Menu
Language
Theme
Experimental. Batch reducer for use with DeltaChannel.
Processes all writes in one pass — dedup by ID and RemoveMessage
tombstoning — without calling messagesStateReducer.
This reducer is batching-invariant, as required by DeltaChannel:
reducer(reducer(state, xs), ys) === reducer(state, xs.concat(ys)).
Raw object / string inputs are coerced to typed BaseMessage objects so
that HTTP-driven graphs work without a separate coercion step. This is not
full messagesStateReducer parity — REMOVE_ALL_MESSAGES,
unknown-id RemoveMessage errors, and missing-id UUID assignment are not
handled here.
messagesDeltaReducer(
state: BaseMessage<MessageStructure<MessageToolSet>, MessageType>[],
writes: Messages[]
): BaseMessage<MessageStructure<MessageToolSet>, MessageType>[]| Name | Type | Description |
|---|---|---|
state* | BaseMessage<MessageStructure<MessageToolSet>, MessageType>[] | The current accumulated list of messages. |
writes* | Messages[] | Batch of writes, each a single message-like or an array. |
import { DeltaChannel, messagesDeltaReducer } from "@langchain/langgraph";
const channel = new DeltaChannel(messagesDeltaReducer);