Force hf-inference provider to avoid nscale/novita routing

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app.py

@@ -17,7 +17,8 @@ class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
         model = InferenceClientModel(
-            model_id="meta-llama/Llama-3.2-3B-Instruct",
+            model_id="Qwen/Qwen2.5-72B-Instruct",
+            provider="hf-inference",
             token=os.getenv("HF_TOKEN"),
         )
         self.agent = CodeAgent(