live-probes.yml

name: Live probes
# Runs the live Claude startup probes against the real Claude service. It is not a pull request check: it runs
# nightly on the default branch and when started by hand. See docs/implementation/ci.md.
on:
  workflow_dispatch:
  schedule:
    - cron: '23 6 * * *'
permissions:
  contents: read
concurrency:
  group: live-probes
  cancel-in-progress: false
jobs:
  live-probes:
    runs-on: ubuntu-latest
    # The probes' own time limits total 44 min (6, 8, 8, 11 and 11). agent-container and agent-supervisor may each spend
    # up to 10 min building the image before their probes; agent-question and agent-planning build inside their probes'
    # own 11 min. The teardown hooks have Vitest limits that total 26 min: agent-container 2 after each test and 13 at
    # the end (two sweeps of up to 5.5 min each, #189), agent-supervisor 7, agent-question 2 and agent-planning 2. That
    # is 90 min, plus setup. These are only Vitest's limits: Vitest's hook timer cannot fire while a synchronous docker
    # call blocks, and some calls in these hooks have no timeout of their own (the sweeps' calls have 30 s each). The
    # 100 min job limit caps the run.
    timeout-minutes: 100
    steps:
      # Fail at once when the secret is missing, so a missing secret never looks like a passing run.
      - name: Require the Claude token
        env:
          CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
        run: |
          if [ -z "$CLAUDE_CODE_OAUTH_TOKEN" ]; then
            echo "::error::The repository secret CLAUDE_CODE_OAUTH_TOKEN is not set. Add it to run the live probes."
            exit 1
          fi
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: '26.7.0'
          cache: npm
      - run: npm ci --ignore-scripts
      # The docker project runs these files one at a time, as in the Agent isolation workflow. The filter keeps only
      # the tests whose titles end in "(live Claude)".
      - name: Run the live Claude probes
        env:
          CODEBOOST_RUN_AUTH_PROBES: '1'
          CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
        run: npx vitest run --project docker -t '\(live Claude\)$' --reporter=default --reporter=json --outputFile=live-probes.json test/agent-container.test.ts test/agent-question.test.ts test/agent-supervisor.test.ts test/agent-planning.test.ts
      # Vitest exits 0 when it skips every probe, so check that each probe passed and nothing else ran.
      - name: Check that every probe passed
        run: node scripts/live-probes.ts check live-probes.json