Class PreloadMemoryTool

A tool that preloads the memory for the current user.

This tool will be automatically executed for each llm_request, and it won't be called by the model.

NOTE: Currently this tool only uses text part from the memory.

Hierarchy (View Summary)

BaseTool
- PreloadMemoryTool

Constructors

constructor

new PreloadMemoryTool(): PreloadMemoryTool
Returns PreloadMemoryTool
Overrides BaseTool.constructor
- Defined in core/src/tools/preload_memory_tool.ts:24

Properties

`Readonly`[BASE_TOOL_SIGNATURE_SYMBOL]

"[BASE_TOOL_SIGNATURE_SYMBOL]": true

A unique symbol to identify ADK base tool class.

`Readonly`description

description: string

`Readonly`isLongRunning

isLongRunning: boolean

`Readonly`name

name: string

Accessors

apiVariant

get apiVariant(): GoogleLLMVariant
The Google API LLM variant to use.

Returns GoogleLLMVariant
Inherited from BaseTool.apiVariant
- Defined in core/src/tools/base_tool.ts:151

Methods

_getDeclaration

_getDeclaration(): FunctionDeclaration | undefined
Gets the OpenAPI specification of this tool in the form of a FunctionDeclaration.

NOTE
- Required if subclass uses the default implementation of processLlmRequest to add function declaration to LLM request.
- Otherwise, can be skipped, e.g. for a built-in GoogleSearch tool for Gemini.
Returns FunctionDeclaration | undefined
The FunctionDeclaration of this tool, or undefined if it doesn't need to be added to LlmRequest.config.
Inherited from BaseTool._getDeclaration
- Defined in core/src/tools/base_tool.ts:94

processLlmRequest

processLlmRequest(request: ToolProcessLlmRequest): 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
- request: ToolProcessLlmRequest
  The request to process the LLM request.
Returns Promise<void>
Overrides BaseTool.processLlmRequest
- Defined in core/src/tools/preload_memory_tool.ts:43

runAsync

runAsync(request: RunAsyncToolRequest): Promise<unknown>
Runs the tool with the given arguments and context.

NOTE
- Required if this tool needs to run at the client side.
- Otherwise, can be skipped, e.g. for a built-in GoogleSearch tool for Gemini.
Parameters
- request: RunAsyncToolRequest
  The request to run the tool.
Returns Promise<unknown>
A promise that resolves to the tool response.
Overrides BaseTool.runAsync
- Defined in core/src/tools/preload_memory_tool.ts:33

Class PreloadMemoryTool

Hierarchy (View Summary)

Constructors

constructor

Returns PreloadMemoryTool

Properties

Readonly[BASE_TOOL_SIGNATURE_SYMBOL]

Readonlydescription

ReadonlyisLongRunning

Readonlyname

Accessors

apiVariant

Returns GoogleLLMVariant

Methods

_getDeclaration

Returns FunctionDeclaration | undefined