Add the agent eval harness pitstop was missing #23
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CI | |
| on: | |
| push: | |
| branches: [main] | |
| pull_request: | |
| jobs: | |
| test: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| python-version: ["3.10", "3.12"] | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - run: python -m pip install --upgrade pip | |
| - run: pip install -e ".[dev]" | |
| - run: pytest -q | |
| mcp-import: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| - run: pip install -e ".[mcp]" | |
| - run: python -c "import pitstop.mcp_server; print('mcp server imports OK')" | |
| build: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| - run: pip install build | |
| - run: python -m build | |
| # Offline half of the eval suite: the eval files match the shipped parser, so a | |
| # recipe or task can never name a command the CLI cannot run. The live half | |
| # needs MIMIT and Overpass and runs in the weekly canary instead. | |
| agent-evals: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| - run: pip install -e . | |
| - run: scripts/run-agent-evals.sh | |
| env: | |
| PITSTOP_EVAL_BIN: pitstop | |
| PITSTOP_EVAL_OFFLINE: "1" |