Struct LLMResponse 

pub struct LLMResponse {
    pub content: Option<String>,
    pub tool_calls: Option<Vec<ToolCall>>,
    pub model: String,
    pub usage: Option<Usage>,
    pub finish_reason: FinishReason,
    pub reasoning: Option<String>,
    pub reasoning_details: Option<Vec<String>>,
    pub tool_references: Vec<String>,
    pub request_id: Option<String>,
    pub organization_id: Option<String>,
    pub compaction: Option<String>,
}

Universal LLM response structure

Fields

content: Option<String>

The response content text

tool_calls: Option<Vec<ToolCall>>

Tool calls made by the model

model: String

The model that generated this response

usage: Option<Usage>

Token usage statistics

finish_reason: FinishReason

Why the response finished

reasoning: Option<String>

Reasoning content (for models that support it)

reasoning_details: Option<Vec<String>>

Detailed reasoning traces (for models that support it)

tool_references: Vec<String>

Tool references for context

request_id: Option<String>

Request ID from the provider

organization_id: Option<String>

Organization ID from the provider

compaction: Option<String>

Compaction summary content from Anthropic’s server-side compaction. Populated when stop_reason is Pause (from "compaction"). The caller should pass this back in subsequent requests so the API can drop prior messages before the compaction block.

Implementations

impl LLMResponse

pub fn new(model: impl Into<String>, content: impl Into<String>) -> LLMResponse

Create a new LLM response with mandatory fields

pub fn content_text(&self) -> &str

Get content or empty string

pub fn content_string(&self) -> String

Get content as String (clone)

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<(), Error>

Formats the value using the given formatter.

impl Default for LLMResponse

fn default() -> LLMResponse

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LLMResponse

fn deserialize<__D>( __deserializer: __D, ) -> Result<LLMResponse, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for LLMResponse

fn eq(&self, other: &LLMResponse) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for LLMResponse

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for LLMResponse

impl ToOpenResponse for LLMResponse

fn to_open_response(&self, response_id: &str, model: &str) -> Response

Converts to an Open Responses Response object.