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
    LangGraph Store
    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
    LangGraph Store
    Checkpoint Postgres
    Store Postgres
    Checkpoint SQLite
    LangGraph Prebuilt
    LangGraph CLI
    LangGraph SDK
    LangGraph Supervisor
    LangGraph Swarm
    Language
    Theme
    PythonlanggraphtypesTaskPayload
    Classā—Since v1.1

    TaskPayload

    Payload for a task start event.

    Copy
    TaskPayload()

    Bases

    TypedDict

    Constructors

    Attributes

    View source on GitHub
    constructor
    __init__
    NameType
    idstr
    namestr
    inputAny
    triggerslist[str]
    metadataNotRequired[dict[str, Any]]
    attribute
    id: str

    Unique identifier for this task.

    attribute
    name: str

    Name of the node being executed.

    attribute
    input: Any

    Input data passed to the task.

    attribute
    triggers: list[str]

    List of triggers that caused this task to be executed (e.g. channel writes).

    attribute
    metadata: NotRequired[dict[str, Any]]

    Framework-resolved metadata associated with the task.

    Generic dict carrier following the messages-stream pattern. Populated by map_debug_tasks from task.config["metadata"] when non-empty, so the same keys stream_mode="messages" consumers see (e.g. lc_agent_name, langgraph_node, langgraph_step) are available to stream transformers.

    Consumers should ignore unrecognized keys.