Struct InferenceResponse 

pub struct InferenceResponse {
    pub text: String,
    pub model_used: String,
    pub input_tokens: u64,
    pub output_tokens: u64,
}

One completion result.

Both token counts are host measurements, not provider-reported figures: the host counts the outgoing payload and the raw driver response with the same tiktoken convention the agent loop uses for its own turns. A driver that reports a usage block reaches the session trace with it, never these fields. model-used is likewise the model string the host sent — the driver wire format never echoes back a confirmed model name.

Fields

text: String

Concatenated text content of the driver’s response.

model_used: String

The model string the host sent for this call.

input_tokens: u64

Host-side token count of the outgoing request payload.

output_tokens: u64

Host-side token count of the raw driver response.

Trait Implementations

impl Clone for InferenceResponse

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl ComponentType for InferenceResponse

impl Debug for InferenceResponse

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for InferenceResponse

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Lift for InferenceResponse

impl Lower for InferenceResponse

impl Serialize for InferenceResponse

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

where __S: Serializer,

Serialize this value into the given Serde serializer.