@juspay/neurolink/dist/models/manifests/huggingface.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";
/**
 * Minimal manifest: huggingface has no MODEL_REGISTRY entries today, so
 * only the provider-wide fallback is known. `functionCalling` is true
 * because the router serves tool-calling models and returns `tool_calls` for
 * them; it previously claimed false, contradicting the wire.
 *
 * Named models can be added here incrementally without touching any
 * consumer — see Task 5 of the model metadata consolidation plan.
 */
export declare const huggingfaceManifest: ProviderModelManifest;