Skip to main content

Agent

molo_agent::agent

Trait Agent 

Source 
pub trait Agent {
    // Required method
    fn run_request_with_context<'life0, 'async_trait>(
        &'life0 mut self,
        request: RunRequest,
        context: RunContext,
    ) -> Pin<Box<dyn Future<Output = Result<RunOutput, AgentError>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait;

    // Provided methods
    fn run_request<'life0, 'async_trait>(
        &'life0 mut self,
        request: RunRequest,
    ) -> Pin<Box<dyn Future<Output = Result<RunOutput, AgentError>> + Send + 'async_trait>>
       where Self: Send + 'async_trait,
             'life0: 'async_trait { ... }
    fn run<'life0, 'life1, 'async_trait>(
        &'life0 mut self,
        input: &'life1 str,
    ) -> Pin<Box<dyn Future<Output = Result<String, AgentError>> + Send + 'async_trait>>
       where Self: Send + 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait { ... }
    fn run_stream_request_with_context<'a, 'async_trait>(
        &'a mut self,
        request: RunRequest,
        context: RunContext,
    ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'a, Result<MessageChunk, AgentError>>, AgentError>> + Send + 'async_trait>>
       where Self: Send + 'async_trait,
             'a: 'async_trait { ... }
    fn run_stream_request<'a, 'async_trait>(
        &'a mut self,
        request: RunRequest,
    ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'a, Result<MessageChunk, AgentError>>, AgentError>> + Send + 'async_trait>>
       where Self: Send + 'async_trait,
             'a: 'async_trait { ... }
    fn run_stream<'a, 'async_trait>(
        &'a mut self,
        input: &'a str,
    ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'a, Result<MessageChunk, AgentError>>, AgentError>> + Send + 'async_trait>>
       where Self: Send + 'async_trait,
             'a: 'async_trait { ... }
}
Expand description

Reasoning-loop interface: one run takes the user input, drives the reasoning loop, and returns the final answer.

Every reasoning loop (the built-in ReActAgent and custom implementations) implements this trait. Cooperative cancellation and deadlines are carried through RunContext.

The streaming and non-streaming entry points share the same semantics: the reply is either given whole (run) or returned as a MessageChunk stream (run_stream, ending with MessageChunk::Done).

Required Methods§

Source

fn run_request_with_context<'life0, 'async_trait>( &'life0 mut self, request: RunRequest, context: RunContext, ) -> Pin<Box<dyn Future<Output = Result<RunOutput, AgentError>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait,

One structured run with caller-provided execution context.

§Errors

Returns AgentError::Memory when context access fails; AgentError::Provider when communicating with the LLM fails; AgentError::TooManyToolRounds when the model keeps requesting tools beyond AgentConfig::max_tool_rounds without a final answer; AgentError::Cancelled when the run is cooperatively cancelled; AgentError::DeadlineExceeded when the run-level deadline elapses.

Provided Methods§

Source

fn run_request<'life0, 'async_trait>( &'life0 mut self, request: RunRequest, ) -> Pin<Box<dyn Future<Output = Result<RunOutput, AgentError>> + Send + 'async_trait>>
where Self: Send + 'async_trait, 'life0: 'async_trait,

One structured run with a generated RunContext.

Source

fn run<'life0, 'life1, 'async_trait>( &'life0 mut self, input: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<String, AgentError>> + Send + 'async_trait>>
where Self: Send + 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

One run: record the user input, drive the reasoning loop, and return the model’s final answer as text.

Source

fn run_stream_request_with_context<'a, 'async_trait>( &'a mut self, request: RunRequest, context: RunContext, ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'a, Result<MessageChunk, AgentError>>, AgentError>> + Send + 'async_trait>>
where Self: Send + 'async_trait, 'a: 'async_trait,

Streaming structured run with caller-provided execution context.

Source

fn run_stream_request<'a, 'async_trait>( &'a mut self, request: RunRequest, ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'a, Result<MessageChunk, AgentError>>, AgentError>> + Send + 'async_trait>>
where Self: Send + 'async_trait, 'a: 'async_trait,

Streaming structured run with a generated RunContext.

Source

fn run_stream<'a, 'async_trait>( &'a mut self, input: &'a str, ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'a, Result<MessageChunk, AgentError>>, AgentError>> + Send + 'async_trait>>
where Self: Send + 'async_trait, 'a: 'async_trait,

Streaming run: same semantics as run, with the reply returned as a stream of message chunks (see MessageChunk), ending with MessageChunk::Done; errors are produced as Err items and terminate the stream (no Done afterwards).

The default implementation is not truly streaming — it completes the structured run first, then emits a single MessageChunk::Delta with the final answer and a MessageChunk::Done carrying the run summary. Implementations that need per-token streaming or tool progress should override this method.

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§