[CLI][Doc] feat/add vllm-sr eval command for router /api/v1/eval prompt checks #928
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: Integration Test [Memory] | |
| description: Integration tests for memory features with Milvus storage backend | |
| on: | |
| pull_request: | |
| branches: | |
| - main | |
| paths: | |
| - 'src/semantic-router/pkg/memory/**' | |
| - 'src/semantic-router/pkg/extproc/*memory*' | |
| - 'src/semantic-router/pkg/responseapi/**' | |
| - 'src/vllm-sr/**' | |
| - 'src/vllm-sr/Dockerfile*' | |
| - 'tools/make/docker.mk' | |
| - 'tools/make/milvus.mk' | |
| - 'e2e/testing/09-memory-features-test.py' | |
| - 'e2e/testing/run_memory_integration.sh' | |
| - 'e2e/testing/llm-katan/**' | |
| - 'e2e/config/config.memory*.yaml' | |
| - '.github/workflows/integration-test-memory.yml' | |
| workflow_dispatch: | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| memory-integration-test: | |
| name: Memory Integration Test | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 60 | |
| steps: | |
| - name: Check out the repo | |
| uses: actions/checkout@v4 | |
| # NOTE: Model storage setup skipped - using echo backend for memory tests | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| # Free up disk space for large Docker build (CUDA + PyTorch dependencies) | |
| - name: Free disk space | |
| run: | | |
| echo "=== Disk space before cleanup ===" | |
| df -h / | |
| # Remove unnecessary tools and libraries | |
| sudo rm -rf /usr/share/dotnet | |
| sudo rm -rf /usr/local/lib/android | |
| sudo rm -rf /opt/ghc | |
| sudo rm -rf /opt/hostedtoolcache/CodeQL | |
| # Clean apt cache | |
| sudo apt-get clean | |
| # Clean Docker (unused images, containers, volumes) | |
| docker system prune -af --volumes || true | |
| echo "=== Disk space after cleanup ===" | |
| df -h / | |
| - name: Pre-pull Milvus image | |
| run: docker pull milvusdb/milvus:v2.3.3 | |
| - name: Run memory integration tests | |
| run: | | |
| make memory-test-integration DOCKER_TAG=ci VLLM_SR_IMAGE=vllm-sr:ci | |
| - name: Collect logs | |
| if: always() | |
| run: | | |
| mkdir -p logs | |
| # Runtime logs (split topology first, legacy single-container fallback second) | |
| docker logs vllm-sr-router-container 2>&1 > logs/router.log || \ | |
| docker exec vllm-sr-container cat /var/log/supervisor/router.log 2>&1 > logs/router.log || true | |
| docker logs vllm-sr-envoy-container 2>&1 > logs/envoy.log || true | |
| docker logs vllm-sr-dashboard-container 2>&1 > logs/dashboard.log || true | |
| docker logs vllm-sr-container 2>&1 > logs/vllm-sr-container.log || true | |
| # llm-katan logs | |
| docker logs llm-katan 2>&1 > logs/llm-katan.log || true | |
| # Milvus logs | |
| docker logs milvus-semantic-cache 2>&1 > logs/milvus.log || true | |
| # Container status | |
| docker ps -a > logs/docker-status.txt || true | |
| - name: Upload logs as artifact | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: memory-test-logs | |
| path: logs/ | |
| retention-days: 7 | |
| - name: Clean up | |
| if: always() | |
| run: | | |
| vllm-sr stop || true | |
| docker stop llm-katan vllm-sr-container vllm-sr-router-container vllm-sr-envoy-container vllm-sr-dashboard-container 2>/dev/null || true | |
| docker rm llm-katan vllm-sr-container vllm-sr-router-container vllm-sr-envoy-container vllm-sr-dashboard-container 2>/dev/null || true | |
| make stop-milvus || true |