brainy/tests/integration/db-mvcc.test.ts
David Snelling 606445cd61 feat(8.0): API simplification — remove neural()/Db.search, one storage path key, integration→0
8.0 RC cleanup toward "one place per thing, zero-config, no deprecation":

- Remove the `brain.neural()` clustering namespace (ImprovedNeuralAPI + the dead
  legacy NeuralAPI + the neural CLI + neural-only types). Similarity is `find({vector})`
  / `similar({to})`; attribute grouping is the aggregation `GROUP BY` engine. The separate
  entity-extraction / smart-import feature (NeuralImport, NeuralEntityExtractor, SmartExtractor,
  NaturalLanguageProcessor, `brain.extract()`/`brain.nlp()`) is kept.
- Remove `Db.search()`; `find()` is the one query verb (accepts a bare string or FindParams).
  Fix the bundled MCP client, which called a non-existent `brain.search(query, limit)` →
  now `find({ query, limit })`.
- Storage config: collapse to one canonical top-level `path` key. The pre-8.0 aliases
  (`rootDirectory`, `options.*`, `fileSystemStorage.*`) are removed and now THROW with the
  exact rename instead of silently defaulting to `./brainy-data` on upgrade. A single resolver
  feeds createStorage, the 7.x→8.0 migration probe, and the plugin-factory handoff, so a native
  storage provider resolves the identical root (no split-brain).
- Fix `similar({ threshold })`: the min-similarity filter was silently dropped; it is now
  applied as a post-filter on `result.score` (the documented way to bound semantic results).
- Fix `vfs.rename()` on a directory: child path updates spread the entity vector into `update()`
  and failed dimension validation; they are metadata-only updates now.
- Fix `vfs.move()`: copy+delete orphaned the content-addressed content blob (the destination
  shared the source hash, then unlink removed it). `move()` now delegates to `rename()` — an
  in-place path change that preserves the blob and the entity id, for files and directories.
- Fix streaming import: the bulk fast path never flushed mid-import nor signalled queryability.
  Entity writes are now chunked by a progressive flush interval (100 → 1000 → 5000); each chunk
  flushes and emits `progress.queryable`, so imported data is queryable during the import.
- Sweep all docs, comments, and JSDoc for the removed/changed APIs.

Integration suite: 49 files / 588 passed / 0 failed. Unit: 80 files / 1456 passed, no type errors.
2026-06-20 13:31:11 -07:00

1187 lines
46 KiB
TypeScript

/**
* @module tests/integration/db-mvcc
* @description Credibility-bar proof suite for Brainy 8.0's generational MVCC
* storage core + Datomic-style Db API. Each test PROVES a stated guarantee
* (not merely exercises the API):
*
* 1. Isolation — a pinned Db reads its pinned state exactly, across 200
* subsequent transact mutations (updates + removes).
* 2. Atomicity — a batch with a failing later operation applies NOTHING
* (generation unchanged, no partial records), for both plan-time and
* execution-phase failures (the latter via real fault injection into the
* storage adapter, exercising the production rollback path).
* 3. CAS — `ifAtGeneration` commits when fresh, throws
* `GenerationConflictError` with correct expected/actual when stale.
* 4. Snapshot integrity — persist → mutate source heavily → `Brainy.load()`
* is byte-identical to the pre-mutation state (hard-link safety), and an
* in-memory brain persists to a loadable directory.
* 5. Compaction safety — pinned reads stay correct across `compactHistory()`;
* after release + compact the superseded record-sets are reclaimed.
* 6. with() — speculative overlays are visible on the overlay Db only; the
* underlying brain and the original Db are untouched.
* 7. Generation monotonicity across close/reopen.
* 8. Crash consistency — a simulated crash between record staging and the
* manifest rename (the commit point) recovers to the exact pre-transaction
* state on reopen, through the REAL production recovery path.
* 9. Versioned provider wiring — a provider implementing the 4-method
* `VersionedIndexProvider` contract receives balanced pin/release (and a
* visibility consult per pin) as Db values are created and released.
* 10. Historical full query surface — vector search, graph traversal, and
* aggregation at a past pinned generation return at-generation results
* via ephemeral index materialization (for `now()` and `asOf()` pins
* alike, built once per Db and cached); `release()` frees the
* materialization by closing the ephemeral reader; speculative overlays
* keep the documented `SpeculativeOverlayError` boundary.
*
* All entities carry explicit vectors so the suite never invokes the
* embedding engine (vector queries use find({ vector }); semantic string
* search on overlays is exercised only for its documented error).
*/
import { describe, it, expect, afterEach, vi } from 'vitest'
import * as fs from 'node:fs'
import * as os from 'node:os'
import * as path from 'node:path'
import { Brainy } from '../../src/brainy.js'
import { Db, type HistoricalQueryHandle } from '../../src/db/db.js'
import {
GenerationCompactedError,
GenerationConflictError,
SpeculativeOverlayError
} from '../../src/db/errors.js'
import type { GenerationStore } from '../../src/db/generationStore.js'
import { GraphAdjacencyIndex } from '../../src/graph/graphAdjacencyIndex.js'
import { RevisionConflictError } from '../../src/transaction/RevisionConflictError.js'
import type { StorageAdapter } from '../../src/coreTypes.js'
import { NounType, VerbType } from '../../src/types/graphTypes.js'
/** Deterministic 384-dim vector so no test ever invokes the embedder. */
function vec(seed: number): number[] {
return Array.from({ length: 384 }, (_, i) => ((seed * 31 + i * 7) % 100) / 100)
}
/**
* Map a readable label to a deterministic UUID-shaped id (entity ids must be
* UUIDs — the sharded storage layout derives the shard from the UUID hex).
* Two independent FNV-style mixes keep 7+ distinct labels collision-free.
*/
function uid(label: string): string {
let h1 = 0x811c9dc5
for (let i = 0; i < label.length; i++) {
h1 = Math.imul(h1 ^ label.charCodeAt(i), 0x01000193) >>> 0
}
let h2 = 0xdeadbeef
for (let i = label.length - 1; i >= 0; i--) {
h2 = Math.imul(h2 ^ label.charCodeAt(i), 0x85ebca6b) >>> 0
}
const hex = h1.toString(16).padStart(8, '0') + h2.toString(16).padStart(8, '0')
return `00000000-0000-4000-8000-${hex.slice(0, 12)}`
}
/** Typed access to the brain's private generation store (test injection point). */
function generationStoreOf(brain: Brainy): GenerationStore {
return (brain as unknown as { generationStore: GenerationStore }).generationStore
}
describe('8.0 Db API — generational MVCC', () => {
const brains: Brainy[] = []
const tempDirs: string[] = []
/** Track a brain for afterEach teardown. */
async function openMemoryBrain(): Promise<Brainy> {
const brain = new Brainy({ requireSubtype: false, storage: { type: 'memory' } })
await brain.init()
brains.push(brain)
return brain
}
/** Open (and track) a filesystem brain rooted at a fresh temp directory. */
async function openFsBrain(dir?: string): Promise<{ brain: Brainy; dir: string }> {
const rootDirectory = dir ?? makeTempDir()
const brain = new Brainy({
requireSubtype: false,
storage: { type: 'filesystem', path: rootDirectory }
})
await brain.init()
brains.push(brain)
return { brain, dir: rootDirectory }
}
function makeTempDir(): string {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'brainy-db-mvcc-'))
tempDirs.push(dir)
return dir
}
afterEach(async () => {
for (const brain of brains.splice(0)) {
try {
await brain.close()
} catch {
// already closed by the test
}
}
for (const dir of tempDirs.splice(0)) {
await fs.promises.rm(dir, { recursive: true, force: true })
}
})
// ==========================================================================
// 1. Isolation
// ==========================================================================
it('proof 1 — a pinned Db reads its pinned state exactly across 200 transact mutations', async () => {
const brain = await openMemoryBrain()
const ids = Array.from({ length: 20 }, (_, i) => uid(`iso-e${i}`))
await brain.transact(
ids.map((id, i) => ({
op: 'add' as const,
id,
type: NounType.Document,
data: `doc-${i}`,
vector: vec(i),
metadata: { v: 0, slot: i }
}))
)
const db = brain.now()
const pinned = new Map<string, unknown>()
for (const id of ids) {
pinned.set(id, await db.get(id))
expect(pinned.get(id)).not.toBeNull()
}
const pinnedFind = await db.find({ type: NounType.Document, limit: 100 })
expect(pinnedFind.length).toBe(20)
// 200 mutations: 198 updates over the first 18 ids + 2 removes.
for (let i = 0; i < 200; i++) {
if (i === 100) {
await brain.transact([{ op: 'remove', id: uid('iso-e18') }])
} else if (i === 150) {
await brain.transact([{ op: 'remove', id: uid('iso-e19') }])
} else {
await brain.transact([
{ op: 'update', id: ids[i % 18], metadata: { v: i + 1, touchedAt: i } }
])
}
}
// Live state moved…
const liveUpdated = await brain.get(ids[0])
expect((liveUpdated?.metadata as { v: number }).v).toBeGreaterThan(0)
expect(await brain.get(uid('iso-e18'))).toBeNull()
expect(await brain.get(uid('iso-e19'))).toBeNull()
// …but EVERY read through the pinned Db is exactly the pinned state,
// including the two entities removed after the pin.
for (const id of ids) {
expect(await db.get(id)).toEqual(pinned.get(id))
}
// Set-level isolation: metadata find() at the pin still sees all 20.
const histFind = await db.find({ type: NounType.Document, limit: 100 })
expect(histFind.length).toBe(20)
for (const row of histFind) {
expect((row.metadata as { v: number }).v).toBe(0)
}
await db.release()
})
// ==========================================================================
// 2. Atomicity
// ==========================================================================
it('proof 2a — a plan-time failure in a later op applies nothing', async () => {
const brain = await openMemoryBrain()
const g0 = brain.generation()
await expect(
brain.transact([
{
op: 'add',
id: uid('atomic-a'),
type: NounType.Document,
data: 'a',
vector: vec(1),
metadata: { ok: true }
},
{ op: 'update', id: uid('never-created'), metadata: { boom: true } }
])
).rejects.toThrow(`Entity ${uid('never-created')} not found`)
expect(brain.generation()).toBe(g0)
expect(await brain.get(uid('atomic-a'))).toBeNull()
expect((await brain.find({ type: NounType.Document, limit: 10 })).length).toBe(0)
})
it('proof 2b — an execution-phase failure rolls back every applied op (generation unchanged, zero partial records)', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{
op: 'add',
id: uid('atomic-base'),
type: NounType.Document,
data: 'base',
vector: vec(0),
metadata: { base: true }
}
])
const g0 = brain.generation()
const storage = brain.storageAdapter
// Real fault injection: the verb-metadata write of the LAST operation
// fails once, after the earlier add operations have already executed —
// exercising the production TransactionManager rollback path.
const spy = vi
.spyOn(storage, 'saveVerbMetadata')
.mockImplementationOnce(async () => {
throw new Error('disk full (injected)')
})
await expect(
brain.transact([
{
op: 'add',
id: uid('atomic-b'),
type: NounType.Person,
data: 'b',
vector: vec(2),
metadata: { name: 'b' }
},
{
op: 'relate',
from: uid('atomic-b'),
to: uid('atomic-base'),
type: VerbType.RelatedTo
}
])
).rejects.toThrow('disk full (injected)')
spy.mockRestore()
// ZERO ops applied: generation unchanged, the add rolled back, no edge.
expect(brain.generation()).toBe(g0)
expect(await brain.get(uid('atomic-b'))).toBeNull()
expect((await brain.related({ from: uid('atomic-b') })).length).toBe(0)
expect((await brain.find({ type: NounType.Person, limit: 10 })).length).toBe(0)
// No partial generation records: the staging directory was removed.
const records = await storage.listRawObjects(`_generations/${g0 + 1}`)
expect(records).toEqual([])
// The store remains fully writable and consistent after the rollback.
const db = await brain.transact([
{
op: 'add',
id: uid('atomic-c'),
type: NounType.Person,
data: 'c',
vector: vec(3),
metadata: { name: 'c' }
}
])
expect(db.generation).toBe(g0 + 1)
await db.release()
})
it('proof 2c — an ifRev conflict on a later update rejects the whole batch', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{
op: 'add',
id: uid('rev-e'),
type: NounType.Document,
data: 'rev',
vector: vec(4),
metadata: { v: 1 }
}
])
await brain.update({ id: uid('rev-e'), metadata: { v: 2 } }) // _rev is now 2
const g0 = brain.generation()
await expect(
brain.transact([
{
op: 'add',
id: uid('rev-new'),
type: NounType.Document,
data: 'new',
vector: vec(5),
metadata: {}
},
{ op: 'update', id: uid('rev-e'), metadata: { v: 3 }, ifRev: 1 } // stale
])
).rejects.toThrow(RevisionConflictError)
expect(brain.generation()).toBe(g0)
expect(await brain.get(uid('rev-new'))).toBeNull()
expect(((await brain.get(uid('rev-e')))?.metadata as { v: number }).v).toBe(2)
})
// ==========================================================================
// 3. CAS (ifAtGeneration)
// ==========================================================================
it('proof 3 — ifAtGeneration commits when fresh and conflicts when stale', async () => {
const brain = await openMemoryBrain()
const db = brain.now()
const committed = await brain.transact(
[
{
op: 'add',
id: uid('cas-e'),
type: NounType.Document,
data: 'cas',
vector: vec(6),
metadata: { n: 1 }
}
],
{ ifAtGeneration: db.generation }
)
expect(committed.generation).toBe(db.generation + 1)
try {
await brain.transact(
[{ op: 'update', id: uid('cas-e'), metadata: { n: 2 } }],
{ ifAtGeneration: db.generation } // stale — committed moved past it
)
expect.unreachable('should have thrown GenerationConflictError')
} catch (err) {
expect(err).toBeInstanceOf(GenerationConflictError)
expect((err as GenerationConflictError).expected).toBe(db.generation)
expect((err as GenerationConflictError).actual).toBe(committed.generation)
}
// Nothing committed by the conflicting attempt.
expect(((await brain.get(uid('cas-e')))?.metadata as { n: number }).n).toBe(1)
expect(brain.generation()).toBe(committed.generation)
await db.release()
await committed.release()
})
// ==========================================================================
// 4. Snapshot integrity (persist → mutate → load)
// ==========================================================================
it('proof 4a — a persisted snapshot is immune to heavy source mutation (hard-link safety)', async () => {
const { brain } = await openFsBrain()
const ids = Array.from({ length: 10 }, (_, i) => uid(`snap-e${i}`))
await brain.transact(
ids.map((id, i) => ({
op: 'add' as const,
id,
type: NounType.Document,
data: `snapshot-doc-${i}`,
vector: vec(i + 10),
metadata: { generation: 'pre', slot: i }
}))
)
const relDb = await brain.transact([
{ op: 'relate', from: ids[0], to: ids[1], type: VerbType.References },
{ op: 'relate', from: ids[1], to: ids[2], type: VerbType.References }
])
await relDb.release()
// Capture pre-mutation state, then snapshot.
const preState = new Map<string, unknown>()
for (const id of ids) {
preState.set(id, await brain.get(id))
}
const preRelations = await brain.related({ from: ids[0] })
expect(preRelations.length).toBe(1)
const snapDir = path.join(makeTempDir(), 'snapshot')
const db = brain.now()
await db.persist(snapDir)
await db.release()
// Mutate the source heavily: rewrite every entity, delete some, add new.
for (const [i, id] of ids.entries()) {
await brain.transact([
{ op: 'update', id, data: `mutated-${i}`, metadata: { generation: 'post' } }
])
}
await brain.transact([{ op: 'remove', id: ids[0] }])
await brain.transact([
{
op: 'add',
id: uid('snap-after'),
type: NounType.Document,
data: 'added after snapshot',
vector: vec(99),
metadata: { generation: 'post' }
}
])
await brain.flush()
// The snapshot opens as a self-contained store with the PRE state.
const loaded = await Brainy.load(snapDir)
for (const id of ids) {
const entity = await loaded.get(id)
expect(entity).toEqual(preState.get(id))
}
expect(await loaded.get(uid('snap-after'))).toBeNull()
const loadedFind = await loaded.find({ type: NounType.Document, limit: 100 })
expect(loadedFind.length).toBe(10)
for (const row of loadedFind) {
expect((row.metadata as { generation: string }).generation).toBe('pre')
}
const loadedRelations = await loaded.related({ from: ids[0] })
expect(loadedRelations.length).toBe(1)
expect(loadedRelations[0].to).toBe(ids[1])
await loaded.release()
// And asOf(path) is the instance-method route to the same snapshot.
const viaAsOf = await brain.asOf(snapDir)
expect(((await viaAsOf.get(ids[3])) as { metadata: { generation: string } }).metadata.generation).toBe('pre')
await viaAsOf.release()
})
it('proof 4b — an in-memory brain persists to a directory loadable as a real store', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{
op: 'add',
id: uid('mem-e1'),
type: NounType.Document,
data: 'memory-persisted',
vector: vec(21),
metadata: { from: 'memory' }
}
])
const snapDir = path.join(makeTempDir(), 'memory-snapshot')
const db = brain.now()
await db.persist(snapDir)
await db.release()
const loaded = await Brainy.load(snapDir)
const entity = await loaded.get(uid('mem-e1'))
expect(entity).not.toBeNull()
expect((entity?.metadata as { from: string }).from).toBe('memory')
await loaded.release()
})
it('proof 4c — persist() refuses a view that history has moved past (honest boundary)', async () => {
const brain = await openMemoryBrain()
const db = brain.now()
await brain.transact([
{
op: 'add',
id: uid('stale-persist'),
type: NounType.Document,
data: 'x',
vector: vec(30),
metadata: {}
}
])
const snapDir = path.join(makeTempDir(), 'stale-snapshot')
await expect(db.persist(snapDir)).rejects.toThrow(GenerationConflictError)
await db.release()
})
// ==========================================================================
// 5. Compaction safety
// ==========================================================================
it('proof 5 — compaction never breaks pinned reads; after release the records are reclaimed', async () => {
const { brain } = await openFsBrain()
const storage = brain.storageAdapter
// Every transact() returns a PINNED Db — release the ones this test
// does not keep, so compaction eligibility is determined solely by `db`.
await (
await brain.transact([
{
op: 'add',
id: uid('compact-e'),
type: NounType.Document,
data: 'v1',
vector: vec(40),
metadata: { v: 1 }
}
])
).release()
await (
await brain.transact([{ op: 'update', id: uid('compact-e'), metadata: { v: 2 } }])
).release()
const db = brain.now() // pinned at v2
const pinnedEntity = await db.get(uid('compact-e'))
await (
await brain.transact([{ op: 'update', id: uid('compact-e'), metadata: { v: 3 } }])
).release()
await (
await brain.transact([{ op: 'update', id: uid('compact-e'), metadata: { v: 4 } }])
).release()
const recordsBefore = (await storage.listRawObjects('_generations')).length
expect(recordsBefore).toBeGreaterThan(0)
// Compact while pinned: record-sets above the pin survive, pinned reads stay correct.
const first = await brain.compactHistory()
expect(await db.get(uid('compact-e'))).toEqual(pinnedEntity)
expect(((await db.get(uid('compact-e')))?.metadata as { v: number }).v).toBe(2)
// After release, everything is reclaimable.
await db.release()
const second = await brain.compactHistory()
expect(first.removedGenerations + second.removedGenerations).toBeGreaterThan(0)
const recordsAfter = (await storage.listRawObjects('_generations')).length
expect(recordsAfter).toBeLessThan(recordsBefore)
expect(recordsAfter).toBe(0)
// Compacted generations are honestly unreachable.
await expect(brain.asOf(1)).rejects.toThrow(GenerationCompactedError)
})
// ==========================================================================
// 6. with() — speculative overlays
// ==========================================================================
it('proof 6 — with() overlays are visible only on the overlay Db; brain and base Db untouched', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{
op: 'add',
id: uid('with-a'),
type: NounType.Person,
data: 'Ada',
vector: vec(50),
metadata: { v: 1 }
},
{
op: 'add',
id: uid('with-b'),
type: NounType.Person,
data: 'Grace',
vector: vec(51),
metadata: { v: 1 }
}
])
const g0 = brain.generation()
const db = brain.now()
const spec = await db.with([
{ op: 'update', id: uid('with-a'), metadata: { v: 2 } },
{
op: 'add',
id: uid('with-new'),
type: NounType.Project,
data: 'Apollo',
metadata: { speculative: true }
},
{ op: 'remove', id: uid('with-b') },
{ op: 'relate', from: uid('with-a'), to: uid('with-new'), type: VerbType.WorksOn }
])
// The overlay view sees everything…
expect(spec.speculative).toBe(true)
expect(((await spec.get(uid('with-a')))?.metadata as { v: number }).v).toBe(2)
expect(await spec.get(uid('with-new'))).not.toBeNull()
expect(await spec.get(uid('with-b'))).toBeNull()
const specEdges = await spec.related({ from: uid('with-a') })
expect(specEdges.length).toBe(1)
expect(specEdges[0].to).toBe(uid('with-new'))
const specFind = await spec.find({ type: NounType.Project, limit: 10 })
expect(specFind.length).toBe(1)
// …the base Db sees none of it…
expect(db.speculative).toBe(false)
expect(((await db.get(uid('with-a')))?.metadata as { v: number }).v).toBe(1)
expect(await db.get(uid('with-new'))).toBeNull()
expect(await db.get(uid('with-b'))).not.toBeNull()
// …and the brain (disk, indexes, generation counter) is untouched.
expect(brain.generation()).toBe(g0)
expect(((await brain.get(uid('with-a')))?.metadata as { v: number }).v).toBe(1)
expect(await brain.get(uid('with-new'))).toBeNull()
expect((await brain.related({ from: uid('with-a') })).length).toBe(0)
await spec.release()
await db.release()
})
// ==========================================================================
// 7. Generation monotonicity across close/reopen
// ==========================================================================
it('proof 7 — the generation counter never moves backwards across close/reopen', async () => {
const dir = makeTempDir()
const { brain: first } = await openFsBrain(dir)
await first.transact([
{
op: 'add',
id: uid('mono-e'),
type: NounType.Document,
data: 'v1',
vector: vec(60),
metadata: { v: 1 }
}
])
await first.transact([{ op: 'update', id: uid('mono-e'), metadata: { v: 2 } }])
// Single-operation write — bumps the counter outside transact.
await first.update({ id: uid('mono-e'), metadata: { v: 3 } })
const beforeClose = first.generation()
expect(beforeClose).toBeGreaterThanOrEqual(3)
await first.close()
const { brain: second } = await openFsBrain(dir)
expect(second.generation()).toBeGreaterThanOrEqual(beforeClose)
const db = await second.transact([{ op: 'update', id: uid('mono-e'), metadata: { v: 4 } }])
expect(db.generation).toBeGreaterThan(beforeClose)
await db.release()
})
// ==========================================================================
// 8. Crash consistency
// ==========================================================================
it('proof 8 — a crash before the manifest rename recovers to the exact pre-transaction state', async () => {
const dir = makeTempDir()
const { brain: first } = await openFsBrain(dir)
await first.transact([
{
op: 'add',
id: uid('crash-e'),
type: NounType.Document,
data: 'stable',
vector: vec(70),
metadata: { v: 1 }
}
])
const committedGen = first.generation()
// Simulated crash at the worst point of the REAL commit protocol: every
// record is staged and the batch has executed, but the atomic manifest
// rename — the commit point — never happens. The throwing injector skips
// the abort cleanup exactly as a dead process would.
generationStoreOf(first).setCommitFaultInjector((phase) => {
if (phase === 'before-manifest-rename') {
throw new Error('simulated process crash')
}
})
await expect(
first.transact([
{ op: 'update', id: uid('crash-e'), metadata: { v: 2 } },
{
op: 'add',
id: uid('crash-new'),
type: NounType.Document,
data: 'uncommitted',
vector: vec(71),
metadata: {}
}
])
).rejects.toThrow('simulated process crash')
generationStoreOf(first).setCommitFaultInjector(undefined)
// The in-process state is dirty (batch executed) — close flushes it all,
// the realistic worst case for the recovery path.
await first.close()
// Reopen: recovery rolls the uncommitted generation back and rebuilds
// the indexes from the repaired records.
const { brain: second } = await openFsBrain(dir)
const recovered = await second.get(uid('crash-e'))
expect((recovered?.metadata as { v: number }).v).toBe(1)
expect(await second.get(uid('crash-new'))).toBeNull()
const found = await second.find({ type: NounType.Document, limit: 10 })
expect(found.length).toBe(1)
expect((found[0].metadata as { v: number }).v).toBe(1)
// The crashed generation number is never reissued.
expect(second.generation()).toBeGreaterThanOrEqual(committedGen + 1)
const db = await second.transact([{ op: 'update', id: uid('crash-e'), metadata: { v: 5 } }])
expect(db.generation).toBeGreaterThan(committedGen + 1)
await db.release()
})
// ==========================================================================
// 9. Versioned provider wiring
// ==========================================================================
it('proof 9 — a VersionedIndexProvider receives balanced pin/release as Db values live and die', async () => {
const calls = {
pins: [] as bigint[],
releases: [] as bigint[],
visibility: [] as bigint[]
}
const brain = new Brainy({ requireSubtype: false, storage: { type: 'memory' } })
brain.use({
name: 'test-versioned-graph-index',
activate: async (ctx) => {
ctx.registerProvider('graphIndex', (storage: StorageAdapter) =>
Object.assign(new GraphAdjacencyIndex(storage), {
generation: () => 0n,
isGenerationVisible: (g: bigint) => {
calls.visibility.push(g)
return true
},
pin: (g: bigint) => {
calls.pins.push(g)
},
release: (g: bigint) => {
calls.releases.push(g)
}
})
)
return true
}
})
await brain.init()
brains.push(brain)
const base = brain.generation()
const db1 = brain.now()
expect(calls.pins).toEqual([BigInt(base)])
expect(calls.visibility).toEqual([BigInt(base)]) // consulted at pin time
const db2 = await brain.transact([
{
op: 'add',
id: uid('vp-e'),
type: NounType.Document,
data: 'pinned',
vector: vec(80),
metadata: {}
}
])
expect(calls.pins).toEqual([BigInt(base), BigInt(base + 1)])
const db3 = await brain.asOf(base)
expect(calls.pins).toEqual([BigInt(base), BigInt(base + 1), BigInt(base)])
// A with() overlay takes its own pin on the same generation.
const spec = await db2.with([{ op: 'update', id: uid('vp-e'), metadata: { spec: true } }])
expect(calls.pins.length).toBe(4)
await db1.release()
await db2.release()
await db3.release()
await spec.release()
await spec.release() // idempotent — must NOT double-release the pin
expect(calls.releases.length).toBe(calls.pins.length)
expect([...calls.releases].sort()).toEqual([...calls.pins].sort())
})
// ==========================================================================
// Supporting guarantees: asOf, since, receipts, tx-log, honest errors
// ==========================================================================
it('asOf(generation) and asOf(Date) resolve historical state; future/negative are rejected', async () => {
const brain = await openMemoryBrain()
const tx1 = await brain.transact(
[
{
op: 'add',
id: uid('asof-e'),
type: NounType.Document,
data: 'v1',
vector: vec(90),
metadata: { v: 1 }
}
],
{ meta: { reason: 'first commit' } }
)
await new Promise((resolve) => setTimeout(resolve, 5))
const betweenCommits = new Date()
await new Promise((resolve) => setTimeout(resolve, 5))
await brain.transact([{ op: 'update', id: uid('asof-e'), metadata: { v: 2 } }])
// By generation.
const atFirst = await brain.asOf(tx1.generation)
expect(((await atFirst.get(uid('asof-e')))?.metadata as { v: number }).v).toBe(1)
expect(atFirst.timestamp).toBe(tx1.timestamp)
await atFirst.release()
// By timestamp: resolves to the newest commit at-or-before the instant.
const atInstant = await brain.asOf(betweenCommits)
expect(atInstant.generation).toBe(tx1.generation)
expect(((await atInstant.get(uid('asof-e')))?.metadata as { v: number }).v).toBe(1)
await atInstant.release()
// Honest range errors.
await expect(brain.asOf(brain.generation() + 100)).rejects.toThrow(RangeError)
await expect(brain.asOf(-1)).rejects.toThrow(RangeError)
await expect(brain.asOf('/no/such/snapshot/dir')).rejects.toThrow('not a snapshot directory')
// The transact meta was reified into the tx-log.
const lines = await brain.storageAdapter.readTxLogLines()
const entries = lines.map((line) => JSON.parse(line))
const first = entries.find((entry) => entry.generation === tx1.generation)
expect(first?.meta).toEqual({ reason: 'first commit' })
await tx1.release()
})
it('receipts resolve ids in input order, including intra-batch references and relate dedupe', async () => {
const brain = await openMemoryBrain()
const db = await brain.transact([
{ op: 'add', id: uid('rcpt-aa'), type: NounType.Person, data: 'a', vector: vec(91), metadata: {} },
{ op: 'add', id: uid('rcpt-bb'), type: NounType.Person, data: 'b', vector: vec(92), metadata: {} },
{ op: 'relate', from: uid('rcpt-aa'), to: uid('rcpt-bb'), type: VerbType.Knows },
{ op: 'update', id: uid('rcpt-bb'), metadata: { seen: true } }
])
expect(db.receipt).toBeDefined()
expect(db.receipt!.generation).toBe(db.generation)
expect(db.receipt!.ids.length).toBe(4)
expect(db.receipt!.ids[0]).toBe(uid('rcpt-aa'))
expect(db.receipt!.ids[1]).toBe(uid('rcpt-bb'))
expect(db.receipt!.ids[3]).toBe(uid('rcpt-bb'))
const relationId = db.receipt!.ids[2]
expect((await brain.related({ from: uid('rcpt-aa') }))[0].id).toBe(relationId)
// Duplicate relate (same from/to/type) dedupes to the SAME id — both
// within a batch and against committed state, mirroring relate().
const dup = await brain.transact([
{ op: 'relate', from: uid('rcpt-aa'), to: uid('rcpt-bb'), type: VerbType.Knows }
])
expect(dup.receipt!.ids[0]).toBe(relationId)
expect((await brain.related({ from: uid('rcpt-aa') })).length).toBe(1)
await db.release()
await dup.release()
})
it('since() reports the ids changed between two pinned views', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{ op: 'add', id: uid('since-a'), type: NounType.Document, data: 'a', vector: vec(93), metadata: {} }
])
const before = brain.now()
await brain.transact([
{ op: 'add', id: uid('since-b'), type: NounType.Document, data: 'b', vector: vec(94), metadata: {} },
{ op: 'relate', from: uid('since-a'), to: uid('since-b'), type: VerbType.References }
])
await brain.transact([{ op: 'update', id: uid('since-a'), metadata: { touched: true } }])
const after = brain.now()
const changed = await after.since(before)
expect([...changed.nouns].sort()).toEqual([uid('since-a'), uid('since-b')].sort())
expect(changed.verbs.length).toBe(1)
expect(changed.fromGeneration).toBe(before.generation)
expect(changed.toGeneration).toBe(after.generation)
// Direction is enforced.
await expect(before.since(after)).rejects.toThrow(RangeError)
await before.release()
await after.release()
})
it('historical vector search is served at the pinned generation via index materialization', async () => {
const brain = await openMemoryBrain()
// Two one-hot vectors: orthogonal under cosine, so nearest-neighbor
// results are fully deterministic.
const axisA = Array.from({ length: 384 }, (_, i) => (i === 0 ? 1 : 0))
const axisB = Array.from({ length: 384 }, (_, i) => (i === 1 ? 1 : 0))
const axisC = Array.from({ length: 384 }, (_, i) => (i === 2 ? 1 : 0))
await brain.transact([
{ op: 'add', id: uid('mat-a'), type: NounType.Document, data: 'a', vector: axisA, metadata: { who: 'a' } },
{ op: 'add', id: uid('mat-b'), type: NounType.Document, data: 'b', vector: axisB, metadata: { who: 'b' } },
{ op: 'add', id: uid('mat-del'), type: NounType.Document, data: 'del', vector: axisC, metadata: { who: 'del' } }
])
const db = brain.now()
// Mutate distinctively after the pin: swap a/b's vectors, delete 'del'.
await brain.transact([
{ op: 'update', id: uid('mat-a'), vector: axisB },
{ op: 'update', id: uid('mat-b'), vector: axisA },
{ op: 'remove', id: uid('mat-del') }
])
// Live index reflects the swap…
const liveNearA = await brain.find({ vector: axisA, limit: 1 })
expect(liveNearA[0].id).toBe(uid('mat-b'))
// …the pinned view finds the OLD vector placement, including the
// since-deleted entity, via the at-generation materialization.
const pinnedNearA = await db.find({ vector: axisA, limit: 1 })
expect(pinnedNearA[0].id).toBe(uid('mat-a'))
const pinnedNearC = await db.find({ vector: axisC, limit: 1 })
expect(pinnedNearC[0].id).toBe(uid('mat-del'))
// Record-path reads on the same Db stay consistent with the materialization.
expect(((await db.get(uid('mat-del')))?.metadata as { who: string }).who).toBe('del')
// Released views refuse all reads (and free the materialization).
await db.release()
await expect(db.find({ vector: axisA, limit: 1 })).rejects.toThrow('released Db')
})
it('historical graph traversal is served at the pinned generation via index materialization', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{ op: 'add', id: uid('trav-a'), type: NounType.Person, data: 'a', vector: vec(110), metadata: {} },
{ op: 'add', id: uid('trav-b'), type: NounType.Document, data: 'b', vector: vec(111), metadata: {} },
{ op: 'add', id: uid('trav-c'), type: NounType.Document, data: 'c', vector: vec(112), metadata: {} },
{ op: 'relate', from: uid('trav-a'), to: uid('trav-b'), type: VerbType.References }
])
const db = brain.now()
// Rewire the graph after the pin: a→b becomes a→c.
const oldEdge = (await brain.related({ from: uid('trav-a') }))[0]
await brain.transact([
{ op: 'unrelate', id: oldEdge.id },
{ op: 'relate', from: uid('trav-a'), to: uid('trav-c'), type: VerbType.References }
])
// Live traversal sees the new wiring…
const liveConnected = await brain.find({ connected: { from: uid('trav-a') }, limit: 10 })
expect(liveConnected.map((row) => row.id)).toContain(uid('trav-c'))
expect(liveConnected.map((row) => row.id)).not.toContain(uid('trav-b'))
// …the pinned view traverses the OLD graph.
const pinnedConnected = await db.find({ connected: { from: uid('trav-a') }, limit: 10 })
expect(pinnedConnected.map((row) => row.id)).toContain(uid('trav-b'))
expect(pinnedConnected.map((row) => row.id)).not.toContain(uid('trav-c'))
// The record-path related() agrees with the materialized traversal.
const pinnedEdges = await db.related({ from: uid('trav-a') })
expect(pinnedEdges.length).toBe(1)
expect(pinnedEdges[0].to).toBe(uid('trav-b'))
await db.release()
})
it('historical aggregation computes at-generation values via index materialization', async () => {
const brain = await openMemoryBrain()
brain.defineAggregate({
name: 'order_totals',
source: { type: NounType.Document },
groupBy: ['category'],
metrics: {
total: { op: 'sum', field: 'amount' },
orders: { op: 'count' }
}
})
await brain.transact([
{ op: 'add', id: uid('agg-1'), type: NounType.Document, data: 'o1', vector: vec(120), metadata: { category: 'invoice', amount: 10 } },
{ op: 'add', id: uid('agg-2'), type: NounType.Document, data: 'o2', vector: vec(121), metadata: { category: 'invoice', amount: 20 } }
])
const db = brain.now()
// Mutate after the pin: add an order and inflate an existing one.
await brain.transact([
{ op: 'add', id: uid('agg-3'), type: NounType.Document, data: 'o3', vector: vec(122), metadata: { category: 'invoice', amount: 70 } },
{ op: 'update', id: uid('agg-1'), metadata: { amount: 100 } }
])
// Live aggregate reflects the mutations…
const liveRows = await brain.find({ aggregate: 'order_totals' })
const liveInvoice = liveRows.find((row) => (row.metadata as { category: string }).category === 'invoice')
expect((liveInvoice?.metadata as { total: number }).total).toBe(190)
expect((liveInvoice?.metadata as { orders: number }).orders).toBe(3)
// …the pinned view computes the aggregate over the at-G record set.
const pinnedRows = await db.find({ aggregate: 'order_totals' })
const pinnedInvoice = pinnedRows.find((row) => (row.metadata as { category: string }).category === 'invoice')
expect((pinnedInvoice?.metadata as { total: number }).total).toBe(30)
expect((pinnedInvoice?.metadata as { orders: number }).orders).toBe(2)
await db.release()
})
it('asOf() pins serve the materialized surface; the build is cached per Db; release() closes the ephemeral reader', async () => {
const brain = await openMemoryBrain()
// Two one-hot vectors — orthogonal, fully deterministic neighbors.
const axisA = Array.from({ length: 384 }, (_, i) => (i === 0 ? 1 : 0))
const axisB = Array.from({ length: 384 }, (_, i) => (i === 1 ? 1 : 0))
const tx = await brain.transact([
{ op: 'add', id: uid('asof-mat-a'), type: NounType.Document, data: 'a', vector: axisA, metadata: {} },
{ op: 'add', id: uid('asof-mat-b'), type: NounType.Document, data: 'b', vector: axisB, metadata: {} }
])
const pinnedGeneration = tx.generation
await tx.release()
// Swap the vectors after the pin point, then open the past via asOf().
await brain.transact([
{ op: 'update', id: uid('asof-mat-a'), vector: axisB },
{ op: 'update', id: uid('asof-mat-b'), vector: axisA }
])
const db = await brain.asOf(pinnedGeneration)
// The asOf() view serves index-accelerated queries at its pinned
// generation — same materialized surface as a now() pin.
expect((await brain.find({ vector: axisA, limit: 1 }))[0].id).toBe(uid('asof-mat-b'))
expect((await db.find({ vector: axisA, limit: 1 }))[0].id).toBe(uid('asof-mat-a'))
// The O(n at G) build runs ONCE per Db: the second index query reuses
// the cached handle (typed access to the private cache, mirroring
// generationStoreOf above).
const internals = db as unknown as { materializedHandle?: Promise<HistoricalQueryHandle> }
expect(internals.materializedHandle).toBeDefined()
const handle = await internals.materializedHandle!
expect((await db.find({ vector: axisB, limit: 1 }))[0].id).toBe(uid('asof-mat-b'))
expect(await internals.materializedHandle).toBe(handle)
// release() frees the materialization by CLOSING the ephemeral reader —
// the reader itself refuses reads afterwards, proving its indexes and
// timers were torn down (not merely hidden behind the released-Db guard).
await db.release()
await db.release() // idempotent
await expect(db.find({ vector: axisA, limit: 1 })).rejects.toThrow('released Db')
await expect(handle.find({ vector: axisA, limit: 1 })).rejects.toThrow('not initialized')
})
it('speculative overlays keep the one honest boundary: index queries and persist throw SpeculativeOverlayError', async () => {
const brain = await openMemoryBrain()
await brain.transact([
{ op: 'add', id: uid('spec-e'), type: NounType.Document, data: 'x', vector: vec(95), metadata: { v: 1 } }
])
const db = brain.now()
const spec = await db.with([{ op: 'update', id: uid('spec-e'), metadata: { v: 2 } }])
// Metadata reads on the overlay are fully supported…
expect(((await spec.get(uid('spec-e')))?.metadata as { v: number }).v).toBe(2)
expect((await spec.find({ type: NounType.Document, where: { v: 2 } })).length).toBe(1)
// …index-accelerated dimensions and persist throw the named error.
await expect(spec.find({ query: 'anything' })).rejects.toThrow(SpeculativeOverlayError)
await expect(spec.find({ vector: vec(95) })).rejects.toThrow(SpeculativeOverlayError)
await expect(spec.find({ connected: { from: uid('spec-e') } })).rejects.toThrow(
SpeculativeOverlayError
)
await expect(spec.persist(path.join(makeTempDir(), 'overlay-snap'))).rejects.toThrow(
SpeculativeOverlayError
)
// The non-speculative base view is unaffected by the overlay boundary.
expect(((await db.get(uid('spec-e')))?.metadata as { v: number }).v).toBe(1)
await spec.release()
await db.release()
})
it('restore() requires confirmation and replaces state from a snapshot (generation floor preserved)', async () => {
const { brain } = await openFsBrain()
await brain.transact([
{ op: 'add', id: uid('restore-e'), type: NounType.Document, data: 'keep', vector: vec(96), metadata: { v: 1 } }
])
const snapDir = path.join(makeTempDir(), 'restore-snapshot')
const db = brain.now()
await db.persist(snapDir)
await db.release()
await brain.transact([{ op: 'update', id: uid('restore-e'), metadata: { v: 2 } }])
await brain.transact([
{ op: 'add', id: uid('restore-extra'), type: NounType.Document, data: 'extra', vector: vec(97), metadata: {} }
])
const beforeRestore = brain.generation()
await expect(
brain.restore(snapDir, { confirm: false })
).rejects.toThrow('confirm')
await brain.restore(snapDir, { confirm: true })
expect(((await brain.get(uid('restore-e')))?.metadata as { v: number }).v).toBe(1)
expect(await brain.get(uid('restore-extra'))).toBeNull()
expect((await brain.find({ type: NounType.Document, limit: 10 })).length).toBe(1)
// The counter never moves backwards — pre-restore generations are not reissued.
expect(brain.generation()).toBeGreaterThanOrEqual(beforeRestore)
const after = await brain.transact([{ op: 'update', id: uid('restore-e'), metadata: { v: 9 } }])
expect(after.generation).toBeGreaterThan(beforeRestore)
await after.release()
})
it('Db values are first-class: Brainy.open() + chained with() overlays compose', async () => {
const brain = await Brainy.open({ requireSubtype: false, storage: { type: 'memory' } })
brains.push(brain)
expect(brain.isInitialized).toBe(true)
await brain.transact([
{ op: 'add', id: uid('chain-e'), type: NounType.Document, data: 'x', vector: vec(98), metadata: { v: 1 } }
])
const db = brain.now()
const spec1 = await db.with([{ op: 'update', id: uid('chain-e'), metadata: { v: 2 } }])
const spec2 = await spec1.with([{ op: 'update', id: uid('chain-e'), metadata: { v: 3 } }])
expect(((await db.get(uid('chain-e')))?.metadata as { v: number }).v).toBe(1)
expect(((await spec1.get(uid('chain-e')))?.metadata as { v: number }).v).toBe(2)
expect(((await spec2.get(uid('chain-e')))?.metadata as { v: number }).v).toBe(3)
expect(spec2).toBeInstanceOf(Db)
await spec2.release()
await spec1.release()
await db.release()
})
it('transactionLog() returns committed entries newest first, with meta and limit', async () => {
const brain = await openMemoryBrain()
// Nothing committed yet — the log is empty (single-op writes do not log).
await brain.add({ id: uid('txlog-solo'), type: NounType.Document, data: 'solo', vector: vec(99), subtype: 'note' })
expect(await brain.transactionLog()).toEqual([])
const first = await brain.transact(
[{ op: 'add', id: uid('txlog-a'), type: NounType.Document, data: 'a', vector: vec(100), metadata: {} }],
{ meta: { author: 'job-1' } }
)
const second = await brain.transact(
[{ op: 'update', id: uid('txlog-a'), metadata: { v: 2 } }],
{ meta: { author: 'job-2' } }
)
const third = await brain.transact([{ op: 'update', id: uid('txlog-a'), metadata: { v: 3 } }])
const entries = await brain.transactionLog()
expect(entries.map((entry) => entry.generation)).toEqual([
third.generation,
second.generation,
first.generation
])
expect(entries[1].meta).toEqual({ author: 'job-2' })
expect(entries[2].meta).toEqual({ author: 'job-1' })
expect(entries[0].meta).toBeUndefined()
for (const entry of entries) {
expect(entry.timestamp).toBeGreaterThan(0)
}
const limited = await brain.transactionLog({ limit: 2 })
expect(limited.map((entry) => entry.generation)).toEqual([third.generation, second.generation])
await first.release()
await second.release()
await third.release()
})
// ==========================================================================
// 9. asOf() / released-Db error paths (Y.15 spot-checks)
// ==========================================================================
it('proof 9 — asOf() rejects out-of-range targets and a released Db throws on every read', async () => {
const brain = await openMemoryBrain()
await (
await brain.transact([
{ op: 'add', id: uid('asof-err'), type: NounType.Document, data: 'x', metadata: { v: 1 } }
])
).release()
const current = brain.generation()
// Negative, non-integer, and future generations are honest RangeErrors —
// never a silent clamp to a neighbouring generation.
await expect(brain.asOf(-1)).rejects.toThrow(RangeError)
await expect(brain.asOf(1.5)).rejects.toThrow(RangeError)
await expect(brain.asOf(current + 999)).rejects.toThrow(RangeError)
// A string that is not a snapshot directory is a descriptive error, not a crash.
await expect(brain.asOf('/no/such/snapshot/dir')).rejects.toThrow(/not a snapshot directory/)
// Use-after-release is rejected on every read method, naming the released generation.
const db = brain.now()
await db.release()
await expect(db.get(uid('asof-err'))).rejects.toThrow(/released Db/)
await expect(db.find({ where: { v: 1 } })).rejects.toThrow(/released Db/)
await expect(db.related(uid('asof-err'))).rejects.toThrow(/released Db/)
})
})