open-brainy/tests/integration/log-authority.test.ts

341 lines
14 KiB
TypeScript
Raw Normal View History

fix(log): acked writes survive power loss; rejected writes never silently commit — the kill-matrix goes 11/11 with zero .fails debt Two release-blocking findings from the durability kill-matrix, both fixed in the owning layer: 1. LOG-AUTHORITY REPLAY AT OPEN: durable-at-ack fsynced the fact before the ack, but open() truncated every fact above the manifest — after a power loss that takes the un-fsynced tmp+rename canonical bytes, the acked write's ONLY durable copy was discarded. Now: under 'log' authority, open() REPLAYS intact facts above the manifest into canonical (FactLog.peekFactsAbove — CRC-gated, order-sorted) and advances the manifest to cover them; tree-authority brains keep the truncate contract they were promised. Pinned end to end: the power-loss row constructs the exact disk state (fsynced log, vanished canonical rename) and the acked write lives. 2. NO SILENT COMMIT: commitSingleOp buffered the generation BEFORE the fact append; an append failure (ENOSPC) rejected the caller but the next flush durably committed the generation with NO fact — a permanent silent log gap. Now the failure path un-buffers and returns the counter reservation: nothing commits, the log stays gap-free, and the canonical execute-residue orphan is the documented crash-equivalent. Plus: the kill-matrix itself (11 rows — every commit-path fault point × reopen-as-crash recovery contract, at-ack variants, disk-full row; five new zero-cost faultPoint sites), the log-authority pin suite (oracle green/red/state-differs, flip refusal, switch survives reopen, 9/9), and the group-commit covering pins (5/5). Gates: unit 2002/2002 (152 files) · integration 785 · conformance 27/27.
2026-08-10 09:29:21 -07:00
/**
* @module tests/integration/log-authority
* @description The guarded log-authority core, end-to-end: the per-brain
* authority switch (default 'tree', stored artifact, checked at open only),
* the verification oracle (replay the fact log, diff latest per-id state
* against the canonical tree, NAME every divergence by class), the guarded
* flip (refuses on red with the cure in the message; lands on green and
* engages durable-at-ack immediately), and the switch surviving reopen.
*
* KNOWN GAPS PINNED WITH `.fails` (real findings, not test bugs see the
* comments on each): a fresh brain is NOT log-complete by construction
* today, because the VFS root is written at init as a baseline
* (generation-less) write that never gets a fact, so the oracle reports it
* as a `pre-log-record` and no fresh brain can flip without a manual
* baseline backfill. The tests that need a green oracle perform that
* backfill explicitly (an identity update of the root as the FINAL write
* final, because derived-index maintenance rewrites canonical noun records
* outside generations, so an earlier fact's after-image goes stale; see the
* module tail comment on `backfillBaseline`).
*/
import { describe, it, expect, afterEach } from 'vitest'
import { mkdtempSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { Brainy } from '../../src/index.js'
import type { OracleReport } from '../../src/db/logAuthority.js'
/** The VFS root — created at init by a baseline (generation-less) write. */
const VFS_ROOT = '00000000-0000-0000-0000-000000000000'
const AUTHORITY_ARTIFACT = '_system/log-authority.json'
/** White-box view of the internals this suite instruments (read-only spies
* plus the sanctioned direct-storage writes for aging/drifting a brain). */
type BrainInternals = {
generationStore: {
getFactLog(): { ensureSynced(): Promise<void> } | null
logDurability: 'deferred' | 'at-ack'
}
storage: {
readRawObject(path: string): Promise<unknown | null>
saveNoun(n: unknown): Promise<void>
saveNounMetadata(id: string, m: Record<string, unknown>): Promise<void>
getNounMetadata(id: string): Promise<Record<string, unknown> | null>
}
}
const internals = (brain: Brainy): BrainInternals =>
brain as unknown as BrainInternals
/** Count calls to the fact log's ensureSynced without changing behavior. */
function spyEnsureSynced(brain: Brainy): { calls: () => number } {
const factLog = internals(brain).generationStore.getFactLog()
expect(factLog, 'filesystem storage hosts a fact log').not.toBeNull()
let calls = 0
const original = factLog!.ensureSynced.bind(factLog)
factLog!.ensureSynced = async () => {
calls++
return original()
}
return { calls: () => calls }
}
/**
* The minimal baseline backfill: an identity update of the VFS root, so the
* one canonical record the log never saw (the init-time baseline write) gets
* a fact carrying its current state. MUST be the final write of the setup
* derived-index maintenance (HNSW/enumeration denormalization) rewrites the
* root's canonical noun record outside any generation, so a root fact taken
* before later writes digests stale and reports `state-differs`.
*/
async function backfillBaseline(brain: Brainy): Promise<void> {
const root = await brain.get(VFS_ROOT)
expect(root, 'the VFS root exists on a fresh brain').toBeTruthy()
await brain.update({ id: VFS_ROOT, metadata: root!.metadata })
}
/** Seed a brain with the standard write mix: 2 adds, an update, a remove. */
async function seedWrites(brain: Brainy): Promise<{ kept: string; removed: string }> {
const kept = await brain.add({ data: 'alpha document', type: 'document', metadata: { n: 1 } })
const removed = await brain.add({ data: 'beta document', type: 'document', metadata: { n: 2 } })
await brain.update({ id: kept, metadata: { n: 10 } })
await brain.remove(removed)
return { kept, removed }
}
describe('log authority — the switch, the oracle, the guarded flip', () => {
const dirs: string[] = []
const brains: Brainy[] = []
const openBrain = async (dir?: string): Promise<{ brain: Brainy; dir: string }> => {
const d = dir ?? mkdtempSync(join(tmpdir(), 'brainy-log-authority-'))
if (!dir) dirs.push(d)
const brain = new Brainy({
storage: { type: 'filesystem', path: d },
requireSubtype: false,
silent: true,
dimensions: 384
})
brains.push(brain)
await brain.init()
return { brain, dir: d }
}
afterEach(async () => {
for (const b of brains.splice(0)) {
await (b as unknown as { close?: () => Promise<void> }).close?.().catch(() => {})
}
for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true })
})
it('DEFAULT IS TREE: a fresh brain reports tree authority, stores no artifact, and plain acks never await a log fsync', async () => {
const { brain } = await openBrain()
expect(brain.logAuthority().authority).toBe('tree')
expect(brain.logAuthority().flippedAt).toBeUndefined()
const artifact = await internals(brain)
.storage.readRawObject(AUTHORITY_ARTIFACT)
.catch(() => null)
expect(artifact, 'no switch artifact exists before any flip').toBeNull()
// The MODE assertion (not a timing one): in tree authority a single-op
// ack must never call the log's covering-fsync path.
const spy = spyEnsureSynced(brain)
await brain.add({ data: 'tree mode write', type: 'document', metadata: { n: 1 } })
expect(spy.calls(), 'tree mode: add() does not call ensureSynced').toBe(0)
expect(internals(brain).generationStore.logDurability).toBe('deferred')
})
// KNOWN GAP (marked .fails — remove the marker when fixed in src): the
// intended contract is that a fresh brain is log-complete by construction,
// because every write dual-writes a fact. Today the VFS root
// (00000000-0000-0000-0000-000000000000) is created at init by a baseline
// write with NO generation and NO fact, yet it is enumerated by the
// canonical walk — so the oracle on a fresh brain is red with exactly one
// `pre-log-record` mismatch on the root, and adoptLogAuthority() refuses
// on every fresh brain. Verified empirically on this branch.
it.fails('ORACLE INTENT: a fresh brain is log-complete by construction — verdict green with zero mismatches', async () => {
const { brain } = await openBrain()
await seedWrites(brain)
await brain.flush()
const report = await brain.verifyLogAuthority()
expect(report.verdict).toBe('green')
expect(report.mismatches).toEqual([])
})
it('a fresh, un-backfilled brain diverges ONLY on the init-time baseline record — every user write is exactly reproduced', async () => {
const { brain } = await openBrain()
await seedWrites(brain)
await brain.flush()
const report = await brain.verifyLogAuthority()
// Tolerant pin (stays true after the baseline gap is fixed in src):
// whatever the verdict, no USER record may ever diverge — the only
// admissible mismatch is the init-time baseline root, as pre-log-record.
expect(
report.mismatches.every(
(m) => m.id === VFS_ROOT && m.reason === 'pre-log-record' && m.kind === 'noun'
),
'the only divergence on a fresh brain is the baseline root record'
).toBe(true)
expect(report.matched).toBe(report.nounsChecked - report.mismatches.length)
expect(report.mismatchListTruncated).toBe(false)
})
it('THE ORACLE GOES GREEN on a log-complete brain: adds + update + remove, every canonical row exactly reproduced', async () => {
const { brain } = await openBrain()
await seedWrites(brain)
await backfillBaseline(brain) // final write — see the helper's contract
await brain.flush()
const report = await brain.verifyLogAuthority()
expect(report.verdict).toBe('green')
expect(report.mismatches).toEqual([])
expect(report.mismatchListTruncated).toBe(false)
// Live count: the kept document + the VFS root (the removed one is a
// tombstone in the log and absent from canonical — checked, not counted).
expect(report.nounsChecked).toBe(2)
expect(report.matched).toBe(2)
// 5 committed generations: add, add, update, remove, root backfill.
expect(report.generationsScanned).toBe(5)
})
it('THE ORACLE NAMES pre-log records: a canonical row no fact ever recorded reports pre-log-record, by id', async () => {
const { brain } = await openBrain()
await seedWrites(brain)
await backfillBaseline(brain)
await brain.flush()
expect((await brain.verifyLogAuthority()).verdict, 'sanity: green before aging').toBe('green')
// Simulate an aged brain: write one canonical record DIRECTLY at the
// storage layer (the write path never sees it, so no fact exists) —
// the pre-log shape: flat metadata, no _fmt stamp, 384-dim vector.
const legacyId = '00000000-0000-4000-8000-00000000a6ed'
const storage = internals(brain).storage
await storage.saveNoun({
id: legacyId,
vector: new Array(384).fill(0.01),
connections: new Map(),
level: 0
})
await storage.saveNounMetadata(legacyId, {
noun: 'document',
confidence: 0.75,
createdAt: 1700000000000,
updatedAt: 1700000000000,
_rev: 1,
legacyField: 'legacy-value'
})
const report = await brain.verifyLogAuthority()
expect(report.verdict).toBe('red')
expect(report.mismatches).toHaveLength(1)
expect(report.mismatches[0]).toEqual({
id: legacyId,
kind: 'noun',
reason: 'pre-log-record'
})
})
it('THE FLIP REFUSES ON RED: names the oracle verdict and the cure, writes nothing, changes nothing', async () => {
const { brain } = await openBrain()
await seedWrites(brain)
await backfillBaseline(brain)
await brain.flush()
// Age the brain: one canonical record the log never saw.
const legacyId = '00000000-0000-4000-8000-00000000a6ed'
const storage = internals(brain).storage
await storage.saveNoun({
id: legacyId,
vector: new Array(384).fill(0.01),
connections: new Map(),
level: 0
})
await storage.saveNounMetadata(legacyId, {
noun: 'document',
confidence: 0.5,
createdAt: 1700000000000,
updatedAt: 1700000000000,
_rev: 1
})
let error: Error | null = null
try {
await brain.adoptLogAuthority()
} catch (err) {
error = err as Error
}
expect(error, 'the flip rejects on a red oracle').not.toBeNull()
expect(error!.message).toMatch(/oracle is RED/)
expect(error!.message).toMatch(/baseline backfill/)
// Nothing changed: authority still tree, no artifact, deferred durability.
expect(brain.logAuthority().authority).toBe('tree')
const artifact = await storage.readRawObject(AUTHORITY_ARTIFACT).catch(() => null)
expect(artifact, 'a refused flip writes no artifact').toBeNull()
expect(internals(brain).generationStore.logDurability).toBe('deferred')
})
it('THE FLIP LANDS ON GREEN: the report is the receipt, the artifact is on disk, and durable-at-ack engages immediately', async () => {
const { brain } = await openBrain()
await seedWrites(brain)
await backfillBaseline(brain)
await brain.flush()
const report: OracleReport = await brain.adoptLogAuthority()
expect(report.verdict).toBe('green')
const authority = brain.logAuthority()
expect(authority.authority).toBe('log')
expect(typeof authority.flippedAt).toBe('number')
expect(authority.oracle).toBeDefined()
expect(authority.oracle!.nounsChecked).toBe(report.nounsChecked)
expect(authority.oracle!.generationsScanned).toBe(report.generationsScanned)
const artifact = (await internals(brain)
.storage.readRawObject(AUTHORITY_ARTIFACT)
.catch(() => null)) as { authority?: string } | null
expect(artifact, 'the switch artifact exists on disk').not.toBeNull()
expect(artifact!.authority).toBe('log')
// Durable-at-ack engaged in THIS session: the next single-op ack awaits
// a covering log fsync.
expect(internals(brain).generationStore.logDurability).toBe('at-ack')
const spy = spyEnsureSynced(brain)
await brain.add({ data: 'post-flip write', type: 'document', metadata: { n: 3 } })
expect(spy.calls(), 'log mode: add() awaits the covering fsync').toBeGreaterThanOrEqual(1)
})
it('THE SWITCH SURVIVES REOPEN: authority restored at open with no re-verification, durable-at-ack active in the new session', async () => {
const { brain, dir } = await openBrain()
await seedWrites(brain)
await backfillBaseline(brain)
await brain.flush()
await brain.adoptLogAuthority()
const flipReceipt = brain.logAuthority()
await (brain as unknown as { close: () => Promise<void> }).close()
const { brain: reopened } = await openBrain(dir)
const restored = reopened.logAuthority()
expect(restored.authority).toBe('log')
// No re-verification happened at open: the restored record IS the stored
// flip receipt, oracle summary and timestamp intact.
expect(restored.flippedAt).toBe(flipReceipt.flippedAt)
expect(restored.oracle).toEqual(flipReceipt.oracle)
// Mode restored at open: an ack in the new session awaits the log fsync.
expect(internals(reopened).generationStore.logDurability).toBe('at-ack')
const spy = spyEnsureSynced(reopened)
await reopened.add({ data: 'new session write', type: 'document', metadata: { n: 4 } })
expect(spy.calls(), 'reopened log mode: add() awaits the covering fsync').toBeGreaterThanOrEqual(1)
})
it('STATE-DIFFERS: canonical drift the write path never saw is named, by id', async () => {
const { brain } = await openBrain()
const { kept } = await seedWrites(brain)
await backfillBaseline(brain)
await brain.flush()
expect((await brain.verifyLogAuthority()).verdict, 'sanity: green before drift').toBe('green')
// Drift one canonical metadata record DIRECTLY at the storage layer —
// the log never hears about it. This is the witness-drift case the
// oracle exists to catch.
const storage = internals(brain).storage
const current = await storage.getNounMetadata(kept)
expect(current, 'the seeded record has stored metadata').toBeTruthy()
await storage.saveNounMetadata(kept, { ...current!, driftedByTest: true })
const report = await brain.verifyLogAuthority()
expect(report.verdict).toBe('red')
expect(report.mismatches).toHaveLength(1)
expect(report.mismatches[0]).toEqual({
id: kept,
kind: 'noun',
reason: 'state-differs'
})
})
})