agent_coder
28251b1e08
One migration + targeted hot-path fixes. API behavior 1:1 (schema change = added
indexes + a byte-identical f_unaccent function-body swap, see below).
- Trigram + composite indexes (20260705T120000-perf-indexes.ts): GIN trigram on
LOWER(f_unaccent(title/name)) for pages/users/groups (the /search/suggest
leading-wildcard LIKE did a seq scan per keystroke — EXPLAIN now confirms
Bitmap Index Scan on idx_pages_title_trgm), + page_history(page_id,id DESC),
comments(page_id,id). DEVIATION (verified byte-identical): PG18 cannot inline
the two-arg f_unaccent body during index creation, so up() swaps it to the
schema-qualified single-arg `SELECT public.unaccent($1)` — same dictionary,
identical output for all inputs, so the tsvector trigger + main @@ search stay
consistent with NO reindex; down() restores the exact two-arg body.
- Auth path: jwt.strategy reuses req.raw.workspace when workspaceId matches (the
middleware already validated it) instead of re-querying; domain.middleware
caches the workspace lookup (withCache 15s, invalidated in all 8 WorkspaceRepo
mutators, with a Date reviver for the JSON-serialized cache). USER + SESSION
caching DEFERRED — the invalidation surface (role change doesn't revoke
sessions; revocation includes background jobs) can't be safely covered, and a
missed hook on a security path is worse than the win.
- AI re-embed coalescing: aiQueue.add gets {jobId: embed-<id>, delay: 30s} so
active editing collapses to one job (worker reads current page state).
- filterAccessiblePageIds: hasRestrictedPagesInWorkspace short-circuit skips the
recursive-ancestor CTE when a workspace has zero restricted pages (wired from
search/favorites/notifications/recent/created-by). EXISTS on the same pageAccess
table the CTE anti-joins → no false-positive / no access leak. Busts the cache
on insertPageAccess so a 0->1 restricted transition takes effect immediately
(review F1).
- Small: syncTransclusion guarded by a family-node probe (both old+new content, so
the removal path is preserved); mention notifications enqueue only when the set
gained a member; redis maintainLock clears a prior interval (leak fix).
Skipped as risky (flagged): global ValidationPipe transform change; a pool-wide
statement_timeout (would kill long CREATE INDEX migrations on the same pool).
NOTE: kept the trash query's `content` select — the trash UI reads page.content
for its preview modal (review F3, would have regressed).
Gate: server tsc 0; jest page-permission/auth/search/persistence 15 suites pass;
migration up+down+idempotency verified on real PG18 with EXPLAIN confirming index
use. No new deps.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
91 lines
3.2 KiB
TypeScript
91 lines
3.2 KiB
TypeScript
import { Inject, Injectable, NestMiddleware } from '@nestjs/common';
|
|
import { FastifyRequest, FastifyReply } from 'fastify';
|
|
import { CACHE_MANAGER } from '@nestjs/cache-manager';
|
|
import { Cache } from 'cache-manager';
|
|
import { EnvironmentService } from '../../integrations/environment/environment.service';
|
|
import { WorkspaceRepo } from '@docmost/db/repos/workspace/workspace.repo';
|
|
import { Workspace } from '@docmost/db/types/entity.types';
|
|
import { withCache } from '../helpers/with-cache';
|
|
import { CacheKey, WORKSPACE_CACHE_TTL_MS } from '../helpers/cache-keys';
|
|
|
|
// #348 — timestamptz columns on the workspace row. The cache store (Keyv/Redis)
|
|
// JSON-serializes values, so a cached workspace comes back with these fields as
|
|
// ISO strings. Reviving them to Date keeps the cached path byte-identical to the
|
|
// direct DB path (postgres.js returns Date), so nothing downstream can observe a
|
|
// cache hit vs miss. Idempotent: `new Date(date)` on an already-Date value is a
|
|
// no-op-equivalent. Keep in sync with the workspace timestamptz columns.
|
|
const WORKSPACE_DATE_FIELDS: Array<keyof Workspace> = [
|
|
'createdAt',
|
|
'updatedAt',
|
|
'deletedAt',
|
|
'trialEndAt',
|
|
];
|
|
|
|
function reviveWorkspaceDates(workspace: Workspace): Workspace {
|
|
for (const field of WORKSPACE_DATE_FIELDS) {
|
|
const value = workspace[field];
|
|
if (value != null) {
|
|
(workspace as any)[field] = new Date(value as any);
|
|
}
|
|
}
|
|
return workspace;
|
|
}
|
|
|
|
@Injectable()
|
|
export class DomainMiddleware implements NestMiddleware {
|
|
constructor(
|
|
private workspaceRepo: WorkspaceRepo,
|
|
private environmentService: EnvironmentService,
|
|
@Inject(CACHE_MANAGER) private readonly cacheManager: Cache,
|
|
) {}
|
|
async use(
|
|
req: FastifyRequest['raw'],
|
|
res: FastifyReply['raw'],
|
|
next: () => void,
|
|
) {
|
|
if (this.environmentService.isSelfHosted()) {
|
|
// #348 — cache the single-workspace lookup that runs on every request.
|
|
// Invalidated by every WorkspaceRepo mutator (see bustWorkspaceCache).
|
|
const workspace = await withCache(
|
|
this.cacheManager,
|
|
CacheKey.WORKSPACE_SELF_HOSTED,
|
|
WORKSPACE_CACHE_TTL_MS,
|
|
() => this.workspaceRepo.findFirst(),
|
|
);
|
|
if (!workspace) {
|
|
//throw new NotFoundException('Workspace not found');
|
|
(req as any).workspaceId = null;
|
|
return next();
|
|
}
|
|
|
|
reviveWorkspaceDates(workspace);
|
|
// TODO: unify
|
|
(req as any).workspaceId = workspace.id;
|
|
(req as any).workspace = workspace;
|
|
} else if (this.environmentService.isCloud()) {
|
|
const header = req.headers.host;
|
|
const subdomain = header.split('.')[0];
|
|
|
|
// #348 — cache per-subdomain workspace resolution. Keyed by subdomain (the
|
|
// hostname column); busted per hostname by every WorkspaceRepo mutator.
|
|
const workspace = await withCache(
|
|
this.cacheManager,
|
|
CacheKey.WORKSPACE_BY_HOST(subdomain),
|
|
WORKSPACE_CACHE_TTL_MS,
|
|
() => this.workspaceRepo.findByHostname(subdomain),
|
|
);
|
|
|
|
if (!workspace) {
|
|
(req as any).workspaceId = null;
|
|
return next();
|
|
}
|
|
|
|
reviveWorkspaceDates(workspace);
|
|
(req as any).workspaceId = workspace.id;
|
|
(req as any).workspace = workspace;
|
|
}
|
|
|
|
next();
|
|
}
|
|
}
|