Skip to main content

Scorer

everruns_core::eval

Enum Scorer 

Source 
pub enum Scorer {
    Contains {
        text: String,
        weight: f64,
    },
    NotContains {
        text: String,
        weight: f64,
    },
    Regex {
        pattern: String,
        weight: f64,
    },
    ToolCalled {
        tool: String,
        min: u32,
        weight: f64,
    },
    ToolNotCalled {
        tool: String,
        weight: f64,
    },
    ToolCallCount {
        min: Option<u32>,
        max: Option<u32>,
        weight: f64,
    },
    TurnsWithin {
        max: u32,
        weight: f64,
    },
    FileContains {
        path: String,
        text: String,
        weight: f64,
    },
    JsonSchema {
        schema: Value,
        weight: f64,
    },
    CitationFaithful {
        min_citations: u32,
        pass_threshold: f64,
        weight: f64,
    },
    CitationJudged {
        rubric: Option<String>,
        model_id: Option<ModelId>,
        pass_threshold: f64,
        weight: f64,
    },
}
Expand description

A scoring rule applied to eval case output.

Variants§

§

Contains

Final assistant message contains substring.

Fields

§text: String
§weight: f64
§

NotContains

Final assistant message does NOT contain substring.

Fields

§text: String
§weight: f64
§

Regex

Final assistant message matches regex pattern.

Fields

§pattern: String
§weight: f64
§

ToolCalled

Agent called named tool at least min times.

Fields

§tool: String
§min: u32
§weight: f64
§

ToolNotCalled

Agent did NOT call named tool.

Fields

§tool: String
§weight: f64
§

ToolCallCount

Total tool calls within range.

Fields

§min: Option<u32>
§max: Option<u32>
§weight: f64
§

TurnsWithin

Completed within N turns.

Fields

§max: u32
§weight: f64
§

FileContains

Session filesystem file contains substring.

Fields

§path: String
§text: String
§weight: f64
§

JsonSchema

Final assistant message parses as JSON matching schema.

Fields

§schema: Value
§weight: f64
§

CitationFaithful

Citation faithfulness: the answer’s citations (see specs/citations.md) must cover the claim and be verified as supported. Scored from the TextAnnotations on the final message — pair with the citation_verification capability so verdicts are present.

Fields

§min_citations: u32

Minimum number of citations the answer must carry.

§pass_threshold: f64

Minimum fraction of citations verified entailed to pass.

§weight: f64

Relative weight of this scorer in the case’s weighted average.

§

CitationJudged

Citation faithfulness judged by an LLM: each cited claim/source pair is graded by a model, so the eval works even without the citation_verification capability. See specs/citations.md.

Fields

§rubric: Option<String>

Rubric override; a citation-faithfulness rubric is used when absent.

§model_id: Option<ModelId>

Judge model; the org’s default is used when absent.

§pass_threshold: f64

Minimum judged score [0,1] to pass.

§weight: f64

Relative weight of this scorer in the case’s weighted average.

Implementations§

Source§

impl Scorer

Source

pub fn kind(&self) -> &'static str

Stable kind tag for this scorer, matching the serde type discriminant.

Scores are persisted as an ordered Vec<Score> that carries no scorer identity, so consumers that need a name (e.g. dataset export) join this positionally against the case’s scorers. Keep this exhaustive so adding a variant forces a decision here.

Trait Implementations§

Source§

impl Clone for Scorer

Source§

fn clone(&self) -> Scorer

Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Debug for Scorer

Source§

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

Formats the value using the given formatter. Read more
Source§

impl<'de> Deserialize<'de> for Scorer

Source§

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>
where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer. Read more
Source§

impl Serialize for Scorer

Source§

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

Serialize this value into the given Serde serializer. Read more

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<T> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. Read more
Source§

impl<T> DeserializeOwned for T
where T: for<'de> Deserialize<'de>,

Source§

impl<T> DynClone for T
where T: Clone,

Source§

fn __clone_box(&self, _: Private) -> *mut ()

Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> FromRef<T> for T
where T: Clone,

Source§

fn from_ref(input: &T) -> T

Converts to this type from a reference to the input type.
Source§

impl<T> FutureExt for T

Source§

fn with_context(self, otel_cx: Context) -> WithContext<Self>

Attaches the provided Context to this type, returning a WithContext wrapper. Read more
Source§

fn with_current_context(self) -> WithContext<Self>

Attaches the current Context to this type, returning a WithContext wrapper. Read more
Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

impl<T> IntoRequest<T> for T

Source§

fn into_request(self) -> Request<T>

Wrap the input message T in a tonic::Request
Source§

impl<L> LayerExt<L> for L

Source§

fn named_layer<S>(&self, service: S) -> Layered<<L as Layer<S>>::Service, S>
where L: Layer<S>,

Applies the layer to a service and wraps it in Layered.
Source§

impl<T> ParallelSend for T

Source§

impl<T> PolicyExt for T
where T: ?Sized,

Source§

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Sized + Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns Action::Follow only if self and other return Action::Follow. Read more
Source§

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Sized + Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns Action::Follow if either self or other returns Action::Follow. Read more
Source§

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,

Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more