Files
TREK/server/tests/unit/auto-backup.test.ts
T
jubnl 305b113d5f Feat/storage driver (#1949)
* feat(storage): storage key validation, driver contract suite, LocalDriver

* feat(storage): MirrorDriver composite backend

* feat(server): add TREK_UPLOADS_DIR env var for the uploads root

* feat(storage): settings-backed registry, StorageService facade, module wiring

* test(storage): pin src/nest/storage coverage thresholds

* feat(storage): multer upload options factory

* refactor(files): spool trip-file uploads through storage

* refactor(collab): spool note attachments through storage; normalize files/ prefix

* refactor(journey): spool journey media uploads through storage

* refactor(trips): spool trip cover upload through storage

* refactor(places): spool place-image and collection uploads through storage

* refactor(auth): spool avatar upload through storage

* fix(server): consolidate allowed_file_types onto AllowedFileTypesService

* fix(storage): default defParamCharset to utf8 in the upload factory

* test(db): re-point the trailing-migration guard at the trip_files prefix strip

* fix(storage): age-gate the boot spool sweep

* test(files): key FILE-P02 residue checks on upload size

* test(storage): raise src/nest/storage coverage pin

* refactor(platform): serve /uploads routes through storage

* refactor(files): serve trip-file downloads through storage

* refactor(memories): serve photo bytes through storage

* refactor(maps): stream place-photo bytes through storage

* refactor(share): stream shared place-photo bytes through storage

* refactor(journey): serve public journey assets through storage

* fix(share): answer place-photo cache miss with 204 like the maps proxy

* test(server): close serving-swap gaps surfaced by the full tier

* test(storage): raise src/nest/storage branches pin

* refactor(place-photos): route place-photo cache through storage

* refactor(places): reclaim place images and collection covers through storage

* refactor(trips): trip covers through storage

* refactor(auth): avatar reclaim through storage

* refactor(collab): note-file deletion through storage

* refactor(files): trash deletion through storage

* refactor(memories): trek photo cache internals through storage

* refactor(memories): thumbnail service category-addressed

* refactor(memories): immich upload reads through storage; drop uploads-root

* refactor(journey): photo deletion through storage

* fix(memories): reclaim orphaned trek photo cache objects in the ttl sweep

* feat(journey): journey-thumbs orphan sweep and delete-site derived-artifact reclaim

* test(server): close slice-4 gaps surfaced by the full tier

* test(coverage): raise slice-4 domain pins

* refactor(backup): list, existence and delete through storage

* refactor(backup): download through storage sendToResponse

* refactor(backup): create backup through per-category storage enumeration

* refactor(backup): restore and upload-restore through storage

* refactor(backup): auto-backup retention through storage

* refactor(server): boot dir-creation to driver init

* test(server): close slice-5 gaps surfaced by the coverage tier

* test(coverage): raise slice-5 backup pin

* test(server): resolve async backupFileExists mocks for the tests typecheck

* test(server): pin ranged-read stat and zero-byte roundtrip in the storage driver contract

* feat(server): TREK_S3_* env wiring — schema, s3 namespace, all-or-nothing boot rule

* feat(server): S3 driver core — aws-lite client seam, stat/delete, driver-owned deadlines

* refactor(server): type the aws-lite S3 client via s3-types reference

* feat(server): S3 driver getStream and list — ranged full-object stat, iterator pagination

* feat(server): S3 driver put — bounded-peek routing, Upload inactivity deadline

* fix(server): S3 driver Upload monitoring — Transform interposition, stream cleanup

* feat(server): env-declared s3-main storage backend; settings-declared s3 rejected

* test(server): env-gated S3 driver contract suite against MinIO

* fix(server): S3 driver zero-byte put — work around aws4 duplicate Content-Length signing defect

* fix(server): scope the zero-byte put workaround to buffered bodies; bind test MinIO to localhost

* ci(server): MinIO-backed S3 driver contract job

* ci(server): align s3-contract shim comment and MinIO bind with references

* docs: S3 storage backend configuration and off-box backup mirroring

* docs: restore README formatting, keep S3 additions only

* ci(server): make live-MinIO contract runs manual-only (AIStor licensing)

MinIO's community line is discontinued entirely; the maintained successor, AIStor, requires a license key that can't safely live in a shared CI runner. The s3-contract CI job is removed; live-provider contract runs against MinIO/AIStor are now a manual, license-gated procedure documented in docker-compose.minio-test.yml's header.

* chore(server): final-review polish — stale CI refs, dockerignore key, boundary pins, zero-byte tempfile contract case

* expose admin ui

* feat(shared): storage backend type registry, wire schemas, category relocation

* feat(server): accept settings-declared s3 backends — shared-schema options, decrypt-at-build, registry preview()

* feat(server): remove TREK_S3_*/TREK_UPLOADS_DIR — tombstone boot rule, built-in override as the relocation path

* feat(server): deriveSecurity.encryptionKeySet and storage secret plumbing (gate, encrypt, unmask, mask, redact)

* chore(server): drop storage-secrets import that only Task 8's probe helper will use

* feat(server): seed-once storage-config.json boot import — fail closed on any invalid seed

* feat(server): registry snapshot() — effective storage config with provenance

* feat(server): api/admin/storage GET/PUT — masked secrets, preview-gated saves, wired reload, audits

* feat(server): api/admin/storage/test — per-target ephemeral probes, mirror targets probed individually

* test(server): e2e coverage for api/admin/storage — guards, managed refusal, envelope, probes

* test(server): give e2e harness DBs the app_settings table the storage registry reads at boot

* test(coverage): raise pins after the storage admin-config slice

* fix(server): final-review polish — encryption-gate wording, all-field sentinel guard, README/e2e notes

* test(server): storage slice-1 review follow-ups — mirror s3-replica probe decrypt, all-encrypted seed without key, test-route 401

* feat(i18n): storage admin domain + tab label in every locale

* feat(client): adminApi storage endpoints — getStorage, updateStorage, testStorageBackend

* feat(client): storage admin draft-document helpers + relative-time util

* feat(client): schema-driven storage BackendForm — fields by kind, mask echo, encryption banner

* feat(client): admin storage panel — backends list, category map, health strip, one-PUT save

* feat(client): storage tab on the admin page

* feat(client): storage admin panel and section on the phone shell

* fix(client): block renaming a storage backend onto an existing name

* feat(server): allow mirrors on any storage category — lift the backups-only rule

* feat(i18n): replicas-on-primary mirror strings in every locale

* feat(client): mirror fold/synthesize model helpers for replicas-on-primary

* feat(client): BackendForm mirror-targets composer; raw mirror type hidden

* feat(client): desktop storage panel folds mirrors into their primaries

* feat(client): phone storage panel folds mirrors into their primaries

* fix(client): strip removed backends from remaining mirror replicas — no phantom refs

* feat(storage): retire photos as a configurable category — served-only via the ServedCategory seam

* feat(i18n): descriptive storage category names and descriptions in every locale

* feat(client): descriptive category names, descriptions and id badges in the storage panel

* docs(storage): fix stale nine-category comments after the eight-category shrink

* docs: storage configuration via the admin UI and seed file — README + compose

* docs(wiki): Admin Storage page and storage cross-links

* docs(server): storage domain blueprint entry; TREK_PLACE_PHOTO_DIR tombstone clarifier

* refactor(server): drop the storage env-var tombstones — the variables never shipped

* docs: storage config is simply new in v4 — drop the removed-variables story

* feat(shared): backfill-status and usage wire schemas on the storage admin state

* feat(server): MirrorDriver.backfill — prefix-scoped, size-compared, cancellable replica catch-up

* feat(server): one-at-a-time storage backfill jobs + the storage events bridge

* feat(server): storage usage scan — nightly cron, on-demand service, persisted with computedAt

* feat(server): replica_failure admin notifications — events bridge, hourly debounce, channel registration

* feat(i18n): replica-failure notification text in every locale

* feat(server): storage backfill and stats-refresh admin endpoints

* feat(client): adminApi backfill and stats-refresh endpoints

* feat(i18n): storage sync and usage strings in every locale

* feat(client): desktop storage panel — sync now, usage display, backfill polling

* feat(client): phone storage panel — sync now, usage display, backfill polling

* fix(client): per-category usage line on the phone storage panel

* docs: sync now, usage stats and replica-failure notifications

* test(server): admin scope now includes replica_failure, not just version_available

Commit 6db135da added replica_failure to ADMIN_SCOPED_EVENTS but left
NPREF-005b asserting the admin scope contained only version_available.
Update the expectation to match.

* test(server): cover storage backfill/stats/jobs branches to hold the coverage pin

* fix(client): guard storage admin polling against stale responses racing a save

A poll GET issued before a save's PUT resolves could land after the save
applied its fresher response, overwriting it with the pre-save world and
re-deriving the draft from that stale snapshot. useStorageAdmin now tracks
a state-application sequence number and drops any refreshState() response
whose sequence has moved on, or that resolves while a save is in flight.
Also guard the fire-and-forget refreshState() calls in startBackfill/
cancelBackfill against unhandled rejections, matching the poll's style.

* fix(server): report 404 before 409 when a backfill start names an unknown mirror

startBackfill checked the global busy flag before validating that :name is
a mirror routed by some category, so POST .../backends/garbage/backfill
answered 409 instead of 404 whenever a sync was already running. Resolve
and validate the target first (BackfillTargetError -> 404), then check
busy (BackfillBusyError -> 409).

* feat(client): two-column category grid on the storage panel

* feat(server): plugin files.getContent reads through the storage layer

* feat(server): plugin files.create writes through the storage layer

* refactor(server): drop FilesService.resolveFilePath, last direct-fs seam in the plugin surface

* fix(server): map StorageInvalidKeyError to the plugin file accessibility envelope

* feat(storage): allow credentialed backends without an explicit ENCRYPTION_KEY

Secrets are still always encrypted at rest; without an explicit key the
implicit data-directory key is used. Removes the plaintext-secret refusal
from the admin PUT and the seed import, the encryptionReady GET field, the
save-blocking banner in both admin shells, and the now-consumerless
security.encryptionKeySet env derivation. Docs now recommend (not require)
an explicit key, since the implicit key rides inside backup archives.

* test(client): pin the stale-poll release to the pre-save GET in FE-ADMIN-STOR-024

The stub deferred EVERY poll GET and rebound the release handle to the
newest one, so a tick landing after the save was released with the
pre-save payload — a response no real backend can produce, which the seq
guard rightly applied. Only the first (genuinely stale) GET is held now;
later GETs answer with the world the mock server currently holds. Also
drops the encryptionReady fixture field removed from the schema in the
previous commit.

* fix(storage): backfill puts carry content-type, stat failures report op stat, progress clamps

* feat(storage): category migration job — copy, flip, delta sweep, reclaimable tally

* feat(storage): migration start/cancel endpoints and client API

* test(client): storage admin fixtures carry the new migrations field

* fix(storage): migration POST answers 200 and validates its body via the shared schema

* fix(storage): cancel running storage jobs when a config save removes their backend

* fix(notifications): in-app replica-failure row carries the suppressed count

* feat(client): migration prompt, queue, and progress on the storage panel

* fix(client): migration queue holds a synchronous single-flight lock

* feat(client): migration prompt and progress on the mobile storage panel

* fix(server): register category-migration routes in the managed-route allow list

StorageAdminController.migrationStart/migrationCancel were added under the
controller-level @ManagedForbidden() decorator but never added to
MANAGED_ROUTE_ALLOW_LIST, so validateManagedRoutes() threw "Managed surface
changed" on every buildApp() call, failing 46 test files (any test booting
the real app).

* test(server): cover category-migration copy/sweep branches to hold the storage coverage pin

Adds MIG-005 (a target object already matching size/key is skipped in the
copy phase itself, not just the delta sweep) and MIG-006 (a copy failure
during the delta sweep is counted without undoing the flip that already
happened). src/nest/storage/**'s branch coverage was 83.91%, just under the
84% pin.

* docs(storage): category migration — move existing objects on reassign

* fix(storage): close the pre-flip cancel window and cancel re-routed migrations

A cancel landing between the last copy iteration and the category flip was
silently ignored, and a config save that re-routed the migrating category to
a third, still-defined backend never stopped the in-flight migration. Also
guards assignCategory against writing an unknown backend name, and fixes a
missing `suppressed` notification param being treated as truthy suppression.

* fix(client): migrations keep mirrors, queue waits on backfills, sweep failures surface

Reassigning a category onto a mirrored primary now posts the migration to the
mirror's wire name instead of the bare primary, so replication survives the
move. The queued-migration effect also waits out a running backfill (the
server's one-job rule spans both), and a done migration with sweep failures
now surfaces a doneFailures line in both shells, translated into every locale.

* ci(server): run the S3 contract suite against MinIO

Resurrects the s3-contract job removed in 6fbff835, adapted for AIStor:
writes the MINIO_LICENSE_KEY secret to a license file, boots the licensed
container, and runs the contract suite hermetically (no --coverage) so the
storage coverage pin keeps holding from unit tests alone. Gated to same-repo
PRs since fork PRs have no access to the license secret.

* fix(server): backup archives uploads from a remote primary

createBackup() enumerated uploads through withLocalFile, which downloads a
remote object to a temp file, hands it to the callback, then deletes it
before archiver ever reads it — archiver reads entries lazily during
finalize(), so a remote (S3) primary silently backed up zero upload bytes.

Add StorageService.getLocalPathOrNull(category, name): a narrow locality
probe that returns a real path only when one exists on disk right now (the
fs-existence check is the fail-safe half of the contract — a driver-reported
path that vanished between list() and here falls back too, not just a
path-less remote driver). The enumeration loop uses it directly when
available (zero-copy, unchanged for a local primary) and otherwise streams
the object into a per-backup staging dir under the backups spool, cleaned up
in the existing finally alongside zipSpool/dbSnap.

Also wire archive.on('warning', reject): archiver treats a missing/unreadable
entry as a warning, not an error, and skips it by default — which would
silently drop the entry from an otherwise "successful" backup.

* fix(server): client aborts stop 500ing and leaking streams

storage.service.ts sendToResponse: the local res.sendFile branch now treats
ECONNABORTED/ECONNRESET/ERR_STREAM_PREMATURE_CLOSE/syscall=write as success,
mirroring res.sendFile's own default callback (the contract
storageStaticHandler already implements caller-side). The remote branch
replaces the hand-rolled pipe+Promise with pipeline(stream, res), which
destroys the source stream on any failure — fixing the leaked S3 keep-alive
socket on a client abort — while swallowing the same client-abort error set;
a real source error still rejects so callers keep their miss contracts.

This centralizes the fix for every caller that streams through
sendToResponse: files-download, journey-public, photo-resolver,
trek-photo-cache, backup downloads, and /uploads/photos.

trek-exception.filter.ts now no-ops (destroying the socket) when headers are
already sent, so no filter path ever writes onto a response in flight.

maps.controller.ts and share.controller.ts's place-photo bytes proxies
switch their direct getStream+pipe to pipeline() with the same abort-tolerant
catch, keeping the existing 204-empty fallback for pre-header failures.

* fix(storage): mirror read fallback consults replicas on primary miss

MirrorDriver.getStream/stat now fall back to replicas on a primary miss
(StorageNotFoundError / null stat), not just an infra error — binding
decision: a read succeeds if ANY member holds the object. Only a
deterministic StorageInvalidKeyError skips fallback.

stat() gets a dedicated fallback loop instead of reusing fromReplicas:
a replica returning null means "keep looking," which the generic
catch-and-continue helper would have short-circuited on.

StorageService.sendToResponse/withLocalFile stop treating composite
driver.stat() as proof the object is at localPath; both now fs-check
the path itself and fall through to the stream branch when it's
missing, which is what actually reaches a MirrorDriver's replicas.

* feat(storage): remote serving parity — content-type, validators, range

Local backends get content type, ETag/Last-Modified, conditional GET, Range
and HEAD for free from res.sendFile; the proxying branch every remote
backend (and a local primary whose file vanished) falls through to had none
of it — every request re-streamed the whole object with no cache validator
and no way to seek.

sendStreamed() reproduces the contract from ONE pre-flight driver.stat():
a miss throws before any header is set (the caller's 404/204/next()
contract), and that same stat then answers 304s, 416s, HEADs and suffix
ranges without ever opening a body. The decisions live in a new pure module,
http-serving.ts:

- validatorsFor: the driver's ETag, else express/send's weak
  W/"<size hex>-<mtime hex>". mtimeMs 0 (S3 can report it) means no
  Last-Modified and no derived tag — serving uncached beats a 1970 header
  that reads as fresh forever.
- isNotModified: If-None-Match (weak compare, *, list) wins over
  If-Modified-Since, per RFC 9110 §13.2.2.
- decideRange: single range only, inclusive clamp, suffix computed from the
  pre-stat size, unsatisfiable → 416, If-Range strong-exact or full entity.
  A multi-range or malformed spec is answered with the full object rather
  than multipart/byteranges. If-Match/If-Unmodified-Since stay out of scope.

Range math uses the pre-stat size as the single source of truth, the ranged
getStream stat is never re-consulted, and the pipeline abort semantics are
unchanged.

S3Driver now surfaces the bucket's ETag on stat()/getStream() (on a ranged
GET it is still the full object's tag). aws-lite strips the tag's
surrounding quotes — verified live against AIStor RELEASE.2026-08-07 — and
an unquoted entity-tag is not a valid HTTP ETag, so the driver restores
exactly the quotes the SDK removed and nothing else.

* fix(server): key rotation covers storage.backends

The S3 storage backend's secretAccessKey is encrypted at rest inside the
app_settings row keyed storage.backends, but scripts/migrate-encryption.ts
didn't know about it — after a key rotation that secret stayed encrypted
under the old key and silently failed to decrypt on the next read.

The script now re-encrypts secretAccessKey for every s3 backend inside the
storage.backends JSON array, using a pinned copy of the secret-field list
(it deliberately can't import @trek/shared). The parity test pins that copy
against storageSecretFields('s3') so a new secret field can't be missed
silently.

* fix(server): restore reloads the storage registry

restoreFromZip closed and reopened the DB but never reloaded the
storage registry, so uploads rehydration ran against the STALE
pre-restore driver/category map instead of the config the restored
archive's own travel.db carries (audit #4, major).

StorageService gains reloadConfig(), a narrow passthrough to the
(unexported) registry's reload() — same shape as health(). backup.impl's
restoreFromZip now calls it right after reinitialize() and right before
the uploads wipe/rehydrateUploads/plugin staging, so rehydrated bytes
land where the restored config says. When reopen fails (reinitFailed),
reload and rehydration are skipped entirely — already reported as
"restart required", and there is no live DB handle for the registry to
read anyway.

* fix(server): category migration rewrites keys across prefix changes

Category migration copied objects to the destination backend using the
SOURCE key verbatim. A mode-A ('' prefix) source migrating onto a
prefixed backend (or vice versa) landed objects at keys the registry
could never resolve post-flip (audit #8).

Extracts StorageRegistryService.keyPrefixFor(category, backendName) from
build()'s inline conditional so startMigration can compute the
destination prefix before the flip. runMigration now maps every
destination key (destPrefix + key.slice(sourcePrefix.length)) in the
copy skip-check, the put, and the delta sweep; the reclaimable tally
stays source-keyed. Equal-prefix migrations are unaffected (identity
mapping).

* fix(plugins): await the now-async place/collection services in RPCs

PlacesService.update/remove and CollectionsService.deletePlace became
async when they started deleting storage objects, but their plugin RPC
handlers still called them synchronously: the null/false refusal check
compared against an always-truthy Promise, and places.update broadcast
a Promise instead of the resolved place. Both handlers now await the
service call; mapCollectionError is async-aware (accepts a sync-or-
async thunk) so the sync callers (create/update/savePlace/copyToTrip)
keep working through the same path. Verified the RPC host already
awaits handler results, so no change was needed there.

* fix(storage): backfill Sync now gains a deletion sweep

The Sync now backfill copied primary objects to replicas but never removed
replica objects the primary no longer has, leaving mirror read-fallback able
to serve stale data indefinitely after a failed replica delete. backfill()
now sweeps each replica post-copy: any replica key absent from the primary
key-set is re-checked against primary.stat (a race gate against the primary
regaining the key) before being deleted. Adds a deleted counter end-to-end
(driver, jobs service, shared schema, both admin shells, all 23 locales) and
a new ReplicaFailure 'list' op for a replica whose listing itself fails
during the sweep.

* feat(storage): optimistic concurrency for admin config saves

A stale admin PUT of storage settings could silently undo a category
migration's just-flipped assignment. Adds a version counter
(app_settings row storage.config_version) bumped inside the same
transaction by both writers — applyConfig and the migration flip
(assignCategory). applyConfig compares the submitted version first
and throws StorageConflictError, mapped to 409 ahead of the blanket
400. The client carries the draft's loaded version through every
local edit and maps a 409 to a distinct "settings changed underneath
you" message, refreshing state while preserving the dirty draft for
review.

* fix(storage): surface a failed config load + redact secretAccessKey

Registry load() now records the exact parse/validate failure as
lastLoadError() instead of silently falling back to last-good config or
built-in defaults; StorageAdminService exposes it as configError on the
admin state (storageAdminStateSchema extended additively), and
AdminStoragePanel renders it as a warning banner naming the error. Save
stays enabled — it's the recovery path — but an admin can no longer save
over a broken stored config without knowing.

Also adds 'secretaccesskey' to globalMiddleware's SENSITIVE_KEYS request-log
redaction list, so storage admin PUT bodies never leak the S3 secret into
debug logs.

* fix(client): admin storage panel state races

Migration prompt now recomputes computeMigrationCandidates(draft, state)
on render and again at confirm time, so a stale open-time snapshot never
drives stripCategories or the migration queue; adds a Cancel button to
the dialog. A failed startMigration POST explicitly clears the remaining
queue with a toast naming the dropped categories and refreshes state,
instead of leaving it invisibly stranded; a "Queued: X, Y" line renders
while the queue is non-empty. Testing a mirrored row now expands the
draft primary + replicas client-side and probes each individually,
instead of sending the mirror stub to the server (which resolved
targets from its own live snapshot, silently testing saved options over
unsaved draft edits). A completed/cancelled/errored backfill now renders
its terminal status alongside the Sync now button instead of hiding it,
so it can be re-run without a page reload.

* fix(storage): refuse shared replica backends so the sync sweep cannot cross categories

A mirror's "Sync now" sweep makes each replica MATCH the primary: it lists the
replica under every prefix the mirror's categories occupy and deletes the keys
the primary doesn't hold. The backups category's prefix is '' — the replica's
entire root — so making a category-serving backend (say uploads-local) a
replica of a backups mirror meant the first sync deleted every user upload.
Nothing forbade the config: validateConfig only checked that mirror targets
existed and weren't nested, and the admin picker offered every backend.

The sweep is correct, so the fix is at the config level:

- validateConfig refuses a backend that is both a mirror replica and a
  category target (directly, or as the primary of a mirror a category routes
  to), and refuses a backend replicating two mirrors whose swept prefixes
  overlap — '' overlaps everything. Disjoint prefixes stay legal.
- assignCategory (the migration flip, the other writer of the settings rows)
  refuses routing a category onto a backend that is currently a replica.
- The admin mirror-target picker (both shells) only offers backends that serve
  no category; already-selected targets stay listed so they can be unchecked.
  A category assigned to a replica still surfaces the server's 400 verbatim.

Existing shared-replica fixtures were rewritten onto dedicated replicas.

* fix(client): a 409 conflict save is recoverable without a page reload

After a 409 the admin storage panel was a dead end. refreshState leaves a
dirty draft's version alone on purpose (audit #7: the background poll must
never float a mid-edit draft past a migration flip it never carried), setDraft
re-attaches that same version to every later edit, and save() resubmits it —
so every retry 409s again and only a full page reload got the operator out,
while the banner told them to "review and save again".

The version block stays. Instead the conflict banner now offers the one action
that can clear it: discard the local edits and reload the saved settings —
a fresh GET applied through applyState, re-deriving the draft (and its
version) and clearing dirty/saveError. Bumping the version in refreshState,
or only in the 409 branch, was rejected: either resurrects audit #7, since a
full-document save would then revert a flip the draft never carried.

storage.saveConflict now points at that action instead of implying a plain
re-save works (all 23 locales). The escape lives in the shared hook, so the
phone panel renders it too.

* fix(client): deflake the queued-migration-waits-out-backfill panel test

FE-ADMIN-STOR-037 seeds a running backfill, so the panel polls GET from
first render — but the stub served the post-save world (files: off-box)
before the PUT had landed, which no real server would do. A poll
resolving while the confirm dialog was open made the confirm-time
candidate recompute see from === to, so nothing was queued and the
migration never POSTed.

The GET stub now stays faithful (pre-save world until the PUT lands,
usage included so candidates keep their object counts), and the test
deterministically forces the once-flaky interleaving: it waits for
polls to land while the dialog is open and asserts the candidate
survives them.

* fix(storage): surface the underlying cause in probe target errors

The admin storage Test probe reported only the driver wrapper's outer
message ("put failed for '…' on 'probe-s3'"), dropping the cause that
says WHY — connection refused vs missing bucket. Flatten the error's
cause chain into the probe result, appending an S3-style code when it
isn't already in the message.

* fix(storage): surface the underlying cause in replica-failure reports

Same defect as the probe fix, one layer over: MirrorDriver's
reportReplicaFailure captured only the wrapper's message, so
replica-failure notifications said "put failed" without the why.
Move the probe's cause-chain flattener into storage.types.ts as
describeError and use it in both call sites.

* fix(storage): strip ContentType from multipart Upload calls (MalformedXML)

Every multipart S3 put carrying a contentType — every backup zip and
photo over the 10MB threshold — failed with 400 MalformedXML. Upstream
@aws-lite/s3's Upload leaks the ContentType param into its final
CompleteMultipartUpload headers ({ ...xml, ...paramHeaders }), clobbering
application/xml, which flips @aws-lite/client's payload serializer to
JSON — so the server receives a JSON parts list where XML belongs.
Confirmed live against MinIO AIStor; any S3 refuses the same.

uploadMonitored now drops ContentType before s3.Upload. Multipart
objects are stored without a content-type, which TREK never reads back
(serving derives Content-Type from the key/caller, never object
metadata); single-request PutObject paths keep sending it.

Also closes the coverage gap that let this ship: the live contract
suite never crossed MULTIPART_THRESHOLD, so s3.Upload had never run
against a real server — it now round-trips a >10MB put carrying a
contentType.

---------

Co-authored-by: Maurice <mauriceboe@icloud.com>
2026-08-22 11:33:55 +02:00

372 lines
16 KiB
TypeScript

/**
* Scheduled backup run (AutoBackupJob).
*
* The auto-backup used to archive the live travel.db: the archiver reads its
* entries while streaming, so a WAL auto-checkpoint writing pages back mid-run
* left a torn copy in the zip — without the -wal that would make it recoverable.
* It also shipped without .encryption_key, so the archive could not be decrypted
* on another install. The run now goes through backupService.createBackup(),
* which snapshots the DB with VACUUM INTO and bundles the key.
*/
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
import type { PathLike } from 'node:fs';
const fsMock = vi.hoisted(() => ({
// The parameter is declared so the double carries fs's real signature: the
// cases below replace this default with a path-dependent implementation.
existsSync: vi.fn((_p: PathLike) => false),
mkdirSync: vi.fn(),
readFileSync: vi.fn(() => '{}'),
writeFileSync: vi.fn(),
readdirSync: vi.fn(() => [] as unknown as string[]),
statSync: vi.fn(() => ({ size: 0, birthtime: new Date(0), mtimeMs: 0 })),
unlinkSync: vi.fn(),
createWriteStream: vi.fn(),
createReadStream: vi.fn(),
rmSync: vi.fn(),
copyFileSync: vi.fn(),
renameSync: vi.fn(),
cpSync: vi.fn(),
realpathSync: vi.fn((p: string) => p),
}));
const archiveMock = vi.hoisted(() => ({
pipe: vi.fn(),
file: vi.fn(),
directory: vi.fn(),
glob: vi.fn(),
finalize: vi.fn(),
on: vi.fn(),
}));
const archiverMock = vi.hoisted(() => vi.fn());
const dbMock = vi.hoisted(() => ({
db: { exec: vi.fn(), prepare: vi.fn() },
closeDb: vi.fn(),
reinitialize: vi.fn(),
}));
const logMock = vi.hoisted(() => ({ logInfo: vi.fn(), logError: vi.fn() }));
vi.mock('fs', () => ({ default: fsMock, ...fsMock }));
vi.mock('node:fs', () => ({ default: fsMock, ...fsMock }));
vi.mock('archiver', () => ({ default: archiverMock }));
vi.mock('unzipper', () => ({ default: { Extract: vi.fn(), Open: { file: vi.fn() } } }));
vi.mock('../../src/db/database', () => dbMock);
vi.mock('../../src/nest/audit/audit-log.logger', () => logMock);
vi.mock('../../src/config', () => ({
JWT_SECRET: 'test-secret',
ENCRYPTION_KEY: 'a'.repeat(64),
updateJwtSecret: () => {},
}));
import path from 'node:path';
import { AutoBackupJob } from '../../src/nest/backup/auto-backup.job';
import { createBackup } from '../../src/nest/backup/backup.impl';
import type { BackupService } from '../../src/nest/backup/backup.service';
import type { StorageService } from '../../src/nest/storage/storage.service';
import type { CronRegistrarService } from '../../src/nest/scheduling/cron-registrar.service';
const liveDb = path.join(__dirname, '../../data', 'travel.db');
// createBackup receives StorageService as a parameter (BackupService injects
// it). fs is mocked wholesale here, so a plain stub stands in for the backups
// backend: staging under /stub/spool, empty category listings, put/stat succeed.
const storageStub = vi.hoisted(() => ({}) as Record<string, unknown>);
function resetStorageStub() {
Object.assign(storageStub, {
spoolDirFor: vi.fn(() => '/stub/spool'),
tempDir: vi.fn(() => '/stub/tmp'),
list: vi.fn(async function* () {}),
withLocalFile: vi.fn(async (_c: string, _k: string, fn: (p: string) => Promise<unknown>) => fn('/stub/local/path')),
put: vi.fn(async () => {}),
stat: vi.fn(async (_c: string, key: string) => ({ key, size: 4096, mtimeMs: Date.parse('2026-04-27T02:00:00Z') })),
exists: vi.fn(async () => true),
delete: vi.fn(async () => {}),
});
}
resetStorageStub();
interface Registered {
name: string;
expr: string;
onTick: () => Promise<void> | void;
}
/** An AutoBackupJob wired to the real createBackup and a capturing registrar double. */
function makeJob() {
const registered: Registered[] = [];
const registrar = {
isEnabled: vi.fn(() => true),
register: vi.fn((name: string, expr: string, onTick: Registered['onTick']) => {
registered.push({ name, expr, onTick });
return true;
}),
unregister: vi.fn(),
};
const job = new AutoBackupJob(
// The same wiring the container does, with the real service function behind
// it — the run below is still the production code path. The forward mirrors
// BackupService: inject the storage stub as the first argument.
{ createBackup: (prefix?: 'backup' | 'auto-backup') => createBackup(storageStub as unknown as StorageService, prefix) } as unknown as BackupService,
registrar as unknown as CronRegistrarService,
storageStub as unknown as StorageService,
);
return { job, registered, registrar };
}
/** Wires up the archiver so finalize() resolves the run, and returns its events. */
function stubArchiver(): Record<string, (arg?: unknown) => void> {
const outputEvents: Record<string, (arg?: unknown) => void> = {};
const archiveEvents: Record<string, (arg?: unknown) => void> = {};
fsMock.createWriteStream.mockReturnValue({
on: vi.fn((event: string, cb: () => void) => { outputEvents[event] = cb; }),
} as never);
archiveMock.on.mockImplementation((event: string, cb: (arg?: unknown) => void) => { archiveEvents[event] = cb; });
archiveMock.finalize.mockImplementation(() => { outputEvents['close']?.(); });
archiverMock.mockReturnValue(archiveMock);
return archiveEvents;
}
/** Arms the job with auto-backup enabled and hands back the cron tick. */
function scheduledRun(): () => Promise<void> {
fsMock.readFileSync.mockReturnValue(JSON.stringify({ enabled: true, interval: 'daily', keep_days: 7 }));
const { job, registered } = makeJob();
job.start();
return registered.at(-1)?.onTick as () => Promise<void>;
}
describe('auto-backup run', () => {
const envKey = process.env.ENCRYPTION_KEY;
beforeEach(() => {
vi.clearAllMocks();
resetStorageStub();
// No ENCRYPTION_KEY in the env means the key file is the source of truth and
// has to travel with the backup.
delete process.env.ENCRYPTION_KEY;
fsMock.statSync.mockReturnValue({ size: 4096, birthtime: new Date('2026-04-27T02:00:00Z'), mtimeMs: Date.now() } as never);
});
afterEach(() => {
process.env.ENCRYPTION_KEY = envKey;
});
it('archives a VACUUM INTO snapshot, never the live travel.db', async () => {
fsMock.existsSync.mockImplementation((p: string) => String(p).endsWith('travel.db') || String(p).endsWith('backup-settings.json'));
stubArchiver();
await scheduledRun()();
expect(dbMock.db.exec).toHaveBeenCalledWith(expect.stringContaining('VACUUM INTO'));
const dbEntry = archiveMock.file.mock.calls.find(([, opts]) => opts?.name === 'travel.db');
expect(dbEntry).toBeDefined();
expect(dbEntry?.[0]).toContain('/stub/spool/travel-snap-auto-backup-');
expect(dbEntry?.[0]).not.toBe(liveDb);
});
it('bundles the at-rest encryption key', async () => {
fsMock.existsSync.mockImplementation((p: string) => String(p).endsWith('.encryption_key') || String(p).endsWith('backup-settings.json'));
stubArchiver();
await scheduledRun()();
expect(archiveMock.file).toHaveBeenCalledWith(
expect.stringContaining('.encryption_key'),
{ name: '.encryption_key' },
);
});
it('keeps the auto-backup-*.zip naming so retention still prunes it', async () => {
fsMock.existsSync.mockImplementation((p: string) => String(p).endsWith('backup-settings.json'));
// An expired scheduled archive sits in the backups category (retention
// lists through storage now); the category enumeration stays empty.
storageStub.list = vi.fn((category: string) =>
(async function* () {
if (category === 'backups') yield { key: 'auto-backup-2020-01-01T02-00-00.zip', size: 0, mtimeMs: 0 };
})(),
);
stubArchiver();
await scheduledRun()();
expect(logMock.logInfo).toHaveBeenCalledWith(expect.stringMatching(/^Auto-Backup created: auto-backup-[\dT-]+\.zip$/));
// cleanupOldBackups(storage, keep_days) still runs after the archive and
// only prunes objects it can match by prefix — through storage.delete
expect(storageStub.delete).toHaveBeenCalledWith('backups', 'auto-backup-2020-01-01T02-00-00.zip');
});
it('logs the failure, drops the partial zip and skips retention', async () => {
fsMock.existsSync.mockImplementation((p: string) => String(p).endsWith('.zip') || String(p).endsWith('backup-settings.json'));
const archiveEvents = stubArchiver();
archiveMock.finalize.mockImplementation(() => { archiveEvents['error']?.(new Error('disk full')); });
await scheduledRun()();
expect(logMock.logError).toHaveBeenCalledWith('Auto-Backup: disk full');
expect(logMock.logInfo).not.toHaveBeenCalledWith(expect.stringContaining('Auto-Backup created'));
// nothing was committed (put commits by rename only on success); the
// half-built zip spool and snapshot scratch are cleaned up, and retention
// never runs
expect(storageStub.put).not.toHaveBeenCalled();
expect(fsMock.rmSync).toHaveBeenCalledWith(expect.stringContaining('zip-build-auto-backup-'), { force: true });
expect(fsMock.rmSync).toHaveBeenCalledWith(expect.stringContaining('travel-snap-auto-backup-'), { force: true });
expect(storageStub.list).not.toHaveBeenCalledWith('backups');
expect(storageStub.delete).not.toHaveBeenCalled();
});
});
describe('auto-backup scheduling (AutoBackupJob.start)', () => {
beforeEach(() => {
vi.clearAllMocks();
resetStorageStub();
fsMock.existsSync.mockImplementation(() => false);
fsMock.readFileSync.mockReturnValue('{}');
});
it('disabled settings unregister the job and log Auto-Backup disabled', () => {
const { job, registrar } = makeJob();
job.start();
expect(registrar.unregister).toHaveBeenCalledWith('auto-backup');
expect(registrar.register).not.toHaveBeenCalled();
expect(logMock.logInfo).toHaveBeenCalledWith('Auto-Backup disabled');
});
it('enabled settings register the built expression under the auto-backup name and log the banner', () => {
fsMock.existsSync.mockImplementation((p: PathLike) => String(p).endsWith('backup-settings.json'));
fsMock.readFileSync.mockReturnValue(JSON.stringify({ enabled: true, interval: 'daily', keep_days: 7, hour: 2 }));
const { job, registered } = makeJob();
job.start();
expect(registered.at(-1)?.name).toBe('auto-backup');
expect(registered.at(-1)?.expr).toBe('0 2 * * *');
expect(logMock.logInfo).toHaveBeenCalledWith(
expect.stringMatching(/^Auto-Backup scheduled: daily \(0 2 \* \* \*\), tz: .+, retention: 7 days$/),
);
});
it('skips the banner when the registrar refuses to arm (test gate)', () => {
fsMock.existsSync.mockImplementation((p: PathLike) => String(p).endsWith('backup-settings.json'));
fsMock.readFileSync.mockReturnValue(JSON.stringify({ enabled: true, interval: 'daily', keep_days: 7 }));
const { job, registrar } = makeJob();
registrar.register.mockImplementation(() => false);
job.start();
expect(logMock.logInfo).not.toHaveBeenCalledWith(expect.stringContaining('Auto-Backup scheduled'));
});
it('onApplicationBootstrap does nothing when the registrar is disabled', () => {
const { job, registrar } = makeJob();
registrar.isEnabled.mockReturnValue(false);
job.onApplicationBootstrap();
expect(registrar.register).not.toHaveBeenCalled();
expect(registrar.unregister).not.toHaveBeenCalled();
expect(logMock.logInfo).not.toHaveBeenCalled();
});
it('onApplicationBootstrap arms the cron when the registrar is enabled', () => {
fsMock.existsSync.mockImplementation((p: PathLike) => String(p).endsWith('backup-settings.json'));
fsMock.readFileSync.mockReturnValue(JSON.stringify({ enabled: true, interval: 'hourly' }));
const { job, registered } = makeJob();
job.onApplicationBootstrap();
expect(registered.at(-1)?.name).toBe('auto-backup');
expect(registered.at(-1)?.expr).toBe('0 * * * *');
});
it('keep_days 0 banners "retention: forever" and skips retention after a run', async () => {
fsMock.existsSync.mockImplementation((p: PathLike) => String(p).endsWith('backup-settings.json'));
fsMock.readFileSync.mockReturnValue(JSON.stringify({ enabled: true, interval: 'daily', keep_days: 0 }));
stubArchiver();
const { job, registered } = makeJob();
job.start();
expect(logMock.logInfo).toHaveBeenCalledWith(expect.stringContaining('retention: forever'));
await (registered.at(-1)?.onTick as () => Promise<void>)();
expect(logMock.logInfo).toHaveBeenCalledWith(expect.stringContaining('Auto-Backup created'));
expect(storageStub.list).not.toHaveBeenCalledWith('backups'); // cleanupOldBackups never ran
expect(storageStub.delete).not.toHaveBeenCalled();
});
it('a non-Error rejection from createBackup is stringified into the failure log', async () => {
const broken = { createBackup: vi.fn().mockRejectedValue('plain string') } as unknown as BackupService;
const registrar = { isEnabled: vi.fn(() => true), register: vi.fn(() => true), unregister: vi.fn() };
const job = new AutoBackupJob(broken, registrar as unknown as CronRegistrarService, storageStub as unknown as StorageService);
await job.runBackup();
expect(logMock.logError).toHaveBeenCalledWith('Auto-Backup: plain string');
});
it('getAutoSettings returns the loaded settings with a resolved timezone', () => {
const prevTz = process.env.TZ;
try {
process.env.TZ = 'Europe/Zurich';
const { job } = makeJob();
expect(job.getAutoSettings()).toEqual({
settings: { enabled: false, interval: 'daily', keep_days: 7, hour: 2, day_of_week: 0, day_of_month: 1 },
timezone: 'Europe/Zurich',
});
delete process.env.TZ;
// Falls back to the host zone (or UTC when the host reports none).
expect(typeof job.getAutoSettings().timezone).toBe('string');
expect(job.getAutoSettings().timezone.length).toBeGreaterThan(0);
} finally {
if (prevTz === undefined) delete process.env.TZ;
else process.env.TZ = prevTz;
}
});
});
// Moved from backup.impl.test.ts when updateAutoSettings moved onto the job
// (the impl used to call scheduler.saveSettings + scheduler.start()).
describe('BACKUP-047 updateAutoSettings', () => {
beforeEach(() => {
vi.clearAllMocks();
resetStorageStub();
fsMock.existsSync.mockImplementation(() => false);
fsMock.readFileSync.mockReturnValue('{}');
});
it('BACKUP-047a — persists the parsed settings to backup-settings.json', () => {
const { job } = makeJob();
job.updateAutoSettings({ enabled: true, interval: 'weekly', hour: 6 });
expect(fsMock.writeFileSync).toHaveBeenCalledOnce();
const [file, payload] = fsMock.writeFileSync.mock.calls[0] as [string, string];
expect(file).toContain('backup-settings.json');
expect(JSON.parse(payload)).toMatchObject({ enabled: true, interval: 'weekly', hour: 6 });
});
it('BACKUP-047b — re-arms the job only after saving', () => {
const order: string[] = [];
fsMock.writeFileSync.mockImplementation(() => { order.push('save'); });
const { job, registrar } = makeJob();
// Saving {enabled:false} sends start() down the disabled path — unregister
// is its scheduling action, so it stands in for the old scheduler.start().
registrar.unregister.mockImplementation(() => { order.push('start'); });
job.updateAutoSettings({ enabled: false });
expect(order).toEqual(['save', 'start']);
});
it('BACKUP-047c — returns the parsed settings object', () => {
const { job } = makeJob();
const result = job.updateAutoSettings({
enabled: true,
interval: 'monthly',
keep_days: 30,
hour: 3,
day_of_week: 2,
day_of_month: 15,
});
expect(result).toEqual({
enabled: true,
interval: 'monthly',
keep_days: 30,
hour: 3,
day_of_week: 2,
day_of_month: 15,
});
});
});