@juspay/neurolink/dist/types/decision.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

/**
 * Decision inference types — typed, calibrated judgements from a model that
 * emits no text.
 *
 * `decide` is the third inference type, alongside `generate` and `stream`. A
 * decision model takes one `state` plus a map of named typed questions and
 * returns one typed answer per question, all evaluated in a single parallel
 * pass. TypeSafe's Jev is the first such model; Vercel's AI SDK models the
 * same class separately from `LanguageModelV4`, for the same reason.
 *
 * The vocabulary here is deliberately **provider-neutral**. TypeSafe calls a
 * yes/no question a `noul` and answers it in a field of the same name; both
 * the Vercel AI SDK and Pydantic AI independently renamed that to `boolean` /
 * `probability` when exposing it. This file follows them, and the mapping to
 * a vendor's wire format belongs in that vendor's provider.
 *
 * Names are domain-prefixed `Decision*` to stay globally unique across
 * `src/lib/types/` (CLAUDE.md rule 9). Note `evaluate`/`Evaluation*` is a
 * different, unrelated feature — scoring a generated response with RAGAS.
 */
export {};