fix mypy check issues

litellm/google_genai/adapters/transformation.py

@@ -9,6 +9,7 @@ from litellm.types.llms.openai import (
     ChatCompletionAssistantMessage,
     ChatCompletionAssistantToolCall,
     ChatCompletionRequest,
+    ChatCompletionSystemMessage,
     ChatCompletionToolCallFunctionChunk,
     ChatCompletionToolChoiceValues,
     ChatCompletionToolMessage,
@@ -33,7 +34,7 @@ class GoogleGenAIStreamWrapper(AdapterCompletionStreamWrapper):
 
     sent_first_chunk: bool = False
     # State tracking for accumulating partial tool calls
-    gccumulated_tool_calls: Dict[str, Dict[str, Any]]
+    accumulated_tool_calls: Dict[str, Dict[str, Any]]
 
     def __init__(self, completion_stream: Any):
         self.sent_first_chunk = False
@@ -373,7 +374,7 @@ class GoogleGenAIAdapter:
             system_parts = system_instruction.get("parts", [])
             if system_parts and "text" in system_parts[0]:
                 messages.append(
-                    ChatCompletionUserMessage(
+                    ChatCompletionSystemMessage(
                         role="system", content=system_parts[0]["text"]
                     )
                 )
@@ -466,10 +467,7 @@ class GoogleGenAIAdapter:
         Returns:
             Dict in Google GenAI generate_content response format
         """
-        if isinstance(response, AdapterCompletionStreamWrapper):
-            return self.translate_streaming_completion_to_generate_content(
-                response, wrapper=response
-            )
+
 
         # Extract the main response content
         choice = response.choices[0] if response.choices else None

litellm/main.py

@@ -24,6 +24,7 @@ from functools import partial
 from typing import (
     TYPE_CHECKING,
     Any,
+    AsyncIterator,
     Callable,
     Coroutine,
     Dict,
@@ -5141,12 +5142,18 @@ async def aadapter_completion(
 
 async def aadapter_generate_content(
     **kwargs,
-) -> Union[ModelResponse, CustomStreamWrapper]:
+) -> Union[Dict[str, Any], AsyncIterator[bytes]]:
     from litellm.google_genai.adapters.handler import (
         GenerateContentToCompletionHandler,
     )
 
-    return await GenerateContentToCompletionHandler.async_generate_content_handler(**kwargs, _is_async=True)
+    coro = cast(
+        Coroutine[Any, Any, Union[Dict[str, Any], AsyncIterator[bytes]]],
+        GenerateContentToCompletionHandler.generate_content_handler(
+            **kwargs, _is_async=True
+        ),
+    )
+    return await coro
 
 
 def adapter_completion(

litellm/proxy/google_endpoints/endpoints.py

@@ -1,4 +1,4 @@
-from fastapi import APIRouter, Depends, Request, Response
+from fastapi import APIRouter, Depends, Request, Response, HTTPException
 from fastapi.responses import StreamingResponse
 
 from litellm.proxy._types import *
@@ -30,9 +30,9 @@ async def google_generate_content(
     data = await _read_request_body(request=request)
     if "model" not in data:
         data["model"] = model_name
-    data["stream"] = False
-
     # call router
+    if llm_router is None:
+        raise HTTPException(status_code=500, detail="Router not initialized")
     response = await llm_router.agenerate_content(**data)
     return response
 
@@ -61,6 +61,8 @@ async def google_stream_generate_content(
     data["stream"] = True  # enforce streaming for this endpoint
 
     # call router
+    if llm_router is None:
+        raise HTTPException(status_code=500, detail="Router not initialized")
     response = await llm_router.agenerate_content(**data)
 
     # Check if response is an async iterator (streaming response)