Struct DagWorkflow 

pub struct DagWorkflow { /* private fields */ }

DAG workflow: nodes execute in topological order; independent nodes run concurrently.

Each node receives the concatenated outputs of all its predecessors (joined by newlines) as input; root nodes with zero in-degree receive the workflow’s original input.

Example

use echo_core::agent::{Agent, AgentEvent};
use echo_core::error::Result;
use echo_orchestration::workflow::{DagWorkflow, Workflow};
use futures::future::BoxFuture;
use futures::stream::{self, BoxStream};


let researcher = DummyAgent::new("researcher");
let analyst = DummyAgent::new("analyst");
let writer = DummyAgent::new("writer");

let mut wf = DagWorkflow::builder()
    .node("research", researcher)
    .node("analyze", analyst)
    .node("write", writer)
    .edge("research", "write")
    .edge("analyze", "write")
    .build()?;

let output = wf.run("Analyze the 2025 AI Agent ecosystem").await?;
println!("{}", output.result);

Implementations

impl DagWorkflow

pub fn builder() -> DagWorkflowBuilder

Trait Implementations

impl Workflow for DagWorkflow

fn run<'a>( &'a mut self, input: &'a str, ) -> Pin<Box<dyn Future<Output = Result<WorkflowOutput, ReactError>> + Send + 'a>>

Run the entire workflow with input as the initial input

fn run_stream<'a>( &'a mut self, input: &'a str, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<WorkflowEvent, ReactError>> + Send + 'a>>, ReactError>> + Send + 'a>>

Run the entire workflow with input as initial input (streaming per-node events).