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 = {}) : AIAgentBase<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

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

Type Parameters

Input

The type of input data expected by the agent.

Output

The type of output data produced by the agent.

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.

pipeline

open override val pipeline: AIAgentFunctionalPipeline

Represents the pipeline used by the AI agent for processing tasks or data.

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<AIAgentTool.AgentToolInput<Input>, AIAgentTool.AgentToolResult<Output>>

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

open suspend override fun close()

Closes the AI Agent and performs necessary cleanup operations.

createSession

open override fun createSession(sessionId: String? = null): AIAgentRunSession<Input, Output, AIAgentFunctionalContext>

Creates a new AIAgentRunSession for executing the agent with the given input.

prepareContext

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

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

run

open suspend override fun run(agentInput: Input, sessionId: String? = null): 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.