Triggering next node in langgraph

I am making a chatbot using langgraph each node allocated to teach a topic e.g AI, Prompts and LLM etc. i am using this Docuemnt: https://langchain-ai.github.io/langgraph/how-tos/multi-agent-network/ here is the code

from typing_extensions import Literal
from langchain_openai import ChatOpenAI
from langchain_core.messages import ToolMessage
from langchain_core.tools import tool
from langgraph.graph import MessagesState, StateGraph, START
from langgraph.checkpoint.memory import MemorySaver
from langgraph.types import Command


model = ChatOpenAI(model="gpt-4o", temperature=0)

# Define a helper for each of the agent nodes to call


@tool
def transfer_to_chat_handler():
    """Ask travel advisor for help."""
    # This tool is not returning anything: we're just using it
    # as a way for LLM to signal that it needs to hand off to another agent
    # (See the paragraph above)
    return


@tool
def transfer_to_teach_ai():
    """Ask chat handler for help."""
    return
@tool
def transfer_to_teach_prompt():
    """Ask chat handler for help."""
    return

def chathandler(
    state: MessagesState,
) -> Command[Literal["teach_ai", "__end__"]]:
    system_prompt = (
        "Your name is arti, you are a friendly teaching chatbot, teaching students about different topics"
        "you only job is get user's name and age and direct user to next lesson"
        # "here is the list of teachers: 'AI Teacher', 'Prompt Teacher"
        "trigger and transition to 'teach_ai' when you recieve user's name and age"
        # "trigger and transition to 'teach_prompt' when user is cleared about AI"
    )
    messages = [{"role": "system", "content": system_prompt}] + state["messages"]
    ai_msg = model.bind_tools([transfer_to_teach_ai]).invoke(messages)
    # If there are tool calls, the LLM needs to hand off to another agent
    if len(ai_msg.tool_calls) > 0:
        if "tool_calls" in ai_msg.additional_kwargs:
          tool_name = ai_msg.additional_kwargs["tool_calls"][0]["function"]["name"]

          if tool_name == "transfer_to_teach_ai":
              tool_call_id = ai_msg.tool_calls[-1]["id"]
              tool_msg = {
                  "role": "tool",
                  "content": "Successfully transferred to teach_ai",
                  "tool_call_id": tool_call_id,
              }
              return Command(goto="teach _ai", update={"messages": [ai_msg, tool_msg]})
          # elif tool_name == "transfer_to_teach_prompt":
          #     tool_call_id = ai_msg.tool_calls[-1]["id"]
          #     tool_msg = {
          #         "role": "tool",
          #         "content": "Successfully transferred to teach_prompt",
          #         "tool_call_id": tool_call_id,
          #     }
          #     return Command(goto="teach_prompt", update={"messages": [ai_msg, tool_msg]})

    return {"messages": [ai_msg]}


def teach_ai(
    state: MessagesState,
    ) -> Command[Literal[ "chathandler", "__end__"]]:
    system_prompt = (
        "introduce yourself that you will teach about AI in a fun and clear way.\n"
        "give a proper definition and examples"
        "ask user if they have any follow up questions"
        "If the user has completely understand the lesson, trigger a transition to 'chathandler'"
    )

    messages = [{"role": "system", "content": system_prompt}] + state["messages"]
    ai_msg = model.bind_tools([transfer_to_chat_handler]).invoke(messages)
    # If there are tool calls, the LLM needs to hand off to another agent
    if "tool_calls" in ai_msg.additional_kwargs:
          tool_name = ai_msg.additional_kwargs["tool_calls"][0]["function"]["name"]

          if tool_name == "transfer_to_chat_handler":
              tool_call_id = ai_msg.tool_calls[-1]["id"]
              tool_msg = {
                  "role": "tool",
                  "content": "Successfully transferred to chat_handler",
                  "tool_call_id": tool_call_id,
              }
              return Command(goto="chathandler", update={"messages": [ai_msg, tool_msg]})

    # If the expert has an answer, return it directly to the user
    return {"messages": [ai_msg]}


builder = StateGraph(MessagesState)
builder.add_node("chathandler", chathandler)
builder.add_node("teach_ai", teach_ai)
# we'll always start with a general travel advisor
builder.add_edge(START, "chathandler")
memory = MemorySaver()
graph = builder.compile(checkpointer=memory)

i have added "chathandler" to initiate conversation. as soon as you get the user's name and age trigger the next node you can see a func: transfer_to_teach_prompt that was being used to trigger teach_prompt node after completing teach_ai node i added if tool_name == "transfer_to_teach_ai": so that i can add more nodes later on however i have problem traversing node. as soon as the teach_ai is triggered i do not see anything on the response side here is a screenshot

here is a code for running the bot for your reference

config = {"configurable": {"user_id": "3", "thread_id": "1"}}
while True:
  user_input = input("user:")
  if user_input == 'q':
    break
  for chunk in graph.stream(
    {"messages": [("user", user_input)]}, config=config):
    pretty_print_messages(chunk)

i am sure i am making a mistake in implementation, maybe i am missing some information, however, later i want to implement more nodes, and each nodes should be triggered after user completes a lesson being taught by the node.