ToolCallChunk Class — langchain Architecture

Source Code

libs/core/langchain_core/messages/tool.py lines 261–300

class ToolCallChunk(TypedDict):
    """A chunk of a tool call (yielded when streaming).

    When merging `ToolCallChunk` objects (e.g., via `AIMessageChunk.__add__`), all
    string attributes are concatenated. Chunks are only merged if their values of
    `index` are equal and not `None`.

    Example:
    ```python
    left_chunks = [ToolCallChunk(name="foo", args='{"a":', index=0)]
    right_chunks = [ToolCallChunk(name=None, args="1}", index=0)]

    (
        AIMessageChunk(content="", tool_call_chunks=left_chunks)
        + AIMessageChunk(content="", tool_call_chunks=right_chunks)
    ).tool_call_chunks == [ToolCallChunk(name="foo", args='{"a":1}', index=0)]
    ```
    """

    name: str | None
    """The name of the tool to be called."""

    args: str | None
    """The arguments to the tool call as a JSON-parseable string."""

    id: str | None
    """An identifier associated with the tool call.

    An identifier is needed to associate a tool call request with a tool
    call result in events when multiple concurrent tool calls are made.
    """

    index: int | None
    """The index of the tool call in a sequence.

    Used for merging chunks.
    """

    type: NotRequired[Literal["tool_call_chunk"]]
    """Used for discrimination."""