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

    Type Alias LLMReservationOverride

    LLMReservationOverride: TokenEstimate & { reserved?: number }

    Accepted shape for the per-call reservation override (v3.8).

    Structurally this is a TokenEstimate plus an optional reserved field, which means the object returned by bulkhead.estimate() (an LLMReservationEstimate) can be passed back verbatim — no need to strip reserved first. When reserved is present it is treated as a consistency check: it must equal input + maxOutput, otherwise admission throws. This catches hand-built overrides whose fields drifted apart (e.g. a cached reserved paired with edited parts).

    Type Declaration

    • Optionalreserved?: number

      Optional cross-check; must equal input + maxOutput when present.