Command: Update State and Route Together

Routing inside the node

A node can return a Command(update=..., goto=...) instead of a plain dict: it updates the state and names the next node. This is useful when the node that did the work is best placed to decide what happens next, and it is the basis of hand-offs between agents (an agent routes to another agent with the data it gathered). Annotate the return type, for example Command[Literal["writer", "__end__"]], so the graph can be drawn and validated. Conditional edges and Command can coexist; use Command for dynamic hand-offs, edges for fixed structure.

A supervisor routing with Command, run

I ran this offline with langgraph 1.2.12 and langchain-core 1.6.6 in a Python virtual environment. No API key or model is needed because plain Python functions stand in for the model, so the output is repeatable. The supervisor sends research tasks to researcher and others to writer; each worker updates result and hands control back, and the supervisor ends the run once a result exists.

from typing import Literal, TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.types import Command

class State(TypedDict):
    task: str
    result: str

def supervisor(state) -> Command[Literal["researcher", "writer", "__end__"]]:
    if not state.get("result"):
        return Command(goto="researcher" if "find" in state["task"] else "writer")
    return Command(goto=END)

def researcher(state) -> Command[Literal["supervisor"]]:
    return Command(update={"result": "facts about " + state["task"]}, goto="supervisor")

def writer(state) -> Command[Literal["supervisor"]]:
    return Command(update={"result": "draft for " + state["task"]}, goto="supervisor")

g = StateGraph(State)
g.add_node("supervisor", supervisor); g.add_node("researcher", researcher); g.add_node("writer", writer)
g.add_edge(START, "supervisor")
app = g.compile()
for task in ("find the 2025 leave policy", "write a welcome note"):
    print(task, "->", app.invoke({"task": task, "result": ""})["result"])

Output:

find the 2025 leave policy -> facts about find the 2025 leave policy
write a welcome note -> draft for write a welcome note

Annotate the Command return type

Literal node names in the annotation let LangGraph draw and validate the possible destinations.

Quick check: What does returning Command(update=..., goto=...) do?

• Calls the model twice
• Deletes the graph
• Updates the state and chooses the next node in one step
• Sets the recursion limit