LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
    • Overview
    • Graphs
    • Functional API
    • Pregel
    • Checkpointing
    • Storage
    • Caching
    • Types
    • Runtime
    • Config
    • Errors
    • Constants
    • Channels
    • Agents
    LangGraph Checkpoint
    Checkpoint Postgres
    Store Postgres
    Checkpoint SQLite
    LangGraph Prebuilt
    LangGraph CLI
    LangGraph SDK
    LangGraph Supervisor
    LangGraph Swarm
    ⌘I

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

    OverviewGraphsFunctional APIPregelCheckpointingStorageCachingTypesRuntimeConfigErrorsConstantsChannelsAgents
    LangGraph Checkpoint
    Checkpoint Postgres
    Store Postgres
    Checkpoint SQLite
    LangGraph Prebuilt
    LangGraph CLI
    LangGraph SDK
    LangGraph Supervisor
    LangGraph Swarm
    Language
    Theme
    PythonlanggraphstreamtransformersUpdatesTransformer
    Class●Since v1.1

    UpdatesTransformer

    Copy
    UpdatesTransformer(
        self,
        scope: tuple[str, ...] = (),
    )

    Bases

    StreamTransformer

    Constructors

    Attributes

    Methods

    Inherited fromStreamTransformer

    Attributes

    Arequires_async: boolAsupports_sync: boolAscope: tuple[str, ...]

    Methods

    Maprocess
    —

    Handle an event on the async lane.

    View source on GitHub
    Mfinalize
    —

    Called when the run ends normally (sync lane).

    Mafinalize
    —

    Called when the run ends normally (async lane).

    Mfail
    —

    Called when the run ends with an error (sync lane).

    Mafail
    —

    Called when the run ends with an error (async lane).

    Mschedule
    —

    Schedule a coroutine tied to this transformer's lifecycle.

    constructor
    __init__
    NameType
    scopetuple[str, ...]
    attribute
    required_stream_modes
    method
    init
    method
    process

    Capture updates events as a drainable stream of node outputs.

    Surfaces stream_mode="updates" data on run.updates as a StreamChannel[dict[str, Any]]. Each item is a dict mapping a node (or task) name to the update it returned after a step.

    Only events at the run's own scope are captured; updates from deeper subgraphs are available on the respective subgraph handle's .updates projection.

    Native transformer — run.updates is a direct attribute.