ollama37/.github/workflows/build-test.yml

name: Build and Test

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

env:
  TESTLINK_URL: http://localhost:8090
  TESTLINK_PROJECT_ID: "1"
  OLLAMA_HOST: http://localhost:11434

jobs:
  build:
    name: Build Verification
    runs-on: self-hosted

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

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Install test runner dependencies
        run: cd tests && npm ci

      - name: Run build tests
        id: build-tests
        run: |
          cd tests
          npm run dev -- run --suite build --no-llm --output json > /tmp/build-results.json 2>&1 || true
          cat /tmp/build-results.json

          # Check if any tests failed
          if grep -q '"passed": false' /tmp/build-results.json; then
            echo "Some build tests failed"
            exit 1
          fi

      - name: Upload build results
        uses: actions/upload-artifact@v4
        if: always()
        with:
          name: build-test-results
          path: /tmp/build-results.json

  runtime:
    name: Container & Runtime Tests
    runs-on: self-hosted
    needs: build

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

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Install test runner dependencies
        run: cd tests && npm ci

      - name: Start container
        run: |
          cd docker
          docker compose down 2>/dev/null || true
          docker compose up -d
          sleep 10

      - name: Run runtime tests
        id: runtime-tests
        run: |
          cd tests
          npm run dev -- run --suite runtime --no-llm --output json > /tmp/runtime-results.json 2>&1 || true
          cat /tmp/runtime-results.json

      - name: Upload runtime results
        uses: actions/upload-artifact@v4
        if: always()
        with:
          name: runtime-test-results
          path: /tmp/runtime-results.json

  inference:
    name: Inference Tests
    runs-on: self-hosted
    needs: runtime

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

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Install test runner dependencies
        run: cd tests && npm ci

      - name: Run inference tests
        id: inference-tests
        run: |
          cd tests
          npm run dev -- run --suite inference --no-llm --output json > /tmp/inference-results.json 2>&1 || true
          cat /tmp/inference-results.json

      - name: Upload inference results
        uses: actions/upload-artifact@v4
        if: always()
        with:
          name: inference-test-results
          path: /tmp/inference-results.json

  llm-judge:
    name: LLM Judge Evaluation
    runs-on: self-hosted
    needs: [build, runtime, inference]
    if: always()

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

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Install test runner dependencies
        run: cd tests && npm ci

      - name: Download all test results
        uses: actions/download-artifact@v4
        with:
          path: /tmp/results

      - name: Run LLM judge on all results
        run: |
          cd tests
          echo "Running LLM judge evaluation..."

          # Re-run all tests with LLM judge using local Ollama
          npm run dev -- run --output json > /tmp/llm-judged-results.json 2>&1 || true
          cat /tmp/llm-judged-results.json

      - name: Upload final results
        uses: actions/upload-artifact@v4
        if: always()
        with:
          name: llm-judged-results
          path: /tmp/llm-judged-results.json

  cleanup:
    name: Cleanup & Summary
    runs-on: self-hosted
    needs: [build, runtime, inference, llm-judge]
    if: always()

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

      - name: Stop Container
        run: |
          cd docker
          docker compose down || true
          echo "Container stopped"

      - name: Summary
        run: |
          echo "## Build and Test Summary" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "| Stage | Status |" >> $GITHUB_STEP_SUMMARY
          echo "|-------|--------|" >> $GITHUB_STEP_SUMMARY
          echo "| Build Verification | ${{ needs.build.result }} |" >> $GITHUB_STEP_SUMMARY
          echo "| Container & Runtime | ${{ needs.runtime.result }} |" >> $GITHUB_STEP_SUMMARY
          echo "| Inference Tests | ${{ needs.inference.result }} |" >> $GITHUB_STEP_SUMMARY
          echo "| LLM Judge Evaluation | ${{ needs.llm-judge.result }} |" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "Commit: ${{ github.sha }}" >> $GITHUB_STEP_SUMMARY