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

AIAgentNodeBase

abstract class AIAgentNodeBase<Input, Output>(source)

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

Parameters

Input

The type of input data this node processes.

Output

The type of output data this node produces.

Inheritors

Types

Link copied to clipboard
data class ResolvedEdge(val edge: AIAgentEdge<*, *>, val output: Any?)

Represents a resolved edge in the context of an AI agent strategy graph, combining an edge and its corresponding resolved output.

Properties

Link copied to clipboard
var edges: List<AIAgentEdge<Output, *>>

Represents the directed edges connecting the current node in the AI agent strategy graph to other nodes. Each edge defines the flow and transformation of output data from this node to another.

Link copied to clipboard
val id: String

Represents the unique identifier of the AI agent node.

Link copied to clipboard
abstract val inputType: KType

The KType of the Input

Link copied to clipboard
abstract val name: String

The name of the AI agent node. This property serves as a unique identifier for the node within the strategy graph and is used to distinguish and reference nodes in the graph structure.

Link copied to clipboard
abstract val outputType: KType

The KType of the Output

Functions

Link copied to clipboard
open fun addEdge(edge: AIAgentEdge<Output, *>)

Adds a directed edge from the current node, enabling connections between this node and other nodes in the AI agent strategy graph.

Link copied to clipboard
abstract suspend fun execute(context: AIAgentContextBase, input: Input): Output?

Executes a specific operation based on the given context and input.

Link copied to clipboard
suspend fun executeUnsafe(context: AIAgentContextBase, input: Any?): Any?

Executes the node operation using the provided execution context and input, bypassing type safety checks. This method internally calls the type-safe execute method after casting the input. The lifecycle hooks onBeforeNode and onAfterNode are invoked before and after the execution respectively.

Link copied to clipboard
infix fun <IncomingOutput, OutgoingInput> AIAgentNodeBase<*, IncomingOutput>.forwardTo(otherNode: AIAgentNodeBase<OutgoingInput, *>): AIAgentEdgeBuilderIntermediate<IncomingOutput, IncomingOutput, OutgoingInput>

Creates a directed edge from this AIAgentNodeBase to another AIAgentNodeBase, allowing data to flow from the output of the current node to the input of the specified node.

Link copied to clipboard
suspend fun resolveEdge(context: AIAgentContextBase, nodeOutput: Output): AIAgentNodeBase.ResolvedEdge?

Resolves the edge associated with the provided node output and execution context. Iterates through available edges and identifies the first edge that can successfully process the given node output within the provided context. If a resolvable edge is found, it returns a ResolvedEdge containing the edge and its output. Otherwise, returns null.