feat: add functional test framework for agent pipelines #21
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: Functional Tests | |
| on: | |
| push: | |
| branches: [main] | |
| paths: | |
| - 'eval/**' | |
| - 'internal/scaffold/**' | |
| pull_request: | |
| branches: [main] | |
| paths: | |
| - 'eval/**' | |
| - 'internal/scaffold/**' | |
| workflow_dispatch: | |
| permissions: | |
| contents: read | |
| id-token: write | |
| concurrency: | |
| group: functional-tests-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| functional-tests: | |
| runs-on: ubuntu-latest | |
| environment: functional-tests | |
| timeout-minutes: 45 | |
| steps: | |
| - uses: actions/checkout@v6.0.2 | |
| with: | |
| submodules: true | |
| - uses: actions/setup-go@v5 | |
| with: | |
| go-version-file: go.mod | |
| - uses: actions/setup-python@v6.2.0 | |
| with: | |
| python-version: "3.12" | |
| - name: Install uv | |
| uses: astral-sh/setup-uv@v7.6.0 | |
| - name: Install agent-eval-harness | |
| # Installs from the git submodule checked out above (submodules: true) | |
| run: uv pip install --system -e 'eval/.agent-eval-harness[anthropic]' | |
| - name: Install yq | |
| run: | | |
| curl -sSfL "https://github.com/mikefarah/yq/releases/download/v4.47.1/yq_linux_amd64" -o /usr/local/bin/yq | |
| chmod +x /usr/local/bin/yq | |
| - name: Configure git identity | |
| run: | | |
| git config --global user.name "fullsend-eval[bot]" | |
| git config --global user.email "fullsend-eval[bot]@users.noreply.github.com" | |
| - name: Build fullsend | |
| run: make go-build | |
| - name: Add bin to PATH | |
| run: echo "${{ github.workspace }}/bin" >> "$GITHUB_PATH" | |
| - name: Install OpenShell CLI | |
| run: .github/scripts/install-openshell.sh | |
| - name: Configure OpenShell gateway | |
| run: | | |
| mkdir -p $HOME/.config/openshell/ | |
| cat > $HOME/.config/openshell/gateway.env << EOF | |
| OPENSHELL_BIND_ADDRESS=0.0.0.0 | |
| EOF | |
| - name: Install Podman | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y podman | |
| - name: Configure rootless Podman | |
| run: | | |
| whoami_user="$(whoami)" | |
| grep -q "^${whoami_user}:" /etc/subuid || sudo usermod --add-subuids 100000-165535 --add-subgids 100000-165535 "${whoami_user}" | |
| podman system migrate | |
| systemctl --user start podman.socket | |
| - name: Install validation dependencies | |
| run: pip install --quiet "jsonschema>=4.18.0" | |
| - name: Authenticate to GCP | |
| uses: google-github-actions/auth@v2 | |
| with: | |
| workload_identity_provider: ${{ secrets.E2E_GCP_WIF_PROVIDER }} | |
| service_account: ${{ secrets.E2E_GCP_SERVICE_ACCOUNT }} | |
| - name: Prepare sandbox credentials | |
| run: | | |
| echo "HOST_GOOGLE_APPLICATION_CREDENTIALS=$GOOGLE_APPLICATION_CREDENTIALS" >> "$GITHUB_ENV" | |
| bash internal/scaffold/fullsend-repo/scripts/prepare-sandbox-credentials.sh | |
| - name: Run functional tests | |
| env: | |
| EVAL_ORG: ${{ vars.EVAL_ORG }} | |
| GH_TOKEN: ${{ secrets.EVAL_GH_TOKEN }} | |
| ANTHROPIC_VERTEX_PROJECT_ID: ${{ vars.EVALS_VERTEX_PROJECT_ID }} | |
| GOOGLE_CLOUD_PROJECT: ${{ secrets.E2E_GCP_PROJECT_ID }} | |
| CLOUD_ML_REGION: ${{ vars.EVALS_GCP_REGION }} | |
| EVALS_HOST_CREDENTIALS: ${{ env.HOST_GOOGLE_APPLICATION_CREDENTIALS }} | |
| run: make functional-tests | |
| - name: Scrub secrets from eval results | |
| if: always() | |
| run: | | |
| for dir in eval/runs/ /tmp/agent-eval/; do | |
| find "$dir" -name '.eval-env' -delete 2>/dev/null || true | |
| find "$dir" -name 'fixture-state.json' -delete 2>/dev/null || true | |
| find "$dir" -name '*.jsonl' -delete 2>/dev/null || true | |
| done | |
| - name: Upload eval results | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: eval-results | |
| path: | | |
| eval/runs/ | |
| !eval/runs/**/.eval-env | |
| !eval/runs/**/fixture-state.json | |
| !eval/runs/**/*.jsonl | |
| retention-days: 30 |