Human-in-the-loop using server API

To review, edit, and approve tool calls in an agent or workflow, use LangGraph’s human-in-the-loop features.

Dynamic interrupts

from langgraph_sdk import get_client
# highlight-next-line
from langgraph_sdk.schema import Command
client = get_client(url=<DEPLOYMENT_URL>)

# Using the graph deployed with the name "agent"
assistant_id = "agent"

# create a thread
thread = await client.threads.create()
thread_id = thread["thread_id"]

# Run the graph until the interrupt is hit.
result = await client.runs.wait(
    thread_id,
    assistant_id,
    input={"some_text": "original text"}   # (1)!
)

print(result['__interrupt__']) # (2)!
# > [
# >     {
# >         'value': {'text_to_revise': 'original text'},
# >         'resumable': True,
# >         'ns': ['human_node:fc722478-2f21-0578-c572-d9fc4dd07c3b'],
# >         'when': 'during'
# >     }
# > ]


# Resume the graph
print(await client.runs.wait(
    thread_id,
    assistant_id,
    # highlight-next-line
    command=Command(resume="Edited text")   # (3)!
))
# > {'some_text': 'Edited text'}

The graph is invoked with some initial state.
When the graph hits the interrupt, it returns an interrupt object with the payload and metadata.
The graph is resumed with a Command(resume=...), injecting the human’s input and continuing execution.

Extended example: using `interrupt`

This is an example graph you can run in the LangGraph API server. See LangGraph Platform quickstart for more details.

from typing import TypedDict
import uuid

from langgraph.checkpoint.memory import InMemorySaver
from langgraph.constants import START
from langgraph.graph import StateGraph
# highlight-next-line
from langgraph.types import interrupt, Command

class State(TypedDict):
    some_text: str

def human_node(state: State):
    # highlight-next-line
    value = interrupt( # (1)!
        {
            "text_to_revise": state["some_text"] # (2)!
        }
    )
    return {
        "some_text": value # (3)!
    }


# Build the graph
graph_builder = StateGraph(State)
graph_builder.add_node("human_node", human_node)
graph_builder.add_edge(START, "human_node")

graph = graph_builder.compile()

interrupt(...) pauses execution at human_node, surfacing the given payload to a human.
Any JSON serializable value can be passed to the interrupt function. Here, a dict containing the text to revise.
Once resumed, the return value of interrupt(...) is the human-provided input, which is used to update the state.

Once you have a running LangGraph API server, you can interact with it using LangGraph SDK

from langgraph_sdk import get_client
# highlight-next-line
from langgraph_sdk.schema import Command
client = get_client(url=<DEPLOYMENT_URL>)

# Using the graph deployed with the name "agent"
assistant_id = "agent"

# create a thread
thread = await client.threads.create()
thread_id = thread["thread_id"]

# Run the graph until the interrupt is hit.
result = await client.runs.wait(
    thread_id,
    assistant_id,
    input={"some_text": "original text"}   # (1)!
)

print(result['__interrupt__']) # (2)!
# > [
# >     {
# >         'value': {'text_to_revise': 'original text'},
# >         'resumable': True,
# >         'ns': ['human_node:fc722478-2f21-0578-c572-d9fc4dd07c3b'],
# >         'when': 'during'
# >     }
# > ]


# Resume the graph
print(await client.runs.wait(
    thread_id,
    assistant_id,
    # highlight-next-line
    command=Command(resume="Edited text")   # (3)!
))
# > {'some_text': 'Edited text'}

The graph is invoked with some initial state.
When the graph hits the interrupt, it returns an interrupt object with the payload and metadata.
The graph is resumed with a Command(resume=...), injecting the human’s input and continuing execution.

Static interrupts

Static interrupts (also known as static breakpoints) are triggered either before or after a node executes.

Static interrupts are not recommended for human-in-the-loop workflows. They are best used for debugging and testing.

You can set static interrupts by specifying interrupt_before and interrupt_after at compile time:

# highlight-next-line
graph = graph_builder.compile( # (1)!
    # highlight-next-line
    interrupt_before=["node_a"], # (2)!
    # highlight-next-line
    interrupt_after=["node_b", "node_c"], # (3)!
)

The breakpoints are set during compile time.
interrupt_before specifies the nodes where execution should pause before the node is executed.
interrupt_after specifies the nodes where execution should pause after the node is executed.

Alternatively, you can set static interrupts at run time:

# highlight-next-line
await client.runs.wait( # (1)!
    thread_id,
    assistant_id,
    inputs=inputs,
    # highlight-next-line
    interrupt_before=["node_a"], # (2)!
    # highlight-next-line
    interrupt_after=["node_b", "node_c"] # (3)!
)

client.runs.wait is called with the interrupt_before and interrupt_after parameters. This is a run-time configuration and can be changed for every invocation.
interrupt_before specifies the nodes where execution should pause before the node is executed.
interrupt_after specifies the nodes where execution should pause after the node is executed.

The following example shows how to add static interrupts:

from langgraph_sdk import get_client
client = get_client(url=<DEPLOYMENT_URL>)

# Using the graph deployed with the name "agent"
assistant_id = "agent"

# create a thread
thread = await client.threads.create()
thread_id = thread["thread_id"]

# Run the graph until the breakpoint
result = await client.runs.wait(
    thread_id,
    assistant_id,
    input=inputs   # (1)!
)

# Resume the graph
await client.runs.wait(
    thread_id,
    assistant_id,
    input=None   # (2)!
)

The graph is run until the first breakpoint is hit.
The graph is resumed by passing in None for the input. This will run the graph until the next breakpoint is hit.

Learn more

Human-in-the-loop conceptual guide: learn more about LangGraph human-in-the-loop features.
Common patterns: learn how to implement patterns like approving/rejecting actions, requesting user input, tool call review, and validating human input.

Build an app with the LangGraph basics

Data models

Core capabilities

LangGraph Studio

Human-in-the-loop using server API

Dynamic interrupts

Static interrupts

Learn more

Build an app with the LangGraph basics

Data models

Core capabilities

LangGraph Studio

​Dynamic interrupts

​Static interrupts

​Learn more

Dynamic interrupts

Static interrupts

Learn more