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

AIAgentContext

class AIAgentContext(val environment: AIAgentEnvironment, val agentInputType: KType, val agentInput: Any?, val config: AIAgentConfigBase, llm: AIAgentLLMContext, stateManager: AIAgentStateManager, storage: AIAgentStorage, val runId: String, val strategyName: String, val pipeline: AIAgentPipeline, val id: String) : AIAgentContextBase(source)

Implements the AIAgentContext interface, providing the context required for an AI agent's execution. This class encapsulates configurations, the execution pipeline, agent environment, and tools for handling agent lifecycles and interactions.

Parameters

environment

The AI agent environment responsible for tool execution and problem reporting.

agentInput

The input message to be used for the agent's interaction with the environment.

config

The configuration settings of the AI agent.

llm

The contextual data and execution utilities for the AI agent's interaction with LLMs.

stateManager

Manages the internal state of the AI agent.

storage

Concurrent-safe storage for managing key-value data across the agent's lifecycle.

runId

The unique identifier for the agent session.

strategyName

The identifier for the selected strategy in the agent's lifecycle.

pipeline

The AI agent pipeline responsible for coordinating AI agent execution and processing.

Constructors

AIAgentContext

constructor(environment: AIAgentEnvironment, agentInputType: KType, agentInput: Any?, config: AIAgentConfigBase, llm: AIAgentLLMContext, stateManager: AIAgentStateManager, storage: AIAgentStorage, runId: String, strategyName: String, pipeline: AIAgentPipeline, id: String)

Creates an instance of the context with the given parameters.

Properties

agentInput

open override val agentInput: Any?

agentInputType

open override val agentInputType: KType

KType representing the type of the agentInput

config

open override val config: AIAgentConfigBase

environment

open override val environment: AIAgentEnvironment

open override val id: String

Represents the unique identifier for the agent.

llm

open override val llm: AIAgentLLMContext

Represents the AI agent's LLM context, providing mechanisms for managing tools, prompts, and interaction with the execution environment. It ensures thread safety during concurrent read and write operations through the use of sessions.

pipeline

open override val pipeline: AIAgentPipeline

runId

open override val runId: String

stateManager

open override val stateManager: AIAgentStateManager

Manages and tracks the state of aт AI agent within the context of its execution.

storage

open override val storage: AIAgentStorage

Concurrent-safe key-value storage for an agent, used to manage and persist data within the context of a the AI agent stage execution. The storage property provides a thread-safe mechanism for sharing and storing data specific to the agent's operation.

strategyName

open override val strategyName: String

Functions

agentInput

inline fun <T> AIAgentContextBase.agentInput(): T

Utility function to get AIAgentContextBase.agentInput and try to cast it to some expected type.

copy

open override fun copy(environment: AIAgentEnvironment, agentInput: Any?, agentInputType: KType, config: AIAgentConfigBase, llm: AIAgentLLMContext, stateManager: AIAgentStateManager, storage: AIAgentStorage, runId: String, strategyId: String, pipeline: AIAgentPipeline): AIAgentContextBase

Creates a copy of the current AIAgentContext, allowing for selective overriding of its properties.

copyWithTools

open override fun copyWithTools(tools: List<ToolDescriptor>): AIAgentContextBase

Creates a new instance of AIAgentContextBase with an updated list of tools, replacing the current tools in the LLM context with the provided list.

feature

open override fun <Feature : Any> feature(key: AIAgentStorageKey<Feature>): Feature?

Retrieves a feature associated with the given key from the AI agent storage.

open override fun <Feature : Any> feature(feature: AIAgentFeature<*, Feature>): Feature?

Retrieves an instance of the specified feature from the AI agent's storage.

featureOrThrow

open fun <Feature : Any> featureOrThrow(feature: AIAgentFeature<*, Feature>): Feature

Retrieves a feature of the specified type from the context or throws an exception if it is not available.

fork

open suspend override fun fork(): AIAgentContextBase

Creates a copy of the current AIAgentContext with deep copies of all mutable properties.

get

open override fun <T> get(key: AIAgentStorageKey<*>): T?

Retrieves data from the agent's storage using the specified key.

getAgentContextData

fun AIAgentContextBase.getAgentContextData(): AgentContextData?

Retrieves the agent-specific context data associated with the current instance.

getHistory

open suspend override fun getHistory(): List<Message>

Retrieves the history of messages exchanged during the agent's execution.

remove

open override fun remove(key: AIAgentStorageKey<*>): Boolean

Removes a feature or data associated with the specified key from the agent's storage.

removeAgentContextData

fun AIAgentContextBase.removeAgentContextData(): Boolean

Removes the agent-specific context data associated with the current context.

replace

open suspend override fun replace(context: AIAgentContextBase)

Replaces the current context with the provided context. This method is used to update the current context with values from another context, particularly useful in scenarios like parallel node execution where contexts need to be merged.

store

open override fun store(key: AIAgentStorageKey<*>, value: Any)

Stores a feature in the agent's storage using the specified key.

store

fun AIAgentContextBase.store(data: AgentContextData)

Stores the given agent context data within the current AI agent context.