OptionaladmissionBounded policy class used for this admission, when configured.
Stable identifier of the admission this usage belongs to.
Cumulative reported consumption (input + output).
Tokens currently held against the budget for this request.
Immutable limit revision captured when this work was admitted or bypassed.
Output tokens reserved for this request (max_tokens/outputCap).
Output reservation remaining before the stream overruns it.
True once cumulative consumption exceeds the original reservation.
Original pre-admission reservation (0 when budget disabled).
Last effective usage-update sequence for this admission. Starts at 0 before any effective report, increments when cumulative usage increases or the effective held-token amount changes, and remains stable for stale/no-op reports.
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 typeserrors.ts—LLMBulkheadRejectedErrorprofiles.ts—PROFILESpresetsestimators.ts— naive + model-aware estimators,extractTextLengthadaptive.ts—createAdaptiveTokenEstimator(v3.8)dedup.ts— deduplication internals (keying, share safety)validation.ts— internal numeric/estimate/usage guardsbulkhead.ts—createLLMBulkhead(admission, budget, events)Deep-importing the internal modules is not supported; the package
exportsmap exposes only this entry point.