agents-core/ai.koog.agents.core.agent.session/AIAgentLLMReadSession

AIAgentLLMReadSession

class AIAgentLLMReadSession : AIAgentLLMSession(source)

Represents a session for interacting with a language model (LLM) in a read-only context within an AI agent setup. This session is configured with a set of tools, an executor for handling prompt execution, a prompt definition, a language model, and specific session configurations.

Parameters

tools

A list of tool descriptors that define the tools available for this session.

executor

The PromptExecutor responsible for handling execution of prompts within this session.

prompt

The Prompt object specifying the input messages and parameters for the session.

model

The language model instance to be used for processing prompts in this session.

config

The configuration settings for the AI agent session.

Properties

model

open val model: LLModel

Represents the active language model used within the session.

prompt

open val prompt: Prompt

Represents the current prompt associated with the LLM session. The prompt captures the input messages, model configuration, and parameters used for interactions with the underlying language model.

tools

open val tools: List<ToolDescriptor>

Provides a list of tools based on the current active state.

Functions

override fun close()

requestLLM

open suspend fun requestLLM(): Message.Response

Sends a request to the underlying LLM and returns the first response. This method ensures the session is active before executing the request.

requestLLMForceOneTool

open suspend fun requestLLMForceOneTool(tool: ToolDescriptor): Message.Response

open suspend fun requestLLMForceOneTool(tool: Tool<*, *>): Message.Response

requestLLMMultiple

open suspend fun requestLLMMultiple(): List<Message.Response>

Sends a request to the language model, potentially utilizing multiple tools, and returns a list of responses from the model.

requestLLMOnlyCallingTools

open suspend fun requestLLMOnlyCallingTools(): Message.Response

requestLLMStructured

open suspend fun <T> requestLLMStructured(structure: StructuredData<T>, retries: Int = 1, fixingModel: LLModel = OpenAIModels.Chat.GPT4o): Result<StructuredResponse<T>>

Coerce LLM to provide a structured output.

requestLLMStructuredOneShot

open suspend fun <T> requestLLMStructuredOneShot(structure: StructuredData<T>): StructuredResponse<T>

Expect LLM to reply in a structured format and try to parse it. For more robust version with model coercion and correction see requestLLMStructured

requestLLMWithoutTools

open suspend fun requestLLMWithoutTools(): Message.Response