Struct LoopAgent 

pub struct LoopAgent { /* private fields */ }

Available on crate feature agents only.

Loop agent executes sub-agents repeatedly for N iterations or until escalation

Implementations

impl LoopAgent

pub fn new( name: impl Into<String>, sub_agents: Vec<Arc<dyn Agent>>, ) -> LoopAgent

Create a new loop agent with the given name and sub-agents.

pub fn with_description(self, desc: impl Into<String>) -> LoopAgent

Set the agent description.

pub fn with_max_iterations(self, max: u32) -> LoopAgent

Set the maximum number of loop iterations.

pub fn with_skills(self, index: SkillIndex) -> LoopAgent

Available on crate feature skills only.

Set a preloaded skills index for this agent.

pub fn with_auto_skills(self) -> Result<LoopAgent, AdkError>

Available on crate feature skills only.

Auto-load skills from .skills/ in the current working directory.

pub fn with_skills_from_root( self, root: impl AsRef<Path>, ) -> Result<LoopAgent, AdkError>

Available on crate feature skills only.

Auto-load skills from .skills/ under a custom root directory.

pub fn with_skill_policy(self, policy: SelectionPolicy) -> LoopAgent

Available on crate feature skills only.

Customize skill selection behavior.

pub fn with_skill_budget(self, max_chars: usize) -> LoopAgent

Available on crate feature skills only.

Limit injected skill content length.

pub fn before_callback( self, callback: Box<dyn Fn(Arc<dyn CallbackContext>) -> Pin<Box<dyn Future<Output = Result<Option<Content>, AdkError>> + Send>> + Sync + Send>, ) -> LoopAgent

Add a before-agent callback.

pub fn after_callback( self, callback: Box<dyn Fn(Arc<dyn CallbackContext>) -> Pin<Box<dyn Future<Output = Result<Option<Content>, AdkError>> + Send>> + Sync + Send>, ) -> LoopAgent

Add an after-agent callback.

Trait Implementations

impl Agent for LoopAgent

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, LoopAgent: 'async_trait,

Executes the agent and returns a stream of events.