Run with entrypoint script instead of executing module inside a package

Modules inside packages should not be invoked directly.

Author: samdoran

Makefile

@@ -20,7 +20,7 @@ CONTAINER_RUNTIME ?= $(shell command -v podman 2>/dev/null || command -v docker
 .PHONY: run run-stack build-llama-stack-image remove-llama-stack-container stop-llama-stack-container start-llama-stack-container wait-for-llama-stack-health clean-llama-stack
 
 run-stack: ## Run lightspeed-stack directly, without building dependent service/s
-	uv run src/lightspeed_stack.py -c $(CONFIG)
+	uv run lightspeed_stack -c $(CONFIG)
 
 run: start-llama-stack-container ## Run the service locally with dependent services
 	@echo "Starting Lightspeed Core Stack..."

deploy/lightspeed-stack/Containerfile

@@ -135,7 +135,7 @@ ENV PYTHONPATH="/app-root"
 
 # Run the application
 EXPOSE 8080
-ENTRYPOINT ["python3.12", "src/lightspeed_stack.py"]
+ENTRYPOINT ["lightspeed-stack"]
 
 LABEL vendor="Red Hat, Inc." \
     name="lightspeed-core/lightspeed-stack-rhel9" \

tests/e2e-prow/rhoai/manifests/lightspeed/lightspeed-stack.yaml

@@ -37,7 +37,7 @@ spec:
               key: key
               optional: true
       image: ${LIGHTSPEED_STACK_IMAGE}
-      command: ["/bin/sh", "-c", "mkdir -p /tmp/data && exec python3.12 src/lightspeed_stack.py"]
+      command: ["/bin/sh", "-c", "mkdir -p /tmp/data && exec lightspeed_stack"]
       ports:
         - containerPort: 8080
       # TCP probes avoid HTTP/auth. LCS + Llama handshake and large images can take 60–120s before :8080 listens;