Struct ModelLimit 

pub struct ModelLimit {
    pub context: u64,
    pub output: u64,
}

Context window and output ceiling advertised for a model.

Fields

context: u64

Total context window (tokens) the model accepts.

output: u64

Maximum output tokens the provider advertises for one reply.

Implementations

impl ModelLimit

pub fn reserve(&self) -> u64

Tokens reserved for the reply: min(output, DEFAULT_RESERVE_CAP).

pub fn trigger(&self) -> u64

Input-token count at which the window is considered full: the context window minus the reply reserve.

pub fn is_full(&self, input_tokens: u64) -> bool

True when a provider-reported input_tokens has reached the trigger — the next request risks running past the window.

Trait Implementations

impl Clone for ModelLimit

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for ModelLimit

impl Debug for ModelLimit

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

Formats the value using the given formatter.

impl Eq for ModelLimit

impl PartialEq for ModelLimit

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for ModelLimit