OpenAgentsControl/.github/workflows/test-agents.yml

name: Test Agents

on:
  pull_request:
    branches: [ main, dev ]
    paths:
      - '.opencode/agent/**'
      - 'evals/**'
      - '.github/workflows/test-agents.yml'
  push:
    branches: [ main ]
  workflow_dispatch:

jobs:
  test-openagent:
    name: Test OpenAgent
    runs-on: ubuntu-latest
    timeout-minutes: 10
    
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
      
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'
          cache: 'npm'
          cache-dependency-path: 'evals/framework/package-lock.json'
      
      - name: Install dependencies
        run: |
          cd evals/framework
          npm ci
      
      - name: Build framework
        run: |
          cd evals/framework
          npm run build
      
      - name: Run OpenAgent smoke test
        run: npm run test:ci:openagent
        env:
          CI: true
      
      - name: Upload test results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: openagent-results
          path: evals/results/
          retention-days: 30

  test-opencoder:
    name: Test OpenCoder
    runs-on: ubuntu-latest
    timeout-minutes: 10
    
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
      
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'
          cache: 'npm'
          cache-dependency-path: 'evals/framework/package-lock.json'
      
      - name: Install dependencies
        run: |
          cd evals/framework
          npm ci
      
      - name: Build framework
        run: |
          cd evals/framework
          npm run build
      
      - name: Run OpenCoder smoke test
        run: npm run test:ci:opencoder
        env:
          CI: true
      
      - name: Upload test results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: opencoder-results
          path: evals/results/
          retention-days: 30

  report-results:
    name: Report Test Results
    runs-on: ubuntu-latest
    needs: [test-openagent, test-opencoder]
    if: always()
    
    steps:
      - name: Download OpenAgent results
        uses: actions/download-artifact@v4
        with:
          name: openagent-results
          path: results/openagent
        continue-on-error: true
      
      - name: Download OpenCoder results
        uses: actions/download-artifact@v4
        with:
          name: opencoder-results
          path: results/opencoder
        continue-on-error: true
      
      - name: Display results summary
        run: |
          echo "## Test Results Summary" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          
          if [ -f results/openagent/latest.json ]; then
            echo "### OpenAgent" >> $GITHUB_STEP_SUMMARY
            cat results/openagent/latest.json | jq -r '"- Passed: \(.passed)\n- Failed: \(.failed)\n- Total: \(.total)"' >> $GITHUB_STEP_SUMMARY
          fi
          
          if [ -f results/opencoder/latest.json ]; then
            echo "" >> $GITHUB_STEP_SUMMARY
            echo "### OpenCoder" >> $GITHUB_STEP_SUMMARY
            cat results/opencoder/latest.json | jq -r '"- Passed: \(.passed)\n- Failed: \(.failed)\n- Total: \(.total)"' >> $GITHUB_STEP_SUMMARY
          fi