Update app.py

app.py

@@ -137,21 +137,30 @@ class BasicAgent:
 
     # ---- Low‑level LLM call
     def _call_llm(self, prompt: str, max_tokens: int = 256) -> str:
-        try:
-            resp = self.llm.chat.completions.create(
-                model="gpt-4o-mini",
-                messages=[
-                    {"role": "system", "content": "You are a careful reasoning assistant."},
-                    {"role": "user", "content": prompt},
-                ],
-                temperature=0.3,
-                max_tokens=max_tokens,
-            )
-            return resp.choices[0].message.content.strip()
-        except Exception as e:
-            print(f"\nLLM Error: {str(e)}")
-            print(f"Prompt that caused error:\n{prompt}")
-            raise
+        # List of models to try in order
+        models = ["gpt-4o-mini", "gpt-3.5-turbo", "gpt-4"]
+        
+        for model in models:
+            try:
+                print(f"\nTrying model: {model}")
+                resp = self.llm.chat.completions.create(
+                    model=model,
+                    messages=[
+                        {"role": "system", "content": "You are a careful reasoning assistant."},
+                        {"role": "user", "content": prompt},
+                    ],
+                    temperature=0.3,
+                    max_tokens=max_tokens,
+                )
+                return resp.choices[0].message.content.strip()
+            except Exception as e:
+                print(f"Error with {model}: {str(e)}")
+                if model == models[-1]:  # If this was the last model
+                    print(f"All models failed. Last error: {str(e)}")
+                    print(f"Prompt that caused error:\n{prompt}")
+                    raise
+                print(f"Falling back to next model...")
+                continue
 
     # ---- Workflow nodes
     def _analyze_question(self, state: AgentState) -> AgentState: