Struct LlmResponse 

pub struct LlmResponse {
    pub content: Content,
    pub finish_reason: Option<String>,
    pub usage: Option<TokenUsage>,
}

The response from an LLM generation request.

Fields

content: Content

The generated content.

finish_reason: Option<String>

Finish reason (if available).

usage: Option<TokenUsage>

Token usage (if available).

Implementations

impl LlmResponse

pub fn from_text(text: impl Into<String>) -> Self

A model turn that says text and finishes.

pub fn tool_call(name: impl Into<String>, args: Value) -> Self

A model turn that calls one tool.

pub fn tool_calls<N: Into<String>>( calls: impl IntoIterator<Item = (N, Value)>, ) -> Self

A model turn that calls several tools at once, in order.

pub fn append(&mut self, chunk: LlmResponse)

Add a streamed chunk to this response: its parts are appended (adjacent text merged), and its finish reason and usage, when present, replace these — a provider’s streamed usage is cumulative.

pub fn with_usage(self, prompt_tokens: u32, completion_tokens: u32) -> Self

Attach token usage, as a provider reports it.

pub fn text(&self) -> String

Extract text from the response, concatenating all text parts.

pub fn function_calls(&self) -> Vec<&FunctionCall>

Extract function calls from the response.

Trait Implementations

impl Clone for LlmResponse

fn clone(&self) -> LlmResponse

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LlmResponse

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for LlmResponse

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LlmResponse

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

where __S: Serializer,

Serialize this value into the given Serde serializer.