@juspay/neurolink/dist/providers/openaiCompatCatalog.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

import { buildCatalogEntries } from "./catalog/loader.js";
/**
 * Config-driven catalog of the OpenAI-compatible providers whose only
 * differences from each other are expressible as named, closed catalog
 * quirks (messageContentFormat, timeoutErrorClass, responseFormatDowngrade)
 * rather than real code. Each entry fully replaces what used to be a
 * hand-written OpenAIChatCompletionsProvider subclass — see
 * ConfiguredOpenAICompatProvider for the class that reads these entries,
 * and providerRegistry.ts for the registration loop that consumes this
 * array.
 *
 * The entries themselves are derived from the JSON catalog
 * (src/lib/providers/catalog/<id>.json) via buildCatalogEntries() — that
 * JSON is now the single source of truth for these providers' identity,
 * models, error rules and wire config. See
 * src/lib/providers/catalog/loader.ts for the derivation logic and
 * docs/superpowers/plans/2026-08-28-provider-json-catalog-spec.md for the
 * authoring format.
 *
 * To add a new OpenAI-compatible provider: add one JSON file under
 * src/lib/providers/catalog/ (see provider-catalog.schema.json) and run
 * `pnpm run codegen:catalog`. Do NOT add a provider here if it needs a real
 * hook override beyond the 3 mandatory ones
 * (getProviderName/getDefaultModel/formatProviderError) and the named
 * catalog quirks above — write a dedicated subclass instead (see
 * azureOpenai.ts).
 */
export const OPENAI_COMPAT_CATALOG = buildCatalogEntries();