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

name: Test Agents

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

jobs:
  # Check if this is a PR merge commit (skip tests if so - they already ran on PR)
  check-trigger:
    name: Check Trigger Type
    runs-on: ubuntu-latest
    outputs:
      should_test: ${{ steps.check.outputs.should_test }}
      should_bump: ${{ steps.check.outputs.should_bump }}
    steps:
      - name: Determine if tests should run
        id: check
        run: |
          # For PRs, always run tests
          if [ "${{ github.event_name }}" == "pull_request" ]; then
            echo "should_test=true" >> $GITHUB_OUTPUT
            echo "should_bump=false" >> $GITHUB_OUTPUT
            echo "PR detected - will run tests"
            exit 0
          fi
          
          # For workflow_dispatch, always run tests
          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
            echo "should_test=true" >> $GITHUB_OUTPUT
            echo "should_bump=false" >> $GITHUB_OUTPUT
            echo "Manual trigger - will run tests"
            exit 0
          fi
          
          # For push events, check if it's a PR merge
          COMMIT_MSG="${{ github.event.head_commit.message }}"
          
          # PR merges have messages like "Merge pull request #123" or contain (#123)
          if echo "$COMMIT_MSG" | grep -qE "^Merge pull request #|^.*\(#[0-9]+\)$"; then
            echo "should_test=false" >> $GITHUB_OUTPUT
            echo "should_bump=true" >> $GITHUB_OUTPUT
            echo "PR merge detected - skipping tests, will bump version"
          # Skip version bump commits
          elif echo "$COMMIT_MSG" | grep -qE "^\[skip ci\]|chore: bump version"; then
            echo "should_test=false" >> $GITHUB_OUTPUT
            echo "should_bump=false" >> $GITHUB_OUTPUT
            echo "Version bump commit - skipping everything"
          else
            echo "should_test=true" >> $GITHUB_OUTPUT
            echo "should_bump=true" >> $GITHUB_OUTPUT
            echo "Direct push detected - will run tests and bump version"
          fi

  test-openagent:
    name: Test OpenAgent
    runs-on: ubuntu-latest
    needs: check-trigger
    if: needs.check-trigger.outputs.should_test == 'true'
    timeout-minutes: 15
    
    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'
      
      # Install the OpenCode CLI (from opencode.ai, NOT our install.sh)
      # Our install.sh only installs agents/commands/tools, not the CLI binary
      # The @opencode-ai/sdk spawns `opencode serve` internally, so CLI is required
      - name: Install OpenCode CLI
        run: |
          npm install -g opencode-ai
          which opencode
          opencode --version
      
      # Install our OpenAgents components (agents, commands, tools)
      - name: Install OpenAgents Components
        run: bash install.sh essential --install-dir .opencode
      
      - name: Install dependencies
        working-directory: evals/framework
        run: npm install
      
      - name: Build framework
        working-directory: evals/framework
        run: 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
    needs: check-trigger
    if: needs.check-trigger.outputs.should_test == 'true'
    timeout-minutes: 15
    
    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'
      
      # Install the OpenCode CLI (from opencode.ai, NOT our install.sh)
      # Our install.sh only installs agents/commands/tools, not the CLI binary
      # The @opencode-ai/sdk spawns `opencode serve` internally, so CLI is required
      - name: Install OpenCode CLI
        run: |
          npm install -g opencode-ai
          which opencode
          opencode --version
      
      # Install our OpenAgents components (agents, commands, tools)
      - name: Install OpenAgents Components
        run: bash install.sh essential --install-dir .opencode
      
      - name: Install dependencies
        working-directory: evals/framework
        run: npm install
      
      - name: Build framework
        working-directory: evals/framework
        run: 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: [check-trigger, test-openagent, test-opencoder]
    if: always() && needs.check-trigger.outputs.should_test == 'true'
    
    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

  auto-version-bump:
    name: Auto Version Bump
    runs-on: ubuntu-latest
    needs: [check-trigger, test-openagent, test-opencoder]
    # Run version bump if:
    # 1. Tests ran and passed, OR
    # 2. This is a PR merge (tests already passed on PR)
    if: |
      github.event_name == 'push' && 
      github.ref == 'refs/heads/main' &&
      needs.check-trigger.outputs.should_bump == 'true' &&
      (needs.check-trigger.outputs.should_test == 'false' || 
       (needs.test-openagent.result == 'success' && needs.test-opencoder.result == 'success'))
    permissions:
      contents: write
    
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          token: ${{ secrets.GITHUB_TOKEN }}
      
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'
      
      - name: Configure Git
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
      
      - name: Determine version bump type
        id: bump-type
        run: |
          # Get the last commit message
          COMMIT_MSG=$(git log -1 --pretty=%B)
          
          # Determine bump type from commit message
          if echo "$COMMIT_MSG" | grep -qiE "^(feat|feature)\(.*\)!:|^BREAKING CHANGE:|^[a-z]+!:"; then
            echo "type=major" >> $GITHUB_OUTPUT
            echo "Detected BREAKING CHANGE - bumping major version"
          elif echo "$COMMIT_MSG" | grep -qiE "^(feat|feature)(\(.*\))?:"; then
            echo "type=minor" >> $GITHUB_OUTPUT
            echo "Detected feature - bumping minor version"
          elif echo "$COMMIT_MSG" | grep -qiE "^(fix|bugfix)(\(.*\))?:"; then
            echo "type=patch" >> $GITHUB_OUTPUT
            echo "Detected fix - bumping patch version"
          elif echo "$COMMIT_MSG" | grep -qiE "^\[alpha\]"; then
            echo "type=alpha" >> $GITHUB_OUTPUT
            echo "Detected [alpha] tag - bumping alpha version"
          elif echo "$COMMIT_MSG" | grep -qiE "^\[beta\]"; then
            echo "type=beta" >> $GITHUB_OUTPUT
            echo "Detected [beta] tag - bumping beta version"
          elif echo "$COMMIT_MSG" | grep -qiE "^\[rc\]"; then
            echo "type=rc" >> $GITHUB_OUTPUT
            echo "Detected [rc] tag - bumping rc version"
          else
            echo "type=patch" >> $GITHUB_OUTPUT
            echo "No specific type detected - defaulting to patch version bump"
          fi
      
      - name: Bump version
        run: |
          BUMP_TYPE="${{ steps.bump-type.outputs.type }}"
          
          # Get current version
          CURRENT_VERSION=$(cat VERSION)
          echo "Current version: $CURRENT_VERSION"
          
          # Bump version in package.json
          npm run version:bump:$BUMP_TYPE
          
          # Get new version
          NEW_VERSION=$(cat VERSION)
          echo "New version: $NEW_VERSION"
          
          # Update CHANGELOG.md
          DATE=$(date +%Y-%m-%d)
          COMMIT_MSG=$(git log -1 --pretty=%B)
          
          # Create changelog entry
          cat > /tmp/changelog_entry.md << EOF
          ## [$NEW_VERSION] - $DATE
          
          ### Changes
          - $COMMIT_MSG
          
          EOF
          
          # Prepend to CHANGELOG.md (after the header)
          if [ -f CHANGELOG.md ]; then
            # Insert after the first occurrence of "## ["
            awk '/^## \[/ && !found {print; system("cat /tmp/changelog_entry.md"); found=1; next} 1' CHANGELOG.md > /tmp/changelog_new.md
            mv /tmp/changelog_new.md CHANGELOG.md
          fi
      
      - name: Commit version bump
        run: |
          NEW_VERSION=$(cat VERSION)
          
          git add VERSION package.json CHANGELOG.md
          git commit -m "chore: bump version to v$NEW_VERSION [skip ci]"
          git tag "v$NEW_VERSION"
      
      - name: Push changes
        run: |
          git push origin main --tags
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
      
      - name: Create GitHub Release
        run: |
          NEW_VERSION=$(cat VERSION)
          
          # Extract changelog entry for this version
          RELEASE_NOTES=$(awk '/^## \['"$NEW_VERSION"'\]/{flag=1; next} /^## \[/{flag=0} flag' CHANGELOG.md)
          
          # If no specific notes found, use commit message
          if [ -z "$RELEASE_NOTES" ]; then
            RELEASE_NOTES="Release v$NEW_VERSION"
          fi
          
          # Create the release
          gh release create "v$NEW_VERSION" \
            --title "v$NEW_VERSION" \
            --notes "$RELEASE_NOTES" \
            --latest
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}