Struct PromptResponse 

#[non_exhaustive]
pub struct PromptResponse {
    pub output: String,
    pub usage: Usage,
    pub completion_calls: Vec<CompletionCall>,
    pub messages: Option<Vec<Message>>,
    pub content: OneOrMany<AssistantContent>,
}

The result of an agent run, returned by both the blocking (PromptRequest) and streaming (StreamingPromptRequest) surfaces so a call site reads identically whether it used .prompt() or .stream_prompt().

On the streaming surface this is the payload of the terminal MultiTurnStreamItem::FinalResponse item.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

output: String

Concatenated assistant text for the final turn.

usage: Usage

Aggregated token usage across the whole run.

completion_calls: Vec<CompletionCall>

Successfully completed completion requests made by this agent run.

usage remains the aggregate across the whole run. Use the last entry’s usage to inspect the final completion request’s prompt/context length. Zero-valued entry usage means the provider reported no usage metrics for that request.

messages: Option<Vec<Message>>

Accumulated message history for the run (the run’s persisted transcript), unless memory/history bookkeeping was disabled for the request.

content: OneOrMany<AssistantContent>

Structured assistant content for the final turn.

Where output is the concatenated text, this preserves the individual content parts (text, reasoning, images, …).

Implementations

impl PromptResponse

pub fn new(output: impl Into<String>, usage: Usage) -> Self

pub fn empty() -> Self

An empty run result (empty output, zero usage, no history).

pub fn with_messages(self, messages: Vec<Message>) -> Self

pub fn with_completion_calls( self, completion_calls: Vec<CompletionCall>, ) -> Self

Attach completion call details to this response.

pub fn with_content(self, content: OneOrMany<AssistantContent>) -> Self

Set the structured assistant content for the final turn.

pub fn output(&self) -> &str

The concatenated assistant text for the final turn.

pub fn usage(&self) -> Usage

Aggregated token usage across the whole run.

pub fn messages(&self) -> Option<&[Message]>

The run’s accumulated message history, if tracked.

pub fn content(&self) -> &OneOrMany<AssistantContent>

The structured assistant content for the final turn.

pub fn completion_calls(&self) -> &[CompletionCall]

Returns successfully completed completion requests made by this agent run.

Zero-valued entry usage means the provider reported no usage metrics for that request.

pub fn requests(&self) -> usize

Number of completion requests this agent run made.

Trait Implementations

impl Clone for PromptResponse

fn clone(&self) -> PromptResponse

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for PromptResponse

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for PromptResponse

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for PromptResponse

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

Formats the value using the given formatter.

impl Serialize for PromptResponse

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.