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

    Type Alias LLMObserveStats

    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.ts — LLMBulkheadRejectedError
    • profiles.ts — PROFILES presets
    • estimators.ts — naive + model-aware estimators, extractTextLength
    • adaptive.ts — createAdaptiveTokenEstimator (v3.8)
    • dedup.ts — deduplication internals (keying, share safety)
    • validation.ts — internal numeric/estimate/usage guards
    • bulkhead.ts — createLLMBulkhead (admission, budget, events)

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

    type LLMObserveStats = {
        bypassed: number;
        bypassedByReason: Partial<Record<LLMShadowableRejectReason, number>>;
        raceBypassed: number;
        totalInputTokens: number;
        totalOutputTokens: number;
        usageReported: number;
    }
    Index
    bypassed bypassedByReason raceBypassed totalInputTokens totalOutputTokens usageReported
    bypassed: number

    Callbacks executed without acquiring concurrency or token capacity.

    bypassedByReason: Partial<Record<LLMShadowableRejectReason, number>>

    Bypassed callbacks grouped by the simulated/authoritative reason.

    raceBypassed: number

    Bypasses caused by a rejection after an advisory positive decision.

    totalInputTokens: number

    Cumulative final input usage from bypassed callbacks.

    totalOutputTokens: number

    Cumulative final output usage from bypassed callbacks.

    usageReported: number

    Bypassed callbacks for which final usage was available.

    Settings
    Member Visibility

    On This Page
    Properties