ADK for TypeScript: API Reference
    Preparing search index...

    Interface CreateNodeErrorEventParams

    Parameters for creating an event with partial fields.

    interface CreateNodeErrorEventParams {
        "[EVENT_SIGNATURE_SYMBOL]"?: true;
        actions?: Partial<EventActions>;
        attemptCount?: number;
        author?: string;
        branch?: string;
        citationMetadata?: CitationMetadata;
        content?: Content;
        customMetadata?: { [key: string]: unknown };
        error: unknown;
        errorCode?: string;
        errorMessage?: string;
        finishReason?: FinishReason;
        goAway?: LiveServerGoAway;
        groundingMetadata?: GroundingMetadata;
        id?: string;
        inputTranscription?: Transcription;
        interactionId?: string;
        interrupted?: boolean;
        invocationId?: string;
        isolationScope?: string;
        liveSessionId?: string;
        liveSessionResumptionUpdate?: LiveServerSessionResumptionUpdate;
        longRunningToolIds?: string[];
        modelVersion?: string;
        nodeInfo?: NodeInfo;
        output?: unknown;
        outputTranscription?: Transcription;
        partial?: boolean;
        route?: Route;
        timestamp?: number;
        turnComplete?: boolean;
        usageMetadata?: GenerateContentResponseUsageMetadata;
    }

    Hierarchy (View Summary)

    Properties

    "[EVENT_SIGNATURE_SYMBOL]"?: true

    Signature brand identifying this object as an ADK Event.

    Set by createEvent and checked by isEvent. Optional because events are also reconstructed from storage/session payloads, where the (non-serializable) brand is absent.

    actions?: Partial<EventActions>
    attemptCount?: number
    author?: string

    "user" or the name of the agent, indicating who appended the event to the session.

    branch?: string

    The branch of the event. The format is like agent_1.agent_2.agent_3, where agent_1 is the parent of agent_2, and agent_2 is the parent of agent_3.

    Branch is used when multiple sub-agent shouldn't see their peer agents' conversation history.

    citationMetadata?: CitationMetadata

    The citation metadata of the response.

    Optionalcontent

    content?: Content

    The content of the response.

    customMetadata?: { [key: string]: unknown }

    The custom metadata of the LlmResponse. An optional key-value pair to label an LlmResponse. NOTE: the entire object must be JSON serializable.

    error: unknown
    errorCode?: string

    Error code if the response is an error. Code varies by model.

    errorMessage?: string

    Error message if the response is an error.

    finishReason?: FinishReason

    The finish reason of the response.

    goAway?: LiveServerGoAway

    Server-side signal that the live connection will be closed soon. The caller should reconnect using the latest session resumption handle.

    groundingMetadata?: GroundingMetadata

    The grounding metadata of the response.

    id?: string

    The unique identifier of the event. Do not assign the ID. It will be assigned by the session.

    inputTranscription?: Transcription

    Audio transcription of user input.

    interactionId?: string

    The interaction ID returned by the model, if any.

    interrupted?: boolean

    Flag indicating that LLM was interrupted when generating the content. Usually it's due to user interruption during a bidi streaming.

    invocationId?: string

    The invocation ID of the event. Should be non-empty before appending to a session.

    isolationScope?: string

    Workflow: scope tag used to isolate multi-agent conversations so peer scopes don't see each other's events. Mirrors Python Event.isolation_scope.

    liveSessionId?: string

    The session ID of the Live session.

    liveSessionResumptionUpdate?: LiveServerSessionResumptionUpdate

    The session resumption update of the LlmResponse

    longRunningToolIds?: string[]

    Set of ids of the long running function calls. Agent client will know from this field about which function call is long running. Only valid for function call event

    modelVersion?: string

    The model version used to generate the response.

    nodeInfo?: NodeInfo

    Workflow: provenance of the emitting node. Mirrors Python Event.node_info.

    output?: unknown

    Workflow: the structured output produced by the emitting node, if any.

    First-class field mirroring google/adk-python Event.output. Used by the workflow engine to carry a node's return value alongside its content.

    outputTranscription?: Transcription

    Audio transcription of model output.

    partial?: boolean

    Indicates whether the text content is part of a unfinished text stream. Only used for streaming mode and when the content is plain text.

    route?: Route

    Workflow: the route key(s) emitted by a routing node, used by the graph to select the matching outgoing edge(s). A single value fires one branch; an array fires every branch whose route matches any listed value (multi-route dispatch). Mirrors Python Event.route.

    timestamp?: number

    The timestamp of the event.

    turnComplete?: boolean

    Indicates whether the response from the model is complete. Only used for streaming mode.

    usageMetadata?: GenerateContentResponseUsageMetadata

    The usage metadata of the LlmResponse.

    Properties