chore: include missing gradle-wrapper.jar for clean repo backup #2
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: AI Quality Gate | |
| on: | |
| pull_request: | |
| branches: [main] | |
| push: | |
| branches: [main] | |
| jobs: | |
| benchmark: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Setup Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| - name: Install backend dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -r backend/requirements.txt | |
| - name: Run benchmark report | |
| run: | | |
| PYTHONPATH=backend python backend/scripts/benchmark_runner.py \ | |
| --scenarios backend/eval/golden_scenarios.jsonl \ | |
| --output backend/eval/ci_benchmark_report.json \ | |
| --min-syncable 0.60 \ | |
| --min-gherkin 0.80 \ | |
| --min-citation 0.00 \ | |
| --min-quality 65 \ | |
| --min-execution 65 | |
| - name: Upload benchmark artifact | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: ai-quality-benchmark | |
| path: backend/eval/ci_benchmark_report.json | |
| strict-quality-gate: | |
| if: ${{ vars.ENABLE_STRICT_AI_GATE == 'true' }} | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Setup Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| - name: Install backend dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -r backend/requirements.txt | |
| - name: Run strict quality gate | |
| env: | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| SERPAPI_API_KEY: ${{ secrets.SERPAPI_API_KEY }} | |
| run: | | |
| PYTHONPATH=backend python backend/scripts/benchmark_runner.py \ | |
| --scenarios backend/eval/golden_scenarios.jsonl \ | |
| --output backend/eval/strict_benchmark_report.json \ | |
| --min-syncable 0.70 \ | |
| --min-gherkin 0.90 \ | |
| --min-citation 0.85 \ | |
| --min-quality 75 \ | |
| --min-execution 75 |