test_evaluation.yml

name: ACE Benchmark Evaluation Test
on: [push]

jobs:
  test:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: ['3.10']

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

      - name: Debug directory structure
        run: |
          echo "Current directory: $(pwd)"
          ls -la

      - name: Setup Python
        uses: actions/setup-python@v4
        with:
          python-version: ${{ matrix.python-version }}

      - name: Install dependencies
        run: |
          pip install --upgrade pip
          pip install pytest pytest-asyncio pytest-mock
          pip install agentscope ray

      - name: Run tests
        env:
          PYTHONPATH: ${{ env.GITHUB_WORKSPACE }}/evaluation/ace_bench
          DASHSCOPE_API_KEY: ${{ secrets.DASHSCOPE_API_KEY }}
        run: |
          python -m pytest tests/evaluation_test.py -v