion 0.5 (`time: [low **median** high]` reported below) |
+| Date | 2026-06-12 |
+
+Run-to-run spread on this box is non-trivial (criterion's low/high bracket the
+median by a few %); the medians below are single-session captures with the smoke
+settings `--warm-up-time 1 --measurement-time 2` (wasm-edge) / `3` (cogs). Re-run
+for your own machine — the absolute numbers are host-specific.
+
+---
+
+## T1 — wasm-edge `process_frame` hot paths (ADR-160 deferred item → DONE host)
+
+The crate is **excluded from the v2 workspace**; bench from the crate dir.
+
+```bash
+cd v2/crates/wifi-densepose-wasm-edge
+cargo bench --features std -- --warm-up-time 1 --measurement-time 2
+# med_seizure_detect is medical-experimental-gated:
+cargo bench --features std,medical-experimental -- --warm-up-time 1 --measurement-time 2 med_seizure
+```
+
+| Hot path (M6-audit-named) | Bench id | Host median | Grade | Doc budget (CLAIMED, ESP32) |
+|---|---|---|---|---|
+| `exo_time_crystal` 256-pt × 128-lag autocorrelation (full buffer) | `exo_time_crystal::process_frame[autocorr_256x128]` | **17.3 µs** | MEASURED-on-host | "H (<10 ms) on ESP32-S3 WASM3" — **NOT reproduced here (needs hardware)** |
+| `exo_ghost_hunter` empty-room periodicity + hidden-breathing | `exo_ghost_hunter::process_frame[empty_room_periodicity]` | **1.44 µs** | MEASURED-on-host | research/exotic; no firm ESP32 figure — host proxy only |
+| `sec_weapon_detect` per-subcarrier Welford (MAX_SC=32) | `sec_weapon_detect::process_frame[per_sc_welford]` | **0.42 µs** (420 ns) | MEASURED-on-host | research-grade; calibration-gated — host proxy only |
+| `med_seizure_detect` clonic-phase rhythm path (steady-state frame) | `med_seizure_detect::process_frame[clonic_rhythm]` | **0.10 µs** (105 ns) | MEASURED-on-host (feature-gated) | doc budget "S (<5 ms) on ESP32"; **NOT reproduced here** |
+
+Reading these honestly:
+
+- `exo_time_crystal` at **17.3 µs host** is the only one whose host cost is even
+  in the same *thousandths* of its 10 ms ESP32 budget — it does the most work
+  (~32K MACs/frame). 17.3 µs native says the algorithm is cheap; it says
+  **nothing** about whether WASM3-on-Xtensa lands under 10 ms. A naïve
+  host→ESP32 extrapolation (assume 100× interpreter+clock penalty) would put it
+  near ~1.7 ms, comfortably under — **but that is an extrapolation, not a
+  measurement**, and is recorded here only to show the host number is not
+  obviously in tension with the budget. ESP32 figure: **UNMEASURED**.
+- `med_seizure_detect`'s 105 ns is the **steady-state** per-frame cost; the
+  expensive clonic autocorrelation only fires when the state machine is in the
+  clonic phase, so this is a lower-bound on the heavy path, not the worst case.
+  It is still a real, committed host datapoint.
+- The pre-existing `tests/budget_compliance.rs` already asserts the L/S/H
+  wall-clock tiers (25 passing tests); these criterion benches add the
+  regression-grade, reproducible median that ADR-160 deferred.
+
+---
+
+## T2 — cog steady-state inference latency (ADR-159/160 deferred item → DONE)
+
+Cog crates are normal workspace members; bench from `v2/`. Real weights
+(`count_v1.safetensors` / `pose_v1.safetensors`) ship in-repo under each cog's
+`cog/artifacts/`, so the bench measures the **real Candle CPU forward**, not the
+stub (the bench `assert!`s `backend().starts_with("candle-")`).
+
+```bash
+cd v2
+cargo bench -p cog-person-count  --no-default-features --bench infer_bench -- --warm-up-time 1 --measurement-time 3
+cargo bench -p cog-pose-estimation --no-default-features --bench infer_bench -- --warm-up-time 1 --measurement-time 3
+```
+
+| Cog | Bench id | Host median (steady-state infer, CPU) | Grade | Manifest cold-start (CLAIMED, different measurement + machine) |
+|---|---|---|---|---|
+| cog-person-count | `cog_person_count::infer[cpu_real_weights_steady_state]` | **305 µs** (idle box) | MEASURED-on-host | — (person-count manifest carries comparable provenance) |
+| cog-pose-estimation | `cog_pose_estimation::infer[cpu_real_weights_steady_state]` | **305 µs** (idle box) | MEASURED-on-host | `cold_start_ms_avg: 5.4` (30 invocations, **ruvultra/RTX 5080 host**, candle 0.9 cpu) — **cold-start, NOT steady-state; NOT this machine** |
+
+> Spread caveat (observed, honest): both medians above were captured with the box
+> otherwise idle. A re-run of the validate-form command *while a second cargo job
+> was loading the same cores* gave 385 µs (person-count) / 973 µs (pose) —
+> the criterion low/high bracket widens to ~0.34–1.18 ms under contention. The
+> 305 µs figures are the idle-box datapoints; the absolute number is host- and
+> load-dependent (the ~10× pose swing is core contention, not a code change).
+
+Reading these honestly:
+
+- **Steady-state ≠ cold-start.** The pose manifest's `5.4 ms` folds in one-time
+  weight load / mmap / first-forward allocation. This bench warms the engine
+  first and times only the recurring per-frame forward, on a *different
+  machine*. The two numbers are not comparable and we do not claim this bench
+  reproduces the 5.4 ms manifest figure.
+- Both cogs share the same conv encoder; person-count adds a count head +
+  confidence head, pose adds a 256-wide MLP head. The host steady-state cost is
+  dominated by the three dilated Conv1d layers (56→64→128→128) shared by both —
+  which is why both land at ~305 µs.
+- **Empirical confirmation of the steady-state/cold-start gap:** pose
+  steady-state (305 µs host) is ~18× *under* the manifest's 5.4 ms cold-start.
+  Even accounting for the different machine, this is the expected shape — the
+  bulk of cold-start is one-time setup, not the forward pass — and it is exactly
+  why conflating the two would be dishonest.
+
+---
+
+## Status vs the deferred items
+
+| Deferred item | Was | Now |
+|---|---|---|
+| ADR-160 "Criterion benches for `process_frame` budget claims" | ACCEPTED-FUTURE | **DONE (host)**; ESP32-on-hardware still **PENDING** (needs the wasm32 target + a flashed ESP32-S3) |
+| ADR-159/160 cog inference latency (`cold_start_ms_avg` uncommitted-benched) | CLAIMED | **MEASURED-on-host (steady-state)**; cold-start-on-ruvultra remains the manifest's separate claim |
+
+Nothing here changes runtime behavior — these are benches + this results file
+only. No crate needs republishing.
@@ -0,0 +1,132 @@
+# Edge-Skill Synthetic-Ground-Truth Validation — RESULTS
+
+**Crate:** `v2/crates/wifi-densepose-wasm-edge` (workspace-EXCLUDED — build from its own dir)
+**Branch:** `feat/edge-skills-synthetic-validation`
+**ADR:** [ADR-160](../../docs/adr/ADR-160-edge-skill-library-honest-labeling.md)
+**Date:** 2026-06-13
+**Harness:** `tests/synthetic_validation.rs`
+
+> **HONESTY BOUNDARY — read first.** Everything below is **synthetic-ground-truth
+> validation**: a signal is *planted* with a known answer, the **real** detector
+> is run, and detection accuracy / precision / recall / rate-error is **measured**.
+> This is **NOT field accuracy.** A skill that recovers a planted sinusoid here is
+> proven to do the math it claims on a *constructed* signal; it is **NOT** proven
+> to work on real CSI in a real room. Skills whose detection target cannot be
+> honestly planted (clinical, weapon, affect, sleep-stage, sign-language) are
+> **NOT** given a number — they are listed under **DATA-GATED** with the real
+> data each would require.
+
+## Reproduce
+
+```bash
+cd v2/crates/wifi-densepose-wasm-edge   # workspace-excluded; build here
+cargo test --features std --test synthetic_validation -- --nocapture
+# also runs under the medical tier (med_* skills stay DATA-GATED, not validated):
+cargo test --features std,medical-experimental --test synthetic_validation -- --nocapture
+```
+
+Each `MEASURED-on-synthetic | …` line printed by the harness is the source of the
+table below. Numbers are deterministic (no RNG; pseudo-noise uses a fixed LCG seed).
+
+---
+
+## MEASURED-on-synthetic (constructible skills)
+
+| Skill | What was planted (ground truth) | Result | Grade |
+|-------|----------------------------------|--------|-------|
+| **vital_trend** | BPM held N≥6 calls at each threshold band (brady/tachy-pnea <12 / >25, brady/tachy-cardia <50 / >120, apnea breathing<1.0 for ≥20) vs normal | **acc 1.000, prec 1.000, recall 1.000** (TP5 FP0 TN5 FN0) | MEASURED |
+| **exo_time_crystal** | period-2 coordinated motion vs pseudo-noise + flat | **acc 1.000** (TP1 FP0 TN2 FN0) | MEASURED † |
+| **exo_ghost_hunter** (hidden breathing) | phase sinusoid at lag-8 (breathing band 5–15) in an empty room vs flat phase | **acc 1.000**; planted score **1.000**, flat **0.000** | MEASURED |
+| **occupancy** | 220-frame flat-amplitude calibration, then strong per-zone amplitude variance vs flat | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
+| **intrusion** | calibrate→arm (330 quiet frames), then per-subcarrier Δphase>1.5 + Δamp≫3σ vs quiet | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
+| **exo_rain_detect** | empty room, 60-frame baseline, then broadband variance (8/8 groups, ratio≫2.5) for ≥10 frames vs stable-low | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
+| **sig_flash_attention** | sustained high phase+amplitude in each of the 8 subcarrier groups; assert reported attention peak == planted group | **peak-localization 8/8 = 1.000** | MEASURED |
+| **spt_spiking_tracker** | sparse (2-subcarrier) large phase-delta in each of the 4 zones; assert tracked zone == planted zone | **zone-localization 4/4 = 1.000** | MEASURED ‡ |
+| **sig_optimal_transport** | sustained large frame-to-frame amplitude-distribution change vs stationary | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
+| **sig_mincut_person_match** | 2 persons with distinct stable per-region variance signatures over 40 frames | **person ids assigned, 0 id-swaps / 40 frames** | MEASURED |
+| **lrn_dtw_gesture_learn** | stillness → 3 identical gesture rehearsals → enrollment | **template enrolled (templates=1)** | MEASURED (enroll) §|
+| **sig_sparse_recovery** | 30 clean frames to init, then 8/32 (25%) nulled subcarriers | **dropout-detect + recovery-trigger = PASS** | MEASURED (trigger) ¶|
+
+### Caveats on individual results
+
+† **exo_time_crystal — honest discriminative limit.** A *pure* periodic signal
+already has autocorrelation peaks at lag L **and** 2L (natural harmonics), so this
+"period-doubling" detector cannot separate a true period-2 sub-harmonic from a
+plain periodic signal — an earlier plant using a clean sine produced a *false
+positive* (recorded during development). The construct it **can** discriminate
+with known ground truth is **periodic-coordination vs aperiodic** (noise/flat),
+which is what is measured (1.000). The original "sub-harmonic vs clean period"
+claim is **NOT** validatable with this algorithm.
+
+‡ **spt_spiking_tracker — plant must be sparse.** With weights init'd home=1.0 /
+cross=0.25, firing all 8 inputs in a zone (8×0.25=2.0 > threshold 1.0) overdrives
+*every* output neuron and the tracker collapses to zone 0 (measured 1/4 during
+development). Firing only 2 inputs (home 2.0 fires, cross 0.5 silent) yields clean
+4/4 zone localization. The validatable claim is *single-zone* localization.
+
+§ **lrn_dtw_gesture_learn — enrollment validated; replay-match NOT.** The
+deterministic, constructible part (stillness → 3 identical rehearsals → a template
+is enrolled) is MEASURED. The DTW *replay match* (731) did **not** fire on the
+identical replay in this run (`match_same=false`) — replay-recognition accuracy is
+**reported, not asserted**, and is not claimed as validated.
+
+¶ **sig_sparse_recovery — trigger validated; recovery accuracy is NEGATIVE.**
+The dropout-detection + ISTA-recovery *trigger* pipeline fires correctly on >10%
+planted nulls (asserted). But the **measured recovery accuracy is NOT a win**:
+recovered RMSE **1.0045** vs unrecovered-null RMSE **0.9830** (**−2.2%**, i.e.
+slightly *worse* than leaving the nulls at zero) on a neighbor-correlated signal.
+The tridiagonal correlation model's fixed point does not equal the planted truth.
+**The recovery's reconstruction quality is therefore NOT validated as effective on
+synthetic data** — only its detection/trigger path is. Reported honestly; no
+positive number claimed.
+
+---
+
+## DATA-GATED — NOT validatable on synthetic data
+
+Planting a "seizure-like" / "weapon-like" / "happy-like" synthetic signal and
+claiming the detector "works" validates **nothing real** and is exactly the
+AI-slop this project fights. These skills run real DSP (per ADR-160, 0 stubs) and
+keep their ADR-160 disclaimers, but get **no accuracy number** here. Each needs
+the specific real, labelled data listed:
+
+| Skill | Why not constructible on synthetic | Real data required |
+|-------|------------------------------------|--------------------|
+| `med_seizure_detect` | "seizure-like" motion is not a seizure; no ground-truth signature exists synthetically | Clinical EEG-/video-labelled tonic-clonic seizure CSI from instrumented patients |
+| `med_sleep_apnea` | a planted breathing-pause is not clinical apnea (AHI scoring, hypopnea, desaturation) | Polysomnography-labelled (PSG) overnight CSI with scored apnea/hypopnea events |
+| `med_cardiac_arrhythmia` | a synthetic HR sequence cannot encode true arrhythmia morphology | ECG-labelled CSI (AFib/PVC/etc.) from clinical monitoring |
+| `med_respiratory_distress` | distress is a clinical gestalt, not a plantable rate | Clinician-labelled respiratory-distress CSI episodes |
+| `med_gait_analysis` | clinical gait metrics need a reference motion-capture standard | Mocap-/force-plate-labelled gait CSI |
+| `sec_weapon_detect` | a high variance ratio is RF reflectivity, **not** weapon discrimination (ADR-160 §A3 already renamed the event to `HIGH_METAL_REFLECTIVITY`) | Labelled metal-object-vs-no-object CSI with controlled object classes |
+| `exo_emotion_detect` | affect is not recoverable from a planted heuristic; outputs are proxies (ADR-160 §A2) | Validated affect-labelled CSI (self-report / physiological ground truth) |
+| `exo_happiness_score` | "happiness" is a gait-energy proxy, not a measured affect (ADR-160 §A2) | Validated affect/valence-labelled CSI |
+| `exo_dream_stage` | sleep staging needs PSG reference (EEG/EOG/EMG) | PSG-staged overnight CSI |
+| `exo_gesture_language` | coarse gesture clusters ≠ true sign language (ADR-160 §A4) | Labelled ASL letter/word CSI dataset |
+
+> The above are **not failures** — they are the honest boundary. A smaller set of
+> genuinely-measured skills plus this explicit gated list is the deliverable, per
+> the prove-everything directive.
+
+---
+
+## Skills not in either list
+
+The remaining edge skills (smart-building / retail / industrial occupancy-style,
+the other `sig_*`/`lrn_*`/`spt_*`/`tmp_*`/`qnt_*`/`aut_*`/`ais_*` algorithm-named
+modules) are **wired and exercised live** in the unified pipeline integration test
+(`tests/pipeline_all.rs`, all 59 default / 64 medical skills run without panic over
+300 synthetic frames) but were **not** given an individual planted-ground-truth
+accuracy number here. They are honest REAL-DSP modules (ADR-160) whose physical
+observable could be planted with more harness work; that is deferred, not claimed.
+
+## Test counts (full crate suite)
+
+```
+DEFAULT  (--features std):                     631 passed, 0 failed
+  (lib 504; budget 25; honest_labeling 10; pipeline_all 4; synthetic_validation 12; bench 1; vendor 75)
+MEDICAL  (--features std,medical-experimental): 669 passed, 0 failed
+  (lib 542; +16 same new tests; med_* stay DATA-GATED, not validated)
+```
+
+(M6 baseline was 615 / 653; the new pipeline_all (4) + synthetic_validation (12)
+tests add 16 to each tier.)
@@ -0,0 +1,26 @@
+# Upstream clone (WiFlow-STD, DY2434) -- never commit third-party code/weights
+upstream/
+
+# Local python env
+.venv/
+
+# Downloaded data / artifacts
+data/
+downloads/
+*.pth
+*.pt
+*.npy
+*.npz
+*.zip
+*.mat
+*.safetensors
+results/parity_fixture.json
+__pycache__/
+*.onnx
+
+# Committed ground truth: corruption masks for the pristine Kaggle download.
+# remote/clean_v2.py zeroes the corrupted source windows IN PLACE, so these
+# masks CANNOT be regenerated from a cleaned copy (generate_corruption_masks.py
+# documents the criteria and reproduces them only from a fresh download).
+!results/nan_windows_mask.npy
+!results/big_windows_mask.npy
@@ -0,0 +1,486 @@
+# WiFlow-STD (DY2434) Benchmark Results — ADR-152 §2.2
+
+Upstream: <https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling>
+pinned at `06899d29` (2026-04-05), Apache-2.0. Dataset: Kaggle `kaka2434/wiflow-dataset`
+(12.8 GB archive → 15.5 GB extracted; 360,000 windows of 540×20 CSI + 15-keypoint 2D labels).
+
+Published claims (README "Setting 1"): PCK@20 97.25%, PCK@30 98.63%, PCK@40 99.16%,
+PCK@50 99.48%, MPJPE 0.007 m, 2.23M params, 0.07 GFLOPs.
+
+## Measurement (a): their model on their data
+
+### Artifact verification (MEASURED, 2026-06-10, this repo `eval_repro.py`)
+
+| Check | Result |
+|---|---|
+| Parameter count | **2,225,042 (2.23M) — matches claim** |
+| FLOPs (torch profiler, batch 1) | ~0.055 GFLOPs — consistent with 0.07B claim |
+| CPU latency (Windows box, torch 2.12 CPU) | 13.2 ms/window @ batch 1 (76/s); 2.48 ms/sample @ batch 64 (403/s) |
+| Checkpoint load | `weights_only=True` (no pickle code execution) |
+
+### Released checkpoint does NOT reproduce the claims — REFUTED as shipped
+
+Running the released `best_pose_model.pth` through the released code on the released
+dataset with the released split procedure (seed-42 file-level 70/15/15; 54,000 test
+samples) yields:
+
+| Metric | Published | Measured (shipped checkpoint) |
+|---|---|---|
+| PCK@20 | 97.25% | **0.08%** |
+| PCK@30 | 98.63% | 0.78% |
+| PCK@40 | 99.16% | 5.53% |
+| PCK@50 | 99.48% | 15.42% |
+| MPJPE | 0.007 | **NaN** (dataset contains NaN CSI windows) |
+
+Raw output: `results/repro_a.json`.
+
+Diagnostics (on 2,000 NaN-free windows from the first files of the dataset, i.e.
+mostly would-be *training* data — so this is not a split mismatch):
+
+- Predictions correlate with targets (Pearson r ≈ 0.76) — the checkpoint is a trained
+  model, but in a **different keypoint normalization/order** than the released data.
+- Best-case post-hoc global per-axis affine correction: PCK@20 ≈ 20%.
+- Best-case per-keypoint affine correction (15×2 fitted transforms — generous
+  cheating): PCK@20 ≈ 72%, still far below 97.25%.
+- Pred↔target keypoint correspondence matrix is degenerate (multiple predicted
+  keypoints best-match the same target joint) — keypoint convention mismatch.
+
+### Reproducibility defects in the released artifacts
+
+1. `models/__init__.py` imports `TemporalConvNet`, which `models/tcn.py` does not
+   define — **the published code does not import/run as-is**.
+2. The released root checkpoint uses pre-rename module names (`att.*`, `final_conv.*`)
+   vs the published code (`attention.*`, `decoder.*`) — same shapes/param count, but
+   confirms the checkpoint predates the published code.
+3. The second shipped checkpoint (`cross_dataset_test/WiFlow/best_pose_model.pth`) is
+   a **different architecture** (342-channel input = MM-Fi layout, 3 TCN layers,
+   3-channel/3D decoder) — not usable on their own dataset.
+4. `run.py` ignores `--data_dir` and hardcodes `../preprocessed_csi_data`.
+5. The released dataset's final 13 files (indices 487–499; 9,072 windows, 2.52%)
+   are corrupted: NaN values plus garbage amplitudes up to 3.4e38 (float32 max) in
+   data that is otherwise [0,1]-normalized. Upstream code has no NaN/inf handling;
+   training as published on this download diverges — the first corrupted batch
+   overflows fp16 autocast and permanently poisons BatchNorm running statistics
+   (GradScaler step-skipping does not protect BN). The authors' training curves
+   show normal convergence, so their local data evidently differed from the
+   Kaggle upload. Window masks: `results/nan_windows_mask.npy`,
+   `results/big_windows_mask.npy`.
+
+### Reproducing the corruption masks
+
+The two mask files (9,070 NaN/Inf windows, 9,072 with |amplitude| > 1.5;
+union 9,072, all in dataset files 487–499) are **committed ground truth**
+(gitignore-negated, ~352 KB each). They can only be regenerated from a
+**pristine** Kaggle download: `remote/clean_v2.py` repairs the dataset by
+zeroing the corrupted windows in place, after which the corruption evidence
+is gone and a rescan returns all-False. `generate_corruption_masks.py`
+re-derives them (chunked scan, criteria: any non-finite value OR
+max |finite| > 1.5 per 540×20 window) and refuses to write all-False masks,
+which indicate a cleaned copy. Verified 2026-06-11: a regeneration from the
+local pristine download is bit-identical to the committed masks.
+
+### Retraining result (MEASURED, 2026-06-10): claims APPROXIMATELY REPRODUCED
+
+Since the shipped checkpoint is unusable, measurement (a) fell back to retraining
+with upstream code + defaults (seed 42, batch 64, early-stopped at epoch 41 of 50,
+best epoch 36, ~75 s/epoch) on ruvultra (RTX 5080). Deviations, all forced and
+documented: one-line fix for defect (1); torch 2.x+cu128 instead of pinned 2.3.1
+(Blackwell sm_120 unsupported); the 9,072 corrupted windows (defect 5) zeroed
+entirely — without this the published pipeline produces NaN from epoch 1 (observed).
+Scripts mirrored in `remote/`; raw metrics in `results/eval_retrained.json`.
+
+| Metric | Published | Retrained (full test, 54,000) | Retrained (corruption-free, 52,560) |
+|---|---|---|---|
+| PCK@20 | 97.25% | **96.09%** | **96.61%** |
+| PCK@30 | 98.63% | 97.89% | 98.23% |
+| PCK@40 | 99.16% | 98.58% | 98.79% |
+| PCK@50 | 99.48% | 98.99% | 99.11% |
+| MPJPE | 0.007 | 0.0098 | 0.0094 |
+
+Within ~0.6–1.2 PCK points of every published figure (single run, corrupted train
+windows zeroed, different torch/GPU). **Verdict: the accuracy claims are credible
+and approximately reproducible — but only after repairing the released dataset and
+code.** Val best: PCK@20 96.99%, MPJPE 0.0086 (epoch 36).
+
+One more defect found during the run:
+
+6. `train.py` calls `plot_training_history`, which is not defined anywhere — the
+   built-in post-training test evaluation is unreachable as published (crashes
+   with NameError after training completes).
+
+## ADR-152 §2.2 citation rule
+
+Evidence grade for the WiFlow-STD accuracy claims after measurement (a):
+**MEASURED-EQUIVALENT (96.1–96.6% PCK@20 reproduced by retraining; shipped
+checkpoint REFUTED; dataset/code require repairs)**. RuView docs may cite
+"~96% PCK@20 (our reproduction)" — still **not comparable** to our 17-keypoint
+ESP32 numbers (different hardware, 5 subjects, in-domain random split,
+15 keypoints).
+
+## Edge optimization (measured)
+
+ADR-152 "optimize beyond SOTA" track, 2026-06-10, this Windows box (Windows 11,
+16 torch threads, torch 2.12.0+cpu, onnxruntime 1.26.0). Subject: the retrained
+checkpoint `results/retrained_best_pose_model.pth` (2,225,042 fp32 params).
+Scripts: `quantize_bench.py`, `onnx_bench.py`, `eval_ort_accuracy.py`.
+Raw numbers: `results/edge_optimization.json`.
+
+Accuracy is on a **10,000-window seed-42 random subset** of the corruption-free
+test split (same seed-42 file-level 70/15/15 split as `eval_repro.py`; 54,000
+test windows, 1,440 corrupted excluded via `results/nan_windows_mask.npy` |
+`results/big_windows_mask.npy`, leaving 52,560; subset drawn with
+`np.random.default_rng(42)`). The fp32 subset PCK@20 (96.68%) matches the full
+clean-test figure (96.61%), so the subset is representative.
+
+Latency is CPU ms/window, median of repeated runs, 3 interleaved repetitions
+per variant (medians below; run-to-run spread on this box is large, roughly
+±20-40% at batch 1 — reps are in the JSON).
+
+| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
+|---|---|---|---|---|---|---|
+| torch fp32 (baseline) | 9.07 MB | 11.0 | 2.27 | 96.68% | 99.15% | 0.00936 |
+| torch fp16 (`.half()`) | **4.58 MB** | 24.3 | 2.42 | 96.68% | 99.15% | 0.00946 |
+| torch int8 dynamic | 9.07 MB (unchanged) | 15.6 | 2.06 | 96.68% (identical) | 99.15% | 0.00936 |
+| ONNX fp32 (onnxruntime) | 8.97 MB | **3.2** | **2.0** | 96.68% | 99.15% | 0.00936 |
+| ONNX int8 (ORT dynamic, supplementary) | **2.44 MB** | 6.5 | 5.8 | 96.52% | 99.15% | 0.01108 |
+
+Findings:
+
+- **torch dynamic INT8 quantizes nothing on this model.** The architecture has
+  **zero `nn.Linear` layers** — it is entirely Conv1d (21) + Conv2d (22) +
+  BatchNorm. `torch.ao.quantization.quantize_dynamic` (requested over
+  `{Linear, Conv1d, Conv2d}`) converted **0 modules / 0.0% of params**: dynamic
+  quantization only has kernels for Linear/RNN-family modules and silently
+  skips convolutions. The "int8" model is bit-identical to fp32 (same outputs,
+  same 9.07 MB). Conv quantization would require static (PTQ) quantization
+  with calibration — out of scope here; the ORT dynamic path below is the
+  honest int8 datapoint.
+- **fp16 halves size for free accuracy-wise** (PCK@20 −0.005 pt, MPJPE
+  +0.0001) but is *slower* on CPU at batch 1 (~2.2×) — torch CPU fp16 conv
+  kernels are emulated. fp16 is a storage/transport format here, not a CPU
+  runtime win.
+- **ONNX Runtime is the real batch-1 latency win: ~3.4× faster than torch**
+  (3.2 vs 11.0 ms/window) at identical accuracy (parity 2.4e-7).
+
+### Verdict on the paper's "~2.2 MB int8" claim
+
+**Plausible but not free, and unreachable by the obvious PyTorch route.**
+2,225,042 params × 1 byte ≈ 2.2 MB assumes *every* parameter quantizes.
+PyTorch dynamic quantization — the one-liner most readers would reach for —
+yields **9.07 MB (0% quantized)** because the model has no Linear layers.
+ONNX Runtime dynamic quantization, which does have int8 conv weight support,
+gets **2.44 MB** (close to the claim; the overhead is BatchNorm params/buffers
+and quantization scales kept in fp32) at a measurable accuracy cost:
+PCK@20 96.68 → 96.52% (−0.16 pt) and MPJPE 0.00936 → 0.01108 (+18%), and
+~2× slower inference than ONNX fp32 (ConvInteger kernels). The paper does not
+state a method or an int8 accuracy; treat "2.2 MB" as a weight-arithmetic
+estimate, achievable in practice only via conv-capable quantization toolchains
+and with a small accuracy penalty.
+
+### ONNX export status
+
+**Works.** Exported via the TorchScript exporter (`dynamo=False`), opset 17,
+with a dynamic batch axis — `results/retrained_fp32_dynamic.onnx` (8.97 MB),
+verified to run at batch 1/2/64. The axial attention's
+`view(N*W, C, H)` reshape traced correctly (sizes recorded as graph ops, not
+baked constants). The dynamo exporter also captures the graph but crashed on
+this box writing a ✅ to a cp1252 console (cosmetic Windows encoding issue, not
+a model blocker). Parity vs torch on the stored fixture
+(`results/parity_fixture.npz`, batch 2, seed 42): **max abs diff 2.4e-7 —
+PASS** (< 1e-4). ORT-quantized int8 model: `results/retrained_int8_ort_dynamic.onnx`.
+
+### Static PTQ (calibrated) — follow-up
+
+Follow-up to the dynamic-int8 row above (2026-06-10, same box, onnxruntime
+1.26.0): ONNX Runtime **static** post-training quantization
+(`quantize_static`, QDQ format, per-channel int8 weights + int8 activations)
+of the same fp32 export, calibrated on **corruption-free TRAINING-split
+windows only** (seed-42 file-level split, same masks; 1,000 windows for
+MinMax, 512 for the histogram calibrators; never test windows). Scopes:
+"conv-only" (`op_types_to_quantize=["Conv"]` — the attention path exports as
+Einsum/Softmax, which ORT never quantizes anyway, so "all-ops" additionally
+quantizes the elementwise Mul/Sigmoid/Add/AveragePool glue). Accuracy on the
+identical 10k-window seed-42 corruption-free test subset; latency median of
+3 interleaved reps (fp32/dynamic re-benched in-session as references).
+Script: `static_ptq_bench.py`; raw: `results/edge_optimization.json`
+(`onnx_static_ptq`).
+
+| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
+|---|---|---|---|---|---|---|
+| ONNX fp32 (reference) | 8.97 MB | 2.5 | 1.9 | 96.68% | 99.15% | 0.00936 |
+| ORT dynamic int8 (baseline) | **2.44 MB** | 5.7 | 4.6 | 96.52% | 99.15% | 0.01108 |
+| static QDQ **Percentile(99.99) conv-only** | 2.53 MB | 5.3 | 4.7 | 96.61% | 99.16% | **0.01031** |
+| static QDQ MinMax conv-only | 2.53 MB | 5.2 | 3.3 | **96.63%** | 99.19% | 0.01084 |
+| static QDQ Entropy conv-only | 2.53 MB | 5.2 | 3.1 | 96.60% | 99.19% | 0.01078 |
+| static QDQ MinMax all-ops | 2.60 MB | 6.5 | 3.9 | 95.45% | 99.14% | 0.01486 |
+| static QDQ Entropy all-ops | 2.60 MB | 5.7 | 4.1 | 95.30% | 99.13% | 0.01510 |
+| static QDQ Percentile all-ops | 2.60 MB | 5.3 | 4.3 | 96.39% | 99.17% | 0.01218 |
+
+**Verdict: static PTQ (conv-only) is the new best int8 point on accuracy —
+but only modestly, and it does not fix int8's latency penalty.**
+
+- **Accuracy: beats dynamic.** All three conv-only calibrations land at
+  PCK@20 96.60–96.63% (vs dynamic 96.52%, fp32 96.68% — recovers ~⅔ of the
+  dynamic gap) and MPJPE 0.0103–0.0108 (vs dynamic 0.01108). Best MPJPE:
+  Percentile conv-only, +10% over fp32 instead of dynamic's +18%.
+- **Size: slightly worse.** 2.53 MB vs 2.44 MB (+3.6%) — QDQ nodes and
+  per-channel scales cost a little; BatchNorm stays fp32 in both (the 12 BNs
+  follow Slice/Einsum/Reshape, never Conv, so they cannot be folded).
+- **Latency: a wash vs dynamic, still ~2× slower than ONNX fp32 at batch 1.**
+  Batch-1 medians 5.2–5.3 vs dynamic 5.7 ms/win in-session — within this
+  box's ±20–40% noise. Batch 64 leans static (3.1–3.3 for MinMax/Entropy
+  conv-only vs 4.6), same caveat.
+- **All-ops QDQ is strictly worse**: up to −1.4 pt PCK@20 and +60% MPJPE for
+  zero size/latency benefit — int8 activations through the elementwise glue
+  around the attention blocks is where the damage is. Conv-only is the right
+  scope.
+- Negative result worth recording: **Entropy calibration is a no-op here** —
+  on an identical calibration set it selects full-range thresholds
+  bit-identical to MinMax (all 247 scales equal; verified on a 64-window
+  smoke set). Also, ORT 1.26's `CalibMaxIntermediateOutputs` raises a
+  spurious "No data is collected" when the batch count divides the chunk
+  size (worked around in the script).
+
+Deployment guidance: need speed → ONNX fp32 (3.2 ms b1). Need int8 weights
+for size → static QDQ conv-only (Percentile or MinMax,
+`results/retrained_int8_static_percentile_conv.onnx`), which strictly
+dominates dynamic int8 on accuracy at ~equal latency and +0.09 MB.
+
+## Efficiency sweep (MEASURED, overnight 2026-06-10/11)
+
+ADR-152 beyond-SOTA track: compact purpose-built variants of the WiFlow-STD
+architecture, trained from scratch on the same cleaned dataset, identical
+seed-42 file-level split, loss and protocol as the measurement-(a) reference
+(fp32, batch 64, ≤50 epochs, patience 5; RTX 5080, ~22–29 min/variant).
+Variant transforms are pure channel/group/stride scalings of an
+architecture-exact parameterized model (validated: reproduces 2,225,042 params
+at the reference config). Scripts: `remote/sweep/`; raw:
+`results/efficiency_sweep.jsonl`; checkpoints `results/{half,quarter,tiny}_best.pth`
+(gitignored).
+
+| Variant | Params | vs 2.23M | Clean-test PCK@20 | PCK@50 | MPJPE | Best epoch |
+|---|---|---|---|---|---|---|
+| full (reference, meas. a) | 2,225,042 | 1× | 96.61% | 99.11% | 0.0094 | 36 |
+| **half** | **843,834** | **0.38×** | **96.62%** | **99.47%** | **0.00898** | 23 |
+| quarter | 338,600 | 0.15× | 96.05% | 99.43% | 0.00928 | 50 |
+| tiny | 56,290 | 0.025× | 94.11% | 99.36% | 0.0125 | 47 |
+
+Findings:
+
+- **The half model (843k params) strictly dominates the full reference** on
+  this dataset — equal PCK@20, better PCK@50 and MPJPE, converges in fewer
+  epochs. The published 2.23M architecture is over-parameterized for its own
+  benchmark.
+- **tiny (56k params, 1/39.5) holds 94.11% PCK@20** — a ~220 KB fp32 /
+  ~60 KB int8-class model in reach of severely constrained edge targets,
+  at −2.5 pt from the full reference.
+- Caveats: in-domain (5-subject random-file split) like every number on this
+  dataset; single run per variant; corruption-free test subset (52,560).
+  Cross-domain behavior of compact variants is untested — ADR-150's evidence
+  says capacity *hurts* cross-subject, so the compact end may generalize no
+  worse, but that is a hypothesis, not a measurement.
+
+### Compact-variant edge artifacts (MEASURED, 2026-06-11)
+
+Edge pipeline for the **tiny** checkpoint (56,290 params), same machinery and
+protocol as the full-model edge rows above (this Windows box, torch
+2.12.0+cpu, onnxruntime 1.26.0; dynamic-batch opset-17 TorchScript export;
+static QDQ **Percentile(99.99) conv-only** int8 calibrated on **512**
+corruption-free TRAIN-split windows; accuracy on the identical 10k-window
+seed-42 clean test subset; latency = median ms/window over 3 interleaved
+reps, with the full-model fp32/int8 sessions interleaved as same-session
+references). Script: `tiny_edge_bench.py`; raw:
+`results/edge_optimization.json` (`tiny_variant`). Torch-vs-ORT parity on the
+stored fixture input: **max abs diff 1.5e-7 — PASS** (< 1e-4). The tiny fp32
+subset PCK@20 (94.11%) matches the full clean-test sweep figure (94.11%)
+exactly, so the subset remains representative.
+
+Two forced deviations, both recorded in the JSON:
+
+1. **Adaptive-pool export rewrite.** tiny's derived stride schedule
+   `[2,1,1,1]` leaves feature width 16, and the TorchScript exporter rejects
+   `AdaptiveAvgPool2d((15,1))` when 15 is not a factor of the input height
+   (the full model never hit this — its width was exactly 15). Since the
+   pool over a fixed-size map is a fixed linear operator, the export wrapper
+   replaces it with `mean(-1)` (W axis, a factor) + a constant averaging
+   matmul using PyTorch's exact bin rule; the parity check (vs the original
+   torch model with the real pool) proves exactness.
+2. **Calibration count 512, not "~500"**: ORT 1.26's histogram collector
+   `np.asarray()`'s the per-batch maxima, so the calibration count must be a
+   multiple of the 64-window calibration batch or the ragged last batch
+   crashes it (the earlier static-PTQ run dodged this by using exactly 512).
+
+| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
+|---|---|---|---|---|---|---|
+| full ONNX fp32 (same-session ref) | 8.97 MB | 2.27 | 1.42 | 96.68% | 99.15% | 0.00936 |
+| full static QDQ Percentile conv-only (same-session ref) | 2.53 MB | 5.53 | 3.82 | 96.61% | 99.16% | 0.01031 |
+| **tiny ONNX fp32** | **0.295 MB** | **0.66** | **0.24** | **94.11%** | 99.37% | 0.01253 |
+| tiny static QDQ Percentile conv-only | 0.248 MB | 0.85 | 1.03 | 92.68% | 99.33% | 0.01491 |
+
+(tiny torch `.pth` checkpoint for reference: 0.34 MB on disk; 56,290 fp32
+params ≈ 225 KB of weights.)
+
+Findings:
+
+- **The smallest deployable WiFlow-class model is the tiny ONNX fp32
+  artifact: ~295 KB on disk, 0.66 ms/window batch-1 CPU (~1,500 windows/s),
+  94.1% PCK@20** — 30× smaller and ~3.4× faster (in-session) than the full
+  ONNX fp32 model for −2.6 pt PCK@20.
+- **int8 is a bad trade at this scale.** Static QDQ conv-only — the recipe
+  that cost the full model only 0.07 pt — costs tiny **−1.43 pt** PCK@20
+  (94.11 → 92.68%) and +19% MPJPE, saves only 47 KB (−16%; QDQ scales and
+  the fp32 BN/attention glue are proportionally larger in a small graph),
+  and is *slower* than tiny fp32 (0.85 vs 0.66 ms b1; 1.03 vs 0.24 ms b64 —
+  QDQ kernel overhead dominates when the convs are this small). A 56k-param
+  model has little redundancy left to absorb weight+activation rounding.
+- Deployment guidance, compact edition: ship tiny as **ONNX fp32** — at
+  295 KB the int8 size saving solves no real constraint and costs accuracy
+  and speed. If ~250 KB vs ~295 KB ever matters, weight-only quantization
+  would be the thing to try next, not QDQ.
+
+## Measurement (b): BLOCKED-ON-DATA (attempted 2026-06-10)
+
+The fine-tune-on-ESP32 measurement stopped at dataset characterization, per the
+pre-registered stop rule (<2,000 paired windows). Findings (MEASURED):
+
+- **Only one trainable paired dataset exists**: `ruvultra:~/work/cog-pose-train/paired.jsonl`
+  — 1,077 windows (one subject, one room, one 29.9-min session, single node;
+  CSI [56, 20]; 17 COCO keypoints, MediaPipe confidence mean 0.44 — only 264
+  windows pass ADR-079's own conf>0.5 training filter). Prior measured attempts
+  on this exact set: 0–3% torso-PCK@20 (temporal splits, three independent
+  pipelines). Fine-tuning a 2.23M-param model on ~860 train windows would
+  measure memorization, not transfer.
+- **The April session behind the old "92.9% PCK@20" claim is lost** (345
+  samples, 35 subcarriers; raw CSI gone from ruvzen/ruvultra/cognitum-v0; only
+  a 69-sample predictions+GT holdout survives at `models/wiflow-real/eval-holdout.jsonl`).
+- **Forensic recheck of that holdout RETRACTS the 92.9% figure**: the trainer's
+  `pck()` used an absolute 0.2 image-unit threshold (not torso-normalized) and
+  the model output a **constant pose** (pred std 0.0000 across 69 near-static
+  frames; a mean predictor scores 100% under the same protocol). The
+  torso-normalized PCK@20 on the same holdout is 19.1%. This corroborates the
+  2026-05-11 audit retraction (CHANGELOG, PR #535); stale doc citations were
+  removed 2026-06-10 (user-guide, readme-details, ADR-152 §2.1.3). The §2.2
+  no-citation rule now applies to ADR-079 accuracy claims.
+
+Unblock criteria: a paired collection session of ≥2k windows (≈35+ min at the
+observed stride; multi-pose, conf>0.5, ideally with the §2.1.3 two-checkerboard
+calibration), plus a re-baselined our-pipeline number under torso-PCK@20 on the
+same split. WiFlow-STD assets stand ready on ruvultra (`~/wiflow-std-bench/`).
+Also worth investigating: ADR-079's protocol predicts ~9k windows per 30 min;
+the May session under-delivered ~8× (aligner drop rate?).
+
+## Measurement (b) (MEASURED 2026-06-10/11)
+
+The data baseline unblocked: the 2026-06-10 22:10–22:40 collection session produced
+**2,046 paired windows** (`ruvultra:~/wiflow-std-bench/paired-20260610.jsonl`; ONE
+subject, ONE room, ONE ESP32 node, varied poses: walk/raise/squat/kick/wave/turn/
+jump/sit; aligner `scripts/align-ground-truth.js`, non-overlapping 20-frame windows
+~0.42 s; 17 COCO keypoints in normalized [0,1] camera coords; MediaPipe confidence
+mean 0.802, min 0.692 — all windows pass the conf>0.5 filter). The −4 h timestamp
+bug and the empty-frame confidence-dilution aligner findings are recorded
+separately; results only here. Trained on ruvultra (RTX 5080, torch 2.11+cu128,
+fp32, batch 32, GPU shared with the efficiency sweep). Scripts mirrored in
+`remote/measb/`; raw metrics + full training curves in `results/measurement_b.json`.
+
+### Two new aligner/dataset findings (forced deviations, MEASURED)
+
+1. **`csi_shape` is heterogeneous, not [70, 20]**: 1,347× [70,20], 284× [134,20],
+   243× [26,20], 130× [12,20], 42× [20,20]. The ESP32 stream emits mixed frame
+   types and `extractCsiMatrix` stamps each window's subcarrier count from
+   `window[0].subcarriers`, zero-padding/truncating the other frames — even
+   native-70 windows contain ~20.4% internally zero-padded short frames
+   (subcarriers 40–69 all-zero). Handling: the primary suite ("all 2,046")
+   linearly resamples every frame's subcarrier axis to 70 bins (identity for
+   native-70 frames) so the pre-registered n and split sizes hold; a secondary
+   suite restricts to the 1,347 native [70,20] windows as a homogeneity check.
+2. **Aligner layout bug**: `extractCsiMatrix` fills `matrix[f * nSc + s]`
+   (frame-major) but declares `shape: [nSc, nFrames]` — the stored shape label is
+   transposed relative to the data. Confirmed by coherent per-frame zero-tails;
+   corrected on load (`reshape(nFrames, nSc).T`).
+
+### Protocol (pre-registered, followed)
+
+Temporal split, no shuffling across time: first 70% train (1,432), next 15% val
+(307), last 15% test (307); seed 42 elsewhere. Model: learned 1×1 Conv1d 70→540
+adapter prepended to the upstream WiFlow-STD trunk; K=17 via the parameter-free
+adaptive pool (`AdaptiveAvgPool2d((17,1))` — pretrained weights load strict for
+any K). CSI normalized by the TRAIN-split p99 amplitude (129.7 all / 130.9
+native-70), clipped to [0,1]. Three runs, ≤60 epochs, early-stop patience 8 on
+val MPJPE, AdamW (adapter lr 1e-4; pretrained trunk lr 1e-5, 10× lower; scratch
+all 1e-4), fp32. Pretrained init = the measurement-(a) **retrained** checkpoint
+(`upstream/test/best_pose_model.pth`, ~96% PCK@20 on WiFlow data; the
+`att.`/`final_conv.` key remap from `eval_repro.py` applied defensively — a no-op,
+that checkpoint already uses post-rename keys). Frozen-trunk run: trunk
+`requires_grad=False` **and** held in `.eval()` so BatchNorm running stats cannot
+drift — a pure transfer probe; only the 70→540 adapter (38,340 params) trains.
+
+PCK is torso-normalized with **torso = ‖l_shoulder(5) − l_hip(11)‖** (upstream
+`calculate_pck` math — per-frame norm clamped at 0.01, mean over keypoints ×
+frames — but upstream's `NECK_IDX/PELVIS_IDX = 2, 12` is a 15-keypoint
+convention; on 17-kp COCO those indices are right_eye/right_hip, so the indices
+were replaced, not the math). MPJPE is in normalized image units (not meters).
+
+### Results — primary suite, all 2,046 windows (test = last 307)
+
+| Run | PCK@10 | PCK@20 | PCK@30 | PCK@40 | PCK@50 | MPJPE | pred std | best ep |
+|---|---|---|---|---|---|---|---|---|
+| **mean-pose baseline** (honesty bar) | **73.1%** | **95.9%** | **98.7%** | 99.3% | 99.3% | **0.0148** | 0 (by constr.) | — |
+| (i) pretrained-init, full fine-tune | 26.0% | 65.0% | 88.0% | 96.4% | 98.9% | 0.0313 | 0.0113 | 58/60 |
+| (ii) scratch | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.2554 | 0.0002 | 4 (stop @13) |
+| (iii) frozen-trunk (adapter only) | 0.0% | 0.0% | 0.2% | 3.2% | 14.4% | 0.1260 | 0.0073 | 59/60 |
+
+Secondary suite (native [70,20] windows only, n=1,347, test=202) reproduces the
+same ordering: mean-baseline 96.0% / pretrained 67.1% / scratch 0.0% /
+frozen-trunk 0.0% PCK@20 (MPJPE 0.0153 / 0.0318 / 0.2236 / 0.1343) — the
+subcarrier-resampling choice does not change any conclusion.
+
+### Interpretation
+
+- **Did pretraining-transfer happen? Partially — as optimization transfer, not
+  feature transfer, and not past the honesty bar.**
+  - *Pretrained vs scratch*: dramatic (65.0% vs 0.0% PCK@20). The pretrained init
+    is the only configuration that trains at all under the pre-registered budget.
+  - *Frozen-trunk*: near-zero (0.0% PCK@20, 14.4% @50). WiFlow-STD's frozen
+    features do **not** transfer to our ESP32 domain through a linear subcarrier
+    adapter — the pretrained benefit is a well-conditioned initialization (incl.
+    calibrated BN/output scales), not reusable CSI→pose features.
+  - *Everything vs mean-pose baseline*: **no run beats it.** A constant
+    train-mean pose scores 95.9% torso-PCK@20 / 0.0148 MPJPE on this test split,
+    because a single subject in one camera frame barely moves in normalized
+    coordinates. The fine-tuned model is a real, non-constant model
+    (pred std 0.0113 > 0 — passes the constant-pose detector that retracted the
+    old 92.9% figure) but its deviations from the mean hurt: it fits train-period
+    temporal dynamics that do not generalize across the temporal split.
+- **Verdict for ADR-152 §2.2(b): fine-tuning WiFlow-STD on this dataset does not
+  demonstrate CSI→pose signal beyond the mean pose.** Until a model beats the
+  mean-pose baseline on a temporal split, no PCK number from this line may be
+  cited as pose-estimation capability.
+
+### Caveats (honest, pre-registered)
+
+- Single subject, single room, single session (30 min), single ESP32 node —
+  in-domain temporal split only; nothing here speaks to cross-room or
+  cross-subject generalization.
+- 2k windows vs the 360k-window WiFlow-STD corpus — **NOT comparable** to the
+  ~96% in-domain measurement-(a) number, and the published 97.25% even less so.
+- The scratch run's total collapse (it cannot even reach the mean pose; its
+  output BatchNorm/SiLU head must learn output scale from random init at lr 1e-4)
+  is an optimization outcome under the fixed budget, not proof the architecture
+  cannot learn from scratch — the pretrained-vs-scratch gap partially reflects
+  this conditioning advantage.
+- Mixed-subcarrier frames (finding 1) mean even the "clean" windows carry ~20%
+  zero-padded frames; collection-side frame-type filtering should precede the
+  next session.
+- Mean-baseline PCK is inflated by low pose variance relative to torso size
+  (~0.2–0.3 image units); PCK@10 (73.1%) shows the same ceiling effect at a
+  stricter threshold — the bar is the bar, but a livelier dataset would lower it.
+
+## Pending
+
+- (b) fine-tune on our ESP32 17-keypoint eval set — **MEASURED 2026-06-10/11**,
+  see above: no run beats the mean-pose baseline; pretraining transfers as
+  optimization aid only.
+- (c) our internal WiFlow on their dataset (15-keypoint subset mapping) — also
+  affected: there is currently no validated internal pose model to compare
+  (the 92.9% artifact is retracted; the MM-Fi SOTA models in ADR-150 §3 are a
+  different input domain).
@@ -0,0 +1,200 @@
+"""Shared infrastructure for the LOCAL wiflow-std benchmark scripts (ADR-152).
+
+This module is the single canonical implementation of the helpers that were
+previously copy-pasted across eval_repro.py / quantize_bench.py /
+onnx_bench.py / eval_ort_accuracy.py / export_to_safetensors.py:
+
+  - ``import_upstream()``  -- sys.path setup + the models-package stub that
+    works around the upstream import bug, plus the >1GB np.load mmap patch
+  - ``install_np_load_mmap_patch()`` -- the mmap patch on its own
+  - ``remap_legacy_keys()`` / ``load_remapped_state()`` -- checkpoint
+    key remap for the pre-rename released checkpoint
+  - ``load_wiflow_model()`` -- WiFlowPoseModel from a checkpoint, eval mode
+  - ``set_seed()`` -- mirrors upstream run.py seeding exactly
+  - ``evaluate()`` -- THE canonical batch-weighted PCK/MPJPE evaluation loop
+    (thresholds 0.1-0.5, upstream utils/metrics.py math); accepts either a
+    torch nn.Module or an onnxruntime InferenceSession
+
+The scripts under remote/ deploy to ruvultra as standalone single files and
+therefore intentionally inline private copies of these helpers; when editing
+them, treat this module as the reference implementation and keep the copies
+in sync.
+"""
+
+import os
+import random
+import sys
+import time
+import types
+
+import numpy as np
+import torch
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+UPSTREAM = os.path.join(HERE, "upstream")
+RESULTS = os.path.join(HERE, "results")
+
+DEFAULT_THRESHOLDS = (0.1, 0.2, 0.3, 0.4, 0.5)
+
+# ---------------------------------------------------------------------------
+# >1GB np.load mmap patch
+# ---------------------------------------------------------------------------
+
+# csi_windows.npy is ~13 GB; mmap large arrays instead of loading into RAM
+# (loading it eagerly needs ~15 GB).
+_np_load = np.load
+
+
+def _np_load_mmap(path, *a, **kw):
+    if (isinstance(path, str) and path.endswith(".npy")
+            and os.path.getsize(path) > 1 << 30 and "mmap_mode" not in kw):
+        kw["mmap_mode"] = "r"
+    return _np_load(path, *a, **kw)
+
+
+def install_np_load_mmap_patch():
+    """Globally patch np.load so .npy files >1GB are mmap'd read-only.
+
+    Idempotent. Patching the numpy module attribute is equivalent to the
+    historical ``upstream_dataset.np.load = _np_load_mmap`` (dataset.np IS
+    the numpy module), but works regardless of import order.
+    """
+    np.load = _np_load_mmap
+
+
+# ---------------------------------------------------------------------------
+# upstream import shim
+# ---------------------------------------------------------------------------
+
+def import_upstream(mmap_patch=True):
+    """Make the upstream WiFlow-STD clone importable; returns its path.
+
+    Upstream bug: models/__init__.py imports TemporalConvNet, which
+    models/tcn.py does not define -- the package fails to import as
+    published. Register a stub package so the broken __init__ never
+    executes; submodules (models.pose_model etc.) still resolve via
+    __path__. Idempotent.
+    """
+    if UPSTREAM not in sys.path:
+        sys.path.insert(0, UPSTREAM)
+    if "models" not in sys.modules:
+        _models_pkg = types.ModuleType("models")
+        _models_pkg.__path__ = [os.path.join(UPSTREAM, "models")]
+        sys.modules["models"] = _models_pkg
+    if mmap_patch:
+        install_np_load_mmap_patch()
+    return UPSTREAM
+
+
+# ---------------------------------------------------------------------------
+# checkpoint loading
+# ---------------------------------------------------------------------------
+
+# The released checkpoint predates the published code: modules were renamed
+# att -> attention, final_conv -> decoder (param count identical, 2.23M).
+LEGACY_RENAMES = {"att.": "attention.", "final_conv.": "decoder."}
+
+
+def remap_legacy_keys(state):
+    """Remap pre-rename state_dict keys; no-op for already-new-style keys."""
+    return {next((new + k[len(old):] for old, new in LEGACY_RENAMES.items()
+                  if k.startswith(old)), k): v
+            for k, v in state.items()}
+
+
+def load_remapped_state(path, map_location="cpu"):
+    """torch.load (weights_only) + legacy key remap."""
+    state = torch.load(path, map_location=map_location, weights_only=True)
+    return remap_legacy_keys(state)
+
+
+def load_wiflow_model(checkpoint, map_location="cpu", dropout=0.5):
+    """Full-size WiFlowPoseModel from a checkpoint, strict load, eval mode."""
+    import_upstream()
+    from models.pose_model import WiFlowPoseModel
+    model = WiFlowPoseModel(dropout=dropout)
+    model.load_state_dict(load_remapped_state(checkpoint, map_location),
+                          strict=True)
+    model.eval()
+    return model
+
+
+# ---------------------------------------------------------------------------
+# seeding
+# ---------------------------------------------------------------------------
+
+def set_seed(seed=42):
+    # mirror upstream run.py exactly
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed(seed)
+        torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+
+# ---------------------------------------------------------------------------
+# THE canonical evaluation loop
+# ---------------------------------------------------------------------------
+
+def evaluate(model, loader, device=None, dtype=None, label="",
+             thresholds=DEFAULT_THRESHOLDS, progress_every=50):
+    """Batch-weighted PCK/MPJPE over a DataLoader (upstream metrics math).
+
+    ``model`` may be a torch nn.Module (optionally evaluated on ``device``
+    with inputs cast to ``dtype``) or an onnxruntime InferenceSession.
+    Per-threshold PCK values are independent in upstream calculate_pck, so
+    evaluating a superset of thresholds never changes any individual value.
+
+    Returns {"samples", "mpjpe", "pck@10".."pck@50", "wall_seconds"}.
+    """
+    import_upstream()
+    from utils.metrics import calculate_mpjpe, calculate_pck
+
+    is_ort = hasattr(model, "get_inputs")  # onnxruntime InferenceSession
+    if is_ort:
+        inp = model.get_inputs()[0].name
+
+        def forward(bx):
+            return torch.from_numpy(model.run(None, {inp: bx.numpy()})[0])
+    else:
+        model.eval()
+
+        def forward(bx):
+            if device is not None:
+                bx = bx.to(device)
+            if dtype is not None:
+                bx = bx.to(dtype)
+            return model(bx).float()
+
+    thresholds = list(thresholds)
+    totals = {t: 0.0 for t in thresholds}
+    total_mpe, n = 0.0, 0
+    t0 = time.time()
+    with torch.no_grad():
+        for batch_idx, (bx, by) in enumerate(loader):
+            out = forward(bx)
+            if device is not None and not is_ort:
+                by = by.to(device)
+            mpe = calculate_mpjpe(out, by)
+            pck = calculate_pck(out, by, thresholds=thresholds)
+            bs = by.size(0)
+            total_mpe += mpe * bs
+            for t in totals:
+                totals[t] += pck[t] * bs
+            n += bs
+            if batch_idx % progress_every == 0:
+                tag = f"[{label}] " if label else ""
+                pck20 = totals.get(0.2)
+                pck20_str = f"pck20={pck20 / n:.4f} " if pck20 is not None else ""
+                print(f"  {tag}batch {batch_idx}: n={n} {pck20_str}"
+                      f"mpjpe={total_mpe / n:.4f} ({time.time() - t0:.0f}s)",
+                      flush=True)
+    return {
+        "samples": n,
+        "mpjpe": total_mpe / n,
+        **{f"pck@{int(t * 100)}": totals[t] / n for t in thresholds},
+        "wall_seconds": time.time() - t0,
+    }
@@ -0,0 +1,67 @@
+"""ADR-152 edge optimization: accuracy of the ONNX fp32 and ORT-dynamic-int8
+models on the same corruption-free 10k test subset used by quantize_bench.py.
+
+The torch dynamic-int8 path quantizes nothing (no nn.Linear in the model), so
+the only real int8 datapoint for the paper's "~2.2 MB int8" claim is the
+onnxruntime dynamically quantized model -- this script measures what that
+quantization costs in PCK/MPJPE.
+
+Usage:
+  .venv/Scripts/python.exe eval_ort_accuracy.py \
+      --data-dir <preprocessed_csi_data> [--subset 10000]
+
+Writes/merges into results/edge_optimization.json under key "onnx_accuracy".
+"""
+
+import argparse
+import json
+import os
+import sys
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+
+from _bench_common import RESULTS, evaluate  # noqa: E402
+from quantize_bench import build_test_subset  # noqa: E402  (sets up upstream imports)
+
+
+def evaluate_ort(sess, loader, label):
+    """ORT-session evaluation via the canonical _bench_common.evaluate loop."""
+    return evaluate(sess, loader, label=label)
+
+
+def main():
+    import onnxruntime as ort
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data-dir", default=os.path.join(
+        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
+        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
+    parser.add_argument("--subset", type=int, default=10000)
+    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
+    args = parser.parse_args()
+
+    loader, _n_clean = build_test_subset(args.data_dir, args.subset)
+    results = {}
+    for label, fname in (("onnx_fp32", "retrained_fp32_dynamic.onnx"),
+                         ("onnx_int8_ort_dynamic", "retrained_int8_ort_dynamic.onnx")):
+        path = os.path.join(RESULTS, fname)
+        if not os.path.exists(path):
+            results[label] = {"error": f"{fname} not found; run onnx_bench.py first"}
+            continue
+        sess = ort.InferenceSession(path, providers=["CPUExecutionProvider"])
+        print(f"=== accuracy: {label} ({fname}) ===")
+        results[label] = evaluate_ort(sess, loader, label)
+        print(json.dumps(results[label], indent=2))
+
+    merged = {}
+    if os.path.exists(args.out):
+        with open(args.out) as f:
+            merged = json.load(f)
+    merged["onnx_accuracy"] = results
+    with open(args.out, "w") as f:
+        json.dump(merged, f, indent=2)
+    print(f"wrote {args.out}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,102 @@
+"""ADR-152 §2.2 measurement (a): reproduce WiFlow-STD (DY2434) published test metrics.
+
+Runs the released pretrained checkpoint (upstream/best_pose_model.pth) against the
+released Kaggle dataset (kaka2434/wiflow-dataset) using the upstream code path:
+identical dataset class, identical file-level 70/15/15 split at seed 42, identical
+PCK/MPJPE implementations (utils/metrics.py).
+
+Published claims (README, "Setting 1 random split"):
+  PCK@20 97.25% | PCK@30 98.63% | PCK@40 99.16% | PCK@50 99.48% | MPJPE 0.007 m
+
+Usage:
+  .venv/Scripts/python.exe eval_repro.py --data-dir <dir containing csi_windows.npy>
+"""
+
+import argparse
+import json
+import os
+import sys
+
+import torch
+from torch.utils.data import DataLoader
+
+from _bench_common import (UPSTREAM, evaluate, import_upstream,
+                           load_remapped_state, set_seed)
+
+import_upstream()  # sys.path + models stub + >1GB np.load mmap patch
+
+from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders  # noqa: E402
+from models.pose_model import WiFlowPoseModel  # noqa: E402
+
+
+def find_data_dir(root):
+    for dirpath, _dirnames, filenames in os.walk(root):
+        if "csi_windows.npy" in filenames:
+            return dirpath
+    return None
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data-dir", required=True,
+                        help="Directory containing csi_windows.npy (searched recursively)")
+    parser.add_argument("--checkpoint", default=os.path.join(UPSTREAM, "best_pose_model.pth"))
+    parser.add_argument("--batch-size", type=int, default=64)
+    parser.add_argument("--out", default=os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                                      "results", "repro_a.json"))
+    args = parser.parse_args()
+
+    data_dir = args.data_dir
+    if not os.path.exists(os.path.join(data_dir, "csi_windows.npy")):
+        located = find_data_dir(data_dir)
+        if located is None:
+            sys.exit(f"csi_windows.npy not found under {data_dir}")
+        data_dir = located
+    print(f"data dir: {data_dir}")
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"device: {device}, torch {torch.__version__}")
+
+    set_seed(42)
+
+    dataset = PreprocessedCSIKeypointsDataset(
+        data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
+
+    # split must match upstream: file-level shuffle at random_seed=42, 70/15/15
+    _train_loader, _val_loader, test_loader = create_preprocessed_train_val_test_loaders(
+        dataset=dataset, batch_size=args.batch_size, num_workers=0, random_seed=42)
+
+    model = WiFlowPoseModel(dropout=0.5).to(device)
+    # released checkpoint predates the published code: modules were renamed
+    # att -> attention, final_conv -> decoder (param count identical, 2.23M)
+    state = load_remapped_state(args.checkpoint, map_location=device)
+    model.load_state_dict(state, strict=True)
+    n_params = sum(p.numel() for p in model.parameters())
+    print(f"checkpoint: {args.checkpoint} ({n_params/1e6:.2f}M params)")
+
+    # upstream also evaluates with drop_last=True; we report the full test set
+    # (drop_last=False) and the drop_last variant for exact comparability
+    results = {"published": {"pck@20": 0.9725, "pck@30": 0.9863, "pck@40": 0.9916,
+                             "pck@50": 0.9948, "mpjpe": 0.007},
+               "params_millions": n_params / 1e6,
+               "data_dir": data_dir,
+               "device": str(device)}
+
+    print("=== test set (full, drop_last=False) ===")
+    results["test_full"] = evaluate(model, test_loader, device=device)
+    print(json.dumps(results["test_full"], indent=2))
+
+    test_loader_dl = DataLoader(test_loader.dataset, batch_size=args.batch_size,
+                                shuffle=False, drop_last=True)
+    print("=== test set (drop_last=True, as upstream train.py) ===")
+    results["test_drop_last"] = evaluate(model, test_loader_dl, device=device)
+    print(json.dumps(results["test_drop_last"], indent=2))
+
+    os.makedirs(os.path.dirname(args.out), exist_ok=True)
+    with open(args.out, "w") as f:
+        json.dump(results, f, indent=2)
+    print(f"wrote {args.out}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,174 @@
+"""ADR-152 §2.2: export the retrained WiFlow-STD PyTorch checkpoint to
+safetensors with tch-rs (VarStore) variable names, plus a numerical-parity
+fixture for the Rust port.
+
+Outputs (all under results/, gitignored):
+  retrained_wiflow_std.safetensors  -- 248 f32 tensors named exactly as the
+                                       Rust WiFlowStdModel VarStore expects
+                                       (see wiflow_std/model.rs
+                                       `dump_variable_names` for the
+                                       authoritative name dump)
+  parity_fixture.npz                -- deterministic input (seed 42,
+                                       shape (2, 540, 20), uniform [0,1]) and
+                                       the Python model's eval-mode output
+  parity_fixture.json               -- same data as flattened f32 lists, for
+                                       the dependency-free Rust test
+                                       (tests/test_wiflow_std_parity.rs)
+
+PyTorch -> tch key mapping (derived from the VarStore dump, not guessed):
+
+  tcn.network.{i}.conv1_group.weight        -> tcn{i}.conv1_group.weight
+  tcn.network.{i}.bn*_{group,pw}.<leaf>     -> tcn{i}.bn*_{group,pw}.<leaf>
+  tcn.network.{i}.downsample.0.weight       -> tcn{i}.ds_conv.weight
+  tcn.network.{i}.downsample.1.<leaf>       -> tcn{i}.ds_bn.<leaf>
+  up.block.{0,1,4,5,8,9}.<leaf>             -> conv_in.{conv1,bn1,conv2,bn2,conv3,bn3}.<leaf>
+  up.downsample.{0,1}.<leaf>                -> conv_in.{ds_conv,ds_bn}.<leaf>
+  residual_blocks.{i}.block.{...}.<leaf>    -> conv{i}.{conv1..bn3}.<leaf>
+  residual_blocks.{i}.downsample.{0,1}      -> conv{i}.{ds_conv,ds_bn}
+  attention.{width,height}_axis.qkv_transform.weight
+                                            -> attention.{width,height}.qkv.weight
+  attention.{width,height}_axis.bn_*        -> attention.{width,height}.bn_*
+  decoder.{0,1,3,4}.<leaf>                  -> {dec_conv1,dec_bn1,dec_conv2,dec_bn2}.<leaf>
+  *.num_batches_tracked                     -> dropped (tch BatchNorm has no such buffer)
+
+Legacy upstream names (att. -> attention., final_conv. -> decoder.) are
+remapped first, exactly as eval_repro.py does for the released checkpoint.
+
+Usage:
+  .venv/Scripts/python.exe export_to_safetensors.py
+"""
+
+import json
+import os
+import re
+
+import numpy as np
+import torch
+from safetensors.torch import save_file
+
+from _bench_common import RESULTS, import_upstream, remap_legacy_keys
+
+import_upstream()  # sys.path + models stub
+
+from models.pose_model import WiFlowPoseModel  # noqa: E402
+
+CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
+
+# Sequential index -> tch sub-name inside one ConvBlock1/AsymmetricConvBlock:
+# [Conv2d(0), BN(1), SiLU(2), Dropout2d(3), Conv2d(4), BN(5), SiLU(6),
+#  Dropout2d(7), Conv2d(8), BN(9)]
+_BLOCK_IDX = {"0": "conv1", "1": "bn1", "4": "conv2", "5": "bn2",
+              "8": "conv3", "9": "bn3"}
+_DS_IDX = {"0": "ds_conv", "1": "ds_bn"}
+_DECODER_IDX = {"0": "dec_conv1", "1": "dec_bn1", "3": "dec_conv2",
+                "4": "dec_bn2"}
+
+
+def _conv_block(new_prefix: str, rest: str) -> str:
+    m = re.fullmatch(r"block\.(\d+)\.(.+)", rest)
+    if m:
+        return f"{new_prefix}.{_BLOCK_IDX[m.group(1)]}.{m.group(2)}"
+    m = re.fullmatch(r"downsample\.(\d+)\.(.+)", rest)
+    if m:
+        return f"{new_prefix}.{_DS_IDX[m.group(1)]}.{m.group(2)}"
+    raise KeyError(f"unmapped conv-block key: {new_prefix} / {rest}")
+
+
+def map_key(key: str) -> str:
+    """Map one PyTorch state_dict key to the tch VarStore name."""
+    m = re.fullmatch(r"tcn\.network\.(\d+)\.(.+)", key)
+    if m:
+        i, rest = m.groups()
+        rest = (rest.replace("downsample.0.", "ds_conv.")
+                    .replace("downsample.1.", "ds_bn."))
+        return f"tcn{i}.{rest}"
+
+    m = re.fullmatch(r"up\.(.+)", key)
+    if m:
+        return _conv_block("conv_in", m.group(1))
+
+    m = re.fullmatch(r"residual_blocks\.(\d+)\.(.+)", key)
+    if m:
+        return _conv_block(f"conv{m.group(1)}", m.group(2))
+
+    m = re.fullmatch(r"attention\.(width|height)_axis\.(.+)", key)
+    if m:
+        axis, rest = m.groups()
+        rest = rest.replace("qkv_transform.", "qkv.")
+        return f"attention.{axis}.{rest}"
+
+    m = re.fullmatch(r"decoder\.(\d+)\.(.+)", key)
+    if m:
+        return f"{_DECODER_IDX[m.group(1)]}.{m.group(2)}"
+
+    raise KeyError(f"unmapped checkpoint key: {key}")
+
+
+def main():
+    state = torch.load(CHECKPOINT, map_location="cpu", weights_only=True)
+    if not isinstance(state, dict) or "tcn.network.0.conv1_group.weight" not in {
+        k for k in state
+    } | {k.replace("att.", "attention.") for k in state}:
+        # tolerate trainer wrappers like {"model_state_dict": ...}
+        for wrapper in ("model_state_dict", "state_dict", "model"):
+            if isinstance(state, dict) and wrapper in state:
+                state = state[wrapper]
+                break
+
+    # Legacy upstream names predate the published code (_bench_common).
+    state = remap_legacy_keys(state)
+
+    mapped = {}
+    dropped = 0
+    for k, v in state.items():
+        if k.endswith("num_batches_tracked"):
+            dropped += 1
+            continue
+        tch_key = map_key(k)
+        if tch_key in mapped:
+            raise KeyError(f"duplicate mapped key: {k} -> {tch_key}")
+        mapped[tch_key] = v.detach().to(torch.float32).contiguous()
+
+    n_params = sum(v.numel() for k, v in mapped.items()
+                   if "running_" not in k)
+    print(f"checkpoint tensors: {len(state)} "
+          f"(dropped {dropped} num_batches_tracked)")
+    print(f"mapped tensors: {len(mapped)}, "
+          f"non-buffer params: {n_params/1e6:.6f}M")
+    assert len(mapped) == 248, f"expected 248 tch variables, got {len(mapped)}"
+    assert n_params == 2_225_042, f"param count mismatch: {n_params}"
+
+    st_path = os.path.join(RESULTS, "retrained_wiflow_std.safetensors")
+    save_file(mapped, st_path)
+    print(f"wrote {st_path}")
+
+    # ---- parity fixture --------------------------------------------------
+    model = WiFlowPoseModel(dropout=0.5)
+    model.load_state_dict(state, strict=True)
+    model.eval()
+
+    gen = torch.Generator().manual_seed(42)
+    x = torch.rand(2, 540, 20, generator=gen, dtype=torch.float32)
+    with torch.no_grad():
+        y = model(x)
+    print(f"fixture input {tuple(x.shape)} -> output {tuple(y.shape)}, "
+          f"output range [{y.min().item():.6f}, {y.max().item():.6f}]")
+
+    np.savez(os.path.join(RESULTS, "parity_fixture.npz"),
+             input=x.numpy(), output=y.numpy())
+    fixture = {
+        "seed": 42,
+        "input_shape": list(x.shape),
+        "input": x.flatten().tolist(),
+        "output_shape": list(y.shape),
+        "output": y.flatten().tolist(),
+    }
+    json_path = os.path.join(RESULTS, "parity_fixture.json")
+    with open(json_path, "w") as f:
+        json.dump(fixture, f)
+    print(f"wrote {os.path.join(RESULTS, 'parity_fixture.npz')}")
+    print(f"wrote {json_path}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,148 @@
+"""Regenerate results/nan_windows_mask.npy + results/big_windows_mask.npy by
+scanning a PRISTINE kagglehub download of the WiFlow-STD dataset
+(kaka2434/wiflow-dataset v1, csi_windows.npy, 360,000 windows of 540x20).
+
+============================ READ THIS FIRST ===============================
+This script MUST be run against an UNCLEANED copy of the dataset.
+
+remote/clean_v2.py (and its predecessor clean_nan.py) repair the dataset by
+zeroing the corrupted windows IN PLACE, with no backup. A cleaned copy
+contains no non-finite values and no out-of-range amplitudes, so on a cleaned
+copy this scan produces ALL-FALSE masks -- silently wrong ground truth. The
+script errors out loudly in that case (see the sanity check in main()).
+
+That irreversibility is exactly why the two committed mask files under
+results/ (gitignore-negated) are the canonical ground truth: once a download
+has been cleaned, the masks can NEVER be regenerated from it. Only run this
+on a fresh `kagglehub.dataset_download("kaka2434/wiflow-dataset")`.
+============================================================================
+
+Criteria (per window; mirrors the original 2026-06-10 scan and the
+remote/clean_v2.py repair criteria):
+
+  nan mask: any non-finite value (NaN/Inf) anywhere in the 540x20 window
+  big mask: max |finite value| > 1.5 (the data is otherwise [0,1]-normalized;
+            the corrupted files contain garbage up to 3.4e38, float32 max)
+
+Expected result on the pristine Kaggle download (RESULTS.md defect 5):
+  nan: 9,070 True | big: 9,072 True | union: 9,072 -- all windows in dataset
+  files 487-499 (the final 13 files), window indices 350,922-359,999.
+
+Usage:
+  PYTHONUTF8=1 .venv/Scripts/python.exe generate_corruption_masks.py \
+      [--data-dir <dir containing csi_windows.npy>] [--out-dir results]
+"""
+
+import argparse
+import os
+import sys
+
+import numpy as np
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+RESULTS = os.path.join(HERE, "results")
+
+EXPECTED = {"nan": 9070, "big": 9072, "union": 9072,
+            "files": (487, 499), "windows": (350922, 359999)}
+
+
+def scan(csi_path, chunk=4000):
+    """Chunked scan of the (mmap'd) windows array; returns (nan_mask, big_mask)."""
+    csi = np.load(csi_path, mmap_mode="r")
+    n = len(csi)
+    nan_mask = np.zeros(n, dtype=bool)
+    big_mask = np.zeros(n, dtype=bool)
+    for i in range(0, n, chunk):
+        block = np.asarray(csi[i:i + chunk])
+        finite = np.isfinite(block)
+        nan_mask[i:i + chunk] = (~finite).any(axis=(1, 2))
+        big_mask[i:i + chunk] = (
+            np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
+        if (i // chunk) % 10 == 0:
+            print(f"  scanned {min(i + chunk, n):,}/{n:,} windows "
+                  f"(nan={int(nan_mask.sum()):,} big={int(big_mask.sum()):,})",
+                  flush=True)
+    return nan_mask, big_mask
+
+
+def describe_files(data_dir, mask):
+    """Map marked windows to dataset file indices via window_info.npz."""
+    info = os.path.join(data_dir, "window_info.npz")
+    if not os.path.exists(info):
+        return None
+    w2f = np.load(info)["window_to_file"]
+    return np.unique(w2f[mask])
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Regenerate the corruption masks from a PRISTINE "
+                    "(uncleaned) kagglehub download. See module docstring.")
+    parser.add_argument("--data-dir", default=os.path.join(
+        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
+        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"),
+        help="Directory containing csi_windows.npy (PRISTINE copy)")
+    parser.add_argument("--out-dir", default=RESULTS,
+                        help="Where to write the two .npy masks")
+    parser.add_argument("--chunk", type=int, default=4000,
+                        help="Windows per scan chunk (memory/speed tradeoff)")
+    args = parser.parse_args()
+
+    csi_path = os.path.join(args.data_dir, "csi_windows.npy")
+    if not os.path.exists(csi_path):
+        sys.exit(f"csi_windows.npy not found in {args.data_dir}")
+
+    print(f"scanning {csi_path} (chunk={args.chunk}) ...")
+    nan_mask, big_mask = scan(csi_path, args.chunk)
+    union = nan_mask | big_mask
+    print(f"nan: {int(nan_mask.sum()):,} | big: {int(big_mask.sum()):,} | "
+          f"union: {int(union.sum()):,} of {len(union):,} windows")
+
+    # ---- sanity check: an all-False result means a CLEANED copy ------------
+    if not union.any():
+        sys.exit(
+            "ERROR: scan found ZERO corrupted windows.\n"
+            "\n"
+            "The pristine Kaggle download (kaka2434/wiflow-dataset v1) is "
+            "known to contain\n"
+            "9,072 corrupted windows (NaN/Inf + amplitudes up to 3.4e38) in "
+            "dataset files\n"
+            "487-499 (RESULTS.md, reproducibility defect 5). Finding none "
+            "means this copy\n"
+            "has almost certainly already been repaired by remote/clean_v2.py "
+            "(or clean_nan.py),\n"
+            "which zeroes the corrupted windows IN PLACE -- after that the "
+            "corruption evidence\n"
+            "is gone and the masks CANNOT be regenerated from this copy.\n"
+            "\n"
+            "Refusing to overwrite the committed ground-truth masks with "
+            "all-False ones.\n"
+            "Re-download the dataset (kagglehub.dataset_download("
+            "'kaka2434/wiflow-dataset'))\n"
+            "and point --data-dir at the fresh, uncleaned copy.")
+
+    files = describe_files(args.data_dir, union)
+    if files is not None:
+        print(f"marked windows span dataset files {files.min()}-{files.max()}: "
+              f"{files.tolist()}")
+        lo, hi = EXPECTED["files"]
+        if files.min() != lo or files.max() != hi:
+            print(f"WARNING: expected marked files exactly {lo}-{hi} "
+                  f"(the pristine v1 download); got {files.min()}-{files.max()}. "
+                  f"Different dataset version, or a partially cleaned copy?")
+    for name, mask, exp in (("nan", nan_mask, EXPECTED["nan"]),
+                            ("big", big_mask, EXPECTED["big"])):
+        if int(mask.sum()) != exp:
+            print(f"WARNING: {name} mask has {int(mask.sum()):,} True windows; "
+                  f"the pristine v1 download yields {exp:,}.")
+
+    os.makedirs(args.out_dir, exist_ok=True)
+    for name, mask in (("nan_windows_mask.npy", nan_mask),
+                       ("big_windows_mask.npy", big_mask)):
+        out = os.path.join(args.out_dir, name)
+        np.save(out, mask)
+        print(f"wrote {out} ({int(mask.sum()):,} True)")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,220 @@
+"""ADR-152 edge optimization: ONNX export + onnxruntime CPU benchmark for the
+retrained WiFlow-STD checkpoint.
+
+- Exports fp32 to ONNX. The axial attention reshapes with python ints taken
+  from tensor.size() (view(N*W, C, H)), so a traced graph bakes the batch
+  size; we first try a dynamic-batch export and verify it actually works at
+  batch sizes 1/2/64 -- if not, we fall back to fixed-batch exports.
+- Verifies output parity vs torch on the stored fixture
+  (results/parity_fixture.npz, batch 2, seed 42): max abs diff < 1e-4.
+- Measures onnxruntime CPU latency at batch 1 and 64 (median of N runs).
+- Supplementary: onnxruntime dynamic int8 quantization of the exported model
+  (weight size datapoint for the paper's "~2.2 MB int8" claim).
+
+Usage:
+  .venv/Scripts/python.exe onnx_bench.py
+
+Writes/merges into results/edge_optimization.json under key "onnx".
+"""
+
+import json
+import os
+import platform
+import statistics
+import time
+import traceback
+
+import numpy as np
+import torch
+
+from _bench_common import RESULTS, import_upstream, load_wiflow_model
+
+import_upstream()  # sys.path + models stub + >1GB np.load mmap patch
+
+CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
+OUT_JSON = os.path.join(RESULTS, "edge_optimization.json")
+
+
+def load_fp32_model():
+    return load_wiflow_model(CHECKPOINT)
+
+
+def try_export(model, path, batch, dynamic, opset=17):
+    """Returns (ok, exporter_used, error)."""
+    x = torch.rand(batch, 540, 20)
+    attempts = []
+    if dynamic:
+        attempts.append(("dynamo", dict(dynamo=True,
+                                        dynamic_shapes={"x": {0: "batch"}})))
+        attempts.append(("torchscript", dict(dynamo=False,
+                                             dynamic_axes={"input": {0: "batch"},
+                                                           "output": {0: "batch"}})))
+    else:
+        attempts.append(("torchscript", dict(dynamo=False)))
+        attempts.append(("dynamo", dict(dynamo=True)))
+    last_err = None
+    for name, kw in attempts:
+        try:
+            with torch.no_grad():
+                torch.onnx.export(model, (x,), path, opset_version=opset,
+                                  input_names=["input"], output_names=["output"],
+                                  **kw)
+            return True, name, None
+        except Exception as e:  # noqa: BLE001
+            last_err = f"{name}: {type(e).__name__}: {e}"
+            traceback.print_exc()
+    return False, None, last_err
+
+
+def ort_session(path):
+    import onnxruntime as ort
+    return ort.InferenceSession(path, providers=["CPUExecutionProvider"])
+
+
+def ort_run(sess, x):
+    inp = sess.get_inputs()[0].name
+    return sess.run(None, {inp: x})[0]
+
+
+def bench_ort(sess, batch, n_runs):
+    rng = np.random.default_rng(123)
+    x = rng.random((batch, 540, 20), dtype=np.float32)
+    for _ in range(max(5, n_runs // 10)):
+        ort_run(sess, x)
+    times = []
+    for _ in range(n_runs):
+        t0 = time.perf_counter()
+        ort_run(sess, x)
+        times.append(time.perf_counter() - t0)
+    med = statistics.median(times)
+    return {
+        "batch_size": batch,
+        "runs": n_runs,
+        "median_ms_per_batch": med * 1e3,
+        "median_ms_per_window": med * 1e3 / batch,
+        "windows_per_second": batch / med,
+    }
+
+
+def main():
+    import argparse
+    parser = argparse.ArgumentParser(
+        description="ONNX export + onnxruntime CPU benchmark for the "
+                    "retrained WiFlow-STD checkpoint (no options; see "
+                    "module docstring). NB: the published "
+                    "retrained_fp32_dynamic.onnx came from the TorchScript "
+                    "exporter; on newer torch the dynamo attempt may succeed "
+                    "first and produce a different (external-data) artifact.")
+    parser.parse_args()
+
+    import onnxruntime
+    model = load_fp32_model()
+    results = {
+        "env": {
+            "torch": torch.__version__,
+            "onnxruntime": onnxruntime.__version__,
+            "platform": platform.platform(),
+        },
+    }
+
+    fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
+    fx, fy = fixture["input"], fixture["output"]  # (2,540,20) -> (2,15,2)
+
+    # ---- export: dynamic batch first, fall back to fixed --------------------
+    dyn_path = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
+    ok, exporter, err = try_export(model, dyn_path, batch=2, dynamic=True)
+    dynamic_works = False
+    if ok:
+        # verify the dynamic graph really runs at other batch sizes
+        try:
+            sess = ort_session(dyn_path)
+            for b in (1, 2, 64):
+                y = ort_run(sess, np.zeros((b, 540, 20), dtype=np.float32))
+                assert y.shape == (b, 15, 2), y.shape
+            dynamic_works = True
+        except Exception as e:  # noqa: BLE001
+            print(f"dynamic-batch model does not generalize: {e}")
+
+    sessions = {}
+    if dynamic_works:
+        results["export"] = {"mode": "dynamic-batch", "exporter": exporter,
+                             "file": os.path.basename(dyn_path),
+                             "size_mb": os.path.getsize(dyn_path) / 1e6}
+        sess = ort_session(dyn_path)
+        sessions = {1: sess, 2: sess, 64: sess}
+        print(f"dynamic-batch export OK via {exporter}")
+    else:
+        results["export"] = {"mode": "fixed-batch", "fallback_reason": err,
+                             "files": {}}
+        for b in (1, 2, 64):
+            p = os.path.join(RESULTS, f"retrained_fp32_b{b}.onnx")
+            ok, exporter, err = try_export(model, p, batch=b, dynamic=False)
+            if not ok:
+                results["export"]["files"][str(b)] = {"error": err}
+                print(f"EXPORT FAILED at batch {b}: {err}")
+                continue
+            results["export"]["files"][str(b)] = {
+                "exporter": exporter, "file": os.path.basename(p),
+                "size_mb": os.path.getsize(p) / 1e6}
+            sessions[b] = ort_session(p)
+            print(f"fixed-batch {b} export OK via {exporter}")
+
+    # ---- parity vs torch on the fixture -------------------------------------
+    if 2 in sessions:
+        y_ort = ort_run(sessions[2], fx)
+        with torch.no_grad():
+            y_torch = model(torch.from_numpy(fx)).numpy()
+        results["parity"] = {
+            "fixture": "results/parity_fixture.npz (batch 2, seed 42)",
+            "max_abs_diff_vs_stored_fixture": float(np.abs(y_ort - fy).max()),
+            "max_abs_diff_vs_torch_now": float(np.abs(y_ort - y_torch).max()),
+            "pass_lt_1e-4": bool(np.abs(y_ort - y_torch).max() < 1e-4),
+        }
+        print("parity:", json.dumps(results["parity"], indent=2))
+
+    # ---- latency -------------------------------------------------------------
+    results["latency"] = {}
+    if 1 in sessions:
+        results["latency"]["batch1"] = bench_ort(sessions[1], 1, 100)
+        print(f"ORT batch 1:  {results['latency']['batch1']['median_ms_per_window']:.2f} ms/window")
+    if 64 in sessions:
+        results["latency"]["batch64"] = bench_ort(sessions[64], 64, 30)
+        print(f"ORT batch 64: {results['latency']['batch64']['median_ms_per_window']:.3f} ms/window")
+
+    # ---- supplementary: ORT dynamic int8 (size datapoint for the 2.2MB claim)
+    src = (dyn_path if dynamic_works
+           else os.path.join(RESULTS, "retrained_fp32_b1.onnx"))
+    if os.path.exists(src):
+        try:
+            from onnxruntime.quantization import QuantType, quantize_dynamic
+            q_path = os.path.join(RESULTS, "retrained_int8_ort_dynamic.onnx")
+            quantize_dynamic(src, q_path, weight_type=QuantType.QInt8)
+            entry = {"file": os.path.basename(q_path),
+                     "size_mb": os.path.getsize(q_path) / 1e6}
+            try:
+                qs = ort_session(q_path)
+                yq = ort_run(qs, fx[:1] if not dynamic_works else fx)
+                ref = fy[:1] if not dynamic_works else fy
+                entry["runs"] = True
+                entry["max_abs_diff_vs_fp32_fixture"] = float(np.abs(yq - ref).max())
+            except Exception as e:  # noqa: BLE001
+                entry["runs"] = False
+                entry["run_error"] = f"{type(e).__name__}: {e}"
+            results["ort_int8_dynamic_supplementary"] = entry
+            print("ORT int8:", json.dumps(entry, indent=2))
+        except Exception as e:  # noqa: BLE001
+            results["ort_int8_dynamic_supplementary"] = {
+                "error": f"{type(e).__name__}: {e}"}
+
+    merged = {}
+    if os.path.exists(OUT_JSON):
+        with open(OUT_JSON) as f:
+            merged = json.load(f)
+    merged["onnx"] = results
+    with open(OUT_JSON, "w") as f:
+        json.dump(merged, f, indent=2)
+    print(f"wrote {OUT_JSON}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,228 @@
+"""ADR-152 "optimize beyond SOTA": edge-optimization benchmark for the
+retrained WiFlow-STD checkpoint (results/retrained_best_pose_model.pth,
+~96% PCK@20, fp32 params 2,225,042).
+
+Measures, for fp32 / fp16 / dynamic-int8 torch variants:
+  (a) serialized state_dict size on disk,
+  (b) CPU inference latency per window at batch 1 and batch 64
+      (median of repeated runs, this Windows box),
+  (c) accuracy (PCK@20/50 + MPJPE, upstream metrics) on a corruption-free
+      random subset of the seed-42 file-level 70/15/15 test split
+      (same split as eval_repro.py; corrupted windows 487-499 excluded via
+      results/nan_windows_mask.npy | results/big_windows_mask.npy).
+
+Also verifies the paper's "~2.2 MB int8" size claim: reports which layer
+types torch dynamic quantization actually converts (the model contains NO
+nn.Linear -- it is Conv1d/Conv2d/BatchNorm only) and the real on-disk size.
+
+Usage:
+  .venv/Scripts/python.exe quantize_bench.py \
+      --data-dir C:/Users/ruv/.cache/kagglehub/datasets/kaka2434/wiflow-dataset/versions/1/preprocessed_csi_data \
+      [--subset 10000] [--skip-accuracy]
+
+Writes/merges into results/edge_optimization.json under key "torch".
+"""
+
+import argparse
+import json
+import os
+import platform
+import statistics
+import time
+
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.utils.data import DataLoader
+
+from _bench_common import HERE, RESULTS, evaluate, import_upstream, load_wiflow_model
+
+import_upstream()  # sys.path + models stub + >1GB np.load mmap patch
+
+from dataset import (  # noqa: E402
+    PreprocessedCSIKeypointsDataset,
+    create_preprocessed_train_val_test_loaders,
+)
+
+CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
+
+
+def load_fp32_model():
+    # legacy upstream key remap inside is a harmless no-op on this checkpoint
+    return load_wiflow_model(CHECKPOINT)
+
+
+def state_dict_size_bytes(model, path):
+    torch.save(model.state_dict(), path)
+    return os.path.getsize(path)
+
+
+def bench_latency(model, batch_size, n_runs, dtype=torch.float32):
+    gen = torch.Generator().manual_seed(123)
+    x = torch.rand(batch_size, 540, 20, generator=gen).to(dtype)
+    with torch.no_grad():
+        for _ in range(max(5, n_runs // 10)):  # warmup
+            model(x)
+        times = []
+        for _ in range(n_runs):
+            t0 = time.perf_counter()
+            model(x)
+            times.append(time.perf_counter() - t0)
+    med = statistics.median(times)
+    return {
+        "batch_size": batch_size,
+        "runs": n_runs,
+        "median_ms_per_batch": med * 1e3,
+        "median_ms_per_window": med * 1e3 / batch_size,
+        "windows_per_second": batch_size / med,
+    }
+
+
+def build_test_subset(data_dir, subset_size, batch_size=64):
+    """Seed-42 file-level 70/15/15 test split (exactly as eval_repro.py),
+    minus corrupted windows, then a seed-42 random subset."""
+    dataset = PreprocessedCSIKeypointsDataset(
+        data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
+    _tr, _va, test_loader = create_preprocessed_train_val_test_loaders(
+        dataset=dataset, batch_size=batch_size, num_workers=0, random_seed=42)
+    test_indices = np.asarray(test_loader.dataset.indices)
+
+    corrupted = (np.load(os.path.join(RESULTS, "nan_windows_mask.npy"))
+                 | np.load(os.path.join(RESULTS, "big_windows_mask.npy")))
+    clean = test_indices[~corrupted[test_indices]]
+    print(f"test split: {len(test_indices)} windows, "
+          f"{len(test_indices) - len(clean)} corrupted excluded, "
+          f"{len(clean)} clean")
+
+    if subset_size and subset_size < len(clean):
+        rng = np.random.default_rng(42)
+        clean = np.sort(rng.choice(clean, size=subset_size, replace=False))
+    subset = torch.utils.data.Subset(dataset, clean.tolist())
+    loader = DataLoader(subset, batch_size=batch_size, shuffle=False,
+                        num_workers=0)
+    return loader, len(clean)
+
+
+def quantize_int8_dynamic(fp32_model):
+    """torch.ao.quantization.quantize_dynamic on Linear/Conv where supported.
+    Returns (model, report) where report documents what actually quantized."""
+    qmodel = torch.ao.quantization.quantize_dynamic(
+        fp32_model, {nn.Linear, nn.Conv1d, nn.Conv2d}, dtype=torch.qint8)
+
+    quantized, total_params, quant_params = [], 0, 0
+    for name, mod in qmodel.named_modules():
+        cls = type(mod).__module__ + "." + type(mod).__name__
+        if "quantized" in cls:
+            w = mod.weight() if callable(getattr(mod, "weight", None)) else None
+            numel = w.numel() if w is not None else 0
+            quant_params += numel
+            quantized.append({"module": name, "class": cls, "params": numel})
+    for p in fp32_model.parameters():
+        total_params += p.numel()
+
+    n_linear = sum(isinstance(m, nn.Linear) for m in fp32_model.modules())
+    n_conv1d = sum(isinstance(m, nn.Conv1d) for m in fp32_model.modules())
+    n_conv2d = sum(isinstance(m, nn.Conv2d) for m in fp32_model.modules())
+    report = {
+        "eligible_module_counts": {
+            "nn.Linear": n_linear, "nn.Conv1d": n_conv1d, "nn.Conv2d": n_conv2d},
+        "modules_actually_quantized": quantized,
+        "n_modules_quantized": len(quantized),
+        "params_total": total_params,
+        "params_quantized": quant_params,
+        "params_quantized_fraction": quant_params / total_params,
+    }
+    return qmodel, report
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data-dir", default=os.path.join(
+        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
+        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
+    parser.add_argument("--subset", type=int, default=10000)
+    parser.add_argument("--runs-b1", type=int, default=100)
+    parser.add_argument("--runs-b64", type=int, default=30)
+    parser.add_argument("--skip-accuracy", action="store_true")
+    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
+    args = parser.parse_args()
+
+    torch.manual_seed(42)
+    results = {
+        "env": {
+            "torch": torch.__version__,
+            "platform": platform.platform(),
+            "processor": platform.processor(),
+            "num_threads": torch.get_num_threads(),
+            "checkpoint": os.path.relpath(CHECKPOINT, HERE),
+        },
+        "variants": {},
+    }
+
+    # ---- build variants ---------------------------------------------------
+    fp32 = load_fp32_model()
+    n_params = sum(p.numel() for p in fp32.parameters())
+    results["env"]["params"] = n_params
+    print(f"fp32 model: {n_params:,} params")
+
+    fp16 = load_fp32_model().half()
+
+    int8, q_report = quantize_int8_dynamic(load_fp32_model())
+    results["int8_dynamic_quant_report"] = q_report
+    print(f"int8 dynamic: {q_report['n_modules_quantized']} modules quantized, "
+          f"{q_report['params_quantized_fraction']*100:.1f}% of params")
+
+    variants = {
+        "fp32": (fp32, torch.float32, "retrained_fp32_resaved.pth"),
+        "fp16": (fp16, torch.float16, "retrained_fp16.pth"),
+        "int8_dynamic": (int8, torch.float32, "retrained_int8_dynamic.pth"),
+    }
+
+    # ---- (a) size + (b) latency -------------------------------------------
+    for name, (model, dtype, fname) in variants.items():
+        path = os.path.join(RESULTS, fname)
+        size = state_dict_size_bytes(model, path)
+        print(f"\n=== {name}: {size/1e6:.3f} MB on disk ({fname}) ===")
+        lat1 = bench_latency(model, 1, args.runs_b1, dtype)
+        lat64 = bench_latency(model, 64, args.runs_b64, dtype)
+        print(f"  batch 1:  {lat1['median_ms_per_window']:.2f} ms/window "
+              f"({lat1['windows_per_second']:.0f}/s)")
+        print(f"  batch 64: {lat64['median_ms_per_window']:.3f} ms/window "
+              f"({lat64['windows_per_second']:.0f}/s)")
+        results["variants"][name] = {
+            "file": fname,
+            "size_bytes": size,
+            "size_mb": size / 1e6,
+            "latency_batch1": lat1,
+            "latency_batch64": lat64,
+        }
+
+    # ---- (c) accuracy ------------------------------------------------------
+    if not args.skip_accuracy:
+        loader, n_clean = build_test_subset(args.data_dir, args.subset)
+        results["accuracy_subset"] = {
+            "description": "seed-42 file-level 70/15/15 test split, corrupted "
+                           "windows (files 487-499) excluded, seed-42 random "
+                           "subset",
+            "subset_size": min(args.subset, n_clean) if args.subset else n_clean,
+            "clean_test_total": n_clean,
+        }
+        for name, (model, dtype, _f) in variants.items():
+            print(f"\n=== accuracy: {name} ===")
+            results["variants"][name]["accuracy"] = evaluate(
+                model, loader, dtype=dtype, label=name)
+            print(json.dumps(results["variants"][name]["accuracy"], indent=2))
+
+    # ---- merge into edge_optimization.json ---------------------------------
+    merged = {}
+    if os.path.exists(args.out):
+        with open(args.out) as f:
+            merged = json.load(f)
+    merged["torch"] = results
+    with open(args.out, "w") as f:
+        json.dump(merged, f, indent=2)
+    print(f"\nwrote {args.out}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,14 @@
+import numpy as np, os
+d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
+csi = np.load(os.path.join(d, 'csi_windows.npy'), mmap_mode='r+')
+zeroed = 0
+chunk = 4000
+for i in range(0, len(csi), chunk):
+    block = csi[i:i+chunk]
+    finite = np.isfinite(block)
+    bad = (~finite).any(axis=(1, 2)) | (np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
+    if bad.any():
+        block[bad] = 0.0
+        zeroed += int(bad.sum())
+csi.flush()
+print(f'zeroed {zeroed} corrupted windows entirely')
@@ -0,0 +1,112 @@
+"""Evaluate the retrained WiFlow-STD checkpoint (ADR-152 §2.2a fallback).
+
+Scores the model produced by run.py (train_output/best_pose_model.pth or similar)
+on the seed-42 test split: full test set AND NaN-free subset (excluding windows
+that were zero-filled by clean_nan.py — file indices 487-499).
+
+NOTE: deployed to ruvultra (~/wiflow-std-bench) as a standalone single file,
+so it deliberately inlines its helpers. The reference implementations (upstream
+import shim, >1GB np.load mmap patch, key-remap loader, canonical evaluate
+loop) live in benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
+"""
+import json, os, random, sys
+
+import numpy as np
+import torch
+from torch.utils.data import DataLoader, Subset
+
+# csi_windows.npy is ~13 GB; mmap large arrays instead of eagerly loading
+# ~15 GB into RAM (same patch as _bench_common._np_load_mmap).
+_np_load = np.load
+
+
+def _np_load_mmap(path, *a, **kw):
+    if (isinstance(path, str) and path.endswith('.npy')
+            and os.path.getsize(path) > 1 << 30 and 'mmap_mode' not in kw):
+        kw['mmap_mode'] = 'r'
+    return _np_load(path, *a, **kw)
+
+
+np.load = _np_load_mmap
+
+sys.path.insert(0, os.path.expanduser('~/wiflow-std-bench/upstream'))
+from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders
+from models.pose_model import WiFlowPoseModel
+from utils.metrics import calculate_pck, calculate_mpjpe
+
+
+def find_checkpoint():
+    cands = []
+    for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/train_output')):
+        for f in files:
+            if f.endswith('.pth'):
+                cands.append(os.path.join(root, f))
+    # also upstream/test default output dir
+    for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/upstream')):
+        for f in files:
+            if f.endswith('.pth') and 'best' in f and 'cross_dataset' not in root:
+                p = os.path.join(root, f)
+                if os.path.getmtime(p) > os.path.getmtime(os.path.expanduser('~/wiflow-std-bench/train.log')) - 86400 * 2:
+                    cands.append(p)
+    cands = [c for c in cands if not c.endswith('upstream/best_pose_model.pth')]
+    if not cands:
+        sys.exit('no retrained checkpoint found')
+    return max(cands, key=os.path.getmtime)
+
+
+def evaluate(model, loader, device):
+    model.eval()
+    totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
+    total_mpe, n = 0.0, 0
+    with torch.no_grad():
+        for bx, by in loader:
+            bx, by = bx.to(device), by.to(device)
+            out = model(bx)
+            bs = by.size(0)
+            total_mpe += calculate_mpjpe(out, by) * bs
+            pck = calculate_pck(out, by, thresholds=list(totals))
+            for t in totals:
+                totals[t] += pck[t] * bs
+            n += bs
+    return {'samples': n, 'mpjpe': total_mpe / n,
+            **{f'pck@{int(t*100)}': totals[t] / n for t in totals}}
+
+
+random.seed(42); np.random.seed(42); torch.manual_seed(42)
+torch.cuda.manual_seed_all(42)
+torch.backends.cudnn.deterministic = True
+
+d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
+dataset = PreprocessedCSIKeypointsDataset(data_dir=d, keypoint_scale=1000.0,
+                                          enable_temporal_clean=True)
+_, _, test_loader = create_preprocessed_train_val_test_loaders(
+    dataset=dataset, batch_size=256, num_workers=2, random_seed=42)
+
+device = torch.device('cuda')
+ckpt = find_checkpoint()
+print('checkpoint:', ckpt)
+model = WiFlowPoseModel(dropout=0.5).to(device)
+state = torch.load(ckpt, map_location=device, weights_only=True)
+renames = {'att.': 'attention.', 'final_conv.': 'decoder.'}
+state = {next((new + k[len(old):] for old, new in renames.items()
+               if k.startswith(old)), k): v for k, v in state.items()}
+model.load_state_dict(state, strict=True)
+
+results = {'checkpoint': ckpt}
+print('=== full test set ===')
+results['test_full'] = evaluate(model, test_loader, device)
+print(json.dumps(results['test_full'], indent=2))
+
+# NaN-free subset: exclude windows from corrupted files 487-499
+test_subset = test_loader.dataset            # Subset(dataset, test_indices)
+w2f = dataset.window_to_file
+clean_idx = [i for i in test_subset.indices if w2f[i] < 487]
+print(f'=== NaN-free test subset ({len(clean_idx)} of {len(test_subset.indices)}) ===')
+clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256, shuffle=False)
+results['test_clean'] = evaluate(model, clean_loader, device)
+print(json.dumps(results['test_clean'], indent=2))
+
+out = os.path.expanduser('~/wiflow-std-bench/eval_retrained.json')
+with open(out, 'w') as f:
+    json.dump(results, f, indent=2)
+print('wrote', out)
@@ -0,0 +1,374 @@
+"""ADR-152 SS2.2 measurement (b): WiFlow-STD fine-tuned on our fresh ESP32 paired dataset.
+
+Dataset: ~/wiflow-std-bench/paired-20260610.jsonl -- 2,046 paired windows collected
+2026-06-10 22:10-22:40 (ONE subject, ONE room, ONE ESP32 node, varied poses).
+Per record: csi = flat float32 list, csi_shape, kp = 17 COCO [x, y] normalized [0,1]
+camera coords, conf (MediaPipe mean confidence, all > 0.5 in this set), ts_start/ts_end.
+Aligner: scripts/align-ground-truth.js, non-overlapping 20-frame windows (~0.42 s each).
+
+Dataset findings (MEASURED on this file, 2026-06-10):
+  - csi_shape is HETEROGENEOUS, not uniformly [70, 20]: 1,347x [70,20], 284x [134,20],
+    243x [26,20], 130x [12,20], 42x [20,20]. The ESP32 stream emits mixed frame types
+    and the aligner stamps each window's subcarrier count from frame[0]
+    (extractCsiMatrix: nSc = window[0].subcarriers), zero-padding/truncating the rest.
+    Even native-70 windows contain ~20.4% internally zero-padded short frames
+    (subcarriers 40..69 all-zero for those frames).
+  - LAYOUT BUG: the aligner fills matrix[f * nSc + s] (frame-major) but declares
+    shape [nSc, nFrames]. The true layout is (frame, subcarrier); we reshape
+    (nFrames, nSc) and transpose. Confirmed by coherent per-frame zero-tails.
+  - Handling here (primary suite, "all2046"): every frame's subcarrier axis is
+    linearly resampled to 70 bins (np.interp over a normalized index domain;
+    identity for native-70 frames) so the pre-registered n=2,046 and split sizes
+    hold. Secondary suite ("native70") restricts to the 1,347 native [70,20]
+    windows (temporal 70/15/15 of those) as a homogeneity robustness check.
+
+Pre-registered protocol (followed exactly):
+  1. TEMPORAL split (records are time-sorted; asserted): first 70% train (1,432),
+     next 15% val (307), last 15% test (307). No shuffling across time. Seed 42
+     for everything else.
+  2. Model: upstream WiFlow-STD trunk (WiFlowPoseModel) with a learned 1x1 Conv1d
+     projection 70->540 prepended, and K=17 via the parameter-free adaptive pool
+     (AdaptiveAvgPool2d((17, 1)) instead of (15, 1)) -- pretrained weights load
+     for any K. CSI normalization: divide by the TRAIN-split 99th-percentile
+     amplitude, clip to [0, 1] (documented in output JSON).
+  3. Three runs, <=60 epochs, early-stop patience 8 on val MPJPE, batch 32,
+     AdamW, fp32 (no autocast):
+       (i)   pretrained-init: trunk init from upstream/test/best_pose_model.pth
+             (the measurement-(a) retrained checkpoint, ~96% PCK@20 on WiFlow data;
+             key remap att.->attention. / final_conv.->decoder. applied defensively
+             as in eval_repro.py -- a no-op for this checkpoint, which already uses
+             the new names). Discriminative lr: adapter 1e-4, trunk 1e-5.
+       (ii)  scratch: same architecture, random init, all params lr 1e-4.
+       (iii) frozen-trunk: pretrained trunk frozen (requires_grad=False AND held in
+             .eval() so BatchNorm running stats cannot drift -- pure transfer probe);
+             only the 70->540 adapter trains, lr 1e-4.
+  4. Metrics on the temporal TEST split: torso-normalized PCK@10/20/30/40/50 and
+     MPJPE. Upstream utils/metrics.py calculate_pck(use_torso_norm=True) hardcodes
+     NECK_IDX/PELVIS_IDX = 2, 12 -- a 15-keypoint convention that is WRONG for our
+     17 COCO keypoints (2 = right_eye, 12 = right_hip). We therefore reimplement the
+     identical math (per-frame norm distance, clamp min 0.01, mean over all
+     keypoints x frames) with torso = ||l_shoulder(5) - l_hip(11)||.
+     Also reported: prediction std across test frames (constant-pose detector;
+     must be > 0) and the mean-pose-predictor baseline (train-split mean pose
+     evaluated on test -- the honesty bar).
+
+Usage (on ruvultra):
+  nice -n 10 nohup ~/wiflow-std-bench/venv/bin/python train_measb.py > train_measb.log 2>&1 &
+
+NOTE: deployed to ruvultra as a standalone single file, so it deliberately
+inlines its helpers. The reference implementations (upstream import shim,
+np.load mmap patch, key-remap loader, canonical evaluate loop) live in
+benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
+"""
+
+import json
+import os
+import random
+import sys
+import time
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+BENCH = os.path.expanduser("~/wiflow-std-bench")
+UPSTREAM = os.path.join(BENCH, "upstream")
+MEASB = os.path.join(BENCH, "measb")
+DATA = os.path.join(BENCH, "paired-20260610.jsonl")
+CHECKPOINT = os.path.join(UPSTREAM, "test", "best_pose_model.pth")
+
+sys.path.insert(0, UPSTREAM)
+
+# Upstream defect (1): models/__init__.py imports a name tcn.py does not define.
+# Register a stub package so the broken __init__ never executes (as eval_repro.py).
+import types  # noqa: E402
+
+_models_pkg = types.ModuleType("models")
+_models_pkg.__path__ = [os.path.join(UPSTREAM, "models")]
+sys.modules["models"] = _models_pkg
+
+from models.pose_model import WiFlowPoseModel  # noqa: E402
+
+SEED = 42
+K = 17
+N_SUBC = 70
+TRUNK_IN = 540
+BATCH = 32          # <= 64 per protocol (GPU shared with the efficiency sweep)
+MAX_EPOCHS = 60
+PATIENCE = 8
+LR_ADAPTER = 1e-4
+LR_TRUNK_FT = 1e-5  # 10x lower for the pretrained trunk vs the fresh adapter
+L_SHOULDER, L_HIP = 5, 11
+THRESHOLDS = (0.1, 0.2, 0.3, 0.4, 0.5)
+
+
+def set_seed(seed=SEED):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+
+def resample_subcarriers(frame_major, n_out=N_SUBC):
+    """(nFrames, nSc) -> (nFrames, n_out) by per-frame linear interpolation.
+
+    Identity for nSc == n_out. Normalized index domain [0, 1] on both sides.
+    """
+    nf, nsc = frame_major.shape
+    if nsc == n_out:
+        return frame_major
+    xi = np.linspace(0.0, 1.0, nsc)
+    xo = np.linspace(0.0, 1.0, n_out)
+    return np.stack([np.interp(xo, xi, frame_major[f]) for f in range(nf)]).astype(np.float32)
+
+
+def load_dataset():
+    csi, kps, confs, ts, native70 = [], [], [], [], []
+    shape_counts = {}
+    with open(DATA) as f:
+        for line in f:
+            r = json.loads(line)
+            nsc, nf = r["csi_shape"]
+            shape_counts[f"{nsc}x{nf}"] = shape_counts.get(f"{nsc}x{nf}", 0) + 1
+            assert nf == 20, r["csi_shape"]
+            # Aligner layout bug: data is frame-major despite the declared
+            # [nSc, nFrames] shape -- reshape (nFrames, nSc), then resample the
+            # subcarrier axis to 70 and transpose to (70 subcarriers, 20 frames).
+            fm = np.asarray(r["csi"], dtype=np.float32).reshape(nf, nsc)
+            csi.append(resample_subcarriers(fm).T)
+            kp = np.asarray(r["kp"], dtype=np.float32)
+            assert kp.shape == (K, 2), kp.shape
+            kps.append(kp)
+            confs.append(r["conf"])
+            ts.append(r["ts_start"])
+            native70.append(nsc == N_SUBC)
+    assert all(ts[i] <= ts[i + 1] for i in range(len(ts) - 1)), "records not time-sorted"
+    return (np.stack(csi), np.stack(kps), np.asarray(confs, dtype=np.float32),
+            np.asarray(native70), shape_counts, ts[0], ts[-1])
+
+
+def temporal_split(n):
+    n_train = int(round(n * 0.70))
+    n_val = int(round(n * 0.15))
+    return slice(0, n_train), slice(n_train, n_train + n_val), slice(n_train + n_val, n)
+
+
+class AdaptedWiFlow(nn.Module):
+    """1x1 Conv1d adapter 70->540 + upstream WiFlow-STD trunk with K=17 pool head."""
+
+    def __init__(self, k=K, dropout=0.5):
+        super().__init__()
+        self.adapter = nn.Conv1d(N_SUBC, TRUNK_IN, kernel_size=1)
+        nn.init.kaiming_normal_(self.adapter.weight, mode="fan_out", nonlinearity="relu")
+        nn.init.constant_(self.adapter.bias, 0)
+        self.trunk = WiFlowPoseModel(dropout=dropout)
+        # K=17 via the parameter-free adaptive pool: decoder emits [B, 2, 15, 20]
+        # spatial maps; pooling H->17 instead of 15 yields [B, 17, 2] with no new
+        # parameters, so the pretrained state_dict loads strict=True for any K.
+        self.trunk.avg_pool = nn.AdaptiveAvgPool2d((k, 1))
+
+    def forward(self, x):
+        return self.trunk(self.adapter(x))
+
+
+def load_pretrained_trunk(trunk, path):
+    state = torch.load(path, map_location="cpu", weights_only=True)
+    # Defensive remap as in eval_repro.py (no-op for the retrained checkpoint).
+    renames = {"att.": "attention.", "final_conv.": "decoder."}
+    state = {next((new + k[len(old):] for old, new in renames.items()
+                   if k.startswith(old)), k): v
+             for k, v in state.items()}
+    trunk.load_state_dict(state, strict=True)
+
+
+def pck_torso(pred, target, thresholds=THRESHOLDS):
+    """Upstream calculate_pck math, torso = l_shoulder(5)<->l_hip(11) for 17-kp COCO."""
+    norm = torch.sqrt(((target[:, L_SHOULDER] - target[:, L_HIP]) ** 2).sum(dim=1))
+    norm = torch.clamp(norm, min=0.01)
+    dist = torch.sqrt(((pred - target) ** 2).sum(dim=2)) / norm.unsqueeze(1)
+    return {f"pck@{int(t * 100)}": (dist <= t).float().mean().item() for t in thresholds}
+
+
+def mpjpe(pred, target):
+    return torch.sqrt(((pred - target) ** 2).sum(dim=2)).mean().item()
+
+
+@torch.no_grad()
+def predict(model, x, batch=256):
+    model.eval()
+    return torch.cat([model(x[i:i + batch]) for i in range(0, len(x), batch)])
+
+
+def eval_preds(pred, target):
+    out = pck_torso(pred, target)
+    out["mpjpe"] = mpjpe(pred, target)
+    # Constant-pose detector: std across test frames per coordinate, mean over
+    # the 17x2 coordinates. 0.0 == degenerate constant predictor.
+    out["pred_std"] = pred.std(dim=0).mean().item()
+    return out
+
+
+def train_run(name, x_tr, y_tr, x_va, y_va, device, pretrained, freeze_trunk,
+              lr_trunk):
+    set_seed(SEED)
+    model = AdaptedWiFlow().to(device)
+    if pretrained:
+        load_pretrained_trunk(model.trunk, CHECKPOINT)
+    if freeze_trunk:
+        for p in model.trunk.parameters():
+            p.requires_grad = False
+        groups = [{"params": model.adapter.parameters(), "lr": LR_ADAPTER}]
+    else:
+        groups = [{"params": model.adapter.parameters(), "lr": LR_ADAPTER},
+                  {"params": model.trunk.parameters(), "lr": lr_trunk}]
+    opt = torch.optim.AdamW(groups)
+    loss_fn = nn.MSELoss()
+
+    n = len(x_tr)
+    best_val, best_state, best_epoch, bad = float("inf"), None, -1, 0
+    history = []
+    t0 = time.time()
+    for epoch in range(MAX_EPOCHS):
+        model.train()
+        if freeze_trunk:
+            model.trunk.eval()  # keep BatchNorm running stats fixed: pure transfer
+        perm = torch.randperm(n, device=device)
+        ep_loss = 0.0
+        for i in range(0, n, BATCH):
+            idx = perm[i:i + BATCH]
+            opt.zero_grad()
+            loss = loss_fn(model(x_tr[idx]), y_tr[idx])
+            loss.backward()
+            opt.step()
+            ep_loss += loss.item() * len(idx)
+        val_mpjpe = mpjpe(predict(model, x_va), y_va)
+        history.append({"epoch": epoch, "train_mse": ep_loss / n, "val_mpjpe": val_mpjpe})
+        marker = ""
+        if val_mpjpe < best_val:
+            best_val, best_epoch, bad = val_mpjpe, epoch, 0
+            best_state = {k: v.detach().cpu().clone() for k, v in model.state_dict().items()}
+            marker = " *"
+        else:
+            bad += 1
+        print(f"[{name}] epoch {epoch:02d} train_mse {ep_loss / n:.6f} "
+              f"val_mpjpe {val_mpjpe:.5f}{marker}", flush=True)
+        if bad >= PATIENCE:
+            print(f"[{name}] early stop at epoch {epoch} (best {best_epoch})", flush=True)
+            break
+    model.load_state_dict(best_state)
+    torch.save(best_state, os.path.join(MEASB, f"{name}_best.pth"))
+    return model, {"best_epoch": best_epoch, "best_val_mpjpe": best_val,
+                   "epochs_run": len(history), "wall_seconds": round(time.time() - t0, 1),
+                   "history": history}
+
+
+def run_suite(tag, csi, kps, device):
+    """Temporal 70/15/15 split, mean-pose baseline, three training runs."""
+    n = len(csi)
+    tr, va, te = temporal_split(n)
+    print(f"=== suite {tag}: n={n} train={tr.stop} val={va.stop - va.start} "
+          f"test={te.stop - te.start} ===", flush=True)
+
+    # CSI normalization constant from TRAIN split only.
+    train_p99 = float(np.percentile(csi[tr], 99))
+    train_max = float(csi[tr].max())
+    print(f"[{tag}] train p99={train_p99:.3f} max={train_max:.3f} -> /p99, clip [0,1]",
+          flush=True)
+    csi_n = np.clip(csi / train_p99, 0.0, 1.0).astype(np.float32)
+
+    x = torch.from_numpy(csi_n).to(device)
+    y = torch.from_numpy(kps).to(device)
+    x_tr, y_tr = x[tr], y[tr]
+    x_va, y_va = x[va], y[va]
+    x_te, y_te = x[te], y[te]
+
+    suite = {
+        "n_windows": n,
+        "split": {"n_train": int(tr.stop), "n_val": int(va.stop - va.start),
+                  "n_test": int(te.stop - te.start)},
+        "csi_norm": {"method": "divide by train-split p99 amplitude, clip [0,1]",
+                     "train_p99": train_p99, "train_max": train_max},
+        "runs": {},
+    }
+
+    # Honesty bar: mean-pose predictor fit on TRAIN, evaluated on TEST.
+    mean_pose = y_tr.mean(dim=0, keepdim=True).expand(len(y_te), -1, -1)
+    suite["mean_pose_baseline"] = eval_preds(mean_pose, y_te)
+    suite["mean_pose_baseline"]["note"] = "train-split mean pose; pred_std 0 by construction"
+    print(f"[{tag}] mean-pose baseline:", json.dumps(suite["mean_pose_baseline"]),
+          flush=True)
+
+    configs = [
+        ("pretrained", dict(pretrained=True, freeze_trunk=False, lr_trunk=LR_TRUNK_FT)),
+        ("scratch", dict(pretrained=False, freeze_trunk=False, lr_trunk=LR_ADAPTER)),
+        ("frozen_trunk", dict(pretrained=True, freeze_trunk=True, lr_trunk=0.0)),
+    ]
+    for name, cfg in configs:
+        print(f"=== run: {tag}/{name} {cfg} ===", flush=True)
+        model, train_info = train_run(f"{tag}_{name}", x_tr, y_tr, x_va, y_va,
+                                      device, **cfg)
+        test_metrics = eval_preds(predict(model, x_te), y_te)
+        n_trainable = sum(p.numel() for p in model.parameters() if p.requires_grad)
+        suite["runs"][name] = {"config": cfg, "trainable_params": n_trainable,
+                               "train": {k: v for k, v in train_info.items()
+                                         if k != "history"},
+                               "history": train_info["history"],
+                               "test": test_metrics}
+        print(f"[{tag}/{name}] TEST:", json.dumps(test_metrics), flush=True)
+    return suite
+
+
+def main():
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"device {device}, torch {torch.__version__}", flush=True)
+    set_seed(SEED)
+
+    csi, kps, confs, native70, shape_counts, ts_first, ts_last = load_dataset()
+    print(f"shape distribution: {shape_counts}", flush=True)
+
+    results = {
+        "protocol": {
+            "dataset": DATA, "n_windows": len(csi),
+            "ts_first": ts_first, "ts_last": ts_last,
+            "conf_mean": float(confs.mean()), "conf_min": float(confs.min()),
+            "csi_shape_distribution": shape_counts,
+            "csi_layout_note": "aligner stores frame-major data under a transposed "
+                               "[nSc, nFrames] shape label; corrected on load",
+            "csi_resample": "per-frame linear interp of subcarrier axis to 70 bins "
+                            "(identity for native-70 frames); native-70 windows still "
+                            "contain ~20.4% internally zero-padded short frames",
+            "split": "temporal 70/15/15 (no shuffle across time)",
+            "model": "1x1 Conv1d 70->540 adapter + WiFlowPoseModel trunk, "
+                     "AdaptiveAvgPool2d((17,1)) head (parameter-free K=17)",
+            "checkpoint": CHECKPOINT,
+            "checkpoint_note": "measurement-(a) retrained checkpoint (~96% PCK@20 on "
+                               "WiFlow data); att./final_conv. remap applied "
+                               "defensively (no-op, already new-style keys)",
+            "optimizer": f"AdamW, adapter lr {LR_ADAPTER}, fine-tuned trunk lr "
+                         f"{LR_TRUNK_FT} (10x lower), scratch all {LR_ADAPTER}",
+            "batch": BATCH, "max_epochs": MAX_EPOCHS, "patience": PATIENCE,
+            "precision": "fp32", "seed": SEED,
+            "pck": "torso-normalized, torso = ||l_shoulder(5) - l_hip(11)||, "
+                   "clamp min 0.01, mean over keypoints x frames "
+                   "(upstream math; upstream 2/12 indices are a 15-kp convention)",
+        },
+        # Primary: all 2,046 windows (pre-registered n), subcarrier axis resampled.
+        "all2046": None,
+        # Secondary robustness check: the 1,347 native [70,20] windows only.
+        "native70": None,
+    }
+
+    results["all2046"] = run_suite("all2046", csi, kps, device)
+    results["native70"] = run_suite("native70", csi[native70], kps[native70], device)
+
+    out = os.path.join(MEASB, "measurement_b.json")
+    with open(out, "w") as f:
+        json.dump(results, f, indent=2)
+    print(f"wrote {out}", flush=True)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,33 @@
+#!/bin/bash
+set -ex
+cd ~/wiflow-std-bench
+
+# 1. clone upstream at the pinned commit
+if [ ! -d upstream ]; then
+  git clone https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling upstream
+fi
+cd upstream && git checkout 06899d294a0f44709d601a53e91dbf24759daefb && cd ..
+
+# 2. documented deviation: fix upstream import bug (TemporalConvNet does not exist)
+sed -i 's/from .tcn import TemporalConvNet/from .tcn import TemporalBlock/; s/'"'"'TemporalConvNet'"'"'/'"'"'TemporalBlock'"'"'/' upstream/models/__init__.py
+
+# 3. venv: torch cu128 (RTX 5080 = sm_120 needs >=2.7; their pin 2.3.1 predates Blackwell)
+if [ ! -d venv ]; then
+  python3 -m venv venv
+  ./venv/bin/pip install -q --upgrade pip
+  ./venv/bin/pip install -q torch --index-url https://download.pytorch.org/whl/cu128
+  ./venv/bin/pip install -q numpy pandas matplotlib seaborn scikit-learn opencv-python-headless scipy tqdm psutil kagglehub
+fi
+./venv/bin/python -c "import torch; print(torch.__version__, torch.cuda.is_available(), torch.cuda.get_device_name(0))"
+
+# 4. dataset via kagglehub (anonymous, public dataset)
+DS=$(./venv/bin/python -c "import kagglehub; print(kagglehub.dataset_download('kaka2434/wiflow-dataset'))")
+echo "dataset at: $DS"
+
+# 5. run.py hardcodes ../preprocessed_csi_data relative to upstream/
+ln -sfn "$DS/preprocessed_csi_data" ~/wiflow-std-bench/preprocessed_csi_data
+
+# 6. train with upstream defaults (seed 42 set inside run.py)
+../venv/bin/python ../clean_nan.py 2>/dev/null || venv/bin/python clean_nan.py
+cd upstream
+../venv/bin/python run.py --gpu 0 --batch_size 64 --epochs 50 --output_dir ../train_output
@@ -0,0 +1,332 @@
+"""Configurable compact variants of the WiFlow-STD pose model (ADR-152 efficiency sweep).
+
+This is a parameterized copy of upstream models/{pose_model,tcn,convnet,attention}.py
+(DY2434/WiFlow @ 06899d29, Apache-2.0). upstream/ is NOT modified. Deviations from
+upstream, all forced by shrinking channels and documented per variant in run_sweep.py:
+
+1. TCN grouped-conv groups: upstream hardcodes groups=20, which does not divide
+   the compact channel counts (e.g. 270, 135, 85). Rule here:
+   - groups_mode='gcd20': per-conv groups = gcd(channels, 20)  (== 20 wherever
+     upstream's choice is valid, incl. the 540-ch input conv; falls back to the
+     largest common divisor with 20 otherwise).
+   - groups_mode='depthwise': groups = channels (tiny variant only).
+2. Conv2d downsampling strides: upstream uses 4 stride-(1,2) blocks because
+   240/2^4 = 15 == n_keypoints. With smaller TCN output widths that would leave
+   <15 rows and AdaptiveAvgPool2d((15,1)) would duplicate rows across keypoints.
+   Rule: halve the width only while the result stays >= 15 (stride-2 blocks
+   first, stride-1 after). Full model: 240 -> 4 halvings = upstream exactly.
+3. input_pw_groups (tiny only): the dense 540->c pointwise + residual downsample
+   in TCN block 1 cost 2*540*c params (a ~117k floor that alone exceeds the
+   tiny <100k budget). tiny groups these two convs (groups=4; 4 | gcd(540, 68)).
+4. Decoder mid-channels: upstream 64->32; here c_last -> max(c_last // 2, 4).
+"""
+import math
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+def tcn_groups(channels: int, mode: str) -> int:
+    if mode == 'depthwise':
+        return channels
+    if mode == 'gcd20':
+        return math.gcd(channels, 20)
+    raise ValueError(mode)
+
+
+# ---------------------------------------------------------------- TCN (copy of tcn.py)
+class Chomp1d(nn.Module):
+    def __init__(self, chomp_size):
+        super().__init__()
+        self.chomp_size = chomp_size
+
+    def forward(self, x):
+        return x[:, :, :-self.chomp_size].contiguous()
+
+
+class CompactGroupedTemporalBlock(nn.Module):
+    """Upstream InnerGroupedTemporalBlock with parameterized groups."""
+
+    def __init__(self, n_inputs, n_outputs, kernel_size, stride, dilation, padding,
+                 dropout=0.2, groups_mode='gcd20', pw_groups=1):
+        super().__init__()
+        g_in = tcn_groups(n_inputs, groups_mode)
+        g_out = tcn_groups(n_outputs, groups_mode)
+        self.groups = (g_in, g_out)
+        self.pw_groups = pw_groups
+
+        self.conv1_group = nn.Conv1d(n_inputs, n_inputs, kernel_size, stride=stride,
+                                     padding=padding, dilation=dilation,
+                                     groups=g_in, bias=False)
+        self.chomp1 = Chomp1d(padding) if padding > 0 else nn.Identity()
+        self.bn1_group = nn.BatchNorm1d(n_inputs)
+        self.relu1_group = nn.SiLU(inplace=True)
+
+        self.conv1_pw = nn.Conv1d(n_inputs, n_outputs, 1, groups=pw_groups, bias=False)
+        self.bn1_pw = nn.BatchNorm1d(n_outputs)
+        self.relu1_pw = nn.SiLU(inplace=True)
+        self.dropout1 = nn.Dropout(dropout)
+
+        self.conv2_group = nn.Conv1d(n_outputs, n_outputs, kernel_size, stride=1,
+                                     padding=padding, dilation=dilation,
+                                     groups=g_out, bias=False)
+        self.chomp2 = Chomp1d(padding) if padding > 0 else nn.Identity()
+        self.bn2_group = nn.BatchNorm1d(n_outputs)
+        self.relu2_group = nn.SiLU(inplace=True)
+
+        self.conv2_pw = nn.Conv1d(n_outputs, n_outputs, 1, bias=False)
+        self.bn2_pw = nn.BatchNorm1d(n_outputs)
+        self.relu2_pw = nn.SiLU(inplace=True)
+        self.dropout2 = nn.Dropout(dropout)
+
+        self.downsample = nn.Sequential(
+            nn.Conv1d(n_inputs, n_outputs, 1, groups=pw_groups, bias=False),
+            nn.BatchNorm1d(n_outputs)
+        ) if n_inputs != n_outputs else nn.Identity()
+
+    def forward(self, x):
+        res = self.downsample(x)
+        out = self.conv1_group(x)
+        out = self.chomp1(out)
+        out = self.bn1_group(out)
+        out = self.relu1_group(out)
+        out = self.conv1_pw(out)
+        out = self.bn1_pw(out)
+        out = self.relu1_pw(out)
+        out = self.dropout1(out)
+        out = self.conv2_group(out)
+        out = self.chomp2(out)
+        out = self.bn2_group(out)
+        out = self.relu2_group(out)
+        out = self.conv2_pw(out)
+        out = self.bn2_pw(out)
+        out = self.relu2_pw(out)
+        out = self.dropout2(out)
+        return F.silu(out + res)
+
+
+class CompactTemporalBlock(nn.Module):
+    def __init__(self, num_inputs, num_channels, kernel_size=3, dropout=0.2,
+                 groups_mode='gcd20', input_pw_groups=1):
+        super().__init__()
+        layers = []
+        for i, out_channels in enumerate(num_channels):
+            dilation_size = 2 ** i
+            in_channels = num_inputs if i == 0 else num_channels[i - 1]
+            layers.append(CompactGroupedTemporalBlock(
+                in_channels, out_channels, kernel_size, stride=1,
+                dilation=dilation_size, padding=(kernel_size - 1) * dilation_size,
+                dropout=dropout, groups_mode=groups_mode,
+                pw_groups=input_pw_groups if i == 0 else 1))
+        self.network = nn.Sequential(*layers)
+
+    def forward(self, x):
+        return self.network(x)
+
+
+# ------------------------------------------------------- Conv2d path (copy of convnet.py)
+class AsymmetricConvBlock(nn.Module):
+    """Upstream block with parameterized width stride (upstream: always (1,2))."""
+
+    def __init__(self, in_channels, out_channels, dropout=0.3, stride_w=2):
+        super().__init__()
+        self.block = nn.Sequential(
+            nn.Conv2d(in_channels, out_channels, kernel_size=(1, 3),
+                      stride=(1, stride_w), padding=(0, 1)),
+            nn.BatchNorm2d(out_channels),
+            nn.SiLU(inplace=True),
+            nn.Dropout2d(dropout),
+            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
+            nn.BatchNorm2d(out_channels),
+            nn.SiLU(inplace=True),
+            nn.Dropout2d(dropout),
+            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
+            nn.BatchNorm2d(out_channels)
+        )
+        self.downsample = nn.Sequential(
+            nn.Conv2d(in_channels, out_channels, kernel_size=1,
+                      stride=(1, stride_w), bias=False),
+            nn.BatchNorm2d(out_channels)
+        )
+        self.activation = nn.SiLU(inplace=True)
+
+    def forward(self, x):
+        return self.activation(self.block(x) + self.downsample(x))
+
+
+class ConvBlock1(nn.Module):
+    def __init__(self, in_channels, out_channels, dropout=0.3):
+        super().__init__()
+        self.block = nn.Sequential(
+            nn.Conv2d(in_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
+            nn.BatchNorm2d(out_channels),
+            nn.SiLU(inplace=True),
+            nn.Dropout2d(dropout),
+            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
+            nn.BatchNorm2d(out_channels),
+            nn.SiLU(inplace=True),
+            nn.Dropout2d(dropout),
+            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
+            nn.BatchNorm2d(out_channels)
+        )
+        self.downsample = nn.Sequential(
+            nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, bias=False),
+            nn.BatchNorm2d(out_channels)
+        )
+        self.activation = nn.SiLU(inplace=True)
+
+    def forward(self, x):
+        return self.activation(self.block(x) + self.downsample(x))
+
+
+# ----------------------------------------------------- attention (verbatim attention.py)
+class AxialAttention(nn.Module):
+    def __init__(self, in_planes, out_planes, groups=8, stride=1, bias=False, width=False):
+        assert (in_planes % groups == 0) and (out_planes % groups == 0)
+        super().__init__()
+        self.in_planes = in_planes
+        self.out_planes = out_planes
+        self.groups = groups
+        self.group_planes = out_planes // groups
+        self.stride = stride
+        self.bias = bias
+        self.width = width
+        self.qkv_transform = nn.Conv1d(in_planes, out_planes * 3, kernel_size=1,
+                                       stride=1, padding=0, bias=False)
+        self.bn_qkv = nn.BatchNorm1d(out_planes * 3)
+        self.bn_similarity = nn.BatchNorm2d(groups)
+        self.bn_output = nn.BatchNorm1d(out_planes)
+        if stride > 1:
+            self.pooling = nn.AvgPool2d(stride, stride=stride)
+        nn.init.normal_(self.qkv_transform.weight.data, 0, math.sqrt(1. / self.in_planes))
+
+    def forward(self, x):
+        if self.width:
+            x = x.permute(0, 2, 1, 3)
+        else:
+            x = x.permute(0, 3, 1, 2)
+        N, W, C, H = x.shape
+        x = x.contiguous().view(N * W, C, H)
+        qkv = self.bn_qkv(self.qkv_transform(x))
+        qkv = qkv.reshape(N * W, 3, self.out_planes, H).permute(1, 0, 2, 3)
+        q, k, v = qkv[0], qkv[1], qkv[2]
+        q = q.reshape(N * W, self.groups, self.group_planes, H)
+        k = k.reshape(N * W, self.groups, self.group_planes, H)
+        v = v.reshape(N * W, self.groups, self.group_planes, H)
+        qk = torch.einsum('bgci, bgcj->bgij', q, k)
+        qk = self.bn_similarity(qk)
+        similarity = F.softmax(qk, dim=-1)
+        sv = torch.einsum('bgij,bgcj->bgci', similarity, v)
+        sv = sv.reshape(N * W, self.out_planes, H)
+        out = self.bn_output(sv)
+        out = out.view(N, W, self.out_planes, H)
+        if self.width:
+            out = out.permute(0, 2, 1, 3)
+        else:
+            out = out.permute(0, 2, 3, 1)
+        if self.stride > 1:
+            out = self.pooling(out)
+        return out
+
+
+class DualAxialAttention(nn.Module):
+    def __init__(self, in_planes, out_planes, groups=8, stride=1, bias=False):
+        super().__init__()
+        self.width_axis = AxialAttention(in_planes, out_planes, groups, stride, bias, width=True)
+        self.height_axis = AxialAttention(out_planes, out_planes, groups, stride, bias, width=False)
+
+    def forward(self, x):
+        return self.height_axis(self.width_axis(x))
+
+
+# --------------------------------------------------------------- full model
+def compute_strides(width: int, n_blocks: int, target: int = 15):
+    """Halve width while result stays >= target (upstream: 240 -> 4 halvings -> 15)."""
+    strides = []
+    for _ in range(n_blocks):
+        nxt = (width + 1) // 2  # conv k=3 s=2 p=1: out = ceil(in/2)
+        if nxt >= target:
+            strides.append(2)
+            width = nxt
+        else:
+            strides.append(1)
+    return strides, width
+
+
+class CompactWiFlowPoseModel(nn.Module):
+    """Parameterized upstream WiFlowPoseModel.
+
+    Upstream config == tcn_channels=[540,440,340,240], conv_channels=[8,16,32,64],
+    attn_groups=8, groups_mode='gcd20' (gcd(c,20)==20 for all upstream channels),
+    input_pw_groups=1 -> identical architecture, 2,225,042 params.
+    """
+
+    def __init__(self, tcn_channels, conv_channels, attn_groups,
+                 groups_mode='gcd20', input_pw_groups=1, dropout=0.3,
+                 num_subcarriers=540, num_keypoints=15):
+        super().__init__()
+        self.tcn = CompactTemporalBlock(
+            num_inputs=num_subcarriers, num_channels=tcn_channels, kernel_size=3,
+            dropout=dropout, groups_mode=groups_mode, input_pw_groups=input_pw_groups)
+
+        self.up = ConvBlock1(1, conv_channels[0])
+
+        strides, self.final_width = compute_strides(
+            tcn_channels[-1], len(conv_channels), target=num_keypoints)
+        self.conv_strides = strides
+        self.residual_blocks = nn.ModuleList()
+        in_channels = conv_channels[0]
+        for out_channels, s in zip(conv_channels, strides):
+            self.residual_blocks.append(
+                AsymmetricConvBlock(in_channels, out_channels, stride_w=s))
+            in_channels = out_channels
+
+        c_last = conv_channels[-1]
+        self.attention = DualAxialAttention(c_last, c_last, groups=attn_groups)
+
+        c_mid = max(c_last // 2, 4)
+        self.decoder = nn.Sequential(
+            nn.Conv2d(c_last, c_mid, kernel_size=3, padding=1),
+            nn.BatchNorm2d(c_mid),
+            nn.SiLU(inplace=True),
+            nn.Conv2d(c_mid, 2, kernel_size=1),
+            nn.BatchNorm2d(2),
+            nn.SiLU(inplace=True)
+        )
+        self.avg_pool = nn.AdaptiveAvgPool2d((num_keypoints, 1))
+        self._initialize_weights()
+
+    def _initialize_weights(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv1d):
+                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+                if m.bias is not None:
+                    nn.init.constant_(m.bias, 0)
+            elif isinstance(m, (nn.BatchNorm1d, nn.LayerNorm)):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+            elif isinstance(m, nn.Linear):
+                nn.init.xavier_normal_(m.weight)
+                if m.bias is not None:
+                    nn.init.constant_(m.bias, 0)
+
+    def forward(self, x):
+        # [B, 540, 20]
+        x = self.tcn(x)                          # [B, C_tcn, 20]
+        x = x.transpose(1, 2).unsqueeze(1)       # [B, 1, 20, C_tcn]
+        x = self.up(x)
+        for block in self.residual_blocks:
+            x = block(x)                         # [B, C_conv, 20, W']
+        x = x.permute(0, 1, 3, 2)                # [B, C_conv, W', 20]
+        x = self.attention(x)
+        x = self.decoder(x)                      # [B, 2, W', 20]
+        x = self.avg_pool(x).squeeze(-1)         # [B, 2, 15]
+        return x.transpose(1, 2)                 # [B, 15, 2]
+
+
+def describe(model: 'CompactWiFlowPoseModel'):
+    params = sum(p.numel() for p in model.parameters())
+    tcn_g = [blk.groups for blk in model.tcn.network]
+    return {'params': params, 'tcn_groups_per_block': tcn_g,
+            'conv_strides': model.conv_strides, 'final_width': model.final_width}
@@ -0,0 +1,278 @@
+"""WiFlow-STD compact-variant efficiency sweep (ADR-152) — sequential overnight runner.
+
+Trains compact variants of the upstream WiFlow-STD architecture on the same
+data/split as the full-size reference retraining (seed 42, file-level 70/15/15,
+upstream dataset.py) and evaluates PCK@10..50 + MPJPE on the full test split and
+the corruption-free test subset (file indices < 487).
+
+Training mirrors upstream run.py/train.py defaults except:
+- fp32 only (no fp16 autocast / GradScaler — avoids the BN-poisoning trap
+  documented in RESULTS.md defect 5; data on disk is already cleaned).
+- batch 64 (kept modest: another GPU job may share the 16 GB card tonight).
+- scheduler + early stopping keyed on val MPJPE (upstream early-stops on val MPE
+  with patience 5; same here).
+
+Usage:
+  venv/bin/python sweep/run_sweep.py --dry-run    # param counts only
+  nohup venv/bin/python sweep/run_sweep.py > sweep/sweep.log 2>&1 &
+
+Idempotent: variants already present in sweep/results.jsonl are skipped.
+
+NOTE: deployed to ruvultra (~/wiflow-std-bench/sweep) as a standalone file, so
+it deliberately inlines its helpers. The reference implementations (upstream
+import shim, >1GB np.load mmap patch, key-remap loader, canonical evaluate
+loop) live in benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
+"""
+import argparse
+import copy
+import json
+import os
+import random
+import sys
+import time
+
+import numpy as np
+import torch
+from torch.utils.data import DataLoader, Subset
+
+# csi_windows.npy is ~13 GB; mmap large arrays instead of eagerly loading
+# ~15 GB into RAM (same patch as _bench_common._np_load_mmap).
+_np_load = np.load
+
+
+def _np_load_mmap(path, *a, **kw):
+    if (isinstance(path, str) and path.endswith('.npy')
+            and os.path.getsize(path) > 1 << 30 and 'mmap_mode' not in kw):
+        kw['mmap_mode'] = 'r'
+    return _np_load(path, *a, **kw)
+
+
+np.load = _np_load_mmap
+
+BENCH = os.path.expanduser('~/wiflow-std-bench')
+SWEEP = os.path.join(BENCH, 'sweep')
+sys.path.insert(0, os.path.join(BENCH, 'upstream'))
+sys.path.insert(0, SWEEP)
+
+from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders  # noqa: E402
+from losses.pose_loss import PoseLoss          # noqa: E402
+from utils.metrics import calculate_pck, calculate_mpjpe  # noqa: E402
+from model_compact import CompactWiFlowPoseModel, describe  # noqa: E402
+
+VARIANTS = [
+    # name, tcn_channels, conv_channels, attn_groups, groups_mode, input_pw_groups
+    dict(name='half',    tcn=[270, 220, 170, 120], conv=[4, 8, 16, 32], attn_groups=4,
+         groups_mode='gcd20', input_pw_groups=1),
+    dict(name='quarter', tcn=[135, 110, 85, 60],   conv=[2, 4, 8, 16],  attn_groups=2,
+         groups_mode='gcd20', input_pw_groups=1),
+    dict(name='tiny',    tcn=[68, 56, 44, 32],     conv=[2, 4, 8, 16],  attn_groups=2,
+         groups_mode='depthwise', input_pw_groups=4),
+]
+
+BATCH = 64
+EPOCHS = 50
+PATIENCE = 5
+LR = 1e-4
+WEIGHT_DECAY = 5e-5
+SEED = 42
+CORRUPT_FILE_START = 487  # files 487-499 were zero-filled by clean_nan.py
+
+
+def set_seed(seed=SEED):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+
+def build_model(v, dropout=0.5):
+    return CompactWiFlowPoseModel(
+        tcn_channels=v['tcn'], conv_channels=v['conv'], attn_groups=v['attn_groups'],
+        groups_mode=v['groups_mode'], input_pw_groups=v['input_pw_groups'],
+        dropout=dropout)
+
+
+@torch.no_grad()
+def evaluate(model, loader, device):
+    model.eval()
+    totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
+    total_mpe, n = 0.0, 0
+    for bx, by in loader:
+        bx, by = bx.to(device), by.to(device)
+        out = model(bx)
+        bs = by.size(0)
+        total_mpe += calculate_mpjpe(out, by) * bs
+        pck = calculate_pck(out, by, thresholds=list(totals))
+        for t in totals:
+            totals[t] += pck[t] * bs
+        n += bs
+    return {'samples': n, 'mpjpe': total_mpe / n,
+            **{f'pck@{int(t * 100)}': totals[t] / n for t in totals}}
+
+
+def train_variant(v, dataset, device):
+    set_seed(SEED)
+    train_loader, val_loader, test_loader = create_preprocessed_train_val_test_loaders(
+        dataset=dataset, batch_size=BATCH, num_workers=2, random_seed=SEED)
+
+    set_seed(SEED)  # re-seed after split so init is split-independent
+    model = build_model(v).to(device)
+    info = describe(model)
+    print(f"[{v['name']}] params={info['params']:,} tcn_groups={info['tcn_groups_per_block']} "
+          f"conv_strides={info['conv_strides']} final_width={info['final_width']}", flush=True)
+
+    criterion = PoseLoss(position_weight=1.0, bone_weight=0.2, loss_type='smooth_l1')
+    optimizer = torch.optim.AdamW(model.parameters(), lr=LR, weight_decay=WEIGHT_DECAY,
+                                  betas=(0.9, 0.999))
+    scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
+        optimizer, mode='min', factor=0.5, patience=3, min_lr=LR / 1000,
+        cooldown=1, threshold=1e-4)
+
+    best_val_mpe = float('inf')
+    best_val_pck20 = 0.0
+    best_epoch = 0
+    best_state = None
+    patience_counter = 0
+    t0 = time.time()
+    error = None
+    epochs_run = 0
+
+    for epoch in range(1, EPOCHS + 1):
+        model.train()
+        ep_loss, nb = 0.0, 0
+        te = time.time()
+        for i, (bx, by) in enumerate(train_loader):
+            bx = bx.to(device, non_blocking=True)
+            by = by.to(device, non_blocking=True)
+            optimizer.zero_grad(set_to_none=True)
+            out = model(bx)
+            loss, _parts = criterion(out, by)
+            if not torch.isfinite(loss):
+                error = f'non-finite loss at epoch {epoch} step {i}'
+                break
+            loss.backward()
+            optimizer.step()
+            ep_loss += loss.item()
+            nb += 1
+            if epoch == 1 and i % 500 == 0:
+                print(f"[{v['name']}] e1 step {i}/{len(train_loader)} loss={loss.item():.5f}",
+                      flush=True)
+        if error:
+            break
+        epochs_run = epoch
+
+        val = evaluate(model, val_loader, device)
+        scheduler.step(val['mpjpe'])
+        lr_now = optimizer.param_groups[0]['lr']
+        print(f"[{v['name']}] epoch {epoch}/{EPOCHS} train_loss={ep_loss / max(nb, 1):.5f} "
+              f"val_mpjpe={val['mpjpe']:.5f} val_pck20={val['pck@20'] * 100:.2f}% "
+              f"lr={lr_now:.2e} ({time.time() - te:.0f}s)", flush=True)
+
+        if val['mpjpe'] < best_val_mpe:
+            best_val_mpe = val['mpjpe']
+            best_val_pck20 = val['pck@20']
+            best_epoch = epoch
+            best_state = copy.deepcopy(model.state_dict())
+            patience_counter = 0
+        else:
+            patience_counter += 1
+            if patience_counter >= PATIENCE:
+                print(f"[{v['name']}] early stop at epoch {epoch} (best {best_epoch})", flush=True)
+                break
+
+    train_seconds = time.time() - t0
+    result = {
+        'variant': v['name'], 'params': info['params'],
+        'tcn_channels': v['tcn'], 'conv_channels': v['conv'],
+        'attn_groups': v['attn_groups'], 'groups_mode': v['groups_mode'],
+        'input_pw_groups': v['input_pw_groups'],
+        'tcn_groups_per_block': info['tcn_groups_per_block'],
+        'conv_strides': info['conv_strides'], 'final_width': info['final_width'],
+        'batch_size': BATCH, 'max_epochs': EPOCHS, 'patience': PATIENCE,
+        'lr': LR, 'weight_decay': WEIGHT_DECAY, 'seed': SEED, 'precision': 'fp32',
+        'epochs_run': epochs_run, 'best_epoch': best_epoch,
+        'best_val_mpjpe': best_val_mpe if best_state else None,
+        'best_val_pck20': best_val_pck20 if best_state else None,
+        'train_seconds': round(train_seconds, 1),
+        'torch': torch.__version__, 'error': error,
+        'finished_utc': time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime()),
+    }
+
+    if best_state is not None:
+        ckpt = os.path.join(SWEEP, f"{v['name']}_best.pth")
+        torch.save(best_state, ckpt)
+        result['checkpoint'] = ckpt
+        model.load_state_dict(best_state)
+
+        eval_loader = DataLoader(test_loader.dataset, batch_size=256, shuffle=False,
+                                 num_workers=2)
+        result['test_full'] = evaluate(model, eval_loader, device)
+
+        w2f = dataset.window_to_file
+        clean_idx = [i for i in test_loader.dataset.indices if w2f[i] < CORRUPT_FILE_START]
+        clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256,
+                                  shuffle=False, num_workers=2)
+        result['test_clean'] = evaluate(model, clean_loader, device)
+        print(f"[{v['name']}] TEST clean: pck20={result['test_clean']['pck@20'] * 100:.2f}% "
+              f"mpjpe={result['test_clean']['mpjpe']:.5f} | full: "
+              f"pck20={result['test_full']['pck@20'] * 100:.2f}%", flush=True)
+    return result
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--dry-run', action='store_true', help='print param counts and exit')
+    args = ap.parse_args()
+
+    if args.dry_run:
+        for v in VARIANTS:
+            m = build_model(v)
+            info = describe(m)
+            x = torch.randn(2, 540, 20)
+            m.eval()
+            y = m(x)
+            print(f"{v['name']:8s} params={info['params']:>9,} "
+                  f"tcn={v['tcn']} conv={v['conv']} attn_g={v['attn_groups']} "
+                  f"mode={v['groups_mode']} pw_g={v['input_pw_groups']} "
+                  f"tcn_groups={info['tcn_groups_per_block']} strides={info['conv_strides']} "
+                  f"W'={info['final_width']} out={tuple(y.shape)}")
+        return
+
+    results_path = os.path.join(SWEEP, 'results.jsonl')
+    done = set()
+    if os.path.exists(results_path):
+        with open(results_path) as f:
+            for line in f:
+                try:
+                    done.add(json.loads(line)['variant'])
+                except Exception:
+                    pass
+
+    device = torch.device('cuda')
+    print(f"torch {torch.__version__} on {torch.cuda.get_device_name(0)}", flush=True)
+    data_dir = os.path.join(BENCH, 'preprocessed_csi_data')
+    dataset = PreprocessedCSIKeypointsDataset(data_dir=data_dir, keypoint_scale=1000.0,
+                                              enable_temporal_clean=True)
+
+    for v in VARIANTS:
+        if v['name'] in done:
+            print(f"[{v['name']}] already in results.jsonl — skipping", flush=True)
+            continue
+        print(f"\n===== variant: {v['name']} =====", flush=True)
+        try:
+            result = train_variant(v, dataset, device)
+        except Exception as e:  # record and move on to next variant
+            import traceback
+            traceback.print_exc()
+            result = {'variant': v['name'], 'error': repr(e),
+                      'finished_utc': time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}
+        with open(results_path, 'a') as f:
+            f.write(json.dumps(result) + '\n')
+            f.flush()
+    print('\nSWEEP COMPLETE', flush=True)
+
+
+if __name__ == '__main__':
+    main()
@@ -0,0 +1,772 @@
+{
+  "torch": {
+    "env": {
+      "torch": "2.12.0+cpu",
+      "platform": "Windows-11-10.0.26200-SP0",
+      "processor": "Intel64 Family 6 Model 197 Stepping 2, GenuineIntel",
+      "num_threads": 16,
+      "checkpoint": "results\\retrained_best_pose_model.pth",
+      "params": 2225042
+    },
+    "variants": {
+      "fp32": {
+        "file": "retrained_fp32_resaved.pth",
+        "size_bytes": 9068948,
+        "size_mb": 9.068948,
+        "latency_batch1": {
+          "batch_size": 1,
+          "runs": 100,
+          "median_ms_per_batch": 24.903650000851485,
+          "median_ms_per_window": 24.903650000851485,
+          "windows_per_second": 40.15475642991324
+        },
+        "latency_batch64": {
+          "batch_size": 64,
+          "runs": 30,
+          "median_ms_per_batch": 184.02919999789447,
+          "median_ms_per_window": 2.875456249967101,
+          "windows_per_second": 347.77089723115813
+        },
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9668200004577636,
+          "pck@50": 0.9915333324432373,
+          "mpjpe": 0.00936222033649683,
+          "wall_seconds": 37.85407733917236
+        }
+      },
+      "fp16": {
+        "file": "retrained_fp16.pth",
+        "size_bytes": 4580332,
+        "size_mb": 4.580332,
+        "latency_batch1": {
+          "batch_size": 1,
+          "runs": 100,
+          "median_ms_per_batch": 23.936699999467237,
+          "median_ms_per_window": 23.936699999467237,
+          "windows_per_second": 41.776853117691964
+        },
+        "latency_batch64": {
+          "batch_size": 64,
+          "runs": 30,
+          "median_ms_per_batch": 102.32584999903338,
+          "median_ms_per_window": 1.5988414062348966,
+          "windows_per_second": 625.4529036465817
+        },
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.966773332977295,
+          "pck@50": 0.9915066654205322,
+          "mpjpe": 0.009460017587244511,
+          "wall_seconds": 21.632277250289917
+        }
+      },
+      "int8_dynamic": {
+        "file": "retrained_int8_dynamic.pth",
+        "size_bytes": 9068948,
+        "size_mb": 9.068948,
+        "latency_batch1": {
+          "batch_size": 1,
+          "runs": 100,
+          "median_ms_per_batch": 18.105350000041653,
+          "median_ms_per_window": 18.105350000041653,
+          "windows_per_second": 55.23229321707117
+        },
+        "latency_batch64": {
+          "batch_size": 64,
+          "runs": 30,
+          "median_ms_per_batch": 168.77549999844632,
+          "median_ms_per_window": 2.6371171874757238,
+          "windows_per_second": 379.20195763359703
+        },
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9668200004577636,
+          "pck@50": 0.9915333324432373,
+          "mpjpe": 0.00936222033649683,
+          "wall_seconds": 45.35376596450806
+        }
+      }
+    },
+    "int8_dynamic_quant_report": {
+      "eligible_module_counts": {
+        "nn.Linear": 0,
+        "nn.Conv1d": 21,
+        "nn.Conv2d": 22
+      },
+      "modules_actually_quantized": [],
+      "n_modules_quantized": 0,
+      "params_total": 2225042,
+      "params_quantized": 0,
+      "params_quantized_fraction": 0.0
+    },
+    "accuracy_subset": {
+      "description": "seed-42 file-level 70/15/15 test split, corrupted windows (files 487-499) excluded, seed-42 random subset",
+      "subset_size": 10000,
+      "clean_test_total": 10000
+    }
+  },
+  "onnx": {
+    "env": {
+      "torch": "2.12.0+cpu",
+      "onnxruntime": "1.26.0",
+      "platform": "Windows-11-10.0.26200-SP0"
+    },
+    "export": {
+      "mode": "dynamic-batch",
+      "exporter": "torchscript",
+      "file": "retrained_fp32_dynamic.onnx",
+      "size_mb": 8.971781
+    },
+    "parity": {
+      "fixture": "results/parity_fixture.npz (batch 2, seed 42)",
+      "max_abs_diff_vs_stored_fixture": 2.384185791015625e-07,
+      "max_abs_diff_vs_torch_now": 2.384185791015625e-07,
+      "pass_lt_1e-4": true
+    },
+    "latency": {
+      "batch1": {
+        "batch_size": 1,
+        "runs": 100,
+        "median_ms_per_batch": 2.5410999987798277,
+        "median_ms_per_window": 2.5410999987798277,
+        "windows_per_second": 393.5303610563043
+      },
+      "batch64": {
+        "batch_size": 64,
+        "runs": 30,
+        "median_ms_per_batch": 181.95204999938142,
+        "median_ms_per_window": 2.8430007812403346,
+        "windows_per_second": 351.7410218803118
+      }
+    },
+    "ort_int8_dynamic_supplementary": {
+      "file": "retrained_int8_ort_dynamic.onnx",
+      "size_mb": 2.438794,
+      "runs": true,
+      "max_abs_diff_vs_fp32_fixture": 0.00827130675315857
+    }
+  },
+  "onnx_accuracy": {
+    "onnx_fp32": {
+      "samples": 10000,
+      "pck@20": 0.9668200004577636,
+      "pck@50": 0.9915333324432373,
+      "mpjpe": 0.00936222568154335,
+      "wall_seconds": 22.34790802001953
+    },
+    "onnx_int8_ort_dynamic": {
+      "samples": 10000,
+      "pck@20": 0.965240001964569,
+      "pck@50": 0.9915466655731201,
+      "mpjpe": 0.01108054072111845,
+      "wall_seconds": 55.742953062057495
+    }
+  },
+  "latency_controlled_rerun": {
+    "note": "3 interleaved repetitions per variant, median ms/window; quiet box",
+    "fp32": {
+      "batch1_ms_per_window_median": 10.969150001983508,
+      "batch1_reps": [
+        10.969150001983508,
+        12.646450000829645,
+        10.49820000116597
+      ],
+      "batch64_ms_per_window_median": 2.2734187500077496,
+      "batch64_reps": [
+        2.377234374989712,
+        2.124126562478068,
+        2.2734187500077496
+      ]
+    },
+    "fp16": {
+      "batch1_ms_per_window_median": 24.313550000442774,
+      "batch1_reps": [
+        25.1078499986761,
+        21.856999999727122,
+        24.313550000442774
+      ],
+      "batch64_ms_per_window_median": 2.414695312495496,
+      "batch64_reps": [
+        2.5705156249955508,
+        1.7137437499741281,
+        2.414695312495496
+      ]
+    },
+    "int8_dynamic": {
+      "batch1_ms_per_window_median": 15.627150000000256,
+      "batch1_reps": [
+        17.67525000104797,
+        14.627999998992891,
+        15.627150000000256
+      ],
+      "batch64_ms_per_window_median": 2.0546906250160646,
+      "batch64_reps": [
+        2.0546906250160646,
+        2.03407343752815,
+        2.9325796875241394
+      ]
+    },
+    "onnx_fp32": {
+      "batch1_ms_per_window_median": 3.186650001225644,
+      "batch1_reps": [
+        2.7332500012562377,
+        3.1995500012271805,
+        3.186650001225644
+      ],
+      "batch64_ms_per_window_median": 1.9893374999924163,
+      "batch64_reps": [
+        1.5590843750032946,
+        1.9893374999924163,
+        2.2144343749914697
+      ]
+    },
+    "onnx_int8_ort_dynamic": {
+      "batch1_ms_per_window_median": 6.50984999811044,
+      "batch1_reps": [
+        6.50984999811044,
+        6.455249998907675,
+        6.789299999581999
+      ],
+      "batch64_ms_per_window_median": 5.770093750015803,
+      "batch64_reps": [
+        5.770093750015803,
+        3.912374999970325,
+        7.8067296875019565
+      ]
+    }
+  },
+  "onnx_static_ptq": {
+    "env": {
+      "onnxruntime": "1.26.0",
+      "torch": "2.12.0+cpu",
+      "platform": "Windows-11-10.0.26200-SP0",
+      "source_model": "retrained_fp32_dynamic.onnx",
+      "preprocessed_model": {
+        "file": "retrained_fp32_preproc.onnx",
+        "size_mb": 8.981529
+      }
+    },
+    "variants": {
+      "minmax_all": {
+        "file": "retrained_int8_static_minmax_all.onnx",
+        "size_bytes": 2604286,
+        "size_mb": 2.604286,
+        "calibration": {
+          "method": "minmax",
+          "windows": 1000,
+          "percentile": null,
+          "seconds": 5.052440166473389
+        },
+        "scope": "all",
+        "per_channel": true,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {
+          "Add": 9,
+          "AveragePool": 1,
+          "BatchNormalization": 12,
+          "Concat": 10,
+          "Conv": 43,
+          "DequantizeLinear": 283,
+          "Einsum": 4,
+          "Gather": 16,
+          "Mul": 39,
+          "QuantizeLinear": 181,
+          "Reshape": 14,
+          "Shape": 2,
+          "Sigmoid": 37,
+          "Slice": 8,
+          "Softmax": 2,
+          "Squeeze": 1,
+          "Transpose": 7,
+          "Unsqueeze": 11
+        },
+        "max_abs_diff_vs_fp32_fixture": 0.015945255756378174,
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9545266661643982,
+          "pck@50": 0.9913666645050049,
+          "mpjpe": 0.014860070134699345,
+          "wall_seconds": 43.455235958099365
+        }
+      },
+      "minmax_conv": {
+        "file": "retrained_int8_static_minmax_conv.onnx",
+        "size_bytes": 2527421,
+        "size_mb": 2.527421,
+        "calibration": {
+          "method": "minmax",
+          "windows": 1000,
+          "percentile": null,
+          "seconds": 4.380746126174927
+        },
+        "scope": "conv",
+        "per_channel": true,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {
+          "Add": 9,
+          "AveragePool": 1,
+          "BatchNormalization": 12,
+          "Concat": 10,
+          "Conv": 43,
+          "DequantizeLinear": 156,
+          "Einsum": 4,
+          "Gather": 16,
+          "Mul": 39,
+          "QuantizeLinear": 78,
+          "Reshape": 14,
+          "Shape": 2,
+          "Sigmoid": 37,
+          "Slice": 8,
+          "Softmax": 2,
+          "Squeeze": 1,
+          "Transpose": 7,
+          "Unsqueeze": 11
+        },
+        "max_abs_diff_vs_fp32_fixture": 0.010693132877349854,
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9663399996757507,
+          "pck@50": 0.9918666641235352,
+          "mpjpe": 0.01084446222037077,
+          "wall_seconds": 35.937947034835815
+        }
+      },
+      "entropy_all": {
+        "file": "retrained_int8_static_entropy_all.onnx",
+        "size_bytes": 2604268,
+        "size_mb": 2.604268,
+        "calibration": {
+          "method": "entropy",
+          "windows": 512,
+          "percentile": null,
+          "seconds": 23.835066318511963
+        },
+        "scope": "all",
+        "per_channel": true,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {
+          "Add": 9,
+          "AveragePool": 1,
+          "BatchNormalization": 12,
+          "Concat": 10,
+          "Conv": 43,
+          "DequantizeLinear": 283,
+          "Einsum": 4,
+          "Gather": 16,
+          "Mul": 39,
+          "QuantizeLinear": 181,
+          "Reshape": 14,
+          "Shape": 2,
+          "Sigmoid": 37,
+          "Slice": 8,
+          "Softmax": 2,
+          "Squeeze": 1,
+          "Transpose": 7,
+          "Unsqueeze": 11
+        },
+        "max_abs_diff_vs_fp32_fixture": 0.015280365943908691,
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9530466662406921,
+          "pck@50": 0.9912600006103516,
+          "mpjpe": 0.015098519864678382,
+          "wall_seconds": 51.514281034469604
+        }
+      },
+      "entropy_conv": {
+        "file": "retrained_int8_static_entropy_conv.onnx",
+        "size_bytes": 2527403,
+        "size_mb": 2.527403,
+        "calibration": {
+          "method": "entropy",
+          "windows": 512,
+          "percentile": null,
+          "seconds": 9.634419918060303
+        },
+        "scope": "conv",
+        "per_channel": true,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {
+          "Add": 9,
+          "AveragePool": 1,
+          "BatchNormalization": 12,
+          "Concat": 10,
+          "Conv": 43,
+          "DequantizeLinear": 156,
+          "Einsum": 4,
+          "Gather": 16,
+          "Mul": 39,
+          "QuantizeLinear": 78,
+          "Reshape": 14,
+          "Shape": 2,
+          "Sigmoid": 37,
+          "Slice": 8,
+          "Softmax": 2,
+          "Squeeze": 1,
+          "Transpose": 7,
+          "Unsqueeze": 11
+        },
+        "max_abs_diff_vs_fp32_fixture": 0.012535125017166138,
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9659599989891052,
+          "pck@50": 0.9918666648864746,
+          "mpjpe": 0.010778637571632861,
+          "wall_seconds": 41.01180171966553
+        }
+      },
+      "percentile_all": {
+        "file": "retrained_int8_static_percentile_all.onnx",
+        "size_bytes": 2604052,
+        "size_mb": 2.604052,
+        "calibration": {
+          "method": "percentile",
+          "windows": 512,
+          "percentile": 99.99,
+          "seconds": 20.221954584121704
+        },
+        "scope": "all",
+        "per_channel": true,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {
+          "Add": 9,
+          "AveragePool": 1,
+          "BatchNormalization": 12,
+          "Concat": 10,
+          "Conv": 43,
+          "DequantizeLinear": 283,
+          "Einsum": 4,
+          "Gather": 16,
+          "Mul": 39,
+          "QuantizeLinear": 181,
+          "Reshape": 14,
+          "Shape": 2,
+          "Sigmoid": 37,
+          "Slice": 8,
+          "Softmax": 2,
+          "Squeeze": 1,
+          "Transpose": 7,
+          "Unsqueeze": 11
+        },
+        "max_abs_diff_vs_fp32_fixture": 0.017689883708953857,
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9639333323478698,
+          "pck@50": 0.9916799991607667,
+          "mpjpe": 0.012176512064039708,
+          "wall_seconds": 49.365190744400024
+        }
+      },
+      "percentile_conv": {
+        "file": "retrained_int8_static_percentile_conv.onnx",
+        "size_bytes": 2527241,
+        "size_mb": 2.527241,
+        "calibration": {
+          "method": "percentile",
+          "windows": 512,
+          "percentile": 99.99,
+          "seconds": 8.223475694656372
+        },
+        "scope": "conv",
+        "per_channel": true,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {
+          "Add": 9,
+          "AveragePool": 1,
+          "BatchNormalization": 12,
+          "Concat": 10,
+          "Conv": 43,
+          "DequantizeLinear": 156,
+          "Einsum": 4,
+          "Gather": 16,
+          "Mul": 39,
+          "QuantizeLinear": 78,
+          "Reshape": 14,
+          "Shape": 2,
+          "Sigmoid": 37,
+          "Slice": 8,
+          "Softmax": 2,
+          "Squeeze": 1,
+          "Transpose": 7,
+          "Unsqueeze": 11
+        },
+        "max_abs_diff_vs_fp32_fixture": 0.014725983142852783,
+        "accuracy": {
+          "samples": 10000,
+          "pck@20": 0.9660599988937378,
+          "pck@50": 0.9916066654205322,
+          "mpjpe": 0.010310938355326652,
+          "wall_seconds": 36.89548587799072
+        }
+      }
+    },
+    "latency": {
+      "note": "3 interleaved repetitions per variant, median ms/window; onnx_fp32 / onnx_int8_ort_dynamic are same-session references",
+      "onnx_fp32": {
+        "batch1_reps": [
+          4.5327999996516155,
+          2.535649999117595,
+          2.167549997466267
+        ],
+        "batch64_reps": [
+          1.9354515624740998,
+          2.4948054687854437,
+          1.9334703125082342
+        ],
+        "batch1_ms_per_window_median": 2.535649999117595,
+        "batch64_ms_per_window_median": 1.9354515624740998
+      },
+      "onnx_int8_ort_dynamic": {
+        "batch1_reps": [
+          5.698599999959697,
+          5.721350000385428,
+          4.805099997611251
+        ],
+        "batch64_reps": [
+          4.096601562508795,
+          4.857628124995017,
+          4.583800000006022
+        ],
+        "batch1_ms_per_window_median": 5.698599999959697,
+        "batch64_ms_per_window_median": 4.583800000006022
+      },
+      "entropy_all": {
+        "batch1_reps": [
+          6.444149999879301,
+          5.038299999796436,
+          5.713200000172947
+        ],
+        "batch64_reps": [
+          4.149468750028973,
+          3.437125000004926,
+          4.410960937491382
+        ],
+        "batch1_ms_per_window_median": 5.713200000172947,
+        "batch64_ms_per_window_median": 4.149468750028973
+      },
+      "entropy_conv": {
+        "batch1_reps": [
+          4.874750000453787,
+          5.169099998965976,
+          5.236699998931726
+        ],
+        "batch64_reps": [
+          3.010160156236452,
+          3.1175546875203963,
+          3.516850781238645
+        ],
+        "batch1_ms_per_window_median": 5.169099998965976,
+        "batch64_ms_per_window_median": 3.1175546875203963
+      },
+      "percentile_all": {
+        "batch1_reps": [
+          5.184749999898486,
+          5.2898499998264015,
+          5.916899999647285
+        ],
+        "batch64_reps": [
+          4.305105468745296,
+          4.460741406262514,
+          4.184502343747454
+        ],
+        "batch1_ms_per_window_median": 5.2898499998264015,
+        "batch64_ms_per_window_median": 4.305105468745296
+      },
+      "percentile_conv": {
+        "batch1_reps": [
+          4.916449999655015,
+          7.150899999032845,
+          5.284949998895172
+        ],
+        "batch64_reps": [
+          3.855813281262499,
+          4.688969531230214,
+          5.220103124997877
+        ],
+        "batch1_ms_per_window_median": 5.284949998895172,
+        "batch64_ms_per_window_median": 4.688969531230214
+      },
+      "minmax_all": {
+        "batch1_reps": [
+          6.463300000177696,
+          7.149449998905766,
+          5.3209000016067876
+        ],
+        "batch64_reps": [
+          3.9251343750095202,
+          4.033442187505898,
+          3.428199218745931
+        ],
+        "batch1_ms_per_window_median": 6.463300000177696,
+        "batch64_ms_per_window_median": 3.9251343750095202
+      },
+      "minmax_conv": {
+        "batch1_reps": [
+          5.9961499991914025,
+          5.236549999608542,
+          4.854399998293957
+        ],
+        "batch64_reps": [
+          4.368359375007458,
+          3.249617187492504,
+          3.0238906249735464
+        ],
+        "batch1_ms_per_window_median": 5.236549999608542,
+        "batch64_ms_per_window_median": 3.249617187492504
+      }
+    },
+    "accuracy_subset": {
+      "description": "seed-42 file-level 70/15/15 test split, corrupted windows excluded, seed-42 random subset (same as quantize_bench/eval_ort_accuracy)",
+      "subset_size": 10000
+    }
+  },
+  "tiny_variant": {
+    "env": {
+      "torch": "2.12.0+cpu",
+      "onnxruntime": "1.26.0",
+      "platform": "Windows-11-10.0.26200-SP0",
+      "num_threads": 16,
+      "checkpoint": "results\\tiny_best.pth",
+      "checkpoint_size_bytes": 340555,
+      "params": 56290,
+      "variant_config": {
+        "tcn": [
+          68,
+          56,
+          44,
+          32
+        ],
+        "conv": [
+          2,
+          4,
+          8,
+          16
+        ],
+        "attn_groups": 2,
+        "groups_mode": "depthwise",
+        "input_pw_groups": 4
+      }
+    },
+    "export": {
+      "mode": "dynamic-batch",
+      "exporter": "torchscript",
+      "opset": 17,
+      "file": "tiny_fp32_dynamic.onnx",
+      "size_bytes": 295279,
+      "size_mb": 0.295279,
+      "verified_batches": [
+        1,
+        2,
+        64
+      ],
+      "note": "AdaptiveAvgPool2d((15,1)) replaced at export by an exact mean(-1) + constant averaging matmul (final_width 16 is not a multiple of 15, which the TorchScript exporter rejects); exactness proven by the parity check vs the original torch model"
+    },
+    "parity": {
+      "fixture": "results/parity_fixture.npz input (batch 2, seed 42); reference output recomputed with the tiny torch model",
+      "max_abs_diff_vs_torch": 1.4901161193847656e-07,
+      "pass_lt_1e-4": true
+    },
+    "int8_static_percentile_conv": {
+      "file": "tiny_int8_static_percentile_conv.onnx",
+      "size_bytes": 248278,
+      "size_mb": 0.248278,
+      "calibration": {
+        "method": "percentile",
+        "percentile": 99.99,
+        "windows": 512,
+        "scope": "conv-only TRAIN-split corruption-free",
+        "seconds": 1.5347836017608643
+      },
+      "per_channel": true,
+      "activation_type": "QInt8",
+      "weight_type": "QInt8",
+      "max_abs_diff_vs_fp32_fixture": 0.018491357564926147
+    },
+    "latency": {
+      "note": "3 interleaved repetitions per variant, median ms/window; full-model sessions are same-session references",
+      "tiny_onnx_fp32": {
+        "batch1_reps": [
+          0.6312500008789357,
+          0.6834500018157996,
+          0.6595999984710943
+        ],
+        "batch64_reps": [
+          0.37747578119251557,
+          0.24196640623586063,
+          0.2314671875183194
+        ],
+        "batch1_ms_per_window_median": 0.6595999984710943,
+        "batch64_ms_per_window_median": 0.24196640623586063
+      },
+      "tiny_onnx_int8_static_percentile_conv": {
+        "batch1_reps": [
+          0.7988500001374632,
+          0.9382499993080273,
+          0.8451000030618161
+        ],
+        "batch64_reps": [
+          0.9211476562995813,
+          1.3045390625165965,
+          1.026230468767153
+        ],
+        "batch1_ms_per_window_median": 0.8451000030618161,
+        "batch64_ms_per_window_median": 1.026230468767153
+      },
+      "full_onnx_fp32_reference": {
+        "batch1_reps": [
+          2.267249998112675,
+          2.80170000041835,
+          2.132149998942623
+        ],
+        "batch64_reps": [
+          1.3050578124875756,
+          1.4244992187855132,
+          1.8014164062947202
+        ],
+        "batch1_ms_per_window_median": 2.267249998112675,
+        "batch64_ms_per_window_median": 1.4244992187855132
+      },
+      "full_onnx_int8_static_percentile_conv_reference": {
+        "batch1_reps": [
+          5.529599999135826,
+          4.768399998283712,
+          6.215800000063609
+        ],
+        "batch64_reps": [
+          3.815724218725336,
+          3.1025562500417436,
+          4.333318749957016
+        ],
+        "batch1_ms_per_window_median": 5.529599999135826,
+        "batch64_ms_per_window_median": 3.815724218725336
+      }
+    },
+    "accuracy_subset": {
+      "description": "seed-42 file-level 70/15/15 test split, corrupted windows excluded, seed-42 random subset (same as quantize_bench/eval_ort_accuracy/static_ptq_bench)",
+      "subset_size": 10000
+    },
+    "accuracy": {
+      "tiny_onnx_fp32": {
+        "samples": 10000,
+        "pck@20": 0.941106667804718,
+        "pck@50": 0.99369333152771,
+        "mpjpe": 0.012527281279861927,
+        "wall_seconds": 10.927234888076782
+      },
+      "tiny_onnx_int8_static_percentile_conv": {
+        "samples": 10000,
+        "pck@20": 0.9268133331298828,
+        "pck@50": 0.9932933319091797,
+        "mpjpe": 0.014906252065300942,
+        "wall_seconds": 12.320892333984375
+      }
+    }
+  }
+}
@@ -0,0 +1,3 @@
+{"variant": "half", "params": 843834, "tcn_channels": [270, 220, 170, 120], "conv_channels": [4, 8, 16, 32], "attn_groups": 4, "groups_mode": "gcd20", "input_pw_groups": 1, "tcn_groups_per_block": [[20, 10], [10, 20], [20, 10], [10, 20]], "conv_strides": [2, 2, 2, 1], "final_width": 15, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 28, "best_epoch": 23, "best_val_mpjpe": 0.008576328293592842, "best_val_pck20": 0.9690593021534107, "train_seconds": 1346.4, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T03:09:47Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/half_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.009419974447676428, "pck@10": 0.8740543655289544, "pck@20": 0.9610469643628156, "pck@30": 0.9813556064146537, "pck@40": 0.9896086878246731, "pck@50": 0.9934827546013726}, "test_clean": {"samples": 52560, "mpjpe": 0.008980081718602137, "pck@10": 0.8840944136840205, "pck@20": 0.9662253179869514, "pck@30": 0.9847971080282144, "pck@40": 0.9917795997050618, "pck@50": 0.9946956242600532}}
+{"variant": "quarter", "params": 338600, "tcn_channels": [135, 110, 85, 60], "conv_channels": [2, 4, 8, 16], "attn_groups": 2, "groups_mode": "gcd20", "input_pw_groups": 1, "tcn_groups_per_block": [[20, 5], [5, 10], [10, 5], [5, 20]], "conv_strides": [2, 2, 1, 1], "final_width": 15, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 50, "best_epoch": 50, "best_val_mpjpe": 0.008780752391864856, "best_val_pck20": 0.9672531302240159, "train_seconds": 1754.4, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T03:39:06Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/quarter_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.009705399298005634, "pck@10": 0.8646123917014511, "pck@20": 0.9553815319449813, "pck@30": 0.979827209190086, "pck@40": 0.9887037501511751, "pck@50": 0.9931309027671814}, "test_clean": {"samples": 52560, "mpjpe": 0.009279253277105465, "pck@10": 0.8742288637923323, "pck@20": 0.9605315079427745, "pck@30": 0.9833016723076865, "pck@40": 0.9908206971631566, "pck@50": 0.9942719799017071}}
+{"variant": "tiny", "params": 56290, "tcn_channels": [68, 56, 44, 32], "conv_channels": [2, 4, 8, 16], "attn_groups": 2, "groups_mode": "depthwise", "input_pw_groups": 4, "tcn_groups_per_block": [[540, 68], [68, 56], [56, 44], [44, 32]], "conv_strides": [2, 1, 1, 1], "final_width": 16, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 50, "best_epoch": 47, "best_val_mpjpe": 0.012602971208592256, "best_val_pck20": 0.9397210340146666, "train_seconds": 1540.1, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T04:04:50Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/tiny_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.012859782406853305, "pck@10": 0.7640358444319831, "pck@20": 0.9364815320968628, "pck@30": 0.9731568422317505, "pck@40": 0.9866444962642811, "pck@50": 0.992488939108672}, "test_clean": {"samples": 52560, "mpjpe": 0.012502924276904246, "pck@10": 0.770895526488985, "pck@20": 0.9411073559313967, "pck@30": 0.9764840687790962, "pck@40": 0.9886695077067278, "pck@50": 0.9936238432039409}}
@@ -0,0 +1,21 @@
+{
+  "checkpoint": "/home/ruvultra/wiflow-std-bench/upstream/test/best_pose_model.pth",
+  "test_full": {
+    "samples": 54000,
+    "mpjpe": 0.009834060806367133,
+    "pck@10": 0.8686346120127925,
+    "pck@20": 0.9608815324571398,
+    "pck@30": 0.9789111610695168,
+    "pck@40": 0.9857975759682832,
+    "pck@50": 0.9898827553325229
+  },
+  "test_clean": {
+    "samples": 52560,
+    "mpjpe": 0.009432755044379373,
+    "pck@10": 0.876996495807189,
+    "pck@20": 0.9661454100405608,
+    "pck@30": 0.9823453060205306,
+    "pck@40": 0.987909734176537,
+    "pck@50": 0.9911238361167036
+  }
+}
@@ -0,0 +1,32 @@
+{
+  "published": {
+    "pck@20": 0.9725,
+    "pck@30": 0.9863,
+    "pck@40": 0.9916,
+    "pck@50": 0.9948,
+    "mpjpe": 0.007
+  },
+  "params_millions": 2.225042,
+  "data_dir": "C:\\Users\\ruv\\.cache\\kagglehub\\datasets\\kaka2434\\wiflow-dataset\\versions\\1\\preprocessed_csi_data",
+  "device": "cpu",
+  "test_full": {
+    "samples": 54000,
+    "mpjpe": NaN,
+    "pck@10": 5.6790124349020145e-05,
+    "pck@20": 0.0007876543271596785,
+    "pck@30": 0.007780246982971827,
+    "pck@40": 0.05529259262923841,
+    "pck@50": 0.1542370371548114,
+    "wall_seconds": 118.03756999969482
+  },
+  "test_drop_last": {
+    "samples": 53952,
+    "mpjpe": NaN,
+    "pck@10": 5.6840649370682976e-05,
+    "pck@20": 0.0007883550872372227,
+    "pck@30": 0.007787168910892621,
+    "pck@40": 0.055318307667895535,
+    "pck@50": 0.15425316342412276,
+    "wall_seconds": 120.87458372116089
+  }
+}
@@ -0,0 +1,333 @@
+"""ADR-152 edge optimization follow-up: ONNX Runtime STATIC post-training
+quantization (calibration-based QDQ) of the retrained WiFlow-STD model, to
+improve on the dynamic-int8 result (2.44 MB, PCK@20 96.52%, 6.5 ms/win b1).
+
+Static PTQ pre-computes activation ranges from calibration data, so inference
+uses QLinearConv/QDQ kernels instead of dynamic ConvInteger -- typically both
+faster and (with good calibration) closer to fp32 accuracy.
+
+Method:
+  - Calibration set: corruption-free windows drawn ONLY from the seed-42
+    file-level TRAINING split (same split as eval_repro.py; corrupted windows
+    excluded via results/nan_windows_mask.npy | big_windows_mask.npy), chosen
+    with np.random.default_rng(42). Never test windows.
+  - quantize_static, QuantFormat.QDQ, per-channel int8 weights, int8
+    activations; calibration methods MinMax / Entropy / Percentile(99.99);
+    scopes "all" (ORT default op set) vs "conv" (op_types_to_quantize=
+    ["Conv"] -- leaves the attention path, which exports as Einsum/Softmax
+    and elementwise ops, in fp32).
+  - Model is pre-processed first (quant_pre_process: symbolic shape
+    inference + ORT graph optimization, folds BatchNormalization into Conv).
+  - Accuracy: identical protocol to eval_ort_accuracy.py -- the 10,000-window
+    seed-42 subset of the corruption-free test split (PCK@20/50, MPJPE).
+  - Latency: median ms/window at batch 1 (100 runs) and batch 64 (30 runs),
+    3 interleaved repetitions across all variants (fp32 and dynamic-int8
+    sessions included as same-session reference points).
+
+Usage:
+  PYTHONUTF8=1 .venv/Scripts/python.exe static_ptq_bench.py \
+      [--data-dir <preprocessed_csi_data>] [--subset 10000]
+      [--calib-minmax 1000] [--calib-hist 512] [--skip-accuracy]
+
+Writes/merges into results/edge_optimization.json under key "onnx_static_ptq".
+"""
+
+import argparse
+import collections
+import json
+import os
+import platform
+import statistics
+import sys
+import time
+
+import numpy as np
+import torch
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+
+from _bench_common import RESULTS  # noqa: E402
+# quantize_bench sets up upstream imports + the np.load mmap patch
+# (both via _bench_common.import_upstream)
+from quantize_bench import build_test_subset  # noqa: E402
+import quantize_bench as qb  # noqa: E402
+from eval_ort_accuracy import evaluate_ort  # noqa: E402
+
+FP32_ONNX = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
+DYN_INT8_ONNX = os.path.join(RESULTS, "retrained_int8_ort_dynamic.onnx")
+PREPROC_ONNX = os.path.join(RESULTS, "retrained_fp32_preproc.onnx")
+
+
+# ---------------------------------------------------------------------------
+# calibration data: corruption-free TRAINING-split windows only
+# ---------------------------------------------------------------------------
+
+def build_calibration_windows(data_dir, n_windows):
+    """Seed-42 file-level 70/15/15 TRAIN split (exactly as eval_repro.py),
+    minus corrupted windows, then a seed-42 random draw of n_windows."""
+    dataset = qb.PreprocessedCSIKeypointsDataset(
+        data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
+    train_loader, _va, _te = qb.create_preprocessed_train_val_test_loaders(
+        dataset=dataset, batch_size=64, num_workers=0, random_seed=42)
+    train_indices = np.asarray(train_loader.dataset.indices)
+
+    corrupted = (np.load(os.path.join(RESULTS, "nan_windows_mask.npy"))
+                 | np.load(os.path.join(RESULTS, "big_windows_mask.npy")))
+    clean = train_indices[~corrupted[train_indices]]
+    print(f"train split: {len(train_indices)} windows, "
+          f"{len(train_indices) - len(clean)} corrupted excluded, "
+          f"{len(clean)} clean")
+
+    rng = np.random.default_rng(42)
+    sel = np.sort(rng.choice(clean, size=n_windows, replace=False))
+    xs = np.stack([dataset[int(i)][0].numpy() for i in sel]).astype(np.float32)
+    print(f"calibration tensor: {xs.shape} from {n_windows} clean TRAIN windows")
+    return xs
+
+
+def make_reader(windows, batch_size=64):
+    from onnxruntime.quantization import CalibrationDataReader
+
+    class WindowReader(CalibrationDataReader):
+        def __init__(self):
+            self._batches = [windows[i:i + batch_size]
+                             for i in range(0, len(windows), batch_size)]
+            self._it = iter(self._batches)
+
+        def get_next(self):
+            b = next(self._it, None)
+            return None if b is None else {"input": b}
+
+        def rewind(self):
+            self._it = iter(self._batches)
+
+        def __len__(self):
+            return len(self._batches)
+
+    return WindowReader()
+
+
+# ---------------------------------------------------------------------------
+# quantization variants
+# ---------------------------------------------------------------------------
+
+def preprocess_model():
+    from onnxruntime.quantization.shape_inference import quant_pre_process
+    quant_pre_process(FP32_ONNX, PREPROC_ONNX)
+    return PREPROC_ONNX
+
+
+def quantize_variant(src, dst, method, scope, calib_windows):
+    from onnxruntime.quantization import (CalibrationMethod, QuantFormat,
+                                          QuantType, quantize_static)
+    methods = {
+        "minmax": CalibrationMethod.MinMax,
+        "entropy": CalibrationMethod.Entropy,
+        "percentile": CalibrationMethod.Percentile,
+    }
+    # NB: do NOT pass CalibMaxIntermediateOutputs -- in ORT 1.26 the MinMax
+    # calibrater clears its buffer every N batches and then raises
+    # "No data is collected" if the batch count is divisible by N.
+    extra = {}
+    if method == "percentile":
+        extra["CalibPercentile"] = 99.99
+    op_types = ["Conv"] if scope == "conv" else None
+
+    t0 = time.time()
+    quantize_static(
+        src, dst, make_reader(calib_windows),
+        quant_format=QuantFormat.QDQ,
+        op_types_to_quantize=op_types,
+        per_channel=True,
+        activation_type=QuantType.QInt8,
+        weight_type=QuantType.QInt8,
+        calibrate_method=methods[method],
+        extra_options=extra,
+    )
+    secs = time.time() - t0
+
+    import onnx
+    ops = collections.Counter(n.op_type for n in onnx.load(dst).graph.node)
+    return {
+        "file": os.path.basename(dst),
+        "size_bytes": os.path.getsize(dst),
+        "size_mb": os.path.getsize(dst) / 1e6,
+        "calibration": {"method": method,
+                        "windows": int(len(calib_windows)),
+                        "percentile": extra.get("CalibPercentile"),
+                        "seconds": secs},
+        "scope": scope,
+        "per_channel": True,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+        "node_counts": {k: v for k, v in sorted(ops.items())},
+    }
+
+
+# ---------------------------------------------------------------------------
+# latency (3 interleaved reps, like the latency_controlled_rerun)
+# ---------------------------------------------------------------------------
+
+def ort_session(path):
+    import onnxruntime as ort
+    return ort.InferenceSession(path, providers=["CPUExecutionProvider"])
+
+
+def bench_ort(sess, batch, n_runs):
+    rng = np.random.default_rng(123)
+    x = rng.random((batch, 540, 20), dtype=np.float32)
+    inp = sess.get_inputs()[0].name
+    for _ in range(max(5, n_runs // 10)):
+        sess.run(None, {inp: x})
+    times = []
+    for _ in range(n_runs):
+        t0 = time.perf_counter()
+        sess.run(None, {inp: x})
+        times.append(time.perf_counter() - t0)
+    return statistics.median(times) * 1e3 / batch  # ms/window
+
+
+def interleaved_latency(sessions, reps=3, runs_b1=100, runs_b64=30):
+    lat = {name: {"batch1_reps": [], "batch64_reps": []} for name in sessions}
+    for rep in range(reps):
+        for name, sess in sessions.items():
+            lat[name]["batch1_reps"].append(bench_ort(sess, 1, runs_b1))
+            lat[name]["batch64_reps"].append(bench_ort(sess, 64, runs_b64))
+            print(f"  rep {rep + 1}/{reps} {name}: "
+                  f"b1={lat[name]['batch1_reps'][-1]:.2f} "
+                  f"b64={lat[name]['batch64_reps'][-1]:.3f} ms/win", flush=True)
+    for name in lat:
+        lat[name]["batch1_ms_per_window_median"] = statistics.median(
+            lat[name]["batch1_reps"])
+        lat[name]["batch64_ms_per_window_median"] = statistics.median(
+            lat[name]["batch64_reps"])
+    return lat
+
+
+# ---------------------------------------------------------------------------
+
+def main():
+    import onnxruntime
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data-dir", default=os.path.join(
+        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
+        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
+    parser.add_argument("--subset", type=int, default=10000)
+    parser.add_argument("--calib-minmax", type=int, default=1000)
+    parser.add_argument("--calib-hist", type=int, default=512,
+                        help="calibration windows for Entropy/Percentile "
+                             "(histogram calibraters hold all intermediate "
+                             "activations in RAM)")
+    parser.add_argument("--skip-accuracy", action="store_true")
+    parser.add_argument("--methods", default="minmax,entropy,percentile",
+                        help="comma list of calibration methods to (re)run; "
+                             "results merge into existing onnx_static_ptq")
+    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
+    args = parser.parse_args()
+
+    results = {
+        "env": {
+            "onnxruntime": onnxruntime.__version__,
+            "torch": torch.__version__,
+            "platform": platform.platform(),
+            "source_model": os.path.basename(FP32_ONNX),
+        },
+        "variants": {},
+    }
+
+    # ---- calibration data (TRAIN split only) -------------------------------
+    calib_mm = build_calibration_windows(args.data_dir, args.calib_minmax)
+    calib_hist = calib_mm[:args.calib_hist]
+
+    # ---- preprocess + quantize ---------------------------------------------
+    print("\n=== quant_pre_process (shape inference + graph optimization) ===")
+    src = preprocess_model()
+    results["env"]["preprocessed_model"] = {
+        "file": os.path.basename(src),
+        "size_mb": os.path.getsize(src) / 1e6,
+    }
+
+    matrix = [(m, s) for m in args.methods.split(",")
+              for s in ("all", "conv")]
+    for method, scope in matrix:
+        name = f"{method}_{scope}"
+        dst = os.path.join(RESULTS, f"retrained_int8_static_{name}.onnx")
+        calib = calib_mm if method == "minmax" else calib_hist
+        print(f"\n=== quantize_static: {name} "
+              f"({len(calib)} calib windows) ===", flush=True)
+        try:
+            results["variants"][name] = quantize_variant(
+                src, dst, method, scope, calib)
+            print(f"  {results['variants'][name]['size_mb']:.3f} MB")
+        except Exception as e:  # noqa: BLE001
+            results["variants"][name] = {"error": f"{type(e).__name__}: {e}"}
+            print(f"  FAILED: {e}")
+
+    # ---- fixture parity (sanity, batch 2) ----------------------------------
+    fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
+    fx, fy = fixture["input"], fixture["output"]
+    sessions = {}
+    for name, info in results["variants"].items():
+        if "error" in info:
+            continue
+        path = os.path.join(RESULTS, info["file"])
+        try:
+            sess = ort_session(path)
+            yq = sess.run(None, {sess.get_inputs()[0].name: fx})[0]
+            info["max_abs_diff_vs_fp32_fixture"] = float(np.abs(yq - fy).max())
+            sessions[name] = sess
+        except Exception as e:  # noqa: BLE001
+            info["run_error"] = f"{type(e).__name__}: {e}"
+    print("\nfixture max-abs-diff vs fp32:",
+          {n: round(results["variants"][n].get("max_abs_diff_vs_fp32_fixture",
+                                               float("nan")), 5)
+           for n in results["variants"]})
+
+    # ---- latency: 3 interleaved reps incl. fp32 + dynamic-int8 reference ----
+    print("\n=== latency (3 interleaved reps) ===")
+    lat_sessions = {"onnx_fp32": ort_session(FP32_ONNX),
+                    "onnx_int8_ort_dynamic": ort_session(DYN_INT8_ONNX)}
+    lat_sessions.update(sessions)
+    results["latency"] = {
+        "note": "3 interleaved repetitions per variant, median ms/window; "
+                "onnx_fp32 / onnx_int8_ort_dynamic are same-session references",
+        **interleaved_latency(lat_sessions),
+    }
+
+    # ---- accuracy on the standard 10k corruption-free test subset ----------
+    if not args.skip_accuracy:
+        loader, n_clean = build_test_subset(args.data_dir, args.subset)
+        results["accuracy_subset"] = {
+            "description": "seed-42 file-level 70/15/15 test split, corrupted "
+                           "windows excluded, seed-42 random subset (same as "
+                           "quantize_bench/eval_ort_accuracy)",
+            "subset_size": min(args.subset, n_clean) if args.subset else n_clean,
+        }
+        for name, sess in sessions.items():
+            print(f"\n=== accuracy: {name} ===")
+            results["variants"][name]["accuracy"] = evaluate_ort(
+                sess, loader, name)
+            print(json.dumps(results["variants"][name]["accuracy"], indent=2))
+
+    # ---- merge into edge_optimization.json ----------------------------------
+    merged = {}
+    if os.path.exists(args.out):
+        with open(args.out) as f:
+            merged = json.load(f)
+    prev = merged.get("onnx_static_ptq")
+    if prev:  # nested merge so partial --methods reruns don't clobber
+        prev["env"] = results["env"]
+        prev["variants"].update(results["variants"])
+        prev.setdefault("latency", {}).update(results["latency"])
+        if "accuracy_subset" in results:
+            prev["accuracy_subset"] = results["accuracy_subset"]
+    else:
+        merged["onnx_static_ptq"] = results
+    with open(args.out, "w") as f:
+        json.dump(merged, f, indent=2)
+    print(f"\nwrote {args.out}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,313 @@
+"""ADR-152 efficiency-sweep follow-up: edge pipeline for the TINY compact
+WiFlow-STD variant (56,290 params, results/tiny_best.pth, trained overnight
+2026-06-10/11 -- see RESULTS.md "Efficiency sweep").
+
+Headline question: what does the smallest deployable WiFlow-class model look
+like (KB + ms + PCK)? Reuses the onnx_bench.py / static_ptq_bench.py
+machinery on the tiny checkpoint:
+
+  1. Load tiny_best.pth with remote/sweep/model_compact.py
+     (depthwise TCN groups, input_pw_groups=4, conv [2,4,8,16], attn groups 2).
+  2. Export ONNX: dynamic batch, opset 17, TorchScript exporter (dynamo=False)
+     -- same recipe that worked for the full model; verified at batch 1/2/64.
+     One forced deviation: tiny's stride schedule [2,1,1,1] leaves final_width
+     16, and the TorchScript exporter cannot export AdaptiveAvgPool2d((15,1))
+     when 15 is not a factor of the input height (the full model never hit
+     this -- its width was exactly 15). The adaptive pool over a fixed-size
+     feature map is a fixed linear map, so the export wrapper replaces it with
+     an exact matmul equivalent (PyTorch adaptive-pool bin semantics:
+     bin i averages rows floor(i*H/K)..ceil((i+1)*H/K)); the W axis (20->1,
+     a factor) becomes mean(-1). Exactness is proven by the parity check
+     below, which compares against the ORIGINAL torch model with the real
+     AdaptiveAvgPool2d.
+  3. Torch-vs-ORT parity on the stored fixture input
+     (results/parity_fixture.npz, batch 2, seed 42 -- same 540x20 input layout;
+     reference output recomputed with the tiny torch model). PASS < 1e-4.
+  4. Static QDQ conv-only int8 (quant_pre_process + quantize_static,
+     per-channel QInt8 weights+activations, Percentile(99.99) calibration on
+     512 corruption-free TRAIN-split windows -- the winning recipe and
+     calibration count from static_ptq_bench.py. 512, not "about 500":
+     ORT 1.26's histogram collector np.asarray()'s the per-batch maxima, so
+     the calibration count must be a multiple of the batch size 64 or the
+     ragged last batch crashes it).
+  5. Disk size + CPU latency b1/b64 (3 interleaved reps, median ms/window)
+     for tiny fp32 + tiny int8, with the full-model ONNX fp32 + static-int8
+     sessions interleaved as same-session references.
+  6. Accuracy (PCK@20/50 + MPJPE) on the identical 10k-window seed-42
+     corruption-free test subset for tiny fp32 + tiny int8.
+
+Usage:
+  PYTHONUTF8=1 .venv/Scripts/python.exe tiny_edge_bench.py \
+      [--data-dir <preprocessed_csi_data>] [--subset 10000] [--calib 512]
+  (--calib must be a multiple of 64; see step 4 above)
+
+Writes/merges into results/edge_optimization.json under key "tiny_variant".
+"""
+
+import argparse
+import json
+import os
+import platform
+import sys
+import time
+
+import numpy as np
+import torch
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+RESULTS = os.path.join(HERE, "results")
+sys.path.insert(0, HERE)
+sys.path.insert(0, os.path.join(HERE, "remote", "sweep"))
+
+# quantize_bench sets up upstream imports + the np.load mmap patch
+from quantize_bench import build_test_subset  # noqa: E402
+from eval_ort_accuracy import evaluate_ort  # noqa: E402
+from static_ptq_bench import (  # noqa: E402
+    build_calibration_windows,
+    interleaved_latency,
+    make_reader,
+    ort_session,
+)
+from model_compact import CompactWiFlowPoseModel, describe  # noqa: E402
+
+TINY_CKPT = os.path.join(RESULTS, "tiny_best.pth")
+TINY_FP32_ONNX = os.path.join(RESULTS, "tiny_fp32_dynamic.onnx")
+TINY_PREPROC_ONNX = os.path.join(RESULTS, "tiny_fp32_preproc.onnx")
+TINY_INT8_ONNX = os.path.join(RESULTS, "tiny_int8_static_percentile_conv.onnx")
+FULL_FP32_ONNX = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
+FULL_INT8_ONNX = os.path.join(RESULTS, "retrained_int8_static_percentile_conv.onnx")
+
+# Exact tiny config from remote/sweep/run_sweep.py VARIANTS (measured 56,290
+# params, clean-test PCK@20 94.11% -- results/efficiency_sweep.jsonl).
+TINY = dict(tcn=[68, 56, 44, 32], conv=[2, 4, 8, 16], attn_groups=2,
+            groups_mode="depthwise", input_pw_groups=4)
+
+
+def load_tiny_model():
+    model = CompactWiFlowPoseModel(
+        tcn_channels=TINY["tcn"], conv_channels=TINY["conv"],
+        attn_groups=TINY["attn_groups"], groups_mode=TINY["groups_mode"],
+        input_pw_groups=TINY["input_pw_groups"], dropout=0.5)
+    state = torch.load(TINY_CKPT, map_location="cpu", weights_only=True)
+    model.load_state_dict(state, strict=True)
+    model.eval()
+    return model
+
+
+def adaptive_pool_matrix(h_in, h_out):
+    """Exact AdaptiveAvgPool1d as a (h_out, h_in) averaging matrix, using
+    PyTorch's bin rule: bin i covers rows floor(i*h_in/h_out) ..
+    ceil((i+1)*h_in/h_out)."""
+    w = torch.zeros(h_out, h_in)
+    for i in range(h_out):
+        s = (i * h_in) // h_out
+        e = -((-(i + 1) * h_in) // h_out)  # ceil division
+        w[i, s:e] = 1.0 / (e - s)
+    return w
+
+
+class ExportWrapper(torch.nn.Module):
+    """CompactWiFlowPoseModel forward with the AdaptiveAvgPool2d((K,1))
+    replaced by an exact fixed linear map (mean over the factor W axis, then
+    a constant averaging matmul over the non-factor H axis) so the
+    TorchScript ONNX exporter accepts it. Bit-equivalent up to float
+    round-off; proven by the parity check against the original model."""
+
+    def __init__(self, m, num_keypoints=15):
+        super().__init__()
+        self.m = m
+        self.register_buffer(
+            "pool_w_t", adaptive_pool_matrix(m.final_width, num_keypoints).t())
+
+    def forward(self, x):
+        m = self.m
+        x = m.tcn(x)
+        x = x.transpose(1, 2).unsqueeze(1)
+        x = m.up(x)
+        for block in m.residual_blocks:
+            x = block(x)
+        x = x.permute(0, 1, 3, 2)
+        x = m.attention(x)
+        x = m.decoder(x)                  # [B, 2, H=final_width, T=20]
+        x = x.mean(-1)                    # W-axis pool (20 -> 1, a factor)
+        x = x.matmul(self.pool_w_t)       # exact adaptive H pool: [B, 2, K]
+        return x.transpose(1, 2)          # [B, K, 2]
+
+
+def export_onnx(model):
+    """Dynamic-batch TorchScript export (the recipe that worked for the full
+    model in onnx_bench.py), verified at batch 1/2/64. Uses ExportWrapper
+    (see docstring) because final_width 16 is not a multiple of 15."""
+    wrapper = ExportWrapper(model).eval()
+    x = torch.rand(2, 540, 20)
+    with torch.no_grad():
+        torch.onnx.export(
+            wrapper, (x,), TINY_FP32_ONNX, opset_version=17,
+            input_names=["input"], output_names=["output"], dynamo=False,
+            dynamic_axes={"input": {0: "batch"}, "output": {0: "batch"}})
+    sess = ort_session(TINY_FP32_ONNX)
+    inp = sess.get_inputs()[0].name
+    for b in (1, 2, 64):
+        y = sess.run(None, {inp: np.zeros((b, 540, 20), dtype=np.float32)})[0]
+        assert y.shape == (b, 15, 2), y.shape
+    return {
+        "mode": "dynamic-batch", "exporter": "torchscript", "opset": 17,
+        "file": os.path.basename(TINY_FP32_ONNX),
+        "size_bytes": os.path.getsize(TINY_FP32_ONNX),
+        "size_mb": os.path.getsize(TINY_FP32_ONNX) / 1e6,
+        "verified_batches": [1, 2, 64],
+        "note": "AdaptiveAvgPool2d((15,1)) replaced at export by an exact "
+                "mean(-1) + constant averaging matmul (final_width 16 is not "
+                "a multiple of 15, which the TorchScript exporter rejects); "
+                "exactness proven by the parity check vs the original torch "
+                "model",
+    }
+
+
+def quantize_tiny(calib_windows):
+    """quant_pre_process + static QDQ conv-only Percentile(99.99) int8 --
+    the winning recipe from static_ptq_bench.py."""
+    from onnxruntime.quantization import (CalibrationMethod, QuantFormat,
+                                          QuantType, quantize_static)
+    from onnxruntime.quantization.shape_inference import quant_pre_process
+
+    quant_pre_process(TINY_FP32_ONNX, TINY_PREPROC_ONNX)
+    t0 = time.time()
+    quantize_static(
+        TINY_PREPROC_ONNX, TINY_INT8_ONNX, make_reader(calib_windows),
+        quant_format=QuantFormat.QDQ,
+        op_types_to_quantize=["Conv"],
+        per_channel=True,
+        activation_type=QuantType.QInt8,
+        weight_type=QuantType.QInt8,
+        calibrate_method=CalibrationMethod.Percentile,
+        extra_options={"CalibPercentile": 99.99},
+    )
+    return {
+        "file": os.path.basename(TINY_INT8_ONNX),
+        "size_bytes": os.path.getsize(TINY_INT8_ONNX),
+        "size_mb": os.path.getsize(TINY_INT8_ONNX) / 1e6,
+        "calibration": {"method": "percentile", "percentile": 99.99,
+                        "windows": int(len(calib_windows)),
+                        "scope": "conv-only TRAIN-split corruption-free",
+                        "seconds": time.time() - t0},
+        "per_channel": True,
+        "activation_type": "QInt8",
+        "weight_type": "QInt8",
+    }
+
+
+def main():
+    import onnxruntime
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data-dir", default=os.path.join(
+        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
+        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
+    parser.add_argument("--subset", type=int, default=10000)
+    parser.add_argument("--calib", type=int, default=512,
+                        help="calibration windows; must be a multiple of the "
+                             "64-window calibration batch (ORT histogram "
+                             "collector rejects ragged batches)")
+    parser.add_argument("--skip-accuracy", action="store_true")
+    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
+    args = parser.parse_args()
+
+    if args.calib % 64 != 0:
+        parser.error(
+            f"--calib must be a multiple of 64 (got {args.calib}): ORT 1.26's "
+            f"histogram calibration collector np.asarray()'s the per-batch "
+            f"maxima and crashes on a ragged final batch (calibration batch "
+            f"size is 64)")
+
+    model = load_tiny_model()
+    info = describe(model)
+    print(f"tiny model: {info['params']:,} params, tcn_groups={info['tcn_groups_per_block']}, "
+          f"strides={info['conv_strides']}, final_width={info['final_width']}")
+    assert info["params"] == 56290, info["params"]
+
+    results = {
+        "env": {
+            "torch": torch.__version__,
+            "onnxruntime": onnxruntime.__version__,
+            "platform": platform.platform(),
+            "num_threads": torch.get_num_threads(),
+            "checkpoint": os.path.relpath(TINY_CKPT, HERE),
+            "checkpoint_size_bytes": os.path.getsize(TINY_CKPT),
+            "params": info["params"],
+            "variant_config": TINY,
+        },
+    }
+
+    # ---- export + parity ----------------------------------------------------
+    print("\n=== ONNX export (dynamic batch, opset 17, torchscript) ===")
+    results["export"] = export_onnx(model)
+    print(f"  {results['export']['size_mb']:.3f} MB, batches {results['export']['verified_batches']} OK")
+
+    fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
+    fx = fixture["input"]  # (2, 540, 20), seed 42 -- same input layout as full model
+    sess_fp32 = ort_session(TINY_FP32_ONNX)
+    y_ort = sess_fp32.run(None, {sess_fp32.get_inputs()[0].name: fx})[0]
+    with torch.no_grad():
+        y_torch = model(torch.from_numpy(fx)).numpy()
+    results["parity"] = {
+        "fixture": "results/parity_fixture.npz input (batch 2, seed 42); "
+                   "reference output recomputed with the tiny torch model",
+        "max_abs_diff_vs_torch": float(np.abs(y_ort - y_torch).max()),
+        "pass_lt_1e-4": bool(np.abs(y_ort - y_torch).max() < 1e-4),
+    }
+    print("parity:", json.dumps(results["parity"], indent=2))
+    assert results["parity"]["pass_lt_1e-4"], "torch-vs-ORT parity FAILED"
+
+    # ---- static PTQ int8 ------------------------------------------------------
+    print(f"\n=== static QDQ int8 (Percentile conv-only, {args.calib} calib windows) ===")
+    calib = build_calibration_windows(args.data_dir, args.calib)
+    results["int8_static_percentile_conv"] = quantize_tiny(calib)
+    print(f"  {results['int8_static_percentile_conv']['size_mb']:.3f} MB")
+    sess_int8 = ort_session(TINY_INT8_ONNX)
+    yq = sess_int8.run(None, {sess_int8.get_inputs()[0].name: fx})[0]
+    results["int8_static_percentile_conv"]["max_abs_diff_vs_fp32_fixture"] = float(
+        np.abs(yq - y_torch).max())
+
+    # ---- latency (3 interleaved reps, full-model sessions as references) -----
+    print("\n=== latency (3 interleaved reps) ===")
+    lat_sessions = {
+        "tiny_onnx_fp32": sess_fp32,
+        "tiny_onnx_int8_static_percentile_conv": sess_int8,
+        "full_onnx_fp32_reference": ort_session(FULL_FP32_ONNX),
+        "full_onnx_int8_static_percentile_conv_reference": ort_session(FULL_INT8_ONNX),
+    }
+    results["latency"] = {
+        "note": "3 interleaved repetitions per variant, median ms/window; "
+                "full-model sessions are same-session references",
+        **interleaved_latency(lat_sessions),
+    }
+
+    # ---- accuracy on the standard 10k corruption-free test subset ------------
+    if not args.skip_accuracy:
+        loader, n_clean = build_test_subset(args.data_dir, args.subset)
+        results["accuracy_subset"] = {
+            "description": "seed-42 file-level 70/15/15 test split, corrupted "
+                           "windows excluded, seed-42 random subset (same as "
+                           "quantize_bench/eval_ort_accuracy/static_ptq_bench)",
+            "subset_size": min(args.subset, n_clean) if args.subset else n_clean,
+        }
+        results["accuracy"] = {}
+        for name, sess in (("tiny_onnx_fp32", sess_fp32),
+                           ("tiny_onnx_int8_static_percentile_conv", sess_int8)):
+            print(f"\n=== accuracy: {name} ===")
+            results["accuracy"][name] = evaluate_ort(sess, loader, name)
+            print(json.dumps(results["accuracy"][name], indent=2))
+
+    # ---- merge into edge_optimization.json -----------------------------------
+    merged = {}
+    if os.path.exists(args.out):
+        with open(args.out) as f:
+            merged = json.load(f)
+    merged["tiny_variant"] = results
+    with open(args.out, "w") as f:
+        json.dump(merged, f, indent=2)
+    print(f"\nwrote {args.out}")
+
+
+if __name__ == "__main__":
+    main()
@@ -14,6 +14,13 @@ COPY v2/crates/ ./crates/
 # Copy vendored RuVector crates
 COPY vendor/ruvector/ /build/vendor/ruvector/

+# Copy vendored RuField submodule — the `wifi-densepose-rufield` bridge crate
+# (ADR-262) path-deps `../../../vendor/rufield/crates/*`, which from the Docker
+# build layout (v2/ collapsed into /build) resolves to /vendor/rufield. Copy the
+# whole tree so the rufield workspace Cargo.toml (workspace-dep inheritance) and
+# the four bridged crates (rufield-core/-provenance/-privacy/-fusion) all resolve.
+COPY vendor/rufield/ /vendor/rufield/
+
 # Build release binaries:
 #   - sensing-server with `mqtt` feature so the HA-DISCO MQTT publisher
 #     (ADR-115) is wired in (auto-discovery topics flow to Home Assistant)
@@ -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:
@@ -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

@@ -57,7 +57,7 @@ This witness separates what was **empirically observed on real silicon today** f

 | # | Claim | Why it's not verified |
 |---|---|---|
-| **B1** | "Wi-Fi 6 HE-LTF: 242 subcarriers per HE20 frame" | The only AP in range (`ruv.net`) is 11n-only. Every captured frame is 128 bytes = 64 subcarriers (HT-LTF, `ppdu_type=0`). No HE-SU/HE-MU/HE-TB observed. Even if an 11ax AP were available, **whether ESP-IDF v5.4's CSI callback exposes HE-LTF subcarriers via `wifi_csi_info_t.buf` is an open question** — the public API was designed for HT-LTF, and the driver may quietly downconvert. **Validate by capturing CSI against an 11ax AP and comparing `info->len` between HT and HE frames.** |
+| **B1** | "Wi-Fi 6 HE-LTF: 242 subcarriers per HE20 frame" | The only AP in range (`ruv.net`) is 11n-only. Every captured frame is 128 bytes = 64 subcarriers (HT-LTF, `ppdu_type=0`). No HE-SU/HE-MU/HE-TB observed. Even if an 11ax AP were available, **whether ESP-IDF v5.4's CSI callback exposes HE-LTF subcarriers via `wifi_csi_info_t.buf` is an open question** — the public API was designed for HT-LTF, and the driver may quietly downconvert. **Validate by capturing CSI against an 11ax AP and comparing `info->len` between HT and HE frames.**<br><br>**RESOLVED WITH MEASUREMENT (2026-06-11, external — issue #1005, production deployment by @stuinfla):** the open question is answered in both directions. **IDF v5.4's driver blob downconverts** (148 B / 64-subcarrier HT frames, PPDU byte 0x00, on a confirmed-HE link); **IDF v5.5.2 delivers true HE-LTF** — 532 B frames = 256 bins (242 active HE20 tones), PPDU byte 0x01 (HE-SU), ~90% of frames, same board/AP/link. Setup: XIAO ESP32-C6 → hostapd on Intel AX210, 2.4 GHz ch 6, `ieee80211ax=1`. No firmware change required (`acquire_csi_su=1` was already set); the gate was purely the IDF driver version. Three C6 nodes ran this mode simultaneously with ADR-110 ESP-NOW sync. Requires the issue-#1005 version-guard fix in `c6_sync_espnow.c` to build on v5.5.x. |<br><br>**REPLICATED IN-HOUSE (2026-06-11):** same source + fix, fresh IDF v5.5.2 toolchain, original COM12 board (`20:6e:f1:17:00:84`), AP `ruv.net` (11ax 2.4 GHz): **84% of 1,525 captured frames at 532 B / PPDU 0x01 (HE-SU)**, HT minority 148 B / 0x00. Evidence grade: MEASURED (two independent rigs). |
 | **B2** | "TWT-bounded deterministic CSI cadence (10 ms wake)" | No 11ax AP in range. The TWT setup *call* was exercised live and the graceful fallback path is now correct (A9), but the agreement itself was never accepted. **Validate by associating with an 11ax AP that has TWT Responder=1, then capturing the timestamped CSI cadence vs the wall clock.** |
 | **B3** | "±100 µs cross-node alignment over 802.15.4" | 3 boards initialized their radios with correct EUIs (A4/A5), but **none stepped down from candidate-leader to follower** during repeated 35-second multi-board captures. <br><br>**Coex hypothesis REJECTED**: rebuilt + reflashed all 3 boards with `CONFIG_C6_TIMESYNC_CHANNEL=26` (2480 MHz, non-overlapping with WiFi ch 5 at 2432 MHz). Result identical: 3× candidate, 0× "stepping down". So 2.4 GHz radio coex was NOT the cause. <br><br>**Current leading hypothesis**: OpenThread (CONFIG_OPENTHREAD_ENABLED=y) owns the 802.15.4 radio when its stack is initialized — our weak-symbol overrides of `esp_ieee802154_receive_done` / `_transmit_done` may never be called because OpenThread registers strong handlers. Validation in progress: rebuilding with `CONFIG_OPENTHREAD_ENABLED=n` (raw 802.15.4 only, our beacon protocol is private — no need for the Thread stack). If leader election fires under raw-15.4-only, hypothesis confirmed. <br><br>If raw-only also fails, next move is to dump the actual PHY frame bytes via the IEEE 802.15.4 sniffer mode on a 4th board and diagnose at the frame level. |
 | **B4** | "~5 µA hibernation for battery seed nodes" | No INA / Joulescope current measurement available on this bench. The shipped code uses `esp_deep_sleep_enable_gpio_wakeup` (ext1 path, ESP-IDF default ~10 µA), not a true LP-core polling program. The 5 µA number is the C6 datasheet figure for ULP-level hibernation, not a measured value. **Validate by hooking an INA219/INA226 between the dev board's 3V3 rail and the regulator output, then averaging current over a 60-second cycle with the LP-core armed.** |
@@ -1081,6 +1081,23 @@ The `wifi-densepose-vitals` crate (ESP32 CSI-grade vital signs) has not yet been
 - SONA-based environment adaptation
 - VitalSignStore with tiered temporal compression

+## Implementation Notes
+
+### 2026-06 — ESP32 edge vitals: person-count over-count + presence flicker (#998, #996)
+
+Two robustness bugs were fixed in the on-device edge path (`firmware/esp32-csi-node/main/edge_processing.c`, the ADR-039 packet `0xC5110002`). These touch the *boolean/count emission logic*, not the underlying CSI signal-processing math, and do **not** constitute a validated-accuracy claim — true occupancy-count and presence accuracy vs labelled ground truth remain hardware/data-gated (COM9 ESP32-S3 + labelled capture).
+
+- **#998 `n_persons` over-count (reported 4 for one person).** `update_multi_person_vitals()` divided the top-K subcarriers into `top_k_count/2` groups and marked *every* group `active`, so one body's multipath always read the full `EDGE_MAX_PERSONS`. Added an energy gate (`EDGE_PERSON_MIN_ENERGY_RATIO`), spatial dedup (`EDGE_PERSON_MIN_SC_SEP`), and a persistence debounce (`EDGE_PERSON_PERSIST_FRAMES`) via two pure functions `count_distinct_persons()` / `person_count_debounce()`.
+- **#996 presence flag flicker at ~50 cm.** Single-threshold compare on a noisy `presence_score` chattered at the boundary. Replaced with a Schmitt trigger + clear-debounce (`presence_flag_update()`, constants `EDGE_PRESENCE_HYST_RATIO` / `EDGE_PRESENCE_CLEAR_FRAMES`); `presence_score` is unchanged and still emitted for consumer-side thresholding.
+
+Both are pinned by host-buildable C99 tests in `firmware/esp32-csi-node/test/test_vitals_count_presence.c` (`make run_vitals`). The exact thresholds are documented constants pending on-device calibration against ground truth.
+
+### 2026-06 — Rust `wifi-densepose-vitals`: IIR filter NaN/inf self-heal (ADR-158 §A1)
+
+A correctness/safety review of the Rust extraction crate found a real bug parallel to the firmware robustness class above. The 2nd-order resonator `bandpass_filter` in both `breathing.rs` and `heartrate.rs` latches each output `y[n]` into its filter state (`y1`/`y2`). A single non-finite amplitude residual from a corrupt CSI frame produced a NaN `output` that was written into the state; the existing `extract()` `is_finite()` guard dropped that one sample from the history buffer **but never sanitized the poisoned filter state**, so every later output stayed NaN, was rejected too, and the sliding-window history never refilled — breathing **and** heart-rate extraction went silently dead (returning `None` forever) until `reset()`. On the alert path this is a safety-relevant denial of service (one bad frame stops vitals monitoring with no error surfaced).
+
+Fix: when `bandpass_filter` computes a non-finite `output`, it resets the IIR state to default and returns `0.0`, so the resonator self-heals on the next clean frame (the `0.0` is still dropped by the caller's finite-check, so no spurious sample enters history). Same shape as the calibration NaN bug (ADR-154 §3) — the prior hardening guarded the *history boundary* but not the *filter-state boundary*. Pinned by `breathing::tests::nan_frame_does_not_permanently_poison_filter`, `breathing::tests::inf_mid_stream_does_not_freeze_history`, and `heartrate::tests::nan_frame_does_not_permanently_poison_filter` (all FAIL pre-fix, verified by reverting). The review also de-magicked the HR physiological plausibility band into named `HR_PLAUSIBLE_MIN_BPM`/`HR_PLAUSIBLE_MAX_BPM` consts (value-identical 40/180 BPM) and added a fabricated-vital negative (`pure_noise_is_never_reported_valid` — broadband noise never yields a clinically `Valid` HR; the extractor honestly returns low-confidence `Unreliable`). Clean dimensions confirmed with evidence: flat/silent input → `None`; pure noise → low-confidence `Unreliable`, never `Valid`; harmonic-rich breathing with no cardiac component → low-confidence, not a confident false HR; out-of-band BPM rejected by the plausibility clamp.
+
 ## References

 - Ramsauer et al. (2020). "Hopfield Networks is All You Need." ICLR 2021. (ModernHopfield formulation)
@@ -83,7 +83,7 @@ This ADR covers Phase 1 (TV box as aggregator) and Phase 2 (custom WiFi firmware
   |---------|--------|-------------|--------------|--------|
   | Broadcom BCM43455 | brcmfmac | **Proven** (Nexmon CSI) | Yes | Low — patches exist |
   | Realtek RTL8822CS | rtw88 | **Moderate** — driver is open-source, CSI hooks need adding | Yes (patched) | Medium |
-   | MediaTek MT7661 | mt76 | **Unknown** — MediaTek has released CSI tools for some chips | Yes | Medium-High |
+   | MediaTek MT7661 | mt76 | **Unverified** — no supported public CSI capture API was found in upstream `mt76` or public MediaTek SDK material | Yes | Research only |

 2. **CSI extraction architecture** (Linux kernel driver modification):

@@ -5,7 +5,7 @@
 | Status | Proposed |
 | Date | 2026-03-06 |
 | Deciders | ruv |
-| Depends on | ADR-012 (ESP32 CSI Mesh), ADR-039 (Edge Intelligence), ADR-040 (WASM Programmable Sensing), ADR-044 (Provisioning Enhancements), ADR-050 (Security Hardening), ADR-051 (Server Decomposition) |
+| Depends on | ADR-012 (ESP32 CSI Mesh), ADR-039 (Edge Intelligence), ADR-040 (WASM Programmable Sensing), ADR-044 (Provisioning Enhancements), ADR-166 (Security Hardening, renumbered from ADR-050), ADR-051 (Server Decomposition) |
 | Issue | [#177](https://github.com/ruvnet/RuView/issues/177) |

 ## Context
@@ -211,7 +211,7 @@ pub struct FlashProgress {
 // commands/ota.rs

 /// Push firmware to a node via HTTP OTA (port 8032).
-/// Includes PSK authentication per ADR-050.
+/// Includes PSK authentication per ADR-166.
 #[tauri::command]
 async fn ota_update(
    node_ip: String,
@@ -801,7 +801,7 @@ Total estimated effort: ~11 weeks for a single developer.
 - ADR-039: ESP32 Edge Intelligence
 - ADR-040: WASM Programmable Sensing
 - ADR-044: Provisioning Tool Enhancements
- ADR-050: Quality Engineering — Security Hardening
+- ADR-166: Quality Engineering — Security Hardening (renumbered from ADR-050)
 - ADR-051: Sensing Server Decomposition
 - `firmware/esp32-csi-node/` — ESP32 firmware source
 - `firmware/esp32-csi-node/provision.py` — Current provisioning script
@@ -1,6 +1,6 @@
 # ADR-080: QE Analysis Remediation Plan

- **Status:** Proposed
+- **Status:** Proposed — P0 security findings #1–#3 **RESOLVED** on the shipped Rust sensing-server boundary (2026-06-13; closes ADR-164 G11)
 - **Date:** 2026-04-06
 - **Source:** [QE Analysis Gist (2026-04-05)](https://gist.github.com/proffesor-for-testing/a6b84d7a4e26b7bbef0cf12f932925b7)
 - **Full Reports:** [proffesor-for-testing/RuView `qe-reports` branch](https://github.com/proffesor-for-testing/RuView/tree/qe-reports/docs/qe-reports)
@@ -13,25 +13,38 @@ An 8-agent QE swarm analyzed ~305K lines across Rust, Python, C firmware, and Ty

 Address the 15 prioritized issues from the QE analysis in three waves: P0 (immediate), P1 (this sprint), P2 (this quarter).

+## Security P0 closure note (2026-06-13) — Rust sensing-server boundary
+
+The three P0 security findings below were logged against the **Python v1** API
+(`archive/v1/src/…`). ADR-164 G11 re-scoped them to the *shipped* boundary:
+`wifi-densepose-sensing-server` (Rust). They were verified against the current
+Rust crate and closed on branch `fix/adr-080-sensing-server-security`. Each fix
+(or already-fixed finding) is pinned by a test that fails on the old behavior.
+**The Python v1 paths remain as-is** — v1 is archived and not the shipped
+surface; this closure governs the live Rust server only.
+
 ## P0 — Fix Immediately

-### 1. Rate Limiter Bypass (Security HIGH)
+### 1. Rate Limiter Bypass / XFF spoofing (Security HIGH) — **RESOLVED (verified absent on Rust boundary)**

- **Location:** `archive/v1/src/middleware/rate_limit.py:200-206`
+- **Original location (v1):** `archive/v1/src/middleware/rate_limit.py:200-206`
 - **Problem:** Trusts `X-Forwarded-For` without validation. Any client bypasses rate limits via header spoofing.
- **Fix:** Validate forwarded headers against trusted proxy list, or use connection IP directly.
+- **Rust verification (2026-06-13):** The Rust sensing-server has **no XFF-trusting control to bypass** — there is no IP-based rate-limiter and no IP-allowlist, and neither security middleware reads a forwarded header. `bearer_auth.rs` authenticates on the token alone (`require_bearer` inspects only the `AUTHORIZATION` header); `host_validation.rs` decides on the `Host` header only. A repo-wide grep for `x-forwarded-for|forwarded|peer_addr|client_ip|real-ip` over `wifi-densepose-sensing-server` returns nothing. The only "rate limiter" is the MQTT *sample-rate* gate (`mqtt/state.rs`), a per-entity publish throttle with no IP/header input.
+- **Resolution:** No code change needed (no vulnerable surface). Regression tests pin the immunity: `bearer_auth::tests::xff_header_never_affects_auth_decision` (spoofed XFF never flips a 401↔200 decision) and `host_validation::tests::forwarded_headers_never_bypass_host_allowlist` (spoofed `X-Forwarded-Host: localhost` never lets a foreign `Host: evil.com` past the allowlist). Residual: if an IP-based control is ever added, it must derive the peer from the socket (`ConnectInfo<SocketAddr>`) and only honor XFF from an explicit `--trusted-proxy` CIDR — captured as guidance in the test docstrings.

-### 2. Exception Details Leaked in Responses (Security HIGH)
+### 2. Exception Details Leaked in Responses (Security HIGH, CWE-209) — **RESOLVED**

- **Location:** `archive/v1/src/api/routers/pose.py:140`, `stream.py:297`, +5 endpoints
- **Problem:** Stack traces visible regardless of environment.
- **Fix:** Wrap with generic error responses in production; log details server-side only.
+- **Original location (v1):** `archive/v1/src/api/routers/pose.py:140`, `stream.py:297`, +5 endpoints
+- **Problem:** Internal error/stack-trace detail serialized into client responses.
+- **Rust finding (2026-06-13):** Six handlers in `wifi-densepose-sensing-server/src/main.rs` serialized the internal error `Display` into the JSON body: `edge_registry_endpoint` returned a panicked `spawn_blocking` `JoinError` (`"task … panicked"`) in a `500` and the raw upstream error in a `503`; `delete_model`/`delete_recording`/`start_recording` returned `std::io::Error` strings (OS detail / path); `calibration_start`/`calibration_stop` returned the `FieldModel` error chain.
+- **Fix:** New `src/error_response.rs` module — `internal_error` / `internal_error_json` / `upstream_unavailable` log the full detail **server-side only** (tagged with a correlation id) and return a generic body (`{"error":"internal_error","correlation_id":…}`) with no `panicked`, no file paths, no Debug chain. All six call-sites rewired. Pinned by `error_response::tests::internal_error_body_does_not_leak_detail` (leak-substring guard, verified to fail on the reverted old body) + 4 sibling tests.

-### 3. WebSocket JWT in URL (Security HIGH, CWE-598)
+### 3. WebSocket JWT in URL (Security HIGH, CWE-598) — **RESOLVED (verified absent on Rust boundary)**

- **Location:** `archive/v1/src/api/routers/stream.py:74`, `archive/v1/src/middleware/auth.py:243`
+- **Original location (v1):** `archive/v1/src/api/routers/stream.py:74`, `archive/v1/src/middleware/auth.py:243`
 - **Problem:** Tokens in query strings visible in logs/proxies/browser history.
- **Fix:** Use WebSocket subprotocol or first-message auth pattern.
+- **Rust verification (2026-06-13):** The Rust sensing-server never reads a token from the URL. `require_bearer` (`bearer_auth.rs`) inspects only the `Authorization` header; the WebSocket handlers (`ws_sensing_handler`/`ws_introspection_handler`/`ws_pose_handler`) take a bare `WebSocketUpgrade` with no `Query` extractor; the single `Query` in the crate (`EdgeRegistryParams`) is a non-secret `refresh` flag.
+- **Resolution:** No code change needed (no query-token path exists). Regression test `bearer_auth::tests::query_string_token_is_never_accepted` proves `?token=`/`?access_token=` in the URL never authenticates (stays `401`) while the same token in the header succeeds (`200`) — verified to fail if a query-token path is re-introduced.

 ### 4. Rust Tests Not in CI

@@ -259,14 +259,75 @@ Validation runs against:
 - **ADR-083** (Proposed) — Per-cluster Pi compute hop. Defines the
  device class that hosts the sketch bank.

+## Pass 2 — randomized rotation + multi-bit (ADR-156 §8, landed 2026-06)
+
+The "Open question" below ("does `BinaryQuantized` need a randomized
+rotation pre-pass?") is now **answered with measured numbers** via
+ADR-156 §10. Summary:
+
+- **Pass 2 (randomized rotation) is implemented** —
+  `crates/wifi-densepose-ruvector/src/rotation.rs`: a deterministic
+  `R = H·D` (Fast Hadamard Transform + seeded ±1 sign flips), `O(d log d)`
+  / `O(d)`, norm-preserving, reproducible from a stored `u64` seed. Opt-in
+  via `Sketch::from_embedding_rotated` / `SketchBank::with_rotation`;
+  Pass-1 API and wire format unchanged.
+- **Measured top-K coverage** (anisotropic planted-cluster fixture,
+  cosine ground truth, dim=128 N=2048 K=8): rotation lifts coverage
+  **36.13% → 46.39%** at the strict `candidate_k = K` bar, and Pass-2
+  reaches the **≥90% acceptance bar at candidate_k = 24 (~3× over-fetch)**.
+  Multi-bit (≤4-bit) reaches 74% at the strict bar. **Honest verdict:
+  neither rotation nor ≤4-bit multi-bit clears the strict-K 90% bar on
+  this distribution; the bar is met via the over-fetch "candidate set"
+  pattern this ADR specifies** (Decision §"the canonical pattern" — sketch
+  picks the candidate set, full precision refines). Full numbers and
+  reproduce commands in ADR-156 §10.
+- **Pre-existing `SketchBank::topk` bug fixed** — the `n > k` heap path
+  returned the k *farthest* sketches (min-heap mistaken for max-heap);
+  only the `n ≤ k` fast path had test coverage. Fixed + regression-pinned
+  (`topk_heap_path_returns_nearest`,
+  `tight_clusters_give_high_coverage_with_overfetch`). This makes every
+  prior top-K acceptance number in this ADR depend on the fixed path; the
+  ≥90% coverage criterion is only meaningful post-fix.
+
+## Pass 2b — RaBitQ unbiased distance estimator (ADR-156 §11, landed 2026-06)
+
+The **real** RaBitQ contribution (Gao & Long, SIGMOD 2024) — an
+**unbiased estimator of the inner product / distance** from the 1-bit
+code + per-vector side info, not just sign bits — is now implemented and
+**MEASURED against this ADR's ≥90% strict-K bar**:
+
+- **Implemented** — `crates/wifi-densepose-ruvector/src/estimator.rs`:
+  `EstimatorSketch` (Pass-2 sign code + 8 B/vec side info:
+  `residual_norm` + `x_dot_o = ⟨x̄, o'⟩`), `DistanceEstimator`
+  (`⟨o',q'⟩ ≈ ⟨x̄,q'⟩ / x_dot_o`, the paper's unbiased rescale), and
+  `EstimatorBank` reranking candidates by the estimate instead of raw
+  Hamming. **Zero-centroid simplification** (`c = 0`) documented;
+  paper-faithful centroid path also built (`with_centroid`). Additive —
+  Pass-1/Pass-2 and the wire format are unchanged.
+- **MEASURED strict-K coverage** (same fixture as §"Pass 2", cosine
+  ground truth): the estimator lifts the strict `candidate_k = K` bar
+  **46.39% (Pass-2 sign) → 49.71% (estimator, cosine rerank)** — a real
+  **+3.3 pp** lift, but **still ~40 pp short of the ≥90% strict bar.**
+  At over-fetch the estimator does better than sign (95.12% vs 91.60% at
+  candidate_k = 24). **Honest verdict: the unbiased estimator does NOT
+  clear the strict-K 90% bar on this distribution** — the binding
+  constraint is the 1-bit code's information ceiling, not estimator
+  variance. The ≥90% acceptance bar is still met only via the over-fetch
+  "candidate set" pattern this ADR's Decision specifies; the estimator
+  **reduces the over-fetch factor** needed but does not remove it. This
+  is a **published negative**, reported as such. Full numbers + reproduce
+  commands in ADR-156 §11.
+
 ## Open questions

 - **Does `BinaryQuantized` need a randomized rotation pre-pass for
-  RuView's embedding distributions?** Pure sign quantization assumes
-  zero-centered, isotropic embeddings. If AETHER / spectrogram
-  distributions are skewed (likely for spectrogram), add a
-  `randomized_rotation` pre-pass following the original RaBitQ paper
-  (Gao & Long, SIGMOD 2024). Decided after pass-1 benchmark.
+  RuView's embedding distributions?** **ANSWERED (ADR-156 §10):** rotation
+  is built and measured — it helps (+10pp at strict K) but is not
+  sufficient alone for strict-K 90% on the tested anisotropic
+  distribution; the over-fetch candidate-set pattern meets the bar.
+  Pure sign quantization assumes zero-centered, isotropic embeddings; the
+  rotation decorrelates anisotropic coords as the RaBitQ paper
+  (Gao & Long, SIGMOD 2024) prescribes.
 - **Sketch dimension target.** Default to the embedding's native
  dimension (128 for AETHER, 256 for spectrogram). Higher-dimensional
  sketches (Johnson-Lindenstrauss-projected to 512) trade compute for
@@ -19,7 +19,7 @@ The production CSI node firmware (`firmware/esp32-csi-node`) was built around th

 | C6 capability | What it enables for sensing | Why we can't get it on S3 |
 |---|---|---|
-| **802.11ax (Wi-Fi 6) HE-LTF CSI** | 242 subcarriers per HE20 frame (vs 52 for HT-LTF), HE-MU/HE-TB PPDU types, OFDMA-aware channel sounding | S3 radio is HT-only (n) |
+| **802.11ax (Wi-Fi 6) HE-LTF CSI** | 242 subcarriers per HE20 frame (vs 52 for HT-LTF), HE-MU/HE-TB PPDU types, OFDMA-aware channel sounding. **Hardware-confirmed 2026-06-11** (issue #1005, external production deployment): requires **ESP-IDF ≥ 5.5** — the v5.4 driver blob silently downconverts to 64-subcarrier HT even on a confirmed-HE link; v5.5.2 delivers 532 B frames = 256 bins (242 active tones), PPDU 0x01 (HE-SU). See WITNESS-LOG-110 §B1 (resolved). | S3 radio is HT-only (n) |
 | **802.15.4 (Thread / Zigbee)** | Cross-node time-sync over a separate radio — frees Wi-Fi airtime for CSI, ±100 µs alignment possible without coordination traffic on the sensing channel | S3 has no 802.15.4 |
 | **TWT (Target Wake Time)** | Sensor negotiates a deterministic wake slot with the AP; CSI cadence becomes scheduler-bounded instead of opportunistic | Requires 802.11ax — S3 can't speak it |
 | **LP-core + hibernation (~5 µA)** | Always-on motion gate runs on a separate RISC-V LP core in deep sleep; HP core stays off until a real event | S3 ULP is FSM-only, ~10 µA floor |
@@ -104,6 +104,57 @@ Ranked by build cost × user impact:
 | **P9** | HACS integration repo (`hass-wifi-densepose`) for HA-side install path | pending |
 | **P10** | Witness bundle + CSA-style spec compliance check | pending |

+## 4.1 Crypto/security review notes (§2.2 witness chain — ADR-262 P2 prerequisite)
+
+Beyond-SOTA crypto+security review of the SHA-256 + Ed25519 witness chain
+(`witness.rs` / `witness_signing.rs`) and the manifest signature surface
+(`manifest.rs`), because ADR-262 P2 proposes to **reuse this exact signing
+chain**. Top priority was the sibling `wifi-densepose-engine` bug class —
+unframed boundary-to-boundary concatenation of operator-influenceable strings
+into a signed/hashed digest.
+
+- **Engine bug class ABSENT (good result, reported with byte evidence).**
+  `canonical_bytes` is `DOMAIN_TAG ‖ prev_hash[32] ‖ seq:u64-be ‖ ts:u64-be ‖
+  kind_len:u32-be ‖ kind ‖ payload_len:u32-be ‖ payload`. The two
+  variable-length operator-influenceable fields (`kind`, `payload`) are
+  **length-prefixed**; the fixed-width fields are self-delimiting → the
+  encoding is injective (no two distinct event tuples share a preimage). The
+  Ed25519 signature signs the **identical** bytes the SHA-256 chain commits to.
+  No separate unframed concatenation exists; the manifest `binary_signature`
+  is signed at build time (Makefile) over a single fixed-length `binary_sha256`
+  hex value, not in-crate.
+
+- **CHM-WIT-01 (FIXED) — domain-separation tag added.** The engine fix
+  prescribed *domain-tag + length-prefix*; length-prefix was present, the
+  domain tag was not. Added a versioned, NUL-terminated
+  `WITNESS_DOMAIN_TAG = b"cog-ha-matter/witness-event/v1\x00"` prefix so the
+  witness message can never be replayed as a message for another Ed25519
+  context that shares key infrastructure (notably the manifest signature).
+  **Witness bytes change by design** (prior on-disk hashes/signatures
+  invalidated, as with the engine fix); verified safe because no in-repo crate
+  consumes cog-ha-matter witness bytes programmatically (doc-mentions only).
+
+- **CHM-WIT-02 (HARDENED) — `verify_signature` now uses `verify_strict`.** For
+  an audit chain the signature is the attestation, so non-canonical encodings
+  and small-order keys are rejected (RFC 8032 strict), giving the "one
+  canonical signature per event" property. Not a forgery fix — the verifying
+  key is caller-pinned, never read from the event.
+
+- **Confirmed clean (with evidence):** verify-before-trust + key-pinning
+  (`verify_signature` takes the verifying key as a parameter; `read_jsonl`
+  re-derives every hash and chain-verifies); key handling (the crate never
+  generates/stores/logs/serializes a signing key — only a documented test-only
+  fixed seed; production keys come from the Seed secure store, out of scope);
+  determinism (positional bytes, deterministic Ed25519, alphabetically-locked
+  JSONL field order, sorted TXT records — no HashMap/float nondeterminism feeds
+  any digest); fail-closed parsing (structured errors, no panics; `main.rs`
+  reads no untrusted files/paths).
+
+Tests: `cog-ha-matter --no-default-features` 64 → **68**, 0 failed (CHM-WIT-01
+pinned by 4 fails-on-old tests across `witness.rs`/`witness_signing.rs`;
+CHM-WIT-02 guarded by a key-pinning test). Python deterministic proof
+unchanged (cog-ha-matter is off the signal proof path).
+
 ## 5. References

 - ADR-101 — `cog-pose-estimation` packaging precedent (signed binaries on GCS, .cog manifest)
@@ -190,4 +190,78 @@ The entity registry is a `RwLock<HashMap<EntityId, EntityEntry>>` backed by an a

 - `v2/crates/wifi-densepose-sensing-server/src/main.rs` — Axum + Tokio architecture pattern used throughout the existing server stack
 - `docs/adr/ADR-126-ruview-native-ha-port-master.md` — HOMECORE master; §5.5 crate naming; §6 compatibility contract; §5.1 RUVIEW-POLICY
+
+---
+
+## 9. Security & concurrency review (P1 core, beyond-SOTA sweep)
+
+Foundational review of the `homecore` crate — the state store + event bus +
+service/entity registries every other HOMECORE module trusts. Same rigor as
+the ADR-129/130/132/133/161 sibling reviews. **Three real fixes (one
+concurrency, two hardening), each pinned by a fails-on-old test; the bus-lag
+and lock-discipline dimensions confirmed clean with evidence.**
+
+- **HC-RACE-01 (state-set TOCTOU — lost / reordered `state_changed`, the
+  crux). FIXED.** `StateMachine::set` did `get()` (releasing the DashMap
+  shard lock) → compute the next snapshot + the no-op / `last_changed`
+  decision → `insert()` (re-acquiring the lock) → `send()`. The
+  read-modify-write was **not atomic** w.r.t. a concurrent writer on the
+  same entity, contradicting §2.1's promise that "the writer atomically
+  replaces the map entry." A writer that read a stale `old` could
+  mis-classify a genuine transition as a no-op and **drop its
+  `state_changed` event** (a missed automation trigger) or fire an event
+  whose `new_state` duplicated the previously delivered one (a spurious
+  trigger for any automation keyed on `old_state != new_state`). **Fix:**
+  hold the shard write-lock across the entire read→decide→insert→fire
+  sequence via `entry()`/`insert_entry()`; `tx.send` is non-blocking,
+  non-async, and never re-enters the map, so firing under the shard lock
+  cannot deadlock and keeps global event order in lock-step with global
+  commit order. Pinned by `concurrent_set_fires_no_duplicate_adjacent_events`
+  (4 writers toggling one entity A/B; asserts no two consecutive fired
+  events carry an identical `new_state` — impossible under correct
+  serialisation; a probe observed ~93k such duplicate-adjacent events across
+  200 trials on the racy code, zero on the fix).
+- **HC-EID-LEN-01 (unbounded `entity_id` — memory-DoS at the REST boundary).
+  FIXED.** `homecore-api/src/rest.rs` parses untrusted path segments
+  straight through `EntityId::parse`; with no length cap, an
+  otherwise-valid id (`a.` + many MB of `[a-z0-9_]`) was accepted and a
+  `POST /api/states/<giant>` would persist it into the DashMap state store
+  (permanent growth across distinct ids). **Fix:** reject ids longer than
+  `MAX_ENTITY_ID_LEN` (255, HA-compatible) up front in `parse()`, before any
+  per-char scan, with a new `EntityIdError::TooLong`; fail-closed at the
+  boundary type protects every caller. Pinned by `entity_id_length_boundary`
+  (exactly-MAX accepted, MAX+1 and a 4 MiB id rejected — fails on old code).
+- **HC-SVC-PANIC-01 (service-handler panic not isolated). HARDENED.**
+  `ServiceRegistry::call` already ran handlers outside the registry lock (no
+  `RwLock` poisoning, no blocking of other callers — clean), but a
+  panicking handler unwound through `call()` into the caller's task. **Fix:**
+  wrap the handler future in `AssertUnwindSafe` + `catch_unwind`, converting
+  a panic to `ServiceError::HandlerPanicked`; the registry stays fully
+  usable. Pinned by `panicking_handler_is_isolated_and_registry_survives`.
+
+**Dimensions confirmed clean (with evidence):**
+
+- **Event-bus bounds / lag (same class as the homecore-api WS lag-DoS).**
+  Both `StateMachine` and `EventBus` use bounded `tokio::sync::broadcast`
+  (capacity 4,096). A slow subscriber gets a recoverable `Lagged(n)`
+  (drop-oldest + re-sync); `fire_*` is non-blocking and **never waits on
+  slow receivers**, so a lagging subscriber cannot block the publisher, grow
+  the channel without bound, or take down a fast subscriber. Evidenced by
+  `slow_subscriber_does_not_block_publisher_or_kill_the_bus` (fire 3×
+  capacity at an idle subscriber; publisher unblocked, bus stays live).
+- **Lock ordering / lock-across-await (deadlock).** No code path holds two
+  of `{state DashMap, registry RwLock, service RwLock}` simultaneously, so
+  no inconsistent-ordering deadlock can exist. Every `tokio::sync::RwLock`
+  guard in `registry.rs`/`service.rs` is used in a single synchronous
+  statement and dropped before any `.await`; `call` explicitly scopes the
+  read guard out before awaiting the handler. The only guard held across a
+  send is the DashMap shard lock in `set`, across a synchronous
+  (non-await) broadcast send — safe.
+- **Panic-on-input.** No reachable `unwrap`/`expect`/index in non-test code
+  beyond the safe `send().unwrap_or(0)` and the dead-but-harmless
+  `split_once(...).unwrap_or(...)` fallbacks on already-validated ids.
+
+`cargo test -p homecore --no-default-features`: **20 → 24 passed, 0 failed**
+(+4 pins). Workspace green; Python deterministic proof unchanged
+(`f8e76f21…46f7a`, bit-exact — `homecore` is off the signal proof path).
 - `docs/adr/ADR-028-esp32-capability-audit.md` — witness chain pattern (Ed25519 per state transition)
@@ -190,6 +190,23 @@ This is the same Wasmtime host already used for integration plugins (ADR-128)

 ---

+## 8a. Security review (beyond-SOTA sweep, post ADR-154–159)
+
+A focused security review of `homecore-automation` (the execution/eval surface — triggers → conditions → actions, with templates) was run after the ADR-154–159 sweep, applying the same rigor that the sibling engine/bfld/calibration/vitals/geo reviews used. **Two real DoS findings, each pinned by a fails-on-old test; the condition-bypass, fail-closed-parsing, and action-authorization dimensions were probed and found clean.**
+
+- **HC-SEC-01 (template-injection / unbounded-expansion DoS, HIGH) — FIXED.** A `template:` condition / `value_template` is user automation config, and was rendered with MiniJinja's defaults: **no instruction budget, no output cap**. A single condition such as `{% for i in range(5000) %}{% for j in range(5000) %}xxxx{% endfor %}{% endfor %}` rendered a **100 MB string over ~11 s on one render call** (measured) — a CPU/memory denial of service (the bfld-class "unbounded expansion"; MiniJinja's per-call `range()` 10k cap does **not** stop nested loops). **Fix:** enable MiniJinja's `fuel` feature and set a per-render budget (`set_fuel(Some(1_000_000))`) so a nested loop burns one unit per iteration — the attack now fails fast (~90 ms) with "engine ran out of fuel"; plus a 64 KiB source-length cap rejecting pathological sources before compilation. Legitimate HA templates (a few dozen instructions) are unaffected. Pinned by `nested_loop_template_is_bounded_not_unbounded_dos`, `single_huge_repeat_template_is_bounded`, `oversized_template_source_is_rejected` (all fail-on-old: unbounded render / no rejection), and `legitimate_template_still_renders_within_fuel` (no regression).
+- **HC-SEC-02 (panic-on-config DoS, MEDIUM) — FIXED.** `Action::Delay { seconds }` and `Action::WaitForTrigger { timeout_seconds }` fed the user-supplied float straight into `Duration::from_secs_f64`, which **panics** on negative, NaN, infinite, or overflowing inputs — all reachable from a crafted (or typo'd) YAML (`delay: {seconds: -1}`, `.nan`, `.inf`, `1e308`). One hostile config aborts the spawned automation run task with a panic (measured: "cannot convert float seconds to Duration: value is negative"). **Fix:** a `safe_duration_from_secs` guard that saturates instead of panicking (NaN/±inf/negative → `Duration::ZERO`, matching HA's lenient "non-positive delay = no delay"; absurdly large → clamped to ~100 years). Pinned by `delay_negative_seconds_does_not_panic`, `delay_nan_seconds_does_not_panic`, `delay_infinite_seconds_does_not_panic`, `wait_for_trigger_negative_timeout_does_not_panic`, `safe_duration_saturates_hostile_values` (incl. overflow clamp).
+
+**Dimensions confirmed clean (with evidence):**
+- **Condition bypass / fail-closed eval** — a `Condition::Template` whose render errors evaluates to `false` (`condition.rs` `Err(_) => false`), and a `Choose` branch condition that fails to deserialize is treated as **non-matching** (the branch is skipped), not silently passing (`action.rs` `ChoiceBranch::matches` `Err(_) => return false`). Both fail **closed** (do-not-run), confirmed by the existing `choose_*` tests and template-false-blocks-action behavioral test. No true-by-default-on-parse-error path found.
+- **Re-entrancy / livelock (DoS)** — run-mode machinery is bounded and tested: `Single`/`IgnoreFirst` re-entrancy guard, `Restart` cancel-and-replace, `Queued` FIFO serialization, and `max: N` semaphore cap (ADR-162; `restart_mode_cancels_prior_run`, `queued_mode_runs_sequentially_not_concurrently`, `max_two_caps_concurrency_at_two`, `single_mode_does_not_double_fire_on_rapid_triggers`). A self-triggering automation does not livelock the engine — each fire is bounded by its run-mode.
+- **Action authorization** — templates are read-only sandboxed (`states`/`state_attr`/`is_state`/`now` globals; no service-call or state-set global is exposed to template scope), so a template cannot escalate into an action. Service authorization itself is enforced at the `homecore` service-registry boundary (out of this crate's scope); no gap found in what the automation crate enforces.
+- **Panic-on-config (parse)** — `serde_yaml`/`serde_json` deserialization returns structured `AutomationError` (no `unwrap`/`expect`/index reachable from a crafted config in the eval/exec path); the only remaining panic surface was the `from_secs_f64` path fixed as HC-SEC-02.
+
+Validation: `cargo test -p homecore-automation --no-default-features` → 54 passed / 0 failed (+14 over baseline). Python deterministic proof unchanged (homecore-automation is off the signal-processing proof path).
+
+---
+
 ## 9. References

 ### HA upstream
@@ -0,0 +1,444 @@
+# ADR-131: HOMECORE-UI — Operational dashboard for the two-tier Cognitum stack
+
+| Field | Value |
+|-------|-------|
+| **Status** | Accepted — UI implemented (§10); full backend wiring specified (§11–§12) |
+| **Date** | 2026-06-14 |
+| **Deciders** | ruv |
+| **Codename** | **HOMECORE-UI** — first-class operator dashboard inside the Cognitum Appliance shell |
+| **Relates to** | [ADR-126](ADR-126-ruview-native-ha-port-master.md) (HOMECORE master), [ADR-127](ADR-127-homecore-state-machine-rust.md) (HOMECORE-CORE state machine), [ADR-128](ADR-128-homecore-integration-plugin-system.md) (HOMECORE-PLUGINS), [ADR-129](ADR-129-homecore-automation-engine.md) (automation engine), [ADR-130](ADR-130-homecore-rest-websocket-api.md) (HOMECORE-API), [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) (recorder/semantic search), [ADR-151](ADR-151-room-calibration-specialist-training.md) (room calibration HTTP API), [ADR-100](ADR-100-cog-packaging-specification.md) (Cog packaging), [ADR-116](ADR-116-cog-ha-matter-seed.md) (cog-ha-matter), [ADR-069](ADR-069-cognitum-seed-csi-pipeline.md) (SEED RVF ingest), [ADR-105](ADR-105-federated-csi-training.md) (federated CSI training) |
+| **Tracking issue** | TBD |
+| **Parent** | [ADR-126](ADR-126-ruview-native-ha-port-master.md) (sub-ADR, HOMECORE-127…134 family) |
+
+---
+
+## 1. Context
+
+HOMECORE (ADR-126 through ADR-134) is the native Rust + WASM + TypeScript port of Home Assistant running as the hub on the Cognitum v0 Appliance. As of P2, the state machine ([ADR-127](ADR-127-homecore-state-machine-rust.md)), API ([ADR-130](ADR-130-homecore-rest-websocket-api.md)), and COG runtime ([ADR-128](ADR-128-homecore-integration-plugin-system.md)) are in place. What is missing is a first-class dashboard UI that operators, integrators, and residents can use to manage the full two-tier hardware stack that HOMECORE coordinates.
+
+### 1.1 The two-tier hardware model this UI must represent
+
+This is the most important architectural constraint the UI must carry through every panel:
+
+- **Cognitum SEED** — a Pi Zero 2 W-based edge node. It has its own RVF vector store (8-dim, content-addressed, with kNN queries), Ed25519 witness chain, SHA-256 ingest audit trail, onboard environmental sensors (BME280 temperature/humidity/pressure, PIR motion, reed switch, ADS1115 4-channel ADC, vibration), 13 drift detectors, an MCP proxy (114 tools, JSON-RPC 2.0, default-deny policy), 98 HTTPS API endpoints, and epoch-based swarm sync for multi-SEED deployments. SEEDs sit close to the ESP32 sensing nodes and receive feature vectors from them at 1 Hz. Multiple SEEDs can form a peer mesh. **This is the sensing and memory tier.**
+- **Cognitum v0 Appliance** — a Pi 5 + Hailo-10H hub, running at `:9000`. It hosts the COG runtime (`/var/lib/cognitum/apps/`), the HOMECORE state machine and event bus, the calibration service, `ruview-mcp-brain:9876`, `cognitum-rvf-agent:9004`, `ruvector-hailo-worker:50051`, and acts as the fleet coordinator for multi-room correlation and federated training. The Appliance is where HOMECORE runs, and it is what the dashboard user is sitting in front of. **This is the computation and orchestration tier.**
+
+SEEDs are **subordinate nodes that the Appliance supervises** — they are not peers. The UI navigation hierarchy must reflect this: the Appliance is the root, SEEDs are children, ESP32 nodes are leaves.
+
+### 1.2 What the UI is not
+
+HOMECORE-UI is **not** a re-skin of the existing Cognitum Cog Store. It is a full operational dashboard that **extends** the Cognitum platform's shell — the Cog Store, API Explorer, and Guide already exist and must remain intact, with the HOMECORE dashboard added as a first-class navigation section alongside them.
+
+---
+
+## 2. Decision
+
+Build HOMECORE-UI as a **complete** TypeScript + Rust→WASM frontend (per this ADR's §3 and the HOMECORE-127…134 family) that:
+
+1. Lives at `http://cognitum-v0:9000/homecore` (or as a dedicated nav item in the Cognitum Appliance shell).
+2. Is visually and stylistically seamless with the existing Cognitum platform — same dark theme, same design tokens, same component patterns as `https://seed.cognitum.one/store`.
+3. Drives the HOMECORE REST + WebSocket API ([ADR-130](ADR-130-homecore-rest-websocket-api.md)) and the calibration HTTP API ([ADR-151](ADR-151-room-calibration-specialist-training.md)) for all data.
+4. Updates in real-time via the homecore `subscribe_events` WebSocket channel. **The UI must never poll for entity state.**
+
+**This is a decision to deliver the complete operational dashboard — every panel in §4.1 through §4.10, every navigation section in §5, fully wired to live data — not a design-system scaffold or a partial first cut.** A static layout shell with placeholder data is explicitly **out of scope as a deliverable**: the design system (§3) is a means to the complete UI, not an end in itself. The acceptance bar for this ADR is that an operator can drive the full two-tier stack — fleet, entities, rooms, COGs, calibration, events, audit, and settings — from the dashboard, against real APIs, with no panel left as a stub.
+
+### 2.1 `homecore-server` is the single backend-for-frontend (BFF) gateway
+
+The data the dashboard needs is spread across **three backend tiers that are not one process**: (a) `homecore-api` (`/api/*` REST + `/api/websocket`, mounted in `homecore-server`); (b) the **calibration API** (`/api/v1/*`, served by a *separate* binary — `wifi-densepose calibrate-serve` / `wifi-densepose-sensing-server`); and (c) the **SEED device tier + appliance daemons** (RVF vector store, witness chain, onboard sensors, reflex rules, COG supervisor, federation), which are physically separate HTTPS services on the SEED nodes and the appliance.
+
+The browser must talk to **exactly one origin.** Therefore `homecore-server` is promoted to the **single BFF / API gateway** for HOMECORE-UI: it serves the static assets at `/homecore`, serves `homecore-api` at `/api/*`, and **adds a new `/api/homecore/*` namespace** that proxies and aggregates the calibration API and the SEED/appliance tiers server-side. The UI only ever issues same-origin requests; cross-service auth (SEED bearer tokens, calibration tokens) is held by the gateway and **never exposed to the browser**. This collapses the CORS/multi-port problem and gives one place to enforce the long-lived-access-token auth (§4.10).
+
+### 2.2 No mock data in production
+
+The in-browser mock layer that the first UI cut shipped behind DEMO banners (§7.1, prior revision) is **demoted to a dev-only fixture** gated behind an explicit `?demo=1` / `HOMECORE_UI_DEMO=1` flag. The production build wires **every** panel to a real gateway endpoint. The full endpoint contract and the backend work each panel needs are specified in **§11**; the staged path to get there is **§12**. A panel may show an empty/typed-error state when its upstream is down, but it must never silently render fabricated data.
+
+---
+
+## 3. Design system — Cognitum platform conventions
+
+The implementor **must study `https://seed.cognitum.one/store` as the definitive design reference before writing a single line of CSS.** The existing platform's design tokens, extracted from production, are:
+
+### 3.1 Colour palette (CSS custom properties)
+
+| Token | Value | Role |
+|---|---|---|
+| `--bg` | `#0a0e1a` | page background (very dark navy) |
+| `--bg2` | `#111627` | secondary background / nav strip |
+| `--card` | `#171d30` | card / panel surface |
+| `--card-h` | `#1e2540` | card hover state |
+| `--border` | `#252d45` | all border strokes (≈0.67px, subtle) |
+| `--t1` | `#e0e4f0` | primary text (near-white) |
+| `--t2` | `#8890a8` | secondary / muted text |
+| `--t3` | `#505872` | tertiary / disabled text |
+| `--cyan` | `#4ecdc4` | primary action colour (Install buttons, live indicators, accents) |
+| `--cyan-d` | `rgba(78,205,196,0.15)` | cyan tint background for status badges |
+| `--green` | `#6bcb77` | success / online / healthy states |
+| `--green-d` | `rgba(107,203,119,0.15)` | green tint background |
+| `--amber` | `#d4a574` | warning / stale / degraded states |
+| `--amber-d` | `rgba(212,165,116,0.15)` | amber tint background |
+| `--red` | `#e06060` | error / offline / veto states |
+| `--red-d` | `rgba(224,96,96,0.15)` | red tint background |
+| `--purple` | `#a78bfa` | informational / epoch / chain indicators |
+| `--purple-d` | `rgba(167,139,250,0.15)` | purple tint background |
+| `--r` | `10px` | standard border radius on all cards and panels |
+
+### 3.2 Typography
+
+- `--font`: `'Segoe UI', system-ui, -apple-system, sans-serif` — all body and heading text.
+- `--mono`: `'Cascadia Code', 'Fira Code', Consolas, monospace` — all entity IDs, API endpoints, hex values, JSON payloads, COG binary hashes.
+
+### 3.3 Component patterns (from the live Cog Store and API Explorer)
+
+- **Cards**: `background: var(--card)`, `border: 0.67px solid var(--border)`, `border-radius: var(--r)`, `padding: 24px`.
+- **Category pills / status badges**: small `border-radius: 4–6px`, uppercase text, coloured background tint (e.g. `background: var(--cyan-d); color: var(--cyan)` for `RUNNING`; `background: var(--amber-d); color: var(--amber)` for `STALE`).
+- **Primary action buttons**: `background: var(--cyan)`, `color: var(--bg)`, no border — matching the existing "Install" button style exactly.
+- **Secondary / ghost buttons**: transparent background, `border: 1px solid var(--border)`, `color: var(--t1)` — matching the existing "Details" button style.
+- **Nav strip**: `background: var(--bg2)`, text items in `--t2`, active item highlighted in `--cyan` with a bottom underline.
+- **Featured card gradient borders**: top-edge linear gradient from `var(--cyan)` to `var(--purple)` — replicate for HOMECORE section headers.
+- **Live metric cards** (API Explorer status page): icon + large numeric value in `--cyan` or `--green`, label in `--t2` below, on a `var(--card)` background.
+- **Method badge pills** on the API Explorer (`GET` in green, `POST` in amber, `AUTH` in purple) — reuse this same pill system for COG status indicators.
+
+The implementor **must not introduce new colours, typefaces, or border radii.** Every component should feel like it was built by the same team that built the Cog Store and the API Explorer. A user navigating from the Cog Store into the HOMECORE dashboard should not notice a visual seam.
+
+---
+
+## 4. UI sections — required panels
+
+### 4.1 System Dashboard (the "home screen")
+
+The always-visible overview panel. Modelled on the API Explorer's live metric cards. All values update in real-time.
+
+- **v0 Appliance health strip** — reuse the exact metric-card pattern from `seed.cognitum.one/status`: one card each for CPU %, RAM usage, Hailo-10H inference load (% utilisation), Hailo temperature, uptime, and the running services (`ruview-mcp-brain:9876`, `cognitum-rvf-agent:9004`, `ruvector-hailo-worker:50051`). Values in `--cyan`, labels in `--t2`. This strip is always at the top — it represents the machine the user is looking at.
+- **SEED Fleet overview** — a grid of SEED node cards (one per paired SEED) on the `var(--card)` surface with `var(--border)`. Each card shows: online/offline status pill (green/red), firmware version, epoch number, current vector count, last ingest timestamp, and witness-chain validity badge. A collapsed row shows the SEED's 5 onboard sensors in summary (PIR: yes/no, door: open/closed, temperature from BME280). Offline SEEDs render the entire card with a `--red-d` background tint. Clicking a SEED card navigates to the SEED Detail view (§4.2).
+- **ESP32 Node summary** — count of active ESP32 nodes per SEED, current frame rate (target: 100 Hz CSI + 1 Hz feature vectors), and a compact warning list for nodes with known issues (presence_score normalisation anomaly, stale firmware version).
+- **COG Runtime status row** — a horizontal strip of status pills for each installed COG on the v0 Appliance. Pill colours follow the existing badge convention: `--green-d`/`--green` for running, `--red-d`/`--red` for failed, `--t3`/`--t2` for stopped. COG name in `--mono`. Clicking a pill navigates to COG Management (§4.6).
+- **Event Bus activity indicator** — a small real-time sparkline showing the homecore broadcast channel event rate (events/sec). Indicate channel lag if a subscriber is falling behind the 4,096-event capacity.
+
+### 4.2 SEED Detail View (per-SEED drill-down)
+
+Accessible from the fleet grid. Full-page panel for a single SEED node, using the card + section-header pattern from the Cog Store's detail views.
+
+- **SEED identity header** — `device_id` in `--mono`, firmware version, paired status in green, USB vs WiFi connection mode. A section-header gradient border (cyan → purple, matching the featured card style) visually separates this from Appliance content.
+- **Vector Store panel** — current vector count, dimension (8), last kNN query latency, current epoch number, a small sparkline of ingest rate over the last hour, and a storage budget bar showing usage against the 100K working-set target. A "Compact now" button (`POST /api/v1/store/compact`) in ghost style. When usage exceeds 80%, the bar renders in `--amber`.
+- **Witness Chain panel** — chain length (SHA-256 entries), last verification timestamp, a one-click "Verify chain" button (`POST /api/v1/witness/verify`), and an "Export attestation bundle" button for regulated deployments. The Ed25519 custody attestation (device-bound keypair, epoch + vector count + witness head) renders here. Chain length in `--purple`, following the existing epoch/chain colour convention.
+- **Onboard Sensors panel** — live readings from all 5 sensors in individual sub-cards: BME280 (temperature °C, humidity %, pressure hPa), PIR (motion boolean with last-triggered timestamp), reed switch (open/closed with last-changed timestamp), ADS1115 (4 analog channels with configurable labels), vibration (boolean with last-triggered). These are ground-truth validators against CSI readings and are critical for diagnosing false positives in the mixture-of-specialists. Sensor values in `--cyan`; sensor names in `--t2`.
+- **Reflex Rules panel** — the 3 pre-configured rules with current state: `fragility_alarm` (threshold 0.3 → relay actuator), `drift_cutoff` (threshold 1.0), `hd_anomaly_indicator` (threshold 200 → PWM brightness). Show last-fired time for each. The `fragility_alarm` threshold is the most commonly adjusted field and should be editable inline. Rules that have recently fired render with a `--amber-d` background tint.
+- **Cognitive Analysis panel** — boundary fragility score (0.0–1.0, from Stoer-Wagner min-cut on the kNN graph) rendered as a progress bar: green below 0.3, amber 0.3–0.6, red above 0.6. High fragility (>0.3) indicates a regime change in the environment and should be visually prominent. Temporal coherence phase boundaries shown as a labelled timeline of detected environment state transitions. kNN graph rebuild cadence indicator (every 10 s).
+- **Ingest pipeline status** — which ESP32 nodes feed this SEED, the packet type each is sending (`0xC5110003` native feature vectors vs `0xC5110002` vitals fallback path — distinguished visually since native is preferred), current ingest batch size, flush interval, and bridge path topology (direct vs host-laptop hop). The bridge-hop warning (known architectural limitation) renders in `--amber` since it adds a network hop.
+
+### 4.3 SEED Fleet Map (multi-SEED topology)
+
+For deployments with more than one SEED, a topology view showing the mesh:
+
+- **Node hierarchy diagram** — v0 Appliance at root, SEEDs as second tier (grouped by room/zone), ESP32 nodes as leaves under each SEED. Lines represent active data flows. ESP-NOW mesh sync links between SEEDs shown as dashed lines. Connection health shown via line colour (green/amber/red). All labels in `--mono`.
+- **Cross-SEED event deduplication indicator** — for events that span multiple SEEDs (one fall detected by two rooms; one occupant tracked through room A → hallway → room B), show a fusion badge indicating how many SEEDs contributed to the composite event.
+- **Federation config** ([ADR-105](ADR-105-federated-csi-training.md)) — federated-learning round coordinator role (which SEED is the round coordinator), current round number, K healthy nodes selected, delta exchange status. **Model deltas only — never raw CSI** is a design invariant that must be labelled explicitly in the UI.
+
+### 4.4 Entity & State Browser
+
+The homecore state machine (`DashMap<EntityId, Arc<State>>`) is the authoritative source of truth. Every COG running on the v0 Appliance contributes entities.
+
+- **Entity list by domain** — grouped by the `domain.` prefix of `EntityId`, using collapsible section headers. The 21 entities per ESP32 node (11 raw + 10 semantic primitives from `cog-ha-matter`) are the most important set. For each entity: current state string (in `--t1`), last-changed timestamp (in `--t3`), attribute map as collapsible JSON in `--mono`, and the Context (`user_id` + `parent_id` causality chain, critical for care/audit deployments). Entity IDs always in `--mono`.
+- **SEED provenance badge** — each entity carries a small badge showing its data lineage: which ESP32 node → which SEED → which COG → homecore state machine. This trace is invaluable for debugging false positives and is a **first-class UI element, not a collapsed detail.**
+- **Domain filter + semantic search** — filter by domain prefix and, once [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) (homecore-recorder) lands, ruvector-backed semantic search: "when did the living room anomaly score last correlate with a door-open event?" A keyword filter across entity IDs and attribute keys ships in the initial release regardless of [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) status, given entity density; the semantic search layers on top once the recorder lands.
+- **Real-time WebSocket feed** — entity states update live via the homecore `subscribe_events` WebSocket command ([ADR-130](ADR-130-homecore-rest-websocket-api.md)). The UI must never poll. Show a broadcast-channel lag indicator; warn visually if the subscriber is falling behind the 4,096-event channel capacity.
+- **StateChanged detail panel** — clicking any entity opens a slide-over panel showing the full `StateChangedEvent`: `old_state`, `new_state`, `context.id`, `context.user_id`, and the `context.parent_id` chain rendered as a breadcrumb trail.
+
+### 4.5 RoomState / Sensing Panel
+
+Surfaces the mixture-of-specialists output from the calibration service — the highest-level per-room sensing result. Data comes from `GET /api/v1/room/state?bank=<room_id>` on the v0 Appliance.
+
+- **Per-room cards** — one card per `room_id` on the `var(--card)` surface. Each card shows live `RoomState` JSON fields as sub-rows: presence (occupied/absent chip in green/red with confidence bar), posture (standing/sitting/lying chip with confidence), breathing BPM (numeric in `--cyan` with range indicator 6–30), heart rate BPM (numeric in `--cyan` with range indicator 40–120), restlessness score (0–1 progress bar), and anomaly score (0–1 with normal/anomalous label, bar turns red above a configurable threshold).
+- **STALE warning** — when `stale: true` (the specialist bank was trained against a different baseline), render the entire room card with a `--amber-d` background tint and a prominent amber banner reading "Bank stale — baseline has changed" with a direct "Recalibrate room" link into the calibration wizard (§4.7). This is the most common real-world failure mode and **must never be subtle.**
+- **VETO indicator** — when `vetoed: true` (anomaly veto suppressed vitals/posture because the window was physically implausible), render the affected specialist slots in `--red` with a "Veto active" label. Values suppressed by veto **must not render as zeros** — they must render as explicitly withheld.
+- **Null specialist placeholders** — specialists not yet trained (`null` in the specialist bank) render as "Not trained" placeholders in `--t3` with a small "Calibrate to enable" prompt in ghost style. They are **not** errors.
+- **Confidence bars** — each specialist output has a confidence float, shown as a small inline bar (`--cyan` fill) next to the reading. Low confidence (< 0.4) renders the bar in `--amber`.
+- **Multi-SEED fusion indicator** — for rooms served by multiple SEEDs, show a small badge indicating how many SEED nodes contributed to the `MultiNodeMixture` for this room's reading.
+
+### 4.6 v0 Appliance COG Management
+
+The v0 Appliance hosts COGs at `/var/lib/cognitum/apps/`. This panel is the operational companion to the existing Cog Store (`seed.cognitum.one/store`). It must match the Cog Store's visual conventions precisely — same card layout, same category pills, same install/detail button pair — because operators will move between the two surfaces.
+
+- **Installed COGs list** — for each COG: `id` and `version` in `--mono`, architecture badge (`arm`/`hailo10` etc., category-pill pattern), status pill (running/stopped/failed/updating in green/grey/red/amber), `binary_sha256` verified badge (Ed25519 signature verification shown as a shield icon in `--green` or `--red`), and PID from the pid file. Actions: start, stop, restart (ghost style), and view `output.log` / `error.log` in a monospace drawer using `--mono`. Edit `config.json` inline with syntax highlighting.
+- **COG Store / App Registry** — browsable `app-registry.json` listing. This panel should visually mirror `seed.cognitum.one/store` as closely as possible — same featured-card hero layout, same icon + title + description + category pill + action button structure. One-click install downloads the binary from GCS, verifies `binary_sha256` + `binary_signature`, writes the manifest, and starts the COG. Show which new homecore entities will appear in the state machine after install, as a preview list before confirming.
+- **OTA Updates** — a badge count on installed COGs with available updates, matching the "Installed (N)" tab badge convention from the existing Cog Store. Show a diff panel (version change, new entities, config schema changes) before confirming the update.
+- **Hailo HEF status** — for COGs with `arch: hailo10`: loaded HEF files on the Hailo-10H, current inference throughput, and `ruvector-hailo-worker:50051` connection status. The RF Foundation Encoder ([ADR-150](ADR-150-rf-foundation-encoder.md)) and neural pose head display here once available.
+
+### 4.7 Calibration Wizard
+
+The full baseline → enroll → train → verify pipeline runs via HTTP against the v0 Appliance ([ADR-151](ADR-151-room-calibration-specialist-training.md)). This is a multi-step guided flow — not a raw API panel. Use a stepped wizard layout with a progress indicator at the top (steps 1–5 as numbered pills, active step in `--cyan`, completed in `--green`, pending in `--t3`).
+
+- **Step 1 — Select room and SEED** — enter a `room_id` name (validated against `[A-Za-z0-9_-]{1,64}`) and select which SEED(s) and ESP32 nodes serve this room from a dropdown populated from the live fleet. Show current CSI ingest health for the selected nodes inline — if frames are not arriving at the expected rate, display an amber warning **before** allowing the operator to proceed. A broken ingest pipeline will silently fail calibration.
+- **Step 2 — Baseline capture** — `POST /api/v1/calibration/start`. A large full-width animated progress bar (cyan fill) reads from `GET /api/v1/calibration/status`: frames recorded vs target, ETA in seconds, `z_median` value. If `motion_flagged` is true, overlay an amber banner: "Room must be empty — movement detected." The baseline UUID produced here is the anchor for all future STALE detection for this room — display it in `--mono` once complete so operators can record it.
+- **Step 3 — Anchor enrollment** — the 8 anchor labels in enforced order: `empty`, `stand_still`, `sit`, `lie_down`, `breathe_slow`, `breathe_normal`, `small_move`, `sleep_posture`. For each: a human-readable instruction with an illustration, a countdown timer rendered as a circular progress ring in `--cyan`, and an immediate quality-gate result (accepted in green, retry in amber with a reason string). Drive via `POST /api/v1/enroll/anchor` + `GET /api/v1/enroll/status`. After each accepted anchor, show the extracted feature values (mean, variance, breathing_score, heart_score) in a small `--mono` data row so operators can sanity-check the capture. Show overall progress as "N / 8 anchors accepted."
+- **Step 4 — Train** — a single `POST /api/v1/room/train` call. Show the 6 specialist results as a checklist: presence (threshold + occupied_var), posture (prototype count), breathing (min_score), heartbeat (min_score), restlessness (calm/active motion values), anomaly (prototype count + scale). Specialists that returned non-null render in `--green`. Null specialists (insufficient anchor data) render in `--amber` with a "Re-enroll missing anchors" prompt linking back to Step 3 for the specific missing labels.
+- **Step 5 — Verify live** — display the live `RoomState` for the just-trained room using the same per-room card layout as §4.5. Prompt the operator to stand in the room and verify presence is detected, try sitting/lying to confirm posture, and breathe normally to confirm vitals are in plausible range. A "Confirm and save" button (cyan, primary) closes the wizard; a "Something's wrong — re-enroll" button (ghost) loops back to Step 3.
+
+### 4.8 Event Bus & Automation Feed
+
+- **Live event stream panel** — a virtualized scrolling list of `SystemEvent` variants (`StateChanged`, `EntityRegistered`, `ConfigReloaded`) and notable `DomainEvent`s from the homecore Tokio broadcast channel. Each row shows: event-type pill (coloured by variant), `entity_id` in `--mono`, old state → new state arrow, timestamp, and `context.user_id`. The stream is filterable by entity domain, event type, or source SEED/COG. The filter bar uses the same search-input style as the Cog Store's search field.
+- **Context causality breadcrumb** — expanding any event row shows the full Context chain (`context.id` → `parent_id` → `grandparent_id`) as a breadcrumb trail in `--mono`. This is how automation loops become visible without any separate debugging tool.
+- **Automation builder** ([ADR-129](ADR-129-homecore-automation-engine.md) scope) — a trigger → condition → action editor on the card surface. The most important RuView-specific trigger types to support are: `state_changed` on `RoomState` entities with a threshold expression (e.g. `anomaly.value > 0.8`), SEED reflex-rule firing events (`fragility_alarm`, `hd_anomaly_indicator`), and custom `domain_event` topics. Actions include calling services in the homecore service registry and firing domain events. The condition expression editor uses `--mono`.
+
+### 4.9 Witness / Audit Log
+
+- **Unified witness timeline** — a chronological merged view of events from both tiers: the SEED's SHA-256 ingest chain (every RVF store write attested) and homecore's Ed25519 state-transition chain (biometric crossings, BFLD identity-risk elevations). Each row: `entity_id` in `--mono`, old/new state, timestamp, source SEED `device_id`, signing key fingerprint (first 8 chars in `--mono`). Pagination uses the same "Showing X–Y of Z" convention from the Cog Store's cog grid.
+- **Privacy mode banner** — a persistent top-of-panel banner showing current privacy mode: `--green-d`/green text for full-publish mode; `--amber-d`/amber text for audit-only mode (SHA-256 digests on-SEED only, no MQTT state messages). Show the per-SEED privacy mode state, since SEEDs can be individually configured. Toggling privacy mode is a high-stakes action — require an explicit "Confirm" step with a summary of what will change.
+- **Export bundle** — an "Export attestation bundle" button (ghost) that packages the SEED witness chain + homecore Ed25519 chain as a downloadable archive for regulated-deployment (care home, hotel, shared office) compliance handoff.
+
+### 4.10 Settings & Integration Config
+
+- **SEED fleet management** — add, remove, and reprovision SEEDs. Show the USB-only pairing requirement prominently (the pairing window only opens via `169.254.42.1`, not WiFi — a security invariant). Per-SEED: `device_id` in `--mono`, firmware version, bearer token status, and a "Rotate token" action (ghost) that walks the operator through the secure token rotation flow.
+- **ESP32 node provisioning** — per-node NVS config display (target IP, target port, node_id), last-seen firmware version, and a link to the provisioning script. The `node_id` → room/zone assignment is editable here and persists to the room calibration system's `room_id` mapping.
+- **MQTT / cog-ha-matter config** ([ADR-116](ADR-116-cog-ha-matter-seed.md)) — broker URL, credentials (masked), MQTT topic prefix, mDNS advertisement status (`_ruview-ha._tcp`), and a live connection indicator (green dot for connected, red for unreachable). The 21 HA-DISCO entities per node are listed here with their `via_device` assignments showing which SEED they belong to in HA's device registry.
+- **Long-lived access tokens** — for homecore-api companion-app connections (HA 2025.1 wire-compat, [ADR-130](ADR-130-homecore-rest-websocket-api.md)). Token creation, last-used timestamp, and revocation. The HA companion-app pairing QR-code flow surfaces here.
+- **Federation config** — for multi-SEED deployments: ESP-NOW mesh sync status, cross-SEED epoch alignment values, and federated-learning round settings (coordinator SEED, round cadence, Krum aggregation parameters per [ADR-105](ADR-105-federated-csi-training.md)). The design invariant **"model deltas only, never raw CSI"** must be labelled explicitly in this panel.
+
+---
+
+## 5. Navigation structure
+
+HOMECORE-UI must integrate into the existing Cognitum Appliance nav shell. The top nav should read:
+
+```
+Framework | Guide | Cog Store | HOMECORE | Status
+```
+
+— inserting **HOMECORE** as a first-class nav item between the existing "Cog Store" and "Status" entries, using the same nav-item style (text in `--t2`, active state in `--cyan` with bottom underline).
+
+Within the HOMECORE section, a left sidebar (or top sub-nav on narrow viewports) provides section navigation:
+
+```
+Dashboard | SEED Fleet | Entities | Rooms | COGs | Calibration | Events | Audit | Settings
+```
+
+The COG Store panel within HOMECORE (§4.6) links out to `seed.cognitum.one/store` for the full catalog view, ensuring the existing Cog Store remains the canonical browsing experience.
+
+---
+
+## 6. Key UX invariants
+
+These must be maintained across every panel:
+
+1. **Always make the tier origin of any data explicit.** A `RoomState` reading traces to an ESP32 node → SEED → COG → v0 Appliance state machine. The provenance badge (§4.4) must appear wherever entity states are displayed.
+2. **The `stale` and `vetoed` flags from `RoomState` and the kNN fragility score from SEED cognitive analysis are meaningful diagnostic signals** — they must never be silently hidden, styled grey-on-grey, or collapsed behind an expand toggle. They represent system health operators need to act on.
+3. **Values that are `null` because a specialist has not been trained must be visually distinct from values that are unavailable due to an error.** The distinction is operationally important: `null` means "calibrate to enable," unavailable means "investigate."
+4. **All entity IDs, hashes, API endpoints, binary signatures, device UUIDs, and JSON payloads must use `--mono` font.** This is already the convention in the API Explorer and must be consistent throughout HOMECORE-UI.
+5. **The v0 Appliance Hailo HAT is a separate subsystem from the SEED's edge compute.** Inference results tagged as Hailo-sourced (COGs with `arch: hailo10`) must be visually distinguished from results from CPU-only COGs (`arch: arm`) so operators can triage hardware-specific failures.
+
+---
+
+## 7. Scope — complete UI delivery
+
+The deliverable is the **entire** dashboard. Every panel below ships fully implemented and wired to its live data source — there is no scaffold-only milestone and no panel left as a placeholder. The table records each panel's authoritative backing API so the build can proceed in whatever order best fits the dependency graph; it is a dependency map, **not** a sequence of partial releases.
+
+| Panel | Section | Backing API / source |
+|---|---|---|
+| System Dashboard | §4.1 | [ADR-130](ADR-130-homecore-rest-websocket-api.md) WebSocket + appliance health endpoints |
+| SEED Detail View | §4.2 | SEED HTTPS API (vector store, witness, sensors, reflex, cognitive analysis) |
+| SEED Fleet Map | §4.3 | fleet topology + federation ([ADR-105](ADR-105-federated-csi-training.md)) |
+| Entity & State Browser | §4.4 | [ADR-127](ADR-127-homecore-state-machine-rust.md) state machine via [ADR-130](ADR-130-homecore-rest-websocket-api.md) `subscribe_events`; semantic search via [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) |
+| RoomState / Sensing | §4.5 | [ADR-151](ADR-151-room-calibration-specialist-training.md) `GET /api/v1/room/state` |
+| COG Management | §4.6 | [ADR-128](ADR-128-homecore-integration-plugin-system.md) plugin runtime + [ADR-100](ADR-100-cog-packaging-specification.md) app registry |
+| Calibration Wizard | §4.7 | [ADR-151](ADR-151-room-calibration-specialist-training.md) calibration HTTP API |
+| Event Bus & Automation | §4.8 | [ADR-130](ADR-130-homecore-rest-websocket-api.md) broadcast channel + [ADR-129](ADR-129-homecore-automation-engine.md) automation engine |
+| Witness / Audit Log | §4.9 | SEED SHA-256 ingest chain + homecore Ed25519 chain |
+| Settings & Integration | §4.10 | SEED provisioning, [ADR-116](ADR-116-cog-ha-matter-seed.md) MQTT/Matter, LLAT, federation |
+
+### 7.1 Build sequencing within the complete deliverable
+
+The complete UI depends on backing services that mature on their own timelines. Each panel is built against the **real gateway endpoint** defined in §11; where the upstream is not yet available the panel renders a typed empty/error state, **not** fabricated data (the dev-only `?demo=1` fixture of §2.2 exists for offline development only and is never the shipped behaviour). Concretely, the hard contract dependencies are: [ADR-130](ADR-130-homecore-rest-websocket-api.md) (REST + WebSocket), [ADR-127](ADR-127-homecore-state-machine-rust.md) (state machine), [ADR-151](ADR-151-room-calibration-specialist-training.md) (calibration), [ADR-128](ADR-128-homecore-integration-plugin-system.md) (plugin runtime), [ADR-129](ADR-129-homecore-automation-engine.md) (automation), [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) (event history + semantic search), [ADR-116](ADR-116-cog-ha-matter-seed.md) (SEED/Matter), [ADR-069](ADR-069-cognitum-seed-csi-pipeline.md) (SEED ingest), and [ADR-105](ADR-105-federated-csi-training.md) (federation). The keyword entity filter (§4.4) ships immediately; semantic search layers on once [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) lands. The exact panel→endpoint→upstream map and the new gateway code each requires are §11; the staged delivery is §12.
+
+---
+
+## 8. Consequences
+
+### 8.1 Positive
+
+- Operators, integrators, and residents get a single coherent surface for the full two-tier stack, replacing the need to SSH into SEEDs or hand-craft API calls.
+- The dashboard reuses the proven Cognitum design tokens and component patterns verbatim, so it ships visually consistent with no separate design effort and no perceptible seam between surfaces.
+- Diagnostic signals that today are invisible (`stale`/`vetoed` flags, kNN fragility, provenance lineage, channel lag) become first-class, surfacing the system's most common real-world failure modes directly to operators.
+
+### 8.2 Negative / risks
+
+- The UI hard-depends on the wire-compat guarantees of ADR-130 and the calibration contract of ADR-151; schema drift in either breaks panels silently. Integration tests against every backing contract in §7 are required.
+- Committing to the complete UI in one deliverable is a larger up-front effort and couples the UI's readiness to the maturity of multiple backing services (§7.1, §11). The mitigation is the BFF gateway (§2.1): each panel targets one same-origin endpoint, and the gateway absorbs upstream churn behind a stable contract.
+- Promoting `homecore-server` to a gateway means it now **proxies cross-tier traffic** (calibration API, SEED HTTPS, appliance daemons). This adds a network hop, a place for upstream timeouts/partial failures to surface, and a server-side store of SEED bearer tokens that must be protected (§11.10). Each proxied route needs an explicit timeout + typed error mapping so one slow SEED cannot stall the dashboard.
+- Several panels depend on data that only exists on **real hardware or new daemons** (SEED device tier, appliance host metrics, COG supervisor). Until those upstreams exist the corresponding gateway routes return `503 upstream_unavailable`; this is honest but means the dashboard is only as "live" as the tiers behind it (§11 classifies every endpoint by what it depends on).
+- Faithfully mirroring `seed.cognitum.one/store` couples HOMECORE-UI to the external Cog Store's evolving design; token drift there must be tracked and re-synced.
+- The two-tier mental model (Appliance root, SEED children, ESP32 leaves) must be enforced consistently; any panel that flattens or peers the tiers undermines the core architectural constraint.
+
+---
+
+## 9. References
+
+- `https://seed.cognitum.one/store` — primary design reference for all visual conventions.
+- `https://seed.cognitum.one/status` — reference for live metric-card layout.
+- [ADR-126](ADR-126-ruview-native-ha-port-master.md) — HOMECORE master ADR.
+- [ADR-127](ADR-127-homecore-state-machine-rust.md) — HOMECORE-CORE state machine and entity registry.
+- [ADR-128](ADR-128-homecore-integration-plugin-system.md) — HOMECORE-PLUGINS WASM COG substrate.
+- [ADR-129](ADR-129-homecore-automation-engine.md) — HOMECORE automation engine.
+- [ADR-130](ADR-130-homecore-rest-websocket-api.md) — HOMECORE-API REST + WebSocket wire-compat.
+- [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) — homecore-recorder, history + semantic search.
+- [ADR-100](ADR-100-cog-packaging-specification.md) — Cognitum Cog packaging specification (manifest.json, status values, on-device layout).
+- [ADR-116](ADR-116-cog-ha-matter-seed.md) — cog-ha-matter (SEED cog, HA-DISCO entity surface, mDNS).
+- [ADR-069](ADR-069-cognitum-seed-csi-pipeline.md) — ESP32 CSI → Cognitum SEED RVF ingest pipeline (SEED architecture detail).
+- [ADR-105](ADR-105-federated-csi-training.md) — Federated CSI training (multi-SEED federation).
+- [ADR-151](ADR-151-room-calibration-specialist-training.md) — Per-room calibration specialist training (calibration HTTP API).
+- `v2/crates/homecore/src/` — state machine, entity, event, registry source.
+- `docs/integration/calibration-appliance-integration.md` — calibration API contract and RoomState schema.
+
+---
+
+## 10. Implementation status
+
+Implemented as a zero-dependency, no-build-step vanilla TS/JS + CSS frontend served by `homecore-server` at `/homecore` (the `rufield-viewer` "Axum + vanilla-JS" pattern). The complete deliverable per §2/§7 — all ten panels, fully rendered, wired to live data where the backing service exists and to a contract-conformant DEMO-flagged mock layer (§7.1) where it does not.
+
+**Location:** `v2/crates/homecore-server/ui/` — `css/tokens.css` (the §3.1 palette, verbatim) + `css/app.css` (§3.3 components); `js/{ui,api,ws,mock,app}.js` (shared helpers, REST client, `subscribe_events` WS client, mock layer, shell+router); `js/panels/*.js` (one module per §4 panel). Mounted via `tower-http` `ServeDir` in `homecore-server::build_app`, gated by `--ui-dir`/`HOMECORE_UI_DIR`.
+
+**Verification:**
+- **Rust** — `#[cfg(test)] mod ui_tests` in `homecore-server/src/main.rs`: 5 integration tests (`tower::oneshot`) covering index, design tokens, all ten panel modules served, API coexistence, and mount-disable. *Written but not compiled in the authoring environment (no Rust toolchain present); run `cargo test -p homecore-server` on a Rust host before merge.*
+- **Frontend** — `ui/` test suite under plain `node` (no npm install): `npm test` → import/export graph verifier (15 modules) + render-smoke (executes every panel against a DOM shim; 21 checks) + interaction suite (live WS patch, ws.js handshake/parse, calibration contract; 3 checks). **24/24 green.**
+- **Benchmark** — `npm run bench`: total bundle **136.8 KB** uncompressed (**~37× smaller** than HA's ~5 MB Lit bundle, the ADR-126 §1.1 foil); slowest panel **1.5 ms/cold-render**.
+
+**Honest scope — current vs. target.** *Earlier cut:* the front-end was complete but only §4.4 Entities was wired to a real backend; the rest rendered from an in-browser mock. *This revision implements the §11 wiring:*
+
+- **Front-end (§11.11) — DONE and verified.** `api.js` rewritten: all data accessors are async and call the §11.2 gateway routes; the mock layer is demoted to a dev-only fixture reachable **only** under `?demo=1` / `HOMECORE_UI_DEMO` (§2.2); every panel `await`s and renders a typed empty/error state on failure (no mock fallback in production). All ten panels converted (3 by hand, 7 via parallel agents). Verified under Node: 5 test files green — import graph, boot, render-smoke (22), interaction (3), **and a new prod-errors suite (13) that runs with demo OFF + gateway unreachable and asserts every panel renders an error state, never mock, never throws** (it caught and fixed a real unhandled-rejection in the events panel).
+- **Gateway (§11.1–§11.6) — IMPLEMENTED, COMPILED, TESTED, RUN.** New `homecore-server/src/gateway.rs` (+`reqwest` dep, +CLI/env flags `--calibration-url`/`--calibration-token`/`--apps-dir`/`--gateway-timeout-ms`, merged into `build_app` via `gateway_router`). Real handlers: `/api/cal/*` reverse-proxy (W2), `GET /api/homecore/rooms` with the §11.3 RoomState adapter (W2), `GET /api/homecore/cogs` supervisor over the apps dir (W4), `GET /api/homecore/appliance` from `/proc` + port probes (W6). SEED-device/appliance-daemon routes (seeds, federation, witness, privacy, settings, automations, events-history, hailo, tokens — W3/W5) return a typed `503 upstream_unavailable` per §11.2. **Verified on Rust 1.89: `cargo test -p homecore-server --no-default-features` = 12/12 pass** (6 gateway + 6 UI mount). **Run live:** `GET /api/homecore/appliance` returns real `/proc` metrics + TCP service probes; unauth → `401`; `cogs` → `[]` with no apps dir; SEED-tier → typed `503`; and against a mock calibration upstream the `/api/cal/*` proxy passes through (`200`) and `GET /api/homecore/rooms` correctly adapts `RoomState` to the UI shape (`breathing`→`breathing_bpm`, `heartbeat:null`→`heart_bpm:null`, injected `anomaly.threshold`/`room_id`, `stale` passthrough). **Live testing caught + fixed one real bug** — a double-`v1` path in the `/api/cal/*` proxy URL.
+
+The endpoint-by-endpoint contract is **§11**; the staged plan and which endpoints depend on real SEED/appliance hardware vs. pure software is **§12**.
+
+---
+
+## 11. Backend wiring — making every panel real
+
+This section is the authoritative contract for full functionality. It removes the mock layer from the production path (§2.2) by routing every panel through the `homecore-server` BFF gateway (§2.1). Each endpoint is classified by what it depends on:
+
+- **EXISTS** — backend code already in this repo; gateway only proxies/adapts.
+- **NEW-GW** — pure software the gateway itself implements (filesystem, `/proc`, process control, recorder query) — no new external service.
+- **NEW-API** — a small HTTP wrapper to add to an existing in-repo crate (`homecore-api`, `homecore-automation`).
+- **SEED-DEV** — depends on a SEED node's on-device HTTPS API (separate hardware/firmware).
+- **APPLIANCE** — depends on an appliance daemon / accelerator stat source.
+
+### 11.1 Gateway shape
+
+`homecore-server` already mounts `homecore-api` at `/api/*` and the UI at `/homecore`. It gains a new **`/api/homecore/*`** namespace (the dashboard-specific aggregation surface) plus a **`/api/cal/*`** reverse-proxy to the calibration service. The browser issues only same-origin requests; the gateway fans out server-side, holding all upstream credentials (§11.10). Every proxied route has an explicit timeout and maps upstream failure to a typed body (`503 upstream_unavailable`, `504 upstream_timeout`) so one slow tier never stalls the dashboard.
+
+### 11.2 Master endpoint contract (panel → gateway route → upstream → status)
+
+| Panel | UI method (`api.js`) | Gateway route | Upstream / source | Class |
+|---|---|---|---|---|
+| §4.4 Entities | `states()` | `GET /api/states` | `homecore` state machine | **EXISTS** ✅ wired |
+| §4.4/§4.8 live feed | WS | `GET /api/websocket` (`subscribe_events`) | `homecore` event bus | **EXISTS** ✅ wired |
+| §4.8 Event history | `eventHistory(q)` | `GET /api/events?since=…` | `homecore-recorder` ([ADR-132](ADR-132-homecore-recorder-history-semantic-search.md)) | **NEW-API** |
+| §4.8 Automations | `automations()` / `saveAutomation()` | `GET/POST/DELETE /api/homecore/automations` | `homecore-automation` ([ADR-129](ADR-129-homecore-automation-engine.md)) | **NEW-API** |
+| §4.5 Rooms | `roomStates()` | `GET /api/homecore/rooms` → per-room `GET /api/cal/v1/room/state?bank=` | `calibrate-serve` ([ADR-151](ADR-151-room-calibration-specialist-training.md)) | **EXISTS** (proxy + adapter) |
+| §4.7 Calibration | `calibration.*` | `POST /api/cal/v1/calibration/{start,stop}`, `GET …/status`, `POST …/enroll/anchor`, `GET …/enroll/status`, `POST …/room/train` | `calibrate-serve` | **EXISTS** (proxy) |
+| §4.6 COGs | `cogs()` / `cogAction()` / `cogLogs()` | `GET /api/homecore/cogs`, `POST …/cogs/:id/{start,stop,restart}`, `GET …/cogs/:id/logs`, `GET/PUT …/cogs/:id/config` | COG supervisor over `/var/lib/cognitum/apps/` ([ADR-100](ADR-100-cog-packaging-specification.md)/[ADR-128](ADR-128-homecore-integration-plugin-system.md)) | **NEW-GW** |
+| §4.6 Hailo HEF | `hailo()` | `GET /api/homecore/hailo` | `ruvector-hailo-worker:50051` | **APPLIANCE** |
+| §4.1 Appliance health | `appliance()` | `GET /api/homecore/appliance` | host `/proc` + Hailo stats + service probes | **NEW-GW** (+APPLIANCE for Hailo) |
+| §4.1/§4.2 Fleet + SEED detail | `seeds()` / `seed(id)` | `GET /api/homecore/seeds`, `GET …/seeds/:id` | SEED device HTTPS API ([ADR-069](ADR-069-cognitum-seed-csi-pipeline.md)) via registry | **SEED-DEV** |
+| §4.2 SEED actions | `seedCompact()` / `seedVerify()` | `POST …/seeds/:id/{compact,witness/verify}` | SEED device API | **SEED-DEV** |
+| §4.3 Federation | `federation()` | `GET /api/homecore/federation` | federation coordinator ([ADR-105](ADR-105-federated-csi-training.md)) | **SEED-DEV/APPLIANCE** |
+| §4.9 Witness/Audit | `witnessLog(p,s)` | `GET /api/homecore/witness?page=…` | merge: `homecore` Ed25519 chain + per-SEED SHA-256 chains | **NEW-API + SEED-DEV** |
+| §4.9 Privacy mode | `privacyModes()` / `setPrivacy()` | `GET/POST /api/homecore/privacy` | SEED privacy control plane ([ADR-141](ADR-141-bfld-privacy-control-plane-modes-attestation.md)) + cog-ha-matter | **SEED-DEV** |
+| §4.9 Export bundle | `exportAttestation()` | `GET /api/homecore/witness/export` | gateway packages both chains | **NEW-GW** |
+| §4.10 Tokens (LLAT) | `tokens()` / `createToken()` / `revokeToken()` | `GET/POST/DELETE /api/homecore/tokens` | `homecore-api` `LongLivedTokenStore` | **NEW-API** |
+| §4.10 MQTT/Matter | `mqttConfig()` | `GET /api/homecore/integrations/mqtt` | cog-ha-matter config ([ADR-116](ADR-116-cog-ha-matter-seed.md)) | **NEW-GW/SEED-DEV** |
+| §4.10 ESP32 provisioning | `nodes()` / `assignRoom()` | `GET/PUT /api/homecore/nodes` | SEED ingest config ([ADR-069](ADR-069-cognitum-seed-csi-pipeline.md)) | **SEED-DEV** |
+| §4.10 SEED mgmt | `pairSeed()` / `rotateToken()` | `POST /api/homecore/seeds/{pair,:id/rotate-token}` | SEED pairing (USB `169.254.42.1`) | **SEED-DEV** |
+
+### 11.3 Calibration proxy + RoomState adapter
+
+The calibration service is real but on a different binary/port; the gateway reverse-proxies it under `/api/cal/*` (upstream base from `HOMECORE_CALIBRATION_URL`). Its `RoomState` (`wifi-densepose-calibration/src/runtime.rs`) does **not** match the UI's shape, so the gateway adapts it in `GET /api/homecore/rooms`:
+
+| Real field (`RoomState`) | UI field | Adapter rule |
+|---|---|---|
+| `breathing: Option<SpecialistReading>` | `breathing_bpm: {value,confidence}\|null` | rename; `value`=`reading.value`, `confidence`=`reading.confidence`; `None`→`null` (preserves "not trained") |
+| `heartbeat: Option<…>` | `heart_bpm: {…}\|null` | rename `heartbeat`→`heart_bpm` |
+| `presence/posture/restlessness` | same names `{value,confidence}\|null` | `posture.value`=`reading.label` (class), else numeric |
+| `anomaly: Option<…>` | `anomaly: {value,confidence,threshold}` | inject `threshold`=`MixtureOfSpecialists.veto_threshold` (0.5) |
+| `vetoed` / `stale` | `vetoed` / `stale` | pass through (drives the §4.5/§6 banners) |
+| *(absent)* | `room_id`, `seeds[]` | injected by the gateway from the **room registry** |
+
+A **room registry** (config or derived from `GET /api/cal/v1/calibration/baselines`) maps each `room_id` → bank name + serving SEED ids, so `GET /api/homecore/rooms` returns one adapted record per room. `Option::None` → JSON `null` keeps the null-vs-withheld distinction (§6 invariant 3) intact end-to-end.
+
+### 11.4 SEED registry & device-API proxy
+
+The gateway holds a **SEED registry** (`device_id` → base URL + bearer token + zone), populated by pairing (§4.10) and persisted server-side. `GET /api/homecore/seeds[/:id]` fans out to each SEED's on-device API and shapes the result to the §4.2 card/detail model. Expected SEED-side endpoints (the contract the SEED firmware must satisfy — a subset of its 98 endpoints): health; vector-store stats (`vector_count`, `dim`, `epoch`, `knn_latency_ms`, ingest rate); witness (`len`, `last_verify`, `valid`) + `POST verify`; onboard sensors (BME280/PIR/reed/ADS1115/vibration); reflex rules + thresholds; cognitive analysis (fragility, coherence phases); ingest feeders (ESP32 node ids + packet type `0xC5110003`/`0xC5110002` + rate). Offline/unreachable SEEDs surface as `online:false` (drives the §4.1 red tint) rather than failing the whole list.
+
+### 11.5 Appliance metrics collector (§4.1)
+
+`GET /api/homecore/appliance`, implemented in the gateway: CPU/RAM/uptime from `/proc`; Hailo load + temperature from the Hailo runtime/sysfs (or `ruvector-hailo-worker` stats); service health by probing `ruview-mcp-brain:9876`, `cognitum-rvf-agent:9004`, `ruvector-hailo-worker:50051`; event-bus rate from the `homecore` broadcast channel + its lag counter (already exposed for §4.1/§4.4).
+
+### 11.6 COG supervisor (§4.6)
+
+`GET /api/homecore/cogs`: read each `/var/lib/cognitum/apps/*/manifest.json` ([ADR-100](ADR-100-cog-packaging-specification.md)), the pid file, and verify `binary_sha256` + `binary_signature` (Ed25519) → status/shield. `POST …/cogs/:id/{start,stop,restart}` performs supervised process control; `GET …/cogs/:id/logs` tails `output.log`/`error.log`; `GET/PUT …/cogs/:id/config` reads/writes `config.json`. Hailo-arch COGs join the §11.5 Hailo stats. The Cog Store/App-Registry **browsing** panel was removed per product decision; this is operational management only.
+
+### 11.7 Witness aggregation + privacy (§4.9)
+
+`GET /api/homecore/witness` merges two chains chronologically: the `homecore` Ed25519 state-transition chain (exposed by a small `homecore-api` route over its witness log) and each paired SEED's SHA-256 ingest chain (proxied via the registry), paginated server-side. `GET/POST /api/homecore/privacy` reads/sets per-SEED privacy mode via the SEED privacy control plane ([ADR-141](ADR-141-bfld-privacy-control-plane-modes-attestation.md)) — the POST is the high-stakes confirmed toggle (§4.9). `GET /api/homecore/witness/export` packages both chains into the downloadable attestation bundle.
+
+### 11.8 Event history + automation CRUD (§4.8)
+
+`homecore-api` adds `GET /api/events?since=…` backed by `homecore-recorder` ([ADR-132](ADR-132-homecore-recorder-history-semantic-search.md)) for history (live updates continue over the existing WS). The automation builder persists through `GET/POST/DELETE /api/homecore/automations`, a thin HTTP wrapper over the `homecore-automation` engine's register/list/remove ([ADR-129](ADR-129-homecore-automation-engine.md)). RuView-specific triggers (RoomState thresholds, SEED reflex events) map onto the engine's trigger types.
+
+### 11.9 Entity provenance convention (§4.4/§6)
+
+The first-class provenance badge requires each entity to carry its lineage. Convention: every integration writes `attributes.source` (and, where known, `attributes.seed` / `attributes.cog`) when it sets state; `cog-ha-matter` ([ADR-116](ADR-116-cog-ha-matter-seed.md)) populates these from the ESP32 node → SEED → COG path and HA `via_device`. The gateway/UI resolves node→seed→cog from these attributes (no fabrication; missing lineage renders as "unknown", not invented).
+
+### 11.10 Auth, credentials, config
+
+- **Browser → gateway:** one long-lived access token (the §4.10 LLAT), sent as `Authorization: Bearer`; validated by `homecore-api`'s `LongLivedTokenStore`. The dev default (`allow_any_non_empty`) stays for local runs; production provisions `HOMECORE_TOKENS`.
+- **Gateway → upstreams:** SEED bearer tokens and the calibration token live **only** server-side (SEED registry + `HOMECORE_CALIBRATION_TOKEN`); never sent to the browser. This is the reason the gateway exists.
+- **Config:** `HOMECORE_CALIBRATION_URL`, SEED registry store path, per-proxy timeout (default 2 s), `HOMECORE_UI_DEMO` (dev fixture). No browser CORS needed (same origin); gateway→upstream is server-to-server.
+
+### 11.11 Front-end changes
+
+`api.js`: drop the mock fallback from the production path — methods call the §11.2 gateway routes; `this.base` stays same-origin; the mock layer is reachable only under `?demo=1`/`HOMECORE_UI_DEMO`. Every panel renders a **typed empty/error state** (not mock) when its route returns `503/504`. `mock.js` moves to a dev fixture (kept for the offline test harness, excluded from the production bundle). The §10 frontend tests are re-pointed at the gateway contract (and gain contract tests per §11.2 route).
+
+---
+
+## 12. Delivery plan to full functionality
+
+Staged so each wave is independently shippable behind the gateway, lands real data for a coherent set of panels, and has an explicit acceptance gate. "Class" reuses §11's tags.
+
+| Wave | Scope | Class | Acceptance gate |
+|---|---|---|---|
+| **W1 — Gateway foundation** | `/api/homecore/*` scaffold in `homecore-server`; auth passthrough; per-proxy timeout + typed errors; `api.js` base + remove prod mock (`?demo=1` only); panels get typed empty/error states | NEW-GW | Entities + live WS still green; with no upstreams, every other panel shows "upstream unavailable", **never** mock (unless `?demo=1`); Rust + JS suites pass |
+| **W2 — Rooms + Calibration** | `/api/cal/*` reverse-proxy; `GET /api/homecore/rooms` with the §11.3 RoomState adapter + room registry; wire §4.5 + the §4.7 wizard to real endpoints; delete the in-browser calibration stub | EXISTS (proxy+adapter) | Against a running `calibrate-serve` (replayed CSI), the wizard drives a real baseline→enroll→train→verify and §4.5 shows real `RoomState` with correct stale/veto/null mapping; contract test on the adapter |
+| **W3 — Events + Automations** | `GET /api/events` over `homecore-recorder`; `/api/homecore/automations` over `homecore-automation` | NEW-API | §4.8 history loads from recorder; an automation created in the UI persists and fires via the engine |
+| **W4 — COG management** | `/api/homecore/cogs*` supervisor over `/var/lib/cognitum/apps/` (manifest + pid + sig verify + logs + config) | NEW-GW | §4.6 lists real installed COGs; start/stop/restart works; sha256/signature shield reflects real verification; logs tail |
+| **W5 — SEED tier** | SEED registry + pairing; `/api/homecore/seeds*` device proxy; witness merge + privacy control; ESP32 provisioning | SEED-DEV | Against a real or emulated SEED API, §4.2/§4.3/§4.9/§4.10 show real vector-store/witness/sensor/reflex/cognition data; SEED tokens stay server-side; offline SEED → red tint, not a failed page |
+| **W6 — Appliance + federation + Hailo** | `/api/homecore/appliance` (host metrics + service probes); `/api/homecore/hailo`; `/api/homecore/federation` ([ADR-105](ADR-105-federated-csi-training.md)) | NEW-GW + APPLIANCE | §4.1 health is real; §4.6 Hailo HEF/throughput real; §4.3 federation round/coordinator/Krum real |
+
+**Definition of done (full functionality):** with W1–W6 merged and the upstream tiers running, loading `/homecore` with **no** `?demo=1` flag shows live data on all ten panels, `api.anyDemo()` is false, and no panel renders fabricated values. Panels whose tier is offline show typed empty/error states. The mock layer is reachable only as the `?demo=1` developer fixture.
+
+### 12.1 Wave status (this revision)
+
+| Wave | Status |
+|---|---|
+| **W1 — Gateway foundation** | ✅ DONE — `gateway.rs`, auth passthrough, typed `503/504`, merged into `build_app`; front-end mock removed from prod path + `?demo=1` fixture; typed error states. **Compiled + 12/12 Rust tests + JS suite green + run live.** |
+| **W2 — Rooms + Calibration** | ✅ DONE — `/api/cal/*` reverse-proxy + `GET /api/homecore/rooms` RoomState adapter; front-end calibration stub deleted (now proxies the real API). **Proven live against a calibration upstream** (proxy 200 + adapted shape); null-preservation unit-tested. |
+| **W3 — Events + Automations** | ⏳ gateway returns typed `503` (recorder/automation HTTP wrappers pending); front-end handles it gracefully (history note, builder still usable). |
+| **W4 — COG management** | ✅ supervisor DONE — lists `/var/lib/cognitum/apps/` manifests + pid liveness (returns `[]` live with no apps dir); start/stop/log/config control is the remaining follow-up. |
+| **W5 — SEED tier** | ⏳ gateway returns typed `503` (SEED registry + device proxy pending real/emulated SEED hardware). |
+| **W6 — Appliance + federation + Hailo** | ◑ appliance host metrics from `/proc` + port probes DONE (live `/proc` data verified); Hailo stats + federation remain `503` (need the accelerator stat source / coordinator). |
+
+**Status:** the gateway is **compiled and tested on Rust 1.89** (`cargo test -p homecore-server` = 12/12) and was **run live** (curl proof in §10). The one remaining caveat is intrinsic, not an environment limit: **W3/W5/W6-Hailo/federation depend on services/hardware that are not in this repo** (recorder/automation HTTP wrappers, real SEED nodes, the Hailo stat source), so they return honest typed `503`s and the UI shows error states — exactly as §2.2/§11.2 prescribe. W1/W2/W4/W6-appliance are functional now.
+
+### 12.2 Security review (PR #1082)
+
+A high-effort public-PR review of the merged gateway + front-end surfaced the following, all fixed and pinned by tests (`cargo test -p homecore-server` is now **18/18**):
+
+| # | Severity | Finding | Fix |
+|---|---|---|---|
+| 1 | **HIGH** | **Path-traversal / confused-deputy SSRF** in the `/api/cal/*` reverse-proxy. The wildcard path was interpolated into the upstream URL while `proxy()` attaches the privileged server-side calibration bearer, so `/api/cal/v1/../../x` (or `..%2f`, `%2e%2e`, leading `/`, `\`, double-encoded `%252e`) could escape the `…/api/` scope **with the token**. | `validate_proxy_path()` decode-then-checks and rejects absolute / backslash / dot-segment / encoded-traversal paths with a typed **400 before the URL is built** (GET **and** POST); legit `v1/...` paths still pass. |
+| 2 | Correctness | **CORS + tracing didn't cover gateway routes** — `/api/homecore/*` + `/api/cal/*` were `.merge()`d outside `homecore-api::router()`'s layers. | The audited HC-05 `build_cors_layer()` + `TraceLayer` are now applied to the whole merged app in `main.rs`. |
+| 3 | Honesty (§6) | **Fabricated data** — hardcoded `anomaly.threshold: 0.5` in the adapter; dashboard rendered `"null%"`/`"null°C"`; COG Hailo pill hardcoded `"connected"`; `rooms.js` defaulted a null threshold to `0.8`. | Threshold passes through the real upstream value or emits `null` (withheld); dashboard renders `—`; the Hailo pill reflects the real appliance probe; the UI treats a null threshold as withheld. |
+| 4 | Robustness | A string `hef` (forwarded verbatim) threw on `.forEach`/`.join`; `frames/target` could be `NaN%`/`Infinity%`; calibration Restart leaked the baseline `setTimeout` poll. | `asArray()` coercion; `target > 0` guard; cancellable poll cleared on Restart / panel teardown. |
+| 5 | Perf | Sequential per-bank RoomState fetches; blocking `std::net::TcpStream::connect_timeout` probes on an async handler; `mock.js` statically bundled. | Concurrent `futures::join_all`; async `tokio::net::TcpStream` + `timeout`; demo-only dynamic `import()` of `mock.js`. |
+
+**Known limitations carried forward (not regressions):**
+- **`reqwest` rustls-only is a workspace-wide concern.** `homecore-server` opts into `rustls-tls` only, but cargo feature-unification means any sibling crate enabling the default `native-tls` re-introduces OpenSSL into the final binary. A true "no OpenSSL on the appliance" guarantee requires aligning **every** reqwest-pulling crate on rustls-only — out of scope for this PR; documented at the dependency in `Cargo.toml`.
+- **DEV-mode auth.** When `HOMECORE_TOKENS` is unset, the token store falls back to `allow_any_non_empty()` (any non-empty bearer accepted) on `0.0.0.0`. This is pre-existing and intentionally **unchanged** here; the loud boot `warn!` is retained. Provision real tokens (`HOMECORE_TOKENS=…`) before exposing the server to a network.
@@ -0,0 +1,166 @@
+# ADR-132: HOMECORE-RECORDER — State History + Semantic Search
+
+| Field | Value |
+|-------|-------|
+| **Status** | Accepted |
+| **Date** | 2026-05-25 |
+| **Deciders** | ruv |
+| **Codename** | **HOMECORE-RECORDER** |
+| **Crate** | `v2/crates/homecore-recorder` |
+| **Relates to** | [ADR-126](ADR-126-ruview-native-ha-port-master.md) (HOMECORE master — series map row ADR-132), [ADR-127](ADR-127-homecore-state-machine-rust.md) (HOMECORE-CORE state machine), [ADR-124](ADR-124-rvagent-mcp-ruvector-npm-integration.md) (ruvector/SENSE-BRIDGE), [ADR-130](ADR-130-homecore-rest-websocket-api.md) (HOMECORE-API query surface, downstream) |
+| **Tracking issue** | [#800](https://github.com/ruvnet/RuView/pull/800) (HOMECORE intake) |
+
+> **Documented retroactively (2026-06-12).** The `homecore-recorder` crate shipped under
+> the ADR-126 series map (which planned an "ADR-132 HOMECORE-RECORDER") but the standalone
+> ADR file was never written; the crate's `Cargo.toml`, `README.md`, `lib.rs`, `schema.rs`,
+> and `semantic.rs` all cite "ADR-132". This ADR reverse-documents the decision that the
+> shipped, tested code already embodies (ADR-164 Gap G3 / Coverage-Gaps Lens §A). It does
+> **not** introduce new design; it records what is built. Date reflects the crate's intake
+> era (first commit `e96ebaea8`, 2026-05-25); real-impl pass landed in `7c8071145`
+> (2026-06-11).
+
+---
+
+## 1. Context
+
+ADR-126 (the HOMECORE master) decided to reimplement Home Assistant (HA) natively in Rust.
+HA persists every state change to a SQLite *recorder* database; downstream features
+(history graphs, the logbook, long-term statistics, automation conditions that reference
+past state) all read that store. HOMECORE therefore needs a durable state-history backbone.
+
+Two forces shape the decision:
+
+1. **Migration / coexistence.** Users adopting HOMECORE will have an existing HA
+   `recorder` database. Reusing HA's on-disk schema (rather than inventing a new one) lets
+   HOMECORE read an existing HA `home-assistant_v2.db` directly and lets HA-aware tooling
+   read HOMECORE's store. This is the same trust boundary that `homecore-migrate`
+   (ADR-165) handles for `.storage/*.json`.
+2. **Semantic queries.** HA history is queried with SQL `BETWEEN`/`WHERE` clauses. The
+   HOMECORE platform already carries ruvector (ADR-124) for vector search, so the recorder
+   can additionally embed state changes and answer natural-language queries
+   ("which kitchen devices were warm at 3 PM?") via k-NN — a capability HA does not have.
+
+The recorder is the **durable-state surface**: if it is wrong, history, logbook, and
+historical-condition automations are all wrong. ADR-164 flagged it as a CRITICAL coverage
+gap precisely because such a load-bearing crate had no governing ADR.
+
+## 2. Decision
+
+Ship `homecore-recorder` as a SQLite state-history recorder with an HA-compatible schema
+and an optional ruvector-backed semantic index, in three phases. P1 and P2 are built and
+tested; P3 is planned.
+
+### 2.1 Storage — SQLite with the HA recorder schema (P1, shipped)
+
+- Persist via `sqlx` with the SQLite backend only (no Postgres, no TLS feature set).
+- Mirror HA recorder **schema v48** so the store is bidirectionally readable
+  (`src/schema.rs`):
+  - `state_attributes` — shared attribute JSON blobs, deduped by an FNV-1a 64-bit hash
+    stored as a signed `i64` (matches HA's dedup key);
+  - `states` — one row per state write (`entity_id`, `state`, `attributes_id` FK,
+    `last_changed_ts`/`last_updated_ts` as REAL Unix seconds, `context_id` UUID);
+  - `events` — domain events (`event_type`, `event_data` JSON, `time_fired_ts`);
+  - `recorder_runs` — boot/shutdown bookends for history-gap detection.
+- All DDL uses `CREATE TABLE IF NOT EXISTS`, so schema application is idempotent and safe
+  on every startup.
+- Default persistence path `.homecore/home.db` (configurable).
+
+### 2.2 Capture — listener on the HOMECORE event bus (P1, shipped)
+
+- `RecorderListener` subscribes to the HOMECORE event bus (ADR-127) and captures
+  `StateChanged` events, writing snapshots through `Recorder` (`src/listener.rs`,
+  `src/db.rs`).
+- A `DedupEngine` (`src/dedup.rs`) skips redundant writes when the state hash is unchanged,
+  matching HA's stateful-listener behaviour.
+
+### 2.3 Semantic search — ruvector HNSW (P2, shipped, feature-gated)
+
+- Behind the `ruvector` Cargo feature, the `Recorder` additionally calls a `SemanticIndex`
+  implementation (`src/semantic.rs`) that embeds state attributes and stores vectors in a
+  `ruvector-core` HNSW index for k-NN search.
+- P2 embeddings are **hash-based** (sha2) — a deliberate, honest placeholder. They give a
+  working HNSW surface without claiming sentence-level semantic quality.
+- When the feature is off, `NullSemanticIndex` satisfies the `SemanticIndex` trait bound
+  with no allocation, so the structural recorder ships independently of ruvector.
+
+### 2.4 Real sentence embeddings (P3, planned — not yet built)
+
+- Replace the hash embeddings with ruvector-attention sentence embeddings (dim → 384). Not
+  implemented; tracked as a follow-up. The README and `Cargo.toml` label this P3 explicitly.
+
+### 2.5 Test evidence (as shipped)
+
+- P1: 14 tests (`cargo test -p homecore-recorder --no-default-features`).
+- P2: 20 tests (`cargo test -p homecore-recorder --features ruvector`).
+
+## 3. Consequences
+
+**Positive.**
+
+- HA-schema compatibility makes migration (ADR-165) and coexistence cheap: HOMECORE can
+  read an existing HA `recorder.db`, and any SQLite tool can read HOMECORE's history.
+- The semantic index is **additive** and feature-gated: the durable structural recorder has
+  no hard dependency on ruvector, so the storage backbone ships first.
+- Standard SQLite means no proprietary export format; history is directly queryable.
+
+**Negative / honest limits.**
+
+- P2 semantic search uses **hash embeddings**, not real sentence embeddings — query quality
+  is limited until P3. This is disclosed in the crate docs and here; it must not be cited as
+  semantic-quality-validated.
+- No per-crate benchmarks exist yet; the latency figures in the README
+  (state-write p50 < 2 ms, semantic search < 10 ms on 1 M records) are design targets /
+  estimates, **needs verification** with a criterion baseline.
+- Pinning to HA schema v48 couples HOMECORE to a specific HA recorder schema generation;
+  future HA schema bumps require an explicit migration step.
+
+**Neutral.**
+
+- This ADR governs the recorder crate only. The query/REST surface over recorder data is
+  HOMECORE-API (ADR-130, P3); automation conditions on historical state are
+  HOMECORE-automation (ADR-129, P3).
+
+## 3a. Security review (2026-06, post-ADR-154–159 sweep)
+
+A beyond-SOTA security review of `homecore-recorder` covered SQL injection, retention/purge
+correctness, fail-closed write integrity, semantic-store NaN poisoning, and PII exposure.
+
+**Confirmed clean (with evidence):**
+
+- **SQL injection — clean.** Every query in `db.rs` uses bound `?` parameters; no user- or
+  entity-influenceable value is interpolated into SQL via `format!`/concatenation. The only
+  `format!` builds the `LIKE` *pattern* string, which is itself **bound** as a parameter with
+  `ESCAPE '\\'` and `% _ \` escaping — so a metacharacter payload is matched literally. Pinned
+  by `malicious_entity_id_is_stored_literally_not_executed` (a `'; DROP TABLE states; --` state
+  value leaves the table intact and round-trips verbatim) and
+  `like_metacharacters_in_query_are_literal_not_wildcards`.
+- **NaN-index poisoning — structurally impossible.** Embeddings are SHA-256 → `i32` →
+  `f32`; an `i32`→`f32` cast is always finite (never NaN/Inf), and an all-zero-digest is
+  guarded by the `norm > 1e-10` check. Empty-index search, empty-string query, and `k=0` were
+  probed and all return `Ok(0)` with no panic. (Unlike the calibration/vitals/geo paths, no raw
+  sensor float ever reaches the index.)
+- **Fail-closed writes.** A removal event returns `Ok(None)`; semantic-index failure is logged,
+  not propagated, so it never blocks the durable SQLite write; `EntityId` parse failure falls
+  back to a sentinel rather than panicking.
+
+**Fixed (real bounding bugs):**
+
+- **Memory-DoS — `get_state_history` was unbounded.** No `LIMIT`, so a wide time window over a
+  high-frequency entity loaded an unbounded row set into memory. Now capped at
+  `MAX_HISTORY_ROWS` (1,000,000); sibling search paths were already `k`-bounded.
+- **Disk-DoS / documented-but-missing `purge`.** The README advertised `Recorder::purge`, but
+  no retention path existed → unbounded disk growth. Added a **transactional** `purge(older_than)`
+  with an **exclusive** cutoff (idempotent, no off-by-one) that deletes old `states`/`events` and
+  GCs orphaned `state_attributes` blobs (dedup-shared blobs kept until their last referrer is gone).
+
+`homecore-recorder` tests: 19 → 25 (`--no-default-features`) / 25 → 31 (`--features ruvector`),
+0 failed. Python deterministic proof unchanged (recorder is off the signal proof path).
+
+## 4. Links
+
+- Crate: `v2/crates/homecore-recorder/` — `Cargo.toml`, `README.md`, `src/lib.rs`,
+  `src/db.rs`, `src/schema.rs`, `src/dedup.rs`, `src/listener.rs`, `src/semantic.rs`.
+- [ADR-126](ADR-126-ruview-native-ha-port-master.md) — HOMECORE master (series map: ADR-132 = HOMECORE-RECORDER).
+- [ADR-165](ADR-165-homecore-migrate-from-home-assistant.md) — HOMECORE-MIGRATE (reads HA `.storage`; P2 exports a side-by-side recorder DB).
+- [ADR-164](ADR-164-adr-corpus-gap-analysis.md) — gap analysis that surfaced this missing ADR (Gap G3).
+- [Home Assistant Recorder integration](https://www.home-assistant.io/integrations/recorder/).
@@ -174,3 +174,71 @@ vs. an in-memory array at compile time), which intersects with ADR-084 (RabitQ)
 | **P1** (this ADR) | `intent`, `recognizer` (regex), `handler` (5 built-ins), `runner` (trait + noop), `pipeline` (end-to-end wiring), 10–15 tests |
 | **P2** | Real `tokio::process::Child` runner with Windows-safe teardown; `SemanticIntentRecognizer` with ruvector HNSW |
 | **P3** | STT/TTS bridge, satellite protocol, cloud fallback |
+
+---
+
+## 6. Security review (beyond-SOTA, untrusted-input → action path)
+
+A focused security review of the Assist pipeline — `utterance → recognizer →
+intent → handler → action`, plus `RufloRunner` — treating the utterance as
+untrusted input (voice transcripts, the WebSocket `assist` command). This
+surface was not covered by the ADR-154–159 sweep.
+
+### 6.1 Finding fixed — HC-ASSIST-01 (unbounded-utterance DoS, LOW)
+
+Both `RegexIntentRecognizer::recognize` and the semantic `recognize_scored`
+accepted utterances of **unbounded length** and ran `to_lowercase()` (a full
+clone) + a per-registered-pattern scan (and, in the semantic path, full
+tokenisation + feature-hash embedding) before any bound — an allocation/CPU
+amplification on attacker-controlled input. The `regex` crate is **linear-time**
+(RE2-style finite automaton, no catastrophic backtracking), so this was a
+throughput/memory DoS, not a hang.
+
+**Fix:** `MAX_UTTERANCE_BYTES = 4096` (far above any real spoken command),
+checked at **both** recognizer boundaries *before* any allocation/scan. An
+over-length utterance **fails closed** to `Ok(None)` — no intent, no action,
+identical to an unrecognised phrase — so it can never be coerced into firing a
+handler. Pinned by `over_length_utterance_fails_closed` (an over-length
+utterance that *contains* a valid command resolves to `None`, which would have
+matched on the old code) and `over_length_utterance_fails_closed_semantic`.
+
+### 6.2 Dimensions confirmed clean (with evidence)
+
+- **Command / argument injection — NO SUBPROCESS SURFACE.** The `RufloRunner`
+  has exactly two impls: `NoopRunner` (no process) and `LocalRunner` (runs the
+  local recognizer, no process). There is **no** `std::process` / `tokio::process`
+  / `Command` / process `.spawn()` anywhere in the crate — the trait `spawn` is
+  only a `started: bool` lifecycle flag — and `RufloRunnerOpts.{script_path,env}`
+  are **inert data, never consumed**. The live `node ruflo-agent.js` runner is
+  genuinely data-gated/future (P2). Defence-in-depth: the `entity_id` capture
+  class `[a-z_][a-z0-9_ .]*` **excludes every shell/SQL metacharacter**, so even
+  when an injection-shaped utterance resolves (the regex is not exact-anchored),
+  the captured slot is a clean token — sanitisation by construction. Pins:
+  `shell_metachars_never_survive_into_a_resolved_slot`,
+  `runner_opts_are_inert_no_process_spawned`,
+  `pipeline_injection_shaped_utterance_carries_no_metachars_to_service`.
+- **ReDoS — STRUCTURALLY IMPOSSIBLE.** `regex 1.12.3` (no `fancy-regex` in the
+  dependency tree) is linear-time; a classic `(a+)+$` shape on adversarial input
+  completes in bounded time. Pin:
+  `pathological_backtracking_pattern_completes_in_bounded_time`. Patterns are
+  operator-registered, not user-supplied, in any case.
+- **NaN-poisoning — EMBEDDINGS STRUCTURALLY FINITE.** The embedding path takes
+  only `&str` and produces values via FNV feature-hashing + a guarded L2
+  normalise (`norm > 1e-12`); no external float input, no unguarded division, so
+  a crafted utterance cannot inject NaN/Inf to poison the cosine k-NN. Cosine
+  against the zero vector is a finite `0.0`; an empty index `max_by` returns
+  `None` (no panic); the NaN-safe `partial_cmp().unwrap_or(Equal)` is already in
+  place. Pins: `embeddings_are_structurally_finite`,
+  `cosine_with_zero_vector_is_finite_not_nan`,
+  `empty_utterance_against_empty_index_no_panic_no_match`.
+- **Intent confusion / fail-closed.** An unrecognised utterance → `not_understood()`
+  (no service call); a recognised intent with no registered handler →
+  `not_understood()`; semantic below-threshold / empty-index → regex fallback.
+  No default high-privilege intent, no fail-open path.
+- **Panic-on-input.** No `unwrap`/`expect`/index reachable from a crafted
+  utterance; the one `exemplars[id]` index uses an `id` from `enumerate()` over
+  the append-only exemplar `Vec` (no remove API), so it is always in bounds.
+
+`cargo test -p homecore-assist --no-default-features`: **29→36, 0 failed** (+7);
+default/`semantic`: **39→48, 0 failed** (+9). Python deterministic proof
+unchanged (homecore-assist is off the signal proof path).
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see §8 Implementation Status, commit `11f89727f`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-core` (`types.rs`: `CsiFrame`/`CsiMetadata`); `wifi-densepose-signal/src/ruvsense/mod.rs` (`RuvSensePipeline`, six-stage flow); `v2/Cargo.toml` (workspace topology) |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `4fa3847ac`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-signal` (`ruvsense/multistatic.rs` — `fuse`, `attention_weighted_fusion`); `wifi-densepose-ruvector` (`viewpoint/fusion.rs` — `MultistaticArray`); `wifi-densepose-bfld` (`event.rs`) |
@@ -495,3 +495,34 @@ Rejected. `ViewpointFusionEvent` (viewpoint/fusion.rs lines 183–219) is an int
 **Integration glue -- not yet on the live path:** emission of `CalibrationIdMismatch` / `DriftProfileConflict` / `PhaseAlignmentFailed` once `calibration_id` propagation and the phase-align convergence signal are threaded onto frames; the BFLD witness record emitted on privacy demotion.

 **Trust contribution:** sensor *agreement made explicit* -- fusion records the evidence it relied on, and any disagreement automatically tightens the downstream privacy class.
+
+---
+
+## Witness Integrity Review (2026-06-14) — domain-separation fix
+
+A beyond-SOTA security review of `wifi-densepose-engine` (the composition root
+that builds the §2.7 trust witness in `witness_of`) found a real **witness
+domain-separation gap**, now fixed.
+
+**Finding (witness-gap, HIGH).** `witness_of` concatenated `model_version`,
+`calibration_version`, and `privacy_decision` boundary-to-boundary, and the
+variable-length `evidence` list carried no explicit count. A string straddling a
+field boundary therefore collided with a *different* trust decision —
+e.g. a per-room adapter id (ADR-150 §3.4, operator-influenceable) that absorbs
+the leading bytes of the calibration epoch (`model="…cal:00a"`, `cal="b"`)
+produces the **same** witness as `model="…"`, `cal="cal:00ab"`. Two distinct
+privacy-relevant input tuples → one witness defeats the "any privacy-relevant
+delta → different witness" guarantee this ADR's §2.7 witness exists to provide.
+
+**Fix.** The witness now (a) prepends a domain tag `ruview.engine.witness.v1`,
+(b) writes an explicit 8-byte evidence count, and (c) **length-prefixes every
+field** (8-byte LE length ‖ bytes), so field framing is unambiguous regardless
+of contents. This is a witness-layout change (all prior witness bytes are
+invalidated by design); downstream consumers only assert witness *relationships*
+(`assert_ne`/`assert_eq` across runs), not absolute bytes, so nothing breaks.
+
+Pinned by `witness_distinguishes_model_calibration_boundary` and
+`witness_distinguishes_evidence_model_boundary` (both fail on the old
+concatenation). Witness **determinism** was reviewed and confirmed clean: no
+HashMap iteration and no float formatting feed the hash (floats appear only in
+the `SemanticState` statement, which is outside the witness).
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `fc7674bde`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-signal` (`ruvsense/multiband.rs`, `ruvsense/multistatic.rs`); `wifi-densepose-ruvector` (`viewpoint/geometry.rs`, `viewpoint/coherence.rs`, `viewpoint/attention.rs`, `viewpoint/fusion.rs`) |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `521a012d8`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | New module/crate `wifi-densepose-worldgraph` alongside `v2/crates/wifi-densepose-geo` and `v2/crates/homecore`; petgraph bridge pattern from `v2/crates/ruv-neural/ruv-neural-graph/src/petgraph_bridge.rs`; integrates `homecore/src/registry.rs` `area_id` and `wifi-densepose-mat/src/domain/scan_zone.rs` |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `169a355bd`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-sensing-server/src/semantic/` (`bus.rs`, `common.rs`); `homecore/src/state.rs` + `event.rs`; `homecore-assist` |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `7d88eb84c`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-bfld` (new module `mode.rs` + `attestation.rs`; extends `lib.rs` `PrivacyClass`, `sink.rs`, `privacy_gate.rs`, `identity_risk.rs`, `emitter.rs`, `ha_discovery.rs`) |
@@ -599,3 +599,53 @@ Per ADR-028/ADR-010, three rows are added to the witness log:
 **Integration glue -- not yet on the live path:** wiring the registry into `PrivacyGate` class transitions, the MQTT discovery payload, and a read-only Home Assistant diagnostic entity exposing the active mode + proof hash.

 **Trust contribution:** the *policy spine* -- privacy posture is a tamper-evident, auditable chain rather than a checkbox; an operator's mode choice actively governs whether identity data may even exist.
+
+---
+
+## Privacy Monotonicity Review (2026-06-14) — confirmed clean
+
+A beyond-SOTA security review of the governed-trust cycle
+(`wifi-densepose-engine::StreamingEngine::process_cycle_calibrated`) examined
+the privacy-demotion path this ADR governs. **The monotonicity invariant holds:
+demotion only ever makes the emitted class more restrictive, never less.**
+
+Verification (no behaviour change, the result is a clean bill with evidence):
+
+- Each cycle computes `effective_class` fresh from the active mode's
+  `target_class()` (the floor) and applies at most a **single-step** demotion
+  (`demote_one`, clamped at `Restricted`). There is no cross-cycle state that
+  could let a permissive class overwrite a restrictive one.
+- A forced contradiction (calibration mismatch / array-geometry insufficiency /
+  mesh partition risk, ADR-032) raises the class byte; a clean cycle emits
+  exactly the base class.
+- Pinned by `forced_contradiction_never_relaxes_class`, a property test over
+  **all five** `PrivacyMode`s asserting `effective_class.as_u8() >=
+  base_class.as_u8()` (strictly greater unless already clamped at `Restricted`)
+  under a forced contradiction, and `== base` on a clean cycle.
+
+Fail-closed boundaries were also pinned: an empty cycle errors (no degenerate
+over-permissive output, `empty_cycle_fails_closed`) and the single-node boundary
+is characterized as a valid non-demoting mode (`single_node_cycle_is_well_formed`).
+
+The related witness domain-separation fix from the same review is recorded in
+ADR-137 (the witness folds `effective_class`, so the demotion is auditable).
+## Security & Privacy Review (2026-06-14)
+
+Beyond-SOTA privacy+security review of `wifi-densepose-bfld` (the crate was not in the ADR-154–159 sweep). Two real bugs fixed (each pinned by a fails-on-old test), several dimensions confirmed clean.
+
+### Findings
+
+| # | Severity | Site | Issue | Fix | Pinned by |
+|---|----------|------|-------|-----|-----------|
+| 1 | **privacy-bypass (HIGH)** | `pipeline.rs::process_to_frame` | The documented wire-bytes production path stamped the frame header with the active `PrivacyClass` but serialized the caller's `BfldPayload` **unchanged** via `BfldFrame::from_payload` — never routing through `PrivacyGate::demote`. A frame labeled `Anonymous`(2)/`Restricted`(3) carried the full `compressed_angle_matrix` (identity surface) + amplitude/phase + `csi_delta`. A `NetworkSink` accepts class ≥ `Derived`(1), so the identity surface could cross the node boundary despite the restrictive class byte — the byte lied about content. | Apply `PrivacyGate::demote(frame, active_class)` after construction: a same-class transition that strips the sections the class forbids; `Raw`/`Derived` keep the full payload. | `tests/pipeline_to_frame.rs::process_to_frame_at_anonymous_strips_identity_leaky_sections`, `…_in_privacy_mode_strips_amplitude_and_phase` (both FAILED pre-fix); `…_at_derived_preserves_full_payload` (over-strip guard) |
+| 2 | **PII/injection (MEDIUM)** | `mqtt_topics.rs::render_events` | `zone_activity` payload built as `format!("\"{zone}\"")` with no JSON escaping (while `ha_discovery.rs` already escapes). A zone name with `"`/`\` produced malformed/injectable JSON on the HA state topic. | `json_string_literal()` escaper mirroring `ha_discovery::push_str_field`. Value-identical for normal zone names. | `tests/mqtt_topic_routing.rs::zone_payload_escapes_json_metacharacters` (FAILED pre-fix) |
+
+### Dimensions confirmed clean (with evidence)
+
+- **Event-field privacy gating** — `BfldEvent::apply_privacy_gating` nulls `identity_risk_score` + `rf_signature_hash` at `Restricted`, and `serde(skip_serializing_if = "Option::is_none")` omits them entirely. `render_events`/`render_discovery_payloads` refuse class < `Anonymous` (stricter than the `sink.rs` `NetworkKind` `MIN_CLASS = Derived` — defense in depth toward less leakage). Covered by `event_privacy_gating.rs`, `mqtt_topic_routing.rs`, `ha_discovery.rs`.
+- **Witness/hash framing (the engine `witness_of` bug class)** — CLEAN. `SignatureHasher::compute` prefixes a **fixed 4-byte** `day_epoch` then a **fixed-width canonical-f32** feature block (`IdentityFeatures`: Embedding = `EMBEDDING_DIM*4`, RiskFactors = 16 B). `PrivacyAttestationProof::compute` hashes a fixed 32-byte `prev_hash` + three fixed 1-byte values. No variable-length operator-influenceable string is concatenated into any digest — no length-prefix-framing collision is possible.
+- **Fail-closed** — `payload.rs::from_bytes` rejects truncated/overflowing/trailing-byte sections (`checked_add`, bounds checks); `frame.rs::from_bytes` validates magic/version/length/CRC; `PrivacyClass::try_from` rejects unknown bytes; `identity_risk::score` maps NaN/degenerate factors → 0.0 (privacy-conservative). The `from_score(NaN) → Accept` choice is a documented, deliberate publish-aggregate-only fallback (NaN never reaches it from `score()`); risk-driven NaN cannot leak identity because identity gating is class-byte-driven, not risk-driven.
+
+### Observation (not a bug)
+
+The ADR-141 control plane (`PrivacyMode`/`PrivacyModeRegistry`) is **not yet wired into the emit path** — the emitter/pipeline enforce the raw `PrivacyClass` directly; the registry is exported + unit-tested but advisory. This matches the "Integration glue — not yet on the live path" status above. The class-byte enforcement (emitter + event + renderers + the now-fixed `process_to_frame`) is the live guarantee. Wiring the registry is the documented next step.
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `1f8e180d6`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-signal` (`ruvsense/longitudinal.rs`, `ruvsense/attractor_drift.rs`, `ruvsense/calibration.rs`, `ruvsense/field_model.rs`, `ruvsense/tomography.rs`); `wifi-densepose-bfld` (`privacy_gate.rs`) |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block, v1 fixed-map default; v2 dataset-gated — see Implementation Status, commit `2d4f3dea5`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-signal` (`ruvsense/field_model.rs`, new `ruvsense/rf_slam.rs`); `wifi-densepose-mat` (`tracking/kalman.rs`, `localization/triangulation.rs`); `wifi-densepose-geo`; `wifi-densepose-ruvector` (`mat/triangulation.rs`) |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; no UWB radio in fleet — see Implementation Status, commit `b10bc2e9a`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-hardware` (new UWB driver/parser/auto-detect in `src/`); `wifi-densepose-signal` (`ruvsense/pose_tracker.rs` constraint-aware Kalman update); `wifi-densepose-mat` (`localization/fusion.rs` constraint integration) |
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Proposed |
+| **Status** | Accepted — partial (built + tested building block; integration glue pending — see Implementation Status, commit `0f336b7d3`) |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-train` (`src/eval.rs`, `src/metrics.rs`, `src/ruview_metrics.rs`, `src/proof.rs`); `wifi-densepose-signal` (`src/bin/*_proof_runner.rs`); `wifi-densepose-cli` |
@@ -9,8 +9,10 @@
 | Relates to | ADR-134, ADR-136, ADR-139, ADR-140, ADR-143, ADR-144, ADR-146, ADR-147                |

 > **Scope note:** ADR-147 deferred Cosmos WFM to "ADR-148" as an offline data generator.
-> That item is promoted to ADR-149. This ADR takes 148 to address the broader drone swarm
-> control architecture, which is the first consumer of ADR-147's OccWorld occupancy output.
+> That item is promoted to ADR-171 (the swarm-benchmarking/evaluation companion to this ADR;
+> renumbered from ADR-149 to resolve the ADR-149 duplicate-number collision). This ADR takes
+> 148 to address the broader drone swarm control architecture, which is the first consumer of
+> ADR-147's OccWorld occupancy output.

 ---

@@ -874,9 +876,9 @@ validated; ITAR/EAR classification completed by export counsel.
 | GPS spoofing of full swarm simultaneously | Medium | Low | UWB mesh cross-check among all nodes; ≥ 3 nodes must agree on position to confirm |
 | 1000-UAV scale claims (not validated) | Low | High | SWARM+ demonstrated in simulation only; scale claims capped at 50 for production targets |

-### 12.3 Open Issues (Forward to ADR-149)
+### 12.3 Open Issues (Forward to ADR-171)

- Cosmos WFM offline training data generation (deferred from ADR-147) — ADR-149
+- Cosmos WFM offline training data generation (deferred from ADR-147) — ADR-171
 - Fixed-wing hybrid platform support (endurance missions) — future ADR
 - Underwater-aerial cross-domain handoff protocol — future ADR
 - Quantum-enhanced task assignment (E6) — future ADR when hardware matures
@@ -998,4 +1000,4 @@ Implementation tracked at: https://github.com/ruvnet/RuView/issues/861

 *ADR authored with research support from `ruflo-goals:deep-researcher` (2026-05-30).
 Implementation progress tracked by `ruflo-goals:horizon-tracker`.
- OccWorld integration basis: ADR-147. Next: ADR-149 (Cosmos WFM offline data generation).*
+ OccWorld integration basis: ADR-147. Next: ADR-171 (Cosmos WFM offline data generation; renumbered from ADR-149).*
@@ -0,0 +1,308 @@
+# ADR-151: RuView Per-Room Calibration & Specialized Model Training System
+
+| Field | Value |
+|-------|-------|
+| **Status** | Accepted — Stages 1–5 implemented (statistical specialists); HF-backbone distillation pending |
+| **Date** | 2026-06-09 |
+| **Deciders** | ruv |
+| **Codebase target** | New `wifi-densepose-calibration` crate (orchestration); `wifi-densepose-train` (`rapid_adapt.rs`, `signal_features.rs`, `trainer.rs`); `wifi-densepose-ruvector` (RVF specialist storage); `wifi-densepose-signal/ruvsense/*` (feature extractors); `wifi-densepose-cli` (`enroll`, `train-room`, `room-status` subcommands) |
+| **Relates to** | ADR-135 (Empty-Room Baseline Calibration), ADR-030 (Persistent Field Model), ADR-134 (CIR), ADR-024 (Contrastive CSI Embedding / AETHER), ADR-027 (Cross-Environment Domain Generalization / MERIDIAN), ADR-070 (Self-Supervised Pretraining), ADR-105 (Federated CSI Training), ADR-149 (AetherArena / Hugging Face), ADR-150 (RF Foundation Encoder) |
+
+---
+
+## 1. Context
+
+### 1.1 The thesis — teach the room before you teach the model
+
+RuView's deployment frontier is not a better generic model. ADR-150 documents the wall directly: an MM-Fi pose head scores **81.63% torso-PCK@20 in-domain but ~11.6% leakage-free cross-subject**, and bigger capacity *hurts* cross-subject (transformer 24.8% < conv 27.3%). A single oversized model that "understands the world" overfits the rooms and bodies it has seen. The lever is the opposite of scale: **a small model that understands *one* room and *one* person**, calibrated in minutes, run locally, and specialised per biological signal.
+
+This positions RuView between the two incumbents in ambient sensing:
+
+- **Wearables** — high fidelity, but people forget to wear them, and they only measure the wearer.
+- **Cameras** — powerful, but invasive, store identifiable video, and fail in the dark / under covers.
+
+RuView sits in the middle: it learns the *space*, learns the *person*, and tracks biological rhythm (breathing, heartbeat, restlessness, posture, presence) without seeing skin or storing video. Heartbeat and breathing are not visual problems — they are tiny, repeating disturbances in the RF field. Capturing them well is a *calibration* problem, not a *model-size* problem.
+
+### 1.2 What already exists (and what is missing)
+
+The pieces of a calibration→training pipeline exist as disconnected modules. There is no system that runs them end to end and emits a per-room model bank.
+
+| Capability | Status today | Gap |
+|------------|--------------|-----|
+| Empty-room baseline (environmental fingerprint) | ADR-135 `BaselineCalibration` (Proposed): per-subcarrier amplitude + circular-phase stats, `ruvcal` NVS namespace | Captures the *room*, but there is no step that captures *guided human anchors* on top of it |
+| Field eigenstructure | ADR-030 `field_model.rs` (SVD room eigenmodes) | Consumes calibration; not wired to a training trigger |
+| Shared invariant backbone | ADR-150 RF Foundation Encoder (pose-preserving, subject/room/device-invariant) | Defined as a *foundation* embedding; nothing distills it into per-room specialists |
+| Few-shot adaptation | `train/src/rapid_adapt.rs` — test-time training → LoRA weight deltas (MERIDIAN P5) | Produces a *single* pose-adaptation delta, not a bank of per-modality specialists |
+| Feature extractors | `ruvsense/{bvp,longitudinal,intention,gesture,pose_tracker,adversarial}.rs`, `train/src/signal_features.rs` | Each emits a signal; none is packaged as a labelled training source for enrollment |
+| Small-model storage | `wifi-densepose-ruvector` (RVF cognitive containers, HNSW, sketch) | No schema for "a bank of specialist models scoped to a room_id" |
+| HF publishing | ADR-149 AetherArena (Hugging Face Space + signed scorer), `sensing-server` `from_pretrained` path | Publishes/評価s a *global* model; no notion of a published *base* + private *local* heads |
+
+**The missing system is the connective tissue**: a guided enrollment protocol, a feature-extraction-to-label bridge, a specialist-bank trainer that reuses the frozen HF backbone, and a runtime that fuses the specialists with confidence gating. This ADR defines that system.
+
+### 1.3 The four-step user model (and where each step lands)
+
+The system is deliberately presented to operators as four plain steps. Each maps to existing or new code:
+
+1. **Capture a quiet baseline** — no people, just room/router/reflections/noise/drift → the *environmental fingerprint*. → **Reuse ADR-135** `BaselineCalibration` + **ADR-030** field eigenmodes. No new capture code; the calibration crate calls it.
+2. **Capture guided samples** — stand, sit, lie down, slow vs normal breathing, small movement, sleep posture. Clean anchors, not hours of data. → **NEW** `EnrollmentProtocol` (Section 2.2).
+3. **Extract the useful signal** — CSI phase, amplitude, Doppler shift, micro-motion, periodicity, variance, timing. → **Reuse** `signal_features.rs` + ruvsense extractors, packaged as labelled `AnchorFeature` records (Section 2.3).
+4. **Compress patterns into small ruVector models** — *specialised* per signal: breathing, heartbeat, sleep restlessness, posture, presence, anomaly. → **NEW** `SpecialistBank` trained via `rapid_adapt` LoRA heads over the frozen ADR-150 backbone, stored as RVF (Section 2.4).
+
+---
+
+## 2. Decision
+
+**Build the RuView Per-Room Calibration & Specialized Model Training System: a four-stage, local-first pipeline (`baseline → enroll → extract → train`) that produces a versioned *bank of small specialised ruVector models* scoped to one `room_id`, each a lightweight head distilled/adapted from the frozen, Hugging-Face-published RF Foundation Encoder (ADR-150).** Big model understands the world; small ruVector models understand *your room*.
+
+Two invariants govern every design choice below:
+
+> **(A) Specialisation over scale.** One small model per biological signal, not one large model for all of them. Each specialist is faster, cheaper, more private, and — because it is calibrated to the room's actual fingerprint — often *more accurate* than a general model.
+>
+> **(B) Local-first, base-shared.** The frozen room/subject/device-invariant backbone is the only artifact published to Hugging Face. Per-room baselines and per-specialist heads never leave the device unless the operator opts into federation (ADR-105).
+
+### 2.1 System architecture
+
+```
+                       HUGGING FACE HUB (public, room-agnostic)
+                       ┌───────────────────────────────────────┐
+                       │  RF Foundation Encoder (ADR-150)       │
+                       │  pose-preserving · subject/room/device │
+                       │  -invariant · frozen · safetensors     │
+                       └───────────────┬───────────────────────┘
+                                       │  from_pretrained() once, cached on device
+                                       ▼
+  STAGE 1 baseline        STAGE 2 enroll        STAGE 3 extract         STAGE 4 train (per room_id)
+  ┌──────────────┐        ┌──────────────┐      ┌────────────────┐      ┌─────────────────────────┐
+  │ ADR-135      │        │ Enrollment   │      │ signal_features│      │ SpecialistBank          │
+  │ Baseline-    │──fp──► │ Protocol     │─clip►│ + ruvsense     │─AF──►│  frozen backbone        │
+  │ Calibration  │        │ guided       │      │ extractors     │      │   │  ┌────────────────┐  │
+  │ (env finger- │        │ anchors:     │      │ → AnchorFeature│      │   ├─►│ breathing head │  │
+  │  print)      │        │ stand/sit/   │      │ (phase, amp,   │      │   ├─►│ heartbeat head │  │
+  │ ADR-030      │        │ lie/breathe/ │      │  doppler,      │      │   ├─►│ restless head  │  │
+  │ field eigen  │        │ move/sleep   │      │  micromotion,  │      │   ├─►│ posture head   │  │
+  └──────────────┘        └──────────────┘      │  periodicity,  │      │   ├─►│ presence head  │  │
+        │                                        │  variance,     │      │   └─►│ anomaly head   │  │
+        │  baseline drift > τ → invalidate bank  │  timing)       │      │     (LoRA / ruVector    │
+        └───────────────────────────────────────┴────────────────┴──────┤      small models)      │
+                                                                          └───────────┬─────────────┘
+                                                                                      │ RVF container
+                                                                                      ▼
+                                                              RUNTIME: Mixture-of-Specialists
+                                                              each head emits {value, confidence};
+                                                              coherence_gate (ADR-135) + anomaly
+                                                              head veto → fused RoomState
+```
+
+The shared backbone is loaded **once per device** and frozen. Every specialist is a small head over its embedding — so the marginal cost of a sixth specialist is kilobytes of LoRA weights, not another full model.
+
+### 2.2 Stage 2 — the guided enrollment protocol (NEW)
+
+`EnrollmentProtocol` is a CLI-driven state machine that walks the operator through a fixed sequence of labelled **anchors**. The design rule from the user vision is explicit: *clean anchors, not hours of data.* Each anchor is a short (default 20 s @ 20 Hz = 400 frames) labelled clip captured against the already-recorded baseline.
+
+| Anchor | Label | Duration | Primary signal taught | Feature emphasis |
+|--------|-------|----------|-----------------------|------------------|
+| `empty` | presence=0 | (reuse ADR-135 baseline) | absence reference | amplitude variance floor |
+| `stand_still` | posture=standing, presence=1 | 20 s | static human load | amplitude mean shift, eigenmode delta |
+| `sit` | posture=sitting | 20 s | lower static load | amplitude profile |
+| `lie_down` | posture=lying | 20 s | sleep-position load | amplitude profile, low Doppler |
+| `breathe_slow` | resp≈0.1–0.15 Hz | 30 s | slow respiration | periodicity, micro-Doppler |
+| `breathe_normal` | resp≈0.2–0.3 Hz | 30 s | normal respiration | periodicity, BVP phase |
+| `small_move` | motion=1 | 20 s | limb micro-motion | Doppler spread, variance |
+| `sleep_posture` | posture=lying, restless=0 | 30 s | quiescent sleep baseline | long-window variance, timing |
+
+The protocol is **adaptive**: an anchor is only accepted when its captured features pass a quality gate (coherence ≥ threshold from `coherence_gate.rs`, sufficient SNR vs baseline, no saturation). A failed anchor is re-prompted rather than silently kept — bad anchors poison small models far more than large ones. Total guided enrollment is ~4 minutes of wall-clock, producing 8 clean anchors. This is intentionally far below the "hours of data" that a from-scratch model needs, because the backbone already carries world knowledge; enrollment only teaches *this* room's offsets.
+
+Anchors are persisted as an append-only `EnrollmentSession` (event-sourced, per CLAUDE.md state rules) under `room_id`, so re-enrollment is incremental and auditable.
+
+### 2.3 Stage 3 — feature extraction to labelled records (REUSE + bridge)
+
+Each accepted anchor clip is run through the existing extractor stack, baseline-subtracted per ADR-135, and packaged into an `AnchorFeature` record. No new DSP is invented — this stage is a *bridge*, not a new algorithm.
+
+| Feature group | Source module | Used by specialists |
+|---------------|---------------|---------------------|
+| CSI amplitude mean/variance | ADR-135 baseline subtraction + `signal_features.rs` | presence, posture |
+| CSI phase (sanitised, LO-aligned) | `phase_sanitizer` → `phase_align` | posture, heartbeat |
+| Doppler shift / micro-Doppler | `ruvsense/bvp.rs`, `breathing` path | breathing, small-move |
+| Micro-motion / intention lead | `ruvsense/intention.rs` | restlessness, anomaly |
+| Periodicity / spectral peaks | `bvp.rs` autocorrelation + FFT | breathing, heartbeat |
+| Long-window variance / drift | `ruvsense/longitudinal.rs` (Welford) | restlessness, presence |
+| Timing / inter-frame epoch | `c6_timesync` epoch, frame Δt | all (rhythm alignment) |
+| Field eigenmode coefficients | ADR-030 `field_model.rs` | posture, presence |
+
+`AnchorFeature` = `{ room_id, anchor_label, t_epoch_us, embedding: [f32; D] (backbone output), aux: { resp_hz?, doppler_spread, variance, periodicity_score, eigen_coeffs } }`. The backbone embedding is the *shared* representation; `aux` carries the cheap hand-features that let small heads specialise without re-learning DSP.
+
+### 2.4 Stage 4 — the specialist bank (NEW, the core contribution)
+
+A **`SpecialistBank`** is a versioned collection of small models scoped to one `room_id`, persisted as a single RVF cognitive container (`wifi-densepose-ruvector`). Each specialist is a *head* over the frozen backbone embedding, trained from the labelled `AnchorFeature` records via the existing `rapid_adapt.rs` LoRA machinery (test-time/few-shot training, contrastive + entropy losses), **not** a from-scratch network.
+
+| Specialist | Model type | Params (typ.) | Label source | Output |
+|------------|-----------|---------------|--------------|--------|
+| **breathing** | 1-D temporal head + periodicity regressor | ~8 KB LoRA + aux | `breathe_slow`/`breathe_normal` | resp rate (Hz) + confidence |
+| **heartbeat** | narrowband phase head (harmonic-aware) | ~12 KB | quiescent anchors + periodicity | HR (bpm) + confidence |
+| **sleep restlessness** | variance/drift classifier | ~4 KB | `sleep_posture` vs `small_move` | restlessness score [0,1] |
+| **posture** | k-way prototype classifier (HNSW NN) | prototypes only | `stand/sit/lie` anchors | posture class + margin |
+| **presence** | binary energy/eigenmode gate | ~2 KB | `empty` vs occupied anchors | presence prob |
+| **anomaly** | one-class / physically-impossible detector (`adversarial.rs`) | ~6 KB | baseline + all anchors (novelty) | anomaly score + veto flag |
+
+Design properties that follow from invariant (A):
+
+- **Independently versioned & swappable.** Re-enrolling breathing does not retrain posture. A specialist carries its own `{trained_at, anchor_set_hash, baseline_hash, backbone_rev}`.
+- **HNSW prototype storage for the classifiers.** Posture and presence are nearest-prototype lookups in the RVF index — no inference engine, microsecond latency, and new postures are added by inserting a prototype, not retraining.
+- **SONA online adaptation.** Each specialist may carry a SONA/MicroLoRA online-adaptation slot (`ruvllm_sona_*` / `microlora` primitives) so it tracks slow drift (furniture moved, seasonal RF change) between full re-enrollments, gated by ADR-135 baseline drift.
+- **Teacher–student distillation (optional, offline).** Where a labelled public corpus exists (MM-Fi, Wi-Pose), the ADR-150 backbone acts as teacher to pre-shape a head before per-room fine-tuning, improving cold-start. The *teacher* is global/HF; the *student head* is local.
+
+**Invalidation contract.** The bank stores the `baseline_id` (the baseline UUID) it was trained against. **As implemented**, the runtime marks the bank `STALE` whenever the *current* baseline id differs from the trained one — a conservative trigger that catches re-calibration (room rearranged, AP moved, band changed) because any of those produces a new baseline. A finer **drift-threshold** trigger (mark STALE when ADR-135's per-subcarrier deviation exceeds τ *without* a full re-baseline) is a planned refinement (P6). Either way the runtime prompts re-enrollment rather than emitting silently wrong vitals — the calibration analogue of the #954 `DEGRADED` honesty rule: never report confident numbers from an invalid model.
+
+### 2.5 Runtime — mixture of specialists with confidence gating
+
+At inference, the frozen backbone embeds each CSI window once; every specialist consumes that shared embedding and emits `{value, confidence}`. Fusion rules:
+
+- The **anomaly** specialist holds a **veto**: a high anomaly score (physically-impossible signal per `adversarial.rs`, or a coherence-gate `Reject`) suppresses positive vitals/posture output and raises a flag, rather than propagating a hallucinated reading.
+- **presence=0** short-circuits breathing/heartbeat/posture to `null` (you cannot have a respiration rate in an empty room).
+- Each emitted reading is tagged with the specialist's confidence and the `baseline_hash`/`backbone_rev` provenance, so downstream consumers (sensing-server, MQTT, Home Assistant) can gate on quality — consistent with ADR-135 coherence-gate semantics.
+
+### 2.6 Crate & module layout
+
+New bounded-context crate `wifi-densepose-calibration` (orchestration only; files < 500 lines, typed public APIs, event-sourced sessions — per CLAUDE.md):
+
+```
+wifi-densepose-calibration/
+  src/
+    lib.rs                 # public API: CalibrationSystem facade
+    enrollment.rs          # EnrollmentProtocol state machine (Stage 2)
+    anchor.rs              # Anchor, EnrollmentSession (event-sourced)
+    extract.rs             # AnchorFeature bridge over signal_features + ruvsense (Stage 3)
+    specialist.rs          # Specialist trait, SpecialistKind enum
+    bank.rs                # SpecialistBank (RVF container, versioning, invalidation)
+    runtime.rs             # MixtureOfSpecialists fusion + veto (Stage 5)
+    backbone.rs            # frozen ADR-150 encoder loader (hf_hub from_pretrained, cached)
+    error.rs
+```
+
+Dependencies (no duplication — orchestrates existing crates): `wifi-densepose-signal` (ruvsense extractors, ADR-135 baseline), `wifi-densepose-train` (`rapid_adapt`, `signal_features`, `trainer`), `wifi-densepose-ruvector` (RVF, HNSW), `wifi-densepose-nn` (backbone inference). The `wifi-densepose-cli` gains `enroll`, `train-room`, and `room-status` subcommands, sequenced after the existing ADR-135 `calibrate`.
+
+### 2.7 CLI flow (operator-facing)
+
+```bash
+# Stage 1 — environmental fingerprint (ADR-135, existing)
+wifi-densepose calibrate --room living-room --duration 60s     # empty room
+
+# Stage 2+3 — guided enrollment (NEW); prompts through 8 anchors, ~4 min
+wifi-densepose enroll --room living-room
+#   → "Stand still in view of the sensor…"  [✓ anchor accepted: coherence 0.91]
+#   → "Sit down…"                            [✗ low SNR, retrying]
+#   ...
+
+# Stage 4 — train the specialist bank (NEW); reuses cached HF backbone
+wifi-densepose train-room --room living-room \
+    --specialists breathing,heartbeat,restlessness,posture,presence,anomaly
+
+# Status / invalidation
+wifi-densepose room-status --room living-room
+#   baseline: fresh (drift 0.04 < 0.20) · backbone: rf-foundation@1.2.0
+#   breathing  ✓ trained 2026-06-09  conf p50 0.88
+#   heartbeat  ✓ trained 2026-06-09  conf p50 0.71
+#   posture    ✓ 3 prototypes (stand/sit/lie)
+#   anomaly    ✓  · presence ✓  · restlessness ✓
+```
+
+---
+
+## 3. Consequences
+
+### 3.1 Positive
+
+- **Fidelity through specialisation.** Six small calibrated heads beat one oversized general model on the cross-room/cross-subject frontier that ADR-150 quantified — and each runs in microseconds-to-milliseconds, on-device.
+- **Privacy by construction.** Only the room-agnostic backbone is public (HF). The environmental fingerprint and the person-specific heads stay local; no video, no skin, no cloud round-trip. This is the core differentiator vs cameras and the convenience differentiator vs wearables.
+- **Minutes, not hours.** Because the backbone carries world knowledge, ~4 minutes of clean anchors calibrates a room. Re-enrollment is incremental.
+- **Honest degradation.** The `baseline_hash` invalidation + anomaly veto mean an out-of-calibration room reports `STALE`/flagged rather than confidently wrong — the same honesty principle as the firmware `DEGRADED` flag.
+- **Composable & cheap to extend.** A new biological signal = a new small head over the same embedding, not a new model.
+
+### 3.2 Negative / risks
+
+- **Backbone dependency.** Every specialist rides on ADR-150's encoder; its quality and revision compatibility (`backbone_rev`) are a single point of leverage. Mitigation: pin `backbone_rev` in each specialist; distillation cold-start reduces sensitivity.
+- **Enrollment burden.** 4 minutes is small but non-zero, and anchor quality depends on the operator following prompts. Mitigation: adaptive re-prompting + quality gates; ship sane defaults so a partial bank (presence+posture) works after just the static anchors.
+- **Heartbeat is hard.** Sub-mm chest displacement at HR frequencies is near the ESP32-S3 noise floor; the heartbeat specialist will have lower and more variable confidence than breathing. The confidence-gated runtime surfaces this rather than faking it.
+- **Per-room storage proliferation.** A bank per room per person; needs a clear RVF lifecycle (list/prune/export) — handled by `bank.rs` versioning and the `room-status` CLI.
+
+### 3.3 Alternatives considered
+
+| Alternative | Verdict | Reason |
+|-------------|---------|--------|
+| One large general model for all signals | **Rejected** | The ADR-150 evidence: scale overfits rooms/subjects and collapses cross-domain; also slower, costlier, less private. Directly contradicts invariant (A). |
+| Cloud training of per-room models | **Rejected** | Violates invariant (B): would ship raw CSI of a person's home/sleep to a server. Local-first is the privacy promise. Federation (ADR-105) is the *opt-in* path for shared improvement, exchanging gradients/deltas, never raw CSI. |
+| Skip the backbone; train each specialist from scratch | **Rejected** | Reintroduces the "hours of data" requirement the user vision explicitly rejects, and loses cross-room priors. |
+| Fold this into ADR-135 | **Rejected** | ADR-135 is *room* calibration (no humans). This ADR is *human-anchor* enrollment + model training on top of it. Distinct lifecycles, distinct invalidation; kept as separate bounded contexts. |
+
+---
+
+## 4. Implementation phases
+
+| Phase | Scope | Exit criterion | Status |
+|-------|-------|----------------|--------|
+| **P1** | Scaffold `wifi-densepose-calibration` crate; `AnchorFeature` schema; (backbone via `hf_hub` deferred) | Crate + schema; unit tests | ✅ Done (crate + Stage-1 baseline via `calibrate`/`calibrate-serve`; HF backbone deferred) |
+| **P2** | `EnrollmentProtocol` + `anchor.rs` (event-sourced sessions) + CLI `enroll` with quality gates | 8-anchor enrollment; bad anchors re-prompt | ✅ Done (`anchor.rs`, `enrollment.rs`, CLI `enroll`) |
+| **P3** | `extract.rs` bridge → labelled records; baseline subtraction (ADR-135) | `AnchorFeature` records persisted per `room_id` | ✅ Done (`extract.rs`; autocorr periodicity + variance/motion) |
+| **P4** | `SpecialistBank` + presence/posture (prototype) + breathing (periodicity); persistence + versioning | `train-room` produces a bank; `room-status` reads it back | ✅ Done (`specialist.rs`, `bank.rs`, CLI `train-room`/`room-status`; JSON persistence — RVF/HNSW = future) |
+| **P5** | heartbeat + restlessness + anomaly specialists; `runtime.rs` mixture + veto + confidence gating | End-to-end RoomState on hardware; anomaly veto verified | ✅ Done (`runtime.rs`, CLI `room-watch`; breathing read live on COM8 ESP32) |
+| **P6** | Baseline-drift `STALE` invalidation; SONA online adaptation; optional ADR-105 federation; HF teacher–student distillation | Drift marks bank STALE; AetherArena entry | ◐ Partial (STALE done; SONA/federation/HF-backbone = follow-ups) |
+
+**Current status (2026-06-10):** Stages 1–5 implemented with *statistical* specialists (threshold/prototype/autocorrelation). 55 tests (35 unit incl. multistatic + 1 full-loop integration + 19 CLI), all passing under qemu-aarch64. **Validation scope is precise:** baseline capture + HTTP API + auth are proven on real CSI (Pi-5 nexmon, 6,813 frames; and an ESP32-S3). The complete `baseline → enroll → train-room → infer` loop is now **proven in-process** on deterministic synthetic CSI (`tests/full_loop.rs`: clean baseline with zero motion flags, 8/8 anchors through the quality gate, 6 specialists trained, JSON bank round-trip, trained-bank inference 18±2 BPM positive / absent negative / foreign-baseline STALE; seed-robust). The one live runtime signal (breathing ~16–31 BPM via `room-watch`) used the *stateless* breathing head, **not** a trained bank; the clean empty-room loop has **not** yet run on-target — the remaining gap is strictly the hardware session (empty room + operator anchors). The four behavioral findings from the full-loop test (z-band squeeze, variance-only presence, ungated hz embedding, heart-band lag-floor leakage) are FIXED and regression-guarded — see the integration doc §7. SOTA-intake decisions affecting this system (geometry conditioning, checkerboard alignment) are recorded in ADR-152. Open refinements: `--source-format adr018v6` (drive from the Pi's own nexmon), phase-based breathing carrier, RVF/HNSW storage, and the ADR-150 frozen HF backbone the specialists would distill from.
+
+Validation per CLAUDE.md: `cargo test --workspace --no-default-features` green; hardware verification on the ESP32-S3 (currently COM8) before any release; witness bundle regenerated if the proof surface changes.
+
+---
+
+## 6. Review notes
+
+### 6.1 Correctness + security review (2026-06-14)
+
+Beyond-SOTA correctness+security review of `wifi-densepose-calibration` (this
+ADR's pipeline), un-covered by the ADR-154–159 sweep.
+
+**Finding (FIXED) — NaN-poisoning of the feature path (numerical / fail-closed).**
+`Features::from_series` — the carrier for both live inference and training-anchor
+extraction — computed `mean`/`variance`/`motion` over the raw scalar series with
+no non-finite guard. A single `NaN`/`±inf` sample (corrupt CSI frame) yielded
+`mean=NaN, variance=NaN` and an all-`NaN` prototype embedding. Persisted into a
+`PresenceSpecialist::threshold`/`empty_mean` at train time, the `NaN` **silently
+disabled presence detection** for the bank's lifetime (every `>` / `|·|`
+comparison against `NaN` is false → always reads *absent*, confidence 0), with no
+error — and an asymmetry against the rigorously NaN-guarded `geometry_embedding`.
+Fixed at the production boundary: non-finite samples are dropped (a corrupt frame
+counts as no frame), an all-non-finite series degrades to `Features::ZERO` like
+the empty series. Value-identical for all-finite input (full-loop + extract tests
+unchanged); pinned by `non_finite_samples_do_not_poison_features` and
+`all_non_finite_series_is_zero` (both fail on the old code).
+
+**Clean dimensions (evidence, no invented issues).**
+- *File/path handling:* the crate performs **zero** file/path I/O (no
+  `std::fs`/`Path`/`File`/`read`/`write` in `src/`; only in-memory `serde_json`).
+  Path-traversal / unbounded-read / artifact-path handling live entirely in the
+  `wifi-densepose-cli` consumer (`room.rs`), outside this crate's boundary.
+- *Untrusted-load:* `SpecialistBank::from_json` shape-validates via serde
+  (malformed → `CalibrationError::Serde`); banks are local-first (invariant B),
+  never network-received. A well-formed bank with adversarial numerics is trusted
+  as-is — acceptable under the local-first threat model; a validate-on-load
+  defense-in-depth pass is a possible future hardening, not a present bug.
+- *Receipt/hash integrity:* the crate emits no hash/receipt/witness/signature, so
+  the unframed-concatenation bug class (cf. the engine `witness_of` fix) is
+  structurally absent.
+- *Other numerical paths:* `geometry_embedding` sanitizes every input and sweeps
+  to finite; presence/restlessness/anomaly divisions are `.max(1e-3)`-guarded;
+  `autocorr_dominant` guards `r0`, short signals, and empty bands; `train` rejects
+  empty anchors; anomaly requires ≥2 anchors.
+
+De-magicked the bare specialist threshold literals (breathing/heartbeat default
+min-scores, anomaly outlier-spread multiple + label cutoff) into named documented
+consts, value-identical, pinned by const-equality tests. Tests
+**58→62 unit + 1 integration, 0 failed**; Python deterministic proof unchanged
+(off the signal proof path).
+
+---
+
+## 5. Summary
+
+> Big models understand the world. Small ruVector models understand *your room*.
+
+ADR-151 makes that operational: a local-first `baseline → enroll → extract → train` pipeline that turns ~4 minutes of clean human anchors — layered on ADR-135's empty-room fingerprint and ADR-150's Hugging-Face-published invariant backbone — into a versioned bank of tiny, specialised, privacy-preserving models for breathing, heartbeat, restlessness, posture, presence, and anomaly. Specialisation over scale; local heads over a shared base; honest `STALE` degradation over confident error.
@@ -0,0 +1,125 @@
+# ADR-152: WiFi-Pose SOTA 2026 Intake — Geometry-Conditioned Calibration, External Benchmarks, and the Foundation-Encoder Training Recipe
+
+| Field | Value |
+|-------|-------|
+| **Status** | Proposed |
+| **Date** | 2026-06-10 |
+| **Deciders** | ruv |
+| **Codebase target** | `wifi-densepose-calibration` (geometry conditioning, ADR-151 Stage 2), `wifi-densepose-train` (camera-supervised path, MAE recipe), `wifi-densepose-cli` (benchmark harness), docs |
+| **Relates to** | ADR-151 (Per-Room Calibration), ADR-150 (RF Foundation Encoder), ADR-135 (Empty-Room Baseline), ADR-079 (Camera-Supervised Pose), ADR-027 (MERIDIAN), ADR-024 (AETHER), ADR-149 (AetherArena), ADR-029 (Multistatic) |
+| **Research provenance** | Deep-research run 2026-06-10: 22 sources fetched, 110 claims extracted, 25 adversarially verified (3-vote), 24 confirmed / 1 refuted. Evidence grades per source below. |
+
+---
+
+## 1. Context
+
+A structured survey of the 2025–2026 WiFi human-sensing state of the art was run on 2026-06-10 to answer: *what should RuView integrate next, and does anything published invalidate our current direction?* Every claim below was verified against the primary source by independent adversarial reviewers; **evidence grades distinguish what the papers measured from what they merely claim**. Almost all performance numbers are author-self-reported preprint results — treated here as CLAIMED until reproduced on our hardware.
+
+### 1.1 The five verified findings
+
+**(F1) "Coordinate overfitting" is a named, diagnosed failure mode of camera-supervised WiFi pose — and our ADR-079 pipeline has the exact shape of it.**
+PerceptAlign (arXiv [2601.12252](https://arxiv.org/abs/2601.12252), accepted ACM MobiCom 2026) shows that models regressing CSI directly to camera-frame coordinates memorize the deployment-specific transceiver layout; SOTA baselines degrade to >600 mm MPJPE in unseen scenes. Their fix is cheap: a <5-minute calibration using two checkerboards and a few photos to align WiFi and vision in one shared 3D frame, plus **fusing transceiver-position embeddings with CSI features**. Claimed: −12.3% in-domain error, −60%+ cross-domain error. They release the claimed-largest cross-domain 3D WiFi pose dataset (21 subjects, 5 scenes, 18 actions, **7 device layouts**). *Evidence: improvements CLAIMED (preprint w/ MobiCom acceptance); the failure mode itself is corroborated across the cross-domain literature — and independently by our own ADR-150 data (81.63% in-domain vs ~11.6% leakage-free cross-subject torso-PCK).*
+
+**(F2) An external model named "WiFlow" claims 97.25% PCK@20 with 2.23M params and ships everything.**
+arXiv [2602.08661](https://arxiv.org/abs/2602.08661) (Apr 2026) — spatio-temporal-decoupled CSI pose, 97.25% PCK@20 / 99.48% PCK@50 / 0.007 m MPJPE, 2.23M parameters (~2.2 MB int8). Code, pretrained weights, and a 360k-sample CSI-pose dataset are public under Apache-2.0 ([repo](https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling), Kaggle dataset). *Evidence: artifact availability MEASURED (verified by direct repo inspection); PCK numbers CLAIMED (5-subject, in-domain, self-collected dataset; hardware unspecified; 15 keypoints vs our 17).* ⚠️ **Name collision:** this is unrelated to RuView's internal WiFlow model. In all RuView docs the external model is referred to as **WiFlow-STD (DY2434)**.
+
+**(F3) For CSI foundation encoders, data scale — not model capacity — is the bottleneck, and the tokenization recipe is now known.**
+UNSW's MAE pretraining study (arXiv [2511.18792](https://arxiv.org/abs/2511.18792), Nov 2025) — the largest heterogeneous CSI pretraining run to date (1,320,892 samples, 14 public datasets incl. MM-Fi, Widar 3.0, Person-in-WiFi 3D; 4 devices; 2.4/5/6 GHz; 20–160 MHz) — reports zero-shot cross-domain gains of 2.2–15.7% over supervised baselines, with unseen-domain performance scaling **log-linearly with pretraining data, unsaturated at 1.3M samples**, while ViT-Base adds only 0.4–0.9% over ViT-Small. Optimal recipe: **80% masking ratio, small (30,3) patches** (+4.7% over (40,5) by preserving fine temporal dynamics). *Evidence: MEASURED within-study (ablations verified in body text) but preprint; downstream tasks are classification, NOT pose — pose transfer is a hypothesis. Independently corroborates ADR-150's finding that capacity hurts cross-subject.*
+
+**(F4) Hardware/standards: 802.11bf is finished; Espressif ships official sensing; Wi-Fi 6 AP CSI is reachable.**
+- **IEEE 802.11bf-2025** published **2025-09-26** (verified against the IEEE SA record) — sensing standardization is complete for both sub-7 GHz and >45 GHz, with formal sensing setup/feedback procedures. No ESP32 silicon implements it yet. *Evidence: MEASURED (standards-body record).*
+- **Espressif `esp_wifi_sensing`** (Apache-2.0, v0.1.x, ESP Component Registry): official CSI presence/motion FSM; esp-csi actively maintained (commit 2026-04-22, verified), CSI confirmed across ESP32/S2/C3/S3/C5/C6/C61. *Evidence: MEASURED (vendor pages + commit log).* ⚠️ A stronger "drop-in compatible with RuView nodes" claim was **REFUTED 0-3** — WiFi-6 parts use a different CSI acquisition config struct.
+- **ZTECSITool** (arXiv [2506.16957](https://arxiv.org/abs/2506.16957), [code](https://github.com/WiFiZTE2025/ZTE_WiFi_Sensing)): CSI from commercial Wi-Fi 6 APs at up to 160 MHz / 512 subcarriers (~5–10× ESP32 subcarrier count; the gain is aperture, not per-Hz granularity). Firmware is gated behind a ZTE serial-number approval. *Evidence: capability CLAIMED by the vendor-authored tool paper; code artifact MEASURED.*
+
+**(F5) Nothing in 2025–2026 does full DensePose UV regression from commodity WiFi.** Keypoint pose remains the field's frontier. Three "wireless foundation model" papers were screened out by full-text inspection (HeterCSI = simulated cellular channels only; the NeurIPS-2025 FMCW pilot = mmWave radar, presence-only; arXiv 2509.15258 = survey, no artifacts). *Evidence: MEASURED (absence verified by full-text inspection of the candidates that surfaced; absence of evidence across the whole literature is necessarily weaker).*
+
+### 1.2 What this means for the ADR-151 calibration system
+
+ADR-151's enrollment protocol captures guided human anchors but does **not** record or condition on transceiver geometry. F1 says that omission is precisely the thing that makes camera-supervised (and, plausibly, anchor-supervised) heads layout-brittle. ADR-151's per-room thesis ("teach the room before you teach the model") is *strengthened* by F1 — PerceptAlign is independent evidence that layout must be modeled explicitly — and the fix composes naturally with our Stage-2 enrollment.
+
+ADR-150's masked-CSI-encoder design is *validated* by F3, which also hands us the hyperparameters and the priority call: **collect/aggregate more heterogeneous CSI before scaling the encoder.**
+
+## 2. Decision
+
+Adopt four changes, ordered by effort-vs-gain:
+
+### 2.1 Geometry-condition the calibration system (extends ADR-151 Stage 2) — ACCEPTED
+
+1. **Record transceiver geometry at enrollment.** `EnrollmentProtocol` gains an optional `NodeGeometry` record per node (position estimate, antenna orientation, inter-node distances where known). Stored alongside the room baseline in the bank; schema-versioned so existing banks remain readable.
+2. **Fuse geometry embeddings into specialist training.** Where a specialist head consumes the (future, ADR-150) backbone embedding, concatenate a small learned embedding of `NodeGeometry` — the PerceptAlign mechanism, transplanted to our per-room banks. Statistical specialists (current) ignore it; LoRA heads (ADR-151 P6) consume it.
+3. **Adopt the two-checkerboard alignment for the camera-supervised path (ADR-079).** When MediaPipe supervision is used, calibrate camera↔WiFi into one shared 3D frame before regression (<5 min, two checkerboards, a few photos). This is the direct defense against F1 for our camera-supervised pipeline. ~~92.9%-PCK@20~~ — *that figure was retracted during measurement (b) (2026-06-10): the surviving holdout shows a constant-output model under an absolute (non-torso) threshold on 69 near-static frames; mean predictor scores 100% under the same protocol. The §2.2 no-citation rule now applies to it.*
+4. **Evaluate on the PerceptAlign cross-domain dataset** (21 subjects / 7 layouts) as the MERIDIAN cross-layout benchmark — *gated on confirming its license and downloadability* (open question; repo per paper: github.com/Trymore-lab/PerceptAlign).
+   > **Gate resolved (2026-06-10, MEASURED by repo inspection):** repo exists, **MIT license**, dataset downloadable from HuggingFace (5 per-scene repos, raw CSI + separate vision keypoints; Intel 5300, 1TX×3RX×3 ant, 57 subcarriers — same order as ESP32 subcarrier counts; Scene3 ships 3 distinct layouts). Code present, no pretrained weights. Benchmark adoption unblocked; dataset-side license terms inherit HF dataset terms (not separately stated — check at download time).
+
+### 2.2 Benchmark against WiFlow-STD (DY2434) — ACCEPTED
+
+Pull the Apache-2.0 weights + 360k-sample dataset; run three measurements: (a) their model on their data (reproduce 97.25% claim), (b) their model fine-tuned on our ESP32 17-keypoint eval set, (c) our internal WiFlow on their dataset (15-keypoint subset mapping). Until (a)–(c) are measured, **no RuView doc may cite 97.25% as a comparable number** — different dataset, subjects, keypoints.
+
+> **Status (2026-06-10, measurement (a) complete — `benchmarks/wiflow-std/RESULTS.md`):** shipped checkpoint REFUTED (0.08% PCK@20 — wrong keypoint normalization, predates published code); released code does not run as published (6 defects, incl. broken package import and an unreachable test phase); released dataset's last 13 files are corrupted (9,072 windows: NaN + float32-max garbage, diverges fp16 training via BatchNorm poisoning). After repairing both, retraining with upstream defaults reproduced **96.09% PCK@20 full-test / 96.61% corruption-free / MPJPE 0.0094–0.0098** (published: 97.25% / 0.007) on an RTX 5080. Accuracy claims graded MEASURED-EQUIVALENT; params (2.23M) and FLOPs (~0.055G) verified. (b)/(c) remain open.
+
+### 2.3 Apply the UNSW recipe to the ADR-150 encoder — ACCEPTED (amends ADR-150 §2.3)
+
+- Pretraining corpus: start from the same 14 public datasets (1.3M samples) + our home/MM-Fi frames; data aggregation takes priority over architecture work.
+- Tokenization: 80% masking, (30,3)-class small patches; encoder stays ViT-Small-class (~15M params) — F3 and our own DANN/transformer results agree that capacity does not pay.
+- The published log-linear scaling (unsaturated) sets the expectation: more heterogeneous CSI in, better zero-shot out.
+
+### 2.4 Hardware watch items — ACCEPTED (no code now)
+
+- **802.11bf**: track silicon/certification; OTA binding remains deferred until commodity chipsets expose standardized sensing measurements. **Amended by ADR-153** (2026-06-10): implement a pure Rust forward-compatibility protocol layer now — typed procedure models, a deterministic session FSM, a transport abstraction, simulation tests, and an `OpportunisticCsiBridge` that maps today's ESP32 CSI batches into standardized sensing-report shape.
+- **esp_wifi_sensing**: benchmark our presence pipeline against the vendor FSM (one afternoon; useful external baseline). Do **not** treat as drop-in (refuted claim).
+- **ZTECSITool AP**: optional high-resolution anchor node for the ADR-029 multistatic mesh — procurement-gated; only pursue if a 160 MHz anchor materially helps tomography.
+
+### 2.5 Explicitly NOT adopted
+
+- No pivot toward "wireless foundation model" papers that don't ship WiFi-CSI artifacts (HeterCSI, FMCW pilot, surveys).
+- No DensePose-UV work item: the field has not demonstrated UV regression from commodity WiFi; keypoints remain our supervised target (F5).
+
+### 2.6 RuVector vendor sync + integration opportunities (added 2026-06-10)
+
+**Vendor sync record.** `vendor/ruvector` moved from pin `e38347601` (2026-05-07) to `a083bd77f` (origin/main, 3 commits past tag `ruvector-v0.2.28`; vendored workspace version 2.2.3). 111 commits in the range, roughly half NAPI-binary/lint chores. Substantive: graph condensation + differentiable min-cut (#547), core HNSW correctness fixes v2.2.3 (#502), RUSTSEC/clippy hardening (#504), ONNX embedder API-contract fix (#523/#525 — npm/TypeScript package only), dead parallel-worker import removal (#532). *Evidence: MEASURED (git range + commit-stat inspection).*
+
+**Opportunity table.** Workspace policy is crates.io versions only, so unpublished crates are WATCH by definition regardless of fit.
+
+| Crate | What it offers | wifi-densepose target | crates.io | Verdict |
+|---|---|---|---|---|
+| `ruvector-graph-condense` (new, #547) | Training-free min-cut graph condensation + **differentiable normalized-cut loss** (`DiffCutCondenser`, analytic MinCutPool-style gradients, gradient-checked tests; provenance-retaining super-nodes) | `subcarrier_selection.rs` (condense 114 subcarriers into cut-preserving regions instead of raw min-cut); auxiliary clustering regularizer for `wifi-densepose-train`; `DynamicPersonMatcher` region structure | **Not published** | **WATCH** — strongest technical fit in the sync; adopt when published. README's "no published method uses graph-cut condensation" is CLAIMED; the diffcut implementation + tests are MEASURED |
+| `ruvector-attention` 2.1.0 | #304 SOTA modules: MLA, KV-cache, SSM, sparse/MoE, hybrid search, Graph RAG (publish date 2026-03-27 matches the #304 commit — MEASURED) | Supersedes pinned 2.0.4 used by `model.rs` spatial attention + `bvp.rs`; SSM/MLA are candidate pure-Rust edge-inference primitives for the ADR-150 encoder | 2.1.0 (pinned **2.0.4**) | **ADOPT** (minor bump; API-compat check first) |
+| `ruvector-gnn` 2.2.0 | panic→`Result` constructors, gradient clipping, MSE/CE/BCE losses, seeded-RNG layer init (#495 is post-2.2.0) | `wifi-densepose-train` GNN path (pinned 2.0.5, `default-features = false`) | 2.2.0 (pinned **2.0.5**) | **ADOPT** (bump) |
+| `ruvector-mincut` / `ruvector-solver` 2.0.6 | Patch-level fixes (workspace republish 2026-03-25) | `metrics.rs` DynamicPersonMatcher, subcarrier interpolation, triangulation | 2.0.6 (pinned **2.0.4** each) | **ADOPT** (routine patch bump) |
+| `ruvector-core` 2.2.3 (vendor) | HNSW correctness: k=0 guard, sorted results, flat-index fixes, cross-integration helpers (#502 — MEASURED, `index/hnsw.rs` + new integration tests) | `homecore-recorder` `RuvectorSemanticIndex` (real HNSW consumer); `sketch.rs` quantization unaffected | **2.2.0 = latest published**; 2.2.3 unpublished | **WATCH** — bump the moment 2.2.3 publishes |
+| `ruvector-cnn` 2.0.6 | Pure-Rust SIMD conv kernels (AVX2/NEON/WASM), MobileNetV3, INT8 quantization, contrastive losses (InfoNCE/triplet, #252) | **Not** the WiFlow-STD training port — `wiflow_std/model.rs` is tch/libtorch (MEASURED). Relevant to the *edge inference* path of the trained ~2.2 MB int8 model, and InfoNCE/triplet overlaps AETHER (ADR-024) | 2.0.6 | **EVALUATE** — only if/when we commit to a no-libtorch edge runtime for WiFlow-STD-class models |
+| `ruvector-acorn` (new-ish) | ACORN predicate-agnostic filtered HNSW (SIGMOD'24 algorithm; γ·M denser graphs for low-selectivity filters) | Metadata-filtered pattern search over ADR-151 calibration banks — speculative; bank sizes are far below where filtered-ANN recall collapse matters | **Not published** | **WATCH** |
+| `ruvector-cluster` 2.0.6 | Distributed sharding, gossip discovery, DAG consensus | No current need; ADR-029 mesh coordination is ESP32-side, not vector-DB-side | 2.0.6 | **WATCH** |
+| ONNX embedder fix (#523/#525) | API-contract + packaging fixes in `npm/packages/ruvector` (TypeScript) | None — `wifi-densepose-nn`'s ONNX backend is Rust (ort/tract), untouched by this change (MEASURED: commit touches npm/ only) | n/a | No action |
+| `ruvector-perception` (new, #547) | "Physical perception substrate" (hypothesis/topology/witness modules) — agent-perception oriented, not RF | None identified | Not published | WATCH (name-overlap only) |
+
+**Security note (RUSTSEC #504).** The substantive fixes target `ruvllm`, `ruvector-dag`, `prime-radiant`, `rvagent-*`, and the `ruvector-server` HTTP endpoint (NaN-safe `partial_cmp`, input-validation guards, env-allowlisted exec) — **none of which we pin**. The commit states `cargo audit` returns clean across the workspace. *Evidence: MEASURED (commit message + file list). Conclusion: no pinned version has an outstanding advisory; no urgent bump required.* The NaN-sort hardening is panic-robustness hygiene our pinned 2.0.4-era crates predate, which is one more reason for the routine bumps below.
+
+**Version-bump recommendations (follow-up PR — no Cargo.toml change in this ADR):** `ruvector-mincut` 2.0.4→2.0.6, `ruvector-solver` 2.0.4→2.0.6, `ruvector-attention` 2.0.4→2.1.0, `ruvector-gnn` 2.0.5→2.2.0. Current: `ruvector-core` 2.2.0, `ruvector-attn-mincut` 2.0.4, `ruvector-temporal-tensor` 2.0.6, `ruvector-crv` 0.1.1 — all at latest published. Nothing in the sync changes §2.1.2 geometry conditioning (our `viewpoint/attention.rs` `GeometricBias` already implements the fusion mechanism) or the ADR-150 MAE recipe (training stays in tch).
+
+## 3. Consequences
+
+**Positive:** the calibration system gains the one mechanism (geometry conditioning) the 2026 literature identifies as the difference between layout-brittle and layout-robust supervised WiFi pose; ADR-150 gets a measured training recipe instead of a guessed one; we acquire two external benchmarks (WiFlow-STD, PerceptAlign dataset) to keep our claims honest.
+
+**Negative / risks:** geometry records add schema surface to banks (mitigated: optional + versioned); every adopted number is preprint-grade until our own benchmark runs land (mitigated by §2.2's no-citation rule); PerceptAlign dataset license is unconfirmed (gated); name collision risk in docs (mitigated: "WiFlow-STD (DY2434)" naming rule).
+
+**Re-check by 2026-12:** 802.11bf silicon, esp_wifi_sensing maturity (v0.1.x today), and the preprint field (newest source Apr 2026).
+
+## 4. Open questions (carried from the research run)
+
+1. Does WiFlow-STD retain accuracy when fine-tuned on ESP32-S3/C6 CSI (fewer subcarriers, lower SNR), scored on our 17-keypoint set? (§2.2 answers this.)
+   > **Partial answer (MEASURED 2026-06-11, measurement (b) on 2,046 single-room windows — `benchmarks/wiflow-std/RESULTS.md`):** pretrained init shows strong *optimization* transfer (65% PCK@20 vs scratch's 0% collapse under the same budget) but **no feature transfer** (frozen-trunk + linear adapter ≈ 0%). And no run beat the mean-pose baseline (95.9% PCK@20 — single subject, near-static normalized coords), so no CSI→pose capability is citable from this data. A definitive answer needs multi-subject/multi-position data where the mean pose is weak.
+2. Is the PerceptAlign dataset downloadable under a usable license, and does the two-checkerboard procedure work with ESP32 transceiver geometry? (§2.1.4 gate.)
+3. Will esp_wifi_sensing evolve toward 802.11bf compliance, replacing opportunistic CSI extraction?
+
+## 5. Source register (evidence-graded)
+
+| Source | Type | Used for | Grade |
+|---|---|---|---|
+| arXiv 2601.12252 (PerceptAlign, MobiCom'26) | preprint+acceptance | F1, §2.1 | CLAIMED numbers; failure mode corroborated |
+| arXiv 2602.08661 + DY2434 repo (WiFlow-STD) | preprint + code | F2, §2.2 | numbers CLAIMED; artifacts MEASURED |
+| arXiv 2511.18792 (UNSW MAE) | preprint | F3, §2.3 | ablations MEASURED in-study; pose transfer hypothesis |
+| IEEE SA 802.11bf-2025 record | standards body | F4, §2.4 | MEASURED |
+| Espressif component registry + esp-csi repo | vendor | F4, §2.4 | MEASURED; "drop-in" REFUTED 0-3 |
+| arXiv 2506.16957 + ZTE repo (ZTECSITool) | vendor preprint + code | F4, §2.4 | capability CLAIMED; code MEASURED |
+| arXiv 2601.18200 (HeterCSI), OpenReview LMufK3vzE5 (FMCW pilot), arXiv 2509.15258 (survey) | preprints | F5, §2.5 (screened out) | MEASURED (full-text inspection) |
@@ -0,0 +1,168 @@
+# ADR-153: IEEE 802.11bf-2025 Forward-Compatibility Protocol Model for wifi-densepose-hardware
+
+- **Status**: accepted
+- **Date**: 2026-06-10
+- **Deciders**: ruv
+- **Tags**: hardware, protocol, sensing, 802.11bf, forward-compatibility
+
+## Context
+
+IEEE 802.11bf-2025 (WLAN Sensing) is an **Active Standard**: board approval
+2025-05-28, published 2025-09-26 (verified against the IEEE SA record,
+<https://standards.ieee.org/ieee/802.11bf/11574/>). Its scope modifies the
+MAC, HE and EHT PHY service interfaces, plus DMG and EDMG PHYs, for WLAN
+sensing in **1–7.125 GHz** and **above 45 GHz** bands, with formal sensing
+measurement setup, measurement instance, feedback/reporting, and
+sensing-by-proxy (SBP) procedures (ADR-152 F4, evidence grade MEASURED).
+
+No commodity silicon implements the standard yet — ESP32 parts included.
+ADR-152 §2.4 therefore decided "track silicon; no code now", with RuView's
+opportunistic CSI extraction remaining the mechanism. That left a gap: when
+silicon does land, RuView would have no typed model of the standard's
+procedures to bind to, and the integration would start from zero.
+
+ADR-152 §2.4 originally classified 802.11bf as a hardware watch item with no
+implementation work until commodity silicon exposes standardized sensing
+measurements. This ADR amends that clause: OTA binding remains deferred, but
+a pure Rust protocol model, session FSM, transport seam, and opportunistic
+CSI bridge will be implemented now so RuView consumers can target a stable
+standardized sensing interface before silicon arrives.
+
+The user directed (2026-06-10) that this **forward-compatibility protocol
+model** — a protocol surface, not a conformance implementation — be built
+now.
+
+## Decision
+
+Implement an `ieee80211bf` **forward-compatibility protocol model** in
+`wifi-densepose-hardware` (pure Rust, no internal deps, simulation-testable,
+no OTA path):
+
+> This module is not a certified 802.11bf implementation. It models the
+> public procedure shape needed by RuView and RuvSense, while intentionally
+> avoiding OTA frame binding until chipset support and vendor APIs exist.
+
+1. **`types.rs`** — typed structures for the standard's sensing procedures
+   (sub-7 GHz focus; DMG stubbed): Sensing Measurement Setup (setup ID,
+   initiator/responder and transmitter/receiver roles, bandwidth,
+   periodicity, threshold-based reporting parameters), Sensing Measurement
+   Instance, Sensing Measurement Report (CSI-variant payload), SBP
+   request/response, termination. Two future-proofing requirements:
+
+   - **Version gates** — every negotiated surface is tagged with a spec
+     profile, because vendors will expose partial or renamed capabilities
+     first:
+
+     ```rust
+     pub enum SpecProfile {
+         DraftCompatible,
+         Ieee80211Bf2025,
+         VendorExtension(String),
+     }
+     ```
+
+   - **Capability negotiation** — no hardcoded ESP32 assumptions in the
+     future-silicon path:
+
+     ```rust
+     pub struct SensingCapabilities {
+         pub sub_7_ghz: bool,
+         pub dmg: bool,
+         pub edmg: bool,
+         pub csi_report: bool,
+         pub threshold_reporting: bool,
+         pub sensing_by_proxy: bool,
+         pub max_bandwidth_mhz: u16,
+         pub max_period_ms: u32,
+         pub max_active_setups: u16,
+     }
+     ```
+
+   - **Privacy and governance fields** — sensing is presence inference, not
+     just radio telemetry. Every `SensingMeasurementSetup` carries policy
+     metadata (required, not optional), for enterprise, elderly-care,
+     retail, workplace, and municipal deployments:
+
+     ```rust
+     pub enum ConsentMode {
+         LabOnly,
+         ExplicitConsent,
+         ManagedEnterprisePolicy,
+         Disabled,
+     }
+     ```
+
+2. **`session.rs`** — deterministic event-driven session state machine:
+   `Idle → SetupNegotiating → Active → Terminating → Idle`, with explicit
+   rejection paths (unsupported parameters, setup-ID collision) and timeout
+   handling.
+3. **`transport.rs`** — a `SensingTransport` trait abstracting frame
+   exchange; a `SimTransport` test double; and an `OpportunisticCsiBridge`
+   adapter mapping today's ESP32 CSI extraction onto the report path
+   (measurement instances ≈ CSI frame batches), so current hardware sits
+   behind the standardized interface. **Replaceability benchmark
+   (acceptance test):** RuvSense must consume either ESP32 opportunistic CSI
+   or future 802.11bf chipset reports through the same `SensingTransport`
+   and `SensingMeasurementReport` path, with no consumer-side rewrite — a
+   future chipset adapter replaces `OpportunisticCsiBridge` without changing
+   consumers.
+
+Constraints: input validation at boundaries (typed errors, no panics on
+adversarial input), files under 500 lines, all protocol tests runnable
+without hardware.
+
+### Acceptance checklist
+
+| Area            | Acceptance test                                                      |
+| --------------- | -------------------------------------------------------------------- |
+| Types           | Serde round trip for setup, instance, report, SBP, termination       |
+| FSM             | Idle → setup → active → terminating → idle                           |
+| Rejection       | Unsupported bandwidth, invalid period, duplicate setup ID            |
+| Timeout         | Negotiation timeout returns typed error and resets to Idle           |
+| Threshold       | Report emitted only when threshold condition is crossed              |
+| SBP             | Proxy request maps to responder path without direct sensor coupling  |
+| Bridge          | ESP32 CSI batch becomes standardized measurement report              |
+| Safety          | No panics on malformed inputs                                        |
+| CI              | All protocol tests run without hardware                              |
+| Maintainability | Each file under 500 lines                                            |
+
+### Non-Goals
+
+This ADR does not claim IEEE 802.11bf conformance, certification, or OTA
+interoperability. It creates a typed protocol compatibility layer so RuView
+can consume standardized sensing reports when commodity silicon exposes
+them. Vendor-specific frame exchange, firmware hooks, trigger-frame
+sounding, and certification test vectors remain future ADRs.
+
+## Consequences
+
+### Positive
+- RuView can adopt standardized WLAN sensing the day any chipset exposes
+  802.11bf measurements — the data model, session FSM, and transport seam
+  already exist and are tested.
+- The `OpportunisticCsiBridge` gives current ESP32 nodes a standardized-shape
+  interface now, decoupling RuvSense consumers from the extraction mechanism.
+- Simulation transport enables protocol-level tests in CI without hardware.
+- `SpecProfile` + `SensingCapabilities` give a clean escape hatch for the
+  partial/renamed vendor capabilities that will certainly arrive first.
+- Consent/policy metadata is structural from day one, not retrofitted.
+
+### Negative
+- Code written against a standard with zero silicon risks drift: vendor
+  implementations may interpret parameters differently; the layer may need
+  rework at first real binding (drift risk scored 7/10 at acceptance).
+- Adds maintenance surface to wifi-densepose-hardware before any
+  user-visible benefit (maintenance cost scored 3/10 — small without OTA).
+
+### Neutral
+- ADR-152 §2.4's "watch item" remains: revisit when silicon/certification
+  appears (re-check by 2026-12). This ADR changes only the "no code now"
+  clause.
+
+## Links
+
+- ADR-152 — WiFi-Pose SOTA 2026 Intake (F4, §2.4 — amended by this ADR)
+- ADR-028 — ESP32 capability audit (opportunistic CSI extraction baseline)
+- ADR-029 — RuvSense multistatic sensing mode (consumer of sensing reports)
+- IEEE 802.11bf-2025 — Active Standard, board approval 2025-05-28, published
+  2025-09-26: <https://standards.ieee.org/ieee/802.11bf/11574/>
@@ -0,0 +1,242 @@
+# ADR-154: Signal/DSP Beyond-SOTA Sweep — Milestone 0 (Correctness, Provable Perf, and the SOTA Landscape)
+
+| Field | Value |
+|-------|-------|
+| **Status** | Proposed |
+| **Date** | 2026-06-11 |
+| **Deciders** | ruv |
+| **Codebase target** | `wifi-densepose-signal` (`ruvsense/`, `features.rs`, `csi_processor.rs`, `spectrogram.rs`, `bvp.rs`), benches, docs |
+| **Relates to** | ADR-134 (CIR sparse recovery), ADR-135 (Empty-Room Baseline), ADR-029/030/032 (Multistatic mesh + security), ADR-152 (WiFi-Pose SOTA 2026 intake), ADR-153 (802.11bf forward-compat) |
+| **Scope** | Milestone 0 of the beyond-SOTA signal/DSP sweep: high-leverage **correctness/security fixes**, two **measured** perf wins, the per-module SOTA landscape with evidence grades, and a prioritized roadmap. **45 review findings were explicitly deferred** (§7 backlog) — **now all addressed across Milestones 0–3** (§7.4 backlog cleared 2026-06-13); nothing was silently dropped. |
+
+---
+
+## 0. PROOF discipline (this ADR's contract)
+
+This project has been publicly accused of "AI slop." This ADR answers that with **evidence, not adjectives**:
+
+- Every claimed code improvement ships with a **committed regression test** (correctness) or a **committed criterion bench** (performance).
+- Every perf number below is **MEASURED before/after** with the exact reproduce command. A perf claim without a measured before/after is **UNPROVEN** and is not made here.
+- Every external SOTA reference is graded **MEASURED** / **CLAIMED** / **THEORETICAL**, distinguishing what a paper *measured* from what it *asserts* and from what is merely *plausible*.
+- The headline finding — a **dead CIR coherence gate that silently fell back in production for every canonical frame** — is disclosed in full (§2), not buried.
+
+Test machine for the perf numbers: Windows 11, `cargo bench --release`, criterion 0.5. Numbers are wall-clock medians on this box; they are about **ratios** (before/after), which are stable across machines, not absolute ns.
+
+---
+
+## 1. Context
+
+The RuvSense signal stack (16 `ruvsense/` modules + the classic `features.rs`/`csi_processor.rs`/`spectrogram.rs`/`bvp.rs` pipeline) grew quickly across ADR-014/029/030/134/135. A beyond-SOTA review surfaced ~50 findings ranging from two **critical correctness/security defects** to micro-optimizations and SOTA-gap research items. Milestone 0 closes the **provable, high-leverage subset**: the two criticals, a divide-by-zero trio, two measured perf wins, and the research landscape. The remaining ~45 are catalogued in §7 so the backlog is explicit and auditable.
+
+---
+
+## 2. The headline finding — the ADR-134 CIR coherence gate was DEAD in production (CRITICAL, FIXED)
+
+### 2.1 What was wrong
+
+`MultistaticFuser` fuses **canonical CSI frames**: `hardware_norm.rs` resamples every chipset onto a uniform **56-tone canonical grid** before fusion (`HardwareNormalizer`, default `canonical_subcarriers = 56`). The ADR-134 CIR coherence gate (`cir_gate_coherence`, multistatic.rs) is supposed to blend a CIR dominant-tap ratio into the cross-node coherence — `coherence = 0.7·freq + 0.3·dominant_tap_ratio`.
+
+But the gate was wired to `CirEstimator::new(CirConfig::ht20())` (`with_cir_ht20`), and `ht20()` expects **64 FFT bins or 52 active tones**. A canonical-56 frame matches *neither*, so every call returned `CirError::SubcarrierMismatch` and `cir_gate_coherence` hit its **silent `Err(_) => freq_coherence` fallback** (multistatic.rs). Net effect: **the CIR gate never ran on a single production frame** — `use_cir_gate = true` was indistinguishable from `false`. This is the exact shape of "AI slop": a feature that compiles, has tests on the *estimator*, and is dead at the *integration seam*.
+
+### 2.2 The fix (the gate now actually runs)
+
+- New `CirConfig::canonical56()` (cir.rs): 64-bin HT20 framing, **56 active tones**, 168 delay taps, Φ built over a contiguous −28..+28 active-tone grid (also the native Atheros-56 layout). `bandwidth_hz`/`tap_spacing` stay physically correct for a 20 MHz HT20 channel; only the active-tone count differs from `ht20()`.
+- New `MultistaticFuser::with_cir_canonical56()` — the **correct default** for the RuvSense pipeline. `with_cir_ht20()` is retained for genuine raw-64/52 feeds and now carries a loud doc-warning.
+- `active_indices()` handles `(64, 56)` explicitly and the fallback now selects the slice whose length matches `num_active` (so Φ's column count is always self-consistent — no silent fall-through to the 52-index slice).
+- The remaining silent fallback is made **LOUD**: a `SubcarrierMismatch` inside `cir_gate_coherence` now fires a `debug_assert!` naming the misconfiguration ("CIR gate DEAD … build it with `CirConfig::canonical56()`"). A *config* error can no longer hide as a graceful runtime degrade.
+- `cir_estimate_first()` exposes the raw `estimate()` verdict so a test can **count Ok vs Err** on a canonical-56 stream.
+
+### 2.3 The PROOF (committed regression tests, `ruvsense::multistatic::tests`)
+
+| Test | Asserts | Result |
+|------|---------|--------|
+| `cir_gate_ht20_is_dead_on_canonical56` | old ht20 estimator on 8 canonical-56 frames → **0 Ok, 8 `SubcarrierMismatch`** | the dead gate, measured |
+| `cir_gate_canonical56_is_alive` | new canonical56 estimator on the same 8 frames → **8 Ok, 0 Err** | the gate runs |
+| `cir_gate_on_changes_coherence_vs_off` | `coherence(gate on)` ≠ `coherence(gate off)` (\|Δ\| > 1e-6) | the CIR term is actually applied |
+| `cir_gate_dead_ht20_equals_gate_off` (release-only) | dead-ht20 coherence == gate-off coherence (\|Δ\| < 1e-9) | confirms the silent degradation the fix removes |
+
+**Reproduce:**
+```bash
+cd v2 && cargo test -p wifi-densepose-signal --no-default-features --lib \
+  ruvsense::multistatic::tests::cir
+# 3 passed (the 4th is #[cfg(not(debug_assertions))], add --release to run it)
+```
+
+**Resolution: FIXED** (not merely loud-fail-documented). The gate now decodes 100% of canonical-56 frames where it previously decoded 0%.
+
+---
+
+## 3. The second critical — NaN/inf adversarial-detector bypass (CRITICAL, FIXED)
+
+### 3.1 What was wrong
+
+`AdversarialDetector::check` (adversarial.rs) takes per-link `link_energies: &[f64]`. A single **NaN/inf** entry bypassed the whole detector: every `e > threshold` test is `false` on NaN, the Gini sort used `partial_cmp().unwrap_or(Equal)`, and the final `anomaly_score.clamp(0,1)` returns NaN on a NaN input. A real RF link can never have NaN/inf energy, so a non-finite input is *itself* the strongest possible spoof — yet it could slip through as "clean."
+
+### 3.2 The fix
+
+Finite-validate at the boundary: the first non-finite `link_energies` entry now **short-circuits to a definite anomaly** (`anomaly_detected = true`, `anomaly_score = 1.0`, `affected_links = [bad_idx]`, `FieldModelViolation`), and the poisoned frame is **not** seeded into the temporal-continuity state.
+
+### 3.3 The PROOF
+
+| Test | Asserts |
+|------|---------|
+| `nan_link_energy_flags_anomaly` | a NaN link energy → `anomaly_detected`, score 1.0, affected link reported, `anomaly_count == 1` |
+| `inf_link_energy_flags_anomaly` | both `+inf` and `−inf` → anomaly, score 1.0 |
+
+```bash
+cd v2 && cargo test -p wifi-densepose-signal --no-default-features --lib \
+  ruvsense::adversarial::tests::nan_link ruvsense::adversarial::tests::inf_link
+```
+
+---
+
+## 4. Divide-by-(n−1) window trio (CORRECTNESS, FIXED)
+
+Three windowing helpers divided by `(n − 1)` with no small-`n` guard:
+
+| Site | Bug | Fix |
+|------|-----|-----|
+| `csi_processor.rs` `CsiPreprocessor::hamming_window(n)` | `n=0` underflowed `0usize − 1`; `n=1` divided by 0 → all-NaN window | `match n { 0 => [], 1 => [1.0], _ => … }` |
+| `bvp.rs` Hann window | `window_size=1` divided by 0 → NaN BVP | length-1 guard → constant `[1.0]` |
+| `spectrogram.rs` `make_window` | `size=1` divided by 0 for Hann/Hamming/Blackman | `size <= 1` short-circuit → `vec![1.0; size]` |
+
+The standard convention for a length-1 window is the constant `1.0`; length-0 is empty.
+
+**PROOF:** `test_hamming_window_degenerate_sizes` (csi_processor), `bvp_window_size_one_is_finite` (bvp), `make_window_size_0_and_1_are_safe` (spectrogram) — each asserts finiteness at sizes 0/1/2.
+
+The Python deterministic proof (`archive/v1/data/proof/verify.py`) still prints **VERDICT: PASS** with the **same** pipeline hash `f8e76f21…46f7a` — the reference path uses `n ≥ 2`, so the guard is bit-transparent there.
+
+---
+
+## 5. Measured performance wins (MEASURED before/after; benches committed)
+
+Both changes are **bit-equivalent** (asserted by a committed test) — they only remove wasted work. New criterion benches in `benches/features_bench.rs` (registered in `Cargo.toml`).
+
+**Reproduce both:**
+```bash
+cd v2 && cargo bench -p wifi-densepose-signal --no-default-features --bench features_bench
+# compile-only: append --no-run
+```
+
+### 5.1 FFT-planner caching for PSD (features.rs)
+
+`PowerSpectralDensity::from_csi_data` constructed a fresh `FftPlanner` and re-planned the FFT **on every frame** — and `FeatureExtractor::extract` calls it per frame on the hot path. New `from_csi_data_with_fft(csi, fft_size, &Arc<dyn Fft>)` reuses a plan cached in `FeatureExtractor` (built once in `new()`). Output is **bit-identical** (`psd_cached_fft_bit_identical_to_fresh` compares `f64::to_bits` of values + all summary stats across 6 FFT sizes).
+
+Bench group `psd_fft_planner` — `fresh_planner` (before) vs `cached_planner` (after), per frame:
+
+| fft_size | before (fresh plan), median | after (cached), median | speedup |
+|----------|------------------------------|-------------------------|---------|
+| 64  | 5.84 µs/frame | 1.89 µs/frame | **3.09×** |
+| 128 | 9.31 µs/frame | 3.61 µs/frame | **2.58×** |
+| 256 | 13.77 µs/frame | 6.73 µs/frame | **2.04×** |
+
+Medians from criterion (warm-up 1 s, 20 samples). Raw three-point estimates (low/median/high), per frame:
+`fresh/64 [5.27, 5.84, 6.34] µs` vs `cached/64 [1.76, 1.89, 2.03] µs`;
+`fresh/256 [13.29, 13.77, 14.32] µs` vs `cached/256 [6.26, 6.73, 7.43] µs`.
+The win is the re-planned `FftPlanner` construction the cache hoists out of the per-frame loop; it grows in *relative* terms at small FFTs (planning is a larger fraction of a cheap transform) and stays a flat ~2× at 256.
+
+### 5.2 DTW Sakoe-Chiba band honored (gesture.rs)
+
+`dtw_distance` computed the band bounds `j_start/j_end` but still iterated the **full** `1..=m` row, `continue`-ing on out-of-band cells — so the band constrained the *path* but not the *work* (still O(n·m)). The fix iterates only `j_start..=j_end` (O(n·band)), resetting just the two boundary-guard cells the recurrence can read, and computes the endpoint reachability (`|n−m| ≤ band`) at the return site. Result is **bit-identical** to the full-row version across 12 shapes × 8 band widths (`dtw_banded_bit_identical_to_fullrow`).
+
+Bench group `dtw_sakoe_chiba` — `full_row` (before) vs `banded` (after):
+
+| case | before (full row), median | after (banded), median | speedup |
+|------|-----------------------------|--------------------------|---------|
+| n=m=100, band=5  | 33.45 µs | 13.77 µs | **2.43×** |
+| n=m=200, band=5  | 122.32 µs | 29.55 µs | **4.14×** |
+| n=m=200, band=10 | 159.98 µs | 60.19 µs | **2.66×** |
+
+Medians from criterion (warm-up 1 s, 20 samples). Raw (low/median/high):
+`full_row n200_band5 [107.6, 122.3, 146.5] µs` vs `banded n200_band5 [26.4, 29.5, 33.1] µs`.
+The speedup tracks the inner-loop cell-count ratio `m / (2·band+1)` — n=m=200, band=5 → 200/11 ≈ 18× fewer cells, but euclidean-distance cost and loop overhead dominate at these sizes so the wall-clock win is ~4× (still the **largest at the longest sequence / narrowest band**, exactly as the algorithm predicts). It shrinks toward 1× as the band widens to cover the whole matrix (band=10 → 2.66×), and grows with sequence length (band=5: 2.43× at n=100 → 4.14× at n=200).
+
+> **Note on the other re-plan sites.** `spectrogram.rs`/`bvp.rs` plan their FFT **once per call** and reuse it across all frames/subcarriers (already amortized), so caching there is marginal — deferred (§7). The PSD site was the only one re-planning *per frame*.
+
+---
+
+## 6. Per-module SOTA landscape (evidence-graded)
+
+Grades: **MEASURED** (the source measured it, ideally with public method/code), **CLAIMED** (asserted, no reproducible artifact), **THEORETICAL** (plausible, no published target).
+
+### 6.1 CSI → CIR (cir.rs — our ISTA/L1 sparse recovery)
+
+- **Deep-unfolded ISTA / LISTA for CSI→CIR — MEASURED.** Learned ISTA unrolling reports ~**3 dB NMSE** improvement over classical OMP/FISTA for channel/CIR estimation (arXiv [2211.15440](https://arxiv.org/abs/2211.15440); survey [2502.05952](https://arxiv.org/abs/2502.05952)). Public methods; numbers measured in-paper. **This is our #1 future item (§7) — our `cir.rs` already builds the sub-DFT Φ that LISTA would make trainable.**
+- **Diffusion CIR prior — MEASURED (artifact).** [github.com/benediktfesl/Diffusion_channel_est](https://github.com/benediktfesl/Diffusion_channel_est) ships **public weights** for a diffusion-model channel-estimation prior. Heavier than our edge budget; tracked, not adopted.
+- **Coherence gating (the §2 gate) — THEORETICAL.** Our 0.7/0.3 freq/CIR blend is an engineering heuristic with no published accuracy target; now that it *runs*, it can finally be A/B-measured.
+
+### 6.2 Adversarial robustness (adversarial.rs)
+
+- **Adversarial-robustness eval for WiFi sensing — MEASURED.** arXiv [2511.20456](https://arxiv.org/abs/2511.20456) + the **Wi-Spoof** benchmark provide a measured evaluation protocol for spoofed/injected CSI. Our detector's physical-plausibility checks (consistency/Gini/temporal/energy) are in the same spirit; adopting Wi-Spoof as an external benchmark is a §7 item. (The §3 NaN fix is a precondition: a detector that NaN-bypasses can't be benchmarked honestly.)
+
+### 6.3 Multi-AP / multistatic fusion (multistatic.rs)
+
+- **Bayesian multi-AP fusion — CLAIMED.** arXiv [2512.02462](https://arxiv.org/abs/2512.02462) proposes a Bayesian fusion across APs; **no code released**, numbers self-reported. Our attention-weighted fusion is a different (cheaper) mechanism; tracked as a comparison target, not adopted.
+
+### 6.4 RF intention-lead / pre-movement (intention.rs) — THEORETICAL
+
+The 200–500 ms pre-movement "lead signal" framing has **no published commodity-WiFi target** we can grade. Honestly THEORETICAL; no work item.
+
+---
+
+## 7. Decision, roadmap, and the deferred-findings backlog
+
+### 7.1 Accepted now (this milestone)
+
+The §2–§5 fixes are **ACCEPTED and committed**: dead CIR gate fixed, NaN bypass fixed, window trio fixed, calibration dead-branch de-misled, two measured perf wins. All `cargo test -p wifi-densepose-signal --no-default-features` (and `--features cir`) green; Python proof PASS.
+
+### 7.2 Top accepted-future item — LISTA-for-CIR (NOT implemented here)
+
+**Unroll the existing ISTA in `cir.rs` into trainable layers (LISTA).** Effort: **M**. The sensing matrix Φ and the ISTA recurrence already exist; LISTA replaces the fixed step size / threshold with per-layer learned parameters over a fixed unroll depth. Measured target to beat: **~3 dB NMSE over OMP/FISTA** (arXiv 2211.15440 — MEASURED). Proposed, not built in Milestone 0.
+
+### 7.3 Other graded-future items
+
+- Adopt **Wi-Spoof** (arXiv 2511.20456, MEASURED) as the external adversarial benchmark for `adversarial.rs`.
+- Evaluate the **diffusion CIR prior** (public weights, MEASURED) as an offline quality ceiling — *not* an edge target.
+- Bayesian multi-AP fusion (2512.02462, CLAIMED) — comparison only, pending released code.
+
+### 7.4 Deferred Milestone-0 review findings (explicit backlog)
+
+Catalogued so nothing is silently dropped. Priority: **P1** correctness-adjacent, **P2** perf, **P3** clarity/style.
+
+**Milestone-1 update (2026-06-13):** the **four P1 backlog items** (#1, #9, #10, #13) are now cleared — #1 and #10 **RESOLVED (MEASURED)**, #9 and #13 **RESOLVED-PARTIAL (DATA-GATED:** de-magicked + boundary-tested, operating values unchanged**)**. Each fix is pinned by a regression test that fails on the old behaviour (commits `fd32f094a`, `4a9f2bcf4`, `d672fa602`, `5193f6369`); workspace `--no-default-features` green, Python proof unchanged (bit-exact).
+
+**Milestone-2 update (2026-06-13):** the **bench-first P2 perf subset** (#5, #6, #7, #8, #20) and the **three missing boundary tests** (#14, #16, #19) are now cleared — ~36 P2/P3 items remained deferred *(now cleared — see the Milestone-3 update)*. PROOF discipline (§0): every perf item was **benched before being touched** — committed in `benches/dsp_perf_bench.rs` (criterion, this Windows box). Only **#20** proved hot and was optimized; **#5/#6/#7** are committed **MEASURED-NULLs** (benched, not hot, left as-is for clarity — exactly the §5.1 "already amortized" pattern); **#8** is **MEASUREMENT-ONLY** but its `eigenvalue`/BLAS backend won't build on this Windows host, so its µs cost must come from a Linux/BLAS box (recorded, not fabricated). Commits `e839fa8f1` (#20 fix), `02e5dd13a` (#14/#16/#19 tests), `aad9464f0` (benches). Workspace `--no-default-features` green; Python proof unchanged (#20 is bit-identical, off the proof path).
+
+**Milestone-3 update (2026-06-13):** the lumped **row #21–45** P3 backlog — *"remaining clarity/doc/magic-constant/missing-boundary-test findings across `ruvsense/*`, `features.rs`, `motion.rs`"* — is now **cleared, and with it the residual P3 items #2/#12/#17/#18.** Honest enumeration first (`grep`, not the ADR's "21–45" estimate — that was a count, not 25 distinct findings): after M0–M2 the genuinely-bare in-function literals resolved to **22 de-magicked constants across 11 modules** (each → a named, documented **EMPIRICAL-DEFAULT** const that **equals the prior literal exactly**), **6 added boundary/characterization tests**, **~4 doc-only fixes** (no-behaviour-change), and **a handful of agent-flagged "findings" that were NOT real** and are reported as skipped (below). **No operating value or behaviour changed** — every module carries a `*_consts_unchanged_from_literals` pin test and every boundary test pins *current* behaviour, so a future retune is a visible, tested change. Resolution by module: `motion.rs` (**#18** — fusion weights / Doppler+variance+phase scales / confidence weights / adaptive-threshold clamp; 5 tests), `gesture.rs` (**#12** — `euclidean_distance` length-mismatch `debug_assert` documenting the silent-`zip`-truncation caller contract, behaviour-preserving in release; + confidence epsilon; + DTW n=0/m=0 boundary), `longitudinal.rs` (7-day/2σ/3-day/7-day drift thresholds + EMA-α + cosine epsilon; day-6/7 + zero-vector boundaries; the duplicated `>=7` deduped), `cross_room.rs`/`multiband.rs`/`intention.rs`/`hampel.rs` (**#17** — division-guard epsilons `1e-9`/`1e-12`/`1e-10`/`1e-15` + zero-norm/zero-variance/zero-MAD boundaries + the previously-untested `hampel half_window==0` error path + `# Errors` doc), `rf_slam.rs` (`NS_PER_DAY` + `MIGRATION_MIN_SPAN_DAYS` + fixed-map defaults; single-sighting zero-span guard), `attractor_drift.rs` (`METRIC_BUFFER_CAPACITY`/`STABLE_CENTER_WINDOW`; **documented** the implicit `recent.len()>=1` divide-safety; `min_observations` off-by-one boundary), `coherence.rs` (**#9 completion** — the residual bare `1e-6` variance-floor ×4 + default `0.95` decay; floor-effect test), `calibration.rs` (**#2 completion** — `DEFAULT_MIN_FRAMES` deduped across all 4 tier constructors + `AMP_STD_FLOOR`/`MOTION_AMP_Z_THRESHOLD`/`MOTION_PHASE_DRIFT_THRESHOLD`/`SUBTRACT_MIN_NORM`), `fusion_quality.rs` (`CONTRADICTION_PENALTY` 0.8 / bound-halfwidth 0.1; n=0 identity boundary), `temporal_gesture.rs` (confidence epsilon + L2-norm quantization scale). **NOT-REAL / skipped (reported honestly, no churn manufactured):** an agent-flagged `attractor_drift.rs:301` "divide-by-zero" is **unreachable** — the `count < min_observations` guard guarantees `recent.len()>=1` before the `PointAttractor` branch (documented + boundary-tested, **not** guarded, per the no-behaviour-change rule); agent-flagged `gesture.rs` `2.0`/`π·6` motion thresholds **do not exist** in that file (a confusion with `calibration.rs::deviation`); **`features.rs` was deliberately left untouched** (it is on the deterministic Python-proof PSD/Doppler path — its `1e-10` guards already exist and are already correct; doc-only-skipped to protect the bit-exact hash). Commits `c794d1a0c` (motion #18), `adf9ed8e4` (gesture #12), `19f5b6335` (longitudinal), `19e0373c8` (epsilon helpers #17), `c6a09b69a` (rf_slam + attractor_drift), `5a1839f33` (coherence #9 completion), `df25a303e` (calibration #2 completion), `0f931ff2f` (fusion_quality + temporal_gesture). Signal crate lib `--no-default-features` **476 passed / 0 failed / 1 ignored**; `--no-default-features --features cir` **476 / 0**; workspace `--no-default-features` **3,275 / 0 failed** (single clean run); Python proof **VERDICT: PASS**, hash `f8e76f21…46f7a` **UNCHANGED (bit-exact)**. **§7.4 backlog is now fully cleared — ADR-154's deferred findings are addressed across M0–M3 with nothing silently dropped.**
+
+| # | Module | Finding | Pri | Why deferred |
+|---|--------|---------|-----|--------------|
+| 1 | cir.rs ~937 | `phase_variance` uses **linear** variance on **wrapped** angles (doc says "variance of phase angles") — spuriously inflates near ±π | P1 | **RESOLVED (`fd32f094a`) — metric MEASURED, threshold DATA-GATED.** Replaced with Mardia's circular variance V = 1 − R̄ ∈ **[0,1]**, invariant to the cluster's position on the circle (branch-cut artefact gone). Guard re-derived against the bounded metric via named const `GHOST_TAP_CIRCULAR_VARIANCE_MAX = 0.99` (fires only when R̄ ≤ 0.01 — essentially uniform phase). The **threshold value is DATA-GATED**: a clean single-path ramp also sweeps the circle, so V alone can't separate clean from unsanitized without labelled frames — the default is deliberately conservative (strictly more permissive at the wrap boundary than the buggy linear guard). Fails-on-old: `phase_variance_circular_not_fooled_by_branch_cut` (old linear variance > TAU on wrap-straddling phases while circular V≈0, guard no longer trips), `phase_variance_circular_is_bounded_and_extremal`. |
+| 2 | calibration.rs ~311 | `subtract_in_place` had a vacuous `if active_input {ki} else {ki}` branch implying a full-FFT→bin remap that didn't exist | P3 | **Resolved (M0 + M3 `df25a303e`).** Branch removed in M0 (sequential-convention documented). M3 completed the de-magic: `DEFAULT_MIN_FRAMES=600` deduped across all four tier constructors, plus `AMP_STD_FLOOR`/`MOTION_AMP_Z_THRESHOLD`/`MOTION_PHASE_DRIFT_THRESHOLD`/`SUBTRACT_MIN_NORM` named + `calibration_consts_unchanged_from_literals`. Behaviour unchanged. |
+| 3 | spectrogram.rs / bvp.rs | FFT planner built once-per-call (already amortized across frames) | P2 | Marginal vs the per-frame PSD site; cache if these become hot. |
+| 4 | features.rs ~347 | Doppler FFT planner planned once per call, reused across subcarriers | P2 | Already amortized within the call. |
+| 5 | multistatic.rs | `node_attention_weights` recomputes consensus/softmax each call; no SIMD | P2 | **MEASURED-NULL (`aad9464f0`) — benched, not hot, left as-is.** `multistatic_attention/weights`: **181 ns** (2 nodes) … **848 ns** (8 nodes) @ 56 subcarriers — sub-µs, no hot-path allocation. A precompute/SIMD rewrite buys nothing measurable at the realistic 2–8 node fan-in; the cosine/softmax cost is dwarfed by the surrounding fusion + per-frame FFT. Bench `multistatic_attention` in `dsp_perf_bench.rs`. |
+| 6 | tomography.rs | ISTA L1 solver re-allocates voxel buffers per solve | P2 | **MEASURED-NULL (`aad9464f0`) — benched, not hot, left as-is.** A full 50-iteration `reconstruct` (256 voxels): **47.5 µs** (16 links) / **60.4 µs** (32 links). The two voxel buffers (`x`, `gradient`; ~4 KB) are already allocated *once* per `reconstruct()` and `.fill`-reused across iterations — the per-solve alloc is a negligible fraction of the O(iters·links·voxels) inner product. Reusing scratch across *calls* would force `reconstruct(&self)`→`&mut self` (API break) for no measurable gain. Bench `tomography_reconstruct`. |
+| 7 | pose_tracker.rs | Kalman gain matrices reallocated per update | P2 | **MEASURED-NULL (`aad9464f0`) — benched, not hot, left as-is.** A Kalman predict+update cycle: **150 ns** (17 keypoints) / **2.82 µs** (170). The "gain matrices" (`s:[f32;3]`, `k:[[f32;3];6]`) are fixed-size **stack** arrays, *not* heap — there is no per-update allocation to reuse; the compiler keeps them in registers/stack. Bench `pose_kalman_update`. |
+| 8 | field_model.rs | SVD recomputed on every perturbation extract | P2 | **MEASUREMENT-ONLY (`aad9464f0`) — BLAS-gated, not measurable on this host.** Correction: `extract_perturbation` does **not** recompute the SVD — it projects against the cached `modes` from `finalize_calibration`. The real per-call eigendecomposition is in the `eigenvalue`-feature `estimate_occupancy` (`cov.eigh()` on a 56×56 covariance, an O(n³)≈175k-flop symmetric eigensolve + O(n²·frames) covariance build, run per call). The bench (`dsp_perf_bench`'s `eig` module) is committed, but `openblas-src` **fails to build on this Windows box** ("Non-vcpkg builds are not supported on Windows" — the very reason the project gate runs `--no-default-features`), so a measured µs number must come from a Linux/BLAS host; **not estimated/fabricated here.** Incremental SVD remains a sized future project, not a micro-fix. |
+| 9 | coherence.rs / coherence_gate.rs | Z-score thresholds are magic constants, untested at boundaries | P1 | **RESOLVED-PARTIAL (`5193f6369`) — DATA-GATED.** De-magicked `classify_drift` (`DRIFT_STABLE_SCORE=0.85`, `DRIFT_STEP_CHANGE_MAX_STALE=10`) and the `coherence_gate.rs` defaults (`DEFAULT_ACCEPT_THRESHOLD`/`…REJECT…`/`…MAX_STALE_FRAMES`/`…PREDICT_ONLY_NOISE`) into named, documented consts marked EMPIRICAL DEFAULT; added at/just-below/just-above boundary tests (`classify_drift_*_boundary`) + `*_consts_unchanged_from_literals`. **Operating values explicitly NOT changed** — defensible values still need labelled stable/drifting traces. The gate already exposed these via `GatePolicyConfig` (config seam). |
+| 10 | longitudinal.rs | Welford update not numerically guarded for n=0 | P1 | **RESOLVED (`4a9f2bcf4`) — MEASURED.** The shared `WelfordStats` (`field_model.rs`, consumed by longitudinal.rs) `count < 2` guards already prevent the n=0 NaN / n=1 div0 / `(count−1)` underflow, but the boundary was untested. Added `welford_finite_at_n0_and_n1` (finite + documented 0.0 sentinel at n=0/n=1). Fails-on-old proof: removing the `sample_variance` guard makes the test panic with "attempt to subtract with overflow" at the `(count − 1)` underflow. |
+| 11 | cross_room.rs | Fingerprint hash collisions unhandled | P2 | Low collision prob; needs design. |
+| 12 | gesture.rs | `euclidean_distance` no length-mismatch guard | P3 | **RESOLVED (M3 `adf9ed8e4`).** Added a `debug_assert_eq!` on the two slice lengths + a doc block stating the same-`feature_dim` caller contract and that `zip()` silently truncates on a mismatch. Behaviour-preserving (no-op in release, the operating path). Also de-magicked the confidence `1e-10` epsilon and pinned the DTW `n=0`/`m=0` boundary (`dtw_empty_sequence_is_infinite`). |
+| 13 | adversarial.rs | Gini/consistency thresholds are magic constants | P1 | **RESOLVED-PARTIAL (`d672fa602`) — DATA-GATED.** Lifted the bare literals in `check`/`check_consistency` (`FIELD_MODEL_GINI_VIOLATION=0.8`, `ENERGY_RATIO_HIGH_VIOLATION=2.0`, `ENERGY_RATIO_LOW_VIOLATION=0.1`, `CONSISTENCY_ACTIVE_FRACTION_OF_MEAN=0.1`, `SCORE_W_*`) into named, documented consts marked EMPIRICAL DEFAULT; added at/just-below/just-above boundary tests (`energy_ratio_high_boundary`, `energy_ratio_low_boundary`, `field_model_gini_boundary`, `consistency_active_fraction_boundary`) + `tuning_consts_unchanged_from_literals`. **Operating values explicitly NOT changed** — defensible values still need labelled spoofed/clean CSI (Wi-Spoof, §6.2/§7.3). Bumping a const fails a boundary test (verified). |
+| 14 | cir.rs | `fft_operator` path changes the witness hash (documented) — no test that it's *numerically close* to dense | P2 | **RESOLVED (`02e5dd13a`) — tolerance test added.** `fft_operator_within_tolerance_of_dense_canonical56` pins the **full `Cir` output** of the FFT path within a *documented* relative tolerance of the dense path on the production **canonical-56** config across τ ∈ {20,50,90} ns: every tap within `1e-2·|dominant|`, identical `dominant_tap_idx`, `active_tap_count`, `ranging_valid`, `dominant_tap_ratio` within `1e-2`, `rms_delay_spread` within `1e-2` rel. A regression that lets the FFT path drift (scaling/Φ-column bug) now fails here instead of silently corrupting a downstream witness. Extends the existing HT20/single-τ `fft_estimate_matches_dense_dominant_tap`. |
+| 15 | multistatic.rs | `cir_gate_coherence` only estimates the **first** node/channel; multi-node CIR consensus unused | P2 | Design item (which node's CIR is authoritative?). |
+| 16 | phase_align.rs | Iterative LO offset estimation has no convergence cap test | P2 | **RESOLVED (`02e5dd13a`) — cap test added.** `refinement_terminates_at_iteration_cap_when_not_converging` forces non-convergence (`tolerance = 0.0`, unreachable since `max_update ≥ 0`) and asserts the loop runs **exactly `max_iterations`** then returns — proving the cap (not convergence) bounds the loop, so a non-converging input can never spin forever. Companion `refinement_converges_before_cap_on_easy_input` proves the cap is an upper bound, not the only exit. Internal-only refactor: `estimate_phase_offsets` still returns the identical offset vector; a `…_counted` core surfaces the iteration count for the test. |
+| 17 | hampel.rs | Window edge handling at series boundaries | P3 | **RESOLVED (M3 `19e0373c8`).** De-magicked the zero-MAD `1e-15` epsilon (`ZERO_MAD_EPSILON`), documented `hampel_filter`'s `# Errors`, and added the previously-untested `half_window == 0` error-path boundary (`test_zero_half_window_error`) + a zero-MAD constant-window characterization (`test_zero_mad_constant_window`). Window-edge handling itself is correct (`saturating_sub`/`.min(n)`); it is now pinned. |
+| 18 | motion.rs | Threshold constants undocumented | P3 | **RESOLVED (M3 `c794d1a0c`).** Lifted the fusion weights, Doppler/variance/phase full-scale divisors, confidence-indicator weights, and adaptive-threshold clamp into named, documented EMPIRICAL-DEFAULT consts (`motion_tuning_consts_unchanged_from_literals` pins them) + small-`n` boundary tests (correlation `n<2`, temporal-variance `len<2`, adaptive-threshold history 9-vs-10, Doppler full-scale saturation). Doc-only-plus: values unchanged. |
+| 19 | csi_ratio.rs | Division guard relies on `1e-12` epsilon; no test | P2 | **RESOLVED (`02e5dd13a`) — boundary test added.** Finding clarification: `csi_ratio.rs` implements the CSI *ratio model* as the **conjugate product** `H_i·conj(H_j)` (SpotFi/IndoTrack) — there is **no division**, hence no literal `1e-12` epsilon; the classic `H_i/H_j` ratio (which a `1e-12` guard protects) is deliberately avoided. `ratio_finite_at_and_below_1e_12_epsilon` pins the property the finding cares about: at and below the `1e-12` target magnitude (and at exact zero — where a division ratio is ±inf/NaN) the conjugate-product output is **finite**, exactly the conjugate product (bit-exact), collapses toward zero (the physically correct "no path" answer), and stays finite through `ratio_to_amplitude_phase`. |
+| 20 | spectrogram.rs | `compute_multi_subcarrier_spectrogram` re-plans per subcarrier via `compute_spectrogram` | P2 | **MEASURED-HOT (`e839fa8f1`) — optimized, bit-identical.** Hoisted the FFT plan + window out of the per-subcarrier loop (new `compute_spectrogram_with_plan` core). **56-subcarrier** multi-spectrogram: **467.88 µs → 254.75 µs = 1.84×** (window 128); **627.27 µs → 448.39 µs = 1.40×** (window 256). The removed cost is the per-subcarrier `FftPlanner` re-plan (~1.86 µs/plan @ w128 × 56). Bit-identical (`multi_subcarrier_hoisted_plan_bit_identical`, `f64::to_bits` across all 4 windows × {power,magnitude}). The most likely real win predicted by the §7.4 intro — confirmed. (Relates to #3, which stays deferred: `spectrogram.rs`/`bvp.rs` single-signal callers already plan once-per-call.) |
+| 21–45 | (assorted) | Remaining clarity/doc/magic-constant/missing-boundary-test findings across `ruvsense/*`, `features.rs`, `motion.rs` | P3 | **RESOLVED (Milestone-3, 2026-06-13).** Enumerated honestly (the "21–45" was an estimate, not 25 distinct findings): **22 bare in-function literals de-magicked → named EMPIRICAL-DEFAULT consts (each == prior literal, pinned)**, **6 boundary/characterization tests added**, **~4 doc-only fixes**, across 11 modules (`motion`, `gesture`, `longitudinal`, `cross_room`, `multiband`, `intention`, `hampel`, `rf_slam`, `attractor_drift`, `coherence`, `calibration`, `fusion_quality`, `temporal_gesture`). **No operating value changed.** **Skipped-as-not-real (reported, no churn):** `attractor_drift.rs:301` "divide-by-zero" is unreachable (guarded by `count < min_observations`) → documented + boundary-tested, not guarded; agent-flagged `gesture.rs` `2.0`/`π·6` motion thresholds don't exist there (confusion with `calibration::deviation`); **`features.rs` left untouched** (on the deterministic Python-proof path; its `1e-10` guards already exist & are correct — doc-only-skipped to keep the `f8e76f21…` hash bit-exact). See the Milestone-3 update note above and the per-row #2/#12/#17/#18 entries. |
+
+> **Horizon-ledger one-liner.** Milestone-0 DONE: dead CIR gate (FIXED+proved), NaN/inf adversarial bypass (FIXED+proved), divide-by-(n−1) window trio (FIXED+proved), calibration dead-branch (FIXED), PSD FFT-planner cache (MEASURED), DTW band (MEASURED). **Milestone-1 DONE (2026-06-13): all four P1 backlog items cleared — circular phase variance #1 (RESOLVED/MEASURED metric, DATA-GATED threshold), Welford n=0 guard #10 (RESOLVED/MEASURED), threshold magic-constants #9 & #13 (RESOLVED-PARTIAL/DATA-GATED — de-magicked + boundary-tested, values unchanged).** **Milestone-2 DONE (2026-06-13): bench-first P2 perf subset + missing boundary tests cleared — spectrogram per-subcarrier FFT re-plan #20 (MEASURED-HOT, 1.40–1.84×, bit-identical); attention/tomography/Kalman #5/#6/#7 (MEASURED-NULL — benched, not hot, left as-is); field_model eigendecompose #8 (MEASUREMENT-ONLY, BLAS un-buildable on this Windows host, number deferred to a BLAS box, NOT fabricated); fft_operator tolerance #14, phase-align convergence-cap #16, csi-ratio epsilon #19 (RESOLVED, tests added).** **Milestone-3 DONE (2026-06-13): the lumped §7.4 row #21–45 P3 backlog cleared, and with it residual P3 items #2/#12/#17/#18 — 22 magic constants de-magicked into named EMPIRICAL-DEFAULT consts (each pinned == prior literal) + 6 boundary/characterization tests across 11 modules; ~4 doc-only; not-real findings (unreachable attractor_drift div0, non-existent gesture thresholds, proof-path features.rs) reported + skipped, no churn; no operating value changed; workspace 3,275/0, Python proof bit-exact `f8e76f21…`.** **§7.4 deferred backlog is now FULLY CLEARED across M0–M3 — nothing silently dropped.**
+
+> **Sibling-crate sweep extension (2026-06-14) — `wifi-densepose-geo` + `wifi-densepose-pointcloud`.** The ADR-154-class numerical-robustness sweep (non-finite-input-poisons-persistent-state + divide-by-zero / asin-domain / degenerate-geometry) was extended to two crates *outside* this ADR's signal scope. **Two real `geo` bugs FIXED, each fails-on-old-pinned:** `terrain.rs::parse_hgt` usize-underflow panic on empty/sub-2x2 SRTM data (`1.0/(side-1)` → panic in debug / inf `cell_size_deg` poisoning `ElevationGrid::get` in release — a truncated download / 404 HTML body reaches it; now `bail!`s when `side < 2`); `coord.rs::haversine` `asin(>1)→NaN` for near-antipodal points (`h` rounds to `1.0+4e-16`; clamped to `[0,1]`). The ±90° pole `cos(lat)=0` ENU singularity is pinned no-panic without changing the transform. **`pointcloud` is confirmed-robust (no manufactured finding):** its only persistent auto-accumulating state (`occupancy` EMA + vitals) is fed solely by the integer-rssi/`sqrt`/`atan2` parser (always finite) and is provably self-healing even under an adversarial NaN/inf `CsiFrame` (`motion_score=(NaN/100).min(1.0)→1.0`; breathing `→0→clamp(5,40)→5.0`) — pinned by `nonfinite_frame_does_not_poison_persistent_state` + degenerate-voxel-fusion no-panic tests. `geo` 9→15 lib / 8 integration; `pointcloud` 18→22; 0 failed; workspace green; Python proof bit-exact `f8e76f21…`. See CHANGELOG `[Unreleased] → Fixed`.
+
+---
+
+## 8. Consequences
+
+- **Positive:** the ADR-134 CIR gate is alive for the first time in production; the adversarial detector can no longer be NaN-bypassed; three latent divide-by-zero NaN sources are gone; the per-frame PSD path and gesture DTW are measurably faster with bit-identical output; the SOTA landscape and a concrete LISTA-for-CIR roadmap are graded and recorded.
+- **Negative / honest limits:** `canonical56()` models the canonical grid as a contiguous 56-tone band — a reasonable physical interpretation of a *resampled* grid, but not a literal hardware tone map; the CIR gate still uses only the first node's CIR (#15). The `phase_variance` **metric** is now correct (Mardia circular variance, Milestone-1 #1), so the branch-cut false-trip is gone — but its ghost-tap **threshold** (`GHOST_TAP_CIRCULAR_VARIANCE_MAX = 0.99`) is a conservative DATA-GATED default, not a calibrated operating point, and still awaits labelled sanitized/unsanitized frames to tune. Likewise the de-magicked coherence/adversarial thresholds (#9/#13) keep their pre-existing empirical values pending labelled calibration.
+- **Neutral:** no public API removed; `with_cir_ht20()` kept (warned); files stay scoped; new bench is additive.
@@ -0,0 +1,259 @@
+# ADR-155: NN / Training Beyond-SOTA Sweep — Milestone 1 (Claim Integrity, Honest Validation, the Unified Metric, and the SOTA Landscape)
+
+| Field | Value |
+|-------|-------|
+| **Status** | Proposed |
+| **Date** | 2026-06-11 |
+| **Deciders** | ruv |
+| **Codebase target** | `wifi-densepose-train` (`metrics.rs`, `dataset.rs`, `proof.rs`, `rapid_adapt.rs`, `ruview_metrics.rs`, `config.rs`, `ablation.rs`, `subcarrier.rs`, `bin/train.rs`, `bin/verify_training.rs`), `wifi-densepose-nn` (`tensor.rs`, `translator.rs`, `onnx.rs`), benches, docs |
+| **Relates to** | ADR-154 (Signal/DSP sweep, Milestone 0), ADR-152 (WiFi-Pose SOTA 2026 intake), ADR-150 (RF Foundation Encoder), ADR-079 (Camera-Supervised Pose), ADR-027 (MERIDIAN), ADR-024 (AETHER) |
+| **Scope** | Milestone 1 of the beyond-SOTA NN/training sweep: the **integrity-critical** fixes that let the training/metrics subsystem substantiate a clean accuracy claim (the unified metric, leak-free validation, honest TTA, rigorous proof), a focused set of **correctness/security** fixes, two **measured** perf wins, the NN SOTA landscape with evidence grades, and a prioritized backlog. **~45 review findings are explicitly deferred (§8)** — nothing is silently dropped. |
+
+---
+
+## 0. PROOF discipline (this ADR's contract)
+
+This project has been publicly accused of "AI slop." Milestone 1 is the **most integrity-critical** of the sweep because a gap review found the training/metrics subsystem **could not substantiate a clean accuracy claim**: there were four divergent PCK implementations and three divergent OKS implementations, a model trained on real data was validated against a *synthetic* set, the dataset had no leak-free split, the test-time-adaptation path descended a *fake* gradient, and the deterministic proof self-certified on any loss decrease (including float noise) with no committed baseline.
+
+We answer that with **evidence, not adjectives**:
+
+- Every integrity fix ships with a **committed regression test that would have caught the bug**.
+- Every perf number is **MEASURED before/after** with the exact reproduce command. A perf claim without a measured before/after is **UNPROVEN** and is not made here.
+- Every external SOTA reference is graded **MEASURED** / **CLAIMED** / **THEORETICAL**.
+- We disclose, in full, what the proof does **not** prove and what remains unmeasured.
+
+### Build/test constraint (disclosed)
+
+The reportable-metric code (`metrics.rs`, `trainer.rs`, `proof.rs`, `model.rs`, `losses.rs`) is gated behind the `tch-backend` Cargo feature (libtorch FFI). libtorch is **not installed on the development host**, so the project's standard gate is `cargo test --workspace --no-default-features` (no tch). The canonical-metric *logic* is therefore validated two ways: (1) the non-tch reachable surface (`compute_pck`/`compute_oks` free functions, `dataset.rs` split, `rapid_adapt.rs`, `ruview_metrics.rs`) runs under the workspace test suite with new regression tests; (2) the `tch`-gated accumulator/trainer/proof changes are routed through those same canonical functions, so the metric definition is identical whether or not tch is present. This limitation is disclosed rather than hidden.
+
+---
+
+## 1. Context — the seven divergent metric definitions
+
+The gap review found **four** PCK and **three** OKS implementations that disagreed on normalization, on the zero-visible-joint case, and on the OKS scale:
+
+| # | Location | Normalizer | Zero-visible PCK | OKS scale |
+|---|----------|-----------|------------------|-----------|
+| PCK-1 | `metrics.rs` `MetricsAccumulator` (the trainer's) | bbox **diagonal** | **1.0** (false-perfect bug) | normalized-coord diag² |
+| PCK-2 | `metrics.rs` `compute_pck` | torso **hip↔shoulder** | 0.0 | — |
+| PCK-3 | `metrics.rs` `compute_pck_v2` | torso **hip↔hip** (pixel) | 0.0 | — |
+| PCK-4 | `training_bench.rs` | **raw threshold** (no torso) | 0.0 | — |
+| OKS-1 | `metrics.rs:443` `compute_oks` | — | — | caller `s` (`1.0` ⇒ fake Gold) |
+| OKS-2 | `metrics.rs:994` `compute_oks_v2` | — | — | `sqrt(area)` (could be 0) |
+| OKS-3 | `ruview_metrics.rs:642` | — | — | caller `s` (`1.0` ⇒ fake Gold) |
+
+Two of these are not merely inconsistent, they are **wrong in a claim-inflating direction**:
+
+- **The `MetricsAccumulator` zero-visible-joint bug** scored a sample with *no visible joints* as PCK = 1.0 ("no errors to measure"). An empty or garbage prediction could thus *inflate* the reported metric.
+- **The OKS `s = 1.0`-on-normalized-coordinates bug** ("fake Gold tier"): with keypoints in `[0,1]` and the scale fixed at `1.0`, every squared distance is ≈0 and the exponential kernel returns ≈1.0 for *any* pose. OKS looked near-perfect regardless of prediction quality.
+
+This is the same metric-bug class ADR-152 flagged. Milestone 1 closes it for real.
+
+---
+
+## 2. Decision — TIER 1: CLAIM INTEGRITY (the "prove everything" core)
+
+### 2.1 Unify the metrics — ONE canonical definition — ACCEPTED & IMPLEMENTED
+
+There is now exactly **one** PCK and one OKS that may be used for any *reported* number, in the `canonical` region of `metrics.rs`:
+
+- **`pck_canonical(pred, gt, vis, k)` — torso-normalized PCK@k.** A keypoint `j` is correct iff `‖pred_j − gt_j‖₂ ≤ k · torso`, where `torso = ‖left_hip(11) − right_hip(12)‖₂` in the keypoint coordinate space, with a **bounding-box-diagonal fallback** when the hips are not both visible. This is the COCO / ADR-152 convention validated in `benchmarks/wiflow-std/RESULTS.md` (the ~96% PCK@20 reproduction — hip↔hip torso, COCO Setting). **Zero visible joints ⇒ `(0, 0, 0.0)`** — a sample with no measurable evidence scores 0, never 1.
+- **`oks_canonical(pred, gt, vis)` — COCO OKS.** `s = sqrt(area)` is derived from the **GT pose extent** (the canonical torso size as a robust, always-positive scale proxy), never a fixed `1.0`. There is no escape hatch that makes OKS ≈ 1.0 for any pose; a degenerate (zero-extent) pose returns 0.0.
+
+**Single source of truth, enforced.** `MetricsAccumulator::update` (the trainer's), `compute_pck`, `compute_per_joint_pck`, `compute_oks`, `aggregate_metrics`, and the deprecated `compute_pck_v2`/`compute_oks_v2`/`MetricsAccumulatorV2` **all route through** `pck_canonical`/`oks_canonical`. So `Trainer::evaluate()` → `MetricsAccumulator` → canonical; the WiFlow-STD bench definition (RESULTS.md) is the reference the canonical *matches*. `eval.rs` reports MPJPE (a distinct, non-divergent error metric, unchanged). The `v2` functions and the `training_bench.rs` raw-threshold kernel are annotated **`#[deprecated]` / "DO NOT USE for reported metrics"**.
+
+**The two claim-inflating bugs are fixed and pinned by regression tests:**
+
+- `canonical_pck_zero_visible_is_zero_not_one` — no-visible ⇒ PCK 0.0 (was 1.0).
+- `canonical_oks_not_one_for_wrong_pose_on_normalized_coords` — a pose off by 3× the torso on `[0,1]` coords yields OKS < 0.2 (the old `s=1.0` path returned ≈1.0).
+- `canonical_pck_uses_hip_to_hip_torso`, `canonical_torso_falls_back_to_bbox_when_hips_hidden` — pin the normalizer.
+- `all_invisible_gives_zero_pck` (renamed from `all_invisible_gives_trivial_pck`, comment cites this ADR) — the trainer accumulator now scores no-visible as 0.
+
+**Legitimately changed test expectations** (each updated with a comment citing this finding): the historical "perfect on an all-coincident pose" fixtures used keypoints at a single point, which is *correctly unscoreable* under canonical (zero extent ⇒ no scale). Test fixtures were given a real ±0.05 hip span so the canonical normalizer is positive; `all_invisible_*` flipped from 1.0 → 0.0.
+
+### 2.2 Honest validation — leak-free split + synthetic-val disclosure — ACCEPTED & IMPLEMENTED
+
+**The leak.** MM-Fi windows are extracted with **stride 1** (`MmFiEntry::num_windows = num_frames − window_frames + 1`), so adjacent windows overlap by `window_frames − 1` frames (~99% at the default 100-frame window). And `bin/train.rs` validated a *real* MM-Fi training run against a **synthetic** val set "for pipeline verification" — any PCK it printed was meaningless on two counts.
+
+**The fix (mirroring the leak-free discipline of `occupancy_bench::EvalSplit`):**
+
+- `MmFiDataset::subject_disjoint_split(test_subject_fraction, seed) → (train_view, test_view)` partitions **whole subjects** to one side. Because every window of a subject travels with that subject, the two views share **no subject and no window** — leak-free by construction, deterministic per seed. Returns `DatasetError::InvalidSplit` on <2 subjects, bad fraction, or an empty side.
+- `assert_split_leak_free(train, test)` independently verifies subject-disjointness **and** window-index-disjointness, and is called inside the split so a leaky split can never be handed out.
+- `bin/train.rs` now **prefers the real split**; the synthetic path is reachable only as a labelled fallback (single-subject data) and is routed through a new `run_smoke_test` that prefixes every metric `[SMOKE-TEST] (DO NOT REPORT)`. `--dry-run` is likewise relabelled. A synthetic-val PCK can no longer be mistaken for a measurement.
+
+**Leak-free proof (tests):** `subject_split_is_subject_and_window_disjoint` (no shared subject, no shared window index, partition covers every window once), `subject_split_is_deterministic_for_seed`, `subject_split_rejects_single_subject`, `subject_split_rejects_bad_fraction`, `assert_leak_free_detects_injected_subject_leak` (the validator catches a deliberately-injected subject overlap — a guard against future partitioner bugs).
+
+### 2.3 rapid_adapt honesty — real gradients, scoped claim — ACCEPTED & IMPLEMENTED
+
+`rapid_adapt.rs`'s `contrastive_step`/`entropy_step` wrote a **fake gradient** (`grad += v * 0.01`) unrelated to the stated triplet / entropy objective — so any "TTA improves the metric" was unsupported by the code.
+
+**Resolution: real gradients (not removal).** The two `*_loss` functions are now **pure evaluators** of the real objective; `RapidAdaptation::adapt` descends them with a **central finite-difference gradient** of that exact loss (`∂L/∂wᵢ ≈ (L(w+εeᵢ) − L(w−εeᵢ))/2ε`). Finite differences genuinely minimize the stated objective (to O(ε²) truncation), so "the adaptation loss decreases" is now a **real, reproducible** measurement rather than an artefact of a hand-tuned step. The returned `final_loss` is the *actual* objective at the produced weights.
+
+**Honest scope caveat (recorded in the module and here):** this minimizes a *self-supervised proxy* (temporal-contrastive + prediction entropy) over a tiny LoRA bottleneck on raw CSI. It is **NOT** wired to the pose model, and **there is no measured end-to-end PCK gain on WiFi pose from this path.** TTA-on-pose is a future, **not-yet-measured** capability — no PCK improvement may be cited from this module.
+
+**Tests:** `contrastive_loss_decreases` and `entropy_loss_decreases` (20/30 real gradient steps do not increase the loss vs 0 steps), `reported_loss_is_the_real_objective_not_a_placeholder` (the returned `final_loss` equals an independent recomputation of the objective at the output weights — i.e. it is the real loss, not a fabricated number).
+
+### 2.4 proof.rs rigor — margin + committed-hash requirement — ACCEPTED & IMPLEMENTED
+
+The deterministic proof self-certified: `generate_expected_hash` blessed whatever the pipeline emitted, PASS counted *any* loss decrease (including 1e-9 float noise), and a *missing* expected hash defaulted to PASS.
+
+**Two hardenings:**
+
+1. **Minimum-decrease margin.** `MIN_LOSS_DECREASE = 1e-4`. A run counts as "learning" only when `initial − final ≥ MIN_LOSS_DECREASE` — well above float noise, far below a real step's decrease. A pipeline that only wanders by noise now **FAILS**.
+2. **No-hash is a SKIP, never a PASS.** `ProofResult::is_pass()` requires `hash_matches == Some(true)` (a *committed* `expected_proof.sha256`). An absent baseline yields SKIP (exit 2). The `verify-training` binary additionally **fails fast** on a sub-margin loss *before* the hash comparison, so a missing baseline can never downgrade a non-learning pipeline to SKIP.
+
+**What this proves — and what it does NOT (disclosed):** the proof certifies **reproducibility and determinism** (same seed ⇒ same weights ⇒ same hash) and that the optimiser *measurably* reduces a loss. It runs on a deterministic *synthetic* dataset by construction, so it does **not** prove the shipped weights came from real MM-Fi data, nor that any accuracy claim is met. Accuracy is substantiated separately (`benchmarks/wiflow-std/RESULTS.md`). There is currently **no committed `expected_proof.sha256` for the Rust proof**, so it is honestly in the SKIP state until a baseline is committed on a libtorch-enabled host — and SKIP is now reported as SKIP, not green.
+
+**Tests:** `no_committed_hash_is_skip_not_pass`, `submargin_loss_change_fails_even_without_hash`, `committed_matching_hash_with_real_decrease_passes`.
+
+---
+
+## 3. Decision — TIER 2: CORRECTNESS / SECURITY
+
+Each fix ships a test that would have caught the bug (all in the non-tch, workspace-tested surface).
+
+| Finding | File | Fix | Test |
+|---------|------|-----|------|
+| `softmax(axis)` ignored the axis (whole-tensor normalize — breaks densepose per-pixel probs) | `nn/tensor.rs` | softmax along the given axis per lane; out-of-range axis ⇒ `NnError` (no panic) | (tier-2 suite) |
+| `apply_attention` identity/uniform stub (any "with attention" ablation == without) | `nn/translator.rs` | **implemented real single-head scaled-dot-product attention** (`softmax(QKᵀ/√d)V` with Q/K/V/output projections); mis-shaped checkpoint projections rejected so a bad checkpoint can't silently become a no-op | `test_attention_is_not_uniform_stub`, `test_attention_rejects_wrong_weight_shape` |
+| `config.validate()` had no UPPER bounds (config-OOM class still open) | `train/config.rs` | upper bounds on `window_frames`/subcarriers/`backbone_channels`/`heatmap_size`/keypoints/parts/`batch_size`; reject negative `gpu_device_id` | rejection tests; defaults+presets still validate |
+| `subcarrier.rs` panic on non-contiguous input | `train/subcarrier.rs` | graceful path / typed error on strided input | non-contiguous-input test |
+| `ablation.rs` `latency_percentiles` `partial_cmp().unwrap()` NaN panic | `train/ablation.rs` | `total_cmp` / NaN-guarded compare | NaN-input no-panic test |
+| `onnx.rs` unchecked `-1` dim cast | `nn/onnx.rs` | reject negative/zero output dims with `NnError` | guarded-dim test |
+| `ruview_metrics` `compute_single_oks` `s=1.0` fake-Gold + unguarded `[j]<17` | `train/ruview_metrics.rs` | derive scale from GT extent when none supplied; reject `s≤0`; bound the loop to array extents | `oks_rejects_nonpositive_scale`, `oks_does_not_panic_on_short_arrays`, `oks_not_perfect_for_wrong_pose_with_derived_scale` |
+
+`rf_encoder.rs` was inspected and found to contain **no checkpoint-deserialization assert**: its `assert_eq!`s in `LinearHead::new` / `ContrastiveBatcher::new` are documented construction-time API contracts on *programmer-supplied* vector lengths, not adversarial-input panics — the described bug does not exist there. Any genuine checkpoint-load assert lives in the tch-gated `proof.rs`/`trainer.rs` path and is deferred (§8) as unverifiable without libtorch. Test pass counts: nn `--no-default-features` **35 passed**, nn `--features onnx onnx::tests` **3 passed**, train `--no-default-features` lib **176 passed**.
+
+---
+
+## 4. Decision — TIER 3: MEASURED perf wins (new criterion benches)
+
+All numbers MEASURED on the Windows dev host with the `onnx` feature (`ort 2.0.0-rc.11`, runtime auto-downloaded), committed in `nn/benches/onnx_bench.rs`.
+
+### 4.1 Zero-copy ORT input — LANDED, MEASURED
+
+`onnx.rs` built the ORT input via `arr.iter().cloned().collect::<Vec<f32>>()` — a full element-wise copy. Replaced with a contiguous fast path (`arr.as_slice() ⇒ single memcpy`, iterator fallback only for strided views).
+
+- **Reproduce:** `cargo bench -p wifi-densepose-nn --no-default-features --features onnx --bench onnx_bench -- onnx_input_copy`
+- **Measured** (input `[1,256,64,64]` = 1.05M f32): **1.972 ms → 1.336 ms (~1.48× faster)**, 532 → 785 Melem/s. Strided fallback unchanged (within noise), correctness preserved. End-to-end real-model inference: ~45.9 µs.
+
+### 4.2 ONNX per-inference write-lock — DIAGNOSED, NOT LANDABLE (honest)
+
+`OnnxBackend::run` takes a `parking_lot::RwLock` **write** lock per inference, serializing concurrency. The intended fix was a read-lock. **It is not landable on `ort 2.0.0-rc.11`:** the safe `Session::run` is `&mut self` (verified against the vendored source) — there is no `&self` run path, so a read-lock fails the borrow checker. The underlying C++ `OrtSession::Run` is thread-safe, but exploiting that would require an `unsafe` interior-mutability bypass; we did **not** introduce that soundness risk. The write lock was kept, with a doc comment recording the upgrade path (a future `ort` with `&self` run ⇒ flip to `read()`).
+
+- **Harness landed anyway**, empirically proving the serialization: `cargo bench -p wifi-densepose-nn --no-default-features --features onnx --bench onnx_bench -- onnx_concurrency` → throughput **drops** with more threads (1 thr 19.4 Kelem/s → 2 thr 16.9K → 4 thr 14.0K → 8 thr 14.3K). When `ort` exposes `&self` run, the one-line lock change will show the speedup on this same bench.
+
+The native-conv naive-loop rewrite was **deferred** (§8) as out of scope for a measured milestone.
+
+---
+
+## 5. The NN / training SOTA landscape (graded)
+
+| Candidate | What | Grade | Verdict |
+|-----------|------|-------|---------|
+| **GraphPose-Fi** (arXiv 2511.19105, code github.com/Cirrick/GraphPose-Fi) | Graph/skeleton pose **decoder** for cross-environment WiFi pose; MM-Fi, 17 joints — matches our setup. ADR-150 §2.2 named a graph decoder but never built it. | **CLAIMED** (preprint; cross-env gains author-reported) | **Top beyond-SOTA candidate. Propose as ACCEPTED-future — NOT built here.** Best fit because the decoder is a drop-in on our 17-joint MM-Fi backbone and directly targets the cross-environment brittleness ADR-150/ADR-027 fight. |
+| **ONNX INT4** | Extend our **measured** INT8 ONNX quantization to INT4 for edge. | **THEORETICAL** for our pipeline (INT8 is MEASURED; INT4 untested here) | #2 priority — natural extension of a measured capability. |
+| **CSI-JEPA vs MAE A/B** | Joint-embedding predictive pretraining vs the ADR-152 §2.3 MAE recipe. | **CLAIMED** (JEPA strong elsewhere) — **honest caveat: no JEPA *or* MAE result exists on WiFi POSE yet** (ADR-152 F3: UNSW MAE downstream tasks are classification, not pose). | #3 — run as a measured A/B, do not pre-announce a winner. |
+| **"Mamba-CSI-pose"** | A state-space-model CSI pose backbone. | — | **Does NOT exist. Do not propose it.** No such artifact in the 2025–2026 literature; naming it would be exactly the kind of unfounded claim this sweep exists to prevent. |
+
+---
+
+## 6. Validation
+
+- `cargo test --workspace --no-default-features` — green (the metric unification legitimately changed a handful of test expectations; each was updated with a comment citing the finding, and the trainer/eval/proof now all route through the one canonical metric).
+- `python archive/v1/data/proof/verify.py` — `VERDICT: PASS` (Python pipeline proof, independent of the Rust changes).
+- New criterion benches compile and run under the `onnx` feature.
+
+---
+
+## 7. What changed, file by file
+
+- `metrics.rs` — `canonical_torso_size`, `pck_canonical`, `oks_canonical` (single source of truth); `MetricsAccumulator`/`compute_pck`/`compute_per_joint_pck`/`compute_oks`/`aggregate_metrics` route through them; `compute_pck_v2`/`compute_oks_v2`/`MetricsAccumulatorV2` deprecated → canonical; zero-visible and `s=1.0` bugs fixed; canonical bug-catching tests.
+- `dataset.rs` — `subject_disjoint_split`, `MmFiSplitView`, `assert_split_leak_free`; leak-free split tests.
+- `error.rs` — `DatasetError::InvalidSplit`.
+- `bin/train.rs` — prefer real subject-disjoint split; synthetic path relabelled `run_smoke_test` ("DO NOT REPORT").
+- `proof.rs` + `bin/verify_training.rs` — `MIN_LOSS_DECREASE` margin; no-hash ⇒ SKIP-not-PASS; sub-margin ⇒ FAIL-not-SKIP; new tests.
+- `rapid_adapt.rs` — fake gradient removed; finite-difference gradient of the real objective; honesty docs + tests.
+- `ruview_metrics.rs` — OKS scale derived from GT extent (no `s=1.0`); `s≤0` rejected; OKS loop bounded; tests.
+- `config.rs` / `ablation.rs` / `subcarrier.rs` / `nn/tensor.rs` / `nn/translator.rs` / `nn/onnx.rs` — Tier-2 fixes (§3) + Tier-3 perf (§4).
+- `training_bench.rs`, `sensing-server/training_api.rs` — divergent local PCK kernels annotated "DO NOT USE for reported metrics"; the sensing-server torso-height PCK unification is a **deferred** backlog item (separate service + tch boundary).
+
+---
+
+## 8. Deferred backlog (NOT silently dropped)
+
+The gap review surfaced ~60 findings; this milestone scoped to the provable integrity-critical subset plus two measured perf wins. The remainder are tracked here for a future ADR-155 milestone:
+
+- **GraphPose-Fi graph decoder** — build the §5 top candidate (ACCEPTED-future, not built).
+- **ONNX INT4** quantization; **CSI-JEPA vs MAE** A/B; the rest of the §5 roadmap.
+- **ONNX read-lock concurrency win** — blocked on an `ort` release exposing `&self` `Session::run` (§4.2); harness already committed.
+- ~~**native-conv naive-loop** perf rewrite (§4).~~ — **RESOLVED in Milestone-2 (see §8.2): bench-first → MEASURED-INCONCLUSIVE, no perf change shipped.**
+- ~~**`rf_encoder.rs` `assert_eq!`-on-checkpoint**~~ — **RESOLVED in Milestone-2 (see §8.2): a pure-Rust fallible `LinearHead::try_new` guard was added.** Any genuine **tch-gated** panic-on-input sites remain deferred — they require a libtorch host to compile/verify (`model.rs` `amp_fc1` unbounded alloc is *indirectly* guarded by the new `config.validate()` upper bounds, but a direct guard + test is deferred).
+- ~~**`sensing-server/training_api.rs` PCK**~~ — **RESOLVED in Milestone-1b (see §8.1, Goal C).** Relabelled (not unified) — and the audit found the *real* live divergence is in `trainer.rs`, not the orphaned `training_api.rs`.
+- ~~**`test_metrics.rs` reference kernels**~~ — **RESOLVED in Milestone-1b (see §8.1, Goal B).** Canonical core hoisted to an un-gated module; the integration test now validates the production functions against hand-computed fixtures + a differential cross-check.
+- **`metrics.rs` `compute_pck_v2`/`compute_oks_v2`/`MetricsAccumulatorV2`/`evaluate_dataset_v2`/`hungarian_assignment_v2`** — confirmed to have **zero external callers** (only `evaluate_dataset_v2`→`MetricsAccumulatorV2` internally). They are already `#[deprecated]` and route through canonical, so they are not a *divergent-definition* risk, only dead weight. Left in place this pass (public API in a tch-gated module; deleting needs a deprecation-cycle + tch host to verify) — flagged here for a future cleanup, NOT deleted silently.
+- **`sensing-server/trainer.rs` `pck_at_threshold` (raw) + `oks_map(area=1.0)` and the `training_bench.rs` raw kernel** — relabelled in Milestone-1b (§8.1); true unification onto `pck_canonical`/`oks_canonical` (needs a torso scale + the train crate as a sensing-server dep) remains deferred.
+- ~~The remaining ~40 lower-severity review findings (style, micro-opt, doc).~~ — **RESOLVED in Milestone-2 (§8.2): the host-verifiable subset is cleared.** The "~40" was an estimate; the actual host-verifiable (non-tch) train/nn surface is smaller. Enumerated resolution below.
+
+### 8.2 Milestone-2 — host-verifiable §8 P3 backlog clearance — RESOLVED
+
+Mirroring the ADR-154 M3 cleanup discipline, M2 closed the **host-verifiable (non-tch) subset** of the §8 backlog in `wifi-densepose-train` (+ the pure-Rust `rf_encoder.rs`/`densepose.rs` in `wifi-densepose-nn` that the §3/§4 items named). Everything behind `#[cfg(feature = "tch-backend")]` (`metrics.rs`, `model.rs`, `losses.rs`, `proof.rs`, `trainer.rs`, `wiflow_std/{layers,model}.rs`) is **out of host-verifiable scope** — it cannot be compiled/verified without libtorch and stays genuinely deferred (not dropped).
+
+**PROOF discipline held:** every de-magicked constant is pinned `== prior literal` by a `*_consts_unchanged_from_literals` test; every boundary test characterizes CURRENT behaviour; no operating-value or behaviour change; the Python proof stays bit-exact at `f8e76f21…46f7a` (the metrics path is off the signal proof path — asserted, not assumed). A smaller-but-true count was reported rather than inventing 40 fixes.
+
+**Enumerated finding → resolution (real counts):**
+
+| # | Finding (location) | Action | Pin/characterization test |
+|---|---|---|---|
+| 1 | `metrics_core.rs` — `0.5` vis / `1e-6` extent / `0.07` OKS-fallback sigma | de-magic → `VISIBILITY_THRESHOLD` / `MIN_REFERENCE_EXTENT` / `OKS_FALLBACK_SIGMA` | `metrics_core_consts_unchanged_from_literals`; `visibility_threshold_boundary_is_inclusive`; `degenerate_extent_below_floor_is_unscoreable` |
+| 2 | `ruview_metrics.rs` — `17` / `0.5` / `0.2` / `1e-3` / `1e-6` | de-magic → `NUM_KEYPOINTS` / `VISIBILITY_THRESHOLD` / `PCK_THRESHOLD` / `MIN_BBOX_DIAG` / `MIN_DURATION_MINUTES` | `ruview_metrics_consts_unchanged_from_literals`; `tracking_zero_duration_does_not_divide_by_zero`; `oks_short_array_is_bounded_at_keypoint_count` |
+| 3 | `subcarrier.rs` — sparse-interp `0.15`/`1e-4`/`0.1`/`1e-8`/`1e-5`/`500` | de-magic → 6 `SPARSE_*` consts | `sparse_interp_consts_unchanged_from_literals`; `compute_interp_weights_single_target_is_index_zero`; `sparse_interp_single_target_is_finite` |
+| 4 | `eval.rs` — `1e-10` division guard (×3) | de-magic → `MIN_POSITIVE_MPJPE` | `eval_min_positive_mpjpe_unchanged_from_literal`; `domain_gap_infinite_when_in_domain_perfect_but_cross_nonzero`; `domain_gap_unity_when_everything_perfect` |
+| 5 | `domain.rs` — `1e-5` LayerNorm eps | de-magic → `LAYER_NORM_EPS` | `layer_norm_eps_unchanged_from_literal` (n=0/zero-var boundary already covered) |
+| 6 | `virtual_aug.rs` — `1e-10` Box-Muller / room-scale guards | de-magic → `BOX_MULLER_U1_FLOOR` / `MIN_ROOM_SCALE` | `virtual_aug_guard_consts_unchanged_from_literals`; `augment_frame_zero_room_scale_passes_amplitude_finite` |
+| 7 | `rf_encoder.rs` — `20.0` softplus overflow threshold | de-magic → `SOFTPLUS_LINEAR_THRESHOLD` | `softplus_threshold_unchanged_from_literal` |
+| 8 | `rf_encoder.rs` — panic-only `LinearHead::new` for untrusted weights (§3) | add pure-Rust fallible `try_new` → typed `RfHeadError` (additive; `new` unchanged) | `try_new_accepts_valid_and_rejects_each_bad_shape` |
+| 9 | `densepose.rs::apply_conv_layer` naive-loop (§4) | **bench-first → MEASURED-INCONCLUSIVE**, no perf change shipped; committed bench + characterization anchor | `native_conv_matches_reference` + `benches/native_conv_bench.rs` |
+| 10 | `rapid_adapt.rs` module-doc "O(ε)" inconsistency | doc-only fix → "O(ε²)" (central differences) | n/a (doc) |
+| 11 | `geometry.rs` `DeepSets::encode` missing `# Panics` | doc-only fix (documents existing `assert!`) | n/a (doc) |
+
+**Tally:** **7 de-magicked (const + pin test)**, **9 new boundary/characterization tests**, **1 added input guard (`try_new`) + test**, **2 doc-only fixes**, **1 perf item bench-first MEASURED-INCONCLUSIVE (not shipped, deferred)**. New tests: train `--no-default-features` **303** (was 288, +15); nn `--no-default-features` lib **38** (was 35, +3).
+
+**Skipped honestly (flagged-but-not-real):** `ablation.rs` (NaN sort + boundary already fixed/tested in M1 — clean), `signal_features.rs` (consts already named, n=0 boundary already tested), `mae.rs` (no bare guard literals found), `metrics_core` already had thorough zero-visible/hip-normalizer coverage from M1. No churn was manufactured to hit a count.
+
+**Genuinely data-gated / tch-gated — remaining backlog (blocked, not dropped):** GraphPose-Fi graph decoder, ONNX INT4, CSI-JEPA vs MAE A/B (all **data/model-gated** — need a training run + datasets); ONNX read-lock concurrency win (**upstream-gated** on `ort`); the tch-gated panic-on-input sites in `proof.rs`/`trainer.rs`/`model.rs` and the `metrics.rs` `*_v2` dead-code deletion (**tch-gated** — need a libtorch host to compile/verify). **The non-tch-verifiable subset of §8 is now cleared.**
+
+### 8.1 Milestone-1b — metric-definition unification (the §8 metric subset) — RESOLVED
+
+This milestone closed the two metric-integrity items above. The work is pinned by tests, graded MEASURED, and surfaced findings the §1 table missed.
+
+**The complete, honest PCK / OKS audit map (every definition in `v2/`):**
+
+| Definition (file:line) | Normalization basis | Threshold convention | Status |
+|---|---|---|---|
+| `metrics_core.rs` `pck_canonical` (was `metrics.rs`) | **hip↔hip torso WIDTH** (bbox-diag fallback), `[0,1]` coords | `k·torso` | **CANONICAL** |
+| `metrics_core.rs` `oks_canonical` | `s=sqrt(area)` from GT pose extent | COCO kernel | **CANONICAL** |
+| `metrics.rs` `compute_pck` / `compute_per_joint_pck` / `compute_oks` | — (thin wrappers) | — | route to canonical |
+| `metrics.rs` `aggregate_metrics` / `MetricsAccumulator` | — | — | route to canonical |
+| `metrics.rs` `compute_pck_v2` / `compute_oks_v2` / `MetricsAccumulatorV2` | hip↔hip (folded) | — | **legacy-redundant, deprecated, NO callers** — route to canonical |
+| `tests/test_metrics.rs` local `compute_pck`/`compute_oks` (removed) | raw-threshold reimpl | raw | **was independent reimpl** → now validate canonical + 1 differential kernel |
+| `benches/training_bench.rs` `compute_pck` | raw-threshold | raw | distinct-by-design (bench-only), annotated DO-NOT-REPORT |
+| `sensing-server/training_api.rs` `compute_pck` | **torso-HEIGHT** (nose→hip), **pixel-space** | `ratio·torso_h`, 50px floor | **distinct-by-design** — and **ORPHAN file (not `mod`-declared, does not compile)**; relabelled `compute_pck_torso_height` |
+| `sensing-server/trainer.rs` `pck_at_threshold` | **RAW (no normalization)** | raw `thr` | **distinct, LIVE** (drives `best_pck`); **MISSED by §1 table**; relabelled `pck_raw@0.2` |
+| `sensing-server/trainer.rs` `oks_map`→`oks_single(area=1.0)` | `area=1.0` | COCO kernel | **fake-Gold, LIVE** (drives `best_oks`); **MISSED by §1 table**; relabelled `oks_map(area=1.0 proxy)` |
+
+**Findings the §1 seven-definition table under-counted (honest correction):** the live sensing-server claim surface is `trainer.rs` (in `lib.rs`), **not** the named `training_api.rs` — which is an **orphan file, never `mod`-declared, so it does not compile into the crate**. The live `best_pck` is a **raw, unnormalized** PCK and the live `best_oks` still uses the **`area=1.0` fake-Gold** path ADR-155 §2.1 reported as closed elsewhere. So the true metric landscape is **messier than §1 documented**: ≥3 PCK and ≥1 OKS live in `sensing-server`, two of them on the inflating side, and the file the ADR named for the fix was dead code. This is a finding, not a failure — recorded here rather than hidden.
+
+**Goal B (`test_metrics.rs`) — RESOLVED, MEASURED.** The canonical core (`pck_canonical`/`oks_canonical`/`canonical_torso_size`/sigmas/`bounding_box_diagonal`) was hoisted into a new **un-gated** `metrics_core` module (the full `metrics` module is `tch-backend`-gated, so the canonical definition was previously unreachable from the workspace test gate; `metrics` now re-exports it → still ONE implementation). `tests/test_metrics.rs` now asserts the **production** functions against hand-computed fixtures — `canonical_pck_matches_hand_computed_fixture` (3/4 correct ⇒ 0.75, hand-derived), zero-visible⇒0.0, hip↔hip normalizer pin, OKS perfect⇒1.0, the fake-Gold pin — plus `test_kernel_agrees_with_canonical`, a differential test where an independent raw-threshold reference must AGREE with canonical in the torso=1.0 regime. (10→12 tests.)
+
+**Goal C (`training_api.rs` PCK) — RESOLVED by RELABEL, MEASURED.** Torso-height is **load-bearing** (pixel-space, vertical nose→hip scale, `[17×3]` layout, no `ndarray`/train dep), so unifying would silently change the live numbers' meaning — exactly what to avoid. Resolution: relabel everywhere the metric surfaces so it is never read as canonical, in both the named `training_api.rs` (now `compute_pck_torso_height`, struct/JSON-field docs, `pck_torso_h@0.2` logs) **and** — the real fix — the LIVE `trainer.rs` path (`pck_at_threshold` documented raw-unnormalized; `oks_map` `area=1.0` flagged fake-Gold; `main.rs` prints `pck_raw@0.2` / `oks_map(area=1.0 proxy)`). No wire-format field or `pub`-fn renames (no silent API break). Pinned by `torso_pck_is_labelled_distinctly_from_canonical` (training_api) and `pck_at_threshold_is_raw_unnormalized_not_canonical` (the live kernel). True unification (route the live server through `pck_canonical`/`oks_canonical`) remains a deferred §8 item — it needs a torso scale on the live data and the train crate as a dep.
+
+---
+
+## 9. Consequences
+
+**Positive.** The training/metrics subsystem can now substantiate a clean accuracy claim: one documented metric used everywhere, a leak-free split, an honest TTA path, a proof that fails on noise and refuses to bless an unbaselined run, and two of the most claim-inflating bugs (false-perfect PCK, fake-Gold OKS) closed and pinned by regression tests. The unmeasured/unprovable parts are **disclosed**, not hidden.
+
+**Negative / honest.** The reportable-metric tch-gated code cannot be compiled on the dev host (libtorch absent), so its validation rests on routing through the workspace-tested canonical functions plus review; the Rust deterministic proof is in SKIP until a baseline is committed on a tch host; the ONNX concurrency win is blocked upstream; and ~45 findings are deferred. None of these is presented as done.
+
+**Picture changed by Milestone-1b (§8.1) — corrected, not hidden.** The §1 "seven divergent metrics" count was an **under-count**. The metric-unification audit (Goal A) found the live `wifi-densepose-sensing-server` carries additional, divergent definitions the §1 table omitted: a **raw, unnormalized** `pck_at_threshold` and an **`area=1.0` fake-Gold** `oks_map` in `trainer.rs` — and these, not the orphaned `training_api.rs` the backlog named, are what actually drive the live-reported `best_pck`/`best_oks`. Milestone-1b **relabelled** them (load-bearing math on different data; relabel beats false unification) and pinned the divergence with tests; full unification onto the canonical definition stays deferred. So the canonical *train/nn* metric is unified and test-validated end-to-end, but the *sensing-server* still computes (now clearly-labelled, non-canonical) progress proxies — disclosed here as the honest current state.
@@ -0,0 +1,265 @@
+# ADR-156: RuVector / Cross-Viewpoint Fusion Beyond-SOTA Sweep — Milestone 2 (Correctness Integrity, an Honest GDOP, Crafted-Input Safety, a Measured Hot-Path Win, and the ANN/Fusion SOTA Landscape)
+
+| Field | Value |
+|-------|-------|
+| **Status** | Proposed |
+| **Date** | 2026-06-11 |
+| **Deciders** | ruv |
+| **Codebase target** | `wifi-densepose-ruvector` — `viewpoint/` (`attention.rs`, `geometry.rs`, `fusion.rs`, `coherence.rs`), `mat/` (`triangulation.rs`, `heartbeat.rs`), `sketch.rs`, benches, docs |
+| **Relates to** | ADR-031 (RuView sensing-first RF mode), ADR-016/017 (RuVector integration), ADR-024 (AETHER re-ID), ADR-027 (MERIDIAN cross-env), ADR-084 (RaBitQ similarity sensor), ADR-138 (ClockQualityGate), ADR-152 (WiFi-Pose SOTA 2026 intake), ADR-154 (Signal/DSP sweep M0), ADR-155 (NN/Training sweep M1) |
+| **Scope** | Milestone 2 of the beyond-SOTA sweep: four **correctness/integrity/security** fixes on the cross-viewpoint fusion path (each pinned by a regression test that fails on the old code), one **measured** hot-path perf win + a new criterion bench, the ANN/fusion SOTA landscape graded MEASURED/CLAIMED/data-gated, and a prioritized deferred backlog. **Nothing is silently dropped.** |
+
+---
+
+## 0. PROOF discipline (this ADR's contract)
+
+This project has been publicly accused of "AI slop." Milestone 2 answers with **evidence, not adjectives** — the same contract as ADR-154/155:
+
+- Every correctness/integrity fix ships a **committed regression test that fails on the old code and passes on the new**. We verified each by reverting the fix and observing the test fail (recorded in §6).
+- Every perf number is **MEASURED before/after** with the exact reproduce command and a committed criterion bench. A perf claim without a measured before/after is **UNPROVEN** and is not made here.
+- Every external SOTA reference is graded **MEASURED** / **CLAIMED** / **DATA-GATED**, distinguishing what a paper *measured* from what it *asserts* from what our own prior measurement (ADR-152) says is **not currently the bottleneck**.
+- We disclose, in full, the **one staged finding that turned out to be a numeric no-op** (§2.1): the geometric-bias "angular wrap bug" is real as a *contract* violation but, because the bias kernel is `cos()` (even and 2π-periodic), it changes **no output value** under the current kernel. We land the fix anyway (it matches the documented contract and reuses the canonical helper) but we **do not claim a behaviour change** — that would be exactly the kind of inflation this sweep exists to prevent.
+
+Test machine for the perf numbers: Windows 11, `cargo bench --release`, criterion 0.5. Numbers are wall-clock medians on this box; the **ratio** (before/after) is the claim, not the absolute ns.
+
+Build/test gate: `cargo test --workspace --no-default-features` (the project's standard gate — no `crv`/GPU features). All fixes in this milestone are on the **default, non-feature-gated surface**, so they are fully exercised by the standard gate.
+
+---
+
+## 1. Context
+
+The cross-viewpoint fusion stack (`viewpoint/` — ADR-031) combines per-viewpoint AETHER embeddings into one fused embedding via geometric-bias attention, gated by phase coherence, with array-geometry quality scored by a Geometric Diversity Index and a Cramér-Rao bound. The `mat/` survivor-localisation helpers (`triangulation.rs`, `heartbeat.rs`) share the same crate. A beyond-SOTA review surfaced findings spanning a **mislabeled metric**, an **angular-distance contract violation**, **crafted-input panics on a network-reachable path**, and a **redundant clone in the fusion hot path**, plus an ANN/fusion SOTA-research gap. Milestone 2 closes the provable subset and grades the research landscape.
+
+---
+
+## 2. Decision — CORRECTNESS / INTEGRITY FIXES
+
+Each fix ships a regression test (all on the non-feature-gated, workspace-tested surface).
+
+### 2.1 GeometricBias angular separation — use the canonical *wrapped* distance — ACCEPTED & IMPLEMENTED (honest: numeric no-op under the current cos kernel)
+
+**The finding.** `attention::GeometricBias::build_matrix` computed the pairwise angular separation as the **raw** `|azimuth_i − azimuth_j|`. That can exceed π and mis-states the separation across the 0/2π seam (350° and 10° are 20° apart, but raw `|Δ|` = 340°). The module already had a correct wrapped helper, `geometry::angular_distance` (returns `[0, π]`), but it was **private** and `GeometricBias` did not use it.
+
+**The honest correction (disclosed, not hidden).** The bias kernel is `w_angle·cos(theta_ij)`. Because `cos` is **even and 2π-periodic**, `cos(raw) == cos(wrapped)` for every pair (verified numerically: max abs diff `1.1e-16` across seam-crossing test cases). So under the *current* kernel this "bug" produces **identical bias values** — it is a **contract violation, not a behaviour bug**. We say so plainly rather than dressing a no-op as a fix.
+
+**Why land it anyway.** (1) It makes the code satisfy its own documented contract (`theta_ij`: "angular separation in radians", which must be `[0, π]`). (2) It reuses the **single canonical** `angular_distance` helper (now made `pub`), eliminating a divergent angle computation — the same single-source-of-truth discipline ADR-155 applied to metrics. (3) It is **correct by construction** for any future non-even angular kernel (e.g. a linear `w_angle·theta_ij` penalty), which the raw-diff form would silently break.
+
+**Tests:** `geometric_bias_angular_separation_uses_wrapped_distance` (pins that a seam-crossing pair's wrapped distance is 20° while its raw `|Δ|` exceeds π, and that `build_matrix` is symmetric across the seam) and `geometric_bias_linear_angular_kernel_would_catch_raw_diff` (pins the wrapped value ∈ `[0, π]` — the invariant a future linear kernel relies on; the raw-diff form gives 190° where the wrapped form gives 170°).
+
+### 2.2 Crafted-input panics on the fusion/localisation path — typed `None` instead of panic — ACCEPTED & IMPLEMENTED (the security item)
+
+**The finding (DoS).** Two functions on a path that can carry **network-sourced multistatic frames** panicked on crafted input:
+
+- `mat::triangulation::solve_triangulation` indexed `ap_positions[0]` (panics on an empty AP table) and `ap_positions[i]` / `ap_positions[j]` (panics when a TDoA measurement references an **out-of-range AP index**). A remote peer supplying a TDoA tuple `(i=99, …)` with only 3 APs triggers an out-of-bounds panic — a remotely-triggerable denial of service.
+- `mat::heartbeat::CompressedHeartbeatSpectrogram::band_power` computed `self.n_freq_bins - 1`, which **underflows** (usize `0 − 1`) for a zero-bin spectrogram — a debug panic / release `usize::MAX` (then an out-of-range index).
+
+**The fix.** `solve_triangulation` uses `ap_positions.first()?` and `ap_positions.get(i)?` / `.get(j)?` — any empty table or out-of-range index returns `None`, never panics. `band_power` guards `n_freq_bins == 0` up front and **clamps both bounds** into `[0, last]`, returning `0.0` for empty/inverted ranges. No out-of-range index, no subtraction overflow, on any input.
+
+**Tests:** `triangulation_out_of_range_index_returns_none_no_panic`, `triangulation_empty_ap_positions_returns_none_no_panic`, `heartbeat_band_power_zero_bins_no_panic`, `heartbeat_band_power_out_of_range_bounds_no_panic`. Each **panics on the old code** (verified by reverting — §6) and returns a clean `None`/`0.0` on the new.
+
+### 2.3 GDOP mislabel — compute a real, dimensionless GDOP — ACCEPTED & IMPLEMENTED
+
+**The finding.** `geometry::CramerRaoBound` exposed a field named `gdop` ("Geometric Dilution of Precision") that was computed as `(crb_x + crb_y).sqrt()` — **identical to `rmse_lower_bound`**. That is the RMSE (metres, noise-dependent), **not** a GDOP. GDOP is a *dimensionless geometry factor* independent of the noise level; the name was a lie about the quantity.
+
+**The fix (honest rename was the fallback; real GDOP was cheap, so we computed it).** True GDOP `= sqrt(trace(G⁻¹))` where `G` is the **unit-variance** bearing-geometry matrix (the Fisher matrix with every `1/σ²` set to 1). It depends only on the array/target geometry and relates noise to position error as `rmse ≈ GDOP·σ`. We accumulate `G` alongside the FIM in both `estimate` and `estimate_regularised` (cheap 2×2), and report `INFINITY` (not NaN/panic) for a degenerate collinear geometry. The doc comment now states exactly what the field is and what it used to (wrongly) be.
+
+**Test:** `gdop_is_dimensionless_and_noise_independent` — scales every sensor's noise by 10× and asserts GDOP is unchanged while RMSE scales ~10×, and that `rmse ≈ GDOP·σ` at both noise levels. The old `gdop = sqrt(crb_x + crb_y)` **fails** this (it scaled with noise, proving it was RMSE) — verified by reverting (§6).
+
+### 2.4 `fuse()` double-clone in the aggregation hot path — eliminate the redundant clone — ACCEPTED & IMPLEMENTED (MEASURED — §4)
+
+**The finding.** `MultistaticArray::fuse` (and `fuse_ungated`) cloned every viewpoint embedding **twice** per fusion: once into the `extracted` tuple vector (`v.embedding.clone()`), then **again** when building the attention input (`extracted.iter().map(|(_, e, _, _)| e.clone())`). At the AETHER dimension (128 f32 = 512 B) over up to 8 viewpoints, that is a wholly redundant second heap allocation + memcpy per viewpoint, every TDM cycle.
+
+**The fix.** Build `extracted` once (the unavoidable clone out of the borrowed `self.viewpoints`), then **consume** `extracted` by value and **move** each embedding into the attention input (`embeddings.push(emb)`), capturing geometry/ids by `Copy` in the same pass. One clone per viewpoint instead of two. Measured win in §4.
+
+---
+
+## 3. Security review (touched files)
+
+The §2.2 crafted-input panics **are** the security item: a DoS via out-of-range indices / zero-bin underflow on a fusion/localisation path that may be driven by network-sourced multistatic frames. Beyond those, the touched files were swept for further panic-on-untrusted-input / unbounded-alloc sites:
+
+- `attention.rs` — all indexing is over internally-sized `n × n` / `d` loops bounded by validated input lengths (`DimensionMismatch` is returned for ragged embeddings); softmax denominators are floored with `f32::EPSILON`. No unbounded alloc (sizes derive from caller-supplied vector lengths already validated against `d_in`). **No further action.**
+- `geometry.rs` — `det`/`det_g` are floored before division; degenerate geometry yields `None`/`INFINITY`, never NaN-panic. **No further action.**
+- `fusion.rs` — embedding dimension is validated in `submit_viewpoint`; the event log is bounded (`max_events`, oldest-half drain). **No further action.**
+- `coherence.rs` — circular buffer is fixed-capacity; gate thresholds are clamped. **No further action.**
+
+No `unsafe`, no `unwrap()` on external input, and no unbounded allocation remain on the touched paths after §2.2.
+
+---
+
+## 4. MEASURED perf win (new criterion bench)
+
+A new bench, `crates/wifi-densepose-ruvector/benches/fusion_bench.rs`, covers the fusion hot path. It has two groups: `fusion_pipeline` (end-to-end `MultistaticArray::fuse_ungated()` at 2/4/8 viewpoints, dim 128) and an isolated A/B of the §2.4 marshalling step (`embedding_extract/before_double_clone` vs `after_single_clone`).
+
+- **Reproduce:** `cargo bench -p wifi-densepose-ruvector --bench fusion_bench`
+- **Measured (`embedding_extract`, 8 viewpoints × 128-d), medians:** `before_double_clone` **1.0029 µs** → `after_single_clone` **461.6 ns** — **~2.17× faster** on the marshalling step. The result is what theory predicts (two embedding clones collapse to one), confirming the redundant clone was the cost, not noise.
+- **End-to-end `fusion_pipeline` (medians):** 2 vp = 56.3 µs, 4 vp = 99.5 µs, 8 vp = 202.1 µs. The marshalling (~0.5–1 µs) is **well under 1%** of total fusion cost (dominated by the `n×n` attention), so the **end-to-end** effect is modest by construction; the `embedding_extract` A/B isolates and proves the clone-elimination itself. We report this honestly rather than attributing the full 2.17× to the pipeline.
+
+The double-clone elimination is also correctness-neutral: all 100 `viewpoint`/`mat` lib tests pass unchanged.
+
+---
+
+## 5. The ANN / cross-viewpoint-fusion SOTA landscape (graded)
+
+| # | Candidate | What | Grade | Verdict |
+|---|-----------|------|-------|---------|
+| **1** | **SymphonyQG** (SIGMOD 2025, public code) | Unified quantization + graph ANN; source reports **3.5–17× QPS over HNSW at equal recall**, pure-CPU / edge-portable. | **MEASURED-direction-tested** (was CLAIMED) — **[ADR-261](ADR-261-ruvector-graph-ann-index.md)** built the missing HNSW baseline + a SymphonyQG-style 1-bit quantized-traversal variant and **measured** the ratio on our hardware. | **DONE — direction REFUTED at our scale (honest negative).** ADR-261 built the real HNSW baseline (**~25× QPS over linear scan at recall ≥0.99**, the substrate this row wanted) and a quantized variant. At N=10k the 1-bit Hamming traversal is **too coarse** — its best recall is 0.738, never reaching the ≥0.90 equal-recall point, so **no QPS win over float HNSW** (the SymphonyQG 3.5–17× is *not* reproduced by our 1-bit construction here). Caveat: **our HNSW + our 1-bit quant, not SymphonyQG's system**; expected crossover at large N + a multi-bit code. We did **not** tune to manufacture a speedup. |
+| **2** | **Multi-bit / Extended RaBitQ + unbiased estimator** | Extends our existing **1-bit** `sketch.rs` (ADR-084): Pass-2 rotation, multi-bit Pass-3, and the **real RaBitQ unbiased distance estimator** (Gao & Long SIGMOD 2024) reranking the candidate set from the 1-bit code + 8 B/vec side info (§11). | **MEASURED-on-our-hardware** (was CLAIMED) — rotation (§10), multi-bit (§10), and the estimator (§11) all implemented + benchmarked. Rotation lifts strict-K 36%→46%; multi-bit (≤4-bit) reaches 74% strict; **the estimator reaches 49.71% strict (cosine rerank), still short of 90%.** All clear 90% only with over-fetch (estimator improves the factor: 95% at candidate_k=24 vs sign 91.6%). | **DONE — RESOLVED-PARTIAL / NEGATIVE.** Rotation (§10) + estimator (§11) built and MEASURED. The honest negative (no strict-bar 90% from rotation, ≤4-bit, **or the unbiased estimator**) is recorded, not hidden. Over-fetch + Pass-2 is the path that meets the bar (ADR-084's "candidate set" pattern); the estimator lowers the over-fetch factor needed. |
+| **3** | **GraphPose-Fi-style learned antenna-attention + ChebGConv fusion head** | Would replace the current **untrained identity-projection + mean-pool** "attention" (the `CrossViewpointAttention` default is `ProjectionWeights::identity` — not a *learned* attention) with a learned graph fusion head. | **DATA-GATED** (per ADR-152 measurement (b): architecture is **NOT** the current bottleneck — **data is**) | **ACCEPTED-future, data-gated. Do NOT build now.** ADR-152's measured lesson was that swapping architecture without more/better paired data does not move PCK. Building a learned fusion head before the data exists would repeat the mistake ADR-155 §5 also flagged for GraphPose-Fi. |
+| — | **Cramér-Rao / sensor-placement** (`geometry.rs` CRB) | Investigated for a 2026 advance beating the textbook Fisher-information CRB already implemented. | **Investigated — NO ACTION** | **Cleared honestly.** No 2026 method beats the closed-form Fisher-information CRB for this 2-D bearing problem; our implementation is already correct SOTA. (Recording a negative result is a deliberate anti-slop signal.) The only CRB change this milestone is the §2.3 *GDOP* honesty fix, which is a labelling/quantity correction, not an algorithmic one. |
+
+---
+
+## 6. Validation
+
+- **Bug-catching tests verified to bite.** Each §2.2/§2.3/§2.4-adjacent fix was reverted and the corresponding test observed to **fail on the old code**, then restored:
+  - `triangulation_out_of_range_index_returns_none_no_panic` / `triangulation_empty_ap_positions_returns_none_no_panic` — **panic** (index out of bounds) on old code.
+  - `heartbeat_band_power_zero_bins_no_panic` — **panic** ("attempt to subtract with overflow") on old code.
+  - `gdop_is_dimensionless_and_noise_independent` — **assertion failure** (GDOP scaled with noise) on old code.
+  - §2.1 (angular wrap) is the **disclosed no-op**: its tests pin the *contract* (wrapped value ∈ `[0, π]`), since the cos kernel makes the bias value numerically identical with or without the fix. We do not claim a behaviour change.
+- **`cd v2 && cargo test -p wifi-densepose-ruvector --no-default-features --lib`** — **100 passed / 0 failed** (was 93; +7 new tests).
+- **`cd v2 && cargo test --workspace --no-default-features`** — **3050 passed / 0 failed** (full-workspace aggregate across all crates and test binaries; the +7 new `wifi-densepose-ruvector` tests are included and green).
+- **`python archive/v1/data/proof/verify.py`** — **`VERDICT: PASS`** (the Python pipeline proof is independent of these Rust changes — confirmed unaffected).
+- New `fusion_bench` compiles and runs under the default feature set.
+
+---
+
+## 7. What changed, file by file
+
+- `viewpoint/geometry.rs` — `angular_distance` made `pub` (single canonical wrapped-angle helper); real dimensionless GDOP (`sqrt(trace(G⁻¹))`) in `estimate`/`estimate_regularised` (was RMSE mislabelled); `gdop` doc states the quantity and the prior bug; `gdop_is_dimensionless_and_noise_independent` test.
+- `viewpoint/attention.rs` — `GeometricBias::build_matrix` uses the canonical wrapped `angular_distance` (contract fix; numeric no-op under cos — disclosed); two contract-pinning tests.
+- `viewpoint/fusion.rs` — `fuse`/`fuse_ungated` move embeddings out of `extracted` (single clone, not double); existing tests unchanged and green.
+- `mat/triangulation.rs` — `first()?` / `get(i)?` / `get(j)?` guards (no panic on empty table / crafted indices); two no-panic tests.
+- `mat/heartbeat.rs` — `band_power` zero-bin guard + bounds clamp (no underflow / out-of-range index); two no-panic tests.
+- `benches/fusion_bench.rs` (new) + `Cargo.toml` `[[bench]]` — fusion hot-path bench + the double-clone A/B.
+
+---
+
+## 8. Deferred backlog (NOT silently dropped)
+
+The review surfaced more than this milestone scoped. Tracked here for a future ADR-156 milestone:
+
+- **SymphonyQG reproduction** (§5 #1) — **RESOLVED-DIRECTION-TESTED** (see [ADR-261](ADR-261-ruvector-graph-ann-index.md)). The missing HNSW baseline + a SymphonyQG-style 1-bit quantized-traversal variant were built and **MEASURED**: float HNSW is ~25× over linear scan at recall ≥0.99 (the baseline this gap needed), but our 1-bit quantized traversal is **too coarse to beat float HNSW at equal recall at N=10k** (best recall 0.738) — the 3.5–17× is **not reproduced** by our construction. Honest negative recorded; expected crossover is large N + a multi-bit traversal code. (Caveat: our HNSW + our 1-bit quant, not SymphonyQG's exact system.)
+- **Multi-bit / Extended RaBitQ** (§5 #2) — **RESOLVED-PARTIAL** (see §10). Pass-2 randomized rotation (FHT + seeded ±1 sign flips, `src/rotation.rs`) and a multi-bit Pass-3 experiment landed and were MEASURED against the ADR-084 ≥90% bar. **Honest result: rotation helps (+10pp at the strict bar) and Pass-2 reaches 90% with ~3× over-fetch, but NEITHER rotation nor multi-bit (up to 4-bit) clears the strict candidate_k==K 90% bar on the tested anisotropic distribution.** The original `1-bit sign quantization ships first; rotation/more-bits later if benchmark-measured top-K coverage drops below 90%` deferral is therefore retired: the rotation is built, the bar is characterised, and the residual gap is documented rather than deferred.
+- **Learned cross-viewpoint fusion head** (§5 #3, GraphPose-Fi-style) — **data-gated**: blocked on the paired multi-room data ADR-152 measurement (b) identified as the real bottleneck; do not build the architecture first.
+- **`CrossViewpointAttention` learned projections** — the default `ProjectionWeights::identity` + mean-pool is honest but unlearned; wiring real learned Q/K/V projections is part of the data-gated item above (no learned weights ⇒ the "attention" is currently a geometric-bias-weighted average, which the code/docs should keep stating plainly).
+- **`coherence.rs` / `fusion.rs` micro-opts and the remaining lower-severity review findings** (style, doc, further hot-path tuning) from the fusion gap review.
+
+---
+
+## 9. Consequences
+
+**Positive.** The fusion path now: uses one canonical wrapped angular-distance helper; reports a **real** dimensionless GDOP instead of a mislabeled RMSE; cannot be panicked by crafted multistatic indices or a zero-bin spectrogram (DoS closed); and does one embedding clone per viewpoint instead of two (measured). Every fix is pinned by a test that fails on the old code, and the ANN/fusion SOTA landscape is graded so the near-term (multi-bit RaBitQ) and the data-gated (learned fusion) are not confused.
+
+**Negative / honest.** The headline angular-wrap fix is a **numeric no-op** under the current cos kernel — we land it for contract/maintainability, not because it changes an output, and we say so. The two strongest external candidates (SymphonyQG, learned fusion) are **not built here** — one is CLAIMED-pending-reproduction, the other is data-gated by a prior measurement. The perf win is a **local hot-path** improvement, modest in the end-to-end pipeline (attention dominates). None of these is presented as more than it is.
+
+---
+
+## 10. RaBitQ Pass-2 / multi-bit — IMPLEMENTED & MEASURED (§8 backlog item #2)
+
+Milestone-1 of the §8 backlog. Status: **RESOLVED-PARTIAL** — built, measured, honest negative on the strict bar.
+
+### 10.1 What landed
+
+- **`crates/wifi-densepose-ruvector/src/rotation.rs`** (new) — `Rotation`, a deterministic randomized orthogonal rotation `R = H·D`: a **Fast Hadamard Transform** (`O(d log d)`, in-place butterfly, `1/√m` normalized so it is norm-preserving) composed with a diagonal of **seeded ±1 sign flips** (SplitMix64 from a stored `u64` seed). Chosen over a dense `d×d` matrix because that is `O(d²)` memory/time and infeasible at the 65,535-d the wire format provisions for; FHT is the standard fast-orthogonal (randomized-Hadamard / fast-JL) construction. Non-power-of-two `d` zero-pads to `next_pow2(d)` and reads back the first `d` coords.
+- **`sketch.rs`** — additive Pass-2 API: `Sketch::from_embedding_rotated`, `SketchBank::with_rotation` + `insert_embedding` / `topk_embedding` / `novelty_embedding`. **Pass 1 (`from_embedding`) is byte-for-byte unchanged**; a Pass-2 sketch has identical `embedding_dim` / packed-byte length / wire shape, so `WireSketch` and existing callers (`event_log.rs`, `signal/longitudinal.rs`) are untouched. Default behaviour preserved.
+- **`coverage.rs`** (new) — single-source-of-truth top-K coverage harness on a deterministic **anisotropic planted-cluster** fixture (cosine ground truth, the metric a sign sketch approximates). Backs both the `pass2_coverage_report` unit test and the `sketch_bench` coverage table.
+- **Multi-bit Pass-3 experiment** — `coverage::measure_multibit`: rotate, then `b`-bit uniform scalar-quantize each coord, rank by L1 over codes. Measures the bit/coverage tradeoff.
+
+### 10.2 Pre-existing bug found and fixed (disclosed)
+
+Building the coverage harness surfaced a **pre-existing correctness bug in `SketchBank::topk`** (shipped in ADR-084): the `n > k` heap path used `BinaryHeap<Reverse<(dist,id)>>` (a *min*-heap) but its comment/logic treated the peek as the max, so it evicted the *nearest* and returned the **k farthest** sketches as "nearest." The shipped unit tests only exercised the `n ≤ k` fast path (≤ 3 entries), so it was never caught. Fixed to a plain max-heap. Pinned by **`topk_heap_path_returns_nearest`** (fails on the old heap when entries are inserted farthest-first) and **`tight_clusters_give_high_coverage_with_overfetch`** (measured **0.072** coverage on the old code — random — vs **>0.99** fixed). This is a real, measured behaviour fix, not a no-op.
+
+### 10.3 MEASURED top-K coverage
+
+Test machine: Windows 11, `cargo bench --release` / `cargo test`. Fixture: **dim=128, N=2048, K=8, 64 planted clusters, intra-cluster noise=0.35, 128 queries, master_seed=0xAD000084, rotation_seed=0x5EEDC0DE12345678**, ground-truth metric = cosine. Reproduce: `cargo test -p wifi-densepose-ruvector --no-default-features pass2_coverage_report -- --nocapture` or `cargo bench -p wifi-densepose-ruvector --bench sketch_bench -- pass2_coverage`.
+
+**Coverage vs over-fetch (`coverage = |sketch_topK ∩ float_cosine_topK| / K`):**
+
+| candidate_k | Pass-1 (1-bit, no rot) | Pass-2 (1-bit, rot) | vs 90% bar |
+|---|---|---|---|
+| **8 (= K, strict bar)** | **36.13%** | **46.39%** | both **BELOW** |
+| 16 | 62.79% | 75.59% | below |
+| 24 | 83.89% | **91.60%** | **Pass-2 clears** |
+| 32 | 100.00% | 100.00% | clears |
+| 64 | 100.00% | 100.00% | clears |
+
+**Multi-bit Pass-3 at the strict bar (candidate_k = K = 8):**
+
+| Variant | Coverage | Memory |
+|---|---|---|
+| Pass-1 (1-bit, no rot) | 36.13% | 16 B/vec |
+| Pass-2 (1-bit, rot) | 46.39% | 16 B/vec |
+| Pass-3 (rot, 2-bit) | 54.39% | 32 B/vec |
+| Pass-3 (rot, 3-bit) | 66.70% | 48 B/vec |
+| Pass-3 (rot, 4-bit) | 74.22% | 64 B/vec |
+
+### 10.4 Honest verdict
+
+- **Rotation consistently helps** — +10.3 pp at the strict bar (36.13%→46.39%) and a uniform lift at every over-fetch level. The FHT construction is verified norm-preserving and deterministic.
+- **Neither rotation nor multi-bit (≤4-bit) clears the strict candidate_k==K 90% bar** on this anisotropic distribution. 1-bit sign quantization simply cannot resolve 8-of-2048 from sign bits alone; even 4× memory (4-bit) reaches only 74%.
+- **Pass-2 reaches the 90% bar at candidate_k=24 (~3× over-fetch)** — i.e. fetch ≥24 sketch candidates, refine to K with full float. This is exactly the "candidate set, then full refinement" deployment pattern ADR-084 specifies, so the bar is met *in the deployment the sensor is designed for*, just not at strict K=K.
+- **This is a measured, partial win, reported as such.** No benchmark was tuned to manufacture a pass. The strict-bar gap (and the multi-bit tradeoff that doesn't close it) is documented rather than spun.
+
+### 10.5 Deferred sub-items (graded, not dropped)
+
+- **Strict-bar 90% from a richer code** — neither rotation nor uniform multi-bit closes it here. A learned/asymmetric quantizer or the full RaBitQ residual-distance estimator (not just a uniform scalar code) might. **RESOLVED-NEGATIVE (§11): the estimator is now built and MEASURED — it lifts strict-K 46.39%→49.71% but does NOT clear the 90% strict bar.** The residual strict-bar gap is a published negative, not a deferral.
+- **Distribution sensitivity** — the result is for one synthetic anisotropic distribution; on real AETHER traces the strict-bar number may differ. Re-measuring on recorded embeddings is deferred to the ADR-084 post-merge soak.
+- **Promoting a `MultiBitSketch` type** — the multi-bit code lives in the measurement harness, not as a shipped sketch type. Building the production type is gated on a use site actually needing strict-K (vs over-fetch), which the measurement says is not required today.
+
+---
+
+## 11. RaBitQ unbiased distance estimator — IMPLEMENTED & MEASURED (Milestone-2, §8 backlog item #2 / §10.5 strict-bar item)
+
+Milestone-2 of the §8 backlog. Status: **RESOLVED-NEGATIVE** — the estimator is built, measured, and lifts strict-K coverage, but the honest result is that it does **not** clear the ADR-084 ≥90% strict-K bar on this distribution. The negative is reported as such, exactly like the Pass-2 rotation result.
+
+### 11.1 What landed
+
+- **`crates/wifi-densepose-ruvector/src/estimator.rs`** (new) — the real Gao & Long (SIGMOD 2024) contribution: an **unbiased estimator of the inner product / squared distance** recovered from the 1-bit code plus per-vector side info, on top of the Pass-2 rotation. Pass-1/Pass-2 ranked candidates by raw Hamming over sign bits — a coarse proxy. This module reranks by the unbiased estimate.
+  - `EstimatorSketch` — Pass-2 sign code (over the **padded** FHT length `D = next_pow2(dim)`, the frame `x̄` is unit in) **plus** the side info.
+  - `SideInfo` = `{ residual_norm: f32, x_dot_o: f32 }` = **8 bytes/vector** (2× f32).
+  - `EstimatorQuery` — query rotated once, reused across all candidates.
+  - `DistanceEstimator` — `estimate_inner_product`, `estimate_sq_distance`, `ranking_key` (euclidean), `cosine_ranking_key` (the correct key vs a cosine ground truth — needs only the code + `x_dot_o`).
+  - `EstimatorBank` — `topk_estimated` (euclidean) / `topk_estimated_cosine`; optional `with_centroid` (the paper's centroid path).
+- **`coverage.rs`** — `measure_estimator` (cosine rerank) + `measure_estimator_euclidean`, on the **bit-identical** fixture / cluster centres / query stream / cosine ground truth as `measure_pass1`/`measure_pass2`. Single source of truth for the §11.3 table; backs both `estimator_coverage_report` and the `sketch_bench` coverage table.
+- **Additive + backward-compatible.** New types only; Pass-1 `Sketch` / Pass-2 `SketchBank` / `WireSketch` wire format are untouched. All external callers (`event_log.rs`, `signal/longitudinal.rs`, `sensing-server`) use Pass-1 `from_embedding` and are unaffected.
+
+### 11.2 The estimator formula (and the zero-centroid simplification, stated honestly)
+
+Let `P` be the Pass-2 orthogonal rotation (`R = H·D`), `D = next_pow2(dim)`. For data `o_raw`, query `q_raw`, centroid `c`:
+
+1. **Centroid — SIMPLIFIED to zero/global `c = 0`.** The paper centres on a per-cluster centroid (`o_r = o_raw − c`); we use `c = 0` (`o_r = o_raw`), because the current sketch path has no IVF/k-means cluster structure. This costs accuracy when the data is far off-origin. **We document it, do not hide it,** and built the paper-faithful centroid path (`from_embedding_centred` / `EstimatorBank::with_centroid`) so the simplification is a measured choice, not an assumption. (We do **not** report a centroid coverage number against the *cosine* ground truth: centroid-subtraction changes the metric — cosine-of-residual ≠ cosine-of-raw — so a centroid number vs raw-cosine truth would be a metric mismatch, itself dishonest. Zero-centroid is the correct match for this raw-cosine harness.)
+2. **Unit residual + 1-bit code.** `o = o_r/‖o_r‖`, `o' = P·o`, code `x̄_i = sign(o'_i)·(1/√D)` — a unit vector at the nearest hypercube corner.
+3. **Side info:** `residual_norm = ‖o_r‖` and `x_dot_o = ⟨x̄, o'⟩ ∈ (0,1]` (the paper's `⟨x̄, o⟩`).
+4. **Unbiased estimator** (paper Eq.): `⟨o', q'⟩ ≈ ⟨x̄, q'⟩ / ⟨x̄, o'⟩ = ⟨x̄, q'⟩ / x_dot_o`. The random rotation makes the code's quantization error orthogonal **in expectation** to `q'`, so the rescale is unbiased (paper's `O(1/√D)` bound). Per candidate: one length-`D` signed sum (`x̄ ∈ {±1/√D}`), as cheap as Hamming + a multiply.
+5. **Distance / cosine.** `⟨o_r,q_r⟩ = ‖o_r‖·(⟨x̄,q'⟩/x_dot_o)`; `‖q_r−o_r‖² = ‖q_r‖²+‖o_r‖²−2⟨o_r,q_r⟩`. For a **cosine** ground truth (AETHER / this harness), rank by `−⟨o,q_r⟩ = −(⟨x̄,q'⟩/x_dot_o)` (needs only the code + `x_dot_o`).
+
+**Unbiasedness is pinned** (`estimator_unbiased_on_fixture`): averaging the estimate of `⟨o_r,q_r⟩` over 4000 random rotation seeds converges to the true inner product within ~6% of the `‖o‖‖q‖` envelope — a biased estimator (or sign-only proxy) would be systematically off.
+
+### 11.3 MEASURED strict-K coverage
+
+Same fixture/seeds as §10 (dim=128, N=2048, K=8, 64 clusters, noise=0.35, 128 queries, `master_seed=0xAD000084`, `rotation_seed=0x5EEDC0DE12345678`), cosine ground truth. Reproduce: `cargo test -p wifi-densepose-ruvector --no-default-features estimator_coverage_report -- --nocapture` or `cargo bench -p wifi-densepose-ruvector --bench sketch_bench -- pass2_coverage`.
+
+| candidate_k | Pass-1 (sign) | Pass-2 (sign) | **Pass-2 + estimator (cosine)** | Pass-2 + estimator (euclid) | vs 90% bar |
+|---|---|---|---|---|---|
+| **8 (= K, strict bar)** | 36.13% | 46.39% | **49.71%** | 49.02% | **all BELOW** |
+| 16 | 62.79% | 75.59% | 79.20% | 77.93% | below |
+| 24 | 83.89% | 91.60% | **95.12%** | 93.65% | estimator clears |
+| 32 | 100.00% | 100.00% | 100.00% | 100.00% | clears |
+| 64 | 100.00% | 100.00% | 100.00% | 100.00% | clears |
+
+Side-info memory overhead: **8 bytes/vector** (2× f32) on top of the 16 B/vec 1-bit sketch.
+
+### 11.4 Honest verdict
+
+- **The estimator helps, and the cosine key beats the euclidean key** (49.71% vs 49.02% at strict-K; cosine is the apples-to-apples match for the cosine ground truth — both it and sign-Hamming are angular). The unbiased rescale is a real, consistent lift at every over-fetch level (e.g. 24: 91.60%→95.12%).
+- **It does NOT clear the strict candidate_k==K 90% bar.** Strict-K goes 36.13% (Pass-1) → 46.39% (Pass-2-sign) → **49.71% (Pass-2 + estimator)** — a **+3.3 pp** improvement over sign-only, **still ~40 pp short of 90%**. This is a **published negative**, the same class of honest result as the Pass-2 rotation (§10).
+- **Why the strict-K gain is modest:** the binding constraint at strict K is the **1-bit code's information ceiling** (resolving 8-of-2048 from a single sign bit per coordinate), not the *estimator's variance* — the estimator sharpens the ranking but cannot add information the 1-bit code never captured. The estimator's larger wins are at over-fetch, where there is room to re-rank a wider candidate pool.
+- **The bar is still met the way ADR-084 deploys the sensor:** at candidate_k=24 (~3× over-fetch) the estimator reaches **95.12%** (vs Pass-2-sign 91.60%) — the "candidate set, then full refinement" pattern. The estimator **improves the over-fetch factor needed** but does not eliminate it.
+- **No benchmark was tuned to manufacture a pass.** The strict-bar gap is documented, not spun.
+
+### 11.5 Pinning tests
+
+- `estimator::estimator_is_deterministic` — fixed seed ⇒ identical estimate + identical bank top-K.
+- `estimator::estimator_unbiased_on_fixture` — Monte-Carlo mean over 4000 seeds converges to the true inner product within tolerance (the unbiasedness claim).
+- `coverage::estimator_rerank_not_worse_than_sign` — estimator-reranked coverage ≥ sign-only Pass-2 on a fixed fixture (must not regress).
+- Plus: `estimator_self_distance_is_small`, `x_dot_o_in_unit_range`, `zero_input_does_not_panic`, `bank_self_query_ranks_self_first`, `centroid_path_self_query_ranks_self_first`, `centroid_zero_matches_default`, `estimator_coverage_is_deterministic`.
@@ -0,0 +1,193 @@
+# ADR-157: Hardware / Sensing-Acquisition Layer Beyond-SOTA Sweep — Milestone 3 (An Already-Hardened Layer, Three Small Real Fixes, an Honestly-Null Perf Win, and a Mostly-NO-ACTION SOTA Landscape)
+
+| Field | Value |
+|-------|-------|
+| **Status** | Proposed |
+| **Date** | 2026-06-11 |
+| **Deciders** | ruv |
+| **Codebase target** | `wifi-densepose-vitals` (`heartrate.rs`, `breathing.rs`, `anomaly.rs`, `store.rs`), `wifi-densepose-wifiscan` (`pipeline/breathing_extractor.rs`, `pipeline/correlator.rs`, `adapter/netsh_scanner.rs`), `wifi-densepose-hardware` (`esp32_parser.rs`, `sync_packet.rs`, `esp32/secure_tdm.rs`, `ieee80211bf/*`), `wifi-densepose-calibration` (`geometry_embedding.rs`), benches, docs |
+| **Relates to** | ADR-021 (ESP32 CSI vitals), ADR-022 (multi-BSSID WiFi sensing), ADR-028 (ESP32 capability audit + witness), ADR-032 (multistatic mesh security), ADR-110 (HE PPDU bandwidth), ADR-151 (per-room calibration), ADR-152 (WiFi-Pose SOTA 2026 intake), ADR-153 (802.11bf forward-compat), ADR-154 (Signal/DSP sweep M0), ADR-155 (NN/Training sweep M1), ADR-156 (RuVector/Fusion sweep M2) |
+| **Scope** | Milestone 3 of the beyond-SOTA sweep across the four hardware/sensing-acquisition crates. The honest headline: **this layer is already well-hardened** — the real work is small. Three correctness/stability fixes (each pinned by a test that fails on the old code), one algorithmic perf change whose end-to-end win is **null at realistic window sizes** (disclosed, not inflated) with a committed bench, one defense-in-depth hardening on an unreachable path, a **MEASURED negative-results section** (the centerpiece — what was investigated and found already-correct), a graded SOTA landscape that is **mostly NO-ACTION**, and a deferred backlog. **Nothing is silently dropped.** |
+
+---
+
+## 0. PROOF discipline (this ADR's contract)
+
+This project has been publicly accused of "AI slop." Milestone 3 answers with **evidence, not adjectives** — the same contract as ADR-154/155/156:
+
+- Every correctness/stability fix ships a **committed regression test that fails on the old code and passes on the new**. Each was verified by reverting the fix and observing the test fail (recorded in §6).
+- Every perf number is **MEASURED before/after** with the exact reproduce command and a committed criterion bench. Where the win is below noise, we **say so and claim nothing** — see §4, which is a deliberately-disclosed near-null result.
+- Every external SOTA reference is graded **MEASURED** / **CLAIMED** / **DATA-GATED**, and where the right answer is "do nothing," we record the negative result explicitly (§5) — a stronger anti-slop signal than a fix.
+- The headline of this milestone is itself a negative result: **the acquisition layer was already hardened.** We disclose what we *checked and did not change* (§3) in as much detail as what we changed (§2), because "investigated, already correct, no action" is the most honest thing a sweep can report when it is true.
+
+Test machine for the perf numbers: Windows 11, `cargo bench --release`, criterion 0.5. Numbers are wall-clock medians on this box; the **ratio** (before/after) is the claim, not the absolute ns.
+
+Build/test gate: `cargo test --workspace --no-default-features` (the project's standard gate — no GPU/`crv` features). All fixes in this milestone are on the **default, non-feature-gated surface**, so they are fully exercised by the standard gate. The serde-validated `ieee80211bf` types are additionally verifiable with `--features serde`; the live-QUIC path in `secure_tdm` is structurally tested (HMAC/replay/tamper) but not live-socket-tested in CI.
+
+---
+
+## 1. Context
+
+The hardware/sensing-acquisition layer is the bottom of the stack: it turns raw RF (ESP32 CSI frames, multi-BSSID netsh scans, 802.11bf measurement reports) into typed, validated domain objects that the signal/fusion/NN layers above consume. A beyond-SOTA review of the four crates surfaced far **fewer** real defects than the signal (ADR-154) or fusion (ADR-156) sweeps — because this layer was written defensively from the start: length-gated parsers, `Option`-returning helpers, `#[serde(try_from)]` validate-on-deserialize, FSMs that return `Result` instead of panicking, and HMAC-authenticated + replay-protected TDM beacons.
+
+The genuine findings are three: an **O(n²) sliding-window data-structure choice** in the vital-sign extractors (perf, latent), a **partial-weights scale-mixing bug** in breathing fusion (correctness), and an **IIR resonator that can diverge at pathologically low sample rates** (stability). Everything else the review flagged turned out to be already-safe — documented in §3 as MEASURED negative results.
+
+---
+
+## 2. Decision — the fixes that landed
+
+Each correctness/stability fix ships a regression test on the non-feature-gated, workspace-tested surface.
+
+### 2.1 §A1 — `Vec::remove(0)` O(n²) sliding windows → `VecDeque` (PERF, latent; MEASURED via bench — near-null at realistic sizes, disclosed)
+
+**The finding.** Every fixed-length sliding window in the extractors was a `Vec<f64>`/`Vec<f32>` whose oldest-sample eviction used `Vec::remove(0)` — an **O(n) shift of the whole buffer on every sample**, making a full-window `extract()` sweep O(n²). Six sites:
+
+| File | Site | Buffer |
+|------|------|--------|
+| `vitals/heartrate.rs` | `extract` history window | `Vec<f64>` → `VecDeque<f64>` |
+| `vitals/breathing.rs` | `extract` history window | `Vec<f64>` → `VecDeque<f64>` |
+| `vitals/anomaly.rs` | `rr_history` / `hr_history` | `Vec<f64>` → `VecDeque<f64>` (×2) |
+| `vitals/store.rs` | `readings` ring buffer | `Vec<VitalReading>` → `VecDeque<VitalReading>` |
+| `wifiscan/pipeline/breathing_extractor.rs` | filtered history | `Vec<f32>` → `VecDeque<f32>` |
+| `wifiscan/pipeline/correlator.rs` | per-BSSID histories | `Vec<Vec<f32>>` → `Vec<VecDeque<f32>>` |
+
+**The fix.** Swap to `VecDeque` with `push_back` + `pop_front` (O(1) eviction). Where the autocorrelation / zero-crossing / Pearson loop needs a contiguous slice, call `make_contiguous()` (or `as_slices().0` after it) **once per `extract()`**. This matches the idiom already used correctly in `wifiscan/pipeline/orchestrator.rs`. **Output is bit-identical** — no behavior test bites; the change is bench-gated.
+
+**The honest measurement (§4).** In **isolation**, the eviction cost collapses from O(n²) to O(n): a microbenchmark of pure eviction shows **34.6× at window=3000 and 3158× at window=100000**. But in the **full `extract()` path at realistic ESP32 window sizes** (heartrate ~1500, breathing ~3000), the per-frame DSP (autocorrelation is O(window·lags); zero-crossing is O(window)) **dominates the eviction entirely**, so the end-to-end win is **below noise** — measured `heartrate` 42.8 ms (before) vs 44.4 ms (after), `breathing` 7.95 ms vs 7.86 ms: overlapping confidence intervals, **no measurable change**. We land A1 because it is the correct data structure and removes a latent O(n²) that *would* bite at higher sample rates or longer windows — **not** because it speeds up the current hot path, which it does not measurably. Claiming an end-to-end speedup here would be exactly the inflation this sweep exists to prevent (the same discipline ADR-156 §2.1 applied to its cos no-op).
+
+### 2.2 §A2 — `breathing.rs` partial-weights scale-mixing (CORRECTNESS, real)
+
+**The finding.** `BreathingExtractor::extract` fused per-subcarrier residuals as `Σ residuals[i]·w[i]` where `w[i] = weights.get(i).unwrap_or(1/n)`. The result was **never normalized**. When `weights` was supplied **shorter than** `n`, the supplied entries (e.g. attention weights ~10.0) were used **raw** while the missing tail defaulted to `uniform_w = 1/n` (~0.125) — two scales summed with no renormalization, **silently mis-scaling the breathing signal** by a factor that depends on `weights.len()`. A caller passing 2 high attention weights for an 8-subcarrier frame got a fused value ~20× too large.
+
+**The fix.** Extracted the fusion into `fuse_weighted_residuals(residuals, weights, n)` and normalized by `Σ(effective weights)` — `weighted_sum / weight_total` — mirroring the **already-correct** pattern in `heartrate::compute_phase_coherence_signal`. A partial weight slice now produces a true weighted average in the residual range, independent of `weights.len()`.
+
+**Tests (fail on old code, verified by reverting — §6):**
+- `partial_weights_are_renormalized_not_scale_mixed` — `residuals=[1.0;8]`, `weights=[10.0,10.0]` → fused value `1.0` (the renormalized weighted mean), and explicitly **not** the old scale-mixed sum `2·10 + 6·0.125 = 20.75`.
+- `partial_weights_fusion_is_weighted_average` — differing residuals → a proper weighted average within `[0, 2]`, which the old un-normalized sum is not.
+
+### 2.3 §A3 — IIR resonator divergence at pathologically low sample rate (STABILITY, real)
+
+**The finding.** Both extractors' `bandpass_filter` set the resonator pole radius `r = 1 - bw/2` with `bw = 2π(f_high − f_low)/fs`. The **research report's stated trigger ("`fs` below ~4 Hz") is incorrect**, and we say so: the resonator pole *magnitude* is `|r|`, and the filter is stable for any `|r| < 1` — a merely-**negative** `r` is still stable. Divergence requires `|r| ≥ 1`, i.e. `bw ≥ 4`, i.e. `fs` very low **relative to the band width** (e.g. `fs = 0.5` Hz with a 0.1–0.9 Hz band → `bw = 10.05`, `r = −4.03`, `|r| = 4.03 > 1`). When that holds, the filter **diverges exponentially**: a unit-step input reaches `~10^183` within 300 frames and **overflows f64 to ±inf within ~600 frames**. Once one inf enters `filtered_history`, the autocorrelation `acf0`/zero-crossing path produces NaN and the extractor is **permanently dead** (silent stall until `reset()`).
+
+**The fix.** Two layers of defense-in-depth:
+1. **Clamp** `r` to a stable range: `r = (1.0 - bw/2.0).clamp(0.0, 0.9999)` — keeps the pole inside the unit circle for **any** sample-rate / band-edge configuration. (We document honestly that the divergence condition is `|r| ≥ 1`, not "`r` negative.")
+2. **Finite-guard** before the history push: `if !filtered.is_finite() { return None; }` — mirrors the NaN-bypass guard in ADR-154 §3, so even a future divergence cannot poison the buffer.
+
+Applied to **both** `heartrate.rs` and `breathing.rs` (identical resonator block).
+
+**Tests (fail on old code, verified by reverting — §6):** `heartrate::low_sample_rate_filter_stays_finite` and `breathing::low_sample_rate_filter_stays_finite` — construct at `fs=0.5` with a 0.1–0.9 Hz band, feed a unit step for 600 frames, assert **every** `filtered_history` sample is finite. On the old code these **panic** (a `filtered_history[i]` is inf/NaN); on the new code all samples are finite.
+
+### 2.4 §D1 — new `vitals/benches/vitals_bench.rs` (MEASURED)
+
+A new criterion bench (`harness = false`, registered in `Cargo.toml`) drives each extractor from empty to a full window (`heartrate` 1500 samples, `breathing` 3000) so the A1 sliding-window bookkeeping is exercised across the whole buffer. Follows the criterion style of the existing `hardware/benches/transport_bench.rs` and ADR-156's `fusion_bench`. Numbers and the honest interpretation are in §4.
+
+### 2.5 §B1 — `ieee80211bf/transport.rs` drop-instead-of-truncate (HARDENING, unreachable path — disclosed)
+
+`OpportunisticCsiBridge::ingest` built `CsiReportPayload { n_subcarriers: self.amp_accum.len() as u16, … }`. The `as u16` would silently wrap a count above 65 535. **This is unreachable in practice**: `ingest` gates `frame.subcarrier_count() > MAX_REPORT_SUBCARRIERS` (484) at entry and returns `None`, and `report.validate()` independently rejects oversized counts downstream. We replaced the cast with `u16::try_from(self.amp_accum.len()).ok()?` (drop-instead-of-truncate) so the construction is **correct-by-construction** rather than relying on the upstream gate. We disclose this as **defense-in-depth on an unreachable path, not a live bug** — no behavior change, no new test (the gate already prevents the input that would exercise it).
+
+### 2.6 §B4 — constant-time HMAC tag compare: **RESOLVED — no-dependency hand-rolled constant-time compare (Milestone-1)**
+
+`secure_tdm.rs` compared the 8-byte HMAC tag with `self.hmac_tag == expected` (data-dependent, non-constant-time: short-circuits on the first differing byte, leaking through verification latency how many leading bytes a forged tag matched — a byte-by-byte tag-recovery oracle). Milestone-3 deferred this **only** to avoid adding the `subtle` crate as a direct dependency. Milestone-1 resolves it **without any dependency**: a hand-rolled `constant_time_tag_eq(a, b)` that XOR-accumulates every byte difference into a single `u8` with **no early exit**, then compares the accumulator to zero exactly once. `#[inline(never)]` + `core::hint::black_box(diff)` stop the optimizer from reintroducing a short-circuit or lowering the loop into a non-constant-time `memcmp`; a length mismatch returns `false` without inspecting contents. The former `==` verify site now calls this helper.
+
+**Test (fails on old code, the hard gate):** `tag_compare_is_constant_time_shape` — asserts correct accept/reject for equal, first-byte-differ, last-byte-differ, all-byte-differ, and length-mismatch tags, plus an end-to-end `verify()` last-byte-only tamper. Verified to **bite**: introducing a classic constant-time bug (loop `take(LEN-1)`, skipping the last byte) makes it fail on `last-byte-differ must reject`. A coarse timing-invariance smoke check `tag_compare_timing_invariance_smoke` exists but is `#[ignore]`d (noisy host — not a CI gate). **Grade MEASURED** (constant-time *construction*; micro-timing on a noisy host is only a smoke check, disclosed honestly). Tracked RESOLVED in §8.
+
+---
+
+## 3. The MEASURED negative-results section (the centerpiece — what was investigated and found already-correct)
+
+This is the core of ADR-157. The acquisition layer was hardened before this sweep; the strongest anti-slop evidence is an honest accounting of what we **checked and did not need to change**. Each is verified against the live code with a file:line citation.
+
+| Area | Claim verified | Evidence (file:line) | Verdict |
+|------|----------------|----------------------|---------|
+| **ESP32 parser subcarrier index math** | A crafted CSI frame cannot panic via the subcarrier-index arithmetic. The total-frame-size length gate (`data.len() < HEADER_SIZE + n_antennas·n_subcarriers·2 → Err`) dominates **every** subsequent `data[byte_offset]`/`[+1]` access; `n_subcarriers ≤ 256`, `n_antennas ≤ 4` are header-bounded, and the `index` math is pure i16 arithmetic with no indexing. | `esp32_parser.rs:211` (length gate) guards the loop at `:224–242` | **Already safe — NO ACTION** |
+| **`sync_packet.rs` `try_into().unwrap()`** | The four `try_into().unwrap()` calls are **infallible**: each slices a fixed-width sub-range (`[0..4]`, `[8..16]`, `[16..24]`, `[24..28]`) of a buffer already guaranteed `len() >= SYNC_PACKET_SIZE` (32) by the early `return Err(InsufficientData)`. | `sync_packet.rs:88` (length gate) → `:94,102,103,104` (fixed-width slices) | **Already safe — NO ACTION** |
+| **The entire `ieee80211bf/` 802.11bf model** | Validate-on-deserialize and no-panic-by-construction throughout. `MeasurementSetupId` is `#[serde(try_from = "u8")]` rejecting `> MAX_SETUP_ID` (127); `ThresholdParams` is `#[serde(try_from = "RawThresholdParams")]` routing every deserialize through `ThresholdParams::new`; the session FSM `handle()` returns `Result<Vec<Action>, BfError>` (never panics) and enforces **single-role** (`self.role != Initiator/Responder → Err`) on every transition; the SBP request is validated through the **same** single `evaluate_setup` chain as a direct setup (no SBP-only policy bypass). | `types.rs:160–161` (setup-id try_from), `:225–226` (threshold try_from), `:165` (range check); `session.rs:118` (`handle` → Result), `:130/143/166/182` (single-role), `messages.rs:130–147` (SBP single-evaluate) | **Already SOTA-shaped — NO ACTION** |
+| **`secure_tdm.rs` HMAC + replay** | Beacon authentication (HMAC-SHA256, 8-byte tag), tamper rejection, and replay-window protection are correct and tested. (The non-constant-time compare at `:284` is the only nit — §2.6, deferred as out-of-threat-model for an 8-byte LAN tag.) | `secure_tdm.rs:279` (`verify`), `:284` (compare), tests `:614–673` (replay), `:728` (tamper) | **Correct — NO ACTION (B4 deferred)** |
+| **`netsh_scanner.rs` command + parse** | No shell-injection surface: the scanner uses a **fixed argv** (`Command::new("netsh").args(["wlan","show","networks","mode=bssid"])`) — no shell, no interpolation. Parsing is **`Option`-based** (`try_parse_ssid_line`/`try_parse_bssid_line`/`try_parse_signal_line` → `Option`, with `.unwrap_or(default)`), so hostile/garbled netsh output is silently skipped, never panicked. | `netsh_scanner.rs:50–51` (fixed argv), `:96–102` (`unwrap_or` defaults), `:242/257/270` (`Option` parsers) | **Already safe — NO ACTION** |
+| **`calibration/geometry_embedding.rs` overflow guard** | The geometry embedding clamps every position/std-dev component into `±MAX_COORD_M` (1000 m) via `clamp_m`, explicitly to stop adversarial coordinates from overflowing the covariance accumulation into `inf`; the documented invariant ("every value is finite, never NaN/inf") holds. | `geometry_embedding.rs:55` (`MAX_COORD_M`), `:145/150` (`clamp_m` on centroid + std-dev) | **Already safe — NO ACTION** |
+
+---
+
+## 4. The §D1 perf measurement (MEASURED — honestly near-null end-to-end)
+
+New bench: `crates/wifi-densepose-vitals/benches/vitals_bench.rs`, two functions covering a full-window fill of each extractor.
+
+- **Reproduce:** `cargo bench -p wifi-densepose-vitals --bench vitals_bench`
+  (compile-only: append `--no-run`; the medians below used `-- --warm-up-time 1 --measurement-time 3 --sample-size 20`).
+
+**End-to-end `extract()` full-window fill, medians:**
+
+| Bench | Before (`Vec::remove(0)`) | After (`VecDeque`) | Verdict |
+|-------|---------------------------|--------------------|---------|
+| `heartrate_extract_full_window_1500` | 42.81 ms `[42.19, 42.81, 43.46]` | 44.37 ms `[43.55, 44.37, 45.19]` | **no measurable change** (after marginally slower; intervals overlap) |
+| `breathing_extract_full_window_3000` | 7.95 ms `[7.86, 7.95, 8.05]` | 7.86 ms `[7.66, 7.86, 8.04]` | **no measurable change** (intervals overlap) |
+
+The end-to-end effect is **null within noise** because the per-frame DSP dominates: heartrate runs an O(window·lags) autocorrelation every frame (≈1500·125 multiply-adds), which utterly swamps the O(window) eviction the A1 change improves; breathing's O(window) zero-crossing and the `make_contiguous` rotation are the same order as the old `remove(0)` memmove at these sizes.
+
+**Where the win actually lives (isolated eviction-only microbench, supporting evidence — not in the committed bench):**
+
+| Window | `Vec::remove(0)` (eviction only) | `VecDeque` | Speedup |
+|--------|----------------------------------|------------|---------|
+| 3 000 | 1.00 ms | 0.029 ms | **34.6×** |
+| 20 000 | 94.5 ms | 0.122 ms | **773×** |
+| 100 000 | 3 139 ms | 0.994 ms | **3 158×** |
+
+So A1 is **algorithmically correct and removes a real latent O(n²)** that would bite at higher sample rates or longer analysis windows — but at the **current** ESP32 window sizes the end-to-end win is below noise, and we claim nothing more. This is the §0 contract in action: a perf claim without a measured before/after improvement is **not made**.
+
+---
+
+## 5. The hardware/sensing SOTA landscape (graded — mostly NO-ACTION, honest)
+
+Grades: **MEASURED** (source measured it, ideally public method/code), **CLAIMED** (asserted, no reproducible artifact), **DATA-GATED** (blocked on data we don't have, per a prior ADR-152 measurement).
+
+| # | Area | Candidate / question | Grade | Verdict |
+|---|------|----------------------|-------|---------|
+| 1 | **CSI vital signs (HR/BR)** | Deep-CSI vital-sign models report **MAE ~2–3 BPM** vs our classical IIR-bandpass + autocorrelation/zero-crossing. | **DATA-GATED + CLAIMED** | **NO ACTION on method.** A deep model needs **paired PPG/ECG ground truth** we do not have, and no public ESP32 artifact reproduces the cited MAE on commodity CSI. Our classical method is the honest commodity baseline; the real wins this milestone are the A1/A3 robustness fixes, not a new model. |
+| 2 | **802.11bf-2025 conformance** | Adopt a conformance test-vector suite for the `ieee80211bf/` forward-compat model. | **CLAIMED (not public)** | **NO ACTION.** No commodity silicon ships a conformant 802.11bf interface as of 2026, and the conformance suites are **WBA / Wi-Fi Alliance pre-certification** material, **not public**. Our model's "no OTA encoding until silicon exists" posture (ADR-153) is the correct one. Tracked in §8: *add SBP conformance vectors when the WFA publishes a test plan* — we will **not invent vectors**. |
+| 3 | **Per-room calibration (ADR-151)** | Bank-of-specialists + drift-veto vs a 2026 calibration SOTA. | **CLAIMED on numbers, DATA-GATED on a head-to-head** | **NO ACTION on architecture.** The bank-of-specialists + drift-veto design is SOTA-shaped, but we have **no head-to-head PCK** against a published method (no paired multi-room data). The geometry-conditioned LoRA head is **built-but-unconsumed** and data-gated → **ACCEPTED-FUTURE** (§8), not built now. |
+| 4 | **Multi-BSSID throughput (wifiscan)** | The module docs assert a native `wlanapi.dll` FFI 10–20 Hz path; the current `WlanApiScanner` wraps `netsh` (~2 Hz). | **MEASURED (Milestone-1)** | **IMPLEMENTED + MEASURED — real positive win.** Status corrected: the native FFI is **fully implemented and wired live** (`wlanapi_native::scan_native` calls `WlanOpenHandle`/`WlanEnumInterfaces`/`WlanGetNetworkBssList`/`WlanFreeMemory`/`WlanCloseHandle`; `WlanApiScanner::scan_instrumented` runs it native-first with a netsh fallback). Milestone-1 **measured both paths on this box** (Intel Wi-Fi 7 BE201 320MHz, 2026-06-13) over an identical 10 s wall-clock window via a new `benchmark_backend`: **native 21.42 Hz vs netsh 3.84 Hz = 5.57× MEASURED** (mean 5.0 BSSIDs/scan each; native-only run 18.0 Hz). Native genuinely beats netsh — a real measured multiple, **not** a fabricated 10×; the achieved 21.4 Hz lands in the asserted >2 Hz regime though below the asserted 10–20 Hz upper bound. 50 back-to-back native scans = 50/50 OK, no handle leak. → §8 MEASURED. |
+
+---
+
+## 6. Validation
+
+- **Bug-catching tests verified to bite.** Each §A2/§A3 fix was reverted and the corresponding test observed to fail on the old code, then restored:
+  - `partial_weights_are_renormalized_not_scale_mixed`, `partial_weights_fusion_is_weighted_average` — **assertion failure** (returned the old un-normalized scale-mixed sum) on old code.
+  - `heartrate::low_sample_rate_filter_stays_finite`, `breathing::low_sample_rate_filter_stays_finite` — **panic** (a `filtered_history[i]` is inf/NaN) on old code.
+  - §A1 is the **disclosed bit-identical change**: no behavior test bites (correctly — output is unchanged); the bench (§4) is the gate, and it shows **no measurable end-to-end change**, which we report honestly.
+  - §B1 is on an **unreachable path** (gated upstream), so it carries no new test — disclosed as defense-in-depth, not a live bug.
+- **`cd v2 && cargo test -p wifi-densepose-vitals -p wifi-densepose-hardware -p wifi-densepose-wifiscan -p wifi-densepose-calibration --no-default-features`** — all green. Lib-test counts: `wifi-densepose-vitals` **55** (was 51; +4 net new bug-catching tests — two §A2, two §A3), `wifi-densepose-hardware` **163**, `wifi-densepose-wifiscan` **87**, `wifi-densepose-calibration` **58**. 0 failures across all four.
+- **`cd v2 && cargo test --workspace --no-default-features`** — **3054 passed / 0 failed** (M2 left the workspace at 3050; the +4 net new bug-catching tests are included and green).
+- **`python archive/v1/data/proof/verify.py`** — **`VERDICT: PASS`**, pipeline hash unchanged `f8e76f21…46f7a` (these are Rust-only changes; the Python pipeline proof is independent and confirmed unaffected).
+- New `vitals_bench` compiles and runs under the default feature set.
+- **Disclosed validation limits:** the live-QUIC transport in `secure_tdm` is **structurally** tested (HMAC compute/verify, tamper, replay-window) but **not live-socket-tested** in CI; the serde-gated `ieee80211bf` types are additionally verifiable with `--features serde`. Clippy is not installed in the local 1.89 toolchain, so the per-crate lint pass was not run locally (the project gate is `cargo test`).
+
+---
+
+## 7. What changed, file by file
+
+- `vitals/heartrate.rs` — `filtered_history: Vec<f64>` → `VecDeque<f64>` (`push_back`/`pop_front`, `make_contiguous` once per `extract`); resonator `r` clamped to `[0, 0.9999]`; finite-guard before history push; corrected divergence-condition doc (`|r| ≥ 1`, not "`r` negative"); `low_sample_rate_filter_stays_finite` test.
+- `vitals/breathing.rs` — same `VecDeque` + clamp + finite-guard changes; weighted fusion extracted to `fuse_weighted_residuals` and **normalized by Σ(effective weights)** (the §A2 fix); three new tests (two A2, one A3).
+- `vitals/anomaly.rs`, `vitals/store.rs` — sliding/ring buffers → `VecDeque` (O(1) eviction); `store::history` takes `&mut self` to hand back a contiguous slice via `make_contiguous` (no external callers; observable contents unchanged).
+- `wifiscan/pipeline/breathing_extractor.rs` — `VecDeque<f32>` + `make_contiguous`.
+- `wifiscan/pipeline/correlator.rs` — per-BSSID histories → `Vec<VecDeque<f32>>`; contiguous-ize each touched buffer once before the Pearson pass.
+- `hardware/ieee80211bf/transport.rs` — `n_subcarriers: … as u16` → `u16::try_from(…).ok()?` (§B1 drop-instead-of-truncate, unreachable-path hardening).
+- `vitals/Cargo.toml` + `vitals/benches/vitals_bench.rs` (new) — criterion dev-dep, `[[bench]]`, the §D1 full-window benches.
+
+---
+
+## 8. Deferred backlog (NOT silently dropped)
+
+- **§B4 constant-time HMAC compare** — **RESOLVED (Milestone-1).** Replaced the short-circuiting `==` on the 8-byte tag with a hand-rolled branch-free `constant_time_tag_eq` (XOR-accumulate, no early exit, `#[inline(never)]` + `black_box`). **No new dependency** — the `subtle` crate was the only reason this was deferred, and a fixed 8-byte compare needs none. Pinned by `tag_compare_is_constant_time_shape` (proven to fail on a last-byte-skipping bug). Grade MEASURED (constant-time construction). See §2.6.
+- **802.11bf SBP conformance vectors** (§5 #2) — add real conformance test vectors to the `ieee80211bf/` model **when the Wi-Fi Alliance / WBA publishes a public test plan**. Do not invent vectors before then.
+- **Geometry-conditioned LoRA calibration head** (§5 #3) — built-but-unconsumed and **data-gated** on paired multi-room PCK data (ADR-152 measurement (b): data, not architecture, is the bottleneck). ACCEPTED-FUTURE.
+- **Native `wlanapi.dll` FFI multi-BSSID fast path** (§5 #4) — **RESOLVED + MEASURED (Milestone-1).** The native FFI is implemented and wired live (native-first, netsh fallback). Measured on this box (Intel Wi-Fi 7 BE201 320MHz, 2026-06-13): **native 21.42 Hz vs netsh 3.84 Hz = 5.57×**, mean 5.0 BSSIDs/scan, 50/50 native scans with no handle leak. Real positive result — no fabricated 10×. See §5 #4. (Note: a prior sweep recorded 9.74 Hz on a different/older adapter; the per-adapter number varies, the ratio over netsh is the claim.)
+- **Deep-CSI vital-sign model** (§5 #1) — DATA-GATED on paired PPG/ECG ground truth. No public ESP32 artifact reproduces the cited ~2–3 BPM MAE. Not on the near-term path.
+
+---
+
+## 9. Consequences
+
+**Positive.** The vital-sign extractors now use the correct O(1)-eviction data structure (no latent O(n²)), cannot mis-scale a breathing estimate from a partial attention-weight slice, and cannot be silently killed by a diverging IIR filter at a pathological sample rate. The 802.11bf construction site drops-instead-of-truncates on an (already-gated) oversized count. Most importantly, the layer's existing hardening — length-gated parsers, infallible fixed-width slices, validate-on-deserialize, no-panic FSMs, fixed-argv scanning, HMAC+replay TDM, overflow-clamped geometry embeddings — is now **documented as MEASURED negative results** with file:line evidence, so a reader can verify the "already safe" claims rather than take them on faith.
+
+**Negative / honest limits.** The §A1 perf change is **null end-to-end** at realistic window sizes — we land it for correctness, not speed, and the committed bench proves the null rather than hiding it. The research report's stated §A3 divergence trigger ("`fs` below ~4 Hz") was **physically inaccurate** (divergence needs `|r| ≥ 1` ⇒ `bw ≥ 4`, a far lower `fs`); we corrected it in the code comments and the test parameters and disclose the correction here. The strongest external SOTA candidates (deep-CSI vitals, learned calibration, native FFI scanning) are **all NO-ACTION or ACCEPTED-FUTURE** — data-gated, unmeasured, or blocked on a non-public conformance suite — and **none is presented as more than it is.** §B4 is consciously deferred. Nothing in this milestone is inflated beyond what a reverting reviewer can reproduce.