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

    Type Alias LLMPriority

    LLMPriority: "high" | "normal"

    Admission priority.

    "high" requests may use the full token budget. "normal" requests (the default) are rejected once available budget drops to tokenBudget.highPriorityReserve, keeping headroom for high-priority traffic. Priority has no effect when tokenBudget is not configured or highPriorityReserve is 0/unset.