fix: use router.huggingface.co/hf endpoint (api-inference DNS not resolvable from Space)

app.py

@@ -39,7 +39,8 @@ def infer(messages, model, temperature=0.7, top_p=0.9, max_tokens=2048, tools=No
     if tools:
         payload["tools"] = tools
 
-    url = f"https://api-inference.huggingface.co/models/{model}/v1/chat/completions"
+    url = f"https://router.huggingface.co/hf/v1/chat/completions"
+    payload["model"] = model
     resp = requests.post(url, headers=headers, json=payload, timeout=120)
 
     if resp.status_code == 503: