fix(#370): ES2021-safe spec, source-specific idle ceiling, processor lock, tested index mapping (review round 1)

F1 [BLOCKER] persistence-store.spec used Array.prototype.at(-1) (ES2022) but the
server targets ES2021, so server tsc failed (TS2550) and ts-jest could not
compile the suite — 22 core manual-save/idle/boundary tests silently did not run
in CI. Replaced with [length - 1] index access.

F2 [WARNING] The idle burst-reset used a hardcoded IDLE_MAX_WAIT_USER for both
tiers, but computeHistoryJob's ceiling is source-specific. On a continuously
agent-edited page the burst marker stayed stale for 5..10m, forcing delay=0 on
every store and writing one idle row per store — the exact per-store bloat the
debounce prevents. The reset now uses the same source-specific max-wait.

F3 [WARNING] The processor did an unlocked findPageLastHistory -> saveHistory,
which TOCTOU-races a concurrent manual-save (that runs under a page-row lock),
producing two page_history rows with identical content (one idle, one manual) and
defeating promote-not-dup. The snapshot decision is now wrapped in executeTx with
the same page-row lock, so the second writer observes the first's committed row
and the isDeepStrictEqual gate collapses the duplicate.

F4 [WARNING] The risky client filtered-index -> full-list mapping had no tests.
Extracted it to a pure resolvePrevSnapshotId(fullItems, id) helper (diff/restore
baseline against the true previous snapshot in the FULL list, never the previous
visible version) and unit-tested it; removed the now-vestigial index threading.

F5/F6 [low] Renamed the misleading ceiling test + fixed its comment; added a
CHANGELOG entry for the user-facing versioning feature.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
agent_coder
2026-07-05 05:31:26 +03:00
committed by agent_coder
parent e10e79c0c4
commit 73146aad21
10 changed files with 183 additions and 52 deletions
@@ -43,10 +43,10 @@ describe('computeHistoryJob (#370 — shared trailing idle pipeline)', () => {
describe('max-wait ceiling', () => {
const T0 = 1_000_000; // arbitrary fixed epoch for deterministic tests
it('early in the burst, the full trailing interval is used', () => {
// 1 minute into the burst: remaining budget (10m - 1m = 9m) still exceeds
// nothing that clamps it below the interval only if interval > remaining.
// For USER, interval 60m > remaining 9m, so delay clamps to the remaining.
it('once a burst is armed, delay clamps to the remaining max-wait budget', () => {
// 1 minute into the burst the USER interval (60m) far exceeds the remaining
// max-wait budget (10m - 1m = 9m), so the delay is clamped DOWN to that
// remaining budget — the full interval is NOT used once a ceiling applies.
const { delay } = computeHistoryJob(page, 'user', T0, T0 + 60_000);
expect(delay).toBe(IDLE_MAX_WAIT_USER - 60_000);
});
@@ -560,7 +560,7 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
// The pending idle autosnapshot is cancelled by the explicit version.
expect(historyQueue.remove).toHaveBeenCalledWith(PAGE_ID);
const msg = JSON.parse(
(document as any).broadcastStateless.mock.calls.at(-1)[0],
(document as any).broadcastStateless.mock.calls[(document as any).broadcastStateless.mock.calls.length - 1][0],
);
expect(msg).toMatchObject({
type: 'version.saved',
@@ -576,7 +576,7 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
await emitSave(document, 'agent');
expect(pageHistoryRepo.saveHistory.mock.calls.at(-1)[1]).toEqual(
expect(pageHistoryRepo.saveHistory.mock.calls[pageHistoryRepo.saveHistory.mock.calls.length - 1][1]).toEqual(
expect.objectContaining({ kind: 'agent' }),
);
});
@@ -601,7 +601,7 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
);
expect(pageHistoryRepo.saveHistory).not.toHaveBeenCalled();
const msg = JSON.parse(
(document as any).broadcastStateless.mock.calls.at(-1)[0],
(document as any).broadcastStateless.mock.calls[(document as any).broadcastStateless.mock.calls.length - 1][0],
);
expect(msg).toMatchObject({ historyId: 'auto-1', alreadySaved: false });
});
@@ -621,7 +621,7 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
expect(pageHistoryRepo.updateHistoryKind).not.toHaveBeenCalled();
expect(pageHistoryRepo.saveHistory).not.toHaveBeenCalled();
const msg = JSON.parse(
(document as any).broadcastStateless.mock.calls.at(-1)[0],
(document as any).broadcastStateless.mock.calls[(document as any).broadcastStateless.mock.calls.length - 1][0],
);
expect(msg).toMatchObject({ alreadySaved: true, kind: 'manual' });
});
@@ -693,12 +693,18 @@ export class PersistenceExtension implements Extension {
// The FIRST arm of a burst records `burstStart`; computeHistoryJob shrinks
// the delay to the remaining max-wait budget from that point, so a continuous
// session cannot re-arm the trailing timer forever and starve the snapshot.
// A burst marker older than the (larger, USER) max-wait means the previous
// idle job has already fired — start a fresh window instead of firing
// immediately on the next edit.
// A burst marker older than THIS TIER's max-wait means the previous idle job
// has already fired — start a fresh window instead of firing immediately on
// the next edit. Must use the SAME source-specific max-wait computeHistoryJob
// uses (agent 5m / user 10m): a hardcoded USER ceiling would leave an agent
// burst's marker stale for 5..10m, forcing delay=0 on every store in that
// window and writing one idle row per store — exactly the per-store bloat the
// debounce exists to prevent, on the continuous-agent path.
const maxWait =
lastUpdatedSource === 'agent' ? IDLE_MAX_WAIT_AGENT : IDLE_MAX_WAIT_USER;
const now = Date.now();
let burstStart = this.idleBurstStart.get(page.id);
if (burstStart === undefined || now - burstStart >= IDLE_MAX_WAIT_USER) {
if (burstStart === undefined || now - burstStart >= maxWait) {
burstStart = now;
this.idleBurstStart.set(page.id, burstStart);
}
@@ -66,6 +66,15 @@ describe('HistoryProcessor.process', () => {
notificationQueue = { add: jest.fn().mockResolvedValue(undefined) };
generalQueue = { add: jest.fn().mockResolvedValue(undefined) };
// #370 F3 — the processor now serializes its find+save under a page-row lock
// via executeTx. A db whose transaction().execute(fn) runs fn with a trx stub
// drives the real executeTx() helper without a database.
const db = {
transaction: () => ({
execute: (fn: (trx: any) => Promise<any>) => fn({ __trx: true }),
}),
};
// WorkerHost's constructor reads `this.worker`; passing repos positionally
// matches the constructor and avoids the Nest DI container.
proc = new HistoryProcessor(
@@ -73,6 +82,7 @@ describe('HistoryProcessor.process', () => {
pageRepo as any,
collabHistory as any,
watcherService as any,
db as any,
notificationQueue as any,
generalQueue as any,
);
@@ -134,7 +144,8 @@ describe('HistoryProcessor.process', () => {
);
expect(pageHistoryRepo.saveHistory).toHaveBeenCalledWith(
expect.objectContaining({ id: PAGE_ID }),
{ contributorIds: ['u1', 'u2'], kind: 'idle' },
// #370 F3 — saveHistory now runs inside the locked tx, so it carries trx.
expect.objectContaining({ contributorIds: ['u1', 'u2'], kind: 'idle' }),
);
expect(generalQueue.add).toHaveBeenCalledWith(
QueueJob.PAGE_BACKLINKS,
@@ -19,6 +19,9 @@ import { isDeepStrictEqual } from 'node:util';
import { CollabHistoryService } from '../services/collab-history.service';
import { WatcherService } from '../../core/watcher/watcher.service';
import { isEmptyParagraphDoc } from '../collaboration.util';
import { InjectKysely } from 'nestjs-kysely';
import { KyselyDB } from '@docmost/db/types/kysely.types';
import { executeTx } from '@docmost/db/utils';
@Processor(QueueName.HISTORY_QUEUE)
export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
@@ -29,6 +32,7 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
private readonly pageRepo: PageRepo,
private readonly collabHistory: CollabHistoryService,
private readonly watcherService: WatcherService,
@InjectKysely() private readonly db: KyselyDB,
@InjectQueue(QueueName.NOTIFICATION_QUEUE) private notificationQueue: Queue,
@InjectQueue(QueueName.GENERAL_QUEUE) private generalQueue: Queue,
) {
@@ -41,6 +45,9 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
try {
const { pageId } = job.data;
// Read the page WITHOUT a lock first, only to bail early on the two cheap
// no-write cases (page gone / empty first snapshot) without opening a
// transaction. The authoritative check-then-write happens locked below.
const page = await this.pageRepo.findById(pageId, {
includeContent: true,
});
@@ -51,44 +58,81 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
return;
}
const lastHistory = await this.pageHistoryRepo.findPageLastHistory(
pageId,
{ includeContent: true },
);
// #370 F3 — the snapshot decision (findPageLastHistory → saveHistory) must
// be serialized against manual-save/boundary writers, which run under a
// page-row lock in onStoreDocument. Without it, this processor and a
// concurrent manual-save each read the same lastHistory (MVCC), both see
// content != lastHistory, and both insert — producing two page_history rows
// with IDENTICAL content (one 'idle', one 'manual'), defeating
// promote-not-dup and the version-vs-autosave split. Taking the same
// page-row lock makes the second writer observe the first's committed row so
// the isDeepStrictEqual gate collapses the duplicate. Only the read+write
// is transacted; the post-snapshot queue work stays outside.
let contributorIds: string[] = [];
let snapshotWritten = false;
let lastHistoryContent: unknown;
if (!lastHistory && isEmptyParagraphDoc(page.content as any)) {
this.logger.debug(
`Skipping first history for page ${pageId}: empty content`,
await executeTx(this.db, async (trx) => {
const lockedPage = await this.pageRepo.findById(pageId, {
includeContent: true,
withLock: true,
trx,
});
if (!lockedPage) return;
const lastHistory = await this.pageHistoryRepo.findPageLastHistory(
pageId,
{ includeContent: true, trx },
);
await this.collabHistory.clearContributors(pageId);
return;
}
lastHistoryContent = lastHistory?.content;
if (
!lastHistory ||
!isDeepStrictEqual(lastHistory.content, page.content)
) {
const contributorIds = await this.collabHistory.popContributors(pageId);
if (!lastHistory && isEmptyParagraphDoc(lockedPage.content as any)) {
this.logger.debug(
`Skipping first history for page ${pageId}: empty content`,
);
return;
}
if (
lastHistory &&
isDeepStrictEqual(lastHistory.content, lockedPage.content)
) {
return; // already snapshotted at this content — nothing to write
}
contributorIds = await this.collabHistory.popContributors(pageId);
try {
await this.watcherService.addPageWatchers(
contributorIds,
pageId,
page.spaceId,
page.workspaceId,
lockedPage.spaceId,
lockedPage.workspaceId,
);
// #370 — every job on this queue is a trailing idle-flush autosnapshot.
await this.pageHistoryRepo.saveHistory(page, {
await this.pageHistoryRepo.saveHistory(lockedPage, {
contributorIds,
kind: job.data.kind ?? 'idle',
trx,
});
snapshotWritten = true;
this.logger.debug(`History created for page: ${pageId}`);
} catch (err) {
await this.collabHistory.addContributors(pageId, contributorIds);
throw err;
}
});
// No snapshot written (page vanished / empty-first / unchanged content) →
// clear the contributor set for the skip cases and stop.
if (!snapshotWritten) {
if (!lastHistoryContent && isEmptyParagraphDoc(page.content as any)) {
await this.collabHistory.clearContributors(pageId);
}
return;
}
{
const mentions = extractMentions(page.content);
const pageMentions = extractPageMentions(mentions);
const internalLinkSlugIds = extractInternalLinkSlugIds(page.content);
@@ -106,7 +150,7 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
);
});
if (contributorIds.length > 0 && lastHistory?.content) {
if (contributorIds.length > 0 && lastHistoryContent) {
await this.notificationQueue
.add(QueueJob.PAGE_UPDATED, {
pageId,