203-cycle grounded evolution run: score ceiling 39.0, self-tuning mut… #20
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: Validate | ||
| on: | ||
| push: | ||
| branches: [main] | ||
| pull_request: | ||
| branches: [main] | ||
| concurrency: | ||
| group: ${{ github.workflow }}-${{ github.ref }} | ||
| cancel-in-progress: true | ||
| jobs: | ||
| lint: | ||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: "3.12" | ||
| - run: pip install ruff | ||
| - run: ruff check . --ignore=E501,F821 --statistics | ||
| imports: | ||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: "3.12" | ||
| - run: pip install openai | ||
| - name: Check all modules load | ||
| run: | | ||
| for mod in generator population_manager mutation_engine; do | ||
| echo "=== $mod ===" | ||
| python -c "import $mod; print('OK')" | ||
| done | ||
| for mod in evaluator.runtime_evaluator; do | ||
| echo "=== $mod ===" | ||
| python -c "import $mod; print('OK')" | ||
| done | ||
| - name: Check scripts parse (no-exec) | ||
| run: | | ||
| for script in infinite_research_loop.py run_experiment.py beautify_readme.py \ | ||
| eval.py auto_evolve.py; do | ||
| echo "=== $script ===" | ||
| python -c "compile(open('$script').read(), '$script', 'exec'); print('syntax OK')" | ||
| done | ||
| experiment_design: | ||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: "3.12" | ||
| - name: Validate benchmarks/tasks.json | ||
| run: | | ||
| python3 -c " | ||
| import json | ||
| with open('benchmarks/tasks.json') as f: | ||
| tasks = json.load(f) | ||
| assert len(tasks) >= 3 | ||
| for t in tasks: | ||
| assert 'name' in t | ||
| assert 'hidden_test_files' in t | ||
| assert len(t['hidden_test_files']) >= 1 | ||
| print(f'{len(tasks)} benchmarks OK') | ||
| " | ||
