pub struct CascadeConfig {
pub enabled: bool,
pub tiers: Vec<CascadeTierConfig>,
pub gate: CascadeGateConfig,
}Expand description
Model cascading configuration for cost-efficient LLM selection.
When enabled, the provider tries cheaper model tiers first and only escalates to the main (most expensive) model when the confidence gate rejects the cheaper response or the tier errors.
Fields§
§enabled: boolEnable model cascading. Default: false.
tiers: Vec<CascadeTierConfig>Model tiers from cheapest to most expensive.
The main [provider].model is always the implicit final tier.
gate: CascadeGateConfigConfidence gate configuration. Default: heuristic with sensible defaults.
Trait Implementations§
Source§impl Clone for CascadeConfig
impl Clone for CascadeConfig
Source§fn clone(&self) -> CascadeConfig
fn clone(&self) -> CascadeConfig
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 CascadeConfig
impl Debug for CascadeConfig
Source§impl<'de> Deserialize<'de> for CascadeConfig
impl<'de> Deserialize<'de> for CascadeConfig
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
Auto Trait Implementations§
impl Freeze for CascadeConfig
impl RefUnwindSafe for CascadeConfig
impl Send for CascadeConfig
impl Sync for CascadeConfig
impl Unpin for CascadeConfig
impl UnsafeUnpin for CascadeConfig
impl UnwindSafe for CascadeConfig
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