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

Sends a request to the language model while enforcing the use of a specific tool, and returns the 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.

requestLLMMultipleChoices

open suspend fun requestLLMMultipleChoices(): List<LLMChoice>

Sends a request to the language model, potentially receiving multiple choices, and returns a list of choices from the model.

requestLLMOnlyCallingTools

open suspend fun requestLLMOnlyCallingTools(): Message.Response

Sends a request to the language model that enforces the usage of tools and retrieves the response.

requestLLMStructured

open suspend fun <T> requestLLMStructured(config: StructuredOutputConfig<T>): Result<StructuredResponse<T>>

inline suspend fun <T> requestLLMStructured(examples: List<T> = emptyList(), fixingParser: StructureFixingParser? = null): Result<StructuredResponse<T>>

open suspend fun <T> requestLLMStructured(serializer: KSerializer<T>, examples: List<T> = emptyList(), fixingParser: StructureFixingParser? = null): Result<StructuredResponse<T>>

Sends a request to LLM and gets a structured response.

requestLLMWithoutTools

open suspend fun requestLLMWithoutTools(): Message.Response

Sends a request to the language model without utilizing any tools and returns the response.

requestModeration

open suspend fun requestModeration(moderatingModel: LLModel? = null): ModerationResult

Sends a moderation request to the specified or default large language model (LLM) for content moderation.