Update app.py

app.py

@@ -30,8 +30,7 @@ async def run_tutor(user_message, chat_history):
     It connects to the local MCP server for every request to ensure fresh context.
     """
     
-    # 1. Define Server Parameters (Point to our local server.py)
-    # We use the current python executable to run the server script
+    # 1. Define Server Parameters
     server_params = StdioServerParameters(
         command=sys.executable, 
         args=["server.py"], 
@@ -54,46 +53,41 @@ async def run_tutor(user_message, chat_history):
                 temperature=0.7
             )
 
-            # 4. Create Agent (Using LangGraph prebuilt agent)
+            # 4. Create Agent
             agent_executor = create_react_agent(llm, tools, state_modifier=SYSTEM_PROMPT)
 
             # 5. Execute
-            # LangGraph expects a dictionary with a "messages" key
             inputs = {"messages": [HumanMessage(content=user_message)]}
-            
-            # We use ainvoke to run the agent asynchronously
             response = await agent_executor.ainvoke(inputs)
             
             # 6. Extract the final response text
-            # The last message in the list is the AI's final answer
             return response["messages"][-1].content
 
-# --- Gradio UI ---
-# REMOVED: theme=gr.themes.Soft() to prevent the TypeError
+# --- Gradio UI (Universal Fix) ---
 with gr.Blocks(title="AI Python Tutor (MCP Powered)") as demo:
     gr.Markdown("# 🐍 Vibe Coding Tutor")
     gr.Markdown("Powered by **Nebius** (Llama 3.1) & **MCP** (Local Filesystem Access)")
     
-    # Type="messages" is critical for Gradio 5 chat interface style
-    chatbot = gr.Chatbot(height=600, type="messages")
+    # REMOVED: type="messages" (This fixes the TypeError)
+    chatbot = gr.Chatbot(height=600) 
     msg = gr.Textbox(placeholder="E.g., Teach me how to use Python decorators with a working example.")
     
     async def user_turn(user_message, history):
-        history.append({"role": "user", "content": user_message})
-        return "", history
+        # Universal format: Append a list of [user_msg, None]
+        # This works on Gradio 3, 4, and 5
+        return "", history + [[user_message, None]]
 
     async def bot_turn(history):
-        # Get the last message content
-        last_message = history[-1]["content"]
+        # Get the last user message (it's the first element of the last tuple)
+        last_message = history[-1][0]
         
         # Run the agent
         response_text = await run_tutor(last_message, [])
         
-        # Append response
-        history.append({"role": "assistant", "content": response_text})
+        # Update the last tuple with the bot response
+        history[-1][1] = response_text
         return history
 
-    # Event wiring
     msg.submit(user_turn, [msg, chatbot], [msg, chatbot]).then(
         bot_turn, [chatbot], [chatbot]
     )