@juspay/neurolink/dist/routing/requestRouter.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

/**
 * Default heuristic request router.
 *
 * `createDefaultRequestRouter` produces a `RequestRouter` function that maps
 * lightweight request characteristics to a provider/model/region override.
 * It is entirely optional — hosts may supply their own `RequestRouter` function
 * instead, or disable routing entirely by not passing either.
 *
 * This PR adds `requestRouter` (and `modelPool`) as NeuroLink constructor
 * options. The router is skipped only when BOTH options.provider AND
 * options.model are explicitly set by the caller — a partial pin (e.g. only
 * provider) still allows the router to run.
 *
 * Decision logic (checked in order):
 * 1. Vision request        → visionTier
 * 2. Large input or tools  → largeTier
 * 3. Default               → smallTier (only when config.smallTier is provided)
 *
 * When none of the configured tiers matches (or when the tier is not
 * configured), the router returns `{}` which is a no-op — the caller keeps
 * whatever provider/model was set by the user.
 */
import type { DefaultRequestRouterConfig, RequestRouter } from "../types/index.js";
/**
 * Creates a heuristic `RequestRouter` from a `DefaultRequestRouterConfig`.
 *
 * @param config — optional tier overrides; built-in defaults apply when omitted.
 * @returns a synchronous `RequestRouter` function (satisfies the async signature).
 */
export declare function createDefaultRequestRouter(config?: DefaultRequestRouterConfig): RequestRouter;