CompiledRoutingPolicy

Enum CompiledRoutingPolicy 

Source
pub enum CompiledRoutingPolicy {
    FallbackChain {
        name: String,
        cheap: Box<RouteTarget>,
        escalate_to: Box<RouteTarget>,
        classifier_url: String,
        classifier_model: String,
        threshold: f64,
        timeout_ms: u64,
        api_key: Option<String>,
    },
    LatencyCost {
        name: String,
        candidates: Vec<RouteTarget>,
        candidate_models: Vec<String>,
        candidate_costs: Vec<u32>,
        candidate_latencies: Vec<u32>,
        preference: AiLatencyPreference,
        live_tracker: Option<Arc<LiveLatencyTracker>>,
    },
}
Expand description

A compiled routing policy (DW-085). Built at AiRuntime compile time from the config block; immutable once built. The evaluate method returns the candidate list to walk (the same shape as AiRuntime::route) plus a PolicyDecision the dataplane records as a metric.

Variants§

§

FallbackChain

Cheap-first with complexity-signal escalation. The evaluate call POSTs the prompt to the external classifier service and picks the cheap or escalate-to target by the returned score.

Fields

§name: String

The routing-policy name (for metrics attribution).

§cheap: Box<RouteTarget>

The primary target of the cheap alias.

§escalate_to: Box<RouteTarget>

The primary target of the escalate_to alias.

§classifier_url: String

The classifier service URL.

§classifier_model: String

The model name passed to the classifier service.

§threshold: f64

The complexity score threshold (>= escalates).

§timeout_ms: u64

The classifier HTTP timeout in milliseconds.

§api_key: Option<String>

Optional resolved API key for the classifier service.

§

LatencyCost

Latency-vs-cost static selection. Candidates are pre-sorted at compile time by the configured preference; evaluate returns the best one (no I/O).

Fields

§name: String

The routing-policy name (for metrics attribution).

§candidates: Vec<RouteTarget>

Candidates sorted best-first by the preference (the first is the pick).

§candidate_models: Vec<String>

AI-15 (#203): the model alias for each candidate (for live latency tracking). Parallel to candidates.

§candidate_costs: Vec<u32>

AI-15 (#203): the static cost scores for each candidate.

§candidate_latencies: Vec<u32>

AI-15 (#203): the static latency scores for each candidate.

§preference: AiLatencyPreference

AI-15 (#203): the selection preference.

§live_tracker: Option<Arc<LiveLatencyTracker>>

AI-15 (#203): live latency tracker. None when live is false (static selection).

Implementations§

Source§

impl CompiledRoutingPolicy

Source

pub fn compile( name: &str, policy: &AiRoutingPolicy, models: &BTreeMap<String, CompiledModel>, ) -> Option<Self>

Compile from config. Resolves each named alias to its primary RouteTarget against the first-pass compiled model map (plain chain/canary aliases only — a policy alias cannot reference another policy alias, so nested policies are rejected by returning None). Returns None when a referenced alias is missing or is itself a policy alias (a validate-vs-build race or an authoring error validation missed).

Source

pub async fn evaluate( &self, prompt_text: &str, ) -> (Vec<RouteTarget>, PolicyDecision)

Evaluate the policy for one request. Returns the candidate list to walk (the same shape as AiRuntime::route) plus a PolicyDecision the dataplane records as a metric. For FallbackChain, this calls the external classifier service (async). For LatencyCost, the candidates are pre-sorted at compile time, so this is effectively synchronous.

Source

pub fn name(&self) -> &str

The routing-policy name (for metrics attribution).

Source

pub fn live_tracker(&self) -> Option<&Arc<LiveLatencyTracker>>

AI-15 (#203): Get the live latency tracker for this policy. Returns None when live tracking is not enabled.

Trait Implementations§

Source§

impl Clone for CompiledRoutingPolicy

Source§

fn clone(&self) -> CompiledRoutingPolicy

Returns a duplicate of the value. Read more
1.0.0 · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Debug for CompiledRoutingPolicy

Source§

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

Formats the value using the given formatter. 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
§

impl<T> AnyExt for T
where T: Any + ?Sized,

§

fn downcast_ref<T>(this: &Self) -> Option<&T>
where T: Any,

Attempts to downcast this to T behind reference
§

fn downcast_mut<T>(this: &mut Self) -> Option<&mut T>
where T: Any,

Attempts to downcast this to T behind mutable reference
§

fn downcast_rc<T>(this: Rc<Self>) -> Result<Rc<T>, Rc<Self>>
where T: Any,

Attempts to downcast this to T behind Rc pointer
§

fn downcast_arc<T>(this: Arc<Self>) -> Result<Arc<T>, Arc<Self>>
where T: Any,

Attempts to downcast this to T behind Arc pointer
§

fn downcast_box<T>(this: Box<Self>) -> Result<Box<T>, Box<Self>>
where T: Any,

Attempts to downcast this to T behind Box pointer
§

fn downcast_move<T>(this: Self) -> Option<T>
where T: Any, Self: Sized,

Attempts to downcast owned Self to T, useful only in generic context as a workaround for specialization
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<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
§

impl<T, X> CoerceTo<T> for X
where T: CoerceFrom<X> + ?Sized,

§

fn coerce_rc_to(self: Rc<X>) -> Rc<T>

§

fn coerce_box_to(self: Box<X>) -> Box<T>

§

fn coerce_ref_to(&self) -> &T

§

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

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.

§

impl<T> Instrument for T

§

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

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

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
§

impl<T> Pointable for T

§

const ALIGN: usize

The alignment of pointer.
§

type Init = T

The type for initializers.
§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
§

impl<T> ServiceExt for T

§

fn map_response_body<F>(self, f: F) -> MapResponseBody<Self, F>
where Self: Sized,

Apply a transformation to the response body. Read more
§

fn trace_for_http(self) -> Trace<Self, SharedClassifier<ServerErrorsAsFailures>>
where Self: Sized,

High level tracing that classifies responses using HTTP status codes. Read more
§

fn trace_for_grpc(self) -> Trace<Self, SharedClassifier<GrpcErrorsAsFailures>>
where Self: Sized,

High level tracing that classifies responses using gRPC headers. Read more
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.
§

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

§

fn vzip(self) -> V

§

impl<T> WithSubscriber for T

§

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
§

fn with_current_subscriber(self) -> WithDispatch<Self>

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

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

§

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

§

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