fix: add runtime version banner, log after unpack for accuracy

.github/workflows/ci.yml

@@ -27,8 +27,6 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
@@ -75,38 +73,13 @@ jobs:
   docker-test:
     runs-on: ubuntu-latest
     if: github.event_name != 'pull_request' || github.head_ref != 'release-please--branches--main'
-    needs: [lint]
     steps:
-      - name: Clear Space
-        # Note: Manual cleanup sufficient for CPU images (python:3.12-slim base ~150MB)
-        # Only CUDA images need aggressive cleanup due to their ~10-15GB size
-        run: |
-          rm -rf /usr/share/dotnet
-          rm -rf /opt/ghc
-          rm -rf "/usr/local/share/boost"
-          rm -rf "$AGENT_TOOLSDIRECTORY"
-          docker system prune -af
-          df -h
-
       - name: Checkout repository
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Set up uv
-        uses: astral-sh/setup-uv@v4
-        with:
-          enable-cache: true
-
-      - name: Setup dependencies
-        run: uv sync
-
       - name: Build CPU Docker image
         uses: docker/build-push-action@v6
         with:
@@ -124,92 +97,16 @@ jobs:
           echo "Testing CPU handler in Docker environment..."
           docker run --rm flash-cpu:test ./test-handler.sh
 
-  docker-test-lb:
-    runs-on: ubuntu-latest
-    if: github.event_name != 'pull_request' || github.head_ref != 'release-please--branches--main'
-    needs: [lint]
-    steps:
-      - name: Free Disk Space
-        uses: jlumbroso/free-disk-space@v1.3.1
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Additional cleanup and report
-        run: |
-          docker system prune -af
-          df -h
-
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Set up uv
-        uses: astral-sh/setup-uv@v4
-        with:
-          enable-cache: true
-
-      - name: Setup dependencies
-        run: uv sync
-
-      - name: Build Load Balancer Docker image
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: ./Dockerfile-lb
-          platforms: linux/amd64
-          push: false
-          tags: flash-lb:test
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-          load: true
-
   docker-test-lb-cpu:
     runs-on: ubuntu-latest
     if: github.event_name != 'pull_request' || github.head_ref != 'release-please--branches--main'
-    needs: [lint]
     steps:
-      - name: Clear Space
-        # Note: Manual cleanup sufficient for CPU images (python:3.12-slim base ~150MB)
-        # Only CUDA images need aggressive cleanup due to their ~10-15GB size
-        run: |
-          rm -rf /usr/share/dotnet
-          rm -rf /opt/ghc
-          rm -rf "/usr/local/share/boost"
-          rm -rf "$AGENT_TOOLSDIRECTORY"
-          docker system prune -af
-          df -h
-
       - name: Checkout repository
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Set up uv
-        uses: astral-sh/setup-uv@v4
-        with:
-          enable-cache: true
-
-      - name: Setup dependencies
-        run: uv sync
-
       - name: Build CPU Load Balancer Docker image
         uses: docker/build-push-action@v6
         with:
@@ -222,14 +119,19 @@ jobs:
           cache-to: type=gha,mode=max
           load: true
 
+      - name: Test LB handler execution in Docker environment
+        run: |
+          echo "Testing LB handler in Docker environment..."
+          docker run --rm flash-lb-cpu:test ./test-lb-handler.sh
+
   docker-validation:
     runs-on: ubuntu-latest
-    needs: [test, lint, docker-test, docker-test-lb, docker-test-lb-cpu]
+    needs: [test, lint, docker-test, docker-test-lb-cpu]
     if: always()
     steps:
       - name: Check all jobs succeeded
         run: |
-          results=("${{ needs.test.result }}" "${{ needs.lint.result }}" "${{ needs.docker-test.result }}" "${{ needs.docker-test-lb.result }}" "${{ needs.docker-test-lb-cpu.result }}")
+          results=("${{ needs.test.result }}" "${{ needs.lint.result }}" "${{ needs.docker-test.result }}" "${{ needs.docker-test-lb-cpu.result }}")
           for result in "${results[@]}"; do
             if [[ "$result" != "success" && "$result" != "skipped" ]]; then
               echo "One or more quality checks failed (got: $result)"
@@ -262,18 +164,9 @@ jobs:
     needs: [release]
     if: needs.release.outputs.release_created
     steps:
-      - name: Free Disk Space
-        uses: jlumbroso/free-disk-space@v1.3.1
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Additional cleanup and report
+      - name: Clear Space
         run: |
+          rm -rf /usr/share/dotnet /opt/ghc /usr/local/share/boost "$AGENT_TOOLSDIRECTORY"
           docker system prune -af
           df -h
 
@@ -394,18 +287,9 @@ jobs:
     needs: [release]
     if: needs.release.outputs.release_created
     steps:
-      - name: Free Disk Space
-        uses: jlumbroso/free-disk-space@v1.3.1
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Additional cleanup and report
+      - name: Clear Space
         run: |
+          rm -rf /usr/share/dotnet /opt/ghc /usr/local/share/boost "$AGENT_TOOLSDIRECTORY"
           docker system prune -af
           df -h
 
@@ -463,18 +347,9 @@ jobs:
     needs: [release]
     if: needs.release.outputs.release_created
     steps:
-      - name: Free Disk Space
-        uses: jlumbroso/free-disk-space@v1.3.1
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Additional cleanup and report
+      - name: Clear Space
         run: |
+          rm -rf /usr/share/dotnet /opt/ghc /usr/local/share/boost "$AGENT_TOOLSDIRECTORY"
           docker system prune -af
           df -h
 

release-please-config.json

@@ -14,7 +14,7 @@
         {"type": "chore", "section": "Miscellaneous", "hidden": true}
       ],
       "extra-files": [
-        "src/__init__.py"
+        "src/version.py"
       ]
     }
   },

src/handler.py

@@ -6,15 +6,19 @@
 
 from logger import setup_logging
 from unpack_volume import maybe_unpack
+from version import format_version_banner
 
 # Initialize logging configuration
 setup_logging()
 
+logger = logging.getLogger(__name__)
+
 # Unpack Flash deployment artifacts if running in Flash mode
 # This is a no-op for Live Serverless and local development
 maybe_unpack()
 
-logger = logging.getLogger(__name__)
+# Log after unpack so bundled runpod_flash is on sys.path
+logger.info(format_version_banner())
 
 
 def _load_generated_handler() -> Optional[Any]:
@@ -62,7 +66,7 @@ def _load_generated_handler() -> Optional[Any]:
     except ImportError as e:
         logger.warning(
             "Generated handler %s failed to import (missing dependency: %s). "
-            "Deploy with --use-local-flash to include latest runpod_flash. "
+            "Redeploy to include latest runpod_flash. "
             "Falling back to FunctionRequest handler.",
             handler_file,
             e,

src/lb_handler.py

@@ -29,6 +29,7 @@
 
 from logger import setup_logging
 from unpack_volume import maybe_unpack
+from version import format_version_banner
 
 # Initialize logging configuration
 setup_logging()
@@ -38,6 +39,9 @@
 # This is a no-op for Live Serverless and local development
 maybe_unpack()
 
+# Log after unpack so bundled runpod_flash is on sys.path
+logger.info(format_version_banner())
+
 # Import from bundled /app/runpod_flash (no system package)
 # These imports must happen AFTER maybe_unpack() so /app is in sys.path
 from runpod_flash.protos.remote_execution import FunctionRequest, FunctionResponse  # noqa: E402

src/test-lb-handler.sh

@@ -24,14 +24,20 @@ trap cleanup EXIT
 
 # Start FastAPI server in background
 echo "Starting FastAPI server on port $PORT..."
-PYTHONPATH=. uv run python3 -m uvicorn lb_handler:app --host $HOST --port $PORT --log-level error > /tmp/lb_handler.log 2>&1 &
+if [ -f /.dockerenv ]; then
+    # Docker: use system python with pre-installed packages
+    PYTHONPATH=. python3 -m uvicorn lb_handler:app --host $HOST --port $PORT --log-level error > /tmp/lb_handler.log 2>&1 &
+else
+    # Local: use uv run to manage dependencies
+    PYTHONPATH=. uv run python3 -m uvicorn lb_handler:app --host $HOST --port $PORT --log-level error > /tmp/lb_handler.log 2>&1 &
+fi
 SERVER_PID=$!
 
 # Wait for server to be ready
 echo "Waiting for server to be ready..."
 attempt=0
 while [ $attempt -lt $TEST_TIMEOUT ]; do
-    if curl -s -f "http://$HOST:$PORT/health" > /dev/null 2>&1; then
+    if curl -s -f "http://$HOST:$PORT/ping" > /dev/null 2>&1; then
         echo "✓ Server is ready"
         break
     fi
@@ -46,10 +52,10 @@ while [ $attempt -lt $TEST_TIMEOUT ]; do
     fi
 done
 
-# Test /health endpoint
+# Test /ping endpoint
 echo ""
-echo "Testing /health endpoint..."
-health_response=$(curl -s "http://$HOST:$PORT/health")
+echo "Testing /ping endpoint..."
+health_response=$(curl -s "http://$HOST:$PORT/ping")
 echo "Response: $health_response"
 
 # Run /execute tests

src/version.py

@@ -0,0 +1,38 @@
+"""Version utilities for flash-worker boot logging."""
+
+from importlib.metadata import PackageNotFoundError, version
+
+__version__ = "1.1.0"  # x-release-please-version
+
+
+def _get_version(package_name: str) -> str:
+    try:
+        return version(package_name)
+    except PackageNotFoundError:
+        return "unknown"
+
+
+def get_worker_version() -> str:
+    return __version__
+
+
+def get_flash_version() -> str:
+    """Read bundled flash version, falling back to pip metadata."""
+    try:
+        from runpod_flash import __version__ as flash_ver
+
+        return str(flash_ver)
+    except (ImportError, AttributeError):
+        return _get_version("runpod-flash")
+
+
+def get_runpod_version() -> str:
+    return _get_version("runpod")
+
+
+def format_version_banner() -> str:
+    return (
+        f"Starting Flash Worker {get_worker_version()} | "
+        f"runpod-flash {get_flash_version()} | "
+        f"runpod {get_runpod_version()}"
+    )

tests/unit/test_lb_handler.py

@@ -14,10 +14,14 @@
 
 
 # Mock heavy dependencies before importing lb_handler to prevent side effects
+_mock_version = MagicMock()
+_mock_version.format_version_banner = MagicMock(return_value="Starting Flash Worker vtest")
+
 _MOCK_MODULES = {
     "logger": MagicMock(),
     "unpack_volume": MagicMock(),
     "remote_executor": MagicMock(),
+    "version": _mock_version,
     "runpod_flash": MagicMock(),
     "runpod_flash.protos": MagicMock(),
     "runpod_flash.protos.remote_execution": MagicMock(),