pub enum EvalLayer {
Reasoning,
Action,
Execution,
Safety,
Cost,
}Expand description
The layer of agent behavior being evaluated.
Each evaluator belongs to exactly one layer. Layers enable aggregation and filtering of scores by concern.
Variants§
Reasoning
Reasoning quality — coherence, completeness, logical soundness.
Action
Action quality — tool usage correctness, argument validity.
Execution
Execution quality — efficiency, iteration count, token usage.
Safety
Safety — policy compliance, blocklist checks, capability enforcement.
Cost
Cost — budget adherence, spend velocity, resource efficiency.
Implementations§
Trait Implementations§
Source§impl<'de> Deserialize<'de> for EvalLayer
impl<'de> Deserialize<'de> for EvalLayer
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 Copy for EvalLayer
impl Eq for EvalLayer
impl StructuralPartialEq for EvalLayer
Auto Trait Implementations§
impl Freeze for EvalLayer
impl RefUnwindSafe for EvalLayer
impl Send for EvalLayer
impl Sync for EvalLayer
impl Unpin for EvalLayer
impl UnsafeUnpin for EvalLayer
impl UnwindSafe for EvalLayer
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
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
Source§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
Source§fn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
Compare self to
key and return true if they are equal.