Add ops-log skill and move logs out of gitignored path (#5039) #6979
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: Marin - Integration Test | |
| on: | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| workflow_dispatch: | |
| jobs: | |
| marin-itest: | |
| if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name == github.repository | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 45 | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| cancel-in-progress: true | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v5 | |
| - name: Set up Python 3.12 | |
| uses: actions/setup-python@v6 | |
| with: | |
| python-version: "3.12" | |
| - name: Set up Node.js | |
| uses: actions/setup-node@v4 | |
| with: | |
| node-version: "22" | |
| - name: Install uv | |
| uses: astral-sh/setup-uv@v7 | |
| with: | |
| enable-cache: true | |
| - name: Install dependencies | |
| # `--no-default-groups` keeps uv from also installing every workspace package's | |
| # dev/docs/test groups (e.g. `levanter[docs,test,dev]`), which saves multiple | |
| # minutes and avoids re-downloading CUDA wheels unnecessarily on cold caches. | |
| run: uv sync --all-packages --extra=cpu --extra=dedup --no-default-groups --group dev | |
| - name: Check df -h | |
| run: df -h | |
| - name: Start local Iris cluster | |
| run: | | |
| uv run iris --config lib/iris/examples/test.yaml \ | |
| cluster start --local > /tmp/iris-cluster.log 2>&1 & | |
| CLUSTER_PID=$! | |
| echo "CLUSTER_PID=$CLUSTER_PID" >> "$GITHUB_ENV" | |
| # Wait for controller to print its URL | |
| for i in $(seq 1 120); do | |
| if grep -q "Controller started at" /tmp/iris-cluster.log 2>/dev/null; then | |
| URL=$(grep "Controller started at" /tmp/iris-cluster.log | head -1 | sed -n 's/.*Controller started at //p') | |
| echo "IRIS_CONTROLLER_URL=$URL" >> "$GITHUB_ENV" | |
| echo "Cluster ready at $URL" | |
| break | |
| fi | |
| sleep 1 | |
| done | |
| if [ -z "${URL:-}" ]; then | |
| echo "Cluster failed to start within timeout" | |
| cat /tmp/iris-cluster.log | |
| exit 1 | |
| fi | |
| - name: Run iris integration tests | |
| run: | | |
| uv run pytest tests/integration/iris/ \ | |
| --controller-url "$IRIS_CONTROLLER_URL" \ | |
| -v -s --log-cli-level=INFO --tb=short --timeout=600 \ | |
| -o "addopts=" \ | |
| -x | |
| env: | |
| WANDB_MODE: disabled | |
| WANDB_API_KEY: "" | |
| JAX_TRACEBACK_FILTERING: off | |
| - name: Run full marin integration pipeline | |
| run: | | |
| timeout 600 uv run pytest tests/test_integration_test.py \ | |
| -m integration -o "addopts=" --timeout=600 -v -s | |
| env: | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| WANDB_MODE: disabled | |
| WANDB_API_KEY: "" | |
| JAX_TRACEBACK_FILTERING: off | |
| - name: Stop cluster | |
| if: always() | |
| run: kill $CLUSTER_PID 2>/dev/null || true | |
| - name: Show cluster logs on failure | |
| if: failure() | |
| run: cat /tmp/iris-cluster.log || true |