Skip to main content

SessionBudget

Struct SessionBudget 

Source
pub struct SessionBudget { /* private fields */ }
Expand description

Thread-safe per-session token budget tracker.

All methods accept the session ID as a &str to avoid requiring a SessionId wrapper at the session-management layer.

§Thread Safety

Internally uses a Mutex<HashMap>. For very high-throughput workloads consider sharding by session prefix.

Implementations§

Source§

impl SessionBudget

Source

pub fn new() -> Self

Create a new, empty budget store.

§Panics

This function does not panic.

Source

pub fn set_limits(&self, session_id: impl Into<String>, limits: SessionLimits)

Register or update limits for a session.

If the session already exists its accumulated spend is preserved; only the limits are updated.

§Panics

This function does not panic.

Source

pub fn remove_session(&self, session_id: &str)

Remove a session from the budget store entirely.

Useful when a session is logically closed and its budget data no longer needs to be retained.

§Panics

This function does not panic.

Source

pub fn record_tokens( &self, session_id: &str, tokens: u64, ) -> Result<BudgetOutcome, BudgetError>

Record tokens spent by session_id and check against limits.

§Hard limit enforcement

If adding tokens would cause accumulated spend to reach or exceed hard_limit_tokens, the spend is not recorded and Err(BudgetError::HardLimitExceeded) is returned. The caller should reject the underlying inference request with a clear user-facing error before dispatching to a worker.

§Soft limit warning

If the new accumulated spend crosses soft_limit_tokens the function returns Ok(BudgetOutcome::SoftLimitWarning { .. }). The request proceeds normally; callers may choose to surface a warning to the user.

§Unregistered sessions

Sessions with no registered limits are silently accepted — all spend calls return Ok(BudgetOutcome::Ok) and no tracking is performed.

§Errors

Returns BudgetError::HardLimitExceeded when the hard limit is hit.

§Panics

This function does not panic.

Source

pub fn reset_session(&self, session_id: &str)

Reset accumulated spend to zero without changing the session limits.

This is the operation behind POST /v1/sessions/{id}/budget/reset.

Does nothing if the session is not registered (no-op, not an error).

§Panics

This function does not panic.

Source

pub fn daily_reset(&self) -> usize

Perform a daily reset: zero the spend of every session whose last_reset was more than 24 hours ago (or was never set).

Intended to be called from a background task, e.g.:

use tokio::time::{interval, Duration};
use tokio_prompt_orchestrator::session::budget::SessionBudget;
use std::sync::Arc;

async fn daily_reset_task(budget: Arc<SessionBudget>) {
    let mut ticker = interval(Duration::from_secs(60 * 60)); // check hourly
    loop {
        ticker.tick().await;
        let count = budget.daily_reset();
        if count > 0 {
            tracing::info!(count, "daily budget reset applied to sessions");
        }
    }
}
§Returns

Number of sessions whose budget was reset.

§Panics

This function does not panic.

Source

pub fn snapshot(&self, session_id: &str) -> Option<SessionBudgetSnapshot>

Return a snapshot of the given session’s budget.

This is the backing data for GET /v1/sessions/{id}/budget.

Returns None if the session has not been registered.

§Panics

This function does not panic.

Source

pub fn all_snapshots(&self) -> Vec<SessionBudgetSnapshot>

Return snapshots for all tracked sessions.

§Panics

This function does not panic.

Source

pub fn session_count(&self) -> usize

Return the number of sessions currently tracked.

§Panics

This function does not panic.

Trait Implementations§

Source§

impl Debug for SessionBudget

Source§

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

Formats the value using the given formatter. Read more
Source§

impl Default for SessionBudget

Source§

fn default() -> SessionBudget

Returns the “default value” for a type. 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
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
§

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,

Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> FutureExt for T

§

fn with_context(self, otel_cx: Context) -> WithContext<Self>

Attaches the provided Context to this type, returning a WithContext wrapper. Read more
§

fn with_current_context(self) -> WithContext<Self>

Attaches the current Context to this type, returning a WithContext wrapper. Read more
§

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> IntoRequest<T> for T

Source§

fn into_request(self) -> Request<T>

Wrap the input message T in a tonic::Request
§

impl<T> PolicyExt for T
where T: ?Sized,

§

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Sized + Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns [Action::Follow] only if self and other return Action::Follow. Read more
§

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Sized + Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns [Action::Follow] if either self or other returns Action::Follow. Read more
§

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

Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
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