Asking a human first

HumanInTheLoopMiddleware is a middleware that pauses an agent before a chosen tool runs and waits for a person to approve or reject the call.

Last updated: 27 Sep, 2026 · LangChain 1.4

Some tools should not run on a model's word alone, such as a refund. The shop adds a second tool to tools.py, and the stand-in model from earlier asks for it when a message mentions a refund.

HumanInTheLoopMiddleware and a checkpointer

from langchain.agents.middleware import HumanInTheLoopMiddleware
from langgraph.checkpoint.memory import InMemorySaver

approval = HumanInTheLoopMiddleware(interrupt_on={"refund_order": True})  # pause on this tool
# a checkpointer is required so the paused run can be resumed later
agent = create_agent(model, tools=tools, middleware=[approval], checkpointer=InMemorySaver())

The refund tool

First the new tool. It refunds an order, which cannot be undone, so it is the call a person should confirm.

@tool
def refund_order(order_id: str) -> str:
    """Refund an order in full. This cannot be undone."""
    return f"Refunded {order_id}."

The agent with approval

Build the agent with both tools and the middleware. interrupt_on names the tools that need a decision; True means every call to that tool pauses. lookup_order is not listed, so it runs as before. The checkpointer is required: a paused agent is saved, and the decision may come minutes or days later.

from langchain.agents import create_agent
from langchain.agents.middleware import HumanInTheLoopMiddleware
from langgraph.checkpoint.memory import InMemorySaver
from langgraph.types import Command
from shop_model import ShopModel
from tools import lookup_order, refund_order

approval = HumanInTheLoopMiddleware(interrupt_on={"refund_order": True})
agent = create_agent(ShopModel(), tools=[lookup_order, refund_order],
                     middleware=[approval], checkpointer=InMemorySaver())

The pause

Ask for a refund. With version="v2", invoke returns an object with the state so far and whatever is waiting for a decision.

thread = {"configurable": {"thread_id": "ravi-refund"}}
ask = {"messages": [{"role": "user", "content": "Please refund A17"}]}
result = agent.invoke(ask, thread, version="v2")

print(result.interrupts[0].value["action_requests"])
print(result.value["messages"][-1].tool_calls[0]["name"])

Invoking with version="v2" returns an object with two parts. value is the state so far, ending with the model's request to refund A17. interrupts holds what is waiting for a decision: the tool, its arguments and a description a reviewer can read. The refund has not run.

Approving

Send a decision back on the same thread with Command(resume=...).

decision = Command(resume={"decisions": [{"type": "approve"}]})
result = agent.invoke(decision, thread, version="v2")

for message in result.value["messages"][2:]:
    print(f"{message.type:<4} {message.text}")

A Command with resume continues the same thread, and decisions holds one decision per paused call. After the approval the refund ran and the model answered.

Rejecting

Reject instead, with a reason for the model to relay.

decision = Command(resume={"decisions": [{"type": "reject", "message": "Refunds need a manager."}]})
result = agent.invoke(decision, thread, version="v2")

for message in result.value["messages"][2:]:
    print(f"{message.type:<4} {message.text}")

A rejection never runs the tool. The model gets a tool message with the reason instead, so it can tell the customer why. Without a message, the middleware writes a default one telling the model not to try the same call again.

What each decision did

• The run paused before the refund. With version="v2", invoke returned value (the state so far) and interrupts (the pending call); the refund had not run.
• Approve runs the tool. Command(resume=...) with {"type": "approve"} continued the thread, the refund ran, and the model confirmed it.
• Reject skips the tool. The model got a tool message with the reason instead, so it could explain the refusal.
• The checkpointer holds the pause. The decision can arrive any time later because the paused state is saved.

Approve vs reject

Where a pause for approval fits

• A refund, a delete, or any action that cannot be undone.
• A step that spends money or emails a customer, held for a person to confirm.
• A review queue where approvals arrive minutes or days after the request.

Related

• Previous: More built-in middleware to reach for
• Next: Edit and respond
• Reference: LangChain agent middleware