Fix UnboundLocalError for StreamingResponse in chat_completions

The issue was caused by importing StreamingResponse and JSONResponse inside
the chat_completions function. In Python, when you have an import statement
anywhere inside a function, it creates a local variable for that name
throughout the entire function scope. This caused the code in the original
implementation path to fail because Python saw StreamingResponse as an
unassigned local variable.

Fix: Move StreamingResponse and JSONResponse imports to module level and
remove redundant imports from inside the function.

coderai

@@ -23,7 +23,7 @@ from typing import AsyncGenerator, Dict, List, Optional, Union
 
 import psutil
 from fastapi import FastAPI, HTTPException, Request
-from fastapi.responses import StreamingResponse, FileResponse
+from fastapi.responses import StreamingResponse, FileResponse, JSONResponse
 from pydantic import BaseModel, Field, validator, field_validator, ConfigDict
 from pydantic_core import PydanticCustomError
 from threading import Thread
@@ -5292,7 +5292,6 @@ async def chat_completions(request: ChatCompletionRequest, http_request: Request
         try:
             if request.stream:
                 # Streaming response
-                from fastapi.responses import StreamingResponse
                 
                 async def generate():
                     try:
@@ -5373,8 +5372,6 @@ async def chat_completions(request: ChatCompletionRequest, http_request: Request
                         completion_tokens=response.get('usage', {}).get('completion_tokens', 0)
                     )
                 
-                from fastapi.responses import JSONResponse
-                return JSONResponse(content=response, headers=headers)
                 
         except Exception as e:
             # Handle litellm errors