Use stdlib HTTP proxy for /v1/responses compatibility

app/routes.py

@@ -5,11 +5,11 @@ import queue
 import re
 import threading
 import time
+import urllib.request
 from uuid import uuid4
 
 from fastapi import APIRouter, HTTPException, Request
 from fastapi.responses import HTMLResponse, JSONResponse, RedirectResponse, StreamingResponse
-from curl_cffi import requests as curl_requests
 
 from . import chat, config, constants, session as session_module
 from .account import (
@@ -175,18 +175,25 @@ def _call_local_chat_completions(chat_body: dict, auth_header: str, x_api_key: s
         headers["Authorization"] = auth_header
     if x_api_key:
         headers["x-api-key"] = x_api_key
-    resp = curl_requests.post(
+    req = urllib.request.Request(
         f"http://127.0.0.1:{local_port}/v1/chat/completions",
+        data=json.dumps(chat_body).encode("utf-8"),
         headers=headers,
-        json=chat_body,
-        impersonate="safari15_3",
-        timeout=180,
+        method="POST",
     )
     try:
-        payload = resp.json()
-    except Exception:
-        payload = {"error": resp.text}
-    return resp.status_code, payload
+        with urllib.request.urlopen(req, timeout=180) as resp:
+            raw = resp.read().decode("utf-8")
+            return resp.status, json.loads(raw)
+    except urllib.error.HTTPError as exc:
+        raw = exc.read().decode("utf-8", errors="replace")
+        try:
+            payload = json.loads(raw)
+        except Exception:
+            payload = {"error": raw}
+        return exc.code, payload
+    except Exception as exc:
+        return 500, {"error": str(exc)}
 
 
 def _chat_completion_to_response_payload(chat_payload: dict) -> dict: