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

FunctionalAIAgent

class FunctionalAIAgent<Input, Output>(val promptExecutor: PromptExecutor, val agentConfig: AIAgentConfig, val strategy: AIAgentFunctionalStrategy<Input, Output>, val toolRegistry: ToolRegistry = ToolRegistry.EMPTY, id: String? = null, val clock: Clock = Clock.System, val installFeatures: FunctionalAIAgent.FeatureContext.() -> Unit = {}) : StatefulSingleUseAIAgent<Input, Output, AIAgentFunctionalContext> (source)

Represents the core AI agent for processing input and generating output using a defined configuration, toolset, and prompt execution pipeline.

Parameters

Input

The type of input data expected by the agent.

Output

The type of output data produced by the agent.

Unique identifier for the agent. Random UUID will be generated if set to null.

Constructors

FunctionalAIAgent

constructor(promptExecutor: PromptExecutor, agentConfig: AIAgentConfig, strategy: AIAgentFunctionalStrategy<Input, Output>, toolRegistry: ToolRegistry = ToolRegistry.EMPTY, id: String? = null, clock: Clock = Clock.System, installFeatures: FunctionalAIAgent.FeatureContext.() -> Unit = {})

Types

FeatureContext

class FeatureContext

Represents a context for managing and configuring features in an AI agent. Provides functionality to install and configure features into a specific instance of an AI agent.

Properties

agentConfig

open override val agentConfig: AIAgentConfig

The configuration for the agent, including the prompt structure and execution parameters.

clock

val clock: Clock

The clock used to calculate message timestamps

override val id: String

Represents the unique identifier for the AI agent.

installFeatures

val installFeatures: FunctionalAIAgent.FeatureContext.() -> Unit

Lambda for installing additional features within the agent environment.

promptExecutor

val promptExecutor: PromptExecutor

The executor responsible for processing prompts and interacting with language models.

strategy

open override val strategy: AIAgentFunctionalStrategy<Input, Output>

The strategy for processing input and generating output.

toolRegistry

val toolRegistry: ToolRegistry

The registry of tools available for the agent. Defaults to an empty registry if not specified.

Functions

asTool

inline fun <Input, Output> AIAgent<Input, Output>.~~asTool~~(agentName: String, agentDescription: String, inputDescription: String? = null, inputSerializer: KSerializer<Input> = serializer(), outputSerializer: KSerializer<Output> = serializer(), json: Json = Json.Default): Tool<Input, AIAgentTool.AgentToolResult<Output>>

Converts the current AI agent into a tool to allow using it in other agents as a tool.

suspend override fun close()

Closes the AI Agent and performs necessary cleanup operations.

feature

fun <TFeature : Any> feature(featureClass: KClass<TFeature>, feature: AIAgentFeature<*, TFeature>): TFeature?

Retrieves a feature from the agent's pipeline associated with this agent using the specified key.

feature

inline fun <TFeature : Any> StatefulSingleUseAIAgent<*, *, *>.feature(feature: AIAgentFeature<*, TFeature>): TFeature?

Retrieves a feature from the StatefulSingleUseAIAgent.pipeline associated with this agent using the specified key.

featureOrThrow

inline fun <TFeature : Any> StatefulSingleUseAIAgent<*, *, *>.featureOrThrow(feature: AIAgentFeature<*, TFeature>): TFeature

Retrieves a feature from the StatefulSingleUseAIAgent.pipeline associated with this agent using the specified key or throws an exception if it is not available.

getState

suspend override fun getState(): AIAgent.Companion.State<Output>

Retrieves the current state of the AI agent during its lifecycle.

isFinished

suspend fun AIAgent<*, *>.isFinished(): Boolean

Checks whether the AI agent has reached a finished state.

isRunning

suspend fun AIAgent<*, *>.isRunning(): Boolean

Checks whether the AI agent is currently in a running state.

prepareContext

open suspend override fun prepareContext(agentInput: Input, runId: String): AIAgentFunctionalContext

Prepares and initializes the agent context required to handle the given input and run ID.

result

open suspend fun result(): Output

Retrieves the result of the operation if the current state is State.Finished. Throws an IllegalStateException if the operation is not in a finished state.

run

suspend override fun run(agentInput: Input): Output

Executes the agent's main functionality, coordinating with various components such as pipelines and strategies. Ensures the agent is run in a thread-safe manner using locking mechanisms.