@juspay/neurolink/dist/proxy/quotaHeaders.d.ts

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

/**
 * Proxy response quota headers.
 *
 * The proxy already knows, per request, exactly how much subscription capacity
 * the serving account has left — it parses Anthropic's `anthropic-ratelimit-*`
 * headers to route on them (see `accountQuota.ts`). Historically none of that
 * reached the client: only the SSE path forwarded a small legacy allowlist, and
 * every JSON/error path dropped headers entirely.
 *
 * This module turns that state into response headers in two layers:
 *
 * 1. **Verbatim passthrough** of Anthropic's own `anthropic-ratelimit-*` and
 *    `retry-after` headers. This is the load-bearing part: a proxied response
 *    then looks byte-identical to a direct one, so a consumer needs exactly one
 *    parser for both.
 * 2. **`x-neurolink-*`** for what only the proxy can know — which account
 *    served the request, pool headroom, whether the numbers are live or stale,
 *    and the derived "how much is left" percentages.
 *
 * Pure CPU, no I/O — safe on the hot path and directly unit-testable.
 *
 * @module proxy/quotaHeaders
 */
import type { AccountQuota, ProxyQuotaHeaderContext } from "../types/index.js";
/**
 * Convert a 0.0-1.0 utilization fraction into a whole-percent "left" figure.
 *
 * Anthropic publishes utilization (used), never remaining, for subscription
 * windows — there is no absolute message or token count to report, so the
 * honest derived form is a percentage. Clamped because a utilization above 1.0
 * (overage) would otherwise produce a negative "left".
 */
export declare function utilizationToLeftPct(used: number): number;
/**
 * Copy Anthropic's rate-limit headers verbatim from an upstream response.
 *
 * Covers both header families: the unified subscription windows
 * (`unified-5h-*`, `unified-7d-*`) and the legacy per-tier counters
 * (`requests-remaining`, `tokens-remaining`, ...) that API-key accounts get.
 * Which family is present depends on the serving account type, which is why
 * `x-neurolink-account-type` accompanies them.
 */
export declare function pickUpstreamRateLimitHeaders(headers: Headers | Record<string, string>): Record<string, string>;
/**
 * Build the `x-neurolink-*` half of the contract from proxy-side state.
 *
 * Always emits `x-neurolink-quota-source` — even when it is "none". A consumer
 * that sees quota numbers with no provenance cannot tell a fresh reading from a
 * snapshot carried over from a previous request, and would happily log stale
 * capacity as current.
 */
export declare function buildQuotaResponseHeaders(context: ProxyQuotaHeaderContext, now?: number): Record<string, string>;
/**
 * Full response header set: upstream verbatim + proxy-derived.
 *
 * Upstream headers are applied first so a `x-neurolink-*` key can never be
 * shadowed by an upstream one (they share no names today, but the ordering
 * makes the precedence explicit rather than incidental).
 */
export declare function buildProxyLimitHeaders(args: {
    upstreamHeaders?: Headers | Record<string, string>;
    context: ProxyQuotaHeaderContext;
    now?: number;
}): Record<string, string>;
/** Compute pool headroom from the runtime account states backing a request. */
export declare function summarizePoolHeadroom(entries: ReadonlyArray<{
    coolingUntil?: number;
    quota?: AccountQuota;
}>, now?: number): {
    available: number;
    cooling: number;
    bestSessionLeftPct?: number;
};