Files
langgraphjs/libs/sdk-react
github-actions[bot] 659d628d19 chore: version packages (#2704)
This PR was opened by the [Changesets
release](https://github.com/changesets/action) GitHub action. When
you're ready to do a release, you can merge this and the packages will
be published to npm automatically. If you're not ready to do a release
yet, that's fine, whenever you add more changesets to main, this PR will
be updated.


# Releases
## @langchain/langgraph@1.4.11

### Patch Changes

- [#2706](https://github.com/langchain-ai/langgraphjs/pull/2706)
[`eaa5472`](https://github.com/langchain-ai/langgraphjs/commit/eaa5472fa480fad2671659d1c9ed0686a55d42bd)
Thanks [@zduric-langchain](https://github.com/zduric-langchain)! -
fix(langgraph): dedupe merged callback handlers by identity

`mergeCallbacks` concatenated `handlers` and `inheritableHandlers` while
deduping `tags`, so a handler inherited by both the ambient and the
explicit
config picked up an extra registration at every graph boundary. With
tracing
  on, a nested `streamMode: "messages"` run delivered every token twice.

- Updated dependencies
[[`3ce9f8d`](https://github.com/langchain-ai/langgraphjs/commit/3ce9f8d11dd64b1d091a25162603c49e6f4a426f),
[`51b4202`](https://github.com/langchain-ai/langgraphjs/commit/51b42020f7c730a15193aa907056881e3d961924),
[`a86f813`](https://github.com/langchain-ai/langgraphjs/commit/a86f813954e010fbf30711c37baa5c53444613d5)]:
  - @langchain/langgraph-sdk@1.9.30
## @langchain/langgraph-sdk@1.9.30

### Patch Changes

- [#2691](https://github.com/langchain-ai/langgraphjs/pull/2691)
[`3ce9f8d`](https://github.com/langchain-ai/langgraphjs/commit/3ce9f8d11dd64b1d091a25162603c49e6f4a426f)
Thanks [@christian-bromann](https://github.com/christian-bromann)! -
fix(sdk): clear messages on hydrate(null) with a pending interrupt

  Teardown awaited the paused root pump, so threadId went null while
  the old conversation stayed on screen. Reset the snapshot first.

- [#2703](https://github.com/langchain-ai/langgraphjs/pull/2703)
[`51b4202`](https://github.com/langchain-ai/langgraphjs/commit/51b42020f7c730a15193aa907056881e3d961924)
Thanks [@christian-bromann](https://github.com/christian-bromann)! -
fix(sdk): keep isLoading true across interrupt→running hydration

Deferred terminal resets no longer clear isLoading when a newer running
lifecycle has already arrived (HITL resume / SSE replay).

- [#2692](https://github.com/langchain-ai/langgraphjs/pull/2692)
[`a86f813`](https://github.com/langchain-ai/langgraphjs/commit/a86f813954e010fbf30711c37baa5c53444613d5)
Thanks [@christian-bromann](https://github.com/christian-bromann)! -
fix(sdk): adopt server metadata on same-id optimistic message echo

  When a `values` snapshot echoes an optimistic human with the same
  content plus committed `additional_kwargs` (e.g. attachment paths),
  `stream.messages` now takes the server copy instead of keeping the
  plain optimistic message until hydration. Preferring is asymmetric:
  lagging or poorer values snapshots do not strip richer current
  metadata. In-flight AI token streaming is unchanged: streamed content
  still wins when it has moved past the snapshot.
## @langchain/angular@1.0.31

### Patch Changes

- Updated dependencies
[[`3ce9f8d`](https://github.com/langchain-ai/langgraphjs/commit/3ce9f8d11dd64b1d091a25162603c49e6f4a426f),
[`51b4202`](https://github.com/langchain-ai/langgraphjs/commit/51b42020f7c730a15193aa907056881e3d961924),
[`a86f813`](https://github.com/langchain-ai/langgraphjs/commit/a86f813954e010fbf30711c37baa5c53444613d5)]:
  - @langchain/langgraph-sdk@1.9.30
## @langchain/react@1.0.31

### Patch Changes

- Updated dependencies
[[`3ce9f8d`](https://github.com/langchain-ai/langgraphjs/commit/3ce9f8d11dd64b1d091a25162603c49e6f4a426f),
[`51b4202`](https://github.com/langchain-ai/langgraphjs/commit/51b42020f7c730a15193aa907056881e3d961924),
[`a86f813`](https://github.com/langchain-ai/langgraphjs/commit/a86f813954e010fbf30711c37baa5c53444613d5)]:
  - @langchain/langgraph-sdk@1.9.30
## @langchain/svelte@1.0.31

### Patch Changes

- Updated dependencies
[[`3ce9f8d`](https://github.com/langchain-ai/langgraphjs/commit/3ce9f8d11dd64b1d091a25162603c49e6f4a426f),
[`51b4202`](https://github.com/langchain-ai/langgraphjs/commit/51b42020f7c730a15193aa907056881e3d961924),
[`a86f813`](https://github.com/langchain-ai/langgraphjs/commit/a86f813954e010fbf30711c37baa5c53444613d5)]:
  - @langchain/langgraph-sdk@1.9.30
## @langchain/vue@1.0.31

### Patch Changes

- Updated dependencies
[[`3ce9f8d`](https://github.com/langchain-ai/langgraphjs/commit/3ce9f8d11dd64b1d091a25162603c49e6f4a426f),
[`51b4202`](https://github.com/langchain-ai/langgraphjs/commit/51b42020f7c730a15193aa907056881e3d961924),
[`a86f813`](https://github.com/langchain-ai/langgraphjs/commit/a86f813954e010fbf30711c37baa5c53444613d5)]:
  - @langchain/langgraph-sdk@1.9.30

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-08-19 12:36:59 -07:00
..
2026-08-19 12:36:59 -07:00
2026-08-19 12:36:59 -07:00

@langchain/react

React SDK for building AI-powered applications with Deep Agents, LangChain and LangGraph.

@langchain/react v1 ships a v2-native useStream hook together with a small family of companion selector hooks. The root hook gives you always-on access to thread state, messages, tool calls, and interrupts; the selector hooks open ref-counted subscriptions for the things that aren't needed on every view (per-subagent messages, media streams, submission queue, message metadata, raw channels, …).

Highlights

  • v2-native streaming protocol. Session-based transport with automatic re-attach on remount; no more reconnectOnMount / joinStream dance.
  • Selector-based subscriptions. Namespaced data (subagents, subgraphs, media) streams only when a component actually mounts the matching selector hook, and releases on unmount.
  • Always-on root projections. values, messages, toolCalls, and interrupts are live at the root with zero per-subscription cost.
  • Agent-brand type inference. useStream<typeof agent>() unwraps state, tool calls, and subagent state maps from an agent brand.
  • Discriminated options. The hosted Agent Server path and the custom-adapter path are two arms of a single typed union — mixing them is a compile-time error.
  • Multimodal media streams. Built-in assembly for audio, images, video, and files.
  • Suspense integration. useSuspenseStream hands the initial hydration phase to <Suspense> and non-streaming errors to Error Boundaries.

Installation

npm install @langchain/react @langchain/core

Peer dependencies: react (^18 || ^19), @langchain/core (^1.1.27).

Quick Start

import { useStream } from "@langchain/react";

function Chat() {
  const { messages, submit, isLoading } = useStream({
    assistantId: "agent",
    apiUrl: "http://localhost:2024",
  });

  return (
    <div>
      {messages.map((msg, i) => (
        <div key={msg.id ?? i}>{String(msg.content)}</div>
      ))}

      <button
        disabled={isLoading}
        onClick={() =>
          void submit({
            messages: [{ type: "human", content: "Hello!" }],
          })
        }
      >
        Send
      </button>
    </div>
  );
}

Mental model

@langchain/react v1 splits the surface into two layers:

  1. Root hook (useStream). Owns the thread lifecycle, the transport, and a handful of always-on projections (values, messages, toolCalls, interrupts, error, isLoading, discovery maps). Mount it once per thread.
  2. Companion selector hooks. Each one opens a ref-counted subscription when the first component mounts it and releases it when the last consumer unmounts. Use them for anything scoped to a namespace, a subagent / subgraph, a specific message, a specific extension channel, or a media stream.
import {
  useStream,
  useMessages,
  useToolCalls,
  useSubmissionQueue,
} from "@langchain/react";

function Chat() {
  const stream = useStream({ assistantId: "agent", apiUrl: "/api" });

  // Root: free reads, no new subscription.
  const messages = useMessages(stream); // same as stream.messages

  // Scoped: opens a namespaced subscription on mount.
  const queue = useSubmissionQueue(stream);
}

Documentation

Detailed guides live in ./docs. Start with the two files most apps need first:

  • useStream — options, return shape, submit(), stop(), respond(), hydrationPromise.
  • Companion selector hooksuseValues, useMessages, useToolCalls, useMessageMetadata, useChannel, useExtension, and friends.

Feature-specific guides:

Migrating from v0 to v1

The useStream import name is unchanged, but the return shape, option bag, and protocol semantics all shifted. Most chat apps migrate in well under an hour — the full migration guide with line-by-line diffs lives in ./docs/v1-migration.md.

Legacy type aliases (UseStream, UseSuspenseStream, UseStreamOptions, UseStreamTransport, QueueEntry, GetToolCallsType, SubagentStream, …) and the legacy FetchStreamTransport class are no longer re-exported from @langchain/react. Apps still on the legacy surface can import directly from @langchain/langgraph-sdk/ui during their migration.

Playground

For complete end-to-end examples with full agentic UIs, visit the LangChain UI Playground.

License

MIT