rebase upstream Jul 31

.github/workflows/claude.yml

@@ -0,0 +1,64 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+      actions: read # Required for Claude to read CI results on PRs
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+          
+          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
+          # model: "claude-opus-4-20250514"
+
+          # Optional: Customize the trigger phrase (default: @claude)
+          # trigger_phrase: "/claude"
+
+          # Optional: Trigger when specific user is assigned to an issue
+          # assignee_trigger: "claude-bot"
+
+          # Optional: Allow Claude to run specific commands
+          # allowed_tools: "Bash(npm install),Bash(npm run build),Bash(npm run test:*),Bash(npm run lint:*)"
+
+          # Optional: Add custom instructions for Claude to customize its behavior for your project
+          # custom_instructions: |
+          #   Follow our coding standards
+          #   Ensure all new code has tests
+          #   Use TypeScript for new files
+
+          # Optional: Custom environment variables for Claude
+          # claude_env: |
+          #   NODE_ENV: test
+

.github/workflows/python-test.yml

@@ -1,29 +1,96 @@
-name: Python Unit Tests
+name: Tests
 
 on: [push, pull_request]
 
 jobs:
-  test:
+  unit-tests:
     runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Cache pip packages
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
 
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Run unit tests
+        env:
+          OPENAI_API_KEY: test  # Mock API key for unit tests
+        run: |
+          # Run unit tests (all tests except integration/)
+          python -m unittest discover -s tests -p "test_*.py" -v
+
+  integration-tests:
+    needs: unit-tests  # Only run if unit tests pass
+    runs-on: ubuntu-latest
+    timeout-minutes: 30  # Limit integration tests to 30 minutes
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v3
-
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.9'
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install -e .
-        # Install test dependencies
-        pip install pytest numpy
-
-    - name: Run unit tests
-      env:
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-        python -m unittest discover -s tests -p "test_*.py" -v
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Cache pip packages
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+          pip install optillm
+
+      - name: Start optillm server
+        run: |
+          echo "Starting optillm server for integration tests..."
+          OPTILLM_API_KEY=optillm HF_TOKEN=${{ secrets.HF_TOKEN }} optillm --model google/gemma-3-270m-it --port 8000 &
+          echo $! > server.pid
+
+          # Wait for server to be ready
+          echo "Waiting for server to start..."
+          sleep 15
+
+          # Test server health
+          curl -s http://localhost:8000/health || echo "Server health check failed"
+        env:
+          OPTILLM_API_KEY: optillm
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+
+      - name: Run integration tests (excluding slow tests)
+        env:
+          OPENAI_API_KEY: optillm
+          OPTILLM_API_KEY: optillm
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          # Run only fast integration tests, skip slow tests that require real LLM
+          pytest tests/integration -v --tb=short -m "not slow"
+
+      - name: Stop optillm server
+        if: always()
+        run: |
+          if [ -f server.pid ]; then
+            kill $(cat server.pid) || true
+            rm server.pid
+          fi
+          pkill -f "optillm.*8000" || true

.github/workflows/release.yml

@@ -29,45 +29,30 @@ jobs:
         uses: pypa/gh-action-pypi-publish@release/v1
 
   docker-publish:
-    name: Publish Docker image
-    runs-on: ubuntu-22.04
+    name: Build and publish Docker image
+    runs-on: ubuntu-latest
     needs: pypi-publish
     permissions:
       contents: read
       packages: write
     steps:
-      - uses: actions/checkout@v4
-
-      # Add aggressive cleanup before any Docker operations
-      - name: Free disk space
-        run: |
-          # Clean Docker
-          docker system prune -af
-          docker image prune -af
-          docker builder prune -af
-
-          df -h
-
+      - name: Checkout
+        uses: actions/checkout@v4
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
-
+        
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-        with:
-          driver-opts: |
-            image=moby/buildkit:buildx-stable-1
-            network=host
-          buildkitd-flags: --debug
-
+
       - name: Log in to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
-      # Extract metadata for Docker image
-      - name: Extract metadata for Docker
+
+      - name: Extract metadata
         id: meta
         uses: docker/metadata-action@v5
         with:
@@ -76,46 +61,23 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
             type=raw,value=latest
-
-      # Build and push Docker image for AMD64
-      - name: Build and push Docker image AMD64
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: Dockerfile
-          push: true
-          platforms: linux/amd64
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=gha,scope=openevolve-amd64
-          cache-to: type=gha,scope=openevolve-amd64,mode=max
-          outputs: type=registry,compression=zstd,compression-level=5
-
-      # Cleanup after AMD64 build
-      - name: Cleanup after AMD64 build
-        run: |
-          docker system prune -af
-          docker builder prune -af
-          df -h
-
-      # Build and push Docker image for ARM64
-      - name: Build and push Docker image ARM64
+          labels: |
+            org.opencontainers.image.title=OpenEvolve
+            org.opencontainers.image.description=Open-source evolutionary coding agent
+            org.opencontainers.image.vendor=OpenEvolve
+            org.opencontainers.image.source=https://github.com/${{ github.repository }}
+            org.opencontainers.image.documentation=https://github.com/${{ github.repository }}#readme
+            org.opencontainers.image.licenses=Apache-2.0
+
+      - name: Build and push multi-platform Docker image
         uses: docker/build-push-action@v5
         with:
           context: .
-          file: Dockerfile
+          platforms: linux/amd64,linux/arm64
           push: true
-          platforms: linux/arm64
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=gha,scope=openevolve-arm64
-          cache-to: type=gha,scope=openevolve-arm64,mode=max
-          outputs: type=registry,compression=zstd,compression-level=5
-
-      # Final cleanup
-      - name: Final cleanup
-        run: |
-          docker system prune -af
-          docker builder prune -af
-          find /tmp -type f -user $(id -u) -exec rm -f {} + 2>/dev/null || true
-          df -h
+          cache-from: type=gha,scope=openevolve-multiarch
+          cache-to: type=gha,scope=openevolve-multiarch,mode=max
+          provenance: mode=max
+          sbom: true