Agent Client Protocol - v0.5.1
    Preparing search index...

    Interface CreateTerminalRequest

    Executes a command in a new terminal

    Only available if the terminal Client capability is set to true.

    Returns a TerminalId that can be used with other terminal methods to get the current output, wait for exit, and kill the command.

    The TerminalId can also be used to embed the terminal in a tool call by using the ToolCallContent::Terminal variant.

    The Agent is responsible for releasing the terminal by using the terminal/release method.

    See protocol docs: Terminals

    interface CreateTerminalRequest {
        _meta?: { [k: string]: unknown };
        args?: string[];
        command: string;
        cwd?: string | null;
        env?: EnvVariable[];
        outputByteLimit?: number | null;
        sessionId: string;
    }
    Index

    Properties

    _meta? args? command cwd? env? outputByteLimit? sessionId

    Properties

    Optional_meta

    _meta?: { [k: string]: unknown }

    Extension point for implementations

    args?: string[]

    Array of command arguments.

    command: string

    The command to execute.

    cwd?: string | null

    Working directory for the command (absolute path).

    env?: EnvVariable[]

    Environment variables for the command.

    outputByteLimit?: number | null

    Maximum number of output bytes to retain.

    When the limit is exceeded, the Client truncates from the beginning of the output to stay within the limit.

    The Client MUST ensure truncation happens at a character boundary to maintain valid string output, even if this means the retained output is slightly less than the specified limit.

    sessionId: string

    The session ID for this request.

    Settings

    Member Visibility

    On This Page

    Properties