Struct JudgeTask 

pub struct JudgeTask {
    pub eval_id: String,
    pub condition: String,
    pub run_index: Option<u32>,
    pub assertion_id: String,
    pub rubric: String,
    pub model: Option<String>,
    pub is_meta: bool,
    pub run_record_path: String,
    pub outputs_dir: String,
    pub response_path: String,
    pub dispatch_prompt_path: String,
    pub dispatch_prompt: String,
}

One judge task. dispatch_prompt carries the full prompt in memory but is stripped from the serialized judge-tasks.json (the orchestrator reads it from dispatch_prompt_path instead). model is always present (null or a model id).

Fields

eval_id: String

condition: String

run_index: Option<u32>

1-based run index within a multi-run cell; absent for single-run cells.

assertion_id: String

rubric: String

model: Option<String>

is_meta: bool

run_record_path: String

outputs_dir: String

response_path: String

dispatch_prompt_path: String

dispatch_prompt: String

Trait Implementations

impl Clone for JudgeTask

fn clone(&self) -> JudgeTask

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for JudgeTask

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

Formats the value using the given formatter.

impl Serialize for JudgeTask

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

where __S: Serializer,

Serialize this value into the given Serde serializer.