Import json and print

llm_server.py

@@ -1,3 +1,4 @@
+import json
 import time
 from fastapi import FastAPI, HTTPException
 from fastapi.responses import StreamingResponse, JSONResponse
@@ -136,6 +137,9 @@ async def keep_model_warm():
 # ─── OpenAI‐compatible endpoint ─────────────────────────────────────────────
 @app.post("/v1/chat/completions")
 async def chat(req: dict):
+
+    print("Request:", req)
+
     # if the client (Qwen-Agent) asked for a stream, proxy the SSE events:
     if req.get("stream", False):
         async def event_generator():