feat(containers): encode container IDs in SDK responses for routing

- Add ContainerRequestUtils.encode_container_id_in_response utility
- Encode container_id in create/retrieve/delete responses (SDK path)
- Fix streaming iterator: gate response ID update on parsed_chunk key
- Follows responses API pattern (encode after handler, not in handler)

Made-with: Cursor

litellm/containers/main.py

@@ -279,7 +279,7 @@ def create_container(
         # Set the correct call type for container creation
         litellm_logging_obj.call_type = CallTypes.create_container.value
 
-        return base_llm_http_handler.container_create_handler(
+        container_obj = base_llm_http_handler.container_create_handler(
             name=name,
             container_create_request_params=container_create_request_params,
             container_provider_config=container_provider_config,
@@ -289,6 +289,17 @@ def create_container(
             timeout=timeout or DEFAULT_REQUEST_TIMEOUT,
             _is_async=_is_async,
         )
+        
+        # Encode container_id with provider/model metadata for routing
+        if isinstance(container_obj, ContainerObject):
+            model_id = kwargs.get("litellm_metadata", {}).get("model_info", {}).get("id")
+            container_obj = ContainerRequestUtils.encode_container_id_in_response(
+                response_obj=container_obj,
+                custom_llm_provider=custom_llm_provider,
+                model_id=model_id,
+            )
+        
+        return container_obj
 
     except Exception as e:
         raise litellm.exception_type(
@@ -683,7 +694,7 @@ def retrieve_container(
         # Set the correct call type
         litellm_logging_obj.call_type = CallTypes.retrieve_container.value
 
-        return base_llm_http_handler.container_retrieve_handler(
+        container_obj = base_llm_http_handler.container_retrieve_handler(
             container_id=original_container_id,  # Use decoded original ID
             container_provider_config=container_provider_config,
             litellm_params=litellm_params,
@@ -693,6 +704,17 @@ def retrieve_container(
             timeout=timeout or DEFAULT_REQUEST_TIMEOUT,
             _is_async=_is_async,
         )
+        
+        # Encode container_id with provider/model metadata for routing
+        if isinstance(container_obj, ContainerObject):
+            model_id = kwargs.get("litellm_metadata", {}).get("model_info", {}).get("id")
+            container_obj = ContainerRequestUtils.encode_container_id_in_response(
+                response_obj=container_obj,
+                custom_llm_provider=custom_llm_provider,
+                model_id=model_id,
+            )
+        
+        return container_obj
 
     except Exception as e:
         raise litellm.exception_type(
@@ -879,7 +901,7 @@ def delete_container(
         # Set the correct call type
         litellm_logging_obj.call_type = CallTypes.delete_container.value
 
-        return base_llm_http_handler.container_delete_handler(
+        delete_result = base_llm_http_handler.container_delete_handler(
             container_id=original_container_id,  # Use decoded original ID
             container_provider_config=container_provider_config,
             litellm_params=litellm_params,
@@ -889,6 +911,17 @@ def delete_container(
             timeout=timeout or DEFAULT_REQUEST_TIMEOUT,
             _is_async=_is_async,
         )
+        
+        # Encode container_id in response with provider/model metadata for routing
+        if isinstance(delete_result, DeleteContainerResult):
+            model_id = kwargs.get("litellm_metadata", {}).get("model_info", {}).get("id")
+            delete_result = ContainerRequestUtils.encode_container_id_in_response(
+                response_obj=delete_result,
+                custom_llm_provider=custom_llm_provider,
+                model_id=model_id,
+            )
+        
+        return delete_result
 
     except Exception as e:
         raise litellm.exception_type(

litellm/containers/utils.py

@@ -1,4 +1,4 @@
-from typing import Dict
+from typing import Any, Dict, Optional, TypeVar
 
 from litellm.llms.base_llm.containers.transformation import BaseContainerConfig
 from litellm.types.containers.main import (
@@ -6,6 +6,8 @@ from litellm.types.containers.main import (
     ContainerListOptionalRequestParams,
 )
 
+T = TypeVar("T")
+
 
 class ContainerRequestUtils:
     @staticmethod
@@ -68,3 +70,35 @@ class ContainerRequestUtils:
                 container_list_optional_params[param] = passed_params[param]  # type: ignore
 
         return container_list_optional_params
+
+    @staticmethod
+    def encode_container_id_in_response(
+        response_obj: T,
+        custom_llm_provider: Optional[str],
+        model_id: Optional[str],
+    ) -> T:
+        """
+        Encode container_id in response object with provider/model metadata for routing.
+        
+        This mirrors the responses API pattern where response IDs are encoded with
+        routing metadata so follow-up calls can route to the correct provider.
+        
+        Args:
+            response_obj: Response object with an `id` attribute (ContainerObject, DeleteContainerResult, etc.)
+            custom_llm_provider: Provider name (e.g., "azure", "openai")
+            model_id: Model ID from litellm_metadata
+            
+        Returns:
+            The same response object with encoded container_id
+        """
+        if response_obj and hasattr(response_obj, "id"):
+            from litellm.responses.utils import ResponsesAPIRequestUtils
+            
+            encoded_id = ResponsesAPIRequestUtils._build_container_id(
+                custom_llm_provider=custom_llm_provider,
+                model_id=model_id,
+                container_id=response_obj.id,
+            )
+            response_obj.id = encoded_id
+        
+        return response_obj