refactor(repos): extract per-repo install logic into internal/repos package #1589
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 | |
| # PR-triggered functional tests use pull_request_target so fork PRs receive | |
| # secrets. Authorization runs in a separate gate job (base checkout only) | |
| # before the test job checks out the PR head — same pattern as e2e.yml. | |
| permissions: {} | |
| on: | |
| push: | |
| branches: [main] | |
| # SYNC-WITH: grep regex in "Check for functional-test-relevant changes" step | |
| paths: | |
| - 'eval/**' | |
| - 'internal/scaffold/**' | |
| - '.github/workflows/functional-tests.yml' | |
| - '.github/scripts/**' | |
| pull_request_target: | |
| types: [opened, synchronize, reopened, labeled] | |
| merge_group: | |
| workflow_dispatch: | |
| concurrency: | |
| group: >- | |
| ${{ github.event_name == 'pull_request_target' | |
| && format('functional-{0}', github.event.pull_request.number) | |
| || format('{0}-{1}', github.workflow, github.ref) }} | |
| cancel-in-progress: >- | |
| ${{ github.event_name == 'pull_request_target' | |
| || github.ref != 'refs/heads/main' }} | |
| jobs: | |
| gate: | |
| # Separate job so pull-requests: write stays out of the job that checks | |
| # out fork head and runs tests with secrets. | |
| # Never checkout github.event.pull_request.head.sha here. | |
| if: >- | |
| github.event_name == 'pull_request_target' && | |
| (github.event.action != 'labeled' || github.event.label.name == 'ok-to-test') | |
| runs-on: ubuntu-24.04 | |
| timeout-minutes: 5 | |
| permissions: | |
| contents: read | |
| pull-requests: write | |
| outputs: | |
| authorized: ${{ steps.auth.outputs.authorized }} | |
| steps: | |
| - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 | |
| with: | |
| ref: ${{ github.sha }} # Base branch only — never checkout PR head in gate | |
| - name: Check PR authorization | |
| id: auth | |
| uses: ./.github/actions/check-e2e-authorization | |
| with: | |
| pr_number: ${{ github.event.pull_request.number }} | |
| repository: ${{ github.repository }} | |
| pr_updated_at: ${{ github.event.pull_request.updated_at }} | |
| event_action: ${{ github.event.action }} | |
| pr_author_association: ${{ github.event.pull_request.author_association }} | |
| pr_author_login: ${{ github.event.pull_request.user.login }} | |
| functional-tests: | |
| # For pull_request_target, runs only when gate sets authorized=true. | |
| # Do not treat a skipped gate as authorized. | |
| # This job checks out untrusted PR head code — no pull-requests: write here. | |
| needs: gate | |
| if: >- | |
| !cancelled() && | |
| (github.event_name != 'pull_request_target' || needs.gate.outputs.authorized == 'true') | |
| runs-on: ubuntu-24.04 | |
| timeout-minutes: 45 | |
| permissions: | |
| contents: read | |
| id-token: write | |
| steps: | |
| - name: Check for functional-test-relevant changes | |
| id: changes | |
| if: github.event_name == 'pull_request_target' || github.event_name == 'merge_group' | |
| env: | |
| GH_TOKEN: ${{ github.token }} | |
| EVENT_NAME: ${{ github.event_name }} | |
| PR_NUMBER: ${{ github.event.pull_request.number }} | |
| REPO: ${{ github.repository }} | |
| MERGE_GROUP_BASE: ${{ github.event.merge_group.base_sha }} | |
| MERGE_GROUP_HEAD: ${{ github.event.merge_group.head_sha }} | |
| # SYNC-WITH: push.paths filter above | |
| run: | | |
| if [ "$EVENT_NAME" = "merge_group" ]; then | |
| FILES=$(gh api "repos/${REPO}/compare/${MERGE_GROUP_BASE}...${MERGE_GROUP_HEAD}" --jq '.files[].filename') || { | |
| echo "::warning::Failed to fetch merge group files — running functional tests as a precaution" | |
| echo "relevant=true" >> "$GITHUB_OUTPUT" | |
| exit 0 | |
| } | |
| FILE_COUNT=$(echo "$FILES" | wc -l) | |
| if [ "$FILE_COUNT" -ge 300 ]; then | |
| echo "::warning::Compare API returned $FILE_COUNT files (possible truncation at 300) — running functional tests as a precaution" | |
| echo "relevant=true" >> "$GITHUB_OUTPUT" | |
| exit 0 | |
| fi | |
| else | |
| FILES=$(gh api "repos/${REPO}/pulls/${PR_NUMBER}/files" --paginate --jq '.[].filename') || { | |
| echo "::warning::Failed to fetch PR files — running functional tests as a precaution" | |
| echo "relevant=true" >> "$GITHUB_OUTPUT" | |
| exit 0 | |
| } | |
| fi | |
| if echo "$FILES" | grep -qE '^eval/|^internal/scaffold/|^\.github/workflows/functional-tests\.yml$|^\.github/scripts/'; then | |
| echo "relevant=true" >> "$GITHUB_OUTPUT" | |
| else | |
| echo "::notice::No functional-test-relevant files changed — skipping tests" | |
| echo "relevant=false" >> "$GITHUB_OUTPUT" | |
| fi | |
| - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 | |
| if: steps.changes.outputs.relevant != 'false' | |
| with: | |
| ref: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.head.sha || github.sha }} | |
| persist-credentials: false | |
| # checkout@v7 blocks fork PR head checkouts on pull_request_target by default. | |
| # Safe here: gate job authorizes before this job runs; no pull-requests: write. | |
| allow-unsafe-pr-checkout: ${{ github.event_name == 'pull_request_target' }} | |
| submodules: true | |
| - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0 | |
| if: steps.changes.outputs.relevant != 'false' | |
| with: | |
| go-version-file: go.mod | |
| - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 | |
| if: steps.changes.outputs.relevant != 'false' | |
| with: | |
| python-version: "3.12" | |
| - name: Install uv | |
| if: steps.changes.outputs.relevant != 'false' | |
| uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0 | |
| - name: Install agent-eval-harness | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: uv pip install --system -e 'eval/.agent-eval-harness[anthropic]' | |
| - name: Install yq | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: | | |
| curl -sSfL "https://github.com/mikefarah/yq/releases/download/v4.47.1/yq_linux_amd64" -o /usr/local/bin/yq | |
| chmod +x /usr/local/bin/yq | |
| - name: Configure git identity | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: | | |
| git config --global user.name "fullsend-eval[bot]" | |
| git config --global user.email "fullsend-eval[bot]@users.noreply.github.com" | |
| - name: Build fullsend | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: make go-build | |
| - name: Add bin to PATH | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: echo "${{ github.workspace }}/bin" >> "$GITHUB_PATH" | |
| - name: Configure OpenShell gateway | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: | | |
| source .github/scripts/openshell-version.sh | |
| mkdir -p "$HOME/.config/openshell" | |
| echo "OPENSHELL_BIND_ADDRESS=0.0.0.0" > "$HOME/.config/openshell/gateway.env" | |
| cat > "$HOME/.config/openshell/gateway.toml" << EOF | |
| [openshell] | |
| version = 1 | |
| [openshell.gateway] | |
| supervisor_image = "ghcr.io/nvidia/openshell/supervisor:${OPENSHELL_VERSION}" | |
| EOF | |
| - name: Install OpenShell CLI | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: .github/scripts/install-openshell.sh | |
| - name: Install Podman | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y podman | |
| - name: Configure rootless Podman | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: | | |
| whoami_user="$(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 | |
| if: steps.changes.outputs.relevant != 'false' | |
| 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: Install validation dependencies | |
| if: steps.changes.outputs.relevant != 'false' | |
| run: pip install --quiet "jsonschema>=4.18.0" | |
| - name: Check for secrets | |
| if: steps.changes.outputs.relevant != 'false' | |
| id: secrets-check | |
| run: | | |
| if [ -z "$WIF_PROVIDER" ]; then | |
| echo "::warning::GCP secrets are not configured. Skipping functional tests." | |
| echo "available=false" >> "$GITHUB_OUTPUT" | |
| else | |
| echo "available=true" >> "$GITHUB_OUTPUT" | |
| fi | |
| env: | |
| WIF_PROVIDER: ${{ secrets.E2E_GCP_WIF_PROVIDER }} | |
| - name: Authenticate to GCP | |
| if: steps.changes.outputs.relevant != 'false' && steps.secrets-check.outputs.available == 'true' | |
| uses: google-github-actions/auth@7c6bc770dae815cd3e89ee6cdf493a5fab2cc093 # v3.0.0 | |
| with: | |
| workload_identity_provider: ${{ secrets.E2E_GCP_WIF_PROVIDER }} | |
| service_account: ${{ secrets.E2E_GCP_SERVICE_ACCOUNT }} | |
| - name: Prepare sandbox credentials | |
| if: steps.changes.outputs.relevant != 'false' && steps.secrets-check.outputs.available == 'true' | |
| run: | | |
| echo "HOST_GOOGLE_APPLICATION_CREDENTIALS=$GOOGLE_APPLICATION_CREDENTIALS" >> "$GITHUB_ENV" | |
| bash internal/scaffold/fullsend-repo/scripts/prepare-sandbox-credentials.sh | |
| - name: Run functional tests | |
| if: steps.changes.outputs.relevant != 'false' && steps.secrets-check.outputs.available == 'true' | |
| 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() && steps.changes.outputs.relevant != 'false' && steps.secrets-check.outputs.available == 'true' | |
| 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() && steps.changes.outputs.relevant != 'false' && steps.secrets-check.outputs.available == 'true' | |
| uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 | |
| with: | |
| name: eval-results | |
| path: | | |
| eval/runs/ | |
| !eval/runs/**/.eval-env | |
| retention-days: 30 |