feat(benchmarks): add deterministic Sentry evaluation #35
Workflow file for this run
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: decisiongrounding CI | |
| # The decisiongrounding benchmark arrived from its standalone repository with | |
| # its workflow at decisiongrounding/.github/workflows/ci.yml — a path GitHub | |
| # does not read in a subdirectory. This root workflow re-homes those same jobs | |
| # (test matrix, offline demo smoke, live AsDecided arm smoke, corpus gate) | |
| # scoped to the subdirectory. | |
| on: | |
| push: | |
| branches: [main] | |
| paths: ["decisiongrounding/**", ".github/scripts/install-asdecided.sh"] | |
| pull_request: | |
| paths: ["decisiongrounding/**", ".github/scripts/install-asdecided.sh"] | |
| permissions: | |
| contents: read | |
| defaults: | |
| run: | |
| working-directory: decisiongrounding | |
| jobs: | |
| test: | |
| name: test (py${{ matrix.python-version }}) | |
| runs-on: ubuntu-latest | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| python-version: ["3.11", "3.12", "3.13"] | |
| steps: | |
| - uses: actions/checkout@v5 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| cache: pip | |
| - name: Install (dev + schema extras) | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -e ".[dev,schema]" | |
| - name: Run tests | |
| run: python -m pytest -q | |
| - name: Smoke the offline demo | |
| run: python -m runner.cli demo | |
| asdecided-core: | |
| # Exercise the actual Rust system-under-test boundary and enforce the | |
| # benchmark's own knowledge corpus. | |
| name: AsDecided Core integration | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v5 | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| - name: Install AsDecided | |
| run: bash ../.github/scripts/install-asdecided.sh 0.23.1 | |
| - name: Install benchmark | |
| run: pip install -e ".[dev,schema]" | |
| - name: Smoke the AsDecided whole-artifact arm | |
| run: python -m runner.cli run --arm rac --scenarios scenarios --out /tmp/dg-core-smoke | |
| - name: Smoke the AsDecided snippet arm | |
| run: python -m runner.cli run --arm rac_snippets --scenarios scenarios --out /tmp/dg-core-snippets-smoke | |
| - name: Gate the RAC corpus (validate + relationships + review) | |
| run: decided gate rac |