Struct RunnerResponse 

pub struct RunnerResponse {
    pub task_id: String,
    pub attempt_id: String,
    pub replacement: String,
    pub model: Option<String>,
    pub prompt_hash: Option<String>,
    pub metadata: Option<Value>,
}

One line the runner writes back for one task.

Only replacement is required beyond the identifiers; the span and file are taken from the mined task, so the runner stays a pure text producer.

Fields

task_id: String

Task this reply answers; advisory, since pairing is positional.

attempt_id: String

Identifier for this attempt; defaults to attempt when omitted.

replacement: String

New content the runner proposes for the task’s editable span.

model: Option<String>

Model the runner used, when it reports one.

prompt_hash: Option<String>

Hash of the prompt the runner built, when it reports one.

metadata: Option<Value>

Free-form runner metadata (cost, latency, sampling settings).

Trait Implementations

impl Clone for RunnerResponse

fn clone(&self) -> RunnerResponse

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RunnerResponse

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for RunnerResponse

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for RunnerResponse

impl PartialEq for RunnerResponse

fn eq(&self, other: &RunnerResponse) -> 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 RunnerResponse

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for RunnerResponse