Streaming

For new applications, we recommend event streaming—the typed-projection API introduced in LangGraph v1.2. Event streaming gives you separate iterators per projection (messages, values, subgraphs, output) so you can consume them independently instead of branching on stream_mode chunks.

This page covers LangGraph’s stream-mode API. It exposes graph execution through stream modes such as updates, values, messages, custom, checkpoints, tasks, and debug. Use it when you need direct access to graph-runtime events or specific stream-mode output.

Get started

Basic usage

LangGraph graphs expose the stream method to yield streamed outputs as iterators.

for await (const chunk of await graph.stream(inputs, {
  streamMode: "updates",
})) {
  console.log(chunk);
}

Debug streaming events, inspect token-by-token LLM output, and monitor latency with LangSmith. Follow the tracing quickstart to get set up.

Stream modes

Pass one or more of the following stream modes as a list to the stream method:

Mode	Description
values	Full state after each step.
updates	State updates after each step. Multiple updates in the same step are streamed separately.
messages	2-tuples of (LLM token, metadata) from LLM calls.
custom	Custom data emitted from nodes via the writer config parameter.
tools	Tool-call lifecycle events (on_tool_start, on_tool_event, on_tool_end, on_tool_error).
debug	All available info throughout graph execution.

Graph state

Use the stream modes updates and values to stream the state of the graph as it executes.

• updates streams the updates to the state after each step of the graph.
• values streams the full value of the state after each step of the graph.

import { StateGraph, StateSchema, START, END } from "@langchain/langgraph";
import { z } from "zod/v4";

const State = new StateSchema({
  topic: z.string(),
  joke: z.string(),
});

const graph = new StateGraph(State)
  .addNode("refineTopic", (state) => {
    return { topic: state.topic + " and cats" };
  })
  .addNode("generateJoke", (state) => {
    return { joke: `This is a joke about ${state.topic}` };
  })
  .addEdge(START, "refineTopic")
  .addEdge("refineTopic", "generateJoke")
  .addEdge("generateJoke", END)
  .compile();

updates

Use this to stream only the state updates returned by the nodes after each step. The streamed outputs include the name of the node as well as the update.

for await (const chunk of await graph.stream(
  { topic: "ice cream" },
  { streamMode: "updates" }
)) {
  for (const [nodeName, state] of Object.entries(chunk)) {
    console.log(`Node ${nodeName} updated:`, state);
  }
}

values

Use this to stream the full state of the graph after each step.

for await (const chunk of await graph.stream(
  { topic: "ice cream" },
  { streamMode: "values" }
)) {
  console.log(`topic: ${chunk.topic}, joke: ${chunk.joke}`);
}

LLM tokens

Use the messages streaming mode to stream Large Language Model (LLM) outputs token by token from any part of your graph, including nodes, tools, subgraphs, or tasks.

The streamed output from messages mode is a tuple [message_chunk, metadata] where:

• message_chunk: the token or message segment from the LLM.
• metadata: a dictionary containing details about the graph node and LLM invocation.

If your LLM is not available as a LangChain integration, you can stream its outputs using custom mode instead. See use with any LLM for details.

import { ChatOpenAI } from "@langchain/openai";
import { StateGraph, StateSchema, GraphNode, START } from "@langchain/langgraph";
import * as z from "zod";

const MyState = new StateSchema({
  topic: z.string(),
  joke: z.string().default(""),
});

const model = new ChatOpenAI({ model: "gpt-5.4-mini" });

const callModel: GraphNode<typeof MyState> = async (state) => {
  // Call the LLM to generate a joke about a topic
  // Note that message events are emitted even when the LLM is run using .invoke rather than .stream
  const modelResponse = await model.invoke([
    { role: "user", content: `Generate a joke about ${state.topic}` },
  ]);
  return { joke: modelResponse.content };
};

const graph = new StateGraph(MyState)
  .addNode("callModel", callModel)
  .addEdge(START, "callModel")
  .compile();

// The "messages" stream mode returns an iterator of tuples [messageChunk, metadata]
// where messageChunk is the token streamed by the LLM and metadata is a dictionary
// with information about the graph node where the LLM was called and other information
for await (const [messageChunk, metadata] of await graph.stream(
  { topic: "ice cream" },
  { streamMode: "messages" }
)) {
  if (messageChunk.content) {
    console.log(messageChunk.content + "|");
  }
}

Filter by LLM invocation

You can associate tags with LLM invocations to filter the streamed tokens by LLM invocation.

import { ChatOpenAI } from "@langchain/openai";

// model1 is tagged with "joke"
const model1 = new ChatOpenAI({
  model: "gpt-5.4-mini",
  tags: ['joke']
});
// model2 is tagged with "poem"
const model2 = new ChatOpenAI({
  model: "gpt-5.4-mini",
  tags: ['poem']
});

const graph = // ... define a graph that uses these LLMs

// The streamMode is set to "messages" to stream LLM tokens
// The metadata contains information about the LLM invocation, including the tags
for await (const [msg, metadata] of await graph.stream(
  { topic: "cats" },
  { streamMode: "messages" }
)) {
  // Filter the streamed tokens by the tags field in the metadata to only include
  // the tokens from the LLM invocation with the "joke" tag
  if (metadata.tags?.includes("joke")) {
    console.log(msg.content + "|");
  }
}

Extended example: filtering by tags

import { ChatOpenAI } from "@langchain/openai";
import { StateGraph, StateSchema, GraphNode, START } from "@langchain/langgraph";
import * as z from "zod";

// The jokeModel is tagged with "joke"
const jokeModel = new ChatOpenAI({
  model: "gpt-5.4-mini",
  tags: ["joke"]
});
// The poemModel is tagged with "poem"
const poemModel = new ChatOpenAI({
  model: "gpt-5.4-mini",
  tags: ["poem"]
});

const State = new StateSchema({
  topic: z.string(),
  joke: z.string(),
  poem: z.string(),
});

const callModel: GraphNode<typeof State> = async (state) => {
  const topic = state.topic;
  console.log("Writing joke...");

  const jokeResponse = await jokeModel.invoke([
    { role: "user", content: `Write a joke about ${topic}` }
  ]);

  console.log("\n\nWriting poem...");
  const poemResponse = await poemModel.invoke([
    { role: "user", content: `Write a short poem about ${topic}` }
  ]);

  return {
    joke: jokeResponse.content,
    poem: poemResponse.content
  };
};

const graph = new StateGraph(State)
  .addNode("callModel", callModel)
  .addEdge(START, "callModel")
  .compile();

// The streamMode is set to "messages" to stream LLM tokens
// The metadata contains information about the LLM invocation, including the tags
for await (const [msg, metadata] of await graph.stream(
  { topic: "cats" },
  { streamMode: "messages" }
)) {
  // Filter the streamed tokens by the tags field in the metadata to only include
  // the tokens from the LLM invocation with the "joke" tag
  if (metadata.tags?.includes("joke")) {
    console.log(msg.content + "|");
  }
}

Omit messages from the stream

Use the nostream tag to exclude LLM output from the stream entirely. Invocations tagged with nostream still run and produce output; their tokens are simply not emitted in messages mode.

This is useful when:

• You need LLM output for internal processing (for example structured output) but do not want to stream it to the client
• You stream the same content through a different channel (for example custom UI messages) and want to avoid duplicate output in the messages stream

import { ChatAnthropic } from "@langchain/anthropic";
import { StateGraph, StateSchema, START } from "@langchain/langgraph";
import * as z from "zod";

const streamModel = new ChatAnthropic({ model: "claude-haiku-4-5-20251001" });
const internalModel = new ChatAnthropic({
  model: "claude-haiku-4-5-20251001",
}).withConfig({
  tags: ["nostream"],
});

const State = new StateSchema({
  topic: z.string(),
  answer: z.string().optional(),
  notes: z.string().optional(),
});

const contentToText = (content: unknown): string => {
  if (typeof content === "string") {
    return content;
  }
  if (Array.isArray(content)) {
    return content
      .map((block) => {
        if (
          typeof block === "object" &&
          block !== null &&
          "text" in block &&
          typeof (block as { text?: unknown }).text === "string"
        ) {
          return (block as { text: string }).text;
        }
        return "";
      })
      .filter(Boolean)
      .join("\n");
  }
  return "";
};

const writeAnswer = async (state: typeof State.State) => {
  const r = await streamModel.invoke([
    { role: "user", content: `Reply briefly about ${state.topic}` },
  ]);
  return { answer: contentToText(r.content) };
};

const internalNotes = async (state: typeof State.State) => {
  // Tokens from this model are omitted from streamMode: "messages" because of nostream
  const r = await internalModel.invoke([
    { role: "user", content: `Private notes on ${state.topic}` },
  ]);
  return { notes: contentToText(r.content) };
};

const graph = new StateGraph(State)
  .addNode("writeAnswer", writeAnswer)
  .addNode("internal_notes", internalNotes)
  .addEdge(START, "writeAnswer")
  .addEdge("writeAnswer", "internal_notes")
  .compile();

const stream = await graph.streamEvents(
  { topic: "AI", answer: "", notes: "" },
  { version: "v3" },
);

Filter by node

To stream tokens only from specific nodes, use stream_mode="messages" and filter the outputs by the langgraph_node field in the streamed metadata:

// The "messages" stream mode returns a tuple of [messageChunk, metadata]
// where messageChunk is the token streamed by the LLM and metadata is a dictionary
// with information about the graph node where the LLM was called and other information
for await (const [msg, metadata] of await graph.stream(
  inputs,
  { streamMode: "messages" }
)) {
  // Filter the streamed tokens by the langgraph_node field in the metadata
  // to only include the tokens from the specified node
  if (msg.content && metadata.langgraph_node === "some_node_name") {
    // ...
  }
}

Extended example: streaming LLM tokens from specific nodes

import { ChatOpenAI } from "@langchain/openai";
import { StateGraph, StateSchema, GraphNode, START } from "@langchain/langgraph";
import * as z from "zod";

const model = new ChatOpenAI({ model: "gpt-5.4-mini" });

const State = new StateSchema({
  topic: z.string(),
  joke: z.string(),
  poem: z.string(),
});

const writeJoke: GraphNode<typeof State> = async (state) => {
  const topic = state.topic;
  const jokeResponse = await model.invoke([
    { role: "user", content: `Write a joke about ${topic}` }
  ]);
  return { joke: jokeResponse.content };
};

const writePoem: GraphNode<typeof State> = async (state) => {
  const topic = state.topic;
  const poemResponse = await model.invoke([
    { role: "user", content: `Write a short poem about ${topic}` }
  ]);
  return { poem: poemResponse.content };
};

const graph = new StateGraph(State)
  .addNode("writeJoke", writeJoke)
  .addNode("writePoem", writePoem)
  // write both the joke and the poem concurrently
  .addEdge(START, "writeJoke")
  .addEdge(START, "writePoem")
  .compile();

// The "messages" stream mode returns a tuple of [messageChunk, metadata]
// where messageChunk is the token streamed by the LLM and metadata is a dictionary
// with information about the graph node where the LLM was called and other information
for await (const [msg, metadata] of await graph.stream(
  { topic: "cats" },
  { streamMode: "messages" }
)) {
  // Filter the streamed tokens by the langgraph_node field in the metadata
  // to only include the tokens from the writePoem node
  if (msg.content && metadata.langgraph_node === "writePoem") {
    console.log(msg.content + "|");
  }
}

Custom data

To send custom user-defined data from inside a LangGraph node or tool, follow these steps:

1. Use the writer parameter from the LangGraphRunnableConfig to emit custom data.
2. Set streamMode: "custom" when calling .stream() to get the custom data in the stream. You can combine multiple modes (e.g., ["updates", "custom"]), but at least one must be "custom".

node

import { StateGraph, StateSchema, GraphNode, START, LangGraphRunnableConfig } from "@langchain/langgraph";
import * as z from "zod";

const State = new StateSchema({
  query: z.string(),
  answer: z.string(),
});

const node: GraphNode<typeof State> = async (state, config) => {
  // Use the writer to emit a custom key-value pair (e.g., progress update)
  config.writer({ custom_key: "Generating custom data inside node" });
  return { answer: "some data" };
};

const graph = new StateGraph(State)
  .addNode("node", node)
  .addEdge(START, "node")
  .compile();

const inputs = { query: "example" };

// Set streamMode: "custom" to receive the custom data in the stream
for await (const chunk of await graph.stream(inputs, { streamMode: "custom" })) {
  console.log(chunk);
}

tool

import { tool } from "@langchain/core/tools";
import { LangGraphRunnableConfig } from "@langchain/langgraph";
import * as z from "zod";

const queryDatabase = tool(
  async (input, config: LangGraphRunnableConfig) => {
    // Use the writer to emit a custom key-value pair (e.g., progress update)
    config.writer({ data: "Retrieved 0/100 records", type: "progress" });
    // perform query
    // Emit another custom key-value pair
    config.writer({ data: "Retrieved 100/100 records", type: "progress" });
    return "some-answer";
  },
  {
    name: "query_database",
    description: "Query the database.",
    schema: z.object({
      query: z.string().describe("The query to execute."),
    }),
  }
);

const graph = // ... define a graph that uses this tool

// Set streamMode: "custom" to receive the custom data in the stream
for await (const chunk of await graph.stream(inputs, { streamMode: "custom" })) {
  console.log(chunk);
}

Tool progress

Use the tools stream mode to receive real-time lifecycle events for tool executions. This is useful for showing progress indicators, partial results, and error states in your UI while tools are running.

The tools stream mode emits four event types:

Event	When	Payload
on_tool_start	Tool invocation begins	name, input, toolCallId
on_tool_event	Tool yields intermediate data	name, data, toolCallId
on_tool_end	Tool returns its final result	name, output, toolCallId
on_tool_error	Tool throws an error	name, error, toolCallId

Define tools that stream progress

To emit on_tool_event events, define your tool function as an async generator (async function*). Each yield sends intermediate data to the stream, and the return value is used as the tool’s final result.

import { tool } from "@langchain/core/tools";
import { z } from "zod/v4";

const searchFlights = tool(
  async function* (input) {
    const airlines = ["United", "Delta", "American", "JetBlue"];
    const completed: string[] = [];

    for (let i = 0; i < airlines.length; i++) {
      await new Promise((r) => setTimeout(r, 500));
      completed.push(airlines[i]);

      // Each yield emits an on_tool_event to the stream
      yield {
        message: `Searching ${airlines[i]}...`,
        progress: (i + 1) / airlines.length,
        completed,
      };
    }

    // The return value becomes the tool result (ToolMessage.content)
    return JSON.stringify({
      flights: [
        { airline: "United", price: 450, duration: "5h 30m" },
        { airline: "Delta", price: 520, duration: "5h 15m" },
      ],
    });
  },
  {
    name: "search_flights",
    description: "Search for available flights to a destination.",
    schema: z.object({
      destination: z.string(),
      date: z.string(),
    }),
  }
);

Existing tools that return a Promise are fully compatible. They emit on_tool_start and on_tool_end events but no on_tool_event events.

Consume tool events server-side

Pass streamMode: ["tools"] (or combine with other modes) to graph.stream():

for await (const [mode, chunk] of await graph.stream(
  { messages: [{ role: "user", content: "Find flights to Tokyo" }] },
  { streamMode: ["updates", "tools"] }
)) {
  if (mode === "tools") {
    switch (chunk.event) {
      case "on_tool_start":
        console.log(`Tool started: ${chunk.name}`, chunk.input);
        break;
      case "on_tool_event":
        console.log(`Tool progress: ${chunk.name}`, chunk.data);
        break;
      case "on_tool_end":
        console.log(`Tool finished: ${chunk.name}`, chunk.output);
        break;
      case "on_tool_error":
        console.error(`Tool failed: ${chunk.name}`, chunk.error);
        break;
    }
  }
}

Use tool progress in React with useStream

The useStream hook from @langchain/langgraph-sdk/react exposes a toolProgress array when you include "tools" in your stream modes. Each entry is a ToolProgress object that tracks the current state of a running tool:

Field	Description
name	The tool name
state	Current lifecycle state: "starting", "running", "completed", or "error"
toolCallId	The tool call ID from the LLM
input	The tool’s input arguments
data	The most recent yielded data from on_tool_event
result	The final result, set on on_tool_end
error	The error, set on on_tool_error

import { useStream } from "@langchain/langgraph-sdk/react";

function Chat() {
  const stream = useStream({
    assistantId: "my-agent",
    streamMode: ["values", "tools"],
  });

  // Filter for actively running tools
  const activeTools = stream.toolProgress.filter(
    (t) => t.state === "starting" || t.state === "running"
  );

  return (
    <div>
      {stream.messages.map((msg) => (
        <MessageBubble key={msg.id} message={msg} />
      ))}

      {/* Show progress cards for running tools */}
      {activeTools.map((tool) => (
        <ToolProgressCard
          key={tool.toolCallId ?? tool.name}
          name={tool.name}
          state={tool.state}
          data={tool.data}
        />
      ))}
    </div>
  );
}

Extended example: travel planning agent with tool progress

This example shows a complete agent with async-generator tools that stream search progress to a React UI.

Agent definition:

import { tool } from "@langchain/core/tools";
import { ChatOpenAI } from "@langchain/openai";
import { createAgent } from "@langchain/langgraph";
import { MemorySaver } from "@langchain/langgraph-checkpoint-memory";
import { z } from "zod/v4";

const searchFlights = tool(
  async function* (input) {
    const airlines = ["United", "Delta", "American", "JetBlue"];
    const completed: string[] = [];

    for (let i = 0; i < airlines.length; i++) {
      await new Promise((r) => setTimeout(r, 600));
      completed.push(`${airlines[i]}: checked`);
      yield {
        message: `Searching ${airlines[i]}...`,
        progress: (i + 1) / airlines.length,
        completed,
      };
    }

    return JSON.stringify({
      flights: [
        { airline: "United", price: 450, duration: "5h 30m" },
        { airline: "Delta", price: 520, duration: "5h 15m" },
      ],
    });
  },
  {
    name: "search_flights",
    description: "Search for available flights.",
    schema: z.object({
      destination: z.string(),
      departure_date: z.string(),
    }),
  }
);

const checkHotels = tool(
  async function* (input) {
    const hotels = ["Grand Hyatt", "Marriott", "Hilton"];
    const completed: string[] = [];

    for (let i = 0; i < hotels.length; i++) {
      await new Promise((r) => setTimeout(r, 400));
      completed.push(`${hotels[i]}: available`);
      yield {
        message: `Checking ${hotels[i]}...`,
        progress: (i + 1) / hotels.length,
        completed,
      };
    }

    return JSON.stringify({
      hotels: [
        { name: "Grand Hyatt", price: 250, rating: 4.5 },
        { name: "Marriott", price: 180, rating: 4.2 },
      ],
    });
  },
  {
    name: "check_hotels",
    description: "Check hotel availability.",
    schema: z.object({
      city: z.string(),
      check_in: z.string(),
      nights: z.number(),
    }),
  }
);

export const agent = createAgent({
  model: new ChatOpenAI({ model: "gpt-4o-mini" }),
  tools: [searchFlights, checkHotels],
  checkpointer: new MemorySaver(),
});

React component with progress cards:

import { useStream } from "@langchain/langgraph-sdk/react";

function TravelPlanner() {
  const stream = useStream<typeof agent>({
    assistantId: "travel-agent",
    streamMode: ["values", "tools"],
  });

  const activeTools = stream.toolProgress.filter(
    (t) => t.state === "starting" || t.state === "running"
  );

  return (
    <div>
      {stream.messages.map((msg) => (
        <div key={msg.id}>{msg.content}</div>
      ))}

      {activeTools.map((tool) => {
        const data = tool.data as {
          message?: string;
          progress?: number;
          completed?: string[];
        } | undefined;

        return (
          <div key={tool.toolCallId ?? tool.name}>
            <strong>{tool.name}</strong>
            {data?.message && <p>{data.message}</p>}
            {data?.progress != null && (
              <div style={{ width: "100%", background: "#eee" }}>
                <div
                  style={{
                    width: `${data.progress * 100}%`,
                    background: "#4CAF50",
                    height: 8,
                    transition: "width 0.3s ease",
                  }}
                />
              </div>
            )}
            {data?.completed?.map((step, i) => (
              <div key={i}>&#10003; {step}</div>
            ))}
          </div>
        );
      })}
    </div>
  );
}

tools vs custom stream mode

Both stream modes can surface tool progress, but they serve different purposes:

• tools—automatically emits structured lifecycle events (on_tool_start, on_tool_event, on_tool_end, on_tool_error) with no code changes needed in your tools beyond using async function*. The useStream hook provides the reactive toolProgress array out of the box.
• custom—gives you full control over what data is emitted and when using config.writer(). Use this when you need freeform data that doesn’t map to the tool lifecycle, or when you want to stream from nodes (not just tools).

Subgraph outputs

To include outputs from subgraphs in the streamed outputs, you can set subgraphs: true in the .stream() method of the parent graph. This will stream outputs from both the parent graph and any subgraphs.

The outputs will be streamed as tuples [namespace, data], where namespace is a tuple with the path to the node where a subgraph is invoked, e.g. ["parent_node:<task_id>", "child_node:<task_id>"].

for await (const chunk of await graph.stream(
  { foo: "foo" },
  {
    // Set subgraphs: true to stream outputs from subgraphs
    subgraphs: true,
    streamMode: "updates",
  }
)) {
  console.log(chunk);
}

Extended example: streaming from subgraphs

import { StateGraph, StateSchema, START } from "@langchain/langgraph";
import { z } from "zod/v4";

// Define subgraph
const SubgraphState = new StateSchema({
  foo: z.string(), // note that this key is shared with the parent graph state
  bar: z.string(),
});

const subgraphBuilder = new StateGraph(SubgraphState)
  .addNode("subgraphNode1", (state) => {
    return { bar: "bar" };
  })
  .addNode("subgraphNode2", (state) => {
    return { foo: state.foo + state.bar };
  })
  .addEdge(START, "subgraphNode1")
  .addEdge("subgraphNode1", "subgraphNode2");
const subgraph = subgraphBuilder.compile();

// Define parent graph
const ParentState = new StateSchema({
  foo: z.string(),
});

const builder = new StateGraph(ParentState)
  .addNode("node1", (state) => {
    return { foo: "hi! " + state.foo };
  })
  .addNode("node2", subgraph)
  .addEdge(START, "node1")
  .addEdge("node1", "node2");
const graph = builder.compile();

for await (const chunk of await graph.stream(
  { foo: "foo" },
  {
    streamMode: "updates",
    // Set subgraphs: true to stream outputs from subgraphs
    subgraphs: true,
  }
)) {
  console.log(chunk);
}

[[], {'node1': {'foo': 'hi! foo'}}]
[['node2:dfddc4ba-c3c5-6887-5012-a243b5b377c2'], {'subgraphNode1': {'bar': 'bar'}}]
[['node2:dfddc4ba-c3c5-6887-5012-a243b5b377c2'], {'subgraphNode2': {'foo': 'hi! foobar'}}]
[[], {'node2': {'foo': 'hi! foobar'}}]

Note that we are receiving not just the node updates, but we also the namespaces which tell us what graph (or subgraph) we are streaming from.

Debug

Use the debug streaming mode to stream as much information as possible throughout the execution of the graph. The streamed outputs include the name of the node as well as the full state.

for await (const chunk of await graph.stream(
  { topic: "ice cream" },
  { streamMode: "debug" }
)) {
  console.log(chunk);
}

Multiple modes at once

You can pass an array as the streamMode parameter to stream multiple modes at once.

The streamed outputs will be tuples of [mode, chunk] where mode is the name of the stream mode and chunk is the data streamed by that mode.

for await (const [mode, chunk] of await graph.stream(inputs, {
  streamMode: ["updates", "custom"],
})) {
  console.log(chunk);
}

Advanced

Use with any LLM

You can use streamMode: "custom" to stream data from any LLM API—even if that API does not implement the LangChain chat model interface.

This lets you integrate raw LLM clients or external services that provide their own streaming interfaces, making LangGraph highly flexible for custom setups.

import { StateGraph, GraphNode, StateSchema } from "@langchain/langgraph";
import * as z from "zod";

const State = new StateSchema({ result: z.string() });

const callArbitraryModel: GraphNode<typeof State> = async (state, config) => {
  // Example node that calls an arbitrary model and streams the output
  // Assume you have a streaming client that yields chunks
  // Generate LLM tokens using your custom streaming client
  for await (const chunk of yourCustomStreamingClient(state.topic)) {
    // Use the writer to send custom data to the stream
    config.writer({ custom_llm_chunk: chunk });
  }
  return { result: "completed" };
};

const graph = new StateGraph(State)
  .addNode("callArbitraryModel", callArbitraryModel)
  // Add other nodes and edges as needed
  .compile();

// Set streamMode: "custom" to receive the custom data in the stream
for await (const chunk of await graph.stream(
  { topic: "cats" },
  { streamMode: "custom" }
)) {
  // The chunk will contain the custom data streamed from the llm
  console.log(chunk);
}

Extended example: streaming arbitrary chat model

import { StateGraph, StateSchema, MessagesValue, GraphNode, START, LangGraphRunnableConfig } from "@langchain/langgraph";
import { tool } from "@langchain/core/tools";
import * as z from "zod";
import OpenAI from "openai";

const openaiClient = new OpenAI();
const modelName = "gpt-5.4-mini";

async function* streamTokens(modelName: string, messages: any[]) {
  const response = await openaiClient.chat.completions.create({
    messages,
    model: modelName,
    stream: true,
  });

  let role: string | null = null;
  for await (const chunk of response) {
    const delta = chunk.choices[0]?.delta;

    if (delta?.role) {
      role = delta.role;
    }

    if (delta?.content) {
      yield { role, content: delta.content };
    }
  }
}

// this is our tool
const getItems = tool(
  async (input, config: LangGraphRunnableConfig) => {
    let response = "";
    for await (const msgChunk of streamTokens(
      modelName,
      [
        {
          role: "user",
          content: `Can you tell me what kind of items i might find in the following place: '${input.place}'. List at least 3 such items separating them by a comma. And include a brief description of each item.`,
        },
      ]
    )) {
      response += msgChunk.content;
      config.writer?.(msgChunk);
    }
    return response;
  },
  {
    name: "get_items",
    description: "Use this tool to list items one might find in a place you're asked about.",
    schema: z.object({
      place: z.string().describe("The place to look up items for."),
    }),
  }
);

const State = new StateSchema({
  messages: MessagesValue,
});

const callTool: GraphNode<typeof State> = async (state) => {
  const aiMessage = state.messages.at(-1);
  const toolCall = aiMessage.tool_calls?.at(-1);

  const functionName = toolCall?.function?.name;
  if (functionName !== "get_items") {
    throw new Error(`Tool ${functionName} not supported`);
  }

  const functionArguments = toolCall?.function?.arguments;
  const args = JSON.parse(functionArguments);

  const functionResponse = await getItems.invoke(args);
  const toolMessage = {
    tool_call_id: toolCall.id,
    role: "tool",
    name: functionName,
    content: functionResponse,
  };
  return { messages: [toolMessage] };
};

const graph = new StateGraph(State)
  // this is the tool-calling graph node
  .addNode("callTool", callTool)
  .addEdge(START, "callTool")
  .compile();

Let’s invoke the graph with an AIMessage that includes a tool call:

const inputs = {
  messages: [
    {
      content: null,
      role: "assistant",
      tool_calls: [
        {
          id: "1",
          function: {
            arguments: '{"place":"bedroom"}',
            name: "get_items",
          },
          type: "function",
        }
      ],
    }
  ]
};

for await (const chunk of await graph.stream(
  inputs,
  { streamMode: "custom" }
)) {
  console.log(chunk.content + "|");
}

Disable streaming for specific chat models

If your application mixes models that support streaming with those that do not, you may need to explicitly disable streaming for models that do not support it.

Set streaming: false when initializing the model.

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  model: "o1-preview",
  // Set streaming: false to disable streaming for the chat model
  streaming: false,
});

Not all chat model integrations support the streaming parameter. If your model doesn’t support it, use disableStreaming: true instead. This parameter is available on all chat models via the base class.

---

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

Edit this page on GitHub or file an issue.