Files
pn-new-crm/src/lib/queue/workers/maintenance.ts

171 lines
7.0 KiB
TypeScript
Raw Normal View History

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 { errorEvents } from '@/lib/db/schema/system';
import { websiteSubmissions } from '@/lib/db/schema/website-submissions';
import { logger } from '@/lib/logger';
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;
/** 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 '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;
}
feat(alerts): rule engine, recurring evaluator, socket fanout PR2 of Phase B. Wires the alert framework end-to-end: - alert-rules.ts: 10 rule evaluators implemented as pure async fns over the existing schema. reservation.no_agreement, interest.stale, document.signer_overdue, berth.under_offer_stalled, expense.duplicate, expense.unscanned, interest.high_value_silent, eoi.unsigned_long, audit.suspicious_login fire against real conditions. document.expiring_soon stays inert until the documents schema gets an expires_at column. audit.suspicious_login also stays inert until the auth layer logs 'login.failed' rows (TODO noted in the rule body). - alert-engine.ts: runAlertEngine() walks every port × every rule and calls reconcileAlertsForPort. Errors per (port, rule) are collected in the summary, not thrown — one bad evaluator can't stop the sweep. - alerts.service.ts: reconcileAlertsForPort now emits 'alert:created' socket events on insert and 'alert:resolved' on auto-resolve; dismissAlert emits 'alert:dismissed'. All scoped to port:{portId} rooms. - socket/events.ts: adds the three Server→Client alert event types. - queue/scheduler.ts: registers 'alerts-evaluate' on the maintenance queue with cron */5 * * * * (every 5 min, per spec risk register). - queue/workers/maintenance.ts: dispatches 'alerts-evaluate' to runAlertEngine; logs sweep summary. Tests: - tests/integration/alerts-engine.test.ts (6 cases): seeds reservation → fires, runs twice → no dupe, adds agreement → auto-resolves; seeds stale interest → fires; hot lead silent → critical; engine summary shape on no-data port. Socket emit module is vi.mocked. Vitest 681/681 (was 675; +6). tsc clean. Lint clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-28 14:50:55 +02:00
case 'alerts-evaluate': {
const { runAlertEngine } = await import('@/lib/services/alert-engine');
const summary = await runAlertEngine();
logger.info(summary, 'Alert engine sweep complete');
break;
}
feat(analytics): real computations + 15-min snapshot refresh job PR3 of Phase B. Replaces the no-op stubs in analytics.service.ts with working drizzle queries and adds the recurring BullMQ job that warms the cache. Computations: - computePipelineFunnel: groups interests by pipeline_stage filtered by port + range + not archived; emits 8-row stages array with conversion pct relative to 'open' as the funnel top. - computeOccupancyTimeline: per day in range, counts berths covered by an active reservation (start_date ≤ day, end_date IS NULL OR ≥ day); emits {date, occupied, total, occupancyPct}. - computeRevenueBreakdown: sums invoices.total grouped by status + currency; filters out archived rows. - computeLeadSourceAttribution: counts interests by source descending; null source bucketed as 'unspecified'. Public API (getPipelineFunnel, getOccupancyTimeline, etc.) reads analytics_snapshots first; falls back to compute + writeSnapshot. TTL 15 minutes (matches the cron interval). Cron: - queue/scheduler.ts registers 'analytics-refresh' on maintenance with pattern '*/15 * * * *'. - queue/workers/maintenance.ts dispatches to refreshSnapshotsForPort for every port; per-port try/catch so one bad port doesn't kill the sweep. Tests: tests/integration/analytics-service.test.ts (9 cases). Pipeline funnel math (incl. zero state), occupancy timeline shape/percentages with seeded reservations, revenue grouped by status + currency, lead source attribution incl. null bucketing, cache hit (mutate snapshot directly → next read returns mutated value), refreshSnapshotsForPort warms every metric×range combo. Vitest 690/690 (+9). tsc + lint clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-28 14:54:46 +02:00
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;
}
feat(phase-b): ship analytics dashboard, alerts, scanner PWA, dedup, audit view Phase B (Insights & Alerts) PR4-11 in one drop. Builds on the schema + service skeletons committed in PRs 1-3. PR4 Analytics dashboard — 4 chart types (funnel/timeline/breakdown/source), date-range picker (today/7d/30d/90d), CSV+PNG export per card. PR5 Alert rail UI + /alerts page — topbar bell w/ live count, dashboard right-rail, three-tab page (active/dismissed/resolved), socket-driven invalidation. Bell lazy-loads list on popover open to keep cold pages fast in non-dashboard routes. PR6 EOI queue tab on documents hub — filters to in-flight EOIs, count surfaces in tab label. PR7 Interests-by-berth tab on berth detail — replaces the stub. PR8 Expense duplicate detection — BullMQ job runs scan on create, yellow banner on detail w/ Merge / Not-a-duplicate, transactional merge consolidates receipts and archives the source. PR9 Receipt scanner PWA + multi-provider AI — port-scoped /scan route in its own (scanner) group with no dashboard chrome, dynamic per-port manifest, OpenAI + Claude provider abstraction, admin OCR settings page (port-level + super-admin global default w/ opt-in fallback), test-connection endpoint, manual-entry fallback when no key is configured. Verify form always shown before save — no ghost rows. PR10 Audit log read view — swap to tsvector full-text search on the existing GIN index, cursor pagination, filters for entity/action/user /date range, batched actor-email resolution. PR11 Real-API tests — opt-in receipt-ocr.spec (admin save+test, optional real-receipt parse via REALAPI_RECEIPT_FIXTURE) and alert-engine socket-fanout spec gated behind RUN_ALERT_ENGINE_REALAPI. Both skip cleanly without their gate envs so CI stays green. Test totals: vitest 690 -> 713, smoke 130 -> 138, realapi +2 opt-in. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-28 17:21:55 +02:00
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 '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');
});