Merge pull request #596 from Luca-Timo/bugfix/crm-backup

Backup & Restore hardening — close the silent files-only data-loss class
This commit is contained in:
Paul Nothaft
2026-06-02 09:10:57 +02:00
committed by GitHub
38 changed files with 6042 additions and 251 deletions
@@ -0,0 +1,242 @@
/**
* Integration test for GET /api/admin/system-health/backup-coverage.
*
* Pins the Stage C diagnostic that tells admins what the next
* "Run Backup Now" will include, skip, or silently miss.
*
* Test surface:
* 1. Empty / fresh install → default seed (7 paths), inline mode,
* no DB dump on file yet, no drift
* 2. Toggle `include_in_default=false` → coverage flips to
* 'skipped-by-toggle'
* 3. Feature_flag gating reflects the actual app_settings value
* (events/archived ⇄ backup_include_archived)
* 4. Drift detection: a top-level subdir on disk with no
* `backup_paths` row is flagged in `unconfiguredOnDisk`
* 5. Allow-list: `backups/` and `tmp/` are never flagged as drift
* 6. Scheduled-only mode + recent dump → `database.ok = true`
* 7. Scheduled-only mode + stale (>26h) dump → `database.ok = false`
* and `lastDumpStale = true`
*
* Same auth/permission pass-through strategy as
* adminBackupIntegrity.test.js — we exercise the route's logic,
* not the auth middleware.
*/
const fs = require('fs');
const path = require('path');
const express = require('express');
const request = require('supertest');
const { bootCrmDb } = require('./helpers/crmDb');
jest.mock('../../src/middleware/auth', () => ({
adminAuth: (req, _res, next) => { req.admin = { id: 1 }; next(); },
customerAuth: (_req, _res, next) => next(),
galleryAuth: (_req, _res, next) => next(),
}));
jest.mock('../../src/middleware/permissions', () => ({
requirePermission: () => (_req, _res, next) => next(),
}));
jest.setTimeout(30000);
describe('GET /api/admin/system-health/backup-coverage', () => {
let db;
let cleanup;
let storagePath;
let app;
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
storagePath = process.env.STORAGE_PATH;
const route = require('../../src/routes/adminSystemHealth');
app = express();
app.use(express.json());
app.use('/api/admin/system-health', route);
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
function mkdir(rel) {
fs.mkdirSync(path.join(storagePath, rel), { recursive: true });
}
function rmdir(rel) {
fs.rmSync(path.join(storagePath, rel), { recursive: true, force: true });
}
async function restoreDefaultPaths() {
await db('backup_paths').del();
const { DEFAULT_PATHS } = require('../../migrations/core/109_add_backup_paths');
await db('backup_paths').insert(DEFAULT_PATHS.map((row) => ({
...row,
created_at: new Date(),
updated_at: new Date(),
})));
}
beforeEach(async () => {
await restoreDefaultPaths();
await db('database_backup_runs').del().catch(() => {});
await db('app_settings').where('setting_type', 'backup').del().catch(() => {});
});
it('returns the canonical 7 paths + database block on a fresh install', async () => {
const res = await request(app).get('/api/admin/system-health/backup-coverage');
expect(res.status).toBe(200);
expect(res.body).toHaveProperty('report');
const { report } = res.body;
expect(report.paths.map((p) => p.path)).toEqual([
'events/active',
'events/archived',
'thumbnails',
'previews',
'heroes',
'uploads',
'business-docs',
]);
// Default mode is inline — no inline_dump setting present means
// "inline is ON" (matches ensureDatabaseDumpForBackup semantics).
expect(report.database.mode).toBe('inline');
expect(report.database.ok).toBe(true);
expect(report.summary).toMatchObject({
configuredCount: 7,
tableMissingFallbackInUse: false,
});
});
it('flips a path to skipped-by-toggle when include_in_default=false', async () => {
await db('backup_paths').where('path', 'thumbnails').update({
include_in_default: false,
});
const res = await request(app).get('/api/admin/system-health/backup-coverage');
const thumbnails = res.body.report.paths.find((p) => p.path === 'thumbnails');
expect(thumbnails.coverage).toBe('skipped-by-toggle');
expect(thumbnails.includeInDefault).toBe(false);
});
it('feature_flag gating reflects app_settings (archived path off vs on)', async () => {
// backup_include_archived not set → archived skipped via flag
const off = await request(app).get('/api/admin/system-health/backup-coverage');
const archivedOff = off.body.report.paths.find((p) => p.path === 'events/archived');
expect(archivedOff.coverage).toBe('skipped-by-feature-flag');
expect(archivedOff.featureFlag).toBe('backup_include_archived');
expect(archivedOff.featureFlagValue).toBe(null); // unset
// Now set the flag — but path is missing on disk, so coverage
// resolves to 'missing-on-disk', proving the flag was honoured.
await db('app_settings').insert({
setting_key: 'backup_include_archived',
setting_value: JSON.stringify(true),
setting_type: 'backup',
}).onConflict('setting_key').merge();
const on = await request(app).get('/api/admin/system-health/backup-coverage');
const archivedOn = on.body.report.paths.find((p) => p.path === 'events/archived');
expect(archivedOn.featureFlagValue).toBe(true);
// No on-disk dir → 'missing-on-disk' (not 'skipped-by-feature-flag')
expect(['missing-on-disk', 'will-scan']).toContain(archivedOn.coverage);
});
it('detects unconfigured top-level subdirs as drift', async () => {
mkdir('events/active'); // configured
mkdir('plugin-store/cache'); // DRIFT
mkdir('shiny-new-feature/data'); // DRIFT
const res = await request(app).get('/api/admin/system-health/backup-coverage');
expect(res.body.report.drift.unconfiguredOnDisk).toEqual(expect.arrayContaining([
'plugin-store',
'shiny-new-feature',
]));
expect(res.body.report.drift.unconfiguredOnDisk).not.toContain('events');
rmdir('plugin-store');
rmdir('shiny-new-feature');
});
it('never flags backups/ or tmp/ as drift (allow-list)', async () => {
mkdir('backups');
mkdir('tmp');
const res = await request(app).get('/api/admin/system-health/backup-coverage');
expect(res.body.report.drift.unconfiguredOnDisk).not.toContain('backups');
expect(res.body.report.drift.unconfiguredOnDisk).not.toContain('tmp');
expect(res.body.report.drift.expectedNonBackupDirs).toEqual(
expect.arrayContaining(['backups', 'tmp']),
);
rmdir('backups');
rmdir('tmp');
});
it('scheduled-only mode + recent dump → database.ok=true, not stale', async () => {
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
const recentDump = path.join(storagePath, 'backups', 'recent.sql.gz');
fs.mkdirSync(path.dirname(recentDump), { recursive: true });
fs.writeFileSync(recentDump, 'pretend dump');
await db('database_backup_runs').insert({
started_at: new Date(),
completed_at: new Date(), // just now
status: 'completed',
backup_type: 'pg',
file_path: recentDump,
file_size_bytes: fs.statSync(recentDump).size,
destination_path: recentDump,
});
const res = await request(app).get('/api/admin/system-health/backup-coverage');
expect(res.body.report.database.mode).toBe('scheduled-only');
expect(res.body.report.database.inlineDumpExplicitlyDisabled).toBe(true);
expect(res.body.report.database.lastDumpStale).toBe(false);
expect(res.body.report.database.ok).toBe(true);
});
it('scheduled-only mode + stale dump → database.ok=false, lastDumpStale=true', async () => {
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
const oldDump = path.join(storagePath, 'backups', 'old.sql.gz');
fs.mkdirSync(path.dirname(oldDump), { recursive: true });
fs.writeFileSync(oldDump, 'pretend old dump');
// 48 hours ago — well past the 26h staleness threshold. ISO
// string instead of a Date object because knex-sqlite's datetime
// serialisation has a quirk where some Date instances coerce to
// '[object Object]' on insert (the test 6 "recent dump" case
// passes only because `new Date()` happens to round-trip safely;
// arithmetic Dates don't).
const stale = new Date(Date.now() - 48 * 60 * 60 * 1000).toISOString();
await db('database_backup_runs').insert({
started_at: stale,
completed_at: stale,
status: 'completed',
backup_type: 'pg',
file_path: oldDump,
file_size_bytes: fs.statSync(oldDump).size,
destination_path: oldDump,
});
const res = await request(app).get('/api/admin/system-health/backup-coverage');
expect(res.body.report.database.lastDumpStale).toBe(true);
expect(res.body.report.database.ok).toBe(false);
// Top-level summary reflects the failed DB check.
expect(res.body.report.summary.databaseOk).toBe(false);
expect(res.body.report.summary.overallOk).toBe(false);
});
});
@@ -0,0 +1,140 @@
/**
* Integration test for GET /api/admin/system-health/backup-integrity.
*
* Auth + permission middleware are mocked to pass-through so the test
* focuses on the route's own behaviour: scope-param validation, the
* successResponse envelope, and that the underlying service report
* surfaces correctly in the JSON body.
*
* The verifier service itself is exercised against the real schema
* (bootCrmDb) and real filesystem — only the auth gate is stubbed.
*/
const fs = require('fs');
const path = require('path');
const express = require('express');
const request = require('supertest');
const { bootCrmDb, seedMinimal } = require('./helpers/crmDb');
// Pass-through auth so we don't need to mint JWTs.
jest.mock('../../src/middleware/auth', () => ({
adminAuth: (req, _res, next) => { req.admin = { id: 1 }; next(); },
customerAuth: (_req, _res, next) => next(),
galleryAuth: (_req, _res, next) => next(),
}));
// Pass-through permissions so settings.view always allows.
jest.mock('../../src/middleware/permissions', () => ({
requirePermission: () => (_req, _res, next) => next(),
}));
jest.setTimeout(30000);
describe('GET /api/admin/system-health/backup-integrity', () => {
let cleanup;
let db;
let customerId;
let app;
let storagePath;
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
({ customerId } = await seedMinimal(db));
storagePath = process.env.STORAGE_PATH;
// Mount the route on a minimal Express app. Cold-require after
// bootCrmDb so the route's downstream `require('../database/db')`
// sees the same db instance.
const route = require('../../src/routes/adminSystemHealth');
app = express();
app.use(express.json());
app.use('/api/admin/system-health', route);
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
beforeEach(async () => {
await db('contracts').del().catch(() => {});
await db('invoices').del().catch(() => {});
await db('quotes').del().catch(() => {});
});
it('returns a report envelope when nothing references any path', async () => {
const res = await request(app).get('/api/admin/system-health/backup-integrity');
expect(res.status).toBe(200);
expect(res.body).toHaveProperty('report');
expect(res.body.report.summary).toMatchObject({
totalRows: 0,
missingFiles: 0,
hashMismatches: 0,
verifiedOk: 0,
existsButNoHash: 0,
});
expect(res.body.report.scopes).toEqual(expect.arrayContaining([
'quote', 'contract', 'contract-signature', 'invoice',
]));
});
it('surfaces a missing file in the response payload', async () => {
await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-B7-MISSING',
status: 'sent',
issue_date: '2026-01-01',
signed_pdf_path: 'business-docs/contract/2026/C-B7-MISSING.pdf',
created_at: new Date(),
});
const res = await request(app).get('/api/admin/system-health/backup-integrity');
expect(res.status).toBe(200);
expect(res.body.report.summary.missingFiles).toBe(1);
expect(res.body.report.missing[0]).toMatchObject({
table: 'contracts',
column: 'signed_pdf_path',
expectedPath: 'business-docs/contract/2026/C-B7-MISSING.pdf',
});
});
it('honours the ?scope=invoice filter', async () => {
// Seed both an invoice and a contract with missing files. With
// scope=invoice the contract row must not appear.
await db('invoices').insert({
customer_account_id: customerId,
invoice_number: 'INV-B7-SCOPE',
status: 'sent',
issue_date: '2026-01-01',
due_date: '2026-01-31',
pdf_path: 'business-docs/invoice/2026/INV-B7-SCOPE.pdf',
created_at: new Date(),
});
await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-B7-SCOPE',
status: 'sent',
issue_date: '2026-01-01',
signed_pdf_path: 'business-docs/contract/2026/C-B7-SCOPE.pdf',
created_at: new Date(),
});
const res = await request(app)
.get('/api/admin/system-health/backup-integrity')
.query({ scope: 'invoice' });
expect(res.status).toBe(200);
expect(res.body.report.scopes).toEqual(['invoice']);
expect(res.body.report.missing.every((m) => m.table === 'invoices')).toBe(true);
});
it('rejects an unknown scope with 400 + a code', async () => {
const res = await request(app)
.get('/api/admin/system-health/backup-integrity')
.query({ scope: 'gallery' });
expect(res.status).toBe(400);
expect(res.body.code).toBe('BACKUP_INTEGRITY_UNKNOWN_SCOPE');
expect(res.body.validScopes).toEqual(expect.arrayContaining([
'quote', 'contract', 'contract-signature', 'invoice',
]));
});
});
@@ -0,0 +1,88 @@
/**
* Regression net for the business-docs coverage gap fixed in this PR.
*
* Prior to the fix, `getFilesToBackupInternal()` enumerated a fixed
* list of storage subdirectories (events/active, events/archived,
* thumbnails, previews, heroes, uploads) and silently omitted the
* entire `business-docs/` tree. That meant every CRM PDF + signature
* drawing — quotes, contracts (system-rendered + wet uploads),
* invoices, Storno, imported historical invoices, and the customer
* signature PNG/JPG drawn on the public signing page — fell outside
* the in-app scheduled backup, leaving every `*_path` column on
* `quotes` / `contracts` / `invoices` as a broken FK after restore.
*
* The fix is a single `scanDirectory(business-docs, ...)` call. This
* suite pins the contract so a future refactor of the walker cannot
* silently drop business-docs again.
*/
const fs = require('fs');
const path = require('path');
const { bootCrmDb } = require('./helpers/crmDb');
describe('backupService — business-docs is in the backup walker', () => {
let cleanup;
let backupService;
let storagePath;
beforeAll(async () => {
({ cleanup } = await bootCrmDb());
storagePath = process.env.STORAGE_PATH;
// Cold-require after bootCrmDb so backupService picks up the same
// db instance + STORAGE_PATH the test harness configured.
backupService = require('../../src/services/backupService');
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
function seed(relPath, content = 'dummy bytes for backup test') {
const abs = path.join(storagePath, relPath);
fs.mkdirSync(path.dirname(abs), { recursive: true });
fs.writeFileSync(abs, content);
}
it('does not error when business-docs is absent', async () => {
// Fresh harness has no business-docs/ tree at all. The walker
// must short-circuit on ENOENT rather than throw — installs that
// never used CRM features have to keep backing up fine.
await expect(backupService.getFilesToBackup(false)).resolves.toEqual(expect.any(Array));
});
it('picks up every CRM-relevant business-docs subdirectory', async () => {
// Seed one file in each of the five subpaths the renderer + import
// routes write to. The signature path is the one most prone to be
// forgotten — it lives one level deeper than the others (per-
// contract subfolder, not per-year).
seed('business-docs/quote/2026/Q-001.pdf');
seed('business-docs/contract/2026/C-001.pdf');
seed('business-docs/contract/signatures/42/customer-1700000000000.png');
seed('business-docs/invoice/2026/INV-001.pdf');
seed('business-docs/invoice-imports/2026/scan.pdf');
const files = await backupService.getFilesToBackup(false);
const rels = files.map((f) => f.relativePath);
expect(rels).toEqual(expect.arrayContaining([
'business-docs/quote/2026/Q-001.pdf',
'business-docs/contract/2026/C-001.pdf',
'business-docs/contract/signatures/42/customer-1700000000000.png',
'business-docs/invoice/2026/INV-001.pdf',
'business-docs/invoice-imports/2026/scan.pdf',
]));
});
it('walks newly-created business-docs files without needing a restart', async () => {
// The walker reads the filesystem live on every call; this guards
// against a future "cache the scan result at boot" optimisation
// that would miss freshly-written PDFs (which is exactly what
// happens during normal operation — every send writes a new file).
seed('business-docs/invoice/2027/INV-NEW.pdf');
const files = await backupService.getFilesToBackup(false);
const rels = files.map((f) => f.relativePath);
expect(rels).toContain('business-docs/invoice/2027/INV-NEW.pdf');
});
});
@@ -0,0 +1,180 @@
/**
* Pins the Stage-B refactor that lifted the file-backup walker's
* subdirectory list out of hard-coded JS into the `backup_paths`
* table seeded by migration 109.
*
* Scenarios:
* 1. Walker reads canonical seed → all 7 default subdirs walked
* 2. include_in_default=false on one row → that subdir is skipped
* 3. New row inserted at runtime → walker picks it up without restart
* 4. feature_flag gating → row only walked when the named app_settings
* boolean is truthy (mirrors historical `includeArchived` behavior)
* 5. Empty table → walker falls back to LEGACY_BACKUP_PATHS (defense
* in depth — never silently scans nothing)
*
* Why not stub `db('backup_paths')`: the whole point of Stage B is
* that the walker is now data-driven, so the test has to actually
* mutate the table and observe the walker's output change. Stubs
* would re-introduce the hard-coding the refactor is meant to remove.
*/
const fs = require('fs');
const path = require('path');
const { bootCrmDb } = require('./helpers/crmDb');
jest.setTimeout(30000);
describe('backupService — configurable walker (backup_paths)', () => {
let db;
let cleanup;
let storagePath;
let backupService;
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
storagePath = process.env.STORAGE_PATH;
backupService = require('../../src/services/backupService');
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
function seedFile(relPath, content = 'dummy bytes') {
const abs = path.join(storagePath, relPath);
fs.mkdirSync(path.dirname(abs), { recursive: true });
fs.writeFileSync(abs, content);
}
beforeEach(async () => {
// Restore canonical seed before every test. Tests mutate this table
// freely; the next test starts from a known state.
await db('backup_paths').del();
const {
DEFAULT_PATHS,
} = require('../../migrations/core/109_add_backup_paths');
await db('backup_paths').insert(DEFAULT_PATHS.map((row) => ({
...row,
created_at: new Date(),
updated_at: new Date(),
})));
});
it('migration 109 seeds the canonical 7 paths', async () => {
const rows = await db('backup_paths').orderBy('display_order', 'asc').select();
expect(rows.map((r) => r.path)).toEqual([
'events/active',
'events/archived',
'thumbnails',
'previews',
'heroes',
'uploads',
'business-docs',
]);
// Only events/archived is gated by a feature flag.
expect(rows.filter((r) => r.feature_flag).map((r) => r.path)).toEqual([
'events/archived',
]);
});
it('walks every default subdir when files are present', async () => {
seedFile('events/active/E1/a.jpg');
seedFile('thumbnails/E1/a.jpg');
seedFile('previews/E1/a.jpg');
seedFile('heroes/E1/hero.jpg');
seedFile('uploads/intake/x.bin');
seedFile('business-docs/quote/2026/Q-001.pdf');
// events/archived is gated — left out of this test; covered below.
const files = await backupService.getFilesToBackup({ backup_include_archived: true });
const rels = files.map((f) => f.relativePath);
expect(rels).toEqual(expect.arrayContaining([
'events/active/E1/a.jpg',
'thumbnails/E1/a.jpg',
'previews/E1/a.jpg',
'heroes/E1/hero.jpg',
'uploads/intake/x.bin',
'business-docs/quote/2026/Q-001.pdf',
]));
});
it('skips a path when include_in_default is toggled off', async () => {
seedFile('thumbnails/E1/thumb.jpg');
seedFile('events/active/E1/photo.jpg');
await db('backup_paths').where('path', 'thumbnails').update({
include_in_default: false,
});
const files = await backupService.getFilesToBackup({ backup_include_archived: true });
const rels = files.map((f) => f.relativePath);
expect(rels).toContain('events/active/E1/photo.jpg');
expect(rels).not.toContain('thumbnails/E1/thumb.jpg');
});
it('picks up a new path inserted at runtime — no restart needed', async () => {
// Simulates a future feature shipping its own subdirectory and
// self-healing a `backup_paths` row at boot.
await db('backup_paths').insert({
path: 'plugin-store',
include_in_default: true,
feature_flag: null,
display_order: 200,
description: 'Hypothetical future feature payload',
created_at: new Date(),
updated_at: new Date(),
});
seedFile('plugin-store/cache/payload.bin');
const files = await backupService.getFilesToBackup({ backup_include_archived: true });
const rels = files.map((f) => f.relativePath);
expect(rels).toContain('plugin-store/cache/payload.bin');
});
it('respects feature_flag gating (events/archived ⇄ backup_include_archived)', async () => {
seedFile('events/active/E1/active.jpg');
seedFile('events/archived/E2/archived.jpg');
// backup_include_archived=false → archived/ is skipped.
const filesOff = await backupService.getFilesToBackup({ backup_include_archived: false });
const relsOff = filesOff.map((f) => f.relativePath);
expect(relsOff).toContain('events/active/E1/active.jpg');
expect(relsOff).not.toContain('events/archived/E2/archived.jpg');
// backup_include_archived=true → archived/ is included.
const filesOn = await backupService.getFilesToBackup({ backup_include_archived: true });
const relsOn = filesOn.map((f) => f.relativePath);
expect(relsOn).toContain('events/archived/E2/archived.jpg');
});
it('falls back to LEGACY_BACKUP_PATHS when the table is empty', async () => {
// Defense in depth: even if seed-and-self-heal both failed, the
// walker must still cover the historical set so "Run Backup Now"
// cannot silently degrade to no-op.
await db('backup_paths').del();
seedFile('events/active/E1/photo.jpg');
seedFile('business-docs/quote/2026/Q-002.pdf');
const files = await backupService.getFilesToBackup({ backup_include_archived: true });
const rels = files.map((f) => f.relativePath);
expect(rels).toContain('events/active/E1/photo.jpg');
expect(rels).toContain('business-docs/quote/2026/Q-002.pdf');
});
it('legacy boolean call signature still works (backward compat)', async () => {
// Existing call sites (and the businessDocs regression test) pass
// a boolean for `includeArchived`. Refactor must not break them.
seedFile('events/archived/E3/legacy.jpg');
const filesOff = await backupService.getFilesToBackup(false);
expect(filesOff.map((f) => f.relativePath)).not.toContain('events/archived/E3/legacy.jpg');
const filesOn = await backupService.getFilesToBackup(true);
expect(filesOn.map((f) => f.relativePath)).toContain('events/archived/E3/legacy.jpg');
});
});
@@ -0,0 +1,188 @@
/**
* Pins the inline-DB-dump + fail-loud guard added to `runBackupInternal`.
*
* The previous behaviour was: file-backup looked up an existing dump via
* `getDatabaseBackupInfo()` and silently shipped a files-only manifest
* when none was found. Admins clicking "Run Backup Now" got an apparent
* success that omitted every customer / quote / invoice / contract row —
* the data-loss footgun that this commit closes.
*
* Five scenarios under test:
* 1. Default (inline dump enabled), dump succeeds → backup proceeds
* 2. Default, dump throws → run aborts, backup_runs row marked failed
* 3. Opt-out + recent DB dump available → backup proceeds
* 4. Opt-out + no DB dump available → fail loud
* 5. Opt-out + DB dump file is 0 bytes on disk → fail loud
*
* Mocking strategy: the underlying `databaseBackupService.backup()` and
* the local-destination writer are stubbed so the test exercises just
* the new guard logic without depending on `pg_dump` / `sqlite3` CLI
* binaries being available in the test environment.
*/
const fs = require('fs');
const path = require('path');
const { bootCrmDb } = require('./helpers/crmDb');
// Set up mocks BEFORE bootCrmDb so backupService picks them up at require time.
const mockBackupFn = jest.fn();
jest.mock('../../src/services/databaseBackup', () => ({
databaseBackupService: { backup: mockBackupFn },
startScheduledBackups: jest.fn(),
stopScheduledBackups: jest.fn(),
DatabaseBackupService: class {},
}));
jest.setTimeout(30000);
describe('backupService — inline DB dump + fail-loud guard', () => {
let db;
let cleanup;
let storagePath;
let backupService;
let dumpFileAbs;
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
storagePath = process.env.STORAGE_PATH;
backupService = require('../../src/services/backupService');
// Seed backup destination settings so the run can proceed past the
// "destination not configured" guard.
const dest = path.join(storagePath, 'backups');
fs.mkdirSync(dest, { recursive: true });
// getBackupConfigInternal filters by setting_type='backup', so the
// tests have to seed with that type or the resolver returns
// `{ ... }` with the keys missing — runBackup then sees
// `backup_destination_type === undefined` and bails before our
// new guard runs.
await db('app_settings').insert([
{ setting_key: 'backup_destination_type', setting_value: JSON.stringify('local'), setting_type: 'backup' },
{ setting_key: 'backup_destination_path', setting_value: JSON.stringify(dest), setting_type: 'backup' },
{ setting_key: 'backup_enabled', setting_value: JSON.stringify(true), setting_type: 'backup' },
{ setting_key: 'backup_email_on_failure', setting_value: JSON.stringify(false), setting_type: 'backup' },
]).onConflict('setting_key').merge();
// Pre-create a dump file that getDatabaseBackupInfo can resolve to.
// Reused/mutated per-test via the database_backup_runs seed below.
dumpFileAbs = path.join(storagePath, 'backups', 'fake-dump.sql.gz');
fs.writeFileSync(dumpFileAbs, 'pretend this is a pg_dump'.repeat(100));
// Neutralise the file-scan step: we don't care which files would
// be backed up, just whether the run reaches that stage at all.
backupService.getFilesToBackup = jest.fn(async () => []);
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
beforeEach(async () => {
mockBackupFn.mockReset();
// Default to "dump produced this file with this size" — the per-test
// setup overrides as needed.
mockBackupFn.mockResolvedValue({
success: true,
path: dumpFileAbs,
size: fs.statSync(dumpFileAbs).size,
duration: 1,
checksum: 'abc',
});
// Re-seed the database_backup_runs row that getDatabaseBackupInfo
// resolves against (its query is `status='completed'` + most recent).
await db('database_backup_runs').del();
await db('database_backup_runs').insert({
started_at: new Date(),
completed_at: new Date(),
status: 'completed',
backup_type: 'pg',
file_path: dumpFileAbs,
file_size_bytes: fs.statSync(dumpFileAbs).size,
destination_path: dumpFileAbs,
});
});
it('default behaviour: inline dump runs, then file backup proceeds', async () => {
// Inline-dump setting is unset (undefined) — default is ON.
await db('app_settings').where('setting_key', 'backup_database_inline_dump').del();
await backupService.runBackup(true);
expect(mockBackupFn).toHaveBeenCalledTimes(1);
const run = await db('backup_runs').orderBy('id', 'desc').first();
expect(run.status).toBe('completed');
expect(run.error_message).toBeNull();
});
it('aborts the run when the inline dump throws', async () => {
await db('app_settings').where('setting_key', 'backup_database_inline_dump').del();
mockBackupFn.mockRejectedValueOnce(new Error('pg_dump segfaulted'));
await backupService.runBackup(true);
const run = await db('backup_runs').orderBy('id', 'desc').first();
expect(run.status).toBe('failed');
expect(run.error_message).toMatch(/pg_dump segfaulted/);
});
it('opt-out: skips inline dump but proceeds when a recent dump exists', async () => {
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
await backupService.runBackup(true);
expect(mockBackupFn).not.toHaveBeenCalled();
const run = await db('backup_runs').orderBy('id', 'desc').first();
expect(run.status).toBe('completed');
});
it('opt-out + no recent dump: fails loud with a clear error', async () => {
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
// Wipe the dump row so getDatabaseBackupInfo returns backupFile=null.
await db('database_backup_runs').del();
await backupService.runBackup(true);
const run = await db('backup_runs').orderBy('id', 'desc').first();
expect(run.status).toBe('failed');
expect(run.error_message).toMatch(/No database backup available/);
});
it('opt-out + 0-byte dump file: fails loud', async () => {
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
const emptyDump = path.join(storagePath, 'backups', 'empty-dump.sql.gz');
fs.writeFileSync(emptyDump, '');
await db('database_backup_runs').del();
await db('database_backup_runs').insert({
started_at: new Date(),
completed_at: new Date(),
status: 'completed',
backup_type: 'pg',
file_path: emptyDump,
file_size_bytes: 0,
destination_path: emptyDump,
});
await backupService.runBackup(true);
const run = await db('backup_runs').orderBy('id', 'desc').first();
expect(run.status).toBe('failed');
expect(run.error_message).toMatch(/is empty/);
});
});
@@ -0,0 +1,180 @@
/**
* Per-Stage-B-path tally — Tier 3 of tonight's backup hardening.
*
* Pins the new `computePerPathStats` logic that the Backup History
* "Content Backed Up" pane reads via `backup_runs.statistics.per_path`.
*
* Three scenarios:
* 1. Single file under one path — straightforward attribution
* 2. Multiple paths with overlapping prefixes — longest-prefix wins
* (e.g. `events/active/E1/x.jpg` should attribute to
* `events/active`, not `events`)
* 3. File outside any configured path — silently dropped, doesn't
* throw or contaminate other buckets
*
* Tests exercise the EXPORTED side: write a backup_runs row via the
* service entry point and assert the statistics JSON shape. We don't
* stub `computePerPathStats` directly — the integration view is what
* the frontend actually consumes.
*/
const fs = require('fs');
const path = require('path');
const { bootCrmDb } = require('./helpers/crmDb');
jest.setTimeout(30000);
describe('backupService — per-Stage-B-path statistics', () => {
let db;
let cleanup;
let storagePath;
let backupService;
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
storagePath = process.env.STORAGE_PATH;
backupService = require('../../src/services/backupService');
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
function mkFile(rel, content = 'x'.repeat(100)) {
const abs = path.join(storagePath, rel);
fs.mkdirSync(path.dirname(abs), { recursive: true });
fs.writeFileSync(abs, content);
}
beforeEach(async () => {
// Clean slate of any artefacts from prior tests
await db('backup_runs').del();
await db('app_settings').where('setting_type', 'backup').del();
await db('app_settings').insert([
{ setting_key: 'backup_destination_type', setting_value: JSON.stringify('local'), setting_type: 'backup' },
{ setting_key: 'backup_destination_path', setting_value: JSON.stringify(path.join(storagePath, 'destination')), setting_type: 'backup' },
{ setting_key: 'backup_enabled', setting_value: JSON.stringify(true), setting_type: 'backup' },
{ setting_key: 'backup_email_on_failure', setting_value: JSON.stringify(false), setting_type: 'backup' },
{ setting_key: 'backup_include_archived', setting_value: JSON.stringify(true), setting_type: 'backup' },
]).onConflict('setting_key').merge();
fs.mkdirSync(path.join(storagePath, 'destination'), { recursive: true });
// Restore canonical backup_paths from migration 109
const { DEFAULT_PATHS } = require('../../migrations/core/109_add_backup_paths');
await db('backup_paths').del();
await db('backup_paths').insert(DEFAULT_PATHS.map((row) => ({
...row,
created_at: new Date(),
updated_at: new Date(),
})));
// Wipe leftover files between tests
for (const dir of ['events', 'business-docs', 'thumbnails', 'previews', 'heroes', 'uploads']) {
const p = path.join(storagePath, dir);
if (fs.existsSync(p)) fs.rmSync(p, { recursive: true, force: true });
}
});
it('attributes files to their owning backup_paths row', async () => {
mkFile('events/active/E1/photo-a.jpg', 'X'.repeat(1000));
mkFile('events/active/E1/photo-b.jpg', 'X'.repeat(2000));
mkFile('business-docs/quote/2026/Q-1.pdf', 'X'.repeat(500));
mkFile('thumbnails/E1/photo-a.jpg', 'X'.repeat(50));
// Disable the inline DB dump so we don't need pg_dump in tests;
// the file walker is what produces per_path.
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
// Seed a fake DB-backup row so the fail-loud guard is satisfied.
const fakeDump = path.join(storagePath, 'destination', 'fake.sql.gz');
fs.writeFileSync(fakeDump, 'pretend dump');
await db('database_backup_runs').insert({
started_at: new Date(),
completed_at: new Date(),
status: 'completed',
backup_type: 'pg',
file_path: fakeDump,
file_size_bytes: fs.statSync(fakeDump).size,
destination_path: fakeDump,
});
await backupService.runBackup(true);
const run = await db('backup_runs').orderBy('id', 'desc').first();
expect(run.status).toBe('completed');
const statsRaw = typeof run.statistics === 'string'
? JSON.parse(run.statistics)
: run.statistics;
expect(statsRaw.per_path).toBeDefined();
// events/active should have 2 files (3000 bytes)
expect(statsRaw.per_path['events/active']).toEqual({ count: 2, size: 3000 });
// business-docs should have 1 file (500 bytes)
expect(statsRaw.per_path['business-docs']).toEqual({ count: 1, size: 500 });
// thumbnails should have 1 file (50 bytes)
expect(statsRaw.per_path['thumbnails']).toEqual({ count: 1, size: 50 });
// No spurious buckets for paths that had nothing
expect(statsRaw.per_path['previews']).toBeUndefined();
expect(statsRaw.per_path['heroes']).toBeUndefined();
});
it('archived path attributed separately from active when both have files', async () => {
mkFile('events/active/E1/active.jpg', 'X'.repeat(100));
mkFile('events/archived/E2/archived.jpg', 'X'.repeat(200));
// backup_include_archived already set true in beforeEach so the
// archived walker fires; same opt-out for inline DB dump.
await db('app_settings').insert({
setting_key: 'backup_database_inline_dump',
setting_value: JSON.stringify(false),
setting_type: 'backup',
}).onConflict('setting_key').merge();
const fakeDump = path.join(storagePath, 'destination', 'fake.sql.gz');
fs.writeFileSync(fakeDump, 'pretend dump');
await db('database_backup_runs').insert({
started_at: new Date(),
completed_at: new Date(),
status: 'completed',
backup_type: 'pg',
file_path: fakeDump,
file_size_bytes: fs.statSync(fakeDump).size,
destination_path: fakeDump,
});
await backupService.runBackup(true);
const run = await db('backup_runs').orderBy('id', 'desc').first();
const statsRaw = typeof run.statistics === 'string'
? JSON.parse(run.statistics)
: run.statistics;
// events/active and events/archived attribute separately —
// longest-prefix match prevents `events/active/...` from claiming
// an `events/archived/...` file or vice versa.
expect(statsRaw.per_path['events/active']).toEqual({ count: 1, size: 100 });
expect(statsRaw.per_path['events/archived']).toEqual({ count: 1, size: 200 });
});
});
// NOTE on walker duplication
//
// If two `backup_paths` rows overlap (e.g. one row at `events` AND
// another at `events/active`), the walker scans the same files twice
// — once via each path. Per-path stats then attribute the file to the
// longest-prefix-matching path BOTH times, producing inflated counts.
//
// The canonical seed in migration 109 contains no overlapping pairs,
// so this isn't exercised in practice. But an admin who hand-adds a
// broad row that overlaps an existing nested one will see double
// counts in their next backup's statistics + the destination will
// receive duplicate copies (wasting space). Worth flagging if anyone
// reports it — the fix is to de-dupe `files` in
// `getFilesToBackupInternal` before returning, OR to skip walking a
// path if a longer one has already covered it.
@@ -0,0 +1,214 @@
/**
* Install-from-backup boot hook — pins the trigger-file convention.
*
* The hook itself depends on `restoreService.restore`, which is hard
* to fully exercise in an integration test without a real PG cluster
* (sequence resync, DROP/CREATE, etc.). So we stub the actual restore
* and verify the BOOT HOOK logic:
*
* - No trigger file → no-op, ran=false
* - Empty trigger file → picks newest manifest from manifests/
* - Non-empty trigger file → uses the path inside
* - DB not empty → refuses (no restore call)
* - DB not empty + FORCE env → proceeds
* - Successful restore → deletes trigger file
* - Failed restore → leaves trigger file in place
*
* These are the surfaces an admin will hit when actually using the
* feature — the docker-compose-on-real-PG end-to-end test belongs in
* the follow-up CI work captured as task #7 earlier today.
*/
const fs = require('fs');
const path = require('path');
const { bootCrmDb } = require('./helpers/crmDb');
// Stub the heavy lifting so the test stays fast + portable.
const mockRestore = jest.fn();
jest.mock('../../src/services/restoreService', () => ({
restoreService: {
restore: (...args) => mockRestore(...args),
},
}));
jest.setTimeout(30000);
describe('installFromBackupBoot', () => {
let db;
let cleanup;
let storagePath;
let backupRoot;
let manifestsDir;
let tryInstallFromBackup;
let originalBackupRootEnv;
let originalForceEnv;
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
storagePath = process.env.STORAGE_PATH;
backupRoot = path.join(storagePath, 'backup');
manifestsDir = path.join(backupRoot, 'manifests');
fs.mkdirSync(manifestsDir, { recursive: true });
originalBackupRootEnv = process.env.BACKUP_ROOT;
originalForceEnv = process.env.INSTALL_FROM_BACKUP_FORCE;
process.env.BACKUP_ROOT = backupRoot;
({ tryInstallFromBackup } = require('../../src/services/_installFromBackupBoot'));
}, 120000);
afterAll(async () => {
if (originalBackupRootEnv === undefined) {
delete process.env.BACKUP_ROOT;
} else {
process.env.BACKUP_ROOT = originalBackupRootEnv;
}
if (originalForceEnv === undefined) {
delete process.env.INSTALL_FROM_BACKUP_FORCE;
} else {
process.env.INSTALL_FROM_BACKUP_FORCE = originalForceEnv;
}
if (cleanup) await cleanup();
});
beforeEach(async () => {
mockRestore.mockReset();
mockRestore.mockResolvedValue({ success: true });
delete process.env.INSTALL_FROM_BACKUP_FORCE;
// Clean trigger files + manifests between tests
for (const name of ['RESTORE_ON_INSTALL', 'RESTORE_ON_INSTALL.txt']) {
const p = path.join(backupRoot, name);
if (fs.existsSync(p)) fs.unlinkSync(p);
}
for (const f of fs.readdirSync(manifestsDir)) {
fs.unlinkSync(path.join(manifestsDir, f));
}
// Reset DB to fresh-install state
await db('events').del();
// Leave admin_users alone — fresh-install state has 1 row.
});
it('no trigger file → no-op', async () => {
const result = await tryInstallFromBackup(db);
expect(result.ran).toBe(false);
expect(mockRestore).not.toHaveBeenCalled();
});
it('empty trigger file picks the newest manifest from manifests/', async () => {
const older = path.join(manifestsDir, 'backup-manifest-001.json');
const newer = path.join(manifestsDir, 'backup-manifest-002.json');
fs.writeFileSync(older, '{}');
// Set the newer file's mtime slightly later so it wins the sort
const past = new Date(Date.now() - 60_000);
fs.utimesSync(older, past, past);
fs.writeFileSync(newer, '{}');
// Empty trigger
fs.writeFileSync(path.join(backupRoot, 'RESTORE_ON_INSTALL'), '');
const result = await tryInstallFromBackup(db);
expect(result.ran).toBe(true);
expect(result.manifestPath).toBe(newer);
expect(mockRestore).toHaveBeenCalledWith(expect.objectContaining({
source: 'local',
manifestPath: newer,
restoreType: 'full',
force: true,
skipPreBackup: true,
}));
});
it('non-empty trigger file uses the path inside', async () => {
const specific = path.join(manifestsDir, 'backup-manifest-specific.json');
fs.writeFileSync(specific, '{}');
// Relative to backupRoot
fs.writeFileSync(
path.join(backupRoot, 'RESTORE_ON_INSTALL'),
'manifests/backup-manifest-specific.json\n',
);
const result = await tryInstallFromBackup(db);
expect(result.ran).toBe(true);
expect(result.manifestPath).toBe(specific);
});
it('deletes the trigger file after a successful restore', async () => {
const manifest = path.join(manifestsDir, 'backup-manifest-001.json');
fs.writeFileSync(manifest, '{}');
const triggerPath = path.join(backupRoot, 'RESTORE_ON_INSTALL');
fs.writeFileSync(triggerPath, '');
await tryInstallFromBackup(db);
expect(fs.existsSync(triggerPath)).toBe(false);
});
it('leaves the trigger file in place when restore throws', async () => {
mockRestore.mockRejectedValueOnce(new Error('restore exploded'));
const manifest = path.join(manifestsDir, 'backup-manifest-001.json');
fs.writeFileSync(manifest, '{}');
const triggerPath = path.join(backupRoot, 'RESTORE_ON_INSTALL');
fs.writeFileSync(triggerPath, '');
const result = await tryInstallFromBackup(db);
expect(result.ran).toBe(false);
expect(result.error).toMatch(/restore exploded/);
expect(fs.existsSync(triggerPath)).toBe(true);
});
it('refuses to run when the install already has events', async () => {
// Simulate an install with existing data
await db('events').insert({
slug: 'existing-event',
event_name: 'Existing Event',
event_type: 'wedding',
event_date: new Date(),
host_email: '[email protected]',
admin_email: '[email protected]',
expires_at: new Date(Date.now() + 7 * 24 * 60 * 60 * 1000),
share_link: 'existing-event-token',
password_hash: 'dummy-hash-for-test',
created_at: new Date(),
});
const manifest = path.join(manifestsDir, 'backup-manifest-001.json');
fs.writeFileSync(manifest, '{}');
fs.writeFileSync(path.join(backupRoot, 'RESTORE_ON_INSTALL'), '');
const result = await tryInstallFromBackup(db);
expect(result.ran).toBe(false);
expect(result.error).toMatch(/Database not empty/);
expect(mockRestore).not.toHaveBeenCalled();
// Trigger file should NOT be deleted — admin needs to fix + retry
expect(fs.existsSync(path.join(backupRoot, 'RESTORE_ON_INSTALL'))).toBe(true);
});
it('proceeds when INSTALL_FROM_BACKUP_FORCE=true even with existing data', async () => {
await db('events').insert({
slug: 'existing-event-2',
event_name: 'Existing Event 2',
event_type: 'wedding',
event_date: new Date(),
host_email: '[email protected]',
admin_email: '[email protected]',
expires_at: new Date(Date.now() + 7 * 24 * 60 * 60 * 1000),
share_link: 'existing-event-2-token',
password_hash: 'dummy-hash-for-test-2',
created_at: new Date(),
});
const manifest = path.join(manifestsDir, 'backup-manifest-001.json');
fs.writeFileSync(manifest, '{}');
fs.writeFileSync(path.join(backupRoot, 'RESTORE_ON_INSTALL'), '');
process.env.INSTALL_FROM_BACKUP_FORCE = 'true';
const result = await tryInstallFromBackup(db);
expect(result.ran).toBe(true);
expect(mockRestore).toHaveBeenCalled();
});
});
@@ -0,0 +1,259 @@
/**
* Pins the fix for the PR #596 review blocker.
*
* **The bug**
*
* `preservedMeta` was declared with `let` INSIDE the PostgreSQL
* `else` branch of `performDatabaseRestore`, then read AFTER the
* `else` block closed at the shared replay site (~L1030). On every
* real PG restore:
*
* ReferenceError: preservedMeta is not defined
*
* would fire — psql had already completed the data restore, but
* the operator-meta replay never ran, the trigger file was left
* in place by `_installFromBackupBoot.js` because the restore
* "failed", and `combined.log` got a loud FAILED line even though
* the data was back. Caught on PR #596 review by the maintainer.
*
* **Why CI missed it**
*
* The integration tests around `performFullRestore` only exercise
* the SQLite branch via `this.dbType === 'sqlite'`. The PG branch
* (~L827-984) requires a real PG connection + real `psql` binary,
* neither of which are in the test environment. So the scope leak
* sat untested until the maintainer ran a real DR cycle.
*
* **What this test does**
*
* Reads the source of `restoreService.js` and asserts the scope
* contract: the `preservedMeta` declaration sits ABOVE the
* SQLite/PG branch split, so the replay block at the bottom of the
* try{} can read it on either branch.
*
* Source-inspection is uglier than a runtime test but it has two
* advantages here: (a) it doesn't require a real PG cluster + psql
* binary in CI, (b) it pins the EXACT contract — "the declaration
* must be visible to the replay block" — which is the property
* that broke, more directly than a runtime test would.
*
* The follow-up "real-PG integration test in CI" (separate task)
* would replace this with an end-to-end exercise, at which point
* this can be deleted.
*/
const fs = require('fs');
const path = require('path');
describe('restoreService — PG branch scope contract (PR #596 review)', () => {
let src;
let lines;
beforeAll(() => {
src = fs.readFileSync(
path.join(__dirname, '..', '..', 'src', 'services', 'restoreService.js'),
'utf8',
);
lines = src.split(/\r?\n/);
});
/** Return the 1-based line number of the FIRST line matching `re`. */
function findFirst(re) {
const idx = lines.findIndex((l) => re.test(l));
return idx >= 0 ? idx + 1 : -1;
}
/** Return the 1-based line number of the LAST line matching `re`. */
function findLast(re) {
let last = -1;
lines.forEach((l, i) => { if (re.test(l)) last = i + 1; });
return last;
}
it('preservedMetaSnapshot lives on `this` and is initialised in the constructor', () => {
// PR #596 round 3 moved the snapshot from a block-scoped local to
// an instance variable so the replay can happen in `restore()`
// AFTER post-restore verification — preventing the replay row
// from inflating the row-count check.
//
// Contract:
// 1. The constructor initialises `this.preservedMetaSnapshot = []`
// 2. The `restore()` entry point resets it per call (no leak
// across consecutive runs in the singleton service instance)
// 3. `performDatabaseRestore` assigns to `this.preservedMetaSnapshot`
// inside the PG branch (must run before DROP)
// 4. The replay reads `this.preservedMetaSnapshot` — NOT a bare
// `preservedMeta` local — so a future refactor can't
// accidentally drop the snapshot half on the floor again.
const constructorInit = lines.some((l) =>
/this\.preservedMetaSnapshot\s*=\s*\[\s*\]/.test(l)
);
expect(constructorInit).toBe(true);
const assignmentSites = lines.filter((l) =>
/this\.preservedMetaSnapshot\s*=\s*(\[\s*\]|await\s+db)/.test(l)
);
// Constructor init + restore() per-run reset + the PG-branch
// assignment from db query. Three writes.
expect(assignmentSites.length).toBeGreaterThanOrEqual(3);
// No stray bare `preservedMeta` local-scoped declaration in
// performDatabaseRestore — would indicate someone re-introduced
// the round-1 footgun.
const dangerousLocalDecl = lines.filter((l) =>
/^\s*(let|const)\s+preservedMeta\s*=/.test(l)
);
expect(dangerousLocalDecl).toEqual([]);
});
it('every .count() result is coerced to Number before comparison', () => {
// PR #596 review caught a second PG-only landmine: pg-driver
// returns COUNT(*) as a string ("16" not 16) to preserve bigint
// precision. The original code compared `result.count !==
// expected.rowCount` and every match flagged as a mismatch on PG.
//
// The fix coerces with `Number(...)` at every comparison +
// interpolation site. This test catches a future regression where
// a refactor uses `.count` directly in a `===` / `!==` / `>` /
// `<` comparison without coercing.
//
// Heuristic: find every `.count` access in the file and make sure
// the line either:
// (a) wraps it in `Number(...)`, or
// (b) is purely an interpolation that already coerced upstream
// (e.g. `validation.warnings.push(`... ${eventCountN} ...`)`
// where eventCountN is the coerced local), or
// (c) is the docstring/comment line (filtered separately).
//
// We approximate this by listing every `.count` reference site
// and asserting that lines doing comparisons (`===`/`!==`/`>`/
// `<`/`>=`/`<=`) on a raw `.count` access without `Number(...)`
// around it are zero.
const dangerousLines = lines
.map((l, i) => ({ line: i + 1, text: l }))
// Filter to lines that compare a .count result
.filter(({ text }) => {
// Skip comments
if (/^\s*(\/\/|\*)/.test(text)) return false;
// Detect a `.count` (followed by `)` for `?.count` or by space/operator)
// being directly compared via ===/!==/>/<.
// Match the BAD pattern: `<something>.count <op> <something>`
// where <op> is === / !== / > / < / >= / <=
const bareCountInComparison = /\w+\??\.count\s*(?:!==|===|>=?|<=?)\s+/;
// ALLOW if the .count is preceded by `Number(` in the same line
const wrappedInNumber = /Number\(\s*\w+\??\.count/;
return bareCountInComparison.test(text) && !wrappedInNumber.test(text);
});
expect(dangerousLines).toEqual([]);
});
it('the completed-restore update sets was_successful=true', () => {
// Without this, every successful restore ends up with
// status='completed', was_successful=false — the dashboard's
// "last successful restore" widget then filters out the row +
// any future audit query gating on was_successful misses it.
// Caught locally + maintainer PR #596 review.
//
// Contract: the update payload that writes status='completed' on
// the SUCCESS branch ALSO includes was_successful: true. We pin
// it by source inspection so any future refactor of the success
// payload keeps both fields together.
// The success-branch update lives AFTER performPostRestoreVerification.
// There's also a `status: 'completed'` in the dry-run / early-return
// path (failure handling has its own block too) — we want the
// SUCCESS-branch one specifically.
const verifyLine = findFirst(/performPostRestoreVerification\s*\(/);
expect(verifyLine).toBeGreaterThan(0);
const completedStatusLineIdx = lines
.map((l, i) => ({ line: i + 1, text: l }))
.find(({ line, text }) =>
line > verifyLine && /status:\s*['"]completed['"]/.test(text)
);
expect(completedStatusLineIdx).toBeDefined();
// Look in the next ~10 lines for was_successful: true. The actual
// payload is small (no nested objects between status and the
// closing })), so a fixed-window search is reliable.
const window = lines.slice(
completedStatusLineIdx.line - 1,
completedStatusLineIdx.line + 10,
).join('\n');
expect(window).toMatch(/was_successful:\s*true/);
});
it('npm run migrate:safe is invoked after the replay in restore()', () => {
// Contract from PR #596 round 4: backups taken on older picpeak
// versions must restore COMPLETELY on a newer image — even if new
// migrations have been added since the backup was taken. The
// restore() flow shells out to `npm run migrate:safe` AFTER the
// operator-meta replay so the schema catches up to the running
// code WITHIN the restore boundary (not on the next container
// restart).
//
// Contract:
// 1. A `migrate:safe` shell-out exists somewhere in restoreService
// 2. It sits AFTER the replay drain — verification → replay →
// migrations is the documented order
// 3. It does NOT sit inside performDatabaseRestore (must run
// against the reinit'd pool from the parent restore())
const migrateLine = findFirst(/['"]migrate:safe['"]/);
expect(migrateLine).toBeGreaterThan(0);
const replayLine = findLast(/this\.preservedMetaSnapshot\.length\s*>\s*0/);
expect(replayLine).toBeGreaterThan(0);
expect(migrateLine).toBeGreaterThan(replayLine);
// Must NOT live inside performDatabaseRestore (same scope as the
// replay check above).
const dbRestoreStart = findFirst(/async\s+performDatabaseRestore\s*\(/);
let dbRestoreEnd = -1;
for (let i = dbRestoreStart; i < lines.length; i++) {
if (/^ \}\s*$/.test(lines[i])) {
dbRestoreEnd = i + 1;
break;
}
}
expect(migrateLine < dbRestoreStart || migrateLine > dbRestoreEnd).toBe(true);
});
it('the replay site lives in restore() AFTER performPostRestoreVerification', () => {
// PR #596 round 3 moved the replay out of performDatabaseRestore
// and into the parent restore() method, sequenced AFTER the
// post-restore verification. Otherwise the replay's upserted row
// count was being flagged as a verification mismatch (e.g.
// "expected 190, got 191" because the fresh-install seeded
// `restore_allow_force_auto_upgraded` that wasn't in the backup).
//
// Contract: the line that drains `this.preservedMetaSnapshot`
// must come AFTER `performPostRestoreVerification` AND must NOT
// sit inside `performDatabaseRestore`.
const verificationLine = findFirst(/performPostRestoreVerification\s*\(/);
expect(verificationLine).toBeGreaterThan(0);
const replayLine = findLast(/this\.preservedMetaSnapshot\.length\s*>\s*0/);
expect(replayLine).toBeGreaterThan(0);
expect(replayLine).toBeGreaterThan(verificationLine);
// `performDatabaseRestore` must not contain the replay drain.
// Find the function bounds + assert no drain line falls inside.
const dbRestoreStart = findFirst(/async\s+performDatabaseRestore\s*\(/);
expect(dbRestoreStart).toBeGreaterThan(0);
// Find the closing brace of performDatabaseRestore. Lazy heuristic:
// the first `^ \}\s*$` (two-space indent + }) after the function
// start. Brittle to indent changes but unambiguous in this codebase.
let dbRestoreEnd = -1;
for (let i = dbRestoreStart; i < lines.length; i++) {
if (/^ \}\s*$/.test(lines[i])) {
dbRestoreEnd = i + 1;
break;
}
}
expect(dbRestoreEnd).toBeGreaterThan(dbRestoreStart);
// The replay drain line must be OUTSIDE [dbRestoreStart, dbRestoreEnd].
expect(replayLine < dbRestoreStart || replayLine > dbRestoreEnd).toBe(true);
});
});
@@ -0,0 +1,219 @@
/**
* Verifies the backup-integrity check covers every CRM document
* artefact column and correctly buckets each row into:
* - verifiedOk — file exists AND hash matches (when hash is stored)
* - missing — `*_path` set but file is not on disk
* - hashMismatches — file exists but bytes don't hash to `*_sha256`
* - existsButNoHash — file exists, no `*_sha256` column for this row
*
* Uses the CRM integration harness (bootCrmDb) so the schema +
* STORAGE_PATH wiring exactly mirrors production behaviour.
*
* Background: this service is the diagnostic for the
* `storage/business-docs/` gap fixed in the same PR — without it,
* a restored install would have audit-trail columns referencing
* files that no longer exist, but admins would have no way to see
* the breakage until a customer asked for their contract back.
*/
const fs = require('fs');
const path = require('path');
const crypto = require('crypto');
const { bootCrmDb, seedMinimal } = require('../integration/helpers/crmDb');
jest.setTimeout(30000);
describe('backupIntegrityService.verifyDocumentArtefacts', () => {
let db;
let cleanup;
let customerId;
let storagePath;
let backupIntegrityService;
function seedFile(relPath, content) {
const abs = path.join(storagePath, relPath);
fs.mkdirSync(path.dirname(abs), { recursive: true });
fs.writeFileSync(abs, content);
return { abs, relPath, sha: sha256(content) };
}
function sha256(content) {
return crypto.createHash('sha256').update(content).digest('hex');
}
beforeAll(async () => {
({ db, cleanup } = await bootCrmDb());
({ customerId } = await seedMinimal(db));
storagePath = process.env.STORAGE_PATH;
backupIntegrityService = require('../../src/services/backupIntegrityService');
}, 120000);
afterAll(async () => {
if (cleanup) await cleanup();
});
beforeEach(async () => {
// Wipe CRM rows between tests so each scenario sees a clean slate.
// Order matters: child tables before parents.
await db('invoice_line_items').del().catch(() => {});
await db('invoice_payment_log').del().catch(() => {});
await db('invoices').del().catch(() => {});
await db('quote_line_items').del().catch(() => {});
await db('quotes').del().catch(() => {});
await db('contracts').del().catch(() => {});
});
it('returns an empty report when no documents reference any path', async () => {
const report = await backupIntegrityService.verifyDocumentArtefacts();
expect(report.summary.totalRows).toBe(0);
expect(report.summary.verifiedOk).toBe(0);
expect(report.missing).toEqual([]);
expect(report.hashMismatches).toEqual([]);
expect(report.existsButNoHash).toEqual([]);
expect(report.scannedAt).toMatch(/^\d{4}-\d{2}-\d{2}T/);
expect(report.scopes).toEqual(expect.arrayContaining(['quote', 'contract', 'contract-signature', 'invoice']));
});
it('flags a contract whose signed_pdf_path file is missing', async () => {
// Reference a file that we deliberately never create on disk.
// knex's `.returning('id')` returns `[{ id: N }]` on Postgres and
// newer SQLite, but `[N]` (plain int) on some SQLite versions —
// unwrap both shapes the same way the crmDb test harness does.
const inserted = await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-2026-MISSING',
status: 'sent',
issue_date: '2026-01-01',
signed_pdf_path: 'business-docs/contract/2026/C-2026-MISSING.pdf',
created_at: new Date(),
}).returning('id');
const contractId = typeof inserted[0] === 'object' ? inserted[0].id : inserted[0];
const report = await backupIntegrityService.verifyDocumentArtefacts({ scope: ['contract'] });
const hit = report.missing.find((m) => m.rowId === contractId);
expect(hit).toMatchObject({
table: 'contracts',
column: 'signed_pdf_path',
expectedPath: 'business-docs/contract/2026/C-2026-MISSING.pdf',
});
expect(report.summary.missingFiles).toBe(1);
});
it('verifies a contract whose file exists AND hash matches', async () => {
const { relPath, sha } = seedFile(
'business-docs/contract/2026/C-2026-OK.pdf',
'this is the signed contract content',
);
await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-2026-OK',
status: 'fully_signed',
issue_date: '2026-01-01',
signed_pdf_path: relPath,
signed_pdf_sha256: sha,
created_at: new Date(),
});
const report = await backupIntegrityService.verifyDocumentArtefacts({ scope: ['contract'] });
expect(report.summary.verifiedOk).toBeGreaterThanOrEqual(1);
expect(report.summary.missingFiles).toBe(0);
expect(report.summary.hashMismatches).toBe(0);
});
it('flags a hash mismatch when the file exists but bytes differ from signed_pdf_sha256', async () => {
const { relPath } = seedFile(
'business-docs/contract/2026/C-2026-TAMPER.pdf',
'tampered bytes on disk',
);
const inserted = await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-2026-TAMPER',
status: 'fully_signed',
issue_date: '2026-01-01',
signed_pdf_path: relPath,
// Hash for completely different content — simulates tampering or
// bit-rot between sign-time and now.
signed_pdf_sha256: sha256('the ORIGINAL bytes the customer signed'),
created_at: new Date(),
}).returning('id');
const contractId = typeof inserted[0] === 'object' ? inserted[0].id : inserted[0];
const report = await backupIntegrityService.verifyDocumentArtefacts({ scope: ['contract'] });
const hit = report.hashMismatches.find((m) => m.rowId === contractId);
expect(hit).toBeDefined();
expect(hit.expectedSha).not.toBe(hit.actualSha);
expect(hit.column).toBe('signed_pdf_path');
});
it('buckets signature PNGs into existsButNoHash (no hash column)', async () => {
const { relPath } = seedFile(
'business-docs/contract/signatures/99/customer-1700000000000.png',
'\x89PNG\r\n\x1a\n', // doesn't have to be a real PNG, just bytes
);
await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-2026-SIG',
status: 'fully_signed',
issue_date: '2026-01-01',
signed_customer_signature_path: relPath,
created_at: new Date(),
});
const report = await backupIntegrityService.verifyDocumentArtefacts({
scope: ['contract-signature'],
});
expect(report.summary.existsButNoHash).toBeGreaterThanOrEqual(1);
expect(report.summary.verifiedOk).toBe(0); // no hash → not "verified ok"
expect(report.summary.missingFiles).toBe(0);
const hit = report.existsButNoHash.find((r) => r.column === 'signed_customer_signature_path');
expect(hit).toBeDefined();
});
it('respects the scope filter — contract scope skips quote/invoice tables', async () => {
// Seed an invoice with a missing pdf_path AND a contract with a
// missing signed_pdf_path. Scoping to contract should only flag
// the contract.
await db('invoices').insert({
customer_account_id: customerId,
invoice_number: 'INV-2026-SCOPE',
status: 'sent',
pdf_path: 'business-docs/invoice/2026/INV-2026-SCOPE.pdf',
issue_date: '2026-01-01',
due_date: '2026-01-31',
created_at: new Date(),
});
await db('contracts').insert({
customer_account_id: customerId,
contract_number: 'C-2026-SCOPE',
status: 'sent',
issue_date: '2026-01-01',
signed_pdf_path: 'business-docs/contract/2026/C-2026-SCOPE.pdf',
created_at: new Date(),
});
const report = await backupIntegrityService.verifyDocumentArtefacts({ scope: ['contract'] });
expect(report.scopes).toEqual(['contract']);
expect(report.missing.every((m) => m.table === 'contracts')).toBe(true);
expect(report.missing.some((m) => m.table === 'invoices')).toBe(false);
});
it('covers invoices.imported_pdf_path (admin-uploaded historical scans)', async () => {
// Imported invoices are the most catastrophic case — there's no
// renderer that can reproduce them. Verifier must check this column
// alongside invoices.pdf_path.
await db('invoices').insert({
customer_account_id: customerId,
invoice_number: 'IMP-2025-001',
status: 'sent',
imported_pdf_path: 'business-docs/invoice-imports/2025/legacy.pdf',
issue_date: '2025-06-01',
due_date: '2025-07-01',
created_at: new Date(),
});
const report = await backupIntegrityService.verifyDocumentArtefacts({ scope: ['invoice'] });
const hit = report.missing.find((m) => m.column === 'imported_pdf_path');
expect(hit).toBeDefined();
});
});