peltier.io/.github/workflows/ci.yml

name: ci
on:
  pull_request:
  push:
    branches: [main]

jobs:
  trust-layer:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: dtolnay/rust-toolchain@stable
      - uses: Swatinem/rust-cache@v2
      - run: cargo test --workspace
      - run: cargo clippy --workspace --all-targets -- -D warnings
      - run: cargo fmt --all --check

  # Phase 1: target gates run mechanically, and the bench workload
  # executes inside a NO-NETWORK container (SPEC §3.1/§10). The runner
  # is a shared VM — fine for gates; bench numbers for verdicts come
  # from calibrated hardware, not this job.
  target-gates-no-net:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: dtolnay/rust-toolchain@stable
      - uses: Swatinem/rust-cache@v2
      - name: Toolchains for C/C++ targets
        run: sudo apt-get update -qq && sudo apt-get install -y -qq clang cmake
      - name: Fetch pinned targets
        run: |
          sh targets/fetch.sh comrak
          sh targets/fetch.sh tokei
          sh targets/fetch.sh cjson
      - name: Generate + verify pinned corpora
        run: |
          sh corpora/comrak/gen-corpus.sh
          sh corpora/tokei/gen-corpus.sh
          sh corpora/cjson/gen-corpus.sh
      - name: Build tokei baseline
        run: cargo build --release --manifest-path targets/tokei/workspace/Cargo.toml
      - name: Gates — tokei (Rust; corpus pin -> upstream tests -> golden replay)
        run: cargo run -p diff-test -- tokei
      - name: Gates — cjson (C; clang build -> Unity/CTest -> golden replay)
        run: cargo run -p diff-test -- cjson
      - name: Bench workload inside no-network container
        run: |
          docker run --rm --network=none \
            -v "$PWD:/w" -w /w \
            debian:bookworm-slim \
            sh -c "targets/tokei/workspace/target/release/tokei --sort code corpora/tokei/input | sha256sum"

  # Informational: measure THIS runner's noise floor with the A/A +
  # injection harness and archive the evidence. A shared VM failing the
  # bars is expected — the artifact is the point (trust layer judges
  # environments empirically; verdict benches belong on bench-metal).
  runner-calibration:
    runs-on: ubuntu-latest
    continue-on-error: true
    steps:
      - uses: actions/checkout@v4
      - uses: dtolnay/rust-toolchain@stable
      - uses: Swatinem/rust-cache@v2
      - name: Calibrate (reduced sessions, synthetic CPU-bound workload)
        run: |
          mkdir -p calib
          cargo run -p bench-runner -- calibrate \
            --cmd "head -c 3000000 /dev/urandom | sha256sum" \
            --sessions 20 --out calib/gh-runner-calibration.json \
            | tee calib/summary.txt
      - uses: actions/upload-artifact@v4
        if: always()
        with:
          name: runner-calibration
          path: calib/

  # Informational: does perf work here, and with which event sources?
  perf-probe:
    runs-on: ubuntu-latest
    continue-on-error: true
    steps:
      - uses: actions/checkout@v4
      - name: Probe perf availability
        run: |
          sudo apt-get -qq update && sudo apt-get -qq install -y linux-tools-common linux-tools-generic || true
          PERF=$(ls /usr/lib/linux-tools/*/perf 2>/dev/null | head -1 || command -v perf || true)
          echo "perf binary: ${PERF:-none}"
          [ -n "$PERF" ] || exit 0
          sudo sysctl -w kernel.perf_event_paranoid=1 || true
          echo "--- software clock sampling:"
          $PERF record -e cpu-clock -o /tmp/p.data -- sh -c 'i=0; while [ $i -lt 2000000 ]; do i=$((i+1)); done' && $PERF report -i /tmp/p.data --stdio | head -5 || echo "cpu-clock sampling unavailable"
          echo "--- hardware cycle counter:"
          $PERF stat -e cycles true 2>&1 | tail -3 || true

  # The peltier skill's contract: preflight must resolve the trust layer when
  # one is reachable, and REFUSE when it is not. The refusal is the
  # safety-critical path — a skill that silently degrades to a hand-rolled
  # timing loop is worse than no skill — so it is asserted here, not assumed.
  # Statistical outcomes are NOT asserted: a shared runner is too noisy for
  # that, which is the whole reason the skill calibrates before it claims.
  skill-preflight:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: dtolnay/rust-toolchain@stable
      - uses: Swatinem/rust-cache@v2

      - name: SKILL.md conforms to the Agent Skills spec (both copies)
        run: |
          python3 - <<'PY'
          import re, sys, yaml, pathlib
          for skill in (".claude/skills/peltier", ".agents/skills/peltier"):
              p = pathlib.Path(skill) / "SKILL.md"
              text = p.read_text(encoding="utf-8")
              if not text.startswith("---\n"):
                  sys.exit(f"{p}: must open with a --- frontmatter block")
              fm = yaml.safe_load(text.split("---", 2)[1])   # raises on malformed YAML
              body = text.split("---", 2)[2]
              for key in ("name", "description"):
                  if not isinstance(fm.get(key), str) or not fm[key].strip():
                      sys.exit(f"{p}: frontmatter '{key}' must be a non-empty string")
              # agentskills.io spec: 1-64 chars, [a-z0-9-], no edge/double hyphens,
              # name == parent dir; description <= 1024 chars; body <= 500 lines.
              n = fm["name"]
              if not re.fullmatch(r"[a-z0-9]+(-[a-z0-9]+)*", n) or len(n) > 64:
                  sys.exit(f"{p}: name '{n}' violates the Agent Skills name rules")
              if n != p.parent.name:
                  sys.exit(f"{p}: name '{n}' != directory '{p.parent.name}'")
              if len(fm["description"]) > 1024:
                  sys.exit(f"{p}: description exceeds 1024 chars")
              if len(body.splitlines()) > 500:
                  sys.exit(f"{p}: body exceeds 500 lines")
              if "metadata" in fm and not (
                  isinstance(fm["metadata"], dict)
                  and all(isinstance(k, str) and isinstance(v, str) for k, v in fm["metadata"].items())
              ):
                  sys.exit(f"{p}: metadata must be a string-to-string map")
              print(f"{p}: spec OK (name={n}, description={len(fm['description'])} chars)")
          PY

      - name: .agents mirror is byte-identical to .claude canonical
        run: |
          diff -r .claude/skills/peltier .agents/skills/peltier
          echo "mirror identical"

      - name: Installer stamps both layouts + the ZeroClaw variant correctly
        run: |
          if sh scripts/install-skill.sh /tmp/no-such-dir 2>/dev/null; then
            echo "FAIL: installer accepted a nonexistent target"; exit 1
          fi
          mkdir -p /tmp/consumer && sh scripts/install-skill.sh /tmp/consumer
          diff -r .claude/skills/peltier /tmp/consumer/.claude/skills/peltier
          diff -r .claude/skills/peltier /tmp/consumer/.agents/skills/peltier
          sh scripts/install-skill.sh --zeroclaw-variant /tmp/zc-variant
          test ! -e /tmp/zc-variant/scripts   # script-less: ZeroClaw blocks script files
          test -f /tmp/zc-variant/SKILL.md
          diff -r .claude/skills/peltier/references /tmp/zc-variant/references
          echo "installer OK: both layouts identical to canonical; zeroclaw variant has no scripts/"

      - name: Preflight resolves inside a peltier checkout
        run: |
          sh .claude/skills/peltier/scripts/preflight.sh | tee /tmp/pf.txt
          grep -q '^STATUS=ok$' /tmp/pf.txt
          grep -q "^PELTIER_HOME=$PWD$" /tmp/pf.txt
          BR=$(sed -n 's/^BENCH_RUNNER=//p' /tmp/pf.txt); test -x "$BR"

      - name: Preflight REFUSES with no trust layer reachable
        run: |
          # The skill must be copied OUT of the checkout: preflight also walks
          # up from its own location, so running it in-place would find this
          # very repo and (correctly) resolve — testing nothing.
          cp -r .claude/skills/peltier /tmp/skillcopy
          cd /tmp && mkdir -p not-a-repo && cd not-a-repo
          set +e
          env -u PELTIER_HOME sh /tmp/skillcopy/scripts/preflight.sh > out.txt 2>&1
          rc=$?
          set -e
          cat out.txt
          test "$rc" -ne 0 || { echo "FAIL: preflight did not refuse"; exit 1; }
          grep -q '^STATUS=refuse$' out.txt

      - name: Preflight works when consumed from another repo (PELTIER_HOME)
        run: |
          cd /tmp && mkdir -p other-project && cd other-project
          PELTIER_HOME="$GITHUB_WORKSPACE" \
            sh "$GITHUB_WORKSPACE/.claude/skills/peltier/scripts/preflight.sh" | tee pf.txt
          grep -q '^STATUS=ok$' pf.txt

      - name: The harness the skill drives actually runs (plumbing, not verdict)
        run: |
          BR=$(sed -n 's/^BENCH_RUNNER=//p' /tmp/pf.txt)
          cp .claude/skills/peltier/assets/accept.template.toml /tmp/accept.toml
          "$BR" --config /tmp/accept.toml compare \
            --baseline 'sleep 0.02' --candidate 'sleep 0.02' | tee /tmp/cmp.txt
          grep -q 'speedup (baseline/candidate): median .*95% CI \[' /tmp/cmp.txt
          grep -q '^verdict: ' /tmp/cmp.txt

      - name: Noise floor of this runner (informational — A/A must find nothing)
        continue-on-error: true
        run: |
          BR=$(sed -n 's/^BENCH_RUNNER=//p' /tmp/pf.txt)
          "$BR" --config /tmp/accept.toml aa --cmd 'sleep 0.02'