Struct AgentPool 

pub struct AgentPool { /* private fields */ }

A collection of agents for group execution.

AgentPool takes ownership of a Vec<Agent> and provides sequential pipeline execution where each agent’s output feeds into the next agent’s input.

Example

use traitclaw_core::pool::AgentPool;
use traitclaw_core::agent::Agent;

let pool = AgentPool::new(agents);
assert_eq!(pool.len(), 3);

Implementations

impl AgentPool

pub fn new(agents: Vec<Agent>) -> Self

Create a new pool from a vector of agents.

pub fn len(&self) -> usize

Returns the number of agents in the pool.

pub fn is_empty(&self) -> bool

Returns true if the pool contains no agents.

pub fn get(&self, index: usize) -> Option<&Agent>

Get a reference to an agent by index.

Returns None if the index is out of bounds.

pub async fn run_sequential(&self, input: &str) -> Result<AgentOutput>

Run agents sequentially, chaining outputs.

Each agent receives the previous agent’s text output as input. The first agent receives the provided input string.

Example

use traitclaw_core::pool::AgentPool;
use traitclaw_core::agent::Agent;

let output = pool.run_sequential("Research Rust async patterns").await?;
println!("Final output: {}", output.text());

Errors

Returns an error immediately if any agent in the pipeline fails. Earlier agents’ outputs are not available on error.

Trait Implementations

impl Debug for AgentPool

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.