fix: mmap-vector backend capacity NaN at the provider FFI boundary

A production deployment reported "[brainy] mmap-vector backend not wired
(Capacity must be > 0); falling back to per-entity vector reads" on every
cold start of populated brains under the native plugin — degrading vector
recall to per-entity disk reads (8.3s cold starts at 685 entities, scaling
linearly).

Root cause: wireMmapVectorBackend computes its initial slot capacity as
idMapper.size * 2. When the metadata index is provider-backed, getIdMapper()
returns a façade exposing getInt/getOrAssign/getUuid but NO `size` property.
`undefined * 2` is NaN, Math.max(NaN, 1024) stays NaN, and NaN coerces to 0
via ToUint32 at the provider's u32 FFI boundary — tripping the provider's
"Capacity must be > 0" guard. The JS-only path never hit this because
brainy's own EntityIdMapper has a real `size` getter.

Fix, two independent layers:
- wireMmapVectorBackend treats a missing/non-finite mapper size as 0, so
  the 1024-slot floor always holds (the file grows on demand past it).
- MmapVectorBackend.open sanitizes the capacity (NaN/Infinity/non-positive
  → 16-slot floor) so no caller can ever hand the provider an invalid
  allocation size.

Regression tests mimic the exact failure: a U32-coercing provider that
rejects capacity 0 plus an idMapper façade without `size`. Pre-fix the
NaN reached create() and threw; post-fix the backend wires with the floor
capacity and round-trips vectors. 1464/1464 unit suite passing.
This commit is contained in:
David Snelling 2026-06-10 09:29:08 -07:00
parent d6daafb426
commit eade6ff1be
3 changed files with 68 additions and 2 deletions

View file

@ -9410,7 +9410,15 @@ export class Brainy<T = any> implements BrainyInterface<T> {
if (!idMapper) return if (!idMapper) return
const dim = this.dimensions ?? 384 const dim = this.dimensions ?? 384
const initialCapacity = Math.max(idMapper.size * 2, 1024) // Provider-supplied id mappers (e.g. a native metadata index's façade) may
// not expose a `size` property. `undefined * 2` is NaN, and NaN coerces to
// 0 at the napi u32 boundary — the provider then rejects the create() with
// "Capacity must be > 0". Treat a missing/non-finite size as 0 so the
// 1024 floor always holds; the file grows on demand past it.
const mapperSize = Number.isFinite((idMapper as { size?: number }).size)
? (idMapper as { size: number }).size
: 0
const initialCapacity = Math.max(mapperSize * 2, 1024)
try { try {
const backend = await MmapVectorBackend.open( const backend = await MmapVectorBackend.open(

View file

@ -77,11 +77,17 @@ export class MmapVectorBackend {
idMapper: EntityIdMapperProvider idMapper: EntityIdMapperProvider
): Promise<MmapVectorBackend> { ): Promise<MmapVectorBackend> {
await mkdir(dirname(path), { recursive: true }) await mkdir(dirname(path), { recursive: true })
// NaN/Infinity/non-positive capacities coerce to 0 at the provider's u32
// FFI boundary ("Capacity must be > 0"). Sanitize here so no caller can
// ever hand the provider an invalid allocation size.
const capacity = Number.isFinite(initialCapacity) && initialCapacity >= 16
? Math.ceil(initialCapacity)
: 16
let store: VectorStoreMmapInstance let store: VectorStoreMmapInstance
try { try {
store = provider.open(path) store = provider.open(path)
} catch { } catch {
store = provider.create(path, dim, Math.max(initialCapacity, 16)) store = provider.create(path, dim, capacity)
} }
return new MmapVectorBackend(store, idMapper) return new MmapVectorBackend(store, idMapper)
} }

View file

@ -239,4 +239,56 @@ describe('MmapVectorBackend (2.4.0 #2 — wraps vectorStore:mmap provider)', ()
const backend2 = await MmapVectorBackend.open(provider, path, 2, 8, idMapper) const backend2 = await MmapVectorBackend.open(provider, path, 2, 8, idMapper)
expect(backend2.readByUuid('persisted')).toEqual([7, 7]) expect(backend2.readByUuid('persisted')).toEqual([7, 7])
}) })
describe('capacity sanitization at the provider FFI boundary (7.31.3 regression)', () => {
/**
* Mimics cortex's NativeMmapVectorStore napi boundary: JS numbers are
* coerced ToUint32 (NaN 0, Infinity 0) before the Rust-side
* `capacity == 0` guard fires with "Capacity must be > 0". This is the
* exact production failure from a metadata-provider idMapper façade that
* exposes no `size` property: `undefined * 2` = NaN at the caller.
*/
class U32CoercingProvider extends MockMmapProvider {
lastCreateCapacity: number | null = null
override create(path: string, dim: number, capacity: number): VectorStoreMmapInstance {
const coerced = capacity >>> 0 // ECMA ToUint32 — what napi-rs does
this.lastCreateCapacity = coerced
if (coerced === 0) throw new Error('Capacity must be > 0')
return super.create(path, dim, coerced)
}
}
it('NaN initialCapacity (idMapper façade without `size`) still wires with the floor capacity', async () => {
const strictProvider = new U32CoercingProvider()
const facadeWithoutSize = {
getInt: (uuid: string) => idMapper.getInt(uuid),
getOrAssign: (uuid: string) => idMapper.getOrAssign(uuid),
getUuid: (intId: number) => idMapper.getUuid(intId)
} as any
// Pre-fix: NaN reached create(), coerced to 0, threw, and the backend
// never wired. Post-fix it must construct with the 16-slot floor.
const naiveCapacity = (facadeWithoutSize.size as number) * 2 // NaN
const backend = await MmapVectorBackend.open(
strictProvider,
path,
4,
naiveCapacity,
facadeWithoutSize
)
expect(strictProvider.lastCreateCapacity).toBeGreaterThanOrEqual(16)
backend.writeByUuid('wired', [1, 2, 3, 4])
expect(backend.readByUuid('wired')).toEqual([1, 2, 3, 4])
})
it('Infinity and non-positive capacities are clamped to the floor', async () => {
for (const bad of [Infinity, -Infinity, 0, -5]) {
const strictProvider = new U32CoercingProvider()
const p = join(dir, `vectors-${String(bad)}.bin`)
await MmapVectorBackend.open(strictProvider, p, 2, bad, idMapper)
expect(strictProvider.lastCreateCapacity).toBe(16)
}
})
})
}) })