Struct LoopRunner 

pub struct LoopRunner<'a> { /* private fields */ }

The ReAct loop execution context.

Holds references to the agent configuration and tool registry. Drives the Thought -> Action -> Observation -> FinalAnswer cycle.

Implementations

impl<'a> LoopRunner<'a>

pub fn new(config: &'a AgentConfig, registry: &'a ToolRegistry) -> Self

Creates a new runner with its own conversation history.

pub fn step(&mut self, llm_response: &str) -> Result<ReActStep, AgentError>

Processes one LLM response, dispatching tool calls when the response is an Action.

In production llm_response comes from an LLM API call. Accepting it as a parameter keeps the runner pure and fully testable without I/O.

Errors

• AgentError::ParseError — response does not match any ReAct format.
• AgentError::ToolNotFound — the requested tool is not in the registry.

pub fn run_scripted(&mut self, responses: &[&str]) -> Result<String, AgentError>

Runs a pre-scripted sequence of LLM responses, returning the final answer.

Useful for offline simulation and deterministic testing.

Errors

• AgentError::MaxIterationsExceeded — sequence exhausted before a FinalAnswer.
• Any error from step.

pub fn history(&self) -> &ConversationHistory

Returns a reference to the accumulated conversation history.

pub fn iteration_count(&self) -> usize

Returns the number of messages currently in the history.