test(8.0): Tier-1 integration via deterministic embedder (suite runnable again)

The integration suite loaded the real WASM model for every test, so a full run
took ~hours and reliably aborted (vitest reporter timeout) — which is why it was
never gated and silently rotted. Brainy already separates the embedder from all
other logic, so running integration with a deterministic embedder keeps every
code path real (HNSW build+search, graph traversal, metadata filtering,
transactions, storage/sharding, VFS, aggregation, import) while making the suite
complete in ~2 min on ANY machine — no GPU, no 16 GB requirement.

- Add isDeterministicEmbedMode() — a single source of truth for the test-embedder
  switch (BRAINY_DETERMINISTIC_EMBEDDINGS, plus the legacy BRAINY_UNIT_TEST alias),
  used by EmbeddingManager (init/embed/embedBatch) and brainy's eager-init guard.
- setup-integration.ts opts into it: Tier 1 = functional end-to-end. Real-model
  semantic quality + the real embedding pipeline move to a Tier-2 suite.

Full integration now runs 482 passing / 583 in ~2 min (was un-completable). The
remaining failures are pre-existing test rot, fixed next. Unit 1414 green.
This commit is contained in:
David Snelling 2026-06-16 12:44:14 -07:00
parent e31ba894f8
commit 542b52ede9
4 changed files with 84 additions and 67 deletions

View file

@ -116,6 +116,7 @@ import { resolveJsHnswConfig, DEFAULT_RECALL } from './utils/recallPreset.js'
import * as fs from 'node:fs' import * as fs from 'node:fs'
import { Db, type DbHost, type HistoricalQueryHandle } from './db/db.js' import { Db, type DbHost, type HistoricalQueryHandle } from './db/db.js'
import { GenerationStore } from './db/generationStore.js' import { GenerationStore } from './db/generationStore.js'
import { isDeterministicEmbedMode } from './embeddings/deterministicEmbedMode.js'
import { GenerationConflictError } from './db/errors.js' import { GenerationConflictError } from './db/errors.js'
import { MemoryStorage } from './storage/adapters/memoryStorage.js' import { MemoryStorage } from './storage/adapters/memoryStorage.js'
import type { import type {
@ -885,9 +886,7 @@ export class Brainy<T = any> implements BrainyInterface<T> {
// //
// `eagerEmbeddings: false` is the explicit override to force lazy init // `eagerEmbeddings: false` is the explicit override to force lazy init
// (first-embed) even when this instance is the active embedder. // (first-embed) even when this instance is the active embedder.
const isUnitTestMode = const isUnitTestMode = isDeterministicEmbedMode()
process.env.BRAINY_UNIT_TEST === 'true' ||
(globalThis as { __BRAINY_UNIT_TEST__?: boolean }).__BRAINY_UNIT_TEST__ === true
const eager = this.config.eagerEmbeddings ?? true const eager = this.config.eagerEmbeddings ?? true
if ( if (
eager && eager &&

View file

@ -14,6 +14,7 @@
import { Vector, EmbeddingFunction } from '../coreTypes.js' import { Vector, EmbeddingFunction } from '../coreTypes.js'
import { WASMEmbeddingEngine } from './wasm/index.js' import { WASMEmbeddingEngine } from './wasm/index.js'
import { isDeterministicEmbedMode } from './deterministicEmbedMode.js'
declare global { declare global {
/** /**
@ -77,9 +78,7 @@ export class EmbeddingManager {
*/ */
async init(): Promise<void> { async init(): Promise<void> {
// In unit test mode, skip real model initialization // In unit test mode, skip real model initialization
const isTestMode = const isTestMode = isDeterministicEmbedMode()
process.env.BRAINY_UNIT_TEST === 'true' ||
globalThis.__BRAINY_UNIT_TEST__
if (isTestMode) { if (isTestMode) {
// Production safeguard // Production safeguard
@ -151,9 +150,7 @@ export class EmbeddingManager {
*/ */
async embed(text: string | string[] | Record<string, unknown>): Promise<Vector> { async embed(text: string | string[] | Record<string, unknown>): Promise<Vector> {
// Check for unit test environment // Check for unit test environment
const isTestMode = const isTestMode = isDeterministicEmbedMode()
process.env.BRAINY_UNIT_TEST === 'true' ||
globalThis.__BRAINY_UNIT_TEST__
if (isTestMode) { if (isTestMode) {
if (process.env.NODE_ENV === 'production') { if (process.env.NODE_ENV === 'production') {
@ -233,9 +230,7 @@ export class EmbeddingManager {
async embedBatch(texts: string[], options?: { signal?: AbortSignal }): Promise<number[][]> { async embedBatch(texts: string[], options?: { signal?: AbortSignal }): Promise<number[][]> {
if (texts.length === 0) return [] if (texts.length === 0) return []
const isTestMode = const isTestMode = isDeterministicEmbedMode()
process.env.BRAINY_UNIT_TEST === 'true' ||
globalThis.__BRAINY_UNIT_TEST__
if (isTestMode) { if (isTestMode) {
if (process.env.NODE_ENV === 'production') { if (process.env.NODE_ENV === 'production') {

View file

@ -0,0 +1,39 @@
/**
* @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
)
}

View file

@ -1,60 +1,44 @@
/** /**
* Integration Test Setup - REAL AI functionality * Integration Test Setup Tier 1: Functional end-to-end (deterministic embedder)
* *
* This setup enables real AI models for integration testing * These tests exercise every real code path HNSW build + search, graph
* Requires high memory environment (16GB+ RAM) * traversal, metadata filtering, triple-intelligence composition, MVCC
* transactions, sharding/persistence, VFS, aggregation, import but with a
* DETERMINISTIC embedder instead of the real WASM transformer. The embedding's
* semantic *quality* is irrelevant to these assertions (which are structural:
* counts, ids, relationships, self-retrieval, transaction outcomes); making the
* vector deterministic turns a multi-hour, un-completable suite into a sub-minute
* one that any contributor can run on any machine, no GPU or 16 GB required.
*
* Semantic relevance + the real embedding pipeline are covered separately by the
* Tier-2 semantic suite (`tests/semantic/`, real model) see
* `tests/configs/vitest.semantic.config.ts`.
*/ */
beforeAll(async () => { beforeAll(() => {
console.log('🤖 Integration Test Environment: Using REAL AI models') console.log('🧪 Integration (Tier 1): deterministic embedder, all other code paths real')
console.log('⚠️ Requires 16GB+ RAM - this is normal for AI testing')
// Set up environment for real AI testing
process.env.BRAINY_INTEGRATION_TEST = 'true'
process.env.BRAINY_MODELS_PATH = './models'
process.env.BRAINY_ALLOW_REMOTE_MODELS = 'false' // Use local models only
// Set memory limits and optimizations
process.env.ORT_DISABLE_MEMORY_ARENA = '1'
process.env.ORT_DISABLE_MEMORY_PATTERN = '1'
process.env.ORT_INTRA_OP_NUM_THREADS = '2'
process.env.ORT_INTER_OP_NUM_THREADS = '2'
// Mark as integration test environment
;(globalThis as any).__BRAINY_INTEGRATION_TEST__ = true
// Check memory availability
const availableMemoryGB = process.env.NODE_OPTIONS?.includes('max-old-space-size')
? parseInt(process.env.NODE_OPTIONS.match(/--max-old-space-size=(\d+)/)?.[1] || '0') / 1024
: 4
console.log(`📊 Node.js heap limit: ${availableMemoryGB.toFixed(1)}GB`)
if (availableMemoryGB < 8) {
console.warn('⚠️ WARNING: Less than 8GB allocated for integration tests')
console.warn(' Recommended: NODE_OPTIONS="--max-old-space-size=16384"')
console.warn(' Tests may fail due to insufficient memory')
}
}, 60000) // 1 minute timeout for setup
afterAll(async () => { // Deterministic embeddings — see src/embeddings/deterministicEmbedMode.ts.
// Clean up process.env.BRAINY_DETERMINISTIC_EMBEDDINGS = 'true'
delete process.env.BRAINY_INTEGRATION_TEST ;(globalThis as { __BRAINY_DETERMINISTIC_EMBED__?: boolean }).__BRAINY_DETERMINISTIC_EMBED__ = true
delete (globalThis as any).__BRAINY_INTEGRATION_TEST__
// Force garbage collection if available
if (global.gc) {
global.gc()
}
}, 30000) // 30 second timeout for cleanup
// Utility function to skip tests if not enough memory // Marker retained for any test that branches on the integration environment.
export function requiresMemory(minGB: number) { ;(globalThis as { __BRAINY_INTEGRATION_TEST__?: boolean }).__BRAINY_INTEGRATION_TEST__ = true
const availableMemoryGB = process.env.NODE_OPTIONS?.includes('max-old-space-size') })
? parseInt(process.env.NODE_OPTIONS.match(/--max-old-space-size=(\d+)/)?.[1] || '0') / 1024
: 4 afterAll(() => {
delete process.env.BRAINY_DETERMINISTIC_EMBEDDINGS
if (availableMemoryGB < minGB) { delete (globalThis as { __BRAINY_DETERMINISTIC_EMBED__?: boolean }).__BRAINY_DETERMINISTIC_EMBED__
throw new Error(`Test requires ${minGB}GB memory, only ${availableMemoryGB.toFixed(1)}GB allocated`) delete (globalThis as { __BRAINY_INTEGRATION_TEST__?: boolean }).__BRAINY_INTEGRATION_TEST__
} })
}
/**
* No-op retained for back-compat. Tier-1 integration tests use the deterministic
* embedder, so the real model's 16 GB requirement no longer applies there is
* nothing to gate on. (Real-model memory cost lives in the Tier-2 semantic suite.)
*
* @param _minGB - Ignored.
*/
export function requiresMemory(_minGB: number): void {
// Intentionally empty — see the doc comment above.
}