agents-core/ai.koog.agents.core.agent.entity

Package-level declarations

Types

A builder class for creating and managing edges between AI agent nodes in a graph. This class serves as an entry point to initiate the construction of directed edges by associating a starting node with subsequent interconnected nodes.

AgentSubgraphBuilder

open class AgentSubgraphBuilder<SubgraphBuilder : AgentSubgraphBuilder<SubgraphBuilder>>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null)

A builder class for configuring and constructing subgraphs in an AI agent graph strategy.

AIAgentEdge

expect class AIAgentEdge<IncomingOutput, OutgoingInput>

Represents a directed edge connecting two nodes in the graph of an AI agent strategy. This edge facilitates the transmission of data between a source node and a destination node, allowing transformation or filtering of output values from the source node before they reach the destination node.

actual class AIAgentEdge<IncomingOutput, OutgoingInput>

AIAgentGraphStrategy

expect class AIAgentGraphStrategy<TInput, TOutput> : AIAgentGraphStrategyBase<TInput, TOutput>

Represents a strategy for managing and executing AI agent workflows built as subgraphs of interconnected nodes.

actual class AIAgentGraphStrategy<TInput, TOutput> : AIAgentGraphStrategyBase<TInput, TOutput>

Represents a strategy for managing and executing AI agent workflows built as subgraphs of interconnected nodes.

actual class AIAgentGraphStrategy<TInput, TOutput> : AIAgentGraphStrategyBase<TInput, TOutput>

Represents a strategy for managing and executing AI agent workflows built as subgraphs of interconnected nodes.

AIAgentGraphStrategyBase

open class AIAgentGraphStrategyBase<TInput, TOutput>(val name: String, val nodeStart: StartNode<TInput>, val nodeFinish: FinishNode<TOutput>, toolSelectionStrategy: ToolSelectionStrategy, serializer: Json = Json { prettyPrint = true }) : AIAgentStrategy<TInput, TOutput, AIAgentGraphContextBase> , AIAgentSubgraphBase<TInput, TOutput>

Base class for AIAgentStrategy.

AIAgentNode

expect open class AIAgentNode<TInput, TOutput> : SimpleAIAgentNodeImpl<TInput, TOutput>

Represents a simple implementation of an AI agent node, encapsulating a specific execution logic that processes the input data and produces an output.

actual open class AIAgentNode<TInput, TOutput> : SimpleAIAgentNodeImpl<TInput, TOutput>

Represents a simple implementation of an AI agent node, encapsulating a specific execution logic that processes the input data and produces an output.

actual open class AIAgentNode<TInput, TOutput> : SimpleAIAgentNodeImpl<TInput, TOutput>

Represents a simple implementation of an AI agent node, encapsulating a specific execution logic that processes the input data and produces an output.

AIAgentNodeBase

abstract class AIAgentNodeBase<in TInput, TOutput>

Represents an abstract node in an AI agent strategy graph, responsible for executing a specific operation and managing directed edges to other nodes.

AIAgentNodeBuilder

class AIAgentNodeBuilder(name: String?)

A Java builder class for creating AIAgentNode with a specified name. This allows the configuration of the node's input type.

AIAgentNodeBuilderWithInput

class AIAgentNodeBuilderWithInput<Input : Any>(name: String?, inputTypeToken: ERROR CLASS: Symbol not found for TypeToken)

A Java builder class for creating AIAgentNode with a specified input type.

AIAgentState

class AIAgentState(iterations: Int = 0) : AutoCloseable

Represents the state of an AI agent.

AIAgentStateManager

class AIAgentStateManager(state: AIAgentState = AIAgentState())

Manages the state of an AI agent by providing thread-safe access and mechanisms to update the internal state using a locking mechanism.

AIAgentStorage

expect class AIAgentStorage : AIAgentStorageAPI

Concurrent-safe key-value storage for an agent. You can create typed keys for your data using the createStorageKey function and set and retrieve data using it by calling set and get.

actual class AIAgentStorage : AIAgentStorageAPI

Represents a storage key used for identifying and accessing data associated with an AI agent.

actual class AIAgentStorage : AIAgentStorageAPI

Concurrent-safe key-value storage for an agent. You can create typed keys for your data using the createStorageKey function and set and retrieve data using it by calling set and get.

AIAgentStorageAPI

interface AIAgentStorageAPI

API for AIAgentStorage

AIAgentStorageKey

class AIAgentStorageKey<T : Any>(val name: String)

Represents a storage key used for identifying and accessing data associated with an AI agent.

AIAgentStrategy

expect interface AIAgentStrategy<TInput, TOutput, TContext : AIAgentContext>

An interface representing the execution strategy of an AI agent.

actual interface AIAgentStrategy<TInput, TOutput, TContext : AIAgentContext>

An interface representing the execution strategy of an AI agent.

actual interface AIAgentStrategy<TInput, TOutput, TContext : AIAgentContext>

An interface representing the execution strategy of an AI agent.

AIAgentSubgraph

expect class AIAgentSubgraph<TInput, TOutput> : AIAgentSubgraphBase<TInput, TOutput>

Represents a subgraph within an AI agent execution strategy capable of processing input and producing output.

actual class AIAgentSubgraph<TInput, TOutput> : AIAgentSubgraphBase<TInput, TOutput>

Represents a subgraph within an AI agent execution strategy capable of processing input and producing output.

actual class AIAgentSubgraph<TInput, TOutput> : AIAgentSubgraphBase<TInput, TOutput>

Represents a subgraph within an AI agent execution strategy capable of processing input and producing output.

AIAgentSubgraphBase

open class AIAgentSubgraphBase<TInput, TOutput>(val name: String, val start: StartNode<TInput>, val finish: FinishNode<TOutput>, toolSelectionStrategy: ToolSelectionStrategy, llmModel: LLModel? = null, llmParams: LLMParams? = null, responseProcessor: ResponseProcessor? = null) : AIAgentNodeBase<TInput, TOutput> , ExecutionPointNode

Base class for AIAgentSubgraph.

AIAgentSubgraphBuilderWithInput

open class AIAgentSubgraphBuilderWithInput<Input : Any, SubgraphBuilder : AgentSubgraphBuilder<SubgraphBuilder>>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null, inputClass: Class<Input>) : AgentSubgraphBuilder<SubgraphBuilder>

A builder class for constructing AI agent subgraphs with a specified input type.

CompatibleFullAgentEdgeBuilder

open class CompatibleFullAgentEdgeBuilder<IncomingOutput, CompatibleOutput : OutgoingInput, OutgoingInput> : FullAgentEdgeBuilder<IncomingOutput, CompatibleOutput, OutgoingInput>

Constructs a compatible full agent edge between two AI agent nodes, enabling the flow and transformation of data from the output of one node to the input of another.

CompressHistoryNodeBuilder

class CompressHistoryNodeBuilder(name: String)

Builder class for creating a compress history node in an AI agent graph strategy.

ContextualAction

fun interface ContextualAction<Input, Output>

Represents a functional interface that defines a contextual action for processing an input and producing an output within a specific AI agent graph context.

ContextualCondition

fun interface ContextualCondition<Output>

ContextualCondition is a functional interface designed to evaluate a condition based on an output value and the given AI agent graph context.

ContextualTransformation

fun interface ContextualTransformation<Output, NewOutput>

A functional interface representing a transformation operation that processes an input output of type Output in the context of AIAgentGraphContextBase and produces a transformed result of type NewOutput.

DefinedAIAgentNodeBuilder

class DefinedAIAgentNodeBuilder<Input : Any, Output : Any>(name: String?, inputTypeToken: ERROR CLASS: Symbol not found for TypeToken, outputTypeToken: ERROR CLASS: Symbol not found for TypeToken, nodeAction: ContextualAction<Input, Output>)

A builder class responsible for constructing instances of AIAgentNode with specific input and output types, a unique node name, and a defined contextual action to be executed within an AI agent graph context.

DefinedAIAgentSubgraphBuilder

class DefinedAIAgentSubgraphBuilder<Input : Any, Output : Any>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null, inputClass: Class<Input>, outputClass: Class<Output>, buildSubgraph: GraphBuilderAction<Input, Output>) : TypedAIAgentSubgraphBuilderBase<Input, Output, TypedAIAgentSubgraphBuilder<Input, Output>>

Builder class for creating a defined AI Agent subgraph with specific input and output types.

ExecutionPoint

data class ExecutionPoint(val node: AIAgentNodeBase<*, *>, val input: Any? = null)

Represents a point of execution within the AI agent's strategy graph. An execution point consists of a specific node and an optional input value.

ExecutionPointNode

interface ExecutionPointNode

Represents a node in the execution graph of an AI agent that can explicitly enforce execution at a specified node with optional input data. This interface provides the ability to define a forced node and input, overriding default execution behavior.

FinishNode

class FinishNode<TOutput> : AIAgentNode<TOutput, TOutput>

Represents a specialized node within an AI agent strategy graph that marks the endpoint of a subgraph. This node serves as a "finish" node and directly passes its input to its output without modification.

FullAgentEdgeBuilder

open class FullAgentEdgeBuilder<IncomingOutput, IntermediateOutput, OutgoingInput>

A builder class for constructing a specialized edge in an AI agent strategy graph. This edge enables data flow between two nodes while supporting a composition of the output transformation logic.

GraphBuilderAction

fun interface GraphBuilderAction<Input : Any, Output : Any>

Functional interface representing an action that builds a graph using a provided TypedGraphStrategyBuilder. This action allows the customization and configuration of a graph strategy based on specific requirements for input and output types.

GraphStrategyBuilder

class GraphStrategyBuilder(strategyName: String)

A builder class used for constructing strategies related to graph processing. This serves as the entry point for configuring a graph strategy, allowing you to define the input type for the graph.

GraphStrategyBuilderWithInput

class GraphStrategyBuilderWithInput<Input : Any>(strategyName: String, inputClass: KClass<Input>)

A builder class for constructing graph strategies that start with a specific input type.

NonSuspendAIAgentStrategy

abstract class NonSuspendAIAgentStrategy<TInput, TOutput, TContext : AIAgentContext> : AIAgentStrategy<TInput, TOutput, TContext>

AIAgentStrategy that is executed in non-suspend context using java.util.concurrent.ExecutorService provided in ai.koog.agents.core.agent.config.AIAgentConfig.

PartialAgentEdgeBuilder

open class PartialAgentEdgeBuilder<IncomingInput, IncomingOutput>(fromNode: AIAgentNodeBase<IncomingInput, IncomingOutput>)

A builder class used to define a transitional directed edge in an AI agent strategy graph.

PromptBuilderAction

fun interface PromptBuilderAction

Represents an action that defines how a PromptBuilder is configured.

SimpleAction

fun interface SimpleAction<Input, Output>

Represents a functional interface designed for performing a simple action that takes an input of type Input and produces an output of type Output.

SimpleAIAgentNodeImpl

open class SimpleAIAgentNodeImpl<TInput, TOutput> : AIAgentNodeBase<TInput, TOutput>

Represents a simple implementation of an AI agent node within a graph-based structure.

SimpleCondition

fun interface SimpleCondition<Output>

Represents a simple, stateless functional interface that evaluates a condition on a given output. This is particularly tailored for Java compatibility, enabling usage in contexts where Java code interacts with Kotlin.

SimpleTransformation

fun interface SimpleTransformation<Output, NewOutput>

A functional interface representing a transformation operation from a given input type to a new output type.

StartNode

class StartNode<TInput> : AIAgentNode<TInput, TInput>

Represents the base node for starting a subgraph in an AI agent strategy graph. This node acts as an entry point for executing subgraphs.

SubgraphMetadata

data class SubgraphMetadata(val nodesMap: Map<String, AIAgentNodeBase<*, *>>, val uniqueNames: Boolean = false)

Represents metadata associated with a subgraph in an AI agent strategy graph.

SubgraphWithFinishToolBuilder

class SubgraphWithFinishToolBuilder<Input : Any, Output : Any, OutputTransformed : Any>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null, inputClass: Class<Input>, finishTool: ERROR CLASS: Symbol not found for Tool<Output, OutputTransformed>)

Builder class for constructing a subgraph with a finish tool in a graph strategy.

SubgraphWithTaskBuilder

class SubgraphWithTaskBuilder<Input : Any, Output : Any>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null, inputClass: Class<Input>, outputOption: OutputOption<Output>, defineTask: ContextualAction<Input, String>, runMode: ToolCalls = ToolCalls.SEQUENTIAL, assistantResponseRepeatMax: Int? = null) : TypedAIAgentSubgraphBuilderBase<Input, Output, SubgraphWithTaskBuilder<Input, Output>>

A builder class for creating an AI agent subgraph that incorporates task definition as part of its configuration. This builder allows customizing the construction of a subgraph while defining how tasks are specified and executed within the subgraph.

ToolSelectionStrategy

sealed interface ToolSelectionStrategy

Represents a strategy to select a subset of tools to be used in a subgraph during its execution.

TypedAIAgentNodeBuilder

class TypedAIAgentNodeBuilder<Input : Any, Output : Any>(name: String?, inputTypeToken: ERROR CLASS: Symbol not found for TypeToken, outputTypeToken: ERROR CLASS: Symbol not found for TypeToken)

A Java builder class for creating instances of AIAgentNode with strongly typed input and output data.

TypedAIAgentSubgraphBuilder

class TypedAIAgentSubgraphBuilder<Input : Any, Output : Any>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null, inputClass: Class<Input>, outputClass: Class<Output>) : TypedAIAgentSubgraphBuilderBase<Input, Output, TypedAIAgentSubgraphBuilder<Input, Output>>

Builder class for creating and configuring a typed AI agent subgraph.

TypedAIAgentSubgraphBuilderBase

abstract class TypedAIAgentSubgraphBuilderBase<Input : Any, Output : Any, SubgraphBuilder : TypedAIAgentSubgraphBuilderBase<Input, Output, SubgraphBuilder>>(name: String?, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, llmModel: ERROR CLASS: Symbol not found for LLModel?? = null, llmParams: ERROR CLASS: Symbol not found for LLMParams?? = null, responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor?? = null, inputClass: Class<Input>, outputOption: OutputOption<Output>) : AgentSubgraphBuilder<SubgraphBuilder>

A base class for constructing a typed AI agent subgraph builder with strongly defined input and output types. This class is designed for creating subgraphs within an AI agent graph structure, enabling the configuration of node interactions, tool usage, and the integration of language models (LLMs).

TypedCompressHistoryNodeBuilder

class TypedCompressHistoryNodeBuilder<Input : Any>(name: String, inputTypeToken: ERROR CLASS: Symbol not found for TypeToken, retrievalModel: ERROR CLASS: Symbol not found for LLModel?? = null, strategy: HistoryCompressionStrategy = HistoryCompressionStrategy.WholeHistory, preserveMemory: Boolean = true)

A builder class for configuring and creating a typed compression history node within an AI agent graph.

TypedGraphStrategyBuilder

class TypedGraphStrategyBuilder<Input : Any, Output : Any>(strategyName: String, inputClass: KClass<Input>, outputClass: KClass<Output>, toolSelectionStrategy: ToolSelectionStrategy = ToolSelectionStrategy.ALL, builder: AIAgentGraphStrategyBuilder<Input, Output> = AIAgentGraphStrategyBuilder( strategyName, typeToken(inputClass), typeToken(outputClass), toolSelectionStrategy ), edgeBuilders: MutableList<AIAgentGraphStrategyBuilder<Input, Output>.() -> Unit> = mutableListOf())

Builder class used for constructing and configuring an AIAgentGraphStrategy.

Functions

createStorageKey

fun <T : Any> createStorageKey(name: String): AIAgentStorageKey<T>

Creates a storage key for a specific type, allowing identification and retrieval of values associated with it.