refactor: update the dockerfile and handler

Signed-off-by: pandyamarut <[email protected]>

Author: pandyamarut

Dockerfile-runtime-two renamed to Dockerfile-load-balancer-sls

@@ -1,4 +1,4 @@
-# Runtime Two Dockerfile - Dual-capability serverless runtime
+# Load Balancer SLS Dockerfile - Dual-capability serverless runtime
 # Supports both remote execution and HTTP endpoints
 
 # Use Python 3.11 base image with CUDA support
@@ -28,7 +28,7 @@ RUN uv sync --frozen
 # Set Python path
 ENV PYTHONPATH="/app/src:$PYTHONPATH"
 
-# Environment variables for Runtime Two
+# Environment variables for Load Balancer SLS
 ENV RUNTIME_MODE="dual"
 ENV ENABLE_HTTP_SERVER="true"
 ENV ENABLE_REMOTE_EXECUTION="true"
@@ -42,4 +42,4 @@ HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
     CMD curl -f http://localhost:8000/health || exit 1
 
 # Default command - can run in both serverless and HTTP modes
-CMD ["uv", "run", "python", "src/runtime_two_handler.py"]
+CMD ["uv", "run", "python", "src/load_balancer_sls_handler.py"]

Makefile

@@ -1,9 +1,9 @@
 IMAGE = runpod/tetra-rp
-RUNTIME_TWO_IMAGE = mwiki/worker-tetra-runtime-two
+LOAD_BALANCER_SLS_IMAGE = mwiki/worker-tetra-load-balancer-sls
 TAG = local
 FULL_IMAGE = $(IMAGE):$(TAG)
 FULL_IMAGE_CPU = $(IMAGE)-cpu:$(TAG)
-FULL_IMAGE_RUNTIME_TWO = $(RUNTIME_TWO_IMAGE):$(TAG)
+FULL_IMAGE_LOAD_BALANCER_SLS = $(LOAD_BALANCER_SLS_IMAGE):$(TAG)
 
 .PHONY: setup help
 
@@ -36,10 +36,10 @@ setup: dev # Initialize project, sync deps, update submodules
 	git submodule update --remote --merge
 	cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
 
-build: # Build all Docker images (GPU, CPU, Runtime Two)
+build: # Build all Docker images (GPU, CPU, Load Balancer SLS)
 	make build-gpu
 	make build-cpu
-	make build-runtime-two
+	make build-load-balancer-sls
 
 build-gpu: setup # Build GPU Docker image (linux/amd64)
 	docker buildx build \
@@ -54,11 +54,11 @@ build-cpu: setup # Build CPU-only Docker image (linux/amd64)
 	-t $(FULL_IMAGE_CPU) \
 	. --load
 
-build-runtime-two: setup # Build Runtime Two dual-capability image (linux/amd64)
+build-load-balancer-sls: setup # Build Load Balancer SLS dual-capability image (linux/amd64)
 	docker buildx build \
 	--platform linux/amd64 \
-	-f Dockerfile-runtime-two \
-	-t $(FULL_IMAGE_RUNTIME_TWO) \
+	-f Dockerfile-load-balancer-sls \
+	-t $(FULL_IMAGE_LOAD_BALANCER_SLS) \
 	. --load
 
 # Test commands
@@ -80,8 +80,8 @@ test-fast: # Run tests with fast-fail mode
 test-handler: # Test handler locally with all test_*.json files
 	cd src && ./test-handler.sh
 
-test-runtime-two: build-runtime-two # Test Runtime Two container locally
-	docker run --rm -p 8000:8000 $(FULL_IMAGE_RUNTIME_TWO)
+test-load-balancer-sls: build-load-balancer-sls # Test Load Balancer SLS container locally
+	docker run --rm -p 8000:8000 $(FULL_IMAGE_LOAD_BALANCER_SLS)
 
 # Smoke Tests (local on Mac OS)
 

pyproject.toml

@@ -9,14 +9,11 @@ dependencies = [
     "pydantic>=2.11.4",
     "requests>=2.25.0",
     "runpod",
-<<<<<<< HEAD
     "fastapi>=0.104.0",
     "uvicorn[standard]>=0.24.0",
     "aiohttp>=3.9.0",
-=======
     "hf_transfer>=0.1.0",
     "huggingface_hub>=0.32.0",
->>>>>>> main
 ]
 
 [dependency-groups]

src/runtime_two_handler.py renamed to src/load_balancer_sls_handler.py

@@ -1,7 +1,7 @@
 """
-Runtime Two Handler - Dual-capability serverless runtime
+Load Balancer SLS Handler - Dual-capability serverless runtime
 
-This module implements the main server for Runtime Two that supports both:
+This module implements the main server for Load Balancer SLS that supports both:
 1. Traditional remote execution (via RemoteExecutor)
 2. HTTP endpoint exposure (via FastAPI)
 """
@@ -23,23 +23,23 @@
 log = logging.getLogger(__name__)
 
 
-class RuntimeTwoServer:
+class LoadBalancerSlsServer:
     """
-    Runtime Two server that provides dual execution capabilities:
+    Load Balancer SLS server that provides dual execution capabilities:
     - Remote execution for programmatic calls
     - HTTP endpoints for decorated methods
     """
 
     def __init__(self):
         self.remote_executor = RemoteExecutor()
         self.class_registry = ClassRegistry()
-        self.app = FastAPI(title="Runtime Two Server", version="1.0.0")
+        self.app = FastAPI(title="Load Balancer SLS Server", version="1.0.0")
         self.port = int(os.environ.get("PORT", 8000))
 
         # Setup routes
         self._setup_routes()
 
-        log.info("Runtime Two server initialized")
+        log.info("Load Balancer SLS server initialized")
 
     def _setup_routes(self):
         """Setup FastAPI routes for HTTP endpoints."""
@@ -49,7 +49,7 @@ def _setup_routes(self):
         async def health_check():
             return {
                 "status": "healthy",
-                "runtime": "two",
+                "runtime": "load_balancer_sls",
                 "capabilities": ["remote_execution", "http_endpoints"],
             }
 
@@ -113,7 +113,8 @@ async def remote_execution(request: Request):
             except Exception as e:
                 log.error(f"Remote execution error: {e}")
                 error_response = FunctionResponse(
-                    success=False, error=f"Runtime Two remote execution error: {str(e)}"
+                    success=False,
+                    error=f"Load Balancer SLS remote execution error: {str(e)}",
                 )
                 return error_response.model_dump()
 
@@ -241,8 +242,8 @@ async def _install_dependencies(self, request: FunctionRequest) -> FunctionRespo
         )
 
     async def start_server(self):
-        """Start the Runtime Two server."""
-        log.info(f"Starting Runtime Two server on port {self.port}")
+        """Start the Load Balancer SLS server."""
+        log.info(f"Starting Load Balancer SLS server on port {self.port}")
 
         # Run FastAPI with uvicorn
         config = uvicorn.Config(
@@ -253,18 +254,18 @@ async def start_server(self):
 
 
 # Singleton server instance
-_server_instance: Optional[RuntimeTwoServer] = None
+_server_instance: Optional[LoadBalancerSlsServer] = None
 
 
-def get_server() -> RuntimeTwoServer:
-    """Get or create the Runtime Two server instance."""
+def get_server() -> LoadBalancerSlsServer:
+    """Get or create the Load Balancer SLS server instance."""
     global _server_instance
     if _server_instance is None:
-        _server_instance = RuntimeTwoServer()
+        _server_instance = LoadBalancerSlsServer()
     return _server_instance
 
 
-# Runtime Two runs as pure FastAPI server - no traditional handler function needed
+# Load Balancer SLS runs as pure FastAPI server - no traditional handler function needed
 
 
 # For standalone HTTP server mode
@@ -277,4 +278,4 @@ def get_server() -> RuntimeTwoServer:
         server = get_server()
         asyncio.run(server.start_server())
     else:
-        log.info("Runtime Two handler ready for serverless execution")
+        log.info("Load Balancer SLS handler ready for serverless execution")