Fix runtime gateway configuration for sub-mode agents

config/settings.py

@@ -20,8 +20,8 @@ class Settings(BaseSettings):
     NAMESPACE_PREFIX: str = "agnet"
 
     # Model gateways
-    HEICODE_NEWAPI_BASE_URL: str = "https://code.xinghanlab.com"
-    LITELLM_BASE_URL: str = "http://litellm-service:8000"
+    HEICODE_NEWAPI_BASE_URL: str = "https://code.xinghanlab.com/v1"
+    LITELLM_BASE_URL: str = "https://code.xinghanlab.com/v1"
 
     # Limits
     MAX_PAYLOAD_SIZE_MB: int = 1

k8s/agent-manager-configmap.yaml

@@ -9,8 +9,8 @@ data:
 
   # Heicode sub-mode runtime integration
   REDIS_URL: "redis://localhost:6379/0"
-  HEICODE_NEWAPI_BASE_URL: "https://code.xinghanlab.com"
-  LITELLM_BASE_URL: "http://litellm-service:8000"
+  HEICODE_NEWAPI_BASE_URL: "https://code.xinghanlab.com/v1"
+  LITELLM_BASE_URL: "https://code.xinghanlab.com/v1"
   NAMESPACE_PREFIX: "agent"
   MAX_CONCURRENT_DEPLOYMENTS_PER_USER: "10"
   MAX_CONCURRENT_DEPLOYMENTS_PER_SCOPE: "50"

k8s/agent-manager-deployment.yaml

@@ -31,7 +31,7 @@ spec:
       
       containers:
       - name: agent-manager
-        image: agnettaiji.azurecr.io/ai-agents/agent-manager:heicode-v2-20260529232620
+        image: agnettaiji.azurecr.io/ai-agents/agent-manager:heicode-v2-runtime-20260601195848-arm64
         imagePullPolicy: Always
         
         ports:

k8s/deployment-with-kubeconfig.yaml

@@ -22,7 +22,7 @@ spec:
         - name: acr-secret
       containers:
         - name: agent-manager
-          image: agnettaiji.azurecr.io/agent-manager:latest
+          image: agnettaiji.azurecr.io/ai-agents/agent-manager:heicode-v2-runtime-20260601195848-arm64
           imagePullPolicy: Always
           ports:
             - containerPort: 8000

k8s/deployment.yaml

@@ -20,7 +20,7 @@ spec:
         - name: acr-secret
       containers:
         - name: agent-manager
-          image: agnettaiji.azurecr.io/agent-manager:latest
+          image: agnettaiji.azurecr.io/ai-agents/agent-manager:heicode-v2-runtime-20260601195848-arm64
           imagePullPolicy: Always
           ports:
             - containerPort: 8000

k8s_manager.py

@@ -2456,7 +2456,9 @@ echo "Identity volume initialized successfully"
             )
             stream_enabled = billing_context.get("stream")
             if stream_enabled is None:
-                stream_enabled = "gpt-5.4" in model_lower or "claude" in model_lower
+                # Default to non-streaming for runtime agents unless Manager explicitly requests it.
+                # This keeps artifact extraction stable across model gateway implementations.
+                stream_enabled = False
             elif isinstance(stream_enabled, str):
                 stream_enabled = stream_enabled.lower() in {"1", "true", "yes", "on"}
             timeout_seconds = int(