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

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>, freshHistory: Boolean = false) : TypedAIAgentSubgraphBuilderBase<Input, Output, TypedAIAgentSubgraphBuilder<Input, Output>> (source)

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

This class facilitates the construction of a subgraph within an AI agent graph strategy by providing methods to define graph structures,

Constructors

constructor(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>, freshHistory: Boolean = false)

Functions

define

fun define(buildSubgraph: GraphBuilderAction<Input, Output>): DefinedAIAgentSubgraphBuilder<Input, Output>

Defines an AI Agent subgraph by applying the provided graph building action.

limitedTools

fun limitedTools(tools: List<ERROR CLASS: Symbol not found for ToolBase<*, *>>): TypedAIAgentSubgraphBuilder<Input, Output>

Configures the builder to use a specific list of tools for the AI agent's subgraph.

fun limitedTools(vararg toolSets: ERROR CLASS: Symbol not found for ToolSet): TypedAIAgentSubgraphBuilder<Input, Output>

Configures the builder with a selection of tools defined by the provided tool sets. The tools will be extracted from each ToolSet and applied to the builder's tool selection strategy.

usingLLM

fun usingLLM(llmModel: ERROR CLASS: Symbol not found for LLModel): TypedAIAgentSubgraphBuilder<Input, Output>

Sets the specified Large Language Model (LLM) for the agent subgraph builder.

withFreshHistory

fun withFreshHistory(freshHistory: Boolean): TypedAIAgentSubgraphBuilder<Input, Output>

Configures the subgraph to start with only the parent's system messages, discarding inherited user/assistant conversation turns. The subgraph's own history is discarded upon completion, so it does not affect the parent's conversation.

withInput

fun <Input : Any> withInput(outputClass: Class<Input>): AIAgentSubgraphBuilderWithInput<Input, *>

Configures the builder with the specified input type and returns a new instance of AIAgentSubgraphBuilderWithInput, allowing further configuration for the specified input type.

withLLMParams

fun withLLMParams(llmParams: ERROR CLASS: Symbol not found for LLMParams): TypedAIAgentSubgraphBuilder<Input, Output>

Sets the parameters for the Language Learning Model (LLM) in the current builder.

withResponseProcessor

fun withResponseProcessor(responseProcessor: ERROR CLASS: Symbol not found for ResponseProcessor): TypedAIAgentSubgraphBuilder<Input, Output>

Sets the specified response processor to handle and modify LLM responses.

withTask

fun withTask(defineTask: ContextualAction<Input, String>): SubgraphWithTaskBuilder<Input, Output>

Configures a task to be executed as part of the subgraph.

fun withTask(defineTask: SimpleAction<Input, String>): SubgraphWithTaskBuilder<Input, Output>

Defines a task within the subgraph using the provided task implementation.

withToolSelectionStrategy

fun withToolSelectionStrategy(strategy: ToolSelectionStrategy): TypedAIAgentSubgraphBuilder<Input, Output>

Sets the tool selection strategy for the subgraph builder and returns the updated builder instance.