fix(adoption): the baseline backfill runs to completion — one call adopts a pre-log baseline of any size
A production brain with a 12.7k-row pre-log baseline advanced exactly 800 rows per adoptLogAuthority() call (a five-pass ceiling × the oracle's 200-row listing cap), refused the flip, and sat tree-authoritative for hours across restarts. The bound was sized for drift, never for a baseline. Now: the adoption path runs the oracle uncapped so ONE scan yields the ENTIRE curable set, every pass cures all of it, and the loop runs to completion with the no-progress guard as its only stop. Pace rides the write path (one full-brain scan amortizes over thousands of cures, not two hundred): 1,000 drifted rows adopt green in one call in ~10s. Progress is narrated for a live operator. The wire report keeps its 200-row cap. Pinned: a baseline above the old ceiling adopts green in a single call.
This commit is contained in:
parent
3915180f7b
commit
a5a1883819
3 changed files with 145 additions and 9 deletions
|
|
@ -8208,10 +8208,20 @@ export class Brainy<T = any> implements BrainyInterface<T> {
|
||||||
* (digests, never bodies).
|
* (digests, never bodies).
|
||||||
*/
|
*/
|
||||||
async verifyLogAuthority(): Promise<OracleReport> {
|
async verifyLogAuthority(): Promise<OracleReport> {
|
||||||
|
return this.runOracle()
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* The oracle run behind {@link Brainy.verifyLogAuthority}; the adoption
|
||||||
|
* backfill calls it with `listAll` so one scan yields the ENTIRE curable
|
||||||
|
* mismatch set instead of the wire-capped first 200.
|
||||||
|
*/
|
||||||
|
private async runOracle(options?: { listAll?: boolean }): Promise<OracleReport> {
|
||||||
await this.ensureInitialized()
|
await this.ensureInitialized()
|
||||||
return runLogCompletenessOracle({
|
return runLogCompletenessOracle({
|
||||||
storage: this.storage as unknown as LogAuthorityStorage,
|
storage: this.storage as unknown as LogAuthorityStorage,
|
||||||
scanFacts: () => this.scanFacts(),
|
scanFacts: () => this.scanFacts(),
|
||||||
|
...(options?.listAll ? { mismatchListCap: Number.POSITIVE_INFINITY } : {}),
|
||||||
// Both sides normalize to ENTITY TRUTH before digesting: canonical
|
// Both sides normalize to ENTITY TRUTH before digesting: canonical
|
||||||
// wrappers denormalize HNSW residue (connections/level) the log never
|
// wrappers denormalize HNSW residue (connections/level) the log never
|
||||||
// carries — digesting it would fake state-differs on any nonzero-level
|
// carries — digesting it would fake state-differs on any nonzero-level
|
||||||
|
|
@ -8256,7 +8266,7 @@ export class Brainy<T = any> implements BrainyInterface<T> {
|
||||||
/** The adoption body — see {@link Brainy.adoptLogAuthority} (which owns the
|
/** The adoption body — see {@link Brainy.adoptLogAuthority} (which owns the
|
||||||
* fold-checkpoint bootstrap arm/disarm around it). */
|
* fold-checkpoint bootstrap arm/disarm around it). */
|
||||||
private async adoptLogAuthorityInner(): Promise<OracleReport> {
|
private async adoptLogAuthorityInner(): Promise<OracleReport> {
|
||||||
let report = await this.verifyLogAuthority()
|
let report = await this.runOracle({ listAll: true })
|
||||||
|
|
||||||
// BASELINE BACKFILL: curable divergences are rows whose CANONICAL truth
|
// BASELINE BACKFILL: curable divergences are rows whose CANONICAL truth
|
||||||
// simply never reached the log — pre-log records (e.g. the generation-0
|
// simply never reached the log — pre-log records (e.g. the generation-0
|
||||||
|
|
@ -8268,8 +8278,18 @@ export class Brainy<T = any> implements BrainyInterface<T> {
|
||||||
// Log-AHEAD divergences (log-live-canonical-absent /
|
// Log-AHEAD divergences (log-live-canonical-absent /
|
||||||
// log-tombstone-canonical-present) are NOT curable by backfill — the
|
// log-tombstone-canonical-present) are NOT curable by backfill — the
|
||||||
// log claims things the witness denies — and refuse loudly below.
|
// log claims things the witness denies — and refuse loudly below.
|
||||||
|
//
|
||||||
|
// RUNS TO COMPLETION. Each pass sees the ENTIRE curable set (the oracle
|
||||||
|
// is run uncapped here) and cures all of it, so a pre-log baseline of
|
||||||
|
// any size adopts in ONE call — the only stop is the no-progress guard.
|
||||||
|
// A production brain with a 12.7k-row baseline once advanced exactly
|
||||||
|
// 800 rows per call (a five-pass ceiling × the 200-row wire cap) and sat
|
||||||
|
// tree-authoritative for hours; the bound was sized for drift, never
|
||||||
|
// for a baseline. Pace rides the write path now: one full-brain scan
|
||||||
|
// per pass amortizes over thousands of cures, not two hundred.
|
||||||
let passes = 0
|
let passes = 0
|
||||||
while (report.verdict === 'red' && passes < 5) {
|
for (;;) {
|
||||||
|
if (report.verdict !== 'red') break
|
||||||
passes++
|
passes++
|
||||||
const curable = report.mismatches.filter(
|
const curable = report.mismatches.filter(
|
||||||
(m) => m.reason === 'pre-log-record' || m.reason === 'state-differs'
|
(m) => m.reason === 'pre-log-record' || m.reason === 'state-differs'
|
||||||
|
|
@ -8290,9 +8310,19 @@ export class Brainy<T = any> implements BrainyInterface<T> {
|
||||||
`[Brainy] adoptLogAuthority: baseline backfill pass ${passes} — re-committing ` +
|
`[Brainy] adoptLogAuthority: baseline backfill pass ${passes} — re-committing ` +
|
||||||
`${curable.length} row(s) whose canonical truth never reached the log`
|
`${curable.length} row(s) whose canonical truth never reached the log`
|
||||||
)
|
)
|
||||||
|
// Progress narration for a live operator: a large baseline is minutes
|
||||||
|
// of visible motion, never a silent wait.
|
||||||
|
const narrateEvery = curable.length >= 2000 ? 1000 : curable.length >= 400 ? 200 : 0
|
||||||
|
let cured = 0
|
||||||
for (const m of curable) {
|
for (const m of curable) {
|
||||||
const raw = await this.storage.readNounRaw(m.id)
|
const raw = await this.storage.readNounRaw(m.id)
|
||||||
if (raw.metadata === null && raw.vector === null) continue // vanished since the scan
|
if (raw.metadata === null && raw.vector === null) continue // vanished since the scan
|
||||||
|
cured++
|
||||||
|
if (narrateEvery > 0 && cured % narrateEvery === 0) {
|
||||||
|
prodLog.info(
|
||||||
|
`[Brainy] adoptLogAuthority: backfill pass ${passes} — ${cured}/${curable.length} rows re-committed`
|
||||||
|
)
|
||||||
|
}
|
||||||
// LAW-SHAPE RE-COMMIT: rewrite canonical as EXACTLY the wrapper the
|
// LAW-SHAPE RE-COMMIT: rewrite canonical as EXACTLY the wrapper the
|
||||||
// log's reconstruction produces (the hydration law: denormalized
|
// log's reconstruction produces (the hydration law: denormalized
|
||||||
// enumeration fields derived from the metadata leg + the embedding
|
// enumeration fields derived from the metadata leg + the embedding
|
||||||
|
|
@ -8330,12 +8360,11 @@ export class Brainy<T = any> implements BrainyInterface<T> {
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
const next = await this.verifyLogAuthority()
|
const next = await this.runOracle({ listAll: true })
|
||||||
if (
|
// THE ONLY STOP: no progress. With uncapped listings both counts are
|
||||||
next.verdict === 'red' &&
|
// exact, so "not fewer mismatches than before" means the cure could
|
||||||
next.mismatches.length >= report.mismatches.length &&
|
// not express this divergence — refuse to spin, name it.
|
||||||
!report.mismatchListTruncated
|
if (next.verdict === 'red' && next.mismatches.length >= report.mismatches.length) {
|
||||||
) {
|
|
||||||
throw new Error(
|
throw new Error(
|
||||||
`adoptLogAuthority(): baseline backfill made no progress ` +
|
`adoptLogAuthority(): baseline backfill made no progress ` +
|
||||||
`(${report.mismatches.length} → ${next.mismatches.length} mismatches; first: ` +
|
`(${report.mismatches.length} → ${next.mismatches.length} mismatches; first: ` +
|
||||||
|
|
@ -8345,6 +8374,12 @@ export class Brainy<T = any> implements BrainyInterface<T> {
|
||||||
}
|
}
|
||||||
report = next
|
report = next
|
||||||
}
|
}
|
||||||
|
if (passes > 0) {
|
||||||
|
prodLog.info(
|
||||||
|
`[Brainy] adoptLogAuthority: baseline backfill complete in ${passes} pass(es) — ` +
|
||||||
|
`oracle ${report.verdict}, ${report.nounsChecked} noun(s) checked`
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
this._logAuthority = await flipToLogAuthority(
|
this._logAuthority = await flipToLogAuthority(
|
||||||
this.storage as unknown as LogAuthorityStorage,
|
this.storage as unknown as LogAuthorityStorage,
|
||||||
|
|
|
||||||
|
|
@ -165,7 +165,16 @@ export async function runLogCompletenessOracle(args: {
|
||||||
getVerbs?: (opts: {
|
getVerbs?: (opts: {
|
||||||
pagination: { limit: number; offset?: number; cursor?: string }
|
pagination: { limit: number; offset?: number; cursor?: string }
|
||||||
}) => Promise<{ items: unknown[]; hasMore?: boolean; nextCursor?: string }>
|
}) => Promise<{ items: unknown[]; hasMore?: boolean; nextCursor?: string }>
|
||||||
|
/**
|
||||||
|
* Cap on the LISTED mismatches (counts are always complete). Defaults to
|
||||||
|
* the wire-friendly {@link MISMATCH_LIST_CAP}; the adoption backfill passes
|
||||||
|
* `Infinity` so ONE scan yields the ENTIRE curable set — a production
|
||||||
|
* brain with a 12.7k-row pre-log baseline once advanced only 800 rows per
|
||||||
|
* adoption call because each pass could see (and cure) at most 200.
|
||||||
|
*/
|
||||||
|
mismatchListCap?: number
|
||||||
}): Promise<OracleReport> {
|
}): Promise<OracleReport> {
|
||||||
|
const listCap = args.mismatchListCap ?? MISMATCH_LIST_CAP
|
||||||
const report: OracleReport = {
|
const report: OracleReport = {
|
||||||
verdict: 'red',
|
verdict: 'red',
|
||||||
generationsScanned: 0,
|
generationsScanned: 0,
|
||||||
|
|
@ -176,7 +185,7 @@ export async function runLogCompletenessOracle(args: {
|
||||||
mismatchListTruncated: false
|
mismatchListTruncated: false
|
||||||
}
|
}
|
||||||
const addMismatch = (m: OracleMismatch): void => {
|
const addMismatch = (m: OracleMismatch): void => {
|
||||||
if (report.mismatches.length < MISMATCH_LIST_CAP) report.mismatches.push(m)
|
if (report.mismatches.length < listCap) report.mismatches.push(m)
|
||||||
else report.mismatchListTruncated = true
|
else report.mismatchListTruncated = true
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
||||||
92
tests/integration/adopt-large-baseline.test.ts
Normal file
92
tests/integration/adopt-large-baseline.test.ts
Normal file
|
|
@ -0,0 +1,92 @@
|
||||||
|
/**
|
||||||
|
* @module tests/integration/adopt-large-baseline
|
||||||
|
* @description Adoption runs the baseline backfill TO COMPLETION in one call.
|
||||||
|
* A production brain with a 12.7k-row pre-log baseline once advanced exactly
|
||||||
|
* 800 rows per `adoptLogAuthority()` call (a five-pass ceiling × the oracle's
|
||||||
|
* 200-row listing cap), refused the flip, and sat tree-authoritative for
|
||||||
|
* hours across restarts. The pin: a baseline larger than that old ceiling
|
||||||
|
* — every row oracle-visible as `state-differs` drift — adopts GREEN in a
|
||||||
|
* SINGLE call, and the row count proves the whole set was cured, not a page.
|
||||||
|
*/
|
||||||
|
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 { NounType } from '../../src/types/graphTypes.js'
|
||||||
|
|
||||||
|
type RawBox = {
|
||||||
|
storage: {
|
||||||
|
readNounRaw(id: string): Promise<{ metadata: unknown; vector: unknown }>
|
||||||
|
writeNounRaw(id: string, r: { metadata: unknown; vector: unknown }): Promise<void>
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
const dirs: string[] = []
|
||||||
|
const brains: Brainy[] = []
|
||||||
|
afterEach(async () => {
|
||||||
|
for (const b of brains.splice(0)) await b.close().catch(() => {})
|
||||||
|
for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true })
|
||||||
|
})
|
||||||
|
|
||||||
|
describe('adoption backfill runs to completion', () => {
|
||||||
|
it('a pre-log baseline larger than the old 800-row ceiling adopts GREEN in ONE call', async () => {
|
||||||
|
const dir = mkdtempSync(join(tmpdir(), 'brainy-large-baseline-'))
|
||||||
|
dirs.push(dir)
|
||||||
|
const brain = new Brainy({
|
||||||
|
storage: { type: 'filesystem', path: dir },
|
||||||
|
requireSubtype: false,
|
||||||
|
logAuthority: 'defer'
|
||||||
|
})
|
||||||
|
await brain.init()
|
||||||
|
brains.push(brain)
|
||||||
|
|
||||||
|
// Above the old ceiling (5 passes × 200 = 800): every row must be cured
|
||||||
|
// in the one call for the flip to be legal.
|
||||||
|
const ROWS = 1000
|
||||||
|
const ids: string[] = []
|
||||||
|
for (let i = 0; i < ROWS; i++) {
|
||||||
|
ids.push(
|
||||||
|
await brain.add({
|
||||||
|
data: `baseline row ${i}`,
|
||||||
|
type: NounType.Document,
|
||||||
|
metadata: { i },
|
||||||
|
vector: Array.from({ length: 384 }, (_, k) => ((i + k) % 7) / 7)
|
||||||
|
})
|
||||||
|
)
|
||||||
|
}
|
||||||
|
await brain.flush()
|
||||||
|
|
||||||
|
// Manufacture the production shape on EVERY row: pre-hydration-law drift
|
||||||
|
// (a stored wrapper whose denormalized fields disagree with its own
|
||||||
|
// metadata leg) — each is a curable `state-differs` mismatch, so the
|
||||||
|
// oracle's full curable set is ROWS, well past any per-pass page.
|
||||||
|
const storage = (brain as unknown as RawBox).storage
|
||||||
|
for (const id of ids) {
|
||||||
|
const raw = await storage.readNounRaw(id)
|
||||||
|
const wrapper = raw.vector as Record<string, unknown>
|
||||||
|
await storage.writeNounRaw(id, {
|
||||||
|
metadata: raw.metadata,
|
||||||
|
vector: { ...wrapper, noun: 'thing', legacyField: 'pre-law residue' }
|
||||||
|
})
|
||||||
|
}
|
||||||
|
const before = await brain.verifyLogAuthority()
|
||||||
|
expect(before.verdict, 'the whole baseline is oracle-red').toBe('red')
|
||||||
|
// The wire report is capped at 200 — the truncation flag is what the old
|
||||||
|
// loop bounded itself on; the cure path no longer reads through it.
|
||||||
|
expect(before.mismatchListTruncated).toBe(true)
|
||||||
|
|
||||||
|
// THE PIN: one call, green, log-authoritative — no restarts, no loop.
|
||||||
|
const report = await brain.adoptLogAuthority()
|
||||||
|
expect(report.verdict).toBe('green')
|
||||||
|
expect(brain.logAuthority().authority).toBe('log')
|
||||||
|
expect(report.nounsChecked).toBeGreaterThanOrEqual(ROWS)
|
||||||
|
|
||||||
|
// Nothing degraded: a sample of rows still serves with intact metadata.
|
||||||
|
for (const id of [ids[0], ids[499], ids[ROWS - 1]]) {
|
||||||
|
const row = await brain.get(id)
|
||||||
|
expect(row).not.toBeNull()
|
||||||
|
expect(typeof (row!.metadata as { i: number }).i).toBe('number')
|
||||||
|
}
|
||||||
|
}, 600000)
|
||||||
|
})
|
||||||
Loading…
Add table
Add a link
Reference in a new issue