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-api@1.2.5 ### Patch Changes - [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): forward named custom stream channels consistently Forward remote `StreamChannel` emissions as `custom:<name>` protocol events and normalize them back to custom-channel payloads in the API session. This aligns JavaScript stream-channel forwarding with the protocol subscription shape used by remote clients, so `custom:<name>` subscriptions receive extension channel data consistently. - Updated dependencies \[]: - @langchain/langgraph-ui@1.2.5 ## @langchain/langgraph-cli@1.2.5 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f)]: - @langchain/langgraph-api@1.2.5 ## @langchain/langgraph@1.3.6 ### Patch Changes - [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): forward named custom stream channels consistently Forward remote `StreamChannel` emissions as `custom:<name>` protocol events and normalize them back to custom-channel payloads in the API session. This aligns JavaScript stream-channel forwarding with the protocol subscription shape used by remote clients, so `custom:<name>` subscriptions receive extension channel data consistently. - Updated dependencies \[[`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph-sdk@1.9.17 ## @langchain/langgraph-sdk@1.9.17 ### Patch Changes - [#2494](https://github.com/langchain-ai/langgraphjs/pull/2494) [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): revive automatic optimistic submit echo Echo `submit()` input into `values` / `messages` immediately with client-side id minting and id-based reconciliation as the server streams back. Expose per-message `optimisticStatus` via message metadata (`pending` → `sent` / `failed`), shallow-merge non-message keys with rollback when no `values` arrive, and add an `optimistic: false` hook opt-out. Plumb through React, Vue, Svelte, and Angular with browser e2e coverage. - [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): coalesce duplicate thread read requests Coalesce concurrent identical `threads.getState()` and `threads.getHistory()` reads within the SDK client so transient remounts do not issue duplicate hydrate requests. Request identity includes the prepared URL, body, method, and headers, and coalescing is skipped for caller-provided abort signals, raw response reads, and `onRequest` hooks to preserve auth and cancellation isolation. - [#2497](https://github.com/langchain-ai/langgraphjs/pull/2497) [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): reconcile subagents and subgraphs on thread reconnect Seed deep-agent subagent cards from checkpoint messages and subgraph hosts from a single bounded `getHistory` read during `hydrate()`, so parallel fan-out discovery reappears immediately on refresh instead of waiting for SSE replay. Subagent execution namespaces are promoted through the existing guarded discovery state machine (bulk at hydrate, lazily per opened card via the selector layer). The getHistory cost is O(1) in requests regardless of fan-out width. ## @langchain/angular@1.0.17 ### Patch Changes - [#2494](https://github.com/langchain-ai/langgraphjs/pull/2494) [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): revive automatic optimistic submit echo Echo `submit()` input into `values` / `messages` immediately with client-side id minting and id-based reconciliation as the server streams back. Expose per-message `optimisticStatus` via message metadata (`pending` → `sent` / `failed`), shallow-merge non-message keys with rollback when no `values` arrive, and add an `optimistic: false` hook opt-out. Plumb through React, Vue, Svelte, and Angular with browser e2e coverage. - [#2497](https://github.com/langchain-ai/langgraphjs/pull/2497) [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): reconcile subagents and subgraphs on thread reconnect Seed deep-agent subagent cards from checkpoint messages and subgraph hosts from a single bounded `getHistory` read during `hydrate()`, so parallel fan-out discovery reappears immediately on refresh instead of waiting for SSE replay. Subagent execution namespaces are promoted through the existing guarded discovery state machine (bulk at hydrate, lazily per opened card via the selector layer). The getHistory cost is O(1) in requests regardless of fan-out width. - Updated dependencies \[[`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph-sdk@1.9.17 ## @langchain/react@1.0.17 ### Patch Changes - [#2494](https://github.com/langchain-ai/langgraphjs/pull/2494) [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): revive automatic optimistic submit echo Echo `submit()` input into `values` / `messages` immediately with client-side id minting and id-based reconciliation as the server streams back. Expose per-message `optimisticStatus` via message metadata (`pending` → `sent` / `failed`), shallow-merge non-message keys with rollback when no `values` arrive, and add an `optimistic: false` hook opt-out. Plumb through React, Vue, Svelte, and Angular with browser e2e coverage. - [#2497](https://github.com/langchain-ai/langgraphjs/pull/2497) [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): reconcile subagents and subgraphs on thread reconnect Seed deep-agent subagent cards from checkpoint messages and subgraph hosts from a single bounded `getHistory` read during `hydrate()`, so parallel fan-out discovery reappears immediately on refresh instead of waiting for SSE replay. Subagent execution namespaces are promoted through the existing guarded discovery state machine (bulk at hydrate, lazily per opened card via the selector layer). The getHistory cost is O(1) in requests regardless of fan-out width. - Updated dependencies \[[`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph-sdk@1.9.17 ## @langchain/svelte@1.0.17 ### Patch Changes - [#2494](https://github.com/langchain-ai/langgraphjs/pull/2494) [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): revive automatic optimistic submit echo Echo `submit()` input into `values` / `messages` immediately with client-side id minting and id-based reconciliation as the server streams back. Expose per-message `optimisticStatus` via message metadata (`pending` → `sent` / `failed`), shallow-merge non-message keys with rollback when no `values` arrive, and add an `optimistic: false` hook opt-out. Plumb through React, Vue, Svelte, and Angular with browser e2e coverage. - [#2497](https://github.com/langchain-ai/langgraphjs/pull/2497) [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): reconcile subagents and subgraphs on thread reconnect Seed deep-agent subagent cards from checkpoint messages and subgraph hosts from a single bounded `getHistory` read during `hydrate()`, so parallel fan-out discovery reappears immediately on refresh instead of waiting for SSE replay. Subagent execution namespaces are promoted through the existing guarded discovery state machine (bulk at hydrate, lazily per opened card via the selector layer). The getHistory cost is O(1) in requests regardless of fan-out width. - Updated dependencies \[[`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph-sdk@1.9.17 ## @langchain/vue@1.0.17 ### Patch Changes - [#2494](https://github.com/langchain-ai/langgraphjs/pull/2494) [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): revive automatic optimistic submit echo Echo `submit()` input into `values` / `messages` immediately with client-side id minting and id-based reconciliation as the server streams back. Expose per-message `optimisticStatus` via message metadata (`pending` → `sent` / `failed`), shallow-merge non-message keys with rollback when no `values` arrive, and add an `optimistic: false` hook opt-out. Plumb through React, Vue, Svelte, and Angular with browser e2e coverage. - [#2497](https://github.com/langchain-ai/langgraphjs/pull/2497) [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): reconcile subagents and subgraphs on thread reconnect Seed deep-agent subagent cards from checkpoint messages and subgraph hosts from a single bounded `getHistory` read during `hydrate()`, so parallel fan-out discovery reappears immediately on refresh instead of waiting for SSE replay. Subagent execution namespaces are promoted through the existing guarded discovery state machine (bulk at hydrate, lazily per opened card via the selector layer). The getHistory cost is O(1) in requests regardless of fan-out width. - Updated dependencies \[[`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph-sdk@1.9.17 ## @langchain/langgraph-ui@1.2.5 ## @example/ai-elements@0.1.32 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph@1.3.6 - @langchain/react@1.0.17 ## @examples/assistant-ui-claude@0.1.32 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph@1.3.6 - @langchain/react@1.0.17 ## @examples/ui-angular@0.0.42 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph@1.3.6 - @langchain/langgraph-sdk@1.9.17 - @langchain/angular@1.0.17 ## @examples/ui-multimodal@0.0.18 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph@1.3.6 - @langchain/react@1.0.17 ## @examples/ui-react@0.0.18 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`0a0e04e`](https://github.com/langchain-ai/langgraphjs/commit/0a0e04e9ff7e82fd08411cc0094e1f94729a1e1e), [`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f), [`a9aa8d6`](https://github.com/langchain-ai/langgraphjs/commit/a9aa8d6a9b23f5f7d4c56889fa68697b1e076b31)]: - @langchain/langgraph@1.3.6 - @langchain/langgraph-sdk@1.9.17 - @langchain/react@1.0.17 ## langgraph@1.0.38 ### Patch Changes - Updated dependencies \[[`658a076`](https://github.com/langchain-ai/langgraphjs/commit/658a076d5b50af9f5b96ab99f26ed629da6e182f)]: - @langchain/langgraph@1.3.6 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@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/joinStreamdance. - 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, andinterruptsare 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.
useSuspenseStreamhands 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:
- 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. - 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 hooks —
useValues,useMessages,useToolCalls,useMessageMetadata,useChannel,useExtension, and friends.
Feature-specific guides:
- Transports — SSE, WebSocket,
HttpAgentServerAdapter, customAgentServerAdapter. - Custom transports — implementing
AgentServerAdapteragainst your own backend, with a worked walkthrough ofexamples/ui-react-transport. - Interrupts & headless tools — pausing runs,
respond(),tools+onTool. - Fork / edit from a checkpoint —
useMessageMetadata+submit({ forkFrom }). - Submission queue —
multitaskStrategy: "enqueue"+useSubmissionQueue. - Subagents & subgraphs — discovery maps, scoped selector subscriptions.
- Multimodal media —
useAudio/useImages/useVideo/useFiles,useMediaURL, players. useSuspenseStream— Suspense + Error Boundary integration.StreamProvider/useStreamContext— share one stream across a subtree.- Type safety — agent-brand inference, prop-drilling, type helpers.
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