pub struct RoutingRequirements {
pub max_latency_ms: Option<u64>,
pub min_quality: Option<f32>,
pub max_cost_usd: Option<f64>,
pub estimated_input_tokens: usize,
pub estimated_output_tokens: usize,
pub prefer_quality: bool,
}Expand description
SLA constraints for a single routing request.
Fields§
§max_latency_ms: Option<u64>Maximum acceptable p95 latency in milliseconds. None = no constraint.
min_quality: Option<f32>Minimum acceptable quality score. None = no constraint.
max_cost_usd: Option<f64>Maximum cost per request in USD. None = no constraint.
estimated_input_tokens: usizeEstimated number of input tokens (used for cost estimation).
estimated_output_tokens: usizeEstimated output tokens (rough guess for cost estimation).
prefer_quality: boolWhen true, ignore cost constraints and always pick the highest-quality
provider that satisfies latency requirements.
Trait Implementations§
Source§impl Clone for RoutingRequirements
impl Clone for RoutingRequirements
Source§fn clone(&self) -> RoutingRequirements
fn clone(&self) -> RoutingRequirements
Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for RoutingRequirements
impl Debug for RoutingRequirements
Auto Trait Implementations§
impl Freeze for RoutingRequirements
impl RefUnwindSafe for RoutingRequirements
impl Send for RoutingRequirements
impl Sync for RoutingRequirements
impl Unpin for RoutingRequirements
impl UnsafeUnpin for RoutingRequirements
impl UnwindSafe for RoutingRequirements
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
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
§impl<T> FutureExt for T
impl<T> FutureExt for T
§fn with_context(self, otel_cx: Context) -> WithContext<Self>
fn with_context(self, otel_cx: Context) -> WithContext<Self>
§fn with_current_context(self) -> WithContext<Self>
fn with_current_context(self) -> WithContext<Self>
§impl<T> Instrument for T
impl<T> Instrument for T
§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> IntoRequest<T> for T
impl<T> IntoRequest<T> for T
Source§fn into_request(self) -> Request<T>
fn into_request(self) -> Request<T>
Wrap the input message
T in a tonic::Request