Struct InferenceResponse 

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

One completion result.

The driver wire format carries no usage block and never echoes back a confirmed model name (see docs/murmur-inference-message-format.md), so model-used is the model string the host actually sent and the two token counts are computed host-side with the same tiktoken convention the agent loop uses for its own turns. They are host measurements, not provider -reported figures.

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) -> InferenceResponse

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 Lift for InferenceResponse

impl Lower for InferenceResponse