HTTP Agent CI/CD Integration

name: Workflow Evaluation with Maxim

on:
  push:
    branches: [main, dev]
  pull_request:
    branches: [main]
  workflow_dispatch:

env:
  TEST_RUN_NAME: "Workflow Evaluation - ${{ github.sha }}"
  CONTEXT_TO_EVALUATE: "context"
  EVALUATORS: "bias, clarity, faithfulness"

jobs:
  evaluate-agent:
    runs-on: ubuntu-latest
    name: Run Workflow Evaluation

    steps:
      - name: Checkout Repository
        uses: actions/checkout@v4

      - name: Run Workflow Test with Maxim
        id: workflow_test
        uses: maximhq/actions/test-runs@v1
        with:
          api_key: ${{ secrets.MAXIM_API_KEY }}
          workspace_id: ${{ vars.WORKSPACE_ID }}
          test_run_name: ${{ env.TEST_RUN_NAME }}
          dataset_id: ${{ vars.DATASET_ID }}
          workflow_id: ${{ vars.WORKFLOW_ID }}
          context_to_evaluate: ${{ env.CONTEXT_TO_EVALUATE }}
          evaluators: ${{ env.EVALUATORS }}

      - name: Display Test Results
        if: always()
        run: |
          echo "Workflow Test Results:"
          echo "${{ steps.workflow_test.outputs.test_run_result }}"
          echo ""
          echo "Failed Indices: ${{ steps.workflow_test.outputs.test_run_failed_indices }}"
          echo ""
          echo "📊 View detailed report: ${{ steps.agent_test.outputs.test_run_report_url }}"

      - name: Check Test Status
        if: failure()
        run: |
          echo "❌ Workflow evaluation failed. Check the detailed report for more information."
          exit 1

      - name: Success Notification
        if: success()
        run: |
          echo "✅ Workflow evaluation passed successfully!"