Struct AiExperiments 

pub struct AiExperiments {
    pub prompts: BTreeMap<String, AiPromptVersions>,
    pub ab_tests: BTreeMap<String, AiAbTest>,
    pub evals: BTreeMap<String, AiEval>,
    pub feedback: Option<AiFeedbackConfig>,
}

Prompt experimentation (DW-086 ai.experiments): prompt versioning, A/B model comparison, regression evals, and feedback ingestion. Absent (the default): no experiments surface.

Fields

prompts: BTreeMap<String, AiPromptVersions>

Named prompt version sets (DW-086). Each entry declares one or more versions (each with a system message) and an active version. The active version can be overridden at runtime via the admin API (stored in the state store). Absent (the default): no prompt versioning.

ab_tests: BTreeMap<String, AiAbTest>

Named A/B tests (DW-086). Each test declares two or more variants (each naming a model alias, an optional prompt version, and a weight). A model alias declares ab_test: <name> to be served by one; the test is evaluated per request (a deterministic weighted pick by request id selects a variant). Absent (the default): no A/B tests.

evals: BTreeMap<String, AiEval>

Named regression evals (DW-086). Each eval declares a golden set of input/expected cases and an optional prompt version; the admin API runs it against a model alias (or an A/B test’s variants) and stores the results. Absent (the default): no evals.

feedback: Option<AiFeedbackConfig>

Feedback ingestion config (DW-086). When enabled, the admin API accepts feedback records (request id, label, comment) and stores them in analytics. Absent (the default): feedback is enabled (the default is enabled: true).

Trait Implementations

impl Clone for AiExperiments

fn clone(&self) -> AiExperiments

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AiExperiments

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

Formats the value using the given formatter.

impl Default for AiExperiments

fn default() -> AiExperiments

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AiExperiments

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for AiExperiments

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for AiExperiments

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

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 AiExperiments