perf(comment): унести Yjs-обновление comment-mark с HTTP-критического пути (#399)

resolve/unresolve/delete comment-mark синхронно дёргали collab-gateway
(handleYjsEvent) прямо в HTTP-запросе — сетевой раунд-трип к collab на
горячем пути. Теперь:
- DB-строка пишется синхронно (источник истины) с общим таймстампом;
- сама mark-операция уходит идемпотентным COMMENT_MARK_UPDATE-джобом на
  GENERAL_QUEUE, воркер проигрывает тот же handleYjsEvent;
- resolve/unresolve — fire-and-forget (best-effort), delete — await энкью
  ДО необратимого hard-delete (durability split);
- race-guard: устаревшее ПРОТИВОПОЛОЖНОЕ событие (ts <= updatedAt строки и
  состояние расходится) пропускается, а не флипает mark в устаревшее;
- DI-цикл обойдён ленивым moduleRef.get(CollaborationGateway, strict:false).

Внутренний цикл: 2 прохода. Правки по внутреннему ревью: `<` → `<=` в
race-guard (безопасная обработка суб-миллисекундной ничьи двух
противоположных тогглов); задокументирован сознательный компромисс —
транзиентный page.updated-broadcast из воркера несёт только {id}, теряя
name/avatarUrl «кто редактировал» (lastUpdatedById выставляется верно,
косметика, самочинится на следующем реальном редактировании).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

apps/server/src/integrations/queue/constants/queue.constants.ts

@@ -61,6 +61,9 @@ export enum QueueJob {
 
   COMMENT_NOTIFICATION = 'comment-notification',
   COMMENT_RESOLVED_NOTIFICATION = 'comment-resolved-notification',
+  // #399: off-critical-path mirror of a comment's inline mark into the collab
+  // Y.Doc (resolve/unresolve flip, or ephemeral-suggestion anchor removal).
+  COMMENT_MARK_UPDATE = 'comment-mark-update',
   PAGE_MENTION_NOTIFICATION = 'page-mention-notification',
   PAGE_PERMISSION_GRANTED = 'page-permission-granted',
   PAGE_UPDATE_DIGEST = 'page-update-digest',

apps/server/src/integrations/queue/constants/queue.interface.ts

@@ -63,6 +63,33 @@ export interface ICommentNotificationJob {
   notifyWatchers: boolean;
 }
 
+/**
+ * GENERAL_QUEUE payload for the off-critical-path comment inline-mark mirror
+ * (#399). The comment DB row is the source of truth and is already updated
+ * synchronously (ms); this job flips/removes the inline `comment` mark in the
+ * collaborative Y.Doc for connected clients, OFF the HTTP response path, so
+ * `POST /api/comments/resolve` no longer waits the whole Y.Doc load + store
+ * pipeline (was ~4.5s p95). The mark op is idempotent, so BullMQ retries are
+ * safe.
+ *
+ * `action`:
+ *   - 'resolve' / 'unresolve' → flip the mark's `resolved` attribute (exactly
+ *     what the synchronous resolveCommentMark path did);
+ *   - 'delete' → strip the anchor mark entirely (ephemeral suggestion #329).
+ * `ts` is the DB-mutation timestamp (ms). The worker's race-guard uses it (with
+ * the row's authoritative resolved state) to skip a resolve/unresolve event
+ * that a newer, opposite event has already superseded (out-of-order drain).
+ * `userId` supplies the connection-context user the store pipeline attributes
+ * the change to (persistence.extension reads context.user.id).
+ */
+export interface ICommentMarkUpdateJob {
+  documentName: string;
+  commentId: string;
+  action: 'resolve' | 'unresolve' | 'delete';
+  ts: number;
+  userId: string;
+}
+
 export interface ICommentResolvedNotificationJob {
   commentId: string;
   commentCreatorId: string;

apps/server/src/integrations/queue/processors/general-queue.processor.comment-mark.spec.ts

@@ -0,0 +1,151 @@
+import { Job } from 'bullmq';
+import { GeneralQueueProcessor } from './general-queue.processor';
+import { QueueJob } from '../constants';
+import { ICommentMarkUpdateJob } from '../constants/queue.interface';
+
+/**
+ * #399: the GENERAL_QUEUE worker replays the comment inline-mark op that used to
+ * run synchronously on the HTTP path. It must call the SAME gateway handler with
+ * the SAME semantics (resolve/unresolve → flip the `resolved` attribute; delete
+ * → strip the anchor), and its timestamp race-guard must skip an event a newer,
+ * opposite event already superseded.
+ */
+describe('GeneralQueueProcessor — COMMENT_MARK_UPDATE (#399)', () => {
+  function makeProc() {
+    const collaborationGateway: any = {
+      handleYjsEvent: jest.fn(async () => undefined),
+    };
+    const commentRepo: any = { findById: jest.fn() };
+    // #399: the processor resolves CollaborationGateway lazily via ModuleRef
+    // (strict:false) to avoid a DI cycle; the fake returns our gateway spy.
+    const moduleRef: any = { get: jest.fn(() => collaborationGateway) };
+    const proc = new GeneralQueueProcessor(
+      {} as any, // db
+      {} as any, // backlinkRepo
+      {} as any, // watcherRepo
+      commentRepo,
+      moduleRef,
+    );
+    return { proc, collaborationGateway, commentRepo };
+  }
+
+  const job = (data: ICommentMarkUpdateJob): Job =>
+    ({ name: QueueJob.COMMENT_MARK_UPDATE, data }) as unknown as Job;
+
+  const base = {
+    documentName: 'page.page-1',
+    commentId: 'c-1',
+    userId: 'user-1',
+  };
+
+  it('resolve → resolveCommentMark with resolved:true and the same-shape args', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+    const ts = 1000;
+    // Row reflects the resolve (source of truth), stamped at the same ts.
+    commentRepo.findById.mockResolvedValue({
+      id: 'c-1',
+      resolvedAt: new Date(ts),
+      updatedAt: new Date(ts),
+    });
+
+    await proc.process(job({ ...base, action: 'resolve', ts }));
+
+    expect(collaborationGateway.handleYjsEvent).toHaveBeenCalledTimes(1);
+    expect(collaborationGateway.handleYjsEvent).toHaveBeenCalledWith(
+      'resolveCommentMark',
+      'page.page-1',
+      { commentId: 'c-1', resolved: true, user: { id: 'user-1' } },
+    );
+  });
+
+  it('unresolve → resolveCommentMark with resolved:false', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+    const ts = 2000;
+    commentRepo.findById.mockResolvedValue({
+      id: 'c-1',
+      resolvedAt: null,
+      updatedAt: new Date(ts),
+    });
+
+    await proc.process(job({ ...base, action: 'unresolve', ts }));
+
+    expect(collaborationGateway.handleYjsEvent).toHaveBeenCalledWith(
+      'resolveCommentMark',
+      'page.page-1',
+      { commentId: 'c-1', resolved: false, user: { id: 'user-1' } },
+    );
+  });
+
+  it('delete → deleteCommentMark (strip the anchor), no row lookup / no state guard', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+
+    await proc.process(job({ ...base, action: 'delete', ts: 123 }));
+
+    expect(collaborationGateway.handleYjsEvent).toHaveBeenCalledWith(
+      'deleteCommentMark',
+      'page.page-1',
+      { commentId: 'c-1', user: { id: 'user-1' } },
+    );
+    // Delete carries no state guard — the row is (being) removed.
+    expect(commentRepo.findById).not.toHaveBeenCalled();
+  });
+
+  it('SKIPS a stale resolve superseded by a newer unresolve (row unresolved, job ts older)', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+    // A later unresolve already set the row: resolvedAt null, updatedAt = 5000.
+    commentRepo.findById.mockResolvedValue({
+      id: 'c-1',
+      resolvedAt: null,
+      updatedAt: new Date(5000),
+    });
+
+    // Stale resolve job enqueued at ts=1000 (< 5000), intends resolved=true,
+    // but the row's authoritative state is unresolved → skip.
+    await proc.process(job({ ...base, action: 'resolve', ts: 1000 }));
+
+    expect(collaborationGateway.handleYjsEvent).not.toHaveBeenCalled();
+  });
+
+  it('SKIPS a stale unresolve superseded by a newer resolve', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+    commentRepo.findById.mockResolvedValue({
+      id: 'c-1',
+      resolvedAt: new Date(5000),
+      updatedAt: new Date(5000),
+    });
+
+    await proc.process(job({ ...base, action: 'unresolve', ts: 1000 }));
+
+    expect(collaborationGateway.handleYjsEvent).not.toHaveBeenCalled();
+  });
+
+  it('applies when the row state agrees even if ts is older (idempotent, not a stale flip)', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+    // Row is resolved and its updatedAt is newer than the job ts, but the state
+    // AGREES with the job → this is a harmless idempotent replay, not a stale
+    // opposite event, so it must still apply.
+    commentRepo.findById.mockResolvedValue({
+      id: 'c-1',
+      resolvedAt: new Date(9000),
+      updatedAt: new Date(9000),
+    });
+
+    await proc.process(job({ ...base, action: 'resolve', ts: 1000 }));
+
+    expect(collaborationGateway.handleYjsEvent).toHaveBeenCalledWith(
+      'resolveCommentMark',
+      'page.page-1',
+      { commentId: 'c-1', resolved: true, user: { id: 'user-1' } },
+    );
+  });
+
+  it('skips (no throw) when the comment row has vanished', async () => {
+    const { proc, collaborationGateway, commentRepo } = makeProc();
+    commentRepo.findById.mockResolvedValue(undefined);
+
+    await expect(
+      proc.process(job({ ...base, action: 'resolve', ts: 1000 })),
+    ).resolves.toBeUndefined();
+    expect(collaborationGateway.handleYjsEvent).not.toHaveBeenCalled();
+  });
+});

apps/server/src/integrations/queue/processors/general-queue.processor.ts

@@ -4,6 +4,7 @@ import { Job } from 'bullmq';
 import { QueueJob, QueueName } from '../constants';
 import {
   IAddPageWatchersJob,
+  ICommentMarkUpdateJob,
   IPageBacklinkJob,
 } from '../constants/queue.interface';
 import { InjectKysely } from 'nestjs-kysely';
@@ -13,8 +14,11 @@ import {
   WatcherRepo,
   WatcherType,
 } from '@docmost/db/repos/watcher/watcher.repo';
-import { InsertableWatcher } from '@docmost/db/types/entity.types';
+import { InsertableWatcher, User } from '@docmost/db/types/entity.types';
 import { processBacklinks } from '../tasks/backlinks.task';
+import { ModuleRef } from '@nestjs/core';
+import { CollaborationGateway } from '../../../collaboration/collaboration.gateway';
+import { CommentRepo } from '@docmost/db/repos/comment/comment.repo';
 
 @Processor(QueueName.GENERAL_QUEUE)
 export class GeneralQueueProcessor
@@ -22,14 +26,32 @@ export class GeneralQueueProcessor
   implements OnModuleDestroy
 {
   private readonly logger = new Logger(GeneralQueueProcessor.name);
+  // #399: CollaborationGateway lives in CollaborationModule. We resolve it lazily
+  // via ModuleRef instead of importing that module into the @Global QueueModule —
+  // CollaborationModule's own HistoryProcessor injects this module's global
+  // GENERAL_QUEUE token, so a static import edge here would form a DI cycle. A
+  // lazy strict:false lookup (cached) sidesteps it; the gateway is a singleton in
+  // both the API-server and collab processes that run this worker.
+  private collaborationGateway?: CollaborationGateway;
   constructor(
     @InjectKysely() private readonly db: KyselyDB,
     private readonly backlinkRepo: BacklinkRepo,
     private readonly watcherRepo: WatcherRepo,
+    private readonly commentRepo: CommentRepo,
+    private readonly moduleRef: ModuleRef,
   ) {
     super();
   }
 
+  private getCollaborationGateway(): CollaborationGateway {
+    if (!this.collaborationGateway) {
+      this.collaborationGateway = this.moduleRef.get(CollaborationGateway, {
+        strict: false,
+      });
+    }
+    return this.collaborationGateway;
+  }
+
   async process(job: Job): Promise<void> {
     try {
       switch (job.name) {
@@ -56,12 +78,87 @@ export class GeneralQueueProcessor
           );
           break;
         }
+
+        case QueueJob.COMMENT_MARK_UPDATE: {
+          await this.processCommentMarkUpdate(
+            job.data as ICommentMarkUpdateJob,
+          );
+          break;
+        }
       }
     } catch (err) {
       throw err;
     }
   }
 
+  /**
+   * #399: apply a comment's inline-mark mirror in the collab Y.Doc, off the HTTP
+   * critical path. Runs the SAME gateway path the synchronous comment.service
+   * code used (byte-identical mark op):
+   *   - resolve / unresolve → resolveCommentMark (flip the `resolved` attribute);
+   *   - delete → deleteCommentMark (strip the ephemeral-suggestion anchor #329).
+   * The op is idempotent, so a BullMQ retry is safe. Throwing propagates to
+   * WorkerHost → the job is retried and, on exhaustion, surfaces in failed-job
+   * metrics (the divergence is now visible rather than a silently-swallowed warn).
+   */
+  private async processCommentMarkUpdate(
+    data: ICommentMarkUpdateJob,
+  ): Promise<void> {
+    const { documentName, commentId, action, ts, userId } = data;
+    // Minimal connection-context user: the store pipeline reads context.user.id
+    // to attribute the change (persistence.extension). The mark mutation itself
+    // does not depend on the user, so the op stays byte-identical. Deliberate
+    // trade-off: the store pipeline's transient `page.updated` broadcast carries
+    // only { id } here, so its live "who edited" badge loses name/avatarUrl for
+    // this async mark replay. lastUpdatedById is still set correctly; the diff is
+    // cosmetic and self-heals on the next real edit — worth it to stay off the
+    // HTTP path and avoid re-loading the users row.
+    const user = { id: userId } as User;
+
+    if (action === 'delete') {
+      await this.getCollaborationGateway().handleYjsEvent(
+        'deleteCommentMark',
+        documentName,
+        { commentId, user },
+      );
+      return;
+    }
+
+    // resolve / unresolve. The comment row is written SYNCHRONOUSLY before this
+    // job is enqueued, so it is the source of truth for the final resolved state
+    // and its updatedAt records when that state last changed. Race-guard: if a
+    // newer, OPPOSITE event has already superseded this one (its ts is older than
+    // the row's last resolve-state mutation AND the row's current resolved state
+    // disagrees with what this job intends — e.g. an unresolve that drained ahead
+    // of this resolve), skip it rather than flip the mark to a stale state.
+    const comment = await this.commentRepo.findById(commentId);
+    if (!comment) {
+      // The comment vanished (e.g. hard-deleted) → nothing left to mirror.
+      return;
+    }
+    const wantResolved = action === 'resolve';
+    const rowResolved = comment.resolvedAt != null;
+    const rowMutatedAt = new Date(comment.updatedAt).getTime();
+    // `<=`, not `<`: on a sub-millisecond tie (two opposite toggles stamped in
+    // the same ms) skip the disagreeing job rather than let queue order decide.
+    // The consistent job (whose intent matches the row) short-circuits on the
+    // first condition, so a real update is never dropped; only a mark that both
+    // disagrees with the row AND is no newer than it is discarded.
+    if (rowResolved !== wantResolved && ts <= rowMutatedAt) {
+      this.logger.debug(
+        `Skipping stale comment mark '${action}' for ${commentId} ` +
+          `(job ts ${ts} < row ${rowMutatedAt}, row resolved=${rowResolved})`,
+      );
+      return;
+    }
+
+    await this.getCollaborationGateway().handleYjsEvent(
+      'resolveCommentMark',
+      documentName,
+      { commentId, resolved: wantResolved, user },
+    );
+  }
+
   @OnWorkerEvent('active')
   onActive(job: Job) {
     this.logger.debug(`Processing ${job.name} job`);