RuView/.github/workflows/model-release-gate.yml

name: Model release gate (ADR-298)

# ADR-298 model-release sanity gates (issue #1521): structural checks that
# block a degenerate/mislabeled classifier head (unreachable decision
# boundary, near-constant output, degenerate class balance, a metric
# surfaced under a task name it wasn't computed as) before it ships.
#
# Checkers:
#   * v2/crates/wifi-densepose-train/src/model_gates.rs
#   * v2/crates/wifi-densepose-train/src/sensing_claim_gate.rs (ADR-328)
#
# IMPORTANT — the honest scope of this job: it protects the structural model
# checker from regressing and hard-fails every committed sensing claim manifest
# that does not satisfy the repository-owned ADR-328 policy. It still does NOT
# gate an actual HuggingFace model publish because this repository does not
# automate uploads to `ruvnet/wifi-densepose-pretrained`; that remains a manual,
# human-run step. Before publishing or replacing a model artifact there, run
# the structural model gate against the real head weights locally:
#
#   cargo test -p wifi-densepose-train model_gates
#
# and, until a CLI entry point exists to run `evaluate_linear_head` against an
# arbitrary `.safetensors`/`.rvf` file, load the head's `weight`/`bias` in a
# short script and call `wifi_densepose_train::evaluate_linear_head` directly.

on:
  push:
    branches:
      - main
      - master
    paths:
      - "v2/crates/wifi-densepose-train/**"
      - "evidence/claims/**"
      - "evidence/fixtures/**"
      - "evidence/policies/**"
      - "README.md"
      - "benchmarks/**"
      - "docs/benchmarks/**"
      - "docs/releases/**"
      - "docs/huggingface/**"
      - "docs/adr/ADR-298-model-release-sanity-gates.md"
      - "docs/adr/ADR-304-evidence-engine.md"
      - "docs/adr/ADR-328-sensing-evidence-claim-gate.md"
      - ".github/workflows/model-release-gate.yml"
      - ".github/CODEOWNERS"
  pull_request:
    paths:
      - "v2/crates/wifi-densepose-train/**"
      - "evidence/claims/**"
      - "evidence/fixtures/**"
      - "evidence/policies/**"
      - "README.md"
      - "benchmarks/**"
      - "docs/benchmarks/**"
      - "docs/releases/**"
      - "docs/huggingface/**"
      - "docs/adr/ADR-298-model-release-sanity-gates.md"
      - "docs/adr/ADR-304-evidence-engine.md"
      - "docs/adr/ADR-328-sensing-evidence-claim-gate.md"
      - ".github/workflows/model-release-gate.yml"
      - ".github/CODEOWNERS"
  workflow_dispatch:

permissions:
  contents: read

env:
  # Update only with the CODEOWNERS-reviewed policy. This prevents an unnoticed
  # threshold edit from changing the policy consumed by the same workflow.
  CLAIM_POLICY_SHA256: 1ba2b73ede726a789aa50f4eb60a443429bb2f38ff3a2acf27755708265e303f

jobs:
  model-release-gate:
    name: Model release gate check
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262
        with:
          persist-credentials: false
          submodules: recursive
          fetch-depth: 0

      - name: Verify protected claim-policy digest
        run: |
          actual="$(sha256sum evidence/policies/sensing-claim-policy-v1.json | cut -d ' ' -f 1)"
          test "$actual" = "$CLAIM_POLICY_SHA256"

      - name: Require evidence manifest for changed public claim surfaces
        if: github.event_name == 'pull_request'
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
        run: |
          mapfile -d '' -t changed < <(git diff --name-only -z --diff-filter=ACMRT "$BASE_SHA" "$GITHUB_SHA")
          changed_manifests=()
          for path in "${changed[@]}"; do
            case "$path" in
              evidence/claims/research/*.json|evidence/claims/production/*.json|evidence/claims/safety_critical/*.json)
                changed_manifests+=("$path")
                ;;
            esac
          done

          for surface in "${changed[@]}"; do
            required_class=""
            case "$surface" in
              README.md)
                if git diff --unified=0 "$BASE_SHA" "$GITHUB_SHA" -- README.md \
                    | grep -Eiq '^\+[^+].*(accuracy|auc|precision|recall|sensitivity|specificity|false[ -]?positive|confidence|detect|through walls|heart[ -]?rate|breathing|occupancy|presence|pose|pck|mpjpe|latency|held[ -]?out|benchmark|score|production[ -]?ready|[0-9]+([.][0-9]+)?(%|[[:space:]]*(ms|hz|bpm)))'; then
                  required_class="production"
                else
                  continue
                fi
                ;;
              benchmarks/*|docs/benchmarks/*)
                if git diff --unified=0 "$BASE_SHA" "$GITHUB_SHA" -- "$surface" \
                    | grep -Eiq '^\+[^+].*(production|ready|deploy|ship|safety|medical|commercial)'; then
                  required_class="production"
                else
                  required_class="any"
                fi
                ;;
              docs/releases/*|docs/huggingface/*)
                required_class="production"
                ;;
              *)
                continue
                ;;
            esac

            matched=false
            for manifest in "${changed_manifests[@]}"; do
              [[ -f "$manifest" ]] || continue
              relative="${manifest#evidence/claims/}"
              class="${relative%%/*}"
              filename="${relative#*/}"
              [[ "$filename" != */* ]] || continue
              if [[ "$required_class" == production && "$class" != production ]]; then
                continue
              fi
              if jq -e --arg surface "$surface" \
                  '(.claim_surface_paths | type == "array") and (.claim_surface_paths | index($surface) != null)' \
                  "$manifest" >/dev/null; then
                matched=true
                break
              fi
            done
            if [[ "$matched" != true ]]; then
              echo "Public claim surface $surface changed without a matching $required_class class-bound evidence manifest." >&2
              exit 1
            fi
          done

      - name: Install Rust toolchain
        run: rustup toolchain install 1.89 --profile minimal

      - name: Run the model-release gate's own test suite
        working-directory: v2
        run: cargo test -p wifi-densepose-train --no-default-features model_gates -- --nocapture

      - name: Run sensing evidence and claim gate tests
        working-directory: v2
        run: cargo test -p wifi-densepose-train --no-default-features sensing_claim_gate -- --nocapture

      - name: Validate repository policy with research-only fixture
        working-directory: v2
        run: |
          mkdir -p ../evidence-receipts
          cargo run -p wifi-densepose-train --no-default-features \
            --bin sensing-claim-gate -- \
            --manifest ../evidence/fixtures/research-synthetic.json \
            --policy ../evidence/policies/sensing-claim-policy-v1.json \
            --required-class research \
            --receipt ../evidence-receipts/research-synthetic.receipt.json

      - name: Gate every committed sensing claim manifest
        working-directory: v2
        run: |
          mkdir -p ../evidence-receipts
          manifest_count=0
          gate_failed=false
          while IFS= read -r -d '' manifest; do
            relative="${manifest#../evidence/claims/}"
            class="${relative%%/*}"
            filename="${relative#*/}"
            if [[ ! -f "$manifest" || -L "$manifest" ]]; then
              echo "Claim manifest must be a regular non-symlink file: $manifest" >&2
              gate_failed=true
              continue
            fi
            if [[ "$filename" == */* || ! "$filename" =~ ^[a-z0-9][a-z0-9._-]*\.json$ ]]; then
              echo "Claim JSON must be exactly one level below a class directory and use a canonical filename: $manifest" >&2
              gate_failed=true
              continue
            fi
            case "$class" in
              research|production|safety_critical) ;;
              *)
                echo "Unsupported claim class directory for $manifest" >&2
                gate_failed=true
                continue
                ;;
            esac
            cli_class="${class//_/-}"
            stem="${filename%.json}"
            manifest_count=$((manifest_count + 1))
            if ! cargo run -p wifi-densepose-train --no-default-features \
                --bin sensing-claim-gate -- \
                --manifest "$manifest" \
                --policy ../evidence/policies/sensing-claim-policy-v1.json \
                --required-class "$cli_class" \
                --receipt "../evidence-receipts/${class}-${stem}.receipt.json"; then
              gate_failed=true
            fi
          done < <(find ../evidence/claims -name '*.json' -print0 | sort -z)
          if (( manifest_count == 0 )); then
            echo "Claim inventory is empty; at least one class-bound manifest is required." >&2
            exit 1
          fi
          if [[ "$gate_failed" == true ]]; then
            echo "One or more sensing claim manifests failed closed." >&2
            exit 1
          fi

      - name: Upload machine-readable evidence receipts
        if: always()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
        with:
          name: sensing-claim-receipts
          path: evidence-receipts/
          if-no-files-found: warn

      - name: Summarize result
        if: always()
        run: |
          {
            echo '### Model release gate (ADR-298)'
            echo ''
            echo 'This job protects `model_gates.rs` and the ADR-328 claim gate from'
            echo 'regressing, and gates every JSON manifest in `evidence/claims/`.'
            echo 'This is repository evidence lint. The committed policy disables'
            echo 'production and safety claims until artifact retrieval, a real presence'
            echo 'reproducer, authenticated evaluator attestation, and maintainer review.'
            echo 'It does not gate the external HuggingFace upload.'
          } >> "$GITHUB_STEP_SUMMARY"