Update app.py

app.py

@@ -4,7 +4,6 @@ from fastapi.responses import StreamingResponse, JSONResponse
 from pydantic import BaseModel
 from typing import List, Optional
 
-import asyncio
 import json
 import time
 import uuid
@@ -28,8 +27,6 @@ logger = logging.getLogger(__name__)
 
 API_KEY = "sk-your-secret-key"
 
-REQUEST_TIMEOUT = 60
-
 
 # =====================================================
 # FASTAPI
@@ -37,7 +34,7 @@ REQUEST_TIMEOUT = 60
 
 app = FastAPI(
     title="Universal AI Gateway",
-    version="5.0.0"
+    version="5.1.0"
 )
 
 
@@ -109,12 +106,12 @@ async def root():
     return {
         "status": "online",
         "service": "Universal AI Gateway",
-        "version": "5.0.0"
+        "version": "5.1.0"
     }
 
 
 # =====================================================
-# MODELS
+# GET MODELS
 # =====================================================
 
 @app.get("/v1/models")
@@ -149,22 +146,19 @@ async def get_models():
 
 # =====================================================
 # SAFE COMPLETION
-# لا تقييد providers
-# نترك g4f يختار تلقائياً
+# لا asyncio
+# لا to_thread
+# لا wait_for
 # =====================================================
 
-async def safe_completion(model, messages, stream=False):
+def safe_completion(model, messages, stream=False):
 
     client = Client()
 
-    response = await asyncio.wait_for(
-        asyncio.to_thread(
-            client.chat.completions.create,
-            model=model,
-            messages=messages,
-            stream=stream
-        ),
-        timeout=REQUEST_TIMEOUT
+    response = client.chat.completions.create(
+        model=model,
+        messages=messages,
+        stream=stream
     )
 
     return response
@@ -206,7 +200,7 @@ async def chat_completions(
 
             try:
 
-                response = await safe_completion(
+                response = safe_completion(
                     model=body.model,
                     messages=messages,
                     stream=True
@@ -263,8 +257,6 @@ async def chat_completions(
                             + "\n\n"
                         )
 
-                        await asyncio.sleep(0)
-
                     except Exception as chunk_error:
 
                         logger.error(
@@ -308,27 +300,6 @@ async def chat_completions(
 
                 yield "data: [DONE]\n\n"
 
-            except asyncio.TimeoutError:
-
-                logger.error(
-                    f"Timeout model={body.model}"
-                )
-
-                error_payload = {
-                    "error": {
-                        "message": "Request timeout",
-                        "type": "timeout"
-                    }
-                }
-
-                yield (
-                    "data: "
-                    + json.dumps(error_payload)
-                    + "\n\n"
-                )
-
-                yield "data: [DONE]\n\n"
-
             except Exception as e:
 
                 logger.error(
@@ -366,7 +337,7 @@ async def chat_completions(
 
     try:
 
-        response = await safe_completion(
+        response = safe_completion(
             model=body.model,
             messages=messages,
             stream=False
@@ -418,13 +389,6 @@ async def chat_completions(
 
         })
 
-    except asyncio.TimeoutError:
-
-        raise HTTPException(
-            status_code=408,
-            detail="Request timeout"
-        )
-
     except Exception as e:
 
         logger.error(f"Chat error: {e}")