langchain.js
    Preparing search index...

    Interface ToolMessageFields<TStructure>

    interface ToolMessageFields<
        TStructure extends MessageStructure = MessageStructure,
    > {
        additional_kwargs?: {
            function_call?: FunctionCall;
            tool_calls?: OpenAIToolCall[];
            [key: string]: unknown;
        };
        artifact?: any;
        content?: $InferMessageContent<TStructure, "tool">;
        contentBlocks?: ContentBlock.Standard[];
        id?: string;
        name?: string;
        response_metadata?: Partial<$InferResponseMetadata<TStructure, "tool">>;
        status?: "success" | "error";
        tool_call_id: string;
    }

    Type Parameters

    Hierarchy (View Summary)

    Index

    Properties

    additional_kwargs?: {
        function_call?: FunctionCall;
        tool_calls?: OpenAIToolCall[];
        [key: string]: unknown;
    }

    Type Declaration

    • [key: string]: unknown
    • Optionalfunction_call?: FunctionCall

      Use "tool_calls" field on AIMessages instead

    • Optionaltool_calls?: OpenAIToolCall[]

      Use "tool_calls" field on AIMessages instead

    artifact?: any

    Artifact of the Tool execution which is not meant to be sent to the model.

    Should only be specified if it is different from the message content, e.g. if only a subset of the full tool output is being passed as message content but the full output is needed in other parts of the code.

    content?: $InferMessageContent<TStructure, "tool">
    contentBlocks?: ContentBlock.Standard[]
    id?: string
    name?: string
    response_metadata?: Partial<$InferResponseMetadata<TStructure, "tool">>
    status?: "success" | "error"
    tool_call_id: string