Struct LlmCallable 

pub struct LlmCallable { /* private fields */ }

LLM-powered callable with tool execution

This is the “agentic” callable - it runs the LLM in a loop, executing tools as requested until a final response is produced.

Note: The loop is controlled by max_iterations to prevent runaway.

Implementations

impl LlmCallable

pub fn with_provider( name: impl Into<String>, system_prompt: impl Into<String>, provider: Arc<dyn ModelProvider>, ) -> Self

Create with a custom provider

pub fn with_emitter(self, emitter: Arc<EventEmitter>) -> Self

Set the event emitter for streaming tool events

pub fn with_model(self, model: impl Into<String>) -> Self

Pin a logical model id for this callable.

pub fn with_routing_policy(self, policy: RoutingPolicy) -> Self

Override routing policy for this callable.

pub fn with_description(self, description: impl Into<String>) -> Self

pub fn add_tool(self, tool: impl Tool + 'static) -> Self

Add a tool to the callable

pub fn add_tools(self, tools: Vec<DynTool>) -> Self

Add multiple tools

pub fn max_iterations(self, max: usize) -> Self

Set max iterations for tool loop

Trait Implementations

impl Callable for LlmCallable

fn name(&self) -> &str

Callable logical name (for logging, debugging, UI)

fn description(&self) -> Option<&str>

Callable description (optional, for documentation)

fn run_streaming<'life0, 'life1, 'async_trait>( &'life0 self, input: &'life1 str, event_tx: Sender<StreamEvent>, ) -> Pin<Box<dyn Future<Output = Result<String>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Execute with streaming events forwarded to the given sender.

fn run<'life0, 'life1, 'async_trait>( &'life0 self, input: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<String>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Execute the callable with the given input

fn last_usage(&self) -> Option<LlmTokenUsage>

Token usage from the last successful run, if available.