Use time-travel

When working with non-deterministic systems that make model-based decisions (e.g., agents powered by LLMs), it can be useful to examine their decision-making process in detail:

1. Understand reasoning: Analyze the steps that led to a successful result.
2. Debug mistakes: Identify where and why errors occurred.
3. Explore alternatives: Test different paths to uncover better solutions.

LangGraph provides time-travel functionality to support these use cases. Specifically, you can resume execution from a prior checkpoint — either replaying the same state or modifying it to explore alternatives. In all cases, resuming past execution produces a new fork in the history.

To use time-travel in LangGraph:

1. Run the graph with initial inputs using invoke or stream methods.
2. Identify a checkpoint in an existing thread: Use the get_state_history method to retrieve the execution history for a specific thread_id and locate the desired checkpoint_id. Alternatively, set an interrupt before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that interrupt.
3. Update the graph state (optional): Use the update_state method to modify the graph’s state at the checkpoint and resume execution from alternative state.
4. Resume execution from the checkpoint: Use the invoke or stream methods with an input of None and a configuration containing the appropriate thread_id and checkpoint_id.

In a workflow

This example builds a simple LangGraph workflow that generates a joke topic and writes a joke using an LLM. It demonstrates how to run the graph, retrieve past execution checkpoints, optionally modify the state, and resume execution from a chosen checkpoint to explore alternate outcomes.

Setup

To build this workflow in this example you need to set up the Anthropic LLM and install the required dependencies:

1. Install dependencies:

pip install langchain_core langchain-anthropic langgraph

2. Initialize the LLM:

import os
import getpass

from langchain_anthropic import ChatAnthropic

def _set_env(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"{var}: ")


_set_env("ANTHROPIC_API_KEY")

llm = ChatAnthropic(model="claude-sonnet-4-6")

Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph. You can also fetch traces from LangSmith to replay and debug production issues locally.

3. Implement the workflow The implementation of the workflow is a simple graph with two nodes, one for generating a joke topic, another for writing the joke itself and a state to storing the intermediate values.

import uuid

from typing_extensions import TypedDict, NotRequired
from langgraph.graph import StateGraph, START, END
from langchain.chat_models import init_chat_model
from langgraph.checkpoint.memory import InMemorySaver


class State(TypedDict):
    topic: NotRequired[str]
    joke: NotRequired[str]


model = init_chat_model(
    "claude-sonnet-4-6",
    temperature=0,
)


def generate_topic(state: State):
    """LLM call to generate a topic for the joke"""
    msg = model.invoke("Give me a funny topic for a joke")
    return {"topic": msg.content}


def write_joke(state: State):
    """LLM call to write a joke based on the topic"""
    msg = model.invoke(f"Write a short joke about {state['topic']}")
    return {"joke": msg.content}


# Build workflow
workflow = StateGraph(State)

# Add nodes
workflow.add_node("generate_topic", generate_topic)
workflow.add_node("write_joke", write_joke)

# Add edges to connect nodes
workflow.add_edge(START, "generate_topic")
workflow.add_edge("generate_topic", "write_joke")
workflow.add_edge("write_joke", END)

# Compile
checkpointer = InMemorySaver()
graph = workflow.compile(checkpointer=checkpointer)
graph

1. Run the graph

To start the workflow, invoke is called without any inputs. Note the thread_id to track this execution and retrieve its checkpoints later.

config = {
    "configurable": {
        "thread_id": uuid.uuid4(),
    }
}
state = graph.invoke({}, config)

print(state["topic"])
print()
print(state["joke"])

Output:

How about "The Secret Life of Socks in the Dryer"? You know, exploring the mysterious phenomenon of how socks go into the laundry as pairs but come out as singles. Where do they go? Are they starting new lives elsewhere? Is there a sock paradise we don't know about? There's a lot of comedic potential in the everyday mystery that unites us all!

# The Secret Life of Socks in the Dryer

I finally discovered where all my missing socks go after the dryer. Turns out they're not missing at all—they've just eloped with someone else's socks from the laundromat to start new lives together.

My blue argyle is now living in Bermuda with a red polka dot, posting vacation photos on Sockstagram and sending me lint as alimony.

2. Identify a checkpoint

To continue from a previous point in the graphs run, use get_state_history to retrieve all the states and select the one where you want to resume execution.

# The states are returned in reverse chronological order.
states = list(graph.get_state_history(config))

for state in states:
    print(state.next)
    print(state.config["configurable"]["checkpoint_id"])
    print()

Output:

()
1f02ac4a-ec9f-6524-8002-8f7b0bbeed0e

('write_joke',)
1f02ac4a-ce2a-6494-8001-cb2e2d651227

('generate_topic',)
1f02ac4a-a4e0-630d-8000-b73c254ba748

('__start__',)
1f02ac4a-a4dd-665e-bfff-e6c8c44315d9

# This is the state before last (states are listed in chronological order)
selected_state = states[1]
print(selected_state.next)
print(selected_state.values)

Output:

('write_joke',)
{'topic': 'How about "The Secret Life of Socks in the Dryer"? You know, exploring the mysterious phenomenon of how socks go into the laundry as pairs but come out as singles. Where do they go? Are they starting new lives elsewhere? Is there a sock paradise we don\\'t know about? There\\'s a lot of comedic potential in the everyday mystery that unites us all!'}

3. Update the state (optional)

update_state will create a new checkpoint. The new checkpoint will be associated with the same thread, but a new checkpoint ID.

new_config = graph.update_state(selected_state.config, values={"topic": "chickens"})
print(new_config)

Output:

{'configurable': {'thread_id': 'c62e2e03-c27b-4cb6-8cea-ea9bfedae006', 'checkpoint_ns': '', 'checkpoint_id': '1f02ac4a-ecee-600b-8002-a1d21df32e4c'}}

4. Resume execution from the checkpoint

For resumings execution from the selected checkpoint, call invoke with the config that points to the new checkpoint.

graph.invoke(None, new_config)

Output:

{'topic': 'chickens',
 'joke': 'Why did the chicken join a band?\n\nBecause it had excellent drumsticks!'}

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.