Time travel using the server API

LangGraph provides the time travel functionality to 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 time travel using the LangGraph Server API (via the LangGraph SDK):

1. Run the graph with initial inputs using LangGraph SDK’s client.runs.wait or client.runs.stream APIs.
2. Identify a checkpoint in an existing thread: Use client.threads.get_history method to retrieve the execution history for a specific thread_id and locate the desired checkpoint_id. Alternatively, set a breakpoint before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that breakpoint.
3. (Optional) modify the graph state: Use the client.threads.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 client.runs.wait or client.runs.stream APIs with an input of None and the appropriate thread_id and checkpoint_id.

Use time travel in a workflow

Example graph

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]

llm = init_chat_model(
    "anthropic:claude-3-7-sonnet-latest",
    temperature=0,
)

def generate_topic(state: State):
    """LLM call to generate a topic for the joke"""
    msg = llm.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 = llm.invoke(f"Write a short joke about {state['topic']}")
    return {"joke": msg.content}

# Build workflow
builder = StateGraph(State)

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

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

# Compile
graph = builder.compile()

1. Run the graph

Python

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
result = await client.runs.wait(
    thread_id,
    assistant_id,
    input={}
)

2. Identify a checkpoint

Python

# The states are returned in reverse chronological order.
states = await client.threads.get_history(thread_id)
selected_state = states[1]
print(selected_state)

3. Update the state

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

Python

new_config = await client.threads.update_state(
    thread_id,
    {"topic": "chickens"},
    checkpoint_id=selected_state["checkpoint_id"]
)
print(new_config)

4. Resume execution from the checkpoint

Python

await client.runs.wait(
    thread_id,
    assistant_id,
    input=None,
    checkpoint_id=new_config["checkpoint_id"]
)

Learn more

• LangGraph time travel guide: learn more about using time travel in LangGraph.