agents-core/ai.koog.agents.core.agent.context/AIAgentLLMContext

AIAgentLLMContext

expect open class AIAgentLLMContext : AIAgentLLMContextCommon(source)

Constructs a new instance of AIAgentLLMContext with the provided parameters.

Parameters

tools

A list of tools described by ToolDescriptor that the agent can interact with.

toolRegistry

A registry of available tools, defaulting to an empty ToolRegistry.

prompt

The initial prompt used in the context, represented by a Prompt instance.

model

The language model used for processing prompts and generating responses.

responseProcessor

An optional ResponseProcessor for handling and processing model responses.

promptExecutor

Responsible for executing the logic for prompt processing in the context.

environment

The operational environment of the AI agent, represented by an AIAgentEnvironment.

config

Configuration settings for the AI agent, encapsulated in an AIAgentConfig.

clock

A clock instance for managing time-related operations within the context.

actual open class AIAgentLLMContext : AIAgentLLMContextCommon(source)

Constructs a new instance of AIAgentLLMContext with the provided parameters.

Parameters

tools

A list of tools described by ToolDescriptor that the agent can interact with.

toolRegistry

A registry of available tools, defaulting to an empty ToolRegistry.

prompt

The initial prompt used in the context, represented by a Prompt instance.

model

The language model used for processing prompts and generating responses.

responseProcessor

An optional ResponseProcessor for handling and processing model responses.

promptExecutor

Responsible for executing the logic for prompt processing in the context.

environment

The operational environment of the AI agent, represented by an AIAgentEnvironment.

config

Configuration settings for the AI agent, encapsulated in an AIAgentConfig.

clock

A clock instance for managing time-related operations within the context.

actual open class AIAgentLLMContext : AIAgentLLMContextCommon(source)

Constructs a new instance of AIAgentLLMContext with the provided parameters.

Parameters

tools

A list of tools described by ToolDescriptor that the agent can interact with.

toolRegistry

A registry of available tools, defaulting to an empty ToolRegistry.

prompt

The initial prompt used in the context, represented by a Prompt instance.

model

The language model used for processing prompts and generating responses.

responseProcessor

An optional ResponseProcessor for handling and processing model responses.

promptExecutor

Responsible for executing the logic for prompt processing in the context.

environment

The operational environment of the AI agent, represented by an AIAgentEnvironment.

config

Configuration settings for the AI agent, encapsulated in an AIAgentConfig.

clock

A clock instance for managing time-related operations within the context.

Constructors

AIAgentLLMContext

expect constructor(tools: List<ToolDescriptor>, toolRegistry: ToolRegistry = ToolRegistry.EMPTY, prompt: Prompt, model: LLModel, responseProcessor: ResponseProcessor?, promptExecutor: PromptExecutor, environment: AIAgentEnvironment, config: AIAgentConfig, clock: Clock)

actual constructor(tools: List<ERROR CLASS: Symbol not found for ToolDescriptor>, toolRegistry: ERROR CLASS: Symbol not found for ToolRegistry, prompt: ERROR CLASS: Symbol not found for Prompt, model: ERROR CLASS: Symbol not found for LLModel, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor??, promptExecutor: ERROR CLASS: Symbol not found for PromptExecutor, environment: AIAgentEnvironment, config: AIAgentConfig, clock: ERROR CLASS: Symbol not found for Clock)

actual constructor(tools: List<ToolDescriptor>, toolRegistry: ToolRegistry, prompt: Prompt, model: LLModel, responseProcessor: ResponseProcessor?, promptExecutor: PromptExecutor, environment: AIAgentEnvironment, config: AIAgentConfig, clock: Clock)

Properties

clock

@get:JvmName(name = "clock")

val clock: Clock

Represents the clock instance used for time-related operations and scheduling within the context.

val clock: kotlin/time/Clock

Represents the clock instance used for time-related operations and scheduling within the context.

@get:JvmName(name = "clock")

val clock: Clock

Represents the clock instance used for time-related operations and scheduling within the context.

config

@get:JvmName(name = "config")

val config: AIAgentConfig

Provides access to the configuration settings for an AI agent within the LLM context.

val config: AIAgentConfig

Provides access to the configuration settings for an AI agent within the LLM context.

@get:JvmName(name = "config")

val config: AIAgentConfig

Provides access to the configuration settings for an AI agent within the LLM context.

environment

@get:JvmName(name = "environment")

val environment: AIAgentEnvironment

Represents the execution environment associated with an AI agent within the context of the LLM (Large Language Model) framework.

val environment: AIAgentEnvironment

Represents the execution environment associated with an AI agent within the context of the LLM (Large Language Model) framework.

@get:JvmName(name = "environment")

val environment: AIAgentEnvironment

Represents the execution environment associated with an AI agent within the context of the LLM (Large Language Model) framework.

model

@DetachedPromptExecutorAPI

@get:JvmName(name = "model")

var model: LLModel

LLM currently associated with this context.

@DetachedPromptExecutorAPI

var model: ai/koog/prompt/llm/LLModel

LLM currently associated with this context.

@DetachedPromptExecutorAPI

@get:JvmName(name = "model")

var model: LLModel

LLM currently associated with this context.

prompt

@get:JvmName(name = "prompt")

var prompt: Prompt

The current prompt used within the AIAgentLLMContext.

var prompt: ai/koog/prompt/dsl/Prompt

The current prompt used within the AIAgentLLMContext.

@get:JvmName(name = "prompt")

var prompt: Prompt

The current prompt used within the AIAgentLLMContext.

promptExecutor

@DetachedPromptExecutorAPI

@get:JvmName(name = "promptExecutor")

val promptExecutor: PromptExecutor

The PromptExecutor responsible for performing operations on the current prompt.

@DetachedPromptExecutorAPI

val promptExecutor: ai/koog/prompt/executor/model/PromptExecutor

The PromptExecutor responsible for performing operations on the current prompt.

@DetachedPromptExecutorAPI

@get:JvmName(name = "promptExecutor")

val promptExecutor: PromptExecutor

The PromptExecutor responsible for performing operations on the current prompt.

responseProcessor

@DetachedPromptExecutorAPI

@get:JvmName(name = "responseProcessor")

var responseProcessor: ResponseProcessor?

Response processor currently associated with this context.

@DetachedPromptExecutorAPI

var responseProcessor: ai/koog/prompt/processor/ResponseProcessor??

Response processor currently associated with this context.

@DetachedPromptExecutorAPI

@get:JvmName(name = "responseProcessor")

var responseProcessor: ResponseProcessor?

Response processor currently associated with this context.

toolRegistry

@get:JvmName(name = "toolRegistry")

val toolRegistry: ToolRegistry

A ToolRegistry that contains metadata about available tools.

val toolRegistry: ai/koog/agents/core/tools/ToolRegistry

A ToolRegistry that contains metadata about available tools.

@get:JvmName(name = "toolRegistry")

val toolRegistry: ToolRegistry

A ToolRegistry that contains metadata about available tools.

tools

@DetachedPromptExecutorAPI

@get:JvmName(name = "tools")

var tools: List<ToolDescriptor>

List of current tools associated with this agent context.

@DetachedPromptExecutorAPI

var tools: List<ai/koog/agents/core/tools/ToolDescriptor>

List of current tools associated with this agent context.

@DetachedPromptExecutorAPI

@get:JvmName(name = "tools")

var tools: List<ToolDescriptor>

List of current tools associated with this agent context.

Functions

copy

open fun copy(tools: List<ToolDescriptor> = this.tools, prompt: Prompt = this.prompt, model: LLModel = this.model, responseProcessor: ResponseProcessor? = this.responseProcessor, promptExecutor: PromptExecutor = this.promptExecutor, environment: AIAgentEnvironment = this.environment, config: AIAgentConfig = this.config, clock: Clock = this.clock): AIAgentLLMContext

Returns the current prompt used in the LLM context.

@JvmOverloads

open suspend fun copy(tools: List<ToolDescriptor> = this.tools, toolRegistry: ToolRegistry = this.toolRegistry, prompt: Prompt = this.prompt, model: LLModel = this.model, responseProcessor: ResponseProcessor? = this.responseProcessor, promptExecutor: PromptExecutor = this.promptExecutor, environment: AIAgentEnvironment = this.environment, config: AIAgentConfig = this.config, clock: Clock = this.clock): AIAgentLLMContext

Creates a deep copy of this LLM context.

open override fun copy(tools: List<ERROR CLASS: Symbol not found for ToolDescriptor>, prompt: ERROR CLASS: Symbol not found for Prompt, model: ERROR CLASS: Symbol not found for LLModel, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor??, promptExecutor: ERROR CLASS: Symbol not found for PromptExecutor, environment: AIAgentEnvironment, config: AIAgentConfig, clock: ERROR CLASS: Symbol not found for Clock): AIAgentLLMContext

open suspend override fun copy(tools: List<ERROR CLASS: Symbol not found for ToolDescriptor>, toolRegistry: ERROR CLASS: Symbol not found for ToolRegistry, prompt: ERROR CLASS: Symbol not found for Prompt, model: ERROR CLASS: Symbol not found for LLModel, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor??, promptExecutor: ERROR CLASS: Symbol not found for PromptExecutor, environment: AIAgentEnvironment, config: AIAgentConfig, clock: ERROR CLASS: Symbol not found for Clock): AIAgentLLMContext

open fun copy(tools: List<ai/koog/agents/core/tools/ToolDescriptor> = this.tools, prompt: ai/koog/prompt/dsl/Prompt = this.prompt, model: ai/koog/prompt/llm/LLModel = this.model, responseProcessor: ai/koog/prompt/processor/ResponseProcessor?? = this.responseProcessor, promptExecutor: ai/koog/prompt/executor/model/PromptExecutor = this.promptExecutor, environment: AIAgentEnvironment = this.environment, config: AIAgentConfig = this.config, clock: kotlin/time/Clock = this.clock): AIAgentLLMContext

Returns the current prompt used in the LLM context.

open suspend fun copy(tools: List<ai/koog/agents/core/tools/ToolDescriptor> = this.tools, toolRegistry: ai/koog/agents/core/tools/ToolRegistry = this.toolRegistry, prompt: ai/koog/prompt/dsl/Prompt = this.prompt, model: ai/koog/prompt/llm/LLModel = this.model, responseProcessor: ai/koog/prompt/processor/ResponseProcessor?? = this.responseProcessor, promptExecutor: ai/koog/prompt/executor/model/PromptExecutor = this.promptExecutor, environment: AIAgentEnvironment = this.environment, config: AIAgentConfig = this.config, clock: kotlin/time/Clock = this.clock): AIAgentLLMContext

Creates a deep copy of this LLM context.

Returns the current prompt used in the LLM context.

@JvmOverloads

Creates a deep copy of this LLM context.

readSession

open suspend fun <T> readSession(block: suspend AIAgentLLMReadSession.() -> T): T

Executes a read session within the AIAgentLLMContext, ensuring concurrent safety with active write session and other read sessions.

fun <T> readSession(block: Function<AIAgentLLMReadSession, T>): T

Executes a read-only session within the context of AIAgentLLMReadSession and returns the result of the provided block.

open suspend fun <T> readSession(block: suspend AIAgentLLMReadSession.() -> T): T

Executes a read session within the AIAgentLLMContext, ensuring concurrent safety with active write session and other read sessions.

open suspend fun <T> readSession(block: suspend AIAgentLLMReadSession.() -> T): T

Executes a read session within the AIAgentLLMContext, ensuring concurrent safety with active write session and other read sessions.

withPrompt

open suspend fun withPrompt(block: Prompt.() -> Prompt)

Updates the current AIAgentLLMContext with a new prompt and ensures thread-safe access using a read lock.

open suspend fun withPrompt(block: ai/koog/prompt/dsl/Prompt.() -> ai/koog/prompt/dsl/Prompt)

Updates the current AIAgentLLMContext with a new prompt and ensures thread-safe access using a read lock.

open suspend fun withPrompt(block: Prompt.() -> Prompt)

Updates the current AIAgentLLMContext with a new prompt and ensures thread-safe access using a read lock.

writeSession

open suspend fun <T> writeSession(block: suspend AIAgentLLMWriteSession.() -> T): T

Executes a write session on the AIAgentLLMContext, ensuring that all active write and read sessions are completed before initiating the write session.

fun <T> writeSession(block: Function<AIAgentLLMWriteSession, T>): T

Executes a block of code within a write session for the AI Agent LLM context.

open suspend fun <T> writeSession(block: suspend AIAgentLLMWriteSession.() -> T): T

Executes a write session on the AIAgentLLMContext, ensuring that all active write and read sessions are completed before initiating the write session.

open suspend fun <T> writeSession(block: suspend AIAgentLLMWriteSession.() -> T): T

Executes a write session on the AIAgentLLMContext, ensuring that all active write and read sessions are completed before initiating the write session.