Struct TypedPromptRequest 

pub struct TypedPromptRequest<'a, T, S, M, P>
where
    T: JsonSchema + DeserializeOwned + WasmCompatSend,
    S: PromptType,
    M: CompletionModel,
    P: PromptHook<M>,
{ /* private fields */ }

A builder for creating typed prompt requests that return deserialized structured output.

This struct wraps a standard PromptRequest and adds:

• Automatic JSON schema generation from the target type T
• Automatic deserialization of the response into T

The type parameter S represents the state of the request (Standard or Extended). Use .extended_details() to transition to Extended state for usage tracking.

Example

let forecast: WeatherForecast = agent
    .prompt_typed("What's the weather in NYC?")
    .max_turns(3)
    .await?;

Implementations

impl<'a, T, M, P> TypedPromptRequest<'a, T, Standard, M, P>

where T: JsonSchema + DeserializeOwned + WasmCompatSend, M: CompletionModel, P: PromptHook<M>,

pub fn from_agent( agent: &Agent<M, P>, prompt: impl Into<Message>, ) -> TypedPromptRequest<'a, T, Standard, M, P>

Create a new TypedPromptRequest from an agent.

This automatically sets the output schema based on the type parameter T.

impl<'a, T, S, M, P> TypedPromptRequest<'a, T, S, M, P>

where T: JsonSchema + DeserializeOwned + WasmCompatSend, S: PromptType, M: CompletionModel, P: PromptHook<M>,

pub fn extended_details(self) -> TypedPromptRequest<'a, T, Extended, M, P>

Enable returning extended details for responses (includes aggregated token usage).

Note: This changes the type of the response from .send() to return a TypedPromptResponse<T> struct instead of just T. This is useful for tracking token usage across multiple turns of conversation.

pub fn max_turns(self, depth: usize) -> TypedPromptRequest<'a, T, S, M, P>

Set the maximum number of turns for multi-turn conversations.

A given agent may require multiple turns for tool-calling before giving an answer. If the maximum turn number is exceeded, it will return a StructuredOutputError::PromptError wrapping a MaxTurnsError.

pub fn with_tool_concurrency( self, concurrency: usize, ) -> TypedPromptRequest<'a, T, S, M, P>

Add concurrency to the prompt request.

This will cause the agent to execute tools concurrently.

pub fn with_history( self, history: &'a mut Vec<Message>, ) -> TypedPromptRequest<'a, T, S, M, P>

Add chat history to the prompt request.

pub fn with_hook<P2>(self, hook: P2) -> TypedPromptRequest<'a, T, S, M, P2>

where P2: PromptHook<M>,

Attach a per-request hook for tool call events.

This overrides any default hook set on the agent.

Trait Implementations

impl<'a, T, M, P> IntoFuture for TypedPromptRequest<'a, T, Extended, M, P>

where T: JsonSchema + DeserializeOwned + WasmCompatSend + 'a, M: CompletionModel + 'a, P: PromptHook<M> + 'static,

type Output = Result<TypedPromptResponse<T>, StructuredOutputError>

The output that the future will produce on completion.

type IntoFuture = Pin<Box<dyn Future<Output = <TypedPromptRequest<'a, T, Extended, M, P> as IntoFuture>::Output> + Send + 'a>>

Which kind of future are we turning this into?

fn into_future( self, ) -> <TypedPromptRequest<'a, T, Extended, M, P> as IntoFuture>::IntoFuture

Creates a future from a value.

impl<'a, T, M, P> IntoFuture for TypedPromptRequest<'a, T, Standard, M, P>

where T: JsonSchema + DeserializeOwned + WasmCompatSend + 'a, M: CompletionModel + 'a, P: PromptHook<M> + 'static,

type Output = Result<T, StructuredOutputError>

The output that the future will produce on completion.

type IntoFuture = Pin<Box<dyn Future<Output = <TypedPromptRequest<'a, T, Standard, M, P> as IntoFuture>::Output> + Send + 'a>>

Which kind of future are we turning this into?

fn into_future( self, ) -> <TypedPromptRequest<'a, T, Standard, M, P> as IntoFuture>::IntoFuture

Creates a future from a value.