Add competitive eval harness with measured scorecards #5
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: Benchmark Suite | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: [main] | |
| paths: | |
| - "eval/benchmark-suite.json" | |
| - "eval/ground-truth/**" | |
| - "scripts/run-benchmark-suite.ps1" | |
| - ".github/workflows/benchmark-suite.yml" | |
| pull_request: | |
| branches: [main] | |
| paths: | |
| - "scripts/run-benchmark-suite.ps1" | |
| - "scripts/export-benchmark-diffs.ps1" | |
| - "scripts/score-competitive-benchmark.py" | |
| - "eval/competitor-scope.json" | |
| - "scripts/enrich-benchmark-sonarcloud.py" | |
| - "scripts/enrich-benchmark-semgrep.py" | |
| - "scripts/benchmark_lib.py" | |
| - "eval/ground-truth/**" | |
| jobs: | |
| benchmark-suite: | |
| runs-on: windows-latest | |
| steps: | |
| - uses: actions/checkout@v6 | |
| - uses: actions/setup-dotnet@v5 | |
| with: | |
| dotnet-version: 8.0.x | |
| - name: Export diffs | |
| shell: pwsh | |
| env: | |
| GH_TOKEN: ${{ github.token }} | |
| run: ./scripts/export-benchmark-diffs.ps1 -CiOnly | |
| - name: Run CI fixtures | |
| shell: pwsh | |
| env: | |
| GH_TOKEN: ${{ github.token }} | |
| run: | | |
| ./scripts/run-benchmark-suite.ps1 -CiOnly | |
| python scripts/score-competitive-benchmark.py --all-with-ground-truth --check | |
| - name: Scorecard check | |
| shell: pwsh | |
| run: python scripts/score-competitive-benchmark.py --fixture stackexchange-redis-pr-2995 --check | |