@juspay/neurolink/dist/types/requestRouter.js

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

/**
 * Pluggable pre-call request router types.
 *
 * A RequestRouter is a host-supplied async function that inspects lightweight
 * request characteristics (token estimate, tools, vision, thinking) and
 * returns an optional provider/model/region override.  The router runs only
 * when the host opts in (by passing `requestRouter` or `modelPool` to
 * the NeuroLink constructor) and only when the user did NOT explicitly set
 * BOTH `options.provider` AND `options.model` on the call (a partial pin —
 * e.g. only `options.provider` — still allows the router to run).
 *
 * Everything fails open: if the router throws or returns an empty decision the
 * call proceeds with whatever provider/model was configured by the caller.
 */
export {};