async-bulkhead-llm - v3.17.0
    Preparing search index...

    Type Alias LLMAdmissionClassStats

    async-bulkhead-llm — public API surface.

    This entry point re-exports everything the package supports; the implementation lives in focused modules:

    • types.ts — request/result/options/stats/event types
    • errors.tsLLMBulkheadRejectedError
    • profiles.tsPROFILES presets
    • estimators.ts — naive + model-aware estimators, extractTextLength
    • adaptive.tscreateAdaptiveTokenEstimator (v3.8)
    • dedup.ts — deduplication internals (keying, share safety)
    • validation.ts — internal numeric/estimate/usage guards
    • bulkhead.tscreateLLMBulkhead (admission, budget, events)

    Deep-importing the internal modules is not supported; the package exports map exposes only this entry point.

    type LLMAdmissionClassStats = {
        admitted: number;
        borrowedConcurrencyAbandoned: number;
        borrowedConcurrent: number;
        borrowedInFlightTokens: number;
        inFlight: number;
        inFlightTokens: number;
        limits: LLMAdmissionClassLimits;
        protectedConcurrentInUse: number;
        protectedTokensInUse: number;
        rejected: number;
        rejectedByReason: Partial<Record<LLMRejectReason, number>>;
        released: number;
        totalBorrowedAdmissions: number;
        totalBorrowedTokensReserved: number;
        totalConsumed: number;
        totalOverrun: number;
        totalRefunded: number;
        totalReserved: number;
    }
    Index
    admitted: number
    borrowedConcurrencyAbandoned: number

    Borrowed class concurrency slots returned before final settlement.

    borrowedConcurrent: number
    borrowedInFlightTokens: number
    inFlight: number
    inFlightTokens: number
    protectedConcurrentInUse: number
    protectedTokensInUse: number
    rejected: number
    rejectedByReason: Partial<Record<LLMRejectReason, number>>
    released: number
    totalBorrowedAdmissions: number

    Admissions whose concurrency slot came from shared capacity.

    totalBorrowedTokensReserved: number

    Reservation tokens placed in shared capacity at admission time.

    totalConsumed: number
    totalOverrun: number
    totalRefunded: number
    totalReserved: number