Update app.py

app.py

@@ -9,7 +9,6 @@ from langchain_mcp_adapters.tools import load_mcp_tools
 from langchain_core.messages import HumanMessage
 
 # --- Configuration ---
-# Ensure NEBIUS_API_KEY is set in your Space's "Settings -> Secrets"
 NEBIUS_API_KEY = os.getenv("NEBIUS_API_KEY") 
 NEBIUS_BASE_URL = "https://api.studio.nebius.ai/v1/"
 MODEL_NAME = "meta-llama/Meta-Llama-3.1-70B-Instruct"
@@ -32,6 +31,7 @@ async def run_tutor(user_message, chat_history):
     """
     
     # 1. Define Server Parameters (Point to our local server.py)
+    # We use the current python executable to run the server script
     server_params = StdioServerParameters(
         command=sys.executable, 
         args=["server.py"], 
@@ -55,7 +55,6 @@ async def run_tutor(user_message, chat_history):
             )
 
             # 4. Create Agent (Using LangGraph prebuilt agent)
-            # This replaces the old AgentExecutor
             agent_executor = create_react_agent(llm, tools, state_modifier=SYSTEM_PROMPT)
 
             # 5. Execute
@@ -70,10 +69,12 @@ async def run_tutor(user_message, chat_history):
             return response["messages"][-1].content
 
 # --- Gradio UI ---
-with gr.Blocks(title="AI Python Tutor (MCP Powered)", theme=gr.themes.Soft()) as demo:
+# REMOVED: theme=gr.themes.Soft() to prevent the TypeError
+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")
     msg = gr.Textbox(placeholder="E.g., Teach me how to use Python decorators with a working example.")
     
@@ -82,11 +83,17 @@ with gr.Blocks(title="AI Python Tutor (MCP Powered)", theme=gr.themes.Soft()) as
         return "", history
 
     async def bot_turn(history):
+        # Get the last message content
         last_message = history[-1]["content"]
+        
+        # Run the agent
         response_text = await run_tutor(last_message, [])
+        
+        # Append response
         history.append({"role": "assistant", "content": response_text})
         return history
 
+    # Event wiring
     msg.submit(user_turn, [msg, chatbot], [msg, chatbot]).then(
         bot_turn, [chatbot], [chatbot]
     )