name: Security

# Security gate: dependency vulnerability scanning (SCA), static analysis
# (CodeQL/SAST), and secret scanning. Runs on every PR to main, on push to
# main, weekly (to catch newly-disclosed CVEs without a code change), and on
# demand. Each job is an independent required check.

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]
  schedule:
    # Mondays 06:00 UTC — surface CVEs disclosed since the last commit.
    - cron: "0 6 * * 1"
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: security-${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

jobs:
  # ---- SCA: dependency vulnerability scan -------------------------------
  # Audits the PRODUCTION dependency set ([all]) exported from uv.lock. The
  # `benchmark` extra is intentionally excluded from [all] (it pulls lm-eval's
  # sqlitedict/nltk, which carry unpatchable upstream High CVEs and are never
  # installed in production), so this gate fails only on actionable findings.
  dependency-audit:
    name: Dependency audit (pip-audit)
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@v7

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.12"

      - name: Install uv
        uses: astral-sh/setup-uv@v5

      - name: Export production dependency set from uv.lock
        run: |
          uv export --frozen --no-dev --no-emit-project --no-hashes \
            --extra all --format requirements-txt > requirements-prod.txt
          echo "Production dependencies audited:"
          wc -l requirements-prod.txt

      - name: Audit dependencies (pip-audit)
        uses: pypa/gh-action-pip-audit@v1.1.0
        with:
          inputs: requirements-prod.txt

  # ---- SAST: CodeQL static analysis ------------------------------------
  codeql:
    name: CodeQL (${{ matrix.language }})
    runs-on: ubuntu-latest
    timeout-minutes: 30
    permissions:
      contents: read
      security-events: write
      actions: read
    strategy:
      fail-fast: false
      matrix:
        language: [python, javascript-typescript]
    steps:
      - uses: actions/checkout@v7

      - name: Initialize CodeQL
        uses: github/codeql-action/init@v3
        with:
          languages: ${{ matrix.language }}
          queries: security-extended

      - name: Perform CodeQL analysis
        uses: github/codeql-action/analyze@v3
        with:
          category: "/language:${{ matrix.language }}"

  # ---- Secret scanning -------------------------------------------------
  # Uses the gitleaks BINARY (MIT-licensed, no key) instead of
  # gitleaks-action, which requires a paid GITLEAKS_LICENSE for organization
  # repos. On PRs we scan only the PR's commits so pre-existing history can't
  # block a PR; on push/schedule we scan the working tree. Config + allowlist
  # live in .gitleaks.toml at the repo root (auto-loaded).
  secret-scan:
    name: Secret scan (gitleaks)
    runs-on: ubuntu-latest
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@v7
        with:
          fetch-depth: 0

      - name: Install gitleaks
        run: |
          version=8.18.4
          curl -sSfL \
            "https://github.com/gitleaks/gitleaks/releases/download/v${version}/gitleaks_${version}_linux_x64.tar.gz" \
            -o /tmp/gitleaks.tar.gz
          tar -xzf /tmp/gitleaks.tar.gz -C /tmp gitleaks
          sudo install /tmp/gitleaks /usr/local/bin/gitleaks
          gitleaks version

      - name: Scan for secrets
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
        run: |
          if [ -n "$BASE_SHA" ]; then
            echo "Scanning PR commits ${BASE_SHA}..HEAD"
            gitleaks detect --source . --log-opts="${BASE_SHA}..HEAD" --redact --no-banner
          else
            echo "Scanning working tree"
            gitleaks detect --source . --no-git --redact --no-banner
          fi