on:
  workflow_run:
    workflows: ["CI"]
    types: [completed]

permissions:
  contents: read
  actions: write

jobs:
  detect-flaky:
    runs-on: ubuntu-latest
    if: ${{ github.event.workflow_run.conclusion == 'failure' }}
…
      - name: Detect flaky test failures
        id: detect
        uses: anthropics/claude-code-action@main
        with:
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          prompt: |
            The CI workflow failed: ${{ github.event.workflow_run.html_url }}

            Check the logs: gh run view ${{ github.event.workflow_run.id }} --log-failed

            Determine if this looks like a flaky test failure by checking for:
            - Timeout errors
            - Race conditions
            - Network errors
            - "Expected X but got Y" intermittent failures
            - Tests that passed in previous commits

            Return:
            - is_flaky: true if likely flaky, false if real bug
            - confidence: number 0-1 indicating confidence level
            - summary: brief one-sentence explanation
          claude_args: |
            --json-schema '{"type":"object","properties":{"is_flaky":{"type":"boolean","description":"Whether this appears to be a flaky test failure"},"confidence":{"type":"number","minimum":0,"maximum":1,"description":"Confidence level in the determination"},"summary":{"type":"string","description":"One-sentence explanation of the failure"}},"required":["is_flaky","confidence","summary"]}'

      # Auto-retry only if flaky AND high confidence (>= 0.7)
      - name: Retry flaky tests
        if: |
          fromJSON(steps.detect.outputs.structured_output).is_flaky == true &&
          fromJSON(steps.detect.outputs.structured_output).confidence >= 0.7
        env:
          GH_TOKEN: ${{ github.token }}
          WORKFLOW_NAME: ${{ github.event.workflow_run.name }}
          HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
        run: |
          OUTPUT='${{ steps.detect.outputs.structured_output }}'
Warm-up
