molecule-core/.github/workflows/codeql.yml

name: CodeQL

# Controls CodeQL scan triggers for this repo.
#
# GitHub's "Code quality" default setup (the UI-configured one) is
# hardcoded to only scan the default branch — on this repo that's
# `staging`, so PRs promoting staging→main would otherwise never be
# scanned. This workflow fills that gap by explicitly scanning both
# branches on push and PR.
#
# Runs on ubuntu-latest (GHA-hosted — public repo, free). GHAS is NOT
# enabled on this repo, so results are not uploaded to the Security
# tab — the scan fails the PR check on findings, and the SARIF is
# kept as a workflow artifact for triage.

on:
  push:
    branches: [main, staging]
  pull_request:
    branches: [main, staging]
  # GitHub merge queue fires `merge_group` for the queue's pre-merge CI run.
  # Required so CodeQL Analyze checks get a real result on the queued
  # commit instead of a false-green. Event only fires once merge queue is
  # enabled on the target branch — safe to add unconditionally.
  merge_group:
    types: [checks_requested]
  schedule:
    # Weekly run picks up findings in code that hasn't been touched.
    - cron: '30 1 * * 0'

# Workflow-level concurrency: only one CodeQL run per branch/PR at a time.
# `cancel-in-progress: false` queues new runs so a quick follow-up push
# doesn't nuke a 45-min analysis mid-flight.
concurrency:
  group: codeql-${{ github.ref }}
  cancel-in-progress: false

permissions:
  actions: read
  contents: read
  # No security-events: write — we don't call the upload API.

jobs:
  analyze:
    name: Analyze (${{ matrix.language }})
    runs-on: ubuntu-latest
    timeout-minutes: 45

    strategy:
      fail-fast: false
      matrix:
        language: [go, javascript-typescript, python]

    steps:
      - name: Checkout
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4

      - name: Checkout sibling plugin repo
        # Same reasoning as publish-workspace-server-image.yml — the Go
        # module's replace directive needs the plugin source so
        # CodeQL's "go build" phase can resolve.
        if: matrix.language == 'go'
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
        with:
          repository: Molecule-AI/molecule-ai-plugin-github-app-auth
          path: molecule-ai-plugin-github-app-auth
          token: ${{ secrets.PLUGIN_REPO_PAT || secrets.GITHUB_TOKEN }}

      # jq is pre-installed on ubuntu-latest — no setup step needed.

      - name: Initialize CodeQL
        uses: github/codeql-action/init@ce64ddcb0d8d890d2df4a9d1c04ff297367dea2a # v3
        with:
          languages: ${{ matrix.language }}
          # security-extended widens past the default to include the
          # full security-query set for a public SaaS surface.
          queries: security-extended

      - name: Autobuild
        uses: github/codeql-action/autobuild@ce64ddcb0d8d890d2df4a9d1c04ff297367dea2a # v3

      - name: Perform CodeQL Analysis
        id: analyze
        uses: github/codeql-action/analyze@ce64ddcb0d8d890d2df4a9d1c04ff297367dea2a # v3
        with:
          category: "/language:${{ matrix.language }}"
          # upload: never — GHAS isn't enabled on this repo, so the
          # upload API 403s. Write SARIF locally instead.
          upload: never
          output: sarif-results/${{ matrix.language }}

      - name: Parse SARIF + fail on findings
        # The analyze step writes <database>.sarif into the output
        # directory — database name is the short CodeQL lang id, not
        # the matrix value (e.g. "javascript-typescript" →
        # javascript.sarif), so glob rather than hardcode.
        # Filter to error/warning severity: security-extended emits
        # "note" rows for informational findings we don't want to fail
        # the build over.
        shell: bash
        run: |
          set -euo pipefail
          dir="sarif-results/${{ matrix.language }}"
          sarif=$(ls "$dir"/*.sarif 2>/dev/null | head -1 || true)
          if [ -z "$sarif" ] || [ ! -f "$sarif" ]; then
            echo "::error::No SARIF file found under $dir"
            ls -la "$dir" 2>/dev/null || true
            exit 1
          fi
          echo "Parsing $sarif"
          count=$(jq '[.runs[].results[] | select(.level == "error" or .level == "warning")] | length' "$sarif")
          echo "CodeQL findings (error+warning) for ${{ matrix.language }}: $count"
          if [ "$count" -gt 0 ]; then
            echo "::error::CodeQL found $count issues. Details below; full SARIF in the artifact."
            jq -r '.runs[].results[] | select(.level == "error" or .level == "warning") | "  - [\(.level)] \(.ruleId // "?"): \(.message.text // "(no message)") @ \(.locations[0].physicalLocation.artifactLocation.uri // "?"):\(.locations[0].physicalLocation.region.startLine // "?")"' "$sarif"
            exit 1
          fi          

      - name: Upload SARIF artifact
        # Keep SARIF around on success + failure so triagers can diff.
        # 14-day retention — longer than default 3, short enough not
        # to bloat quota.
        if: always()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
        with:
          name: codeql-sarif-${{ matrix.language }}
          path: sarif-results/${{ matrix.language }}/
          retention-days: 14