scene-actor-extraction/.gitea/workflows/traceability-check.yml

name: Traceability Validation

# Mirrors JellyTau's .gitea/workflows/traceability-check.yml. The extractor is
# stdlib Python, so there is no toolchain install step and no jq.
#
# This workflow is component-agnostic: every repo-specific setting - which ID
# prefixes count, which file suffixes are source, which directories to scan,
# the threshold - lives in traceability.toml at the repo root, and the same
# extractor is shared by all three JRay components. Copying this file into
# another component needs no edits.
#
# NOTE: the runner here is an Intel N100 with no discrete GPU. This job is only
# ever static analysis of source comments plus markdown parsing, so it is cheap;
# the requirements it reports as "tagged but unexecuted" are the ones that need
# a GPU host, and they are deliberately never counted as covered.

on:
  push:
    branches:
      - main
      - master
      - develop
  pull_request:
    branches:
      - main
      - master
      - develop

jobs:
  validate-traces:
    runs-on: linux/amd64
    name: Check requirement traces

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          submodules: recursive

      - name: Check Python is available
        run: |
          set -e
          command -v python3 >/dev/null 2>&1 || {
            echo "python3 is missing from the runner image."
            echo "The traceability tooling is stdlib-only Python;"
            echo "3.9+ with CLI flags, 3.11+ to read traceability.toml."
            exit 1
          }
          python3 --version

      # The gate's own arithmetic is the thing being trusted, so its tests run
      # before it does. JellyTau's gate was believed for months while it was
      # dividing by frozen literals; untested gate logic is how that happens.
      - name: Test the extractor
        run: python3 scripts/vendor/jray-project/scripts/traceability/test_extract_traces.py

      # Threshold policy and every other repo-specific setting live in
      # traceability.toml, not here, so local runs and CI runs cannot disagree
      # about what "passing" means. Denominators come from docs/requirements.md
      # at run time and are never hardcoded -- in this file or anywhere else.
      #
      # A misconfigured run (zero requirements parsed, zero files scanned) is a
      # hard failure rather than a plausible-looking 0%.
      - name: Traceability gate
        run: sh scripts/vendor/jray-project/scripts/traceability/traceability-gate.sh

      - name: Check modified files for traces
        if: github.event_name == 'pull_request'
        run: |
          set -e
          echo "Checking modified sources for TRACES tags..."

          # The extensions come from the report the gate just wrote, which got
          # them from traceability.toml. Restating them here would be a second
          # place for the source-file definition to live, and the two would
          # drift the first time a language is added.
          PATTERN=$(python3 -c "
          import json, re, sys
          suffixes = json.load(open('traces-report.json'))['config']['sourceSuffixes']
          print('(' + '|'.join(re.escape(s) + '\$' for s in suffixes) + ')')
          ")
          echo "Source suffixes from traceability.toml: $PATTERN"

          CHANGED=$(git diff --name-only "origin/${{ github.base_ref }}...HEAD" \
                    | grep -E "$PATTERN" || true)

          if [ -z "$CHANGED" ]; then
            echo "No source files changed."
            exit 0
          fi

          echo "Changed files:"
          echo "$CHANGED" | sed 's/^/   /'
          echo ""

          # Advisory by design: not every file implements a requirement, and a
          # tag on every function is noise that rots faster than it helps
          # (CLAUDE.md: tag the unit that decides). This step exists to prompt,
          # not to block. The blocking checks are in the gate step above.
          #
          # Piped into the loop rather than a here-string, and `case` rather
          # than `[[ == ]]`, so this works under dash as well as bash. The loop
          # body runs in a subshell, so misses are recorded in a file.
          MISSING=$(mktemp)
          echo "$CHANGED" | while IFS= read -r file; do
            case "$file" in
              */test_*.py|*_test.py|*Tests.cs|tests/*|*/tests/*) continue ;;
            esac
            [ -f "$file" ] || continue
            if ! grep -q 'TRACES:' "$file"; then
              echo "   no TRACES tag: $file"
              echo "$file" >> "$MISSING"
            fi
          done

          COUNT=$(wc -l < "$MISSING" | tr -d ' ')
          rm -f "$MISSING"

          if [ "$COUNT" -gt 0 ]; then
            echo ""
            echo "$COUNT changed file(s) carry no requirement tag."
            echo "Format: // TRACES: AR-012, AR-013 | SR-002"
            echo "        (pipe separates requirement types, comma separates IDs)"
            echo "A deliberate invariant exception is tagged separately:"
            echo "        // EXCEPTION: AR-024 <reason>"
            echo "See CLAUDE.md and SPEC.md section 6."
          fi

      - name: Report summary
        if: always()
        run: |
          echo "Traceability matrix: docs/traceability.md"
          echo ""
          head -40 docs/traceability.md || true

      - name: Save reports
        if: always()
        uses: actions/upload-artifact@v3
        with:
          name: traceability-reports
          path: |
            traces-report.json
            docs/traceability.md
          retention-days: 30