Class GetUserChoiceTool

Tool that allows an agent to get a choice from the user

Hierarchy (view full)

Constructors

constructor

Properties

name description isLongRunning shouldRetryOnFailure maxRetryAttempts baseRetryDelay maxRetryDelay logger

Accessors

apiVariant

Methods

validateArguments processLlmRequest safeExecute getDeclaration runAsync

Constructors

constructor

Properties

name

name: string

Name of the tool

description

description: string

Description of the tool

isLongRunning

isLongRunning: boolean

Whether the tool is a long running operation, which typically returns a resource id first and finishes the operation later.

shouldRetryOnFailure

shouldRetryOnFailure: boolean

Whether the tool execution should be retried on failure

maxRetryAttempts

maxRetryAttempts: number

Maximum retry attempts

baseRetryDelay

baseRetryDelay: number = 1000

Base delay for retry in ms (will be used with exponential backoff)

maxRetryDelay

maxRetryDelay: number = 10000

Maximum delay for retry in ms

Protectedlogger

logger: Logger = ...

Accessors

ProtectedapiVariant

Methods

validateArguments

processLlmRequest

  • processLlmRequest(_toolContext, llmRequest): Promise<void>

  • Processes the outgoing LLM request for this tool.

    Use cases:

    • Most common use case is adding this tool to the LLM request.
    • Some tools may just preprocess the LLM request before it's sent out.

    Parameters

    Returns Promise<void>

safeExecute

getDeclaration

runAsync

  • runAsync(args, context): Promise<any>

  • Execute the user choice action This is a long running operation that will return null initially and the actual choice will be provided asynchronously

    Parameters

    • args: {
          options: string[];
          question?: string;
      }
      • options: string[]
      • Optionalquestion?: string
    • context: ToolContext

    Returns Promise<any>

Settings

Member Visibility

On This Page

Constructors
Properties
Accessors
Methods