Struct LlmConditionalAgent 

pub struct LlmConditionalAgent { /* private fields */ }

Available on crate feature agents only.

LLM-based intelligent conditional routing agent.

Uses an LLM to classify user input and route to the appropriate sub-agent based on the classification result. Supports multi-way routing.

For rule-based routing (A/B testing, feature flags), use crate::ConditionalAgent.

Example

let router = LlmConditionalAgent::builder("router", model)
    .instruction("Classify as 'technical', 'general', or 'creative'.")
    .route("technical", tech_agent)
    .route("general", general_agent.clone())
    .route("creative", creative_agent)
    .default_route(general_agent)
    .build()?;

Implementations

impl LlmConditionalAgent

pub fn builder( name: impl Into<String>, model: Arc<dyn Llm>, ) -> LlmConditionalAgentBuilder

Create a new builder for LlmConditionalAgent.

Trait Implementations

impl Agent for LlmConditionalAgent

fn name(&self) -> &str

Returns the unique name of this agent.

fn description(&self) -> &str

Returns a human-readable description of this agent’s purpose.

fn sub_agents(&self) -> &[Arc<dyn Agent>]

Returns the child agents managed by this agent.

fn supports_agent_transfer(&self) -> bool

Whether this agent participates in LLM-driven agent transfer and may be resumed directly across conversation turns.

fn run<'life0, 'async_trait>( &'life0 self, ctx: Arc<dyn InvocationContext>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<Event, AdkError>> + Send>>, AdkError>> + Send + 'async_trait>>

where 'life0: 'async_trait, LlmConditionalAgent: 'async_trait,

Executes the agent and returns a stream of events.