Struct EchoWorker 

pub struct EchoWorker {
    pub delay_ms: u64,
}

Dummy echo worker for testing

Simply splits the prompt into words and returns them as tokens. Useful for pipeline smoke tests without real model dependencies.

Fields

delay_ms: u64

Simulated inference delay

Implementations

impl EchoWorker

pub fn new() -> Self

Create a new EchoWorker with a default 10 ms simulated delay.

The echo worker requires no API keys or external services. It splits the prompt on whitespace and returns each word as a token, making it ideal for pipeline smoke tests and local development.

Errors

This constructor never returns an error.

Examples

use tokio_prompt_orchestrator::worker::EchoWorker;
use std::sync::Arc;

let worker = Arc::new(EchoWorker::new());
// Use worker with spawn_pipeline or directly

pub fn with_delay(delay_ms: u64) -> Self

Create a new EchoWorker with a custom simulated inference delay in milliseconds.

Trait Implementations

impl Default for EchoWorker

fn default() -> Self

Returns the “default value” for a type.

impl ModelWorker for EchoWorker

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

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

Perform inference on the given prompt.

fn infer_stream<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<TokenStream, OrchestratorError>> + Send + 'async_trait>>

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

Stream inference tokens as they arrive from the provider.