Run Evals #12
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: Run Evals | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| suite_filter: | |
| description: "Space-separated glob patterns for eval files to run" | |
| required: false | |
| default: "evals/**/eval.yaml examples/features/agent-skills-evals/multi-provider-skill-trigger.EVAL.yaml" | |
| target: | |
| description: "Target name from .agentv/targets.yaml" | |
| required: false | |
| default: "copilot-cli" | |
| threshold: | |
| description: "Minimum score threshold (0-1)" | |
| required: false | |
| default: "0.8" | |
| jobs: | |
| evals: | |
| name: Run AgentV Evals | |
| runs-on: ubuntu-latest | |
| permissions: | |
| contents: read | |
| checks: write | |
| models: read | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: ./.github/actions/setup-bun | |
| - name: Build | |
| run: bun run build | |
| - name: Install GitHub Copilot CLI | |
| run: curl -fsSL https://gh.io/copilot-install | bash | |
| - name: Configure credentials | |
| run: | | |
| cat > .env <<EOF | |
| GH_MODELS_TOKEN=${{ secrets.COPILOT_PAT || secrets.GH_MODELS_TOKEN || secrets.GITHUB_TOKEN }} | |
| GH_MODELS_MODEL=${{ vars.GH_MODELS_MODEL || 'gpt-5-mini' }} | |
| COPILOT_MODEL=${{ vars.COPILOT_MODEL || 'gpt-5-mini' }} | |
| EOF | |
| - name: Resolve inputs | |
| id: filter | |
| env: | |
| DEFAULT_PATTERNS: "evals/**/eval.yaml examples/features/agent-skills-evals/multi-provider-skill-trigger.EVAL.yaml" | |
| run: | | |
| echo "patterns=${{ github.event.inputs.suite_filter || vars.EVAL_PATTERNS || env.DEFAULT_PATTERNS }}" >> "$GITHUB_OUTPUT" | |
| echo "target=${{ github.event.inputs.target || vars.EVAL_TARGET || 'copilot-cli' }}" >> "$GITHUB_OUTPUT" | |
| echo "threshold=${{ github.event.inputs.threshold || '0.8' }}" >> "$GITHUB_OUTPUT" | |
| - name: Run AgentV evals | |
| id: run-evals | |
| env: | |
| COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_PAT }} | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| run: | | |
| mkdir -p .agentv/ci-results | |
| # shellcheck disable=SC2086 | |
| bun apps/cli/dist/cli.js eval run ${{ steps.filter.outputs.patterns }} \ | |
| --targets .agentv/targets.yaml \ | |
| --target ${{ steps.filter.outputs.target }} \ | |
| --workers 1 \ | |
| --threshold ${{ steps.filter.outputs.threshold }} \ | |
| -o .agentv/ci-results/junit.xml \ | |
| --benchmark-json .agentv/ci-results/benchmark.json \ | |
| --artifacts .agentv/ci-results/artifacts \ | |
| --verbose \ | |
| 2>&1 | tee .agentv/ci-results/eval-output.log | |
| echo "exit_code=${PIPESTATUS[0]}" >> "$GITHUB_OUTPUT" | |
| - name: Publish JUnit test results | |
| if: always() | |
| uses: dorny/test-reporter@v1 | |
| with: | |
| name: AgentV Eval Results | |
| path: .agentv/ci-results/junit.xml | |
| reporter: java-junit | |
| fail-on-error: false | |
| - name: Upload eval artifacts | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: eval-results-${{ github.run_id }} | |
| path: .agentv/ci-results/ | |
| retention-days: 30 | |
| - name: Fail if threshold not met | |
| if: always() | |
| run: | | |
| if [ "${{ steps.run-evals.outputs.exit_code }}" != "0" ]; then | |
| echo "::error::Eval score below threshold (${{ steps.filter.outputs.threshold }})" | |
| exit 1 | |
| fi |