@juspay/neurolink/dist/models/manifests/typesafe.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

import type { ProviderModelManifest } from "../../types/index.js";
/**
 * TypeSafe (Jev) — the `decide` inference type, not text generation.
 *
 * `contextWindow` is genuinely meaningful here: it is the budget for the
 * `state` being judged, measured by bisection at ~33,000 tokens for state
 * plus the longest single question. (A separate, larger ~64,000 ceiling
 * governs state plus ALL questions; the manifest has nowhere to express a
 * second limit, and the tighter one is the safe number to publish.)
 *
 * `maxOutputTokens` is required by the manifest type but has no honest value
 * for a model that emits no text — Jev returns a handful of numbers per
 * question, so a small non-zero figure is the least misleading choice.
 * `functionCalling` and `vision` are false: it has neither.
 */
export declare const typesafeManifest: ProviderModelManifest;