pub struct EvalCase {
pub version: u32,
pub id: String,
pub title: String,
pub category: String,
pub mode: EvalMode,
pub task: String,
pub setup: Vec<VerifierSpec>,
pub verifiers: Vec<VerifierSpec>,
pub tags: Vec<String>,
pub notes: Option<String>,
pub metadata: BTreeMap<String, String>,
}Expand description
A versioned, replayable eval case.
Fields§
§version: u32Schema version for forward compatibility.
id: StringStable eval id, unique within a suite.
title: StringHuman-readable title.
category: StringSuite category, e.g. “simple_repo_task” or “security_stress”.
mode: EvalModeHarness mode this case is intended to measure.
task: StringUser-facing task prompt or objective.
setup: Vec<VerifierSpec>Optional setup commands, run before verifiers.
verifiers: Vec<VerifierSpec>Required and optional verification commands.
Tags for filtering/reporting.
notes: Option<String>Optional notes for humans.
metadata: BTreeMap<String, String>Extensible metadata for future routing/training.
Implementations§
Trait Implementations§
Source§impl<'de> Deserialize<'de> for EvalCase
impl<'de> Deserialize<'de> for EvalCase
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
impl StructuralPartialEq for EvalCase
Auto Trait Implementations§
impl Freeze for EvalCase
impl RefUnwindSafe for EvalCase
impl Send for EvalCase
impl Sync for EvalCase
impl Unpin for EvalCase
impl UnsafeUnpin for EvalCase
impl UnwindSafe for EvalCase
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more