open-brainy/src/embeddings/deterministicEmbedMode.ts

40 lines
1.8 KiB
TypeScript
Raw Normal View History

/**
* @module embeddings/deterministicEmbedMode
* @description Single source of truth for "use deterministic test embeddings".
*
* Brainy's embedding model is a real WASM transformer correct, but slow on CPU
* (a forward pass per text). For TEST tiers that exercise database *logic* (HNSW
* build + search, graph traversal, metadata filtering, transactions, storage,
* VFS, find composition), the embedding's semantic *quality* is irrelevant; only
* a deterministic, content-derived vector is needed. Switching the embedder to a
* deterministic stand-in keeps every other code path real while turning a
* multi-hour suite into a sub-minute, gateable one. Semantic quality and the
* real embedding pipeline are covered separately by the real-model test tier.
*
* This flag is honored ONLY outside production: {@link EmbeddingManager} throws
* if it is set while `NODE_ENV=production` (mock vectors in prod is a security
* risk). Enabled by env var or global so test setup files can opt in per tier.
*/
interface DeterministicEmbedGlobals {
__BRAINY_DETERMINISTIC_EMBED__?: boolean
/** Legacy alias — the original unit-test-only spelling. */
__BRAINY_UNIT_TEST__?: boolean
}
/**
* @description Whether the deterministic test embedder should be used instead of
* the real WASM model. True when `BRAINY_DETERMINISTIC_EMBEDDINGS=true` or the
* legacy `BRAINY_UNIT_TEST=true` env var is set, or the matching global is set.
* @returns `true` to use deterministic embeddings, `false` for the real model.
*/
export function isDeterministicEmbedMode(): boolean {
const g = globalThis as DeterministicEmbedGlobals
return (
process.env.BRAINY_DETERMINISTIC_EMBEDDINGS === 'true' ||
process.env.BRAINY_UNIT_TEST === 'true' ||
g.__BRAINY_DETERMINISTIC_EMBED__ === true ||
g.__BRAINY_UNIT_TEST__ === true
)
}