Struct IterativeProblemSolver 

pub struct IterativeProblemSolver { /* private fields */ }

An agent that iteratively attempts to solve a problem using available tools.

The solver uses a chat-based approach to break down and solve complex problems. It will continue attempting to solve the problem until it either succeeds, fails explicitly, or reaches the maximum number of iterations.

Examples

use mojentic::agents::IterativeProblemSolver;
use mojentic::llm::{LlmBroker, LlmGateway};
use mojentic::llm::gateways::OllamaGateway;
use mojentic::llm::tools::simple_date_tool::SimpleDateTool;
use std::sync::Arc;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let gateway = Arc::new(OllamaGateway::default());
    let broker = LlmBroker::new("qwen3:32b", gateway, None);

    let tools: Vec<Box<dyn LlmTool>> = vec![Box::new(SimpleDateTool)];

    let solver = IterativeProblemSolver::builder(broker)
        .tools(tools)
        .max_iterations(5)
        .build();

    let result = solver.solve("What's the date next Friday?").await?;
    println!("Result: {}", result);

    Ok(())
}

Implementations

impl IterativeProblemSolver

pub fn new(broker: LlmBroker) -> Self

Create a new problem solver with default settings.

Arguments

• broker - The LLM broker to use for generating responses

Examples

use mojentic::agents::IterativeProblemSolver;
use mojentic::llm::LlmBroker;

let solver = IterativeProblemSolver::new(broker);

pub fn builder(broker: LlmBroker) -> IterativeProblemSolverBuilder

Create a problem solver builder for custom configuration.

Arguments

• broker - The LLM broker to use for generating responses

Examples

use mojentic::agents::IterativeProblemSolver;

let solver = IterativeProblemSolver::builder(broker)
    .max_iterations(10)
    .system_prompt("You are a specialized problem solver.")
    .tools(vec![Box::new(SimpleDateTool)])
    .build();

pub async fn solve(&mut self, problem: &str) -> Result<String>

Execute the problem-solving process.

This method runs the iterative problem-solving process, continuing until one of these conditions is met:

• The task is completed successfully (response contains “DONE”)
• The task fails explicitly (response contains “FAIL”)
• The maximum number of iterations is reached

After completion, the agent requests a summary of the final result.

Arguments

• problem - The problem or request to be solved

Returns

A summary of the final result, excluding the process details

Examples

let result = solver.solve("Calculate the date 7 days from now").await?;
println!("Solution: {}", result);