feat: add functional test framework for agent pipelines #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: 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-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| functional-tests: | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 45 | |
| steps: | |
| - uses: actions/checkout@v6.0.2 | |
| with: | |
| submodules: true | |
| - uses: actions/setup-go@v5 | |
| with: | |
| go-version-file: go.mod | |
| - uses: actions/setup-python@v6.2.0 | |
| with: | |
| python-version: "3.12" | |
| - name: Install uv | |
| uses: astral-sh/setup-uv@v7.6.0 | |
| - name: Install agent-eval-harness | |
| # Installs from the git submodule checked out above (submodules: true) | |
| run: uv pip install --system -e 'eval/.agent-eval-harness[anthropic]' | |
| - name: Install yq | |
| run: | | |
| curl -sSfL "https://github.com/mikefarah/yq/releases/download/v4.47.1/yq_linux_amd64" -o /usr/local/bin/yq | |
| chmod +x /usr/local/bin/yq | |
| - name: Configure git identity | |
| run: | | |
| git config --global user.name "fullsend-eval[bot]" | |
| git config --global user.email "fullsend-eval[bot]@users.noreply.github.com" | |
| - name: Build fullsend | |
| run: make go-build | |
| - name: Add bin to PATH | |
| run: echo "${{ github.workspace }}/bin" >> "$GITHUB_PATH" | |
| # TODO: The openshell setup below (version, CLI, gateway, Podman, | |
| # gateway start) is duplicated from action.yml. Extract into a | |
| # shared script (e.g. .github/scripts/setup-openshell.sh) so the | |
| # version and config stay in sync across both places. | |
| - name: Set OpenShell version | |
| run: echo "OPENSHELL_VERSION=0.0.38" >> "${GITHUB_ENV}" | |
| - name: Install OpenShell CLI | |
| run: | | |
| uv tool install "openshell==${OPENSHELL_VERSION}" | |
| openshell --version | |
| - name: Download openshell-gateway | |
| run: | | |
| set -euo pipefail | |
| arch="$(uname -m)" | |
| case "${arch}" in | |
| x86_64) ;; | |
| aarch64|arm64) arch=aarch64 ;; | |
| *) echo "::error::Unsupported architecture: ${arch}"; exit 1 ;; | |
| esac | |
| GATEWAY_ASSET="openshell-gateway-${arch}-unknown-linux-gnu.tar.gz" | |
| GATEWAY_URL="https://github.com/NVIDIA/OpenShell/releases/download/v${OPENSHELL_VERSION}/${GATEWAY_ASSET}" | |
| curl -fsSL "${GATEWAY_URL}" -o "/tmp/${GATEWAY_ASSET}" | |
| tar xzf "/tmp/${GATEWAY_ASSET}" -C "${{ runner.temp }}" | |
| rm -f "/tmp/${GATEWAY_ASSET}" | |
| - name: Install Podman | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y podman | |
| - name: Configure rootless Podman | |
| run: | | |
| whoami_user="$(whoami)" | |
| grep -q "^${whoami_user}:" /etc/subuid || sudo usermod --add-subuids 100000-165535 --add-subgids 100000-165535 "${whoami_user}" | |
| podman system migrate | |
| - name: Start Podman API service | |
| run: | | |
| SOCKET_PATH="${XDG_RUNTIME_DIR:-/run/user/$(id -u)}/podman/podman.sock" | |
| if [ ! -S "${SOCKET_PATH}" ]; then | |
| mkdir -p "$(dirname "${SOCKET_PATH}")" | |
| podman system service --time=0 "unix://${SOCKET_PATH}" & | |
| for _i in $(seq 1 30); do | |
| [ -S "${SOCKET_PATH}" ] && podman --url "unix://${SOCKET_PATH}" info >/dev/null 2>&1 && break | |
| sleep 1 | |
| done | |
| [ -S "${SOCKET_PATH}" ] || { echo "::error::Podman socket not ready"; exit 1; } | |
| fi | |
| - name: Start openshell-gateway | |
| run: | | |
| set -euo pipefail | |
| OPENSHELL_SSH_HANDSHAKE_SECRET="ci-$(openssl rand -hex 16)" | |
| export OPENSHELL_SSH_HANDSHAKE_SECRET | |
| echo "::add-mask::${OPENSHELL_SSH_HANDSHAKE_SECRET}" | |
| export OPENSHELL_SUPERVISOR_IMAGE="ghcr.io/nvidia/openshell/supervisor:dfd47683e7da4f1a4a8fa5d77f92d3696e6a41f9" | |
| "${{ runner.temp }}/openshell-gateway" \ | |
| --bind-address 0.0.0.0 \ | |
| --health-port 8081 \ | |
| --drivers podman \ | |
| --disable-tls \ | |
| --db-url "sqlite:/tmp/gateway.db?mode=rwc" \ | |
| >/tmp/gateway.log 2>&1 & | |
| for _i in $(seq 1 30); do | |
| curl -sf http://127.0.0.1:8081/healthz >/dev/null 2>&1 && break | |
| sleep 2 | |
| done | |
| curl -sf http://127.0.0.1:8081/healthz >/dev/null 2>&1 || { | |
| echo "::error::Gateway health check failed" | |
| cat /tmp/gateway.log 2>/dev/null || true | |
| exit 1 | |
| } | |
| openshell gateway add http://127.0.0.1:8080 --local --name local | |
| openshell gateway select local | |
| - 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: find eval/runs/ -name '.eval-env' -delete 2>/dev/null || true; find /tmp/agent-eval/ -name '.eval-env' -delete 2>/dev/null || true | |
| - name: Upload eval results | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: eval-results | |
| path: | | |
| eval/runs/ | |
| !eval/runs/**/.eval-env | |
| retention-days: 30 |