auto-retry-flaky-tests.yml

name: Auto-Retry Flaky Tests

# Use case: When CI fails, automatically determine if it's likely flaky and retry if so.
# Original: https://github.com/anthropics/claude-code-action/blob/main/examples/test-failure-analysis.yml

on:
  workflow_run:
    workflows: ["Flow build and test"]
    types: [completed]

permissions:
  contents: read
  actions: write
  id-token: write
  pull-requests: write

jobs:
  detect-flaky:
    if: |
      github.event.workflow_run.conclusion == 'failure' &&
      github.event.workflow_run.head_repository.full_name == github.repository &&
      github.event.workflow_run.run_attempt <= 5
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6

      - name: Detect flaky test failures
        id: detect
        uses: anthropics/claude-code-action@a92e7c70a4da9793dc164451d829089dc057a464 # main
        with:
          allowed_bots: 'renovate'
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          additional_permissions: |
            actions: read
          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: |
            --allowedTools 'Bash(gh run view *)' --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 }}
          OUTPUT: ${{ steps.detect.outputs.structured_output }}
        run: |
          CONFIDENCE=$(echo "$OUTPUT" | jq -r '.confidence')
          SUMMARY=$(echo "$OUTPUT" | jq -r '.summary')

          echo "🔄 Flaky test detected (confidence: $CONFIDENCE)"
          echo "Summary: $SUMMARY"
          echo ""
          echo "Triggering automatic retry..."

          gh run rerun ${{ github.event.workflow_run.id }} --failed

      # Low confidence flaky detection - skip retry
      - name: Low confidence detection
        if: |
          fromJSON(steps.detect.outputs.structured_output).is_flaky == true &&
          fromJSON(steps.detect.outputs.structured_output).confidence < 0.7
        env:
          OUTPUT: ${{ steps.detect.outputs.structured_output }}
        run: |
          CONFIDENCE=$(echo "$OUTPUT" | jq -r '.confidence')

          echo "⚠️ Possible flaky test but confidence too low ($CONFIDENCE)"
          echo "Not retrying automatically - manual review recommended"

      # Comment on PR if this was a PR build
      - name: Comment on PR
        if: github.event.workflow_run.event == 'pull_request'
        env:
          GH_TOKEN: ${{ github.token }}
          OUTPUT: ${{ steps.detect.outputs.structured_output }}
        run: |
          IS_FLAKY=$(echo "$OUTPUT" | jq -r '.is_flaky')
          CONFIDENCE=$(echo "$OUTPUT" | jq -r '.confidence')
          SUMMARY=$(echo "$OUTPUT" | jq -r '.summary')

          pr_number=$(gh pr list --head "${{ github.event.workflow_run.head_branch }}" --json number --jq '.[0].number')

          if [ -n "$pr_number" ]; then
            if [ "$IS_FLAKY" = "true" ] && [ "$(echo "$CONFIDENCE >= 0.7" | bc)" -eq 1 ]; then
              TITLE="🔄 Flaky Test Detected"
              ACTION="✅ Automatically retrying the workflow"
            elif [ "$IS_FLAKY" = "true" ]; then
              TITLE="🔄 Possible Flaky Test"
              ACTION="⚠️ Confidence too low ($CONFIDENCE) to retry automatically - manual review recommended"
            else
              TITLE="❌ Test Failure"
              ACTION="⚠️ This appears to be a real bug - manual intervention needed"
            fi

            gh pr comment "$pr_number" --body "$(cat <<EOF
          ## $TITLE

          **Analysis**: $SUMMARY
          **Confidence**: $CONFIDENCE

          $ACTION

          [View workflow run](${{ github.event.workflow_run.html_url }})
          EOF
          )"
          fi