Add supports_native_websocket to handle providers who don't handle websocket

litellm/llms/base_llm/responses/transformation.py

@@ -218,6 +218,18 @@ class BaseResponsesAPIConfig(ABC):
         """Returns True if litellm should fake a stream for the given model and stream value"""
         return False
 
+    def supports_native_websocket(self) -> bool:
+        """
+        Returns True if the provider has a native WebSocket endpoint for Responses API.
+        
+        Providers with native websocket support can connect directly to wss:// endpoints.
+        Providers without native support will use the ManagedResponsesWebSocketHandler
+        which makes HTTP streaming calls and forwards events over the websocket.
+        
+        Default: False (use managed websocket handler)
+        """
+        return False
+
     #########################################################
     ########## CANCEL RESPONSE API TRANSFORMATION ##########
     #########################################################

litellm/llms/chatgpt/responses/transformation.py

@@ -1,14 +1,14 @@
 import json
 from typing import Any, Optional
 
-from litellm.exceptions import AuthenticationError
 from litellm.constants import STREAM_SSE_DONE_STRING
+from litellm.exceptions import AuthenticationError
 from litellm.litellm_core_utils.core_helpers import process_response_headers
-from litellm.llms.openai.common_utils import OpenAIError
-from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig
 from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import (
     _safe_convert_created_field,
 )
+from litellm.llms.openai.common_utils import OpenAIError
+from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig
 from litellm.types.llms.openai import (
     ResponsesAPIResponse,
     ResponsesAPIStreamEvents,
@@ -200,3 +200,7 @@ class ChatGPTResponsesAPIConfig(OpenAIResponsesAPIConfig):
         api_base = api_base or self.authenticator.get_api_base() or CHATGPT_API_BASE
         api_base = api_base.rstrip("/")
         return f"{api_base}/responses"
+
+    def supports_native_websocket(self) -> bool:
+        """ChatGPT does not support native WebSocket for Responses API"""
+        return False

litellm/llms/databricks/responses/transformation.py

@@ -98,3 +98,7 @@ class DatabricksResponsesAPIConfig(DatabricksBase, OpenAIResponsesAPIConfig):
             litellm_params=litellm_params,
             headers=headers,
         )
+
+    def supports_native_websocket(self) -> bool:
+        """Databricks does not support native WebSocket for Responses API"""
+        return False

litellm/llms/github_copilot/responses/transformation.py

@@ -22,8 +22,8 @@ from litellm.types.utils import LlmProviders
 
 from ..authenticator import Authenticator
 from ..common_utils import (
-    GetAPIKeyError,
     GITHUB_COPILOT_API_BASE,
+    GetAPIKeyError,
     get_copilot_default_headers,
 )
 
@@ -329,3 +329,7 @@ class GithubCopilotResponsesAPIConfig(OpenAIResponsesAPIConfig):
             )
 
         return False
+
+    def supports_native_websocket(self) -> bool:
+        """GitHub Copilot does not support native WebSocket for Responses API"""
+        return False

litellm/llms/hosted_vllm/responses/transformation.py

@@ -69,3 +69,7 @@ class HostedVLLMResponsesAPIConfig(OpenAIResponsesAPIConfig):
             return f"{api_base}/responses"
 
         return f"{api_base}/v1/responses"
+
+    def supports_native_websocket(self) -> bool:
+        """Hosted vLLM does not support native WebSocket for Responses API"""
+        return False

litellm/llms/litellm_proxy/responses/transformation.py

@@ -46,3 +46,7 @@ class LiteLLMProxyResponsesAPIConfig(OpenAIResponsesAPIConfig):
         api_base = api_base.rstrip("/")
 
         return f"{api_base}/responses"
+
+    def supports_native_websocket(self) -> bool:
+        """LiteLLM Proxy does not support native WebSocket for Responses API"""
+        return False

litellm/llms/manus/responses/transformation.py

@@ -247,6 +247,10 @@ class ManusResponsesAPIConfig(OpenAIResponsesAPIConfig):
         response._hidden_params["headers"] = raw_response_headers
         return response
 
+    def supports_native_websocket(self) -> bool:
+        """Manus does not support native WebSocket for Responses API"""
+        return False
+
     def transform_get_response_api_request(
         self,
         response_id: str,

litellm/llms/openai/responses/transformation.py

@@ -344,6 +344,10 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
                 )
         return False
 
+    def supports_native_websocket(self) -> bool:
+        """OpenAI supports native WebSocket for Responses API"""
+        return True
+
     #########################################################
     ########## DELETE RESPONSE API TRANSFORMATION ##############
     #########################################################

litellm/llms/openrouter/responses/transformation.py

@@ -75,3 +75,7 @@ class OpenRouterResponsesAPIConfig(OpenAIResponsesAPIConfig):
         api_base = api_base.rstrip("/")
 
         return f"{api_base}/responses"
+
+    def supports_native_websocket(self) -> bool:
+        """OpenRouter does not support native WebSocket for Responses API"""
+        return False

litellm/llms/perplexity/responses/transformation.py

@@ -490,3 +490,7 @@ class PerplexityResponsesConfig(OpenAIResponsesAPIConfig):
             verbose_logger.debug("Failed to transform Perplexity cost object: %s", e)
 
         return chunk
+
+    def supports_native_websocket(self) -> bool:
+        """Perplexity does not support native WebSocket for Responses API"""
+        return False

litellm/llms/volcengine/responses/transformation.py

@@ -16,16 +16,17 @@ from pydantic import fields as pyd_fields
 
 import litellm
 from litellm._logging import verbose_logger
-from litellm.types.llms.openai import ResponseInputParam, ResponsesAPIStreamingResponse
-from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig
 from litellm.litellm_core_utils.core_helpers import process_response_headers
 from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import (
     _safe_convert_created_field,
 )
+from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig
 from litellm.secret_managers.main import get_secret_str
 from litellm.types.llms.openai import (
+    ResponseInputParam,
     ResponsesAPIOptionalRequestParams,
     ResponsesAPIResponse,
+    ResponsesAPIStreamingResponse,
 )
 from litellm.types.responses.main import DeleteResponseResult
 from litellm.types.router import GenericLiteLLMParams
@@ -555,3 +556,7 @@ class VolcEngineResponsesAPIConfig(OpenAIResponsesAPIConfig):
 
         # Fall back to the first candidate
         return candidates[0]
+
+    def supports_native_websocket(self) -> bool:
+        """VolcEngine does not support native WebSocket for Responses API"""
+        return False

litellm/llms/xai/responses/transformation.py

@@ -252,3 +252,7 @@ class XAIResponsesAPIConfig(OpenAIResponsesAPIConfig):
         
         return f"{api_base}/responses"
 
+    def supports_native_websocket(self) -> bool:
+        """XAI does not support native WebSocket for Responses API"""
+        return False
+