Backend-agnostic disaster-recovery backup engine that runs on the current storage backend (no storage cutover required): - Full-bundle export: db.dump (pg_dump custom) + every storage blob + manifest.json with per-object SHA-256, streamed as a tar. Entry points: admin UI download, GET /api/v1/admin/backup/export, scripts/create-full-backup.ts. - Admin-configurable push destinations (backup_destinations table, migration 0091): SFTP/SSH, S3-compatible (reuses the minio client), and mounted path/NAS behind one transport interface (test/push/prune). Secrets AES-GCM at rest; API returns only *IsSet markers. - Opt-in per-destination AES-256 bundle encryption (scrypt KDF, streamed) + scripts/decrypt-backup.ts for restore. - Wired the previously-dead database-backup cron to runScheduledBackupPush (push to enabled destinations, prune to retention, alert super-admins on failure). Tests: 1608 unit/integration pass; tsc + lint clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
206 lines
8.5 KiB
TypeScript
206 lines
8.5 KiB
TypeScript
import { Worker, type Job } from 'bullmq';
|
|
import { env } from '@/lib/env';
|
|
import { and, eq, lt, isNotNull } from 'drizzle-orm';
|
|
|
|
import type { ConnectionOptions } from 'bullmq';
|
|
import { db } from '@/lib/db';
|
|
import { formSubmissions } from '@/lib/db/schema/documents';
|
|
import { gdprExports } from '@/lib/db/schema/gdpr';
|
|
import { aiUsageLedger } from '@/lib/db/schema/ai-usage';
|
|
import { auditLogs, errorEvents } from '@/lib/db/schema/system';
|
|
import { websiteSubmissions } from '@/lib/db/schema/website-submissions';
|
|
import { logger } from '@/lib/logger';
|
|
import { attachWorkerAudit } from '@/lib/queue/audit-helpers';
|
|
import { getStorageBackend } from '@/lib/storage';
|
|
import { QUEUE_CONFIGS } from '@/lib/queue';
|
|
|
|
/** AI usage rows older than this are deleted by the retention job. */
|
|
const AI_USAGE_RETENTION_DAYS = 90;
|
|
/** error_events rows older than this are pruned. Migration 0040 declares
|
|
* this contract; the worker had no implementation until now. */
|
|
const ERROR_EVENTS_RETENTION_DAYS = 90;
|
|
/** audit_logs rows older than this are pruned. Mirrors error_events.
|
|
* Metadata is masked at insert time but older rows have no operational
|
|
* value past the window and represent residual stale-PII exposure. */
|
|
const AUDIT_LOGS_RETENTION_DAYS = 90;
|
|
/** Raw website inquiry payloads (website_submissions) - kept long enough
|
|
* to investigate "why didn't this lead reach the CRM" inbound questions
|
|
* but not indefinitely. 180d aligns with the typical sales cycle. */
|
|
const WEBSITE_SUBMISSIONS_RETENTION_DAYS = 180;
|
|
|
|
export const maintenanceWorker = new Worker(
|
|
'maintenance',
|
|
async (job: Job) => {
|
|
logger.info({ jobId: job.id, jobName: job.name }, 'Processing maintenance job');
|
|
switch (job.name) {
|
|
case 'currency-refresh': {
|
|
const { refreshRates } = await import('@/lib/services/currency');
|
|
await refreshRates();
|
|
break;
|
|
}
|
|
case 'database-backup': {
|
|
// Scheduled full-bundle backup pushed to every enabled destination.
|
|
// No-op until an admin turns the schedule on AND enables a destination
|
|
// (`backup_schedule` setting + `backup_destinations`). Replaces the
|
|
// previous silent no-op (this case did not exist before).
|
|
const { runScheduledBackupPush } =
|
|
await import('@/lib/services/backup-destinations.service');
|
|
const summary = await runScheduledBackupPush();
|
|
logger.info(summary, 'Scheduled backup push complete');
|
|
break;
|
|
}
|
|
case 'form-expiry-check': {
|
|
const result = await db
|
|
.update(formSubmissions)
|
|
.set({ status: 'expired' })
|
|
.where(
|
|
and(eq(formSubmissions.status, 'pending'), lt(formSubmissions.expiresAt, new Date())),
|
|
)
|
|
.returning({ id: formSubmissions.id });
|
|
logger.info({ expired: result.length }, 'Form expiry check complete');
|
|
break;
|
|
}
|
|
case 'alerts-evaluate': {
|
|
const { runAlertEngine } = await import('@/lib/services/alert-engine');
|
|
const summary = await runAlertEngine();
|
|
logger.info(summary, 'Alert engine sweep complete');
|
|
break;
|
|
}
|
|
case 'bounce-poll': {
|
|
const { processImapBouncePoll } = await import('@/jobs/processors/imap-bounce-poller');
|
|
await processImapBouncePoll();
|
|
break;
|
|
}
|
|
case 'analytics-refresh': {
|
|
const { ports } = await import('@/lib/db/schema/ports');
|
|
const { refreshSnapshotsForPort } = await import('@/lib/services/analytics.service');
|
|
const allPorts = await db.select({ id: ports.id }).from(ports);
|
|
for (const p of allPorts) {
|
|
try {
|
|
await refreshSnapshotsForPort(p.id);
|
|
} catch (err) {
|
|
logger.warn({ portId: p.id, err }, 'Analytics refresh failed for port');
|
|
}
|
|
}
|
|
logger.info({ count: allPorts.length }, 'Analytics snapshot refresh complete');
|
|
break;
|
|
}
|
|
case 'expense-dedup-scan': {
|
|
const { expenseId } = job.data as { expenseId: string };
|
|
if (!expenseId) {
|
|
logger.warn({ jobId: job.id }, 'expense-dedup-scan missing expenseId');
|
|
break;
|
|
}
|
|
const { markBestDuplicate } = await import('@/lib/services/expense-dedup.service');
|
|
const matchedId = await markBestDuplicate(expenseId);
|
|
logger.info({ expenseId, matchedId: matchedId ?? null }, 'expense-dedup-scan complete');
|
|
break;
|
|
}
|
|
case 'gdpr-export-cleanup': {
|
|
// GDPR Article 17 (right to erasure): when an export expires we must
|
|
// actually delete the bytes, not just mark a flag. Pulls every row
|
|
// past expiresAt with a storage_key, removes the MinIO object, then
|
|
// deletes the row.
|
|
const expired = await db
|
|
.select({ id: gdprExports.id, storageKey: gdprExports.storageKey })
|
|
.from(gdprExports)
|
|
.where(
|
|
and(
|
|
isNotNull(gdprExports.expiresAt),
|
|
lt(gdprExports.expiresAt, new Date()),
|
|
isNotNull(gdprExports.storageKey),
|
|
),
|
|
);
|
|
|
|
let removed = 0;
|
|
let failed = 0;
|
|
for (const row of expired) {
|
|
try {
|
|
if (row.storageKey) {
|
|
await (await getStorageBackend()).delete(row.storageKey);
|
|
}
|
|
await db.delete(gdprExports).where(eq(gdprExports.id, row.id));
|
|
removed++;
|
|
} catch (err) {
|
|
failed++;
|
|
logger.warn({ err, exportId: row.id }, 'Failed to clean up GDPR export');
|
|
}
|
|
}
|
|
logger.info({ removed, failed, total: expired.length }, 'GDPR export cleanup complete');
|
|
break;
|
|
}
|
|
case 'ai-usage-retention': {
|
|
// Trim ai_usage_ledger to the retention window. Older rows aren't
|
|
// useful for budget rollups (which always operate on the current
|
|
// period) and bloat both the table and admin breakdown queries.
|
|
const cutoff = new Date(Date.now() - AI_USAGE_RETENTION_DAYS * 24 * 60 * 60 * 1000);
|
|
const result = await db
|
|
.delete(aiUsageLedger)
|
|
.where(lt(aiUsageLedger.createdAt, cutoff))
|
|
.returning({ id: aiUsageLedger.id });
|
|
logger.info(
|
|
{ deleted: result.length, retentionDays: AI_USAGE_RETENTION_DAYS },
|
|
'AI usage retention sweep complete',
|
|
);
|
|
break;
|
|
}
|
|
case 'error-events-retention': {
|
|
// Honor the contract from migration 0040: error_events older than
|
|
// ERROR_EVENTS_RETENTION_DAYS get dropped. Otherwise the table
|
|
// grows unbounded and the admin error log becomes unusable.
|
|
const cutoff = new Date(Date.now() - ERROR_EVENTS_RETENTION_DAYS * 24 * 60 * 60 * 1000);
|
|
const result = await db
|
|
.delete(errorEvents)
|
|
.where(lt(errorEvents.createdAt, cutoff))
|
|
.returning({ requestId: errorEvents.requestId });
|
|
logger.info(
|
|
{ deleted: result.length, retentionDays: ERROR_EVENTS_RETENTION_DAYS },
|
|
'Error events retention sweep complete',
|
|
);
|
|
break;
|
|
}
|
|
case 'audit-logs-retention': {
|
|
const cutoff = new Date(Date.now() - AUDIT_LOGS_RETENTION_DAYS * 24 * 60 * 60 * 1000);
|
|
const result = await db
|
|
.delete(auditLogs)
|
|
.where(lt(auditLogs.createdAt, cutoff))
|
|
.returning({ id: auditLogs.id });
|
|
logger.info(
|
|
{ deleted: result.length, retentionDays: AUDIT_LOGS_RETENTION_DAYS },
|
|
'Audit logs retention sweep complete',
|
|
);
|
|
break;
|
|
}
|
|
case 'website-submissions-retention': {
|
|
// Raw inquiry payloads from the marketing-site dual-write. Keep
|
|
// long enough to debug capture issues but not forever - these
|
|
// rows include reCAPTCHA + IP + UA metadata.
|
|
const cutoff = new Date(
|
|
Date.now() - WEBSITE_SUBMISSIONS_RETENTION_DAYS * 24 * 60 * 60 * 1000,
|
|
);
|
|
const result = await db
|
|
.delete(websiteSubmissions)
|
|
.where(lt(websiteSubmissions.receivedAt, cutoff))
|
|
.returning({ id: websiteSubmissions.id });
|
|
logger.info(
|
|
{ deleted: result.length, retentionDays: WEBSITE_SUBMISSIONS_RETENTION_DAYS },
|
|
'Website submissions retention sweep complete',
|
|
);
|
|
break;
|
|
}
|
|
default:
|
|
logger.warn({ jobName: job.name }, 'Unknown maintenance job');
|
|
}
|
|
},
|
|
{
|
|
connection: { url: env.REDIS_URL } as ConnectionOptions,
|
|
concurrency: QUEUE_CONFIGS.maintenance.concurrency,
|
|
},
|
|
);
|
|
|
|
maintenanceWorker.on('failed', (job, err) => {
|
|
logger.error({ jobId: job?.id, jobName: job?.name, err }, 'Maintenance job failed');
|
|
});
|
|
|
|
attachWorkerAudit(maintenanceWorker, 'maintenance');
|