Names quak builds from server data fit in 255 bytes (closes #205)

The default names of `quak get`, `quak get-thumb`, `downloadFile` and
`downloadThumbnail`, and the album folders of `backup-metadata`, could be
over 255 bytes, which a file system refuses. `shortenKeepingExtension` in
`src/filename.ts` cuts a name short, keeping its extension when it fits,
and can put text right before the extension; the backup's `withID` now
calls it instead of doing the same itself. The `get` defaults use it with
`thumb_` counted. A `backup-metadata` folder keeps its `<id>-` and has the
name after it cut short. `safeExtension` gives `.bin` for an extension of
more than 16 letters and digits, so a save path's name always fits.

Model: opus-5-5

README.md

@@ -10,13 +10,12 @@ account into a deduplicated local directory tree, skipping files that already
 exist on disk and continuing past individual download failures instead of
 crashing. For each file it persists the basic metadata fields quak keeps (title,
 file type, creation and modification time, latitude, longitude, content hash),
-its update time, and the private and public magic metadata in full. It keeps any
+its update time, the private and public magic metadata in full, Ente's ML data
-ML data Ente has for the file, except the CLIP embedding, and writes the file's
+for it when there is any, and, for an image (for a live photo, its image), its
-keywords in place of the embedding. For an image (for a live photo, its image),
+original's EXIF and XMP, with its dimensions for a JPEG only; for a video it
-it keeps its original's EXIF and XMP, with its dimensions for a JPEG only. For a
+keeps none of these three. It runs unattended from cron (see "Running the backup
-video it keeps none of these three. It runs unattended from cron (see "Running
+from cron"). A helper subcommand can detect and regenerate missing thumbnails,
-the backup from cron"). A helper subcommand can detect and regenerate missing
+encrypting and uploading them back to the server.
-thumbnails, encrypting and uploading them back to the server.
 
 ## Getting Started
 
@@ -36,11 +35,8 @@ yarn quak login
 # List the user's collections (albums).
 yarn quak collections
 
-# List every file in the account.
+# List files in a collection.
-yarn quak files
+yarn quak files --collection 12345
-
-# List the files in a collection.
-yarn quak files 12345
 
 # Download and decrypt a single file.
 yarn quak get 67890 --out ./photo.jpg
@@ -139,9 +135,9 @@ matters.
 ### Exit codes
 
 | Code | Meaning                                                                                                                                                                                                        |
-| ---- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `0`  | The backup is complete: every original is at its save path, and no file failed.                                                                                                                                |
-| `1`  | The run finished with files in `failures.json` or albums it could not decrypt or write (see "Backup layout"), and its last line says how many, or it stopped on another error, printed as one line `quak: <message>`. The next run tries again. |
+| `1`  | The run finished with files in `failures.json` or albums it could not decrypt or write (see "Backup layout"), or it stopped on another error, printed as one line `quak: <message>`. The next run tries again. |
 | `2`  | Another backup of the same directory is running. This run sent no request and changed nothing.                                                                                                                 |
 | `3`  | There is no usable session: none is saved, the saved one is corrupt, or the server no longer accepts it. Run `quak login` as the user the cron job runs as.                                                    |
 
@@ -372,11 +368,6 @@ quak/
                         backup-metadata: the metadata quak keeps, as JSON
         exif.ts         EXIF read from an image's bytes with exifreader
         mldata-fetch.ts fetch + decrypt per-file ML data
-        clip-keywords.ts
-                        a file's keywords from its CLIP embedding
-        clip-keyword-vectors.ts
-                        Ente's Discover categories with their text
-                        embeddings, written by bin/clip-keyword-vectors
         filename.ts     safe file names from server metadata
         errors.ts       error types shared across layers, and how an error
                         is described
@@ -384,8 +375,6 @@ quak/
         thumbnails.ts   detect + regenerate missing thumbnails
         client.ts       high-level Client class assembled from the above
         cli-commands.ts the CLI's commands as functions returning exit codes
-        cli-log.ts      the CLI's log level, and the one function the
-                        commands write stderr lines through
         cli-output.ts   how the CLI prints a file's title and time
         cli-read.ts     fresh reads for the CLI's read commands
         cli-run.ts      run a command, print its error, exit with its code
@@ -393,9 +382,6 @@ quak/
         index.ts        public library exports
     bin/
         quak.ts         CLI entrypoint (commander.js)
-        clip-keyword-vectors, clip-keyword-vectors.py
-                        write src/clip-keyword-vectors.ts and a test
-                        fixture (see Source attribution)
     examples/
         download-albums.ts
                         download every album's photos and metadata
@@ -467,12 +453,6 @@ A custom API endpoint is configurable for self-hosted servers via the
 constructor option `apiOrigin`. When set, file downloads route through
 `<apiOrigin>/files/download/<id>` instead of the dedicated CDN host.
 
-The constructor option `onRequest` is called once for each request sent, a
-retried request once for each attempt, with its method, its URL and the status
-of the answer or the error the request failed with. The URL of a presigned
-upload is given without its query, which holds the upload's signature. The CLI
-logs each request with `-vv` (see "CLI surface").
-
 Required request headers on every authenticated call:
 
 - `X-Auth-Token`: the decrypted auth token from login.
@@ -549,9 +529,7 @@ each wait is drawn at random below its ceiling. Every other command uses the
 defaults. A library user gets the same budget by passing
 `UNATTENDED_RETRY_OPTIONS` as `ApiClientOptions.retry`. `sleep` and `random` are
 injectable through the same option, which is how the test suite exercises the
-whole policy without waiting. `onRetry`, given there too, is called before each
+whole policy without waiting.
-wait with the error the attempt failed with, the attempt's number and the wait;
-the CLI logs it with `-v` (see "CLI surface").
 
 Two deadlines, renewed for each attempt:
 
@@ -665,12 +643,11 @@ thumbnails), for the user to delete if they want it gone.
 
 ```
 quak [--cache-dir <path>] <command>                       global: local metadata/content cache location
-quak [-v | -vv | -q] <command>                            global: log more on stderr, or only fatal errors
 quak login                                                interactive or QUAK_EMAIL/QUAK_PASSWORD
 quak whoami                                               print logged-in account as JSON
 quak logout                                               end the session, delete it
 quak collections [--json]                                 list all collections
-quak files [collectionID] [--json]                        list files in a collection, or every file
+quak files --collection <id> [--json]                     list files in a collection
 quak get <fileID> [--out path] [--collection]             download and decrypt a file
 quak get-thumb <fileID> [--out] [--collection]            download and decrypt a thumbnail
 quak backup <dir> [--json] [--verify]                     full incremental backup
@@ -684,77 +661,14 @@ library. The read commands — `collections`, `files`, `get`, `get-thumb`,
 `backup-metadata`, `helper list-missing-thumbnails` and
 `helper fix-missing-thumbnails` — force a fresh server round-trip before they
 answer, so they report current account state rather than whatever the cache last
-held. `collections` asks the server for the collection list alone, in one
+held. If that round-trip fails, the command prints the error on one line and
-request, and neither fetches any collection's files nor changes the cache. The
+exits 1, or 3 when the server no longer accepts the saved session (see "Session
-others wait for a refresh. With an empty cache, as on a first run, that refresh
+handling"). An album or file quak cannot decrypt does not fail it; the command
-fetches the files of every collection, one collection after another, and stores
+answers from what did decrypt (see "Default reads vs. fresh reads").
-nothing until it has them all, which on a large account takes a while. Meanwhile
-the command logs a line on stderr for each collection whose files it has
-fetched, such as `Fetched the files of 3 of 120 collections`, with `--json` too;
-`backup` does the same while the refresh it starts with runs. stdout holds only
-the command's output. If that round-trip fails, the command prints the error on
-one line and exits 1, or 3 when the server no longer accepts the saved session
-(see "Session handling"). An album or file quak cannot decrypt does not fail it;
-the command answers from what did decrypt (see "Default reads vs. fresh reads").
 `--cache-dir` overrides where the cache lives; without it each account gets its
 own directory under the per-user cache path.
 
-`-v` (`--verbose`) and `-q` (`--quiet`) set how much quak logs on stderr. Like
+An ID given to `files --collection`, `get`, `get-thumb` or
-`--cache-dir`, they go before or after any command's name. Every line quak
-prints on stderr is a log line at one of six levels, from the quietest: fatal,
-error, warning, info, debug and trace. A run prints the lines at its own level
-and at every quieter one. stdout holds only the command's output, at every
-level.
-
-- Every command that exits non-zero logs a fatal line saying why, such as
-  `quak: <message>`, `Not logged in`, an invalid ID or a collection that does
-  not exist. A command that exits 1 because files or albums failed logs it last,
-  saying how many failed and where to look: `backup` points to `failures.json`
-  and its `FAILED` lines, `backup-metadata` to the `mlDataError` in the JSON of
-  each such file, and `helper fix-missing-thumbnails` to its `Failed files:`
-  list, or to its JSON with `--json`.
-- An error line reports something that failed: the `FAILED` lines that `backup`
-  and `helper fix-missing-thumbnails` log as they work,
-  `ML data of file <id> could not be read` and
-  `ML data request for <n> file(s) failed` from `backup-metadata`,
-  `Could not check <title>` from both thumbnail helpers, and the `Failed files:`
-  list at the end of `backup` and of `helper fix-missing-thumbnails`.
-- A warning reports something that did not fail but needs your attention: after
-  `logout`, that the cache directory still holds decrypted data.
-- Every other line quak logs by default is info.
-
-With `--json`, a command's result on stdout takes the place of its summary on
-stderr: for `backup`, the lines from `--- Backup complete ---` to the end of its
-`Failed files:` list; for `helper list-missing-thumbnails`,
-`No missing thumbnails found.` or `<n> file(s) with missing thumbnails:`; and
-for `helper fix-missing-thumbnails`, the lines from `--- Done ---` to the end of
-its `Failed files:` list. Every other line is logged as it is without `--json`.
-
-- With neither option the level is info: the lines quak prints as it works, such
-  as a refresh's progress, the files a backup fetches, its summary and the files
-  that failed.
-- `-v` raises the level to debug, which adds each retry of a request, with why
-  the attempt failed and how long quak waits before the next, and the start and
-  end of each refresh and each ML data fetch, with the error of one that failed.
-- `-vv` raises it to trace, which adds each request quak sends: its method, its
-  URL and the status of the answer, or the error the request failed with. The
-  URL of an upload of a thumbnail is logged without its query, which holds the
-  upload's signature. More repeats stay at trace, and `--verbose --verbose` is
-  `-vv`.
-- `-q` lowers it to fatal: a run that exits 0 prints nothing on stderr, and one
-  that exits non-zero prints only its fatal lines. The prompts of `login` are
-  not log lines, and `-q` leaves them as they are.
-
-`-q` with `-v` is refused with one line,
-`error: option '-q, --quiet' cannot be used with option '-v, --verbose'`, and
-exit status 1.
-
-`files <collectionID>` lists the files in that collection. `files` with no
-argument lists every file in the account, collection by collection, each file
-once: a file in several collections is listed with the first of them, which is
-its `collectionID` in `--json`.
-
-An ID given to `files`, `get`, `get-thumb` or
 `helper fix-missing-thumbnails --file` is written in decimal digits, no larger
 than 9007199254740991. Anything else, such as `0x10`, `1e3` or `-1`, is refused
 before any request with one line, `Invalid file ID: <arg>` or
@@ -765,26 +679,24 @@ Without `--out`, `get` writes the file to the working directory under its title,
 and `get-thumb` writes the thumbnail there under `thumb_` followed by the title,
 each with unsafe characters replaced. A name over 255 bytes, which most file
 systems refuse, is cut short between two characters before its extension, so the
-extension is kept whenever it fits. An extension too long to leave room for the
+extension is kept whenever it fits.
-name's first character is cut short too, so the name never starts with a dot.
 
 `get` and `get-thumb` resolve the file by ID directly, so `--collection` is
 accepted for backward compatibility but ignored. For a live photo, `get` writes
 its image and its video, each named after the title with its own extension, as
-Ente's clients name them (`IMG_0001.heic` and `IMG_0001.mov`), and each name is
+Ente's clients name them (`IMG_0001.heic` and `IMG_0001.mov`). With
-cut short as above once its own extension is in it. With `--out PATH`, the image
+`--out PATH`, the image is written to `PATH` and the video beside it, with
-is written to `PATH` and the video beside it, with `PATH`'s name and the video's
+`PATH`'s name and the video's extension; a `PATH` with the video's extension is
-extension; a `PATH` with the video's extension is refused.
+refused. `backup-metadata --exif` (alias `--all`) additionally fetches each
-`backup-metadata --exif` (alias `--all`) additionally fetches each file's
+file's original through the cache and records, from it or a live photo's image,
-original through the cache and records, from it or a live photo's image, its XMP
+its XMP metadata, its EXIF metadata and, for a JPEG, its dimensions. EXIF is
-metadata, its EXIF metadata and, for a JPEG, its dimensions. EXIF is read with
+read with [exifreader](https://github.com/mattiasw/ExifReader) from any image
-[exifreader](https://github.com/mattiasw/ExifReader) from any image format it
+format it reads, JPEG, HEIC/HEIF, AVIF, PNG and WebP among them. The record's
-reads, JPEG, HEIC/HEIF, AVIF, PNG and WebP among them. The record's `exif` field
+`exif` field is exifreader's EXIF tag output: each tag by name, with its
-is exifreader's EXIF tag output: each tag by name, with its `value`,
+`value`, `description` and `computed` value. An EXIF block exifreader finds but
-`description` and `computed` value. An EXIF block exifreader finds but reads no
+reads no tag from is recorded, base64, as `exifRaw`, with the reason in
-tag from is recorded, base64, as `exifRaw`, with the reason in `exifError`.
+`exifError`. `collections`, `files`, `backup`, `helper list-missing-thumbnails`
-`collections`, `files`, `backup`, `helper list-missing-thumbnails` and
+and `helper fix-missing-thumbnails` take `--json` for machine-readable output.
-`helper fix-missing-thumbnails` take `--json` for machine-readable output.
 
 `backup --verify` also hashes the originals already in the backup and replaces
 any that do not match the content hash Ente records; one it cannot replace stays
@@ -792,18 +704,16 @@ as it was and goes into `failures.json` (see "Backup layout").
 
 `backup-metadata <dir>` writes `account.json` and, for each collection, a
 directory `collections/<id>-<name>/` holding `_collection.json` and a
-`<fileID>.json` for each of its files. Each `<fileID>.json` holds the file's ML
+`<fileID>.json` for each of its files. The collection's name has unsafe
-data and keywords as `quak backup` writes them (see "Backup layout"). The
+characters replaced and is cut short between two characters so that the
-collection's name has unsafe characters replaced and is cut short between two
+directory's name fits in 255 bytes; the ID keeps the directories apart.
-characters so that the directory's name fits in 255 bytes; the ID keeps the
-directories apart.
 
 `backup-metadata` fetches ML data in requests of up to 200 files. When a request
 fails, the error is logged, each of its files is written with the reason in an
 `mlDataError` field instead of `mlData`, and the dump goes on. A file whose ML
 data does not decrypt, gunzip or parse is logged and written the same way, with
 why in `mlDataError`. The exit code is non-zero if any file was written with
-`mlDataError`, and the last line then says how many were.
+`mlDataError`.
 
 `helper fix-missing-thumbnails` regenerates thumbnails for JPEG images only,
 because the bundled decoder (`jpeg-js`) decodes only JPEG. A non-JPEG image
@@ -829,11 +739,11 @@ the smallest does not.
                                     below)
         YYYY-MM-DD.<fileID>.json    the file's basic metadata fields quak
                                     keeps, its update time, its private and
-                                    public magic metadata, its ML data and
+                                    public magic metadata, its ML data, and,
-                                    keywords, and, for an image (for a live
+                                    for an image (for a live photo, its
-                                    photo, its image), its original's EXIF
+                                    image), its original's EXIF and XMP, with
-                                    and XMP, with dimensions for a JPEG
+                                    dimensions for a JPEG only; none of these
-                                    only; none of these three for a video
+                                    three for a video
         YYYY-MM-DD.<fileID>.livephoto.json
                                     which of a live photo's two files is which
     collections/
@@ -864,51 +774,20 @@ JSON holds its `id`, `collectionID`, `ownerID`, `metadata` and `updationTime`,
 and its `magicMetadata` and `pubMagicMetadata` when it has them. Update times
 are in microseconds, as Ente records them.
 
-A file's JSON holds Ente's ML data for it as `mlData`, such as the faces Ente
+A file's JSON holds Ente's ML data for it (its faces and its CLIP embedding) as
-found, without its CLIP embedding. It holds `keywords` in place of the
+`mlData`, the same payload `backup-metadata` writes; a file Ente has no ML data
-embedding.
+for has no `mlData`. The backup waits for the library's ML data fetch to finish
-
+before it writes the JSON files. If that fetch fails, each file whose ML data is
-The Discover section of Ente's photos app has 16 categories:
+not in the cache gets the reason in `mlDataError` instead and counts as failed,
-
+and the next run fetches it again. The same goes for a file with no ML data in
-- Identity (no videos)
+the cache whose ML data the server sent but quak could not decrypt, gunzip or
-- Screenshots (no videos)
+parse. Its `mlDataError` says why, and `failures.json` records it with an error
-- QR Codes (no videos)
+starting `ML data: `. quak keeps that reason in memory only and caches nothing
-- Receipts
+for the file, so the next run asks for its ML data again. An ML data fetch that
-- Notes
+fails, such as one the library's refresh starts while the backup writes the JSON
-- Memes
+files, leaves the reasons as the last fetch that succeeded left them. The JSON
-- Visiting Cards (no videos)
+files are rewritten on every run, so ML data that arrived since the last run
-- Babies
+appears.
-- Pets
-- Selfies
-- Wallpapers (no videos)
-- Food
-- Celebrations
-- Sunset
-- Hills
-- Greenery
-
-A file's keywords are the titles of the categories it falls in. A file's score
-for a category is the cosine similarity of its CLIP embedding and the text
-embedding of the category's query. As in Ente's app, the file falls in the
-category when that score is at least the category's minimum score. A video never
-falls in a category marked "no videos". The keywords are listed highest score
-first.
-
-A file with no ML data has neither `mlData` nor `keywords`. A file whose ML data
-holds no usable CLIP embedding has no `keywords`. `backup-metadata` writes both
-fields the same way.
-
-The backup waits for the library's ML data fetch to finish before it writes the
-JSON files. If that fetch fails, each file whose ML data is not in the cache
-gets the reason in `mlDataError` instead and counts as failed, and the next run
-fetches it again. The same goes for a file with no ML data in the cache whose ML
-data the server sent but quak could not decrypt, gunzip or parse. Its
-`mlDataError` says why, and `failures.json` records it with an error starting
-`ML data: `. quak keeps that reason in memory only and caches nothing for the
-file, so the next run asks for its ML data again. An ML data fetch that fails,
-such as one the library's refresh starts while the backup writes the JSON files,
-leaves the reasons as the last fetch that succeeded left them. The JSON files
-are rewritten on every run, so ML data that arrived since the last run appears.
 
 A file's JSON holds, as `imageMetadata`, what `backup-metadata --exif` records
 from its original, or from a live photo's image: `format`, `width` and `height`
@@ -931,8 +810,8 @@ reads vs. fresh reads") goes into `failures.json` with an error that starts
 `could not be decrypted:` and gives the reason. If a copy of it in another album
 decrypted, it does not: its original is stored from that copy, and the album
 where it does not decrypt neither links nor lists it. An album the library could
-not decrypt has no name quak can read and no files it can list. `quak backup`
+not decrypt has no name quak can read and no files it can list. A run without
-prints one line for it on stderr,
+`--json` prints one line for it,
 `FAILED album <id>: could not be decrypted: <reason>`, and `--json` and the
 `BackupResult` list its ID in `undecryptableAlbums`. Such a file in
 `failures.json`, or such an album, keeps the exit code at 1, run after run,
@@ -977,16 +856,15 @@ gets its ID added as well: beside an album `x`, whose JSON is `x.json`, an album
 named `x.json` gets the directory `x.json (12)/`. A name too long for a file
 name, which most file systems limit to 255 bytes, gets its ID added too. A name
 with its ID added is cut short between two characters in the part before the ID,
-just far enough that it fits. When a symlink's extension leaves no room for the
+just far enough that it fits. When a symlink's extension alone leaves no room
-ID and the first character of the name, the extension is cut short, and the part
+for the ID, the extension is cut short and the part before the ID keeps only the
-before the ID keeps that character and any bytes the cut leaves over. A
+bytes that cut leaves over. A collection's directory name also leaves room for
-collection's directory name also leaves room for the `.json` its JSON adds. IDs
+the `.json` its JSON adds. IDs never change, so a name stays the same from run
-never change, so a name stays the same from run to run until such a clash
+to run until such a clash appears or goes away.
-appears or goes away.
 
 A collection whose directory or JSON cannot be written, such as one whose
 directory name is taken by a file you put in `collections/`, does not stop the
-run. `quak backup` prints `FAILED album <name>: <reason>` for it on stderr,
+run. A run without `--json` prints `FAILED album <name>: <reason>` for it,
 `--json` and the `BackupResult` list its ID in `failedAlbums`, and the exit code
 is 1. The other collections and `failures.json` are still written.
 
@@ -1096,11 +974,7 @@ loop, and resolves to a `Library`. On an empty cache it awaits the first
 refresh, so it opens onto the account's data whenever the server is reachable;
 if that refresh fails, it opens with no data and records the error in
 `lib.status()`. On an existing cache it returns immediately and refreshes in the
-background, so an unreachable server does not block opening. With
+background, so an unreachable server does not block opening.
-`refreshOnOpen: false` it starts no refresh and returns at once onto what the
-cache holds, empty or not; a refresh then starts only when `fresh()` or
-`lib.backup()` asks, or the background timer fires. The CLI's read commands open
-it so (see "CLI surface").
 
 `LibraryOptions`:
 
@@ -1110,7 +984,6 @@ it so (see "CLI surface").
 | `cacheDirectory`         | `quak/<userID>` under the per-user cache directory | where `metadata.json` and the content cache live                     |
 | `downloadDirectory`      | `photos` in the working directory                  | root of the save paths; an original stored there counts as cached    |
 | `refreshIntervalSeconds` | `3`                                                | background refresh cadence; `Infinity` for no background timer       |
-| `refreshOnOpen`          | `true`                                             | start a refresh as the library opens                                 |
 | `precacheThumbnails`     | `true`                                             | prefetch every thumbnail, newest first                               |
 | `precacheOriginals`      | `true`                                             | prefetch the favorites album and the latest-window originals         |
 | `precacheOriginalsDays`  | `7`                                                | length in days of that latest window                                 |
@@ -1124,14 +997,6 @@ it so (see "CLI surface").
 The default `downloadDirectory` is resolved against the working directory once,
 when the library opens; `lib.downloadDirectory` holds the result.
 
-`onProgress` receives a `RefreshEvent` with status `"started"` as a refresh, an
-ML data fetch or a precache sweep starts, and `"done"` or `"failed"` as it ends.
-In between, a refresh sends `"progress"` after each collection whose files it
-fetched, with `fetched`, how many collections it has fetched the files of so
-far, and `total`, how many it will. A refresh fetches the files of each
-collection that is new or changed since the cache's copy, so on an empty cache
-it fetches those of every collection.
-
 Concurrency is set through `pools`: construct
 `new RequestPools({ metadataConcurrency, contentConcurrency, thumbnailConcurrency })`
 and pass it. The three pools default to 10 / 5 / 25 (see Request pools below).
@@ -1171,15 +1036,6 @@ rejects the caller (default reads stay silent and keep serving the last good
 copy). The CLI's read commands use fresh reads (issue
 https://git.eeqj.de/sneak/quak/issues/75).
 
-`await lib.freshCollections()` is the fresh read of the collection list alone:
-one collections request, answered with every live collection that decrypts, as
-the `Collection` objects `listCollections()` returns, in the server's order. It
-fetches no collection's files and stores nothing, not even the list: a refresh
-fetches a collection's files only when the collection is new or has changed
-since the stored copy, so a collection stored without its files would never get
-them. `quak collections` uses it (issue
-https://git.eeqj.de/sneak/quak/issues/210).
-
 An album or file in the server's answer that quak cannot decrypt, or whose
 metadata is not JSON, does not fail the refresh. The refresh leaves it out, an
 album with all its files, and drops any older copy the cache held, so reads
@@ -1312,18 +1168,18 @@ photos newest first). `lib.subscribe({ onChange })` delivers a `LibraryChange`
   not already at its save path there as `photo.download()` does (and, with
   `includeThumbnails`, fetches thumbnails) through the content cache, waits for
   an ML data fetch, and rebuilds the on-disk backup tree with a durable failure
-  ledger. Each file's JSON holds its ML data and keywords. An image's JSON also
+  ledger. Each file's JSON holds its ML data and, for an image (for a live
-  holds the EXIF and XMP of its original, and its dimensions if it is a JPEG. A
+  photo, its image), its original's EXIF and XMP, with its dimensions for a JPEG
-  live photo's JSON holds these for its image. A video's JSON holds no EXIF, XMP
+  only; a video's JSON holds none of these three. A fetched original is written
-  or dimensions. A fetched original is written straight to its save path and not
+  straight to its save path and not into the cache, which then counts it as
-  into the cache, which then counts it as present; one the cache already held is
+  present; one the cache already held is copied from there. `BackupOptions`:
-  copied from there. `BackupOptions`: `downloadDirectory` (falls back to the
+  `downloadDirectory` (falls back to the library's), `includeOriginals` (default
-  library's), `includeOriginals` (default `true`), `includeThumbnails` (default
+  `true`), `includeThumbnails` (default `false`), `onlyAlbumNames`, `verify`
-  `false`), `onlyAlbumNames`, `verify` (default `false`), `onProgress`, and
+  (default `false`), `onProgress`, and `lock`. See Backup layout above for the
-  `lock`. See Backup layout above for the tree it writes, and for the albums
+  tree it writes, and for the albums `BackupResult` lists in
-  `BackupResult` lists in `undecryptableAlbums` and `failedAlbums`. Whether the
+  `undecryptableAlbums` and `failedAlbums`. Whether the backup took the lock or
-  backup took the lock or its caller did, once the lock is lost the backup
+  its caller did, once the lock is lost the backup rejects with
-  rejects with `lost the lock on <dir>: <reason>` before it starts another file.
+  `lost the lock on <dir>: <reason>` before it starts another file.
 
 ### Request pools
 
@@ -1406,14 +1262,6 @@ is rewritten in TypeScript in this repository. Protocol fidelity is verified
 against the upstream implementations in `web/packages/base/`,
 `mobile/apps/photos/lib/`, and `cli/`.
 
-The keywords come from Ente too. `src/clip-keyword-vectors.ts` holds the
-Discover categories of Ente's photos app, from
-`mobile/apps/photos/assets/discover.json`, each with its query's text embedding
-from Ente's CLIP text model. `bin/clip-keyword-vectors` writes that file and the
-CLIP embedding of a public-domain photo that the tests use. It runs Ente's
-models in Docker, with every download pinned by sha256. It is run by hand only,
-followed by `make fmt`.
-
 ## For LLMs
 
 If you are an LLM agent working on this repository, read and follow these

TODO.md

@@ -17,75 +17,26 @@ pre-1.0
 
 # Next Step
 
-No bug is open, and no change sneak asked for is open. The check of quak against
+No bug is open. The check of quak against a live Ente account,
-a live Ente account, https://git.eeqj.de/sneak/quak/issues/187, needs an account
+https://git.eeqj.de/sneak/quak/issues/187, needs an account only sneak has, so
-only sneak has, so it waits on him.
+it waits on him.
 
 Tagging and releases are decided by sneak alone, and happen only when he
 declares one.
 
 # Completed Steps
 
-- 2026-10-22: The JSON `quak backup` and `quak backup-metadata` write for a file
-  holds `keywords` in place of the CLIP embedding in its ML data
-  (https://git.eeqj.de/sneak/quak/issues/218). The keywords are the titles of
-  the Discover categories of Ente's photos app that the file falls in, by the
-  app's rule: the cosine similarity of the file's CLIP embedding and the text
-  embedding of a category's query is at least the category's minimum score, and
-  videos stay out of the categories that leave them out. `src/clip-keywords.ts`
-  applies the rule. `src/clip-keyword-vectors.ts` holds the 16 categories with
-  their text embeddings. `bin/clip-keyword-vectors` writes it with Ente's CLIP
-  text model, and writes the CLIP embedding of a public-domain photo of a sunset
-  that the tests use.
-
-- 2026-10-18: `-v`/`--verbose` raises the CLI's log level once for each repeat,
-  and `-q`/`--quiet` prints only fatal errors
-  (https://git.eeqj.de/sneak/quak/issues/212). The levels are fatal, error,
-  warning, info, debug and trace; the default is info, everything quak printed
-  on stderr before, `-v` gives debug and `-vv` trace. `src/cli-log.ts` holds the
-  level and the log the commands write stderr lines through. Debug adds each
-  retry, which `withRetry` reports through the new `onRetry`, and the start and
-  end of each refresh and ML data fetch; trace adds each request, which
-  `ApiClient` reports through the new `onRequest`. `--json` no longer keeps the
-  progress lines off stderr, so `backup` and `--json` runs log a refresh's
-  progress too. Every line that reports a failed file or album is at error,
-  which the progress callbacks of `backup`, `backup-metadata` and the thumbnail
-  helpers now say, and a command that exits 1 because files or albums failed
-  ends with one fatal line saying how many and where to look.
-
-- 2026-10-18: `quak files` takes the collection ID as an optional argument
-  instead of the `--collection` option, which is gone
-  (https://git.eeqj.de/sneak/quak/issues/211). With no argument it lists every
-  file in the account once, collection by collection; a file in several
-  collections is listed with the first of them, which is its `collectionID` in
-  `--json`. The fresh read in `src/cli-read.ts` does this.
-
 - 2026-10-18: Names quak builds from an album name or a title fit in a file name
-  (https://git.eeqj.de/sneak/quak/issues/205). `shortenKeepingExtension` in
+  (issue 205). `shortenKeepingExtension` in `src/filename.ts` cuts a name short
-  `src/filename.ts` cuts a name short to a number of bytes, keeping its
+  to a number of bytes, keeping its extension when it fits, and can put text
-  extension when it fits and always its first character, and can put text right
+  right before the extension; the backup's `withID` uses it for an ID. The
-  before the extension; the backup's `withID` uses it for an ID.
+  default names of `quak get`, `quak get-thumb`, `downloadFile` and
-  `defaultFileName` there gives the name a file is saved under when the caller
+  `downloadThumbnail` are cut short with it to 255 bytes, `thumb_` included.
-  gives no path: a prefix such as `thumb_` and the title with unsafe characters
+  `backup-metadata` cuts an album's name short so that its folder,
-  replaced, cut short with it to 255 bytes, and, for a live photo's image or
+  `<id>-<name>`, fits in 255 bytes. `safeExtension` gives `.bin` for an
-  video, with that part's own extension before the cut. `quak get`,
-  `quak get-thumb`, `downloadFile` and `downloadThumbnail` use it without
-  `--out` or `outPath`. `backup-metadata` cuts an album's name short so that its
-  folder, `<id>-<name>`, fits in 255 bytes. `safeExtension` gives `.bin` for an
   extension of more than 16 letters and digits, so a save path's name always
   fits.
 
-- 2026-10-18: `quak collections` no longer waits for the files of every
-  collection (issue 210). On an empty cache it opened its library with a refresh
-  that fetched and decrypted the files of each collection in turn, printing
-  nothing and storing nothing until all were done, so on a large account it
-  seemed to hang. It now reads the collection list alone through the new
-  `lib.freshCollections()`, one request that stores nothing. The read commands
-  open their library with the new `refreshOnOpen: false`, so each makes only the
-  refresh it asks for. A refresh sends a `"progress"` event after each
-  collection whose files it fetched, and the commands that wait on one print it
-  on stderr, except with `--json`.
-
 - 2026-10-16: ML data the server sends that does not decrypt, gunzip or parse is
   no longer taken for no ML data (issue 198). `fetchMLDataBatch` returns why for
   each such file beside the payloads; ML data that parses to something other

bin/clip-keyword-vectors

@@ -1,31 +0,0 @@
-#!/bin/sh
-# Writes src/clip-keyword-vectors.ts and test/clip-keywords-sunset.json by
-# running bin/clip-keyword-vectors.py in a Python image pinned by digest, with
-# its packages pinned by hash. Run it by hand from a checkout, then `make fmt`;
-# no gate runs it. Besides the Python image, it downloads about 265 MB, most of
-# it Ente's two CLIP models.
-set -eu
-
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
-
-# python:3.13-slim (Python 3.13.17 on Debian 13.7), 2026-10-21. The wheels
-# below are the ones for this image on linux/amd64.
-IMAGE=python@sha256:57b29a7c050c4e679e4bea572e14b3965cf4b5839de2da49d55e49ffc4024f39
-
-main() {
-    cd "$ROOT"
-    docker run --rm -i --platform linux/amd64 \
-        --user "$(id -u):$(id -g)" -e HOME=/tmp \
-        -v "$ROOT:/repo" -w /repo "$IMAGE" sh -c '
-            python -m venv /tmp/venv &&
-            /tmp/venv/bin/pip install --quiet --disable-pip-version-check \
-                --no-cache-dir --no-deps --require-hashes -r /dev/stdin &&
-            /tmp/venv/bin/python bin/clip-keyword-vectors.py' <<'EOF'
-numpy==2.5.3 --hash=sha256:a5fa86b80fd24bcd1aff83ad23be44ea323de3f787be8f8b15d4a65621e25321
-onnxruntime==1.30.0 --hash=sha256:86f940afc801ea9681a4da8af84fbe95e1d9ea7d80903952cc1bfad54faad38f
-pillow==12.3.0 --hash=sha256:0847a763afefb695bc912d7c131e7e0632d4edc1d8698f58ddabec8e46b8b6d3
-tokenizers==0.23.2 --hash=sha256:41c2f84d172449b4dadb9cdc508e3e364076613c35b16e76ecfe47a60d1e3305
-EOF
-}
-
-main "$@"

bin/clip-keyword-vectors.py

@@ -1,158 +0,0 @@
-"""Write src/clip-keyword-vectors.ts and test/clip-keywords-sunset.json.
-
-bin/clip-keyword-vectors runs this in a pinned Python image. It downloads
-Ente's Discover list, Ente's CLIP text and image models, the CLIP tokenizer
-and a public-domain photo of a sunset, checks each against its sha256, and
-writes:
-
-- src/clip-keyword-vectors.ts: each Discover category of Ente's photos app,
-  with the text embedding Ente's CLIP text model gives its query;
-- test/clip-keywords-sunset.json: the CLIP embedding Ente's image model gives
-  the photo, prepared as Ente's apps prepare a photo.
-
-Both embeddings are scaled to length 1, as Ente's apps scale them.
-"""
-
-import hashlib
-import io
-import json
-import urllib.request
-
-import numpy as np
-import onnxruntime
-from PIL import Image, ImageOps
-from tokenizers import Tokenizer
-
-ENTE_COMMIT = "f5ad70a860ed25d0c8057b0efb4bd6eaefe4b0c5"
-DISCOVER_PATH = "mobile/apps/photos/assets/discover.json"
-DISCOVER_URL = (
-    f"https://raw.githubusercontent.com/ente-io/ente/{ENTE_COMMIT}/{DISCOVER_PATH}"
-)
-DISCOVER_SHA256 = "cf70ac7116b592f7921ca4cf67cdbb421a8e6b287fbe44b2be678b8d198e5c24"
-
-TEXT_MODEL = "mobileclip_s2_text_opset18_quant.onnx"
-TEXT_MODEL_SHA256 = "d92f33dfcff83077fc2e0d3414250710efbb51795dfd89767bdbefb5fdc47322"
-IMAGE_MODEL = "mobileclip_s2_image_gelu_opset20.onnx"
-IMAGE_MODEL_SHA256 = "205a430af825e501c5138e5bb9abea942482a7a4fd4a680e98e47cf0830dce7e"
-
-# The CLIP tokenizer Hugging Face publishes for OpenAI's CLIP. Its vocabulary
-# and merges are those of bpe_simple_vocab_16e6.txt, the vocabulary Ente's
-# apps tokenize with.
-TOKENIZER_URL = (
-    "https://huggingface.co/openai/clip-vit-base-patch32/resolve/"
-    "3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268/tokenizer.json"
-)
-TOKENIZER_SHA256 = "b556ac8c99757ffb677208af34bc8c6721572114111a6e0aaf5fa69ff0b8d842"
-
-# "Sunset off the Massachusetts coast", a NOAA photo in the public domain:
-# https://commons.wikimedia.org/wiki/File:Sunset_off_the_Massachusetts_coast_-_NOAA.jpg
-PHOTO_URL = (
-    "https://upload.wikimedia.org/wikipedia/commons/d/db/"
-    "Sunset_off_the_Massachusetts_coast_-_NOAA.jpg"
-)
-PHOTO_SHA256 = "be62f3289c9bf7b75af68cd6978021d54e8a531d5d4cc493f6e9fbf5e1ab74d3"
-
-# Ente's text model takes 77 token ids, padded with 0; its image model takes
-# a 256x256 RGB image.
-TOKEN_COUNT = 77
-IMAGE_SIZE = 256
-
-
-def download(url, sha256):
-    # Wikimedia refuses requests without a User-Agent.
-    request = urllib.request.Request(url, headers={"User-Agent": "quak"})
-    with urllib.request.urlopen(request) as response:
-        data = response.read()
-    digest = hashlib.sha256(data).hexdigest()
-    if digest != sha256:
-        raise SystemExit(f"{url} has sha256 {digest}, not {sha256}")
-    return data
-
-
-def ente_model(name, sha256):
-    return onnxruntime.InferenceSession(
-        download(f"https://models.ente.com/{name}", sha256),
-        providers=["CPUExecutionProvider"],
-    )
-
-
-def run(session, tensor):
-    (output,) = session.run(None, {session.get_inputs()[0].name: tensor})
-    embedding = output[0]
-    return embedding / np.linalg.norm(embedding)
-
-
-def text_embedding(session, tokenizer, query):
-    ids = tokenizer.encode(query).ids
-    ids += [0] * (TOKEN_COUNT - len(ids))
-    return run(session, np.array([ids], dtype=np.int32))
-
-
-def image_embedding(session, photo):
-    image = ImageOps.exif_transpose(Image.open(io.BytesIO(photo))).convert("RGB")
-    # Scale to cover IMAGE_SIZE x IMAGE_SIZE and crop the centre.
-    square = ImageOps.fit(image, (IMAGE_SIZE, IMAGE_SIZE), Image.Resampling.BILINEAR)
-    pixels = np.asarray(square, dtype=np.float32) / 255
-    return run(session, pixels.transpose(2, 0, 1)[np.newaxis])
-
-
-def numbers(embedding):
-    return ", ".join(str(value) for value in embedding)
-
-
-def write_categories(prompts, embeddings):
-    lines = [
-        "// Written by bin/clip-keyword-vectors; do not edit by hand.",
-        "//",
-        "// The Discover categories of Ente's photos app, in their order, from",
-        f"// {DISCOVER_PATH} in https://github.com/ente-io/ente",
-        f"// at commit {ENTE_COMMIT}. Each has the text",
-        f"// embedding Ente's CLIP text model ({TEXT_MODEL})",
-        "// gives its query, scaled to length 1. `showVideo` is false for a category",
-        "// that leaves out videos.",
-        "",
-        "export const DISCOVER_CATEGORIES = [",
-    ]
-    for prompt, embedding in zip(prompts, embeddings):
-        lines += [
-            "    {",
-            f"        title: {json.dumps(prompt['title'])},",
-            f"        query: {json.dumps(prompt['query'])},",
-            f"        minScore: {json.dumps(prompt['minScore'])},",
-            f"        showVideo: {json.dumps(prompt.get('showVideo', True))},",
-            f"        textEmbedding: [{numbers(embedding)}],",
-            "    },",
-        ]
-    lines.append("];")
-    with open("src/clip-keyword-vectors.ts", "w", encoding="utf-8") as file:
-        file.write("\n".join(lines) + "\n")
-
-
-def write_fixture(embedding):
-    with open("test/clip-keywords-sunset.json", "w", encoding="utf-8") as file:
-        file.write(
-            "{\n"
-            f'    "photo": {json.dumps(PHOTO_URL)},\n'
-            f'    "sha256": {json.dumps(PHOTO_SHA256)},\n'
-            f'    "embedding": [{numbers(embedding)}]\n'
-            "}\n"
-        )
-
-
-def main():
-    prompts = json.loads(download(DISCOVER_URL, DISCOVER_SHA256))["prompts"]
-    tokenizer = Tokenizer.from_str(
-        download(TOKENIZER_URL, TOKENIZER_SHA256).decode("utf-8")
-    )
-    text_model = ente_model(TEXT_MODEL, TEXT_MODEL_SHA256)
-    embeddings = [
-        text_embedding(text_model, tokenizer, prompt["query"]) for prompt in prompts
-    ]
-    write_categories(prompts, embeddings)
-
-    image_model = ente_model(IMAGE_MODEL, IMAGE_MODEL_SHA256)
-    write_fixture(image_embedding(image_model, download(PHOTO_URL, PHOTO_SHA256)))
-
-
-if __name__ == "__main__":
-    main()

bin/quak.ts

@@ -2,9 +2,8 @@
 
 import { stdout, stderr } from "node:process";
 import { input, password } from "@inquirer/prompts";
-import { Command, Option } from "commander";
+import { Command } from "commander";
 import envPaths from "env-paths";
-import { logLevel, logRequests, stderrLog, type Log } from "../src/cli-log.js";
 import { init } from "../src/crypto/index.js";
 import {
     type CliContext,
@@ -30,9 +29,6 @@ const paths = envPaths("quak", { suffix: "" });
 
 const program = new Command();
 
-// Program options, so they are taken before or after any command's name.
-// `-v` counts its repeats, the way commander's documentation counts a repeated
-// option.
 program
     .name("quak")
     .description("CLI for the Ente end-to-end encrypted photo service")
@@ -41,46 +37,21 @@ program
         "--cache-dir <path>",
         "Directory for the local metadata/content cache " +
             "(default: the per-user cache directory)",
-    )
+    );
-    .option(
-        "-v, --verbose",
-        "Log more on stderr: debug lines with -v, trace lines too with -vv",
-        (_value: string, previous: number) => previous + 1,
-        0,
-    )
-    .addOption(
-        new Option(
-            "-q, --quiet",
-            "Print nothing on stderr but the error a failing command exits with",
-        ).conflicts("verbose"),
-    )
-    .configureHelp({ showGlobalOptions: true });
-
-interface ProgramOptions {
-    cacheDir?: string;
-    verbose: number;
-    quiet?: boolean;
-}
-
-// The log for this run, at the level `-v` and `-q` ask for.
-const log = (): Log => {
-    const { verbose, quiet } = program.opts<ProgramOptions>();
-    return stderrLog(stderr, logLevel(verbose, quiet ?? false));
-};
 
 const context = (): CliContext => ({
     stdout,
-    log: log(),
+    stderr,
     sessionDir: paths.data,
-    cacheDir: program.opts<ProgramOptions>().cacheDir,
+    cacheDir: program.opts<{ cacheDir?: string }>().cacheDir,
-    loadSession: (path) => loadSession(path, logRequests(log())),
+    loadSession,
-    login: (opts) => Client.login({ ...opts, apiOptions: logRequests(log()) }),
+    login: (opts) => Client.login(opts),
     prompt: (message) => input({ message }),
     promptSecret: (message) => password({ message, mask: true }),
 });
 
 const run = (command: Promise<number>): Promise<void> =>
-    runCommand(command, stdout, stderr, log(), (code) => process.exit(code));
+    runCommand(command, stdout, stderr, (code) => process.exit(code));
 
 program
     .command("login")
@@ -107,15 +78,14 @@ program
 
 program
     .command("files")
-    .description("List the files in a collection, or every file in the account")
+    .description("List files in a collection")
-    .argument(
+    .requiredOption(
-        "[collectionID]",
+        "--collection <id>",
-        "Collection ID (from `quak collections`); without it, every file " +
+        "Collection ID (from `quak collections`)",
-            "is listed once",
     )
     .option("--json", "Output as JSON array")
-    .action((collectionID: string | undefined, opts: { json?: boolean }) =>
+    .action((opts: { collection: string; json?: boolean }) =>
-        run(filesCommand(context(), collectionID, opts)),
+        run(filesCommand(context(), opts)),
     );
 
 program
@@ -172,10 +142,7 @@ program
                 {
                     ...context(),
                     loadSession: (path) =>
-                        loadSession(
+                        loadSession(path, { retry: UNATTENDED_RETRY_OPTIONS }),
-                            path,
-                            logRequests(log(), UNATTENDED_RETRY_OPTIONS),
-                        ),
                 },
                 dir,
                 opts,

src/api/client.ts

@@ -36,15 +36,6 @@ export interface ApiClientOptions {
     retry?: RetryOptions;
     requestTimeoutMs?: number;
     downloadTimeoutMs?: number;
-    // Called once for each request sent, with the status of its response or
-    // the error it failed with, for a caller that logs requests. A request
-    // that is retried is reported once for each attempt.
-    onRequest?: (request: {
-        method: string;
-        url: string;
-        status?: number;
-        error?: unknown;
-    }) => void;
 }
 
 export interface StreamOptions {
@@ -168,7 +159,6 @@ export class ApiClient {
     private readonly retry: ResolvedRetryOptions;
     private readonly requestTimeoutMs: number;
     private readonly downloadTimeoutMs: number;
-    private readonly onRequest: NonNullable<ApiClientOptions["onRequest"]>;
     private token: string | undefined;
 
     constructor(opts?: ApiClientOptions) {
@@ -190,7 +180,6 @@ export class ApiClient {
             opts?.requestTimeoutMs ?? DEFAULT_REQUEST_TIMEOUT_MS;
         this.downloadTimeoutMs =
             opts?.downloadTimeoutMs ?? DEFAULT_DOWNLOAD_TIMEOUT_MS;
-        this.onRequest = opts?.onRequest ?? (() => {});
         this.token = opts?.authToken;
     }
 
@@ -225,33 +214,6 @@ export class ApiClient {
         return h;
     }
 
-    // Send one request and report it to `onRequest`, with the status of its
-    // response or the error it failed with. `reportedURL` is the URL given to
-    // `onRequest`, when that must not be the one sent.
-    private async send(
-        url: string,
-        init: RequestInit & { method: string },
-        reportedURL = url,
-    ): Promise<Response> {
-        let resp: Response;
-        try {
-            resp = await this._fetch(url, init);
-        } catch (err) {
-            this.onRequest({
-                method: init.method,
-                url: reportedURL,
-                error: err,
-            });
-            throw err;
-        }
-        this.onRequest({
-            method: init.method,
-            url: reportedURL,
-            status: resp.status,
-        });
-        return resp;
-    }
-
     private async throwIfError(resp: Response): Promise<void> {
         if (resp.ok) return;
         const requestID = resp.headers.get("x-request-id") ?? undefined;
@@ -295,7 +257,7 @@ export class ApiClient {
         const url = buildURL(this.apiOrigin, path, query);
         // A GET changes nothing, so it is retried under the full policy.
         return withRetry(async () => {
-            const resp = await this.send(url, {
+            const resp = await this._fetch(url, {
                 method: "GET",
                 headers: this.headers(),
                 signal: AbortSignal.timeout(this.requestTimeoutMs),
@@ -318,7 +280,7 @@ export class ApiClient {
         // 3xx status, which is not retried.
         return withRetry(
             async () => {
-                const resp = await this.send(url, {
+                const resp = await this._fetch(url, {
                     method: "POST",
                     headers: this.headers({
                         "Content-Type": "application/json",
@@ -359,13 +321,8 @@ export class ApiClient {
         // object at one key in one request, so replaying it either overwrites
         // the same bytes or lands them for the first time. There is no partial
         // state to protect, hence the full policy rather than the POST rule.
-        // It is reported without its query, which holds the upload's
-        // signature: a log keeps what it is given.
-        const { origin, pathname } = new URL(presignedURL);
         await withRetry(async () => {
-            const resp = await this.send(
+            const resp = await this._fetch(presignedURL, {
-                presignedURL,
-                {
                 method: "PUT",
                 headers: {
                     "Content-Type": "application/octet-stream",
@@ -373,9 +330,7 @@ export class ApiClient {
                 },
                 body: data,
                 signal: AbortSignal.timeout(this.requestTimeoutMs),
-                },
+            });
-                origin + pathname,
-            );
             if (!resp.ok) {
                 // An ApiError, not a bare Error: without the status on the
                 // error the upload path cannot be classified at all, and a
@@ -393,7 +348,7 @@ export class ApiClient {
         // Same replay and redirect rules as `postJSON`, for the same reasons.
         return withRetry(
             async () => {
-                const resp = await this.send(url, {
+                const resp = await this._fetch(url, {
                     method: "PUT",
                     headers: this.headers({
                         "Content-Type": "application/json",
@@ -439,7 +394,7 @@ export class ApiClient {
             // headers, when no bytes have arrived either.
             const deadline = idleDeadline(this.downloadTimeoutMs);
             try {
-                const resp = await this.send(url, {
+                const resp = await this._fetch(url, {
                     method: "GET",
                     headers: this.headers(),
                     signal: deadline.signal,

src/backup.ts

@@ -14,9 +14,9 @@
 //         YYYY/YYYY-MM/YYYY-MM-DD/
 //             YYYY-MM-DD.<fileID>.<ext>    the decrypted bytes (the save path)
 //             YYYY-MM-DD.<fileID>.json     per-file metadata sidecar, with
-//                                          the file's ML data, its
+//                                          the file's ML data and its
-//                                          keywords, and its original's
+//                                          original's EXIF, XMP and
-//                                          EXIF, XMP and dimensions
+//                                          dimensions
 //         collections/<name>/<title>       symlink to the original
 //         collections/<name>.json          per-collection metadata
 //         account.json                     the account's email and user ID
@@ -77,7 +77,6 @@ import { readFile } from "node:fs/promises";
 import { dirname, extname, join, relative, resolve } from "node:path";
 import lockfile from "proper-lockfile";
 
-import { clipKeywords } from "./clip-keywords.js";
 import { removeLeftoverTempFiles } from "./download/index.js";
 import { describeError } from "./errors.js";
 import {
@@ -102,10 +101,7 @@ import type { MLData } from "./mldata-fetch.js";
 import type { Collection, EnteFile, FileMetadata } from "./model/types.js";
 import { hasTransportCode } from "./retry.js";
 
-// Reports one line of the backup's progress. `level` is "error" when the line
+export type ProgressCallback = (message: string) => void;
-// reports something that failed, such as a file or an album, and is left out
-// for every other line.
-export type ProgressCallback = (message: string, level?: "error") => void;
 
 // The lock in a backup directory, as `lockBackupDirectory` returns it.
 export interface BackupLock {
@@ -294,10 +290,9 @@ const rebuildSymlink = (linkPath: string, target: string): void => {
 // case (two names that differ only in case are one entry on a case-insensitive
 // file system), or it is too long for a file name; then it gets ` (<id>)`,
 // right before the extension when `beforeExtension` is set. To fit, the part
-// before the ID is cut short as far as it must be. When the extension leaves
+// before the ID is cut short as far as it must be. When the extension alone
-// no room for the ID and the first character of the name, the extension is
+// leaves no room for the ID, the extension is cut short and the part before
-// cut short, and the part before the ID keeps that character and any bytes
+// the ID keeps only the bytes that cut leaves over. With `withJSON`, each
-// the cut leaves over (see `shortenKeepingExtension`). With `withJSON`, each
 // entry also has the JSON file `<name>.json` beside it, as an album does: a
 // name then leaves room for `.json`, and one that is another entry's JSON name
 // gets its ID added too.
@@ -498,9 +493,8 @@ const imageMetadataFor = async (
     }
 };
 
-// The file's JSON: its basic fields, its magic metadata, its ML data without
+// The file's JSON: its basic fields, its magic metadata, its ML data or the
-// the CLIP embedding and the keywords that embedding gives, or the reason the
+// reason the ML data is missing, and its image metadata.
-// ML data is missing, and its image metadata.
 const writeSidecar = (
     path: string,
     file: EnteFile,
@@ -516,13 +510,7 @@ const writeSidecar = (
     };
     if (file.magicMetadata) meta.magicMetadata = file.magicMetadata;
     if (file.pubMagicMetadata) meta.pubMagicMetadata = file.pubMagicMetadata;
-    if (ml.mlData) {
+    if (ml.mlData) meta.mlData = ml.mlData;
-        const { clip: _clip, ...mlDataWithoutClip } = ml.mlData;
-        meta.mlData = mlDataWithoutClip;
-        const isVideo = file.metadata.fileType === "video";
-        const keywords = clipKeywords(ml.mlData, isVideo);
-        if (keywords) meta.keywords = keywords;
-    }
     if (ml.mlDataError) meta.mlDataError = ml.mlDataError;
     if (image.imageMetadata) meta.imageMetadata = image.imageMetadata;
     if (image.imageMetadataError) {
@@ -665,7 +653,7 @@ const runLockedBackup = async (
     for (const record of lib.undecryptable()) {
         const error = `could not be decrypted: ${record.error}`;
         if (record.fileID === undefined) {
-            log(`FAILED album ${record.collectionID}: ${error}`, "error");
+            log(`FAILED album ${record.collectionID}: ${error}`);
             undecryptableAlbums.push(record.collectionID);
         } else if (scope.has(record.collectionID)) {
             const copies = memberships.get(record.fileID);
@@ -710,7 +698,6 @@ const runLockedBackup = async (
             } catch (err) {
                 log(
                     `FAILED verifying original ${file.metadata.title}: ${describeError(err)}`,
-                    "error",
                 );
                 recordFailure(
                     file.id,
@@ -744,7 +731,6 @@ const runLockedBackup = async (
         } catch (err) {
             log(
                 `FAILED original ${file.metadata.title}: ${describeError(err)}`,
-                "error",
             );
             recordFailure(
                 file.id,
@@ -820,7 +806,7 @@ const runLockedBackup = async (
             await lib.fetchMLData();
         } catch (err) {
             mlDataFailure = err;
-            log(`FAILED ML data: ${describeError(err)}`, "error");
+            log(`FAILED ML data: ${describeError(err)}`);
         }
         for (const file of distinct.values()) {
             if (lock.lost) throw lock.lost;
@@ -881,10 +867,7 @@ const runLockedBackup = async (
             downloadDirectory,
         );
     } catch (err) {
-        log(
+        log(`FAILED removing old album directories: ${describeError(err)}`);
-            `FAILED removing old album directories: ${describeError(err)}`,
-            "error",
-        );
     }
 
     // An album whose folder or JSON cannot be written, such as one whose
@@ -913,7 +896,6 @@ const runLockedBackup = async (
             } catch (err) {
                 log(
                     `FAILED removing old links in ${c.name}: ${describeError(err)}`,
-                    "error",
                 );
             }
 
@@ -932,7 +914,6 @@ const runLockedBackup = async (
                 } catch (err) {
                     log(
                         `FAILED symlink ${c.name}/${linkName}: ${describeError(err)}`,
-                        "error",
                     );
                     recordFailure(
                         link.file.id,
@@ -949,7 +930,7 @@ const runLockedBackup = async (
                 metaFiles,
             );
         } catch (err) {
-            log(`FAILED album ${c.name}: ${describeError(err)}`, "error");
+            log(`FAILED album ${c.name}: ${describeError(err)}`);
             failedAlbums.push(c.id);
         }
     }

src/cli-commands.ts

@@ -4,10 +4,7 @@
 // code; a thrown error is left to the caller. Nothing here calls
 // `process.exit`: `bin/quak.ts` wires these to the command line, and `run` in
 // `cli-run.ts` prints a thrown error as one line and exits once output has
-// drained. Output must stay byte-identical (see `cli-output.ts`). Each line on
+// drained. Output must stay byte-identical (see `cli-output.ts`).
-// stderr goes through `ctx.log` at its level (see `cli-log.ts`). Every command
-// that exits non-zero logs a fatal line saying why; one that exits 1 because
-// files or albums failed logs it last, saying how many and where to look.
 
 import {
     copyFileSync,
@@ -36,7 +33,6 @@ import {
     originalName,
     thumbnailName,
 } from "./cli-output.js";
-import { type Log, logRefresh } from "./cli-log.js";
 import { freshCollections, freshFiles, freshFile } from "./cli-read.js";
 import { withExtension } from "./filename.js";
 import { runMetadataBackup } from "./metadata-backup.js";
@@ -44,8 +40,7 @@ import { listMissingThumbnails, fixMissingThumbnails } from "./thumbnails.js";
 
 export interface CliContext {
     stdout: { write(text: string): unknown };
-    // Writes a line on stderr at a log level, if the run's level prints it.
+    stderr: { write(text: string): unknown };
-    log: Log;
     // Directory holding `session.json`.
     sessionDir: string;
     // The `--cache-dir` global, or undefined to let the library pick its
@@ -87,16 +82,16 @@ const requireSession = (ctx: CliContext): Client | undefined => {
     try {
         client = ctx.loadSession(sessionPath(ctx));
     } catch (err) {
-        ctx.log("fatal", err instanceof Error ? err.message : String(err));
+        ctx.stderr.write(
-        ctx.log(
+            `${err instanceof Error ? err.message : err}\n` +
-            "fatal",
+                `Run "quak logout" and then "quak login" to replace it.\n`,
-            `Run "quak logout" and then "quak login" to replace it.`,
         );
         return undefined;
     }
     if (!client) {
-        ctx.log("fatal", `Not logged in. Run "quak login" first.`);
+        ctx.stderr.write(
-        ctx.log("fatal", `Session file: ${sessionPath(ctx)}`);
+            `Not logged in. Run "quak login" first.\nSession file: ${sessionPath(ctx)}\n`,
+        );
         return undefined;
     }
     return client;
@@ -112,7 +107,7 @@ const parseID = (
 ): number | undefined => {
     const id = Number(text);
     if (/^[0-9]+$/.test(text) && Number.isSafeInteger(id)) return id;
-    ctx.log("fatal", `Invalid ${kind} ID: ${text}`);
+    ctx.stderr.write(`Invalid ${kind} ID: ${text}\n`);
     return undefined;
 };
 
@@ -130,19 +125,15 @@ const readLibraryClient = (client: Client): LibraryClient => ({
 
 // Open a library for a single point command: the aggressive background precache
 // (issue #48) is off — a one-shot `collections` or `get` must not start
-// downloading the whole account — and no refresh starts as it opens or on a
+// downloading the whole account — and the refresh interval is long so no second
-// timer: each command asks for the one it needs, and `collections` needs none
+// refresh fires mid-command.
-// (issue #210). While a refresh runs, each collection whose files it has
-// fetched is logged, so a large account shows progress rather than nothing.
 const openReadLibrary = (ctx: CliContext, client: Client): Promise<Library> =>
     Library.open({
         client: readLibraryClient(client),
         cacheDirectory: ctx.cacheDir,
-        refreshOnOpen: false,
+        refreshIntervalSeconds: 3600,
-        refreshIntervalSeconds: Infinity,
         precacheThumbnails: false,
         precacheOriginals: false,
-        onProgress: logRefresh(ctx.log),
     });
 
 export const loginCommand = async (ctx: CliContext): Promise<number> => {
@@ -151,7 +142,7 @@ export const loginCommand = async (ctx: CliContext): Promise<number> => {
     const password =
         process.env.QUAK_PASSWORD ?? (await ctx.promptSecret("Password"));
 
-    ctx.log("info", "Authenticating...");
+    ctx.stderr.write("Authenticating...\n");
     try {
         const client = await ctx.login({
             email,
@@ -162,12 +153,11 @@ export const loginCommand = async (ctx: CliContext): Promise<number> => {
 
         saveSession(ctx.sessionDir, client.toJSON());
         const info = client.whoami();
-        ctx.log("info", `Logged in as ${info.email} (user ${info.userID})`);
+        ctx.stderr.write(`Logged in as ${info.email} (user ${info.userID})\n`);
-        ctx.log("info", `Session saved to ${sessionPath(ctx)}`);
+        ctx.stderr.write(`Session saved to ${sessionPath(ctx)}\n`);
     } catch (err) {
-        ctx.log(
+        ctx.stderr.write(
-            "fatal",
+            `Login failed: ${err instanceof Error ? err.message : err}\n`,
-            `Login failed: ${err instanceof Error ? err.message : err}`,
         );
         return 1;
     }
@@ -189,7 +179,7 @@ export const whoamiCommand = async (ctx: CliContext): Promise<number> => {
 export const logoutCommand = async (ctx: CliContext): Promise<number> => {
     const path = sessionPath(ctx);
     if (!existsSync(path)) {
-        ctx.log("info", "No session found.");
+        ctx.stderr.write("No session found.\n");
         return 0;
     }
     await init();
@@ -207,15 +197,16 @@ export const logoutCommand = async (ctx: CliContext): Promise<number> => {
     }
     unlinkSync(path);
     if (failure === undefined) {
-        ctx.log("info", "Session ended on the server.");
+        ctx.stderr.write("Session ended on the server.\n");
     } else {
-        ctx.log("fatal", `Could not end the session on the server: ${failure}`);
+        ctx.stderr.write(
+            `Could not end the session on the server: ${failure}\n`,
+        );
     }
-    ctx.log("info", "Session deleted.");
+    ctx.stderr.write("Session deleted.\n");
     if (cacheDir !== undefined) {
-        ctx.log(
+        ctx.stderr.write(
-            "warning",
+            `Cache directory ${cacheDir} still holds decrypted data; delete it to remove that data.\n`,
-            `Cache directory ${cacheDir} still holds decrypted data; delete it to remove that data.`,
         );
     }
     return failure === undefined ? 0 : 1;
@@ -230,10 +221,9 @@ export const collectionsCommand = async (
     if (!client) return 3;
     const lib = await openReadLibrary(ctx, client);
     try {
-        // Ask the server for the collection list alone and list it in its
+        // Force a server round-trip and list in enumeration order (issue #36
-        // order (issue #36 amendment, issues #52 and #210): the pre-library
+        // amendment, issue #52): the pre-library CLI printed current state in
-        // CLI printed current state in this order, not the albums
+        // this order, not the albums projection's newest-first order.
-        // projection's newest-first order.
         const collections = await freshCollections(lib);
 
         if (opts.json) {
@@ -264,21 +254,15 @@ export const collectionsCommand = async (
     }
 };
 
-// Lists the files of the collection `collectionIDStr` names, or without it every
-// file in the account, each once (issue #211).
 export const filesCommand = async (
     ctx: CliContext,
-    collectionIDStr: string | undefined,
+    opts: { collection: string; json?: boolean },
-    opts: { json?: boolean },
 ): Promise<number> => {
     await init();
     const client = requireSession(ctx);
     if (!client) return 3;
-    const collectionID =
+    const collectionID = parseID(ctx, "collection", opts.collection);
-        collectionIDStr === undefined
+    if (collectionID === undefined) return 1;
-            ? undefined
-            : parseID(ctx, "collection", collectionIDStr);
-    if (collectionIDStr !== undefined && collectionID === undefined) return 1;
 
     const lib = await openReadLibrary(ctx, client);
     try {
@@ -289,7 +273,7 @@ export const filesCommand = async (
         // newest-first order.
         const files = await freshFiles(lib, collectionID);
         if (!files) {
-            ctx.log("fatal", `Collection ${collectionID} not found`);
+            ctx.stderr.write(`Collection ${collectionID} not found\n`);
             return 1;
         }
 
@@ -325,7 +309,7 @@ export const getCommand = async (
         // (issue #36 amendment, issue #52).
         const resolved = await freshFile(lib, fileID);
         if (!resolved) {
-            ctx.log("fatal", `File ${fileID} not found`);
+            ctx.stderr.write(`File ${fileID} not found\n`);
             return 1;
         }
         const { photo, file } = resolved;
@@ -333,33 +317,30 @@ export const getCommand = async (
         const result = await photo.original();
         // Default name is the file's own title, as the pre-library CLI used
         // (not the editedName-preferring projection title) (issue #52).
-        if (result.videoPath === undefined) {
         const outPath = opts.out ?? originalName(file);
+        if (result.videoPath === undefined) {
             copyFileSync(result.path, outPath);
-            ctx.log("info", `${result.bytes} bytes -> ${outPath}`);
+            ctx.stderr.write(`${result.bytes} bytes -> ${outPath}\n`);
             return 0;
         }
         // A live photo is written as its image and its video, each named after
         // the title with its own extension, as Ente's clients name them. With
         // --out, the image goes there and the video beside it.
-        const imageExt = extname(result.path);
+        const imageOut =
-        const videoExt = extname(result.videoPath);
+            opts.out ?? withExtension(outPath, extname(result.path));
-        const imageOut = opts.out ?? originalName(file, imageExt);
+        const videoOut = withExtension(outPath, extname(result.videoPath));
-        const videoOut =
-            opts.out === undefined
-                ? originalName(file, videoExt)
-                : withExtension(opts.out, videoExt);
         if (imageOut.toLowerCase() === videoOut.toLowerCase()) {
-            ctx.log(
+            ctx.stderr.write(
-                "fatal",
+                `File ${fileID} is a live photo, and its video would also be written to ${imageOut}\n`,
-                `File ${fileID} is a live photo, and its video would also be written to ${imageOut}`,
             );
             return 1;
         }
         copyFileSync(result.path, imageOut);
         copyFileSync(result.videoPath, videoOut);
-        ctx.log("info", `${result.bytes} bytes -> ${imageOut}`);
+        ctx.stderr.write(
-        ctx.log("info", `${statSync(videoOut).size} bytes -> ${videoOut}`);
+            `${result.bytes} bytes -> ${imageOut}\n` +
+                `${statSync(videoOut).size} bytes -> ${videoOut}\n`,
+        );
         return 0;
     } finally {
         await lib.close();
@@ -383,7 +364,7 @@ export const getThumbCommand = async (
         // (issue #36 amendment, issue #52).
         const resolved = await freshFile(lib, fileID);
         if (!resolved) {
-            ctx.log("fatal", `File ${fileID} not found`);
+            ctx.stderr.write(`File ${fileID} not found\n`);
             return 1;
         }
         const { photo, file } = resolved;
@@ -393,7 +374,7 @@ export const getThumbCommand = async (
         // used (not the projection title) (issue #52).
         const outPath = opts.out ?? thumbnailName(file);
         copyFileSync(result.path, outPath);
-        ctx.log("info", `${result.bytes} bytes -> ${outPath}`);
+        ctx.stderr.write(`${result.bytes} bytes -> ${outPath}\n`);
         return 0;
     } finally {
         await lib.close();
@@ -415,14 +396,9 @@ export const backupMetadataCommand = async (
         await lib.fresh();
         const result = await runMetadataBackup(lib, client, dir, {
             exif: opts.exif || opts.all,
-            onProgress: (msg, level) => ctx.log(level ?? "info", msg),
+            onProgress: (msg) => ctx.stderr.write(msg + "\n"),
         });
-        if (result.filesWithMLDataError === 0) return 0;
+        return result.filesWithMLDataError > 0 ? 1 : 0;
-        ctx.log(
-            "fatal",
-            `quak: the ML data of ${result.filesWithMLDataError} file(s) could not be read; see mlDataError in their JSON in ${dir}`,
-        );
-        return 1;
     } finally {
         await lib.close();
     }
@@ -437,7 +413,7 @@ export const backupCommand = async (
     const client = requireSession(ctx);
     if (!client) return 3;
 
-    ctx.log("info", "Starting backup...");
+    ctx.stderr.write("Starting backup...\n");
     // The lock is taken before the library opens and starts its refresh, so a
     // run refused while another backup of `dir` runs sends no request.
     let lock: BackupLock;
@@ -445,7 +421,7 @@ export const backupCommand = async (
         lock = await lockBackupDirectory(dir);
     } catch (err) {
         if ((err as NodeJS.ErrnoException).code !== "ELOCKED") throw err;
-        ctx.log("fatal", `quak: ${(err as Error).message}`);
+        ctx.stderr.write(`quak: ${(err as Error).message}\n`);
         return 2;
     }
     try {
@@ -460,48 +436,45 @@ export const backupCommand = async (
             refreshIntervalSeconds: Infinity,
             precacheThumbnails: false,
             precacheOriginals: false,
-            onProgress: logRefresh(ctx.log),
         });
         try {
             const result = await lib.backup({
                 downloadDirectory: dir,
                 lock,
                 verify: opts.verify,
-                onProgress: (msg, level) => ctx.log(level ?? "info", msg),
+                onProgress: (msg) => {
+                    if (!opts.json) ctx.stderr.write(msg + "\n");
+                },
             });
 
             if (opts.json) {
                 ctx.stdout.write(JSON.stringify(result, null, 2) + "\n");
             } else {
-                ctx.log("info", "\n--- Backup complete ---");
+                ctx.stderr.write("\n--- Backup complete ---\n");
-                ctx.log("info", `  Total files: ${result.totalFiles}`);
+                ctx.stderr.write(`  Total files: ${result.totalFiles}\n`);
-                ctx.log("info", `  Downloaded:  ${result.downloaded}`);
+                ctx.stderr.write(`  Downloaded:  ${result.downloaded}\n`);
-                ctx.log("info", `  Skipped:     ${result.skipped}`);
+                ctx.stderr.write(`  Skipped:     ${result.skipped}\n`);
                 if (opts.verify) {
-                    ctx.log("info", `  Verified:    ${result.verified}`);
+                    ctx.stderr.write(`  Verified:    ${result.verified}\n`);
-                    ctx.log("info", `  Mismatched:  ${result.mismatched}`);
+                    ctx.stderr.write(`  Mismatched:  ${result.mismatched}\n`);
-                    ctx.log("info", `  Unchecked:   ${result.unchecked}`);
+                    ctx.stderr.write(`  Unchecked:   ${result.unchecked}\n`);
                 }
-                ctx.log("info", `  Failed:      ${result.failed}`);
+                ctx.stderr.write(`  Failed:      ${result.failed}\n`);
                 if (result.errors.length > 0) {
-                    ctx.log("error", "\nFailed files:");
+                    ctx.stderr.write("\nFailed files:\n");
                     for (const e of result.errors) {
-                        ctx.log(
+                        ctx.stderr.write(
-                            "error",
+                            `  [${e.collection}] ${e.title} (id ${e.fileID}): ${e.error}\n`,
-                            `  [${e.collection}] ${e.title} (id ${e.fileID}): ${e.error}`,
                         );
                     }
                 }
             }
 
-            const albums =
+            return result.failed > 0 ||
-                result.undecryptableAlbums.length + result.failedAlbums.length;
+                result.undecryptableAlbums.length > 0 ||
-            if (result.failed === 0 && albums === 0) return 0;
+                result.failedAlbums.length > 0
-            ctx.log(
+                ? 1
-                "fatal",
+                : 0;
-                `quak: ${result.failed} file(s) and ${albums} album(s) failed; see ${join(dir, "failures.json")} and the FAILED lines`,
-            );
-            return 1;
         } finally {
             await lib.close();
         }
@@ -522,19 +495,18 @@ export const listMissingThumbnailsCommand = async (
         // Refresh first so files added since the cache was written are
         // checked; a failed refresh throws.
         await lib.fresh();
-        const missing = await listMissingThumbnails(lib, client, (msg, level) =>
+        const missing = await listMissingThumbnails(lib, client, (msg) => {
-            ctx.log(level ?? "info", msg),
+            if (!opts.json) ctx.stderr.write(msg + "\n");
-        );
+        });
 
         if (opts.json) {
             ctx.stdout.write(JSON.stringify(missing, null, 2) + "\n");
         } else {
             if (missing.length === 0) {
-                ctx.log("info", "No missing thumbnails found.");
+                ctx.stderr.write("No missing thumbnails found.\n");
             } else {
-                ctx.log(
+                ctx.stderr.write(
-                    "info",
+                    `\n${missing.length} file(s) with missing thumbnails:\n`,
-                    `\n${missing.length} file(s) with missing thumbnails:`,
                 );
                 for (const m of missing) {
                     ctx.stdout.write(
@@ -569,28 +541,27 @@ export const fixMissingThumbnailsCommand = async (
         // a failed refresh throws.
         await lib.fresh();
         if (fileIDs.length === 0) {
-            ctx.log("info", "Scanning for missing thumbnails...");
+            ctx.stderr.write("Scanning for missing thumbnails...\n");
-            const missing = await listMissingThumbnails(
+            const missing = await listMissingThumbnails(lib, client, (msg) => {
-                lib,
+                if (!opts.json) ctx.stderr.write(msg + "\n");
-                client,
+            });
-                (msg, level) => ctx.log(level ?? "info", msg),
-            );
             fileIDs = missing.map((m) => m.fileID);
             if (fileIDs.length === 0) {
-                ctx.log("info", "No missing thumbnails found.");
+                ctx.stderr.write("No missing thumbnails found.\n");
                 return 0;
             }
-            ctx.log("info", `Found ${fileIDs.length} file(s) to fix.`);
+            ctx.stderr.write(`Found ${fileIDs.length} file(s) to fix.\n`);
         }
 
         const results = await fixMissingThumbnails(
             lib,
             client,
             fileIDs,
-            (msg, level) => ctx.log(level ?? "info", msg),
+            (msg) => {
+                if (!opts.json) ctx.stderr.write(msg + "\n");
+            },
         );
 
-        const failed = results.filter((r) => r.status === "failed").length;
         if (opts.json) {
             ctx.stdout.write(JSON.stringify(results, null, 2) + "\n");
         } else {
@@ -598,30 +569,30 @@ export const fixMissingThumbnailsCommand = async (
             const skipped = results.filter(
                 (r) => r.status === "skipped",
             ).length;
-            ctx.log("info", `\n--- Done ---`);
+            const failed = results.filter((r) => r.status === "failed").length;
-            ctx.log("info", `  Fixed:   ${fixed}`);
+            ctx.stderr.write(`\n--- Done ---\n`);
-            ctx.log("info", `  Skipped: ${skipped}`);
+            ctx.stderr.write(`  Fixed:   ${fixed}\n`);
-            ctx.log("info", `  Failed:  ${failed}`);
+            ctx.stderr.write(`  Skipped: ${skipped}\n`);
+            ctx.stderr.write(`  Failed:  ${failed}\n`);
             if (skipped > 0) {
-                ctx.log("info", "\nSkipped:");
+                ctx.stderr.write("\nSkipped:\n");
                 for (const r of results.filter((r) => r.status === "skipped")) {
-                    ctx.log("info", `  ${r.fileID}\t${r.title}\t${r.reason}`);
+                    ctx.stderr.write(
+                        `  ${r.fileID}\t${r.title}\t${r.reason}\n`,
+                    );
                 }
             }
             if (failed > 0) {
-                ctx.log("error", "\nFailed files:");
+                ctx.stderr.write("\nFailed files:\n");
                 for (const r of results.filter((r) => r.status === "failed")) {
-                    ctx.log("error", `  ${r.fileID}\t${r.title}\t${r.reason}`);
+                    ctx.stderr.write(
+                        `  ${r.fileID}\t${r.title}\t${r.reason}\n`,
+                    );
                 }
             }
         }
 
-        if (failed === 0) return 0;
+        return results.some((r) => r.status === "failed") ? 1 : 0;
-        ctx.log(
-            "fatal",
-            `quak: ${failed} file(s) failed; see the "Failed files:" list, or the JSON with --json`,
-        );
-        return 1;
     } finally {
         await lib.close();
     }

src/cli-log.ts

@@ -1,99 +0,0 @@
-// The CLI's log level, and the one function the commands write stderr lines
-// through.
-//
-// Every line quak prints on stderr is a log line at one of six levels, from
-// the quietest: fatal, error, warning, info, debug, trace. A run prints the
-// lines at its own level and at every quieter one. Its level is info unless
-// `-v` or `-q` asks for another (see "CLI surface" in the README). Every
-// command that exits non-zero logs a fatal line saying why, so even `-q`, which
-// prints only fatal lines, never leaves a non-zero exit unexplained. An error
-// line reports something that failed, such as a file or an album, and a
-// warning something that did not fail but needs the user's attention. stdout
-// carries only a command's output and is not a log.
-//
-// The library itself writes no lines: its layers report through callbacks, and
-// the CLI logs what they report. `logRequests` gives the API client options
-// that log each request and each retry, and `logRefresh` the library's
-// `onProgress` that logs what a refresh and an ML data fetch report.
-
-import type { ApiClientOptions } from "./api/client.js";
-import { describeError } from "./errors.js";
-import type { RefreshEvent } from "./library/index.js";
-import type { RetryOptions } from "./retry.js";
-
-const LEVELS = ["fatal", "error", "warning", "info", "debug", "trace"] as const;
-
-export type LogLevel = (typeof LEVELS)[number];
-
-// Writes `line` on stderr when the run's level prints lines at `level`.
-export type Log = (level: LogLevel, line: string) => void;
-
-// The level asked for by `-v` given `verbose` times, or by `-q`: info without
-// either, debug for `-v`, trace for `-vv` and more, fatal for `-q`.
-// `bin/quak.ts` refuses `-q` and `-v` together.
-export const logLevel = (verbose: number, quiet: boolean): LogLevel => {
-    if (quiet) return "fatal";
-    if (verbose === 0) return "info";
-    return verbose === 1 ? "debug" : "trace";
-};
-
-// The log that writes each line at `level` or quieter to `stderr`, ending it
-// with a newline.
-export const stderrLog =
-    (stderr: { write(text: string): unknown }, level: LogLevel): Log =>
-    (lineLevel, line) => {
-        if (LEVELS.indexOf(lineLevel) <= LEVELS.indexOf(level)) {
-            stderr.write(line + "\n");
-        }
-    };
-
-// API client options that log each request at trace, with the status of its
-// response or the error it failed with, and each retry at debug, with why and
-// how long it waits. `retry` is the retry policy, the default when not given.
-export const logRequests = (
-    log: Log,
-    retry?: RetryOptions,
-): ApiClientOptions => ({
-    retry: {
-        ...retry,
-        onRetry: (err, attempt, delayMs) =>
-            log(
-                "debug",
-                `Attempt ${attempt} failed, retrying in ${Math.round(delayMs)} ms: ${describeError(err)}`,
-            ),
-    },
-    onRequest: ({ method, url, status, error }) =>
-        log(
-            "trace",
-            `${method} ${url}: ${error === undefined ? `HTTP ${status}` : describeError(error)}`,
-        ),
-});
-
-// How a log line names each operation the library reports the start and end
-// of.
-const OPERATION_NAMES: Record<RefreshEvent["operation"], string> = {
-    refresh: "Refresh",
-    fetchMLData: "ML data fetch",
-    precacheThumbnails: "Thumbnail precache",
-    precacheOriginals: "Original precache",
-};
-
-// A library `onProgress` that logs, at info, each collection whose files a
-// refresh has fetched, and at debug the start and end of each refresh and ML
-// data fetch, with the error of one that failed.
-export const logRefresh =
-    (log: Log) =>
-    (event: RefreshEvent): void => {
-        if (event.status === "progress") {
-            log(
-                "info",
-                `Fetched the files of ${event.fetched} of ${event.total} collections`,
-            );
-            return;
-        }
-        const error = event.error === undefined ? "" : `: ${event.error}`;
-        log(
-            "debug",
-            `${OPERATION_NAMES[event.operation]} ${event.status}${error}`,
-        );
-    };

src/cli-output.ts

@@ -9,7 +9,11 @@
 // `metadata.title`, and issue #52 requires that output stay byte-identical, so
 // the commands shape their output from the raw `EnteFile` through here.
 
-import { defaultFileName } from "./filename.js";
+import {
+    MAX_NAME_BYTES,
+    sanitizeFileName,
+    shortenKeepingExtension,
+} from "./filename.js";
 import type { EnteFile, FileType, Microseconds } from "./model/types.js";
 
 // One row of `quak files --json`.
@@ -33,13 +37,20 @@ export const fileListRow = (file: EnteFile): FileListRow => ({
 export const fileListLine = (file: EnteFile): string =>
     `${file.id}\t${file.metadata.fileType}\t${file.metadata.title}`;
 
-// Default output path for `quak get` when `--out` is not given, made from the
+// Default output path for `quak get` when `--out` is not given. The title comes
-// title (see `defaultFileName`), with `ext` in place of its extension for a
+// from the server, so it is sanitized, and cut short to fit in a file name,
-// live photo's image or video; `--out` is the user's and is used as is.
+// keeping its extension; `--out` is the user's and is used as is.
-export const originalName = (file: EnteFile, ext?: string): string =>
+export const originalName = (file: EnteFile): string =>
-    defaultFileName(file.metadata.title, file.id, { ext });
+    shortenKeepingExtension(
+        sanitizeFileName(file.metadata.title, `file-${file.id}`),
+        MAX_NAME_BYTES,
+    );
 
 // Default output path for `quak get-thumb` when `--out` is not given: `thumb_`
-// and the title.
+// and the title, cut short so that the two fit in a file name.
 export const thumbnailName = (file: EnteFile): string =>
-    defaultFileName(file.metadata.title, file.id, { prefix: "thumb_" });
+    "thumb_" +
+    shortenKeepingExtension(
+        sanitizeFileName(file.metadata.title, `file-${file.id}`),
+        MAX_NAME_BYTES - "thumb_".length,
+    );

src/cli-read.ts

@@ -1,72 +1,50 @@
 // How the CLI's read commands obtain current data.
 //
-// `collections`, `files`, `get`, and `get-thumb` must answer for
+// `collections`, `files --collection`, `get`, and `get-thumb` must answer for
 // the account's state at the moment the command runs, not for whatever the
-// local cache last happened to hold (owner amendment, issue #36). `files`,
+// local cache last happened to hold (owner amendment, issue #36). Each helper
-// `get` and `get-thumb` therefore force a server round-trip through
+// therefore forces a server round-trip through `Library.fresh()` and only then
-// `Library.fresh()` and only then read — so a collection, file, or metadata
+// reads — so a collection, file, or metadata change made elsewhere is visible.
-// change made elsewhere is visible. `collections` asks the library for the
-// collection list alone through `Library.freshCollections()` (issue #210): a
-// refresh would also fetch the files of every collection, which on a large
-// account takes long and which `collections` does not print.
 //
-// `collections` lists in the server's order and `files` in the library's own
+// `collections` and `files` also list in the library's own enumeration order —
-// enumeration order (`listFiles()`), the orders the pre-library CLI printed,
+// `listCollections()`/`listFiles()`, the order the pre-library CLI printed —
 // rather than the `albums`/`photos` projection's newest-first order, which
 // re-sorts the rows. The field values still come from each record's raw
-// metadata via `cli-output.ts`. `files` without a collection ID lists every
+// metadata via `cli-output.ts`.
-// file in the account once (issue #211): the library keeps a record of a file
-// for each collection that holds it, and only the first collection's record is
-// listed.
 
 import type { Collection, EnteFile } from "./model/types.js";
 import type { Photo, PhotosAPI } from "./library/index.js";
 
 // The slice of `Library` these helpers read. `Library` satisfies it
 // structurally; a test can drive them with a stand-in that records the
-// `fresh()` and `freshCollections()` calls and serves records in a known
+// `fresh()` call and serves records in a known enumeration order.
-// enumeration order.
 export interface FreshReadLibrary {
     fresh(): Promise<unknown>;
-    freshCollections(): Promise<Collection[]>;
-    getCollection(id: number): Collection | undefined;
     listCollections(): Collection[];
+    getCollection(id: number): Collection | undefined;
     listFiles(collectionID: number): EnteFile[];
     getFileByID(fileID: number): EnteFile | undefined;
     photos: Pick<PhotosAPI, "byID">;
 }
 
-// Every live collection, current as of one collections request, in the
+// Every live collection, current as of a forced refresh, in enumeration order.
-// server's order.
+export const freshCollections = async (
-export const freshCollections = (
     lib: FreshReadLibrary,
-): Promise<Collection[]> => lib.freshCollections();
+): Promise<Collection[]> => {
+    await lib.fresh();
+    return lib.listCollections();
+};
 
 // The files of one collection, current as of a forced refresh, in enumeration
 // order. `undefined` (not an empty list) when the collection does not exist, so
-// the caller can tell "no such collection" from "an empty collection". Without
+// the caller can tell "no such collection" from "an empty collection".
-// a collection ID, every file in the account, each once, as held by the first
-// collection that holds it.
 export const freshFiles = async (
     lib: FreshReadLibrary,
-    collectionID?: number,
+    collectionID: number,
 ): Promise<EnteFile[] | undefined> => {
     await lib.fresh();
-    if (collectionID !== undefined) {
+    if (!lib.getCollection(collectionID)) return undefined;
-        return lib.getCollection(collectionID)
+    return lib.listFiles(collectionID);
-            ? lib.listFiles(collectionID)
-            : undefined;
-    }
-    const listed = new Set<number>();
-    const files: EnteFile[] = [];
-    for (const collection of lib.listCollections()) {
-        for (const file of lib.listFiles(collection.id)) {
-            if (listed.has(file.id)) continue;
-            listed.add(file.id);
-            files.push(file);
-        }
-    }
-    return files;
 };
 
 // One file, current as of a forced refresh, resolved to both its content

src/cli-run.ts

@@ -2,23 +2,21 @@
 
 import type { Writable } from "node:stream";
 import { ApiError } from "./api/client.js";
-import type { Log } from "./cli-log.js";
 import { describeError } from "./errors.js";
 
 // Run a command and exit with its code once stdout/stderr have drained.
 // Exiting before the drain can truncate piped output, and the library can keep
 // the event loop alive after a command returns, so a plain return could hang.
-// An error the command throws is logged as one fatal `quak: MESSAGE` line,
+// An error the command throws is printed as one `quak: MESSAGE` line, without
-// without the stack trace, and exits 1. MESSAGE is the error as
+// the stack trace, and exits 1. MESSAGE is the error as `describeError` gives
-// `describeError` gives it, so it carries the reason Node's `fetch` puts on
+// it, so it carries the reason Node's `fetch` puts on `cause`. A 401 from the
-// `cause`. A 401 from the server means it no longer accepts the saved session:
+// server means it no longer accepts the saved session: that prints one line
-// that logs one fatal line saying to log in again and exits 3, as a missing or
+// saying to log in again and exits 3, as a missing or corrupt session file
-// corrupt session file does.
+// does.
 export const run = async (
     command: Promise<number>,
     stdout: Writable,
     stderr: Writable,
-    log: Log,
     exit: (code: number) => void,
 ): Promise<void> => {
     let code: number;
@@ -26,13 +24,12 @@ export const run = async (
         code = await command;
     } catch (err) {
         if (err instanceof ApiError && err.status === 401) {
-            log(
+            stderr.write(
-                "fatal",
+                `quak: the saved session is no longer valid; run "quak login"\n`,
-                `quak: the saved session is no longer valid; run "quak login"`,
             );
             code = 3;
         } else {
-            log("fatal", `quak: ${describeError(err)}`);
+            stderr.write(`quak: ${describeError(err)}\n`);
             code = 1;
         }
     }

src/clip-keywords.ts

@@ -1,57 +0,0 @@
-// Keywords for a file from its CLIP embedding.
-//
-// Ente stores no keywords. A file's ML data holds a CLIP embedding, the 512
-// numbers Ente's image model gave the photo, and Ente's photos app sorts files
-// into the categories of its Discover section with it: a file falls in a
-// category when the cosine similarity of its CLIP embedding and the text
-// embedding of the category's query is at least the category's `minScore`,
-// unless the file is a video and the category leaves out videos. A file's
-// keywords are the titles of the categories it falls in. The categories and
-// their text embeddings are in `clip-keyword-vectors.ts`.
-
-import { DISCOVER_CATEGORIES } from "./clip-keyword-vectors.js";
-import { clipEmbedding } from "./library/mldata.js";
-import type { MLData } from "./mldata-fetch.js";
-
-// How many numbers a CLIP embedding from Ente's image model has.
-const EMBEDDING_LENGTH = 512;
-
-const norm = (vector: number[]): number => Math.hypot(...vector);
-
-const cosineSimilarity = (a: number[], b: number[]): number => {
-    let dot = 0;
-    a.forEach((value, i) => {
-        dot += value * (b[i] ?? 0);
-    });
-    return dot / (norm(a) * norm(b));
-};
-
-// The titles of the Discover categories a file falls in, highest score first,
-// or undefined when its ML data has no CLIP embedding of 512 finite numbers
-// that are not all zero. Tests pass their own `categories`.
-export const clipKeywords = (
-    mlData: MLData,
-    isVideo: boolean,
-    categories = DISCOVER_CATEGORIES,
-): string[] | undefined => {
-    const embedding = clipEmbedding(mlData);
-    if (
-        !embedding ||
-        embedding.length !== EMBEDDING_LENGTH ||
-        norm(embedding) === 0
-    ) {
-        return undefined;
-    }
-
-    const matches: { title: string; score: number }[] = [];
-    for (const category of categories) {
-        if (isVideo && !category.showVideo) continue;
-        const score = cosineSimilarity(embedding, category.textEmbedding);
-        if (score >= category.minScore) {
-            matches.push({ title: category.title, score });
-        }
-    }
-    return matches
-        .sort((a, b) => b.score - a.score)
-        .map((match) => match.title);
-};

src/download/index.ts

@@ -16,7 +16,13 @@ import {
     streamTagFinal,
 } from "../crypto/index.js";
 import { TruncatedStreamError } from "../errors.js";
-import { defaultFileName, safeExtension, withExtension } from "../filename.js";
+import {
+    MAX_NAME_BYTES,
+    safeExtension,
+    sanitizeFileName,
+    shortenKeepingExtension,
+    withExtension,
+} from "../filename.js";
 import { withRetry } from "../retry.js";
 import type { ApiClient } from "../api/client.js";
 import type { EnteFile } from "../model/types.js";
@@ -365,14 +371,10 @@ const openPart = async (
 // name starts with `image` as the image and the one whose name starts with
 // `video` as the video, and refuses a ZIP holding a second of either. It is
 // written unpacked: each part is named `destination` with the extension
-// replaced by its own entry's, and the two must differ ignoring case. When
+// replaced by its own entry's, and the two must differ ignoring case. When the
-// `defaultName` is set, `destination` is the name `defaultFileName` made from
+// file records a hash, `<imageHash>:<videoHash>` must match it, each over that
-// the title rather than a path the caller gave, and each part is named as
+// part's own bytes. Only then are the image, then the video, renamed into
-// `defaultFileName` names it with its own extension, so that the name is cut
+// place; on any failure neither is stored.
-// short to fit with that extension. When the file records a hash,
-// `<imageHash>:<videoHash>` must match it, each over that part's own bytes.
-// Only then are the image, then the video, renamed into place; on any failure
-// neither is stored.
 //
 // The ZIP is chosen by its uploader and may expand enormously, so each part is
 // written as it decompresses and never held, and the ZIP is refused once the
@@ -392,7 +394,6 @@ const decryptLivePhoto = async (
     key: Uint8Array,
     onProgress: ProgressCallback | undefined,
     file: EnteFile,
-    defaultName: boolean,
 ): Promise<DownloadResult> => {
     const sliceSize = 4096;
     const dir = dirname(destination);
@@ -491,12 +492,8 @@ const decryptLivePhoto = async (
                 `live photo's image and video have the same extension, ${video.ext}`,
             );
         }
-        const partPath = (ext: string): string =>
+        const path = withExtension(destination, image.ext);
-            defaultName
+        const videoPath = withExtension(destination, video.ext);
-                ? defaultFileName(file.metadata.title, file.id, { ext })
-                : withExtension(destination, ext);
-        const path = partPath(image.ext);
-        const videoPath = partPath(video.ext);
         for (const part of parts) {
             await part.handle.sync();
             await part.handle.close();
@@ -540,9 +537,6 @@ const decryptLivePhoto = async (
 // and then removes its own temp file, and only the attempt that reaches
 // TAG_FINAL renames one into place, so a download that needed three tries still
 // performs exactly one rename over the destination.
-//
-// `defaultName` says `destination` is the name `defaultFileName` made, not a
-// path the caller gave (see `decryptLivePhoto`).
 const fetchAndDecrypt = async (
     api: ApiClient,
     openStream: () => Promise<ReadableStream<Uint8Array>>,
@@ -551,7 +545,6 @@ const fetchAndDecrypt = async (
     destination: string,
     onProgress?: ProgressCallback,
     original?: EnteFile,
-    defaultName = false,
 ): Promise<DownloadResult> =>
     withRetry(async () => {
         const stream = await openStream();
@@ -564,7 +557,6 @@ const fetchAndDecrypt = async (
                     key,
                     onProgress,
                     original,
-                    defaultName,
                 );
             }
             const bytesWritten = await decryptToTemp(
@@ -596,11 +588,15 @@ export const downloadFile = async (
     outPath?: string,
     onProgress?: ProgressCallback,
 ): Promise<DownloadResult> => {
-    // `outPath` is the caller's and is used as is. Without it, the file is
+    // `outPath` is the caller's and is used as is; the title is the server's
-    // written in the current directory under the name `defaultFileName` makes
+    // and is sanitized so it can only name a file in the current directory,
-    // from the title, which is the server's.
+    // and cut short to fit in a file name, keeping its extension.
     const resolvedPath =
-        outPath ?? defaultFileName(file.metadata.title, file.id);
+        outPath ??
+        shortenKeepingExtension(
+            sanitizeFileName(file.metadata.title, `file-${file.id}`),
+            MAX_NAME_BYTES,
+        );
     const header = fromBase64(file.file.decryptionHeader);
     return fetchAndDecrypt(
         api,
@@ -610,7 +606,6 @@ export const downloadFile = async (
         resolvedPath,
         onProgress,
         file,
-        outPath === undefined,
     );
 };
 
@@ -623,7 +618,11 @@ export const downloadThumbnail = async (
     // As in `downloadFile`, with `thumb_` before the title.
     const resolvedPath =
         outPath ??
-        defaultFileName(file.metadata.title, file.id, { prefix: "thumb_" });
+        "thumb_" +
+            shortenKeepingExtension(
+                sanitizeFileName(file.metadata.title, `file-${file.id}`),
+                MAX_NAME_BYTES - "thumb_".length,
+            );
     const header = fromBase64(file.thumbnail.decryptionHeader);
     return fetchAndDecrypt(
         api,

src/filename.ts

@@ -6,8 +6,6 @@
 // directory the caller chose: never a path, never `..`, never hidden, never a
 // Windows device name. Such a name can still be too long for a file name, and
 // `shortenToBytes` or `shortenKeepingExtension` cuts one short.
-// `defaultFileName` does both for the name a file is saved under when the
-// caller gives no path.
 //
 // A path the user typed (`--out`, `outPath`) is not passed through here: the
 // caller is trusted, the server is not.
@@ -63,12 +61,10 @@ export const shortenToBytes = (name: string, maxBytes: number): string => {
 // `name` cut short to fit in `maxBytes` bytes with `insert` put right before
 // its extension (`IMG_0001 (12).jpg`), each cut made as `shortenToBytes`
 // makes it. The part before the extension is cut first, so the extension is
-// kept whenever it fits, but that part always keeps its first character:
+// kept whenever it fits. When the extension alone leaves no room for
-// when the extension leaves no room for `insert` and that character, the
+// `insert`, the extension is cut short too, and the part before it keeps only
-// extension is cut short too, and the part before it keeps the bytes that cut
+// the bytes that cut leaves over. `insert` is never cut. With no `insert`, a
-// leaves over. So a name that does not start with a dot never comes back
+// name that fits comes back unchanged.
-// starting with one, which would hide it. `insert` is never cut. With no
-// `insert`, a name that fits comes back unchanged.
 export const shortenKeepingExtension = (
     name: string,
     maxBytes: number,
@@ -76,36 +72,7 @@ export const shortenKeepingExtension = (
 ): string => {
     const fullExt = extname(name);
     const stem = name.slice(0, name.length - fullExt.length);
-    const first = Array.from(stem)[0] ?? "";
+    const ext = shortenToBytes(fullExt, maxBytes - Buffer.byteLength(insert));
-    const ext = shortenToBytes(
-        fullExt,
-        maxBytes - Buffer.byteLength(insert + first),
-    );
     const room = maxBytes - Buffer.byteLength(insert + ext);
     return shortenToBytes(stem, room) + insert + ext;
 };
-
-// The name a file is saved under in the working directory when the caller
-// gives no path (`quak get` without `--out`, `downloadFile` without
-// `outPath`): `prefix` (`thumb_` for a thumbnail), then the file's title with
-// unsafe characters replaced, or `file-<id>` when the title is empty, cut
-// short so that the whole fits in a file name, keeping the title's extension
-// whenever it fits. `ext` (".mov"), when given, takes the place of the
-// title's extension before the name is cut short; a live photo's image and
-// video are each named with their own. The cut can leave a device name
-// (`CONSOLE.<long extension>` becomes `CON.<long extension>`); that name gets
-// a leading `_`, as `sanitizeFileName` gives one, and is cut a byte shorter to
-// leave room for it.
-export const defaultFileName = (
-    title: string,
-    fileID: number,
-    opts: { prefix?: string; ext?: string } = {},
-): string => {
-    const { prefix = "", ext } = opts;
-    const safe = sanitizeFileName(title, `file-${fileID}`);
-    const name = ext === undefined ? safe : withExtension(safe, ext);
-    const room = MAX_NAME_BYTES - Buffer.byteLength(prefix);
-    const cut = prefix + shortenKeepingExtension(name, room);
-    if (!RESERVED_DEVICE_NAME.test(cut)) return cut;
-    return `_${prefix}${shortenKeepingExtension(name, room - 1)}`;
-};

src/library/index.ts

@@ -18,16 +18,6 @@
 // the caller (the default reads stay silent and serve the last good copy). The
 // default methods and the background loop are unchanged.
 //
-// `freshCollections()` is the fresh read of the collection list alone (issue
-// #210): one collections request, no collection's files, and nothing stored,
-// for a caller such as `quak collections` that needs no more. A caller that
-// asks for each refresh it needs can also open the library with
-// `refreshOnOpen: false`, so that `open()` starts none.
-//
-// A refresh reports through `onProgress` each collection whose files it has
-// fetched, so a large account, whose first refresh fetches the files of every
-// collection, shows progress.
-//
 // A refresh stages all of its network work first and only mutates the store
 // once every fetch has succeeded. A refresh that fails partway therefore never
 // becomes visible to reads: the last good snapshot stays in place, and the
@@ -171,21 +161,18 @@ export interface LibraryClient {
 // exactly one of "done" or "failed"; "failed" carries the error message and
 // an ML "done" reports how many payloads it stored and, in `mlDataErrors`,
 // each file whose ML data did not decrypt, gunzip or parse, with the reason.
-// In between, a refresh fires "progress" after each collection whose files it
+// The precache fills ("precacheThumbnails"/"precacheOriginals", #48) fire
-// fetched: `fetched` is how many collections it has fetched the files of so
+// "started"/"done" around each sweep that has work, "done" reporting the count
-// far, `total` how many it will. The precache fills
+// newly cached.
-// ("precacheThumbnails"/"precacheOriginals", #48) fire "started"/"done" around
-// each sweep that has work, "done" reporting the count newly cached.
 export interface RefreshEvent {
     operation:
         | "refresh"
         | "fetchMLData"
         | "precacheThumbnails"
         | "precacheOriginals";
-    status: "started" | "progress" | "done" | "failed";
+    status: "started" | "done" | "failed";
     error?: string;
     fetched?: number;
-    total?: number;
     mlDataErrors?: { fileID: number; error: string }[];
 }
 
@@ -205,10 +192,6 @@ export interface LibraryOptions {
     // `Infinity` starts none: the library then refreshes only as it opens and
     // when `fresh()` or `backup()` asks.
     refreshIntervalSeconds?: number;
-    // Whether `open()` starts a refresh. Defaults to true. With false, `open()`
-    // returns at once onto what the cache holds, empty or not, and a refresh
-    // starts only when `fresh()` or `backup()` asks or the timer fires.
-    refreshOnOpen?: boolean;
     onProgress?: RefreshProgressCallback;
     // The bounded request pools (issue #45), shared by the ML-data fetch (the
     // metadata pool) and the content cache. Defaults to a fresh set at the
@@ -399,8 +382,7 @@ export class Library {
     // then opens empty with the failure recorded in `status()`. With an
     // existing cache the first refresh runs in the background and `open()`
     // returns as soon as the cached data is ready — an unreachable server does
-    // not block opening. With `refreshOnOpen: false` there is no first
+    // not block opening.
-    // refresh: `open()` returns onto the cache as it is.
     static async open(opts: LibraryOptions): Promise<Library> {
         const { userID } = opts.client.whoami();
         const cacheDirectory =
@@ -503,10 +485,7 @@ export class Library {
         // refresh.
         precache?.start();
 
-        if (opts.refreshOnOpen === false) {
+        if (store.loadedFromDisk) {
-            // The caller asks for each refresh it needs.
-            lib.scheduleNext();
-        } else if (store.loadedFromDisk) {
             // An existing copy already answers reads; refresh in the background
             // and start the interval once that first cycle settles.
             void lib.runRefresh().then(() => lib.scheduleNext());
@@ -610,21 +589,6 @@ export class Library {
         };
     }
 
-    // The fresh read of the collection list alone (issue #210): every live
-    // collection that decrypts, in the server's order, from one collections
-    // request. Unlike a refresh, it fetches no collection's files, which on a
-    // large account take long. Nothing is stored: a refresh fetches a
-    // collection's files only when the collection is new or has changed since
-    // the stored copy, so a collection stored here without its files would
-    // never have them fetched.
-    async freshCollections(): Promise<Collection[]> {
-        if (this.closed) throw new Error("the library is closed");
-        const { collections } = await this.client.collectionsSince({
-            sinceTime: 0,
-        });
-        return collections;
-    }
-
     // Back up every in-scope file to `opts.downloadDirectory`, or else the
     // library's, each original at its save path, with a durable failure
     // ledger (issue #51). Takes the lock in that directory first, unless the
@@ -778,28 +742,18 @@ export class Library {
         // Stage per-collection file diffs. A collection's files are
         // re-enumerated only when its updationTime has advanced past the cached
         // copy; an unchanged album's file list cannot have changed. New
-        // collections enumerate from the beginning of time. Each collection
+        // collections enumerate from the beginning of time.
-        // whose files are fetched is reported, with how many there are to
-        // fetch.
-        const changedCollections = page.collections.filter((collection) => {
-            const known = this.store.getCollection(collection.id);
-            return !known || collection.updationTime > known.updationTime;
-        });
         const filePages: { collectionID: number; page: FilesPage }[] = [];
-        for (const collection of changedCollections) {
+        for (const collection of page.collections) {
             const known = this.store.getCollection(collection.id);
+            if (known && collection.updationTime <= known.updationTime)
+                continue;
             const filePage = await this.client.filesSince({
                 collectionID: collection.id,
                 collectionKey: collection.key,
                 sinceTime: known ? known.updationTime : 0,
             });
             filePages.push({ collectionID: collection.id, page: filePage });
-            this.emit({
-                operation: "refresh",
-                status: "progress",
-                fetched: filePages.length,
-                total: changedCollections.length,
-            });
         }
 
         // Network work done; commit to the store and persist only if something

src/library/mldata.ts

@@ -61,7 +61,7 @@ export interface MLIndex {
 // Pull the CLIP embedding out of a payload, or undefined when it is absent or
 // misshapen. Kept strict so a bad payload is skipped rather than corrupting the
 // packed index.
-export const clipEmbedding = (payload: MLData): number[] | undefined => {
+const clipEmbedding = (payload: MLData): number[] | undefined => {
     const clip = payload.clip;
     if (typeof clip !== "object" || clip === null) return undefined;
     const embedding = (clip as { embedding?: unknown }).embedding;

src/metadata-backup.ts

@@ -1,7 +1,6 @@
 import { mkdirSync, readFileSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
 import * as jpeg from "jpeg-js";
-import { clipKeywords } from "./clip-keywords.js";
 import type { Client } from "./client.js";
 import { describeError } from "./errors.js";
 import { readExifTags } from "./exif.js";
@@ -18,10 +17,7 @@ import {
 } from "./mldata-fetch.js";
 import type { EnteFile } from "./model/types.js";
 
-// Reports one line of the dump's progress. `level` is "error" when the line
+export type ProgressCallback = (message: string) => void;
-// reports ML data that could not be read, and is left out for every other
-// line.
-export type ProgressCallback = (message: string, level?: "error") => void;
 
 export interface MetadataBackupOptions {
     exif?: boolean;
@@ -98,8 +94,7 @@ const extractExif = async (
 
 // Dump every decrypted metadata layer the account holds into a directory tree
 // of plain JSON: account, per-collection, and per-file records including the
-// private and public magic metadata and the ML data, with the keywords of its
+// private and public magic metadata and (by default) the ML data. Collections
-// CLIP embedding in place of the embedding (see clip-keywords.ts). Collections
 // and files are enumerated from the library's cache, which the caller refreshes
 // first. Returns how many files have no ML data because their ML data request
 // failed or their ML data did not decrypt, gunzip or parse; they are still
@@ -200,17 +195,13 @@ export const runMetadataBackup = async (
             for (const [id, payload] of payloads) mlDataMap.set(id, payload);
             for (const [id, err] of errors) {
                 const reason = describeError(err);
-                log(
+                log(`ML data of file ${id} could not be read: ${reason}`);
-                    `ML data of file ${id} could not be read: ${reason}`,
-                    "error",
-                );
                 mlDataErrors.set(id, reason);
             }
         } catch (err) {
             const reason = err instanceof Error ? err.message : String(err);
             log(
                 `ML data request for ${batch.length} file(s) failed: ${reason}`,
-                "error",
             );
             for (const id of batch) mlDataErrors.set(id, reason);
         }
@@ -232,16 +223,8 @@ export const runMetadataBackup = async (
         if (file.pubMagicMetadata)
             fileMeta.pubMagicMetadata = file.pubMagicMetadata;
 
-        // The ML data without the CLIP embedding, and the keywords that
-        // embedding gives.
         const ml = mlDataMap.get(file.id);
-        if (ml) {
+        if (ml) fileMeta.mlData = ml;
-            const { clip: _clip, ...mlDataWithoutClip } = ml;
-            fileMeta.mlData = mlDataWithoutClip;
-            const isVideo = file.metadata.fileType === "video";
-            const keywords = clipKeywords(ml, isVideo);
-            if (keywords) fileMeta.keywords = keywords;
-        }
         const mlError = mlDataErrors.get(file.id);
         if (mlError) fileMeta.mlDataError = mlError;
 

src/retry.ts

@@ -24,9 +24,6 @@ export interface RetryOptions {
     sleep?: (ms: number) => Promise<void>;
     // Injected so the jitter is reproducible under test.
     random?: () => number;
-    // Called before each wait with the error that failed attempt number
-    // `attempt` and how long the wait is, for a caller that logs retries.
-    onRetry?: (err: unknown, attempt: number, delayMs: number) => void;
 }
 
 export type ResolvedRetryOptions = Required<RetryOptions>;
@@ -38,7 +35,6 @@ export const DEFAULT_RETRY_OPTIONS: ResolvedRetryOptions = {
     sleep: (ms: number): Promise<void> =>
         new Promise((resolve) => setTimeout(resolve, ms)),
     random: Math.random,
-    onRetry: () => {},
 };
 
 // For a run nobody is watching, such as `quak backup` from cron. A request that
@@ -59,7 +55,6 @@ export const resolveRetryOptions = (
     maxDelayMs: opts?.maxDelayMs ?? DEFAULT_RETRY_OPTIONS.maxDelayMs,
     sleep: opts?.sleep ?? DEFAULT_RETRY_OPTIONS.sleep,
     random: opts?.random ?? DEFAULT_RETRY_OPTIONS.random,
-    onRetry: opts?.onRetry ?? DEFAULT_RETRY_OPTIONS.onRetry,
 });
 
 // Transport failures: the request did not complete, for reasons below HTTP.
@@ -239,9 +234,7 @@ export const withRetry = async <T>(
                 // and its status intact.
                 throw err;
             }
-            const delayMs = backoffMs(attempt, policy);
+            await policy.sleep(backoffMs(attempt, policy));
-            policy.onRetry(err, attempt, delayMs);
-            await policy.sleep(delayMs);
         }
     }
 };

src/thumbnails.ts

@@ -49,10 +49,7 @@ export interface ThumbnailFixResult {
     reason?: string;
 }
 
-// Reports one line of progress. `level` is "error" when the line reports a
+export type ProgressCallback = (message: string) => void;
-// file that could not be checked or fixed, and is left out for every other
-// line.
-export type ProgressCallback = (message: string, level?: "error") => void;
 
 // Enumerate every file the library knows about, newest album first, each file
 // once, and report those whose server-side thumbnail is missing. "Missing" is
@@ -114,7 +111,6 @@ export const listMissingThumbnails = async (
                 } else {
                     log(
                         `[${album.name}] Could not check ${photo.title}: ${err instanceof Error ? err.message : String(err)} (not reported as missing)`,
-                        "error",
                     );
                 }
             }
@@ -363,7 +359,6 @@ export const fixMissingThumbnails = async (
         } catch (err) {
             log(
                 `[${collectionName}] FAILED ${title}: ${err instanceof Error ? err.message : err}`,
-                "error",
             );
             results.push({
                 fileID,

test/api/client.test.ts

@@ -1222,65 +1222,3 @@ describe("ApiClient non-idempotent requests", () => {
         }
     });
 });
-
-// `onRequest` hears of each request the client sends, as its response arrives
-// or as it fails. The CLI logs these with `-vv`. A retried request is reported
-// once for each attempt.
-describe("ApiClient onRequest", () => {
-    it("reports each request with its status, or with the error it failed with", async () => {
-        const refused = new TypeError("fetch failed");
-        const { fetch } = scriptedFetch(
-            refused,
-            textResponse("unavailable", 503),
-            jsonResponse({ collections: [] }),
-            jsonResponse({}),
-            streamResponse(new Uint8Array([1, 2, 3])),
-        );
-        const requests: unknown[] = [];
-        const client = new ApiClient({
-            fetch,
-            retry: noWait,
-            onRequest: (request) => requests.push(request),
-        });
-
-        await client.getJSON("/collections/v2", { sinceTime: 0 });
-        await client.postJSON("/users/logout", {});
-        await readAll(await client.getFileStream(7));
-
-        const collections = "https://api.ente.io/collections/v2?sinceTime=0";
-        expect(requests).toEqual([
-            { method: "GET", url: collections, error: refused },
-            { method: "GET", url: collections, status: 503 },
-            { method: "GET", url: collections, status: 200 },
-            {
-                method: "POST",
-                url: "https://api.ente.io/users/logout",
-                status: 200,
-            },
-            {
-                method: "GET",
-                url: "https://files.ente.io/?fileID=7",
-                status: 200,
-            },
-        ]);
-    });
-
-    it("reports a presigned upload without its query, which holds the upload's signature", async () => {
-        const { fetch } = scriptedFetch(new Response(null, { status: 200 }));
-        const requests: unknown[] = [];
-        const client = new ApiClient({
-            fetch,
-            retry: noWait,
-            onRequest: (request) => requests.push(request),
-        });
-
-        await client.putFile(
-            "https://s3.example/obj?X-Amz-Signature=abc",
-            new Uint8Array([1, 2]),
-        );
-
-        expect(requests).toEqual([
-            { method: "PUT", url: "https://s3.example/obj", status: 200 },
-        ]);
-    });
-});

test/cli/backup-end-to-end.test.ts

@@ -54,7 +54,6 @@ import {
     saveSession,
     type CliContext,
 } from "../../src/cli-commands.js";
-import { stderrLog } from "../../src/cli-log.js";
 import { run } from "../../src/cli-run.js";
 import { loadSession } from "../../src/cli-session.js";
 import { Client } from "../../src/client.js";
@@ -86,17 +85,10 @@ const DAY = "2024/2024-03/2024-03-01";
 const TOAST = new TextEncoder().encode("a few seconds of the wedding toast");
 
 // Ente's ML data for beach.jpg: a face it found, and the photo's CLIP
-// embedding, here that of a photo of a sunset (see clip-keywords.test.ts).
+// embedding.
 const ML_DATA = {
     face: { faces: [{ faceID: "100_1", score: 0.98 }] },
-    clip: {
+    clip: { embedding: [0.5, 0.6, 0.7] },
-        embedding: JSON.parse(
-            readFileSync(
-                new URL("../clip-keywords-sunset.json", import.meta.url),
-                "utf-8",
-            ),
-        ).embedding,
-    },
 };
 
 // Each file's ID, its owner, its original as uploaded, and the metadata its
@@ -311,10 +303,9 @@ const backup = async (
     const prompted = async (): Promise<never> => {
         throw new Error("quak backup prompted");
     };
-    const log = stderrLog(stderr, "info");
     const ctx: CliContext = {
         stdout,
-        log,
+        stderr,
         sessionDir,
         cacheDir: `${dir}-cache`,
         loadSession: (path) =>
@@ -328,7 +319,7 @@ const backup = async (
         promptSecret: prompted,
     };
     const code = await new Promise<number>((resolve) => {
-        void run(backupCommand(ctx, dir, opts), stdout, stderr, log, resolve);
+        void run(backupCommand(ctx, dir, opts), stdout, stderr, resolve);
     });
     return { code, stderr: printed, stdout: output };
 };
@@ -493,10 +484,7 @@ describe("the first backup of the account", () => {
             },
             updationTime: TAKEN,
         });
-        // The JSON holds the ML data without its CLIP embedding, and the
+        expect(beach.mlData).toEqual(ML_DATA);
-        // keywords the embedding gives in its place.
-        expect(beach.mlData).toEqual({ face: ML_DATA.face });
-        expect(beach.keywords).toEqual(["Sunset"]);
         expect(beach.imageMetadata.exif.Make.description).toBe("Canon");
         expect(beach.imageMetadata.exif.Model.description).toBe("EOS R5");
 
@@ -507,7 +495,6 @@ describe("the first backup of the account", () => {
             metadata: { title: "toast.mp4", fileType: "video" },
         });
         expect(toast).not.toHaveProperty("mlData");
-        expect(toast).not.toHaveProperty("keywords");
         expect(toast).not.toHaveProperty("imageMetadata");
         expect(toast).not.toHaveProperty("imageMetadataError");
 
@@ -1117,9 +1104,6 @@ describe("a backup whose lock is lost", () => {
         expect(code).toBe(1);
         expect(stderr).toBe(
             "Starting backup...\n" +
-                "Fetched the files of 1 of 3 collections\n" +
-                "Fetched the files of 2 of 3 collections\n" +
-                "Fetched the files of 3 of 3 collections\n" +
                 "Refreshing library...\n" +
                 "Fetching original beach.jpg (100)...\n" +
                 "Fetching original IMG_0002.HEIC (300)...\n" +

test/cli/backup-undecryptable.test.ts

@@ -42,7 +42,6 @@ import {
     saveSession,
     type CliContext,
 } from "../../src/cli-commands.js";
-import { stderrLog } from "../../src/cli-log.js";
 import { loadSession } from "../../src/cli-session.js";
 import { Client, type ClientSnapshot } from "../../src/client.js";
 import { encryptBlob, init, toBase64 } from "../../src/crypto/index.js";
@@ -305,7 +304,7 @@ const context = (ente: FakeEnte): CliContext => {
     saveSession(join(root, "session"), ente.snapshot());
     return {
         stdout,
-        log: stderrLog(stderr, "info"),
+        stderr,
         sessionDir: join(root, "session"),
         cacheDir: join(root, "cache"),
         loadSession: (path) =>
@@ -371,24 +370,6 @@ describe("quak backup with records it cannot decrypt", () => {
         expect(stderr.text).toContain("  Failed:      2\n");
     });
 
-    // The album is an error line. The last line is fatal and counts the files
-    // and the album, so `-q`, which prints fatal lines only, still says why
-    // the backup exits 1.
-    it("logs the album at error, and ends with one fatal line counting the files and the album", async () => {
-        const ctx = {
-            ...context(brokenAccount()),
-            log: stderrLog(stderr, "error"),
-        };
-        expect(await backupCommand(ctx, backupDir(), {})).toBe(1);
-
-        expect(stderr.text).toMatch(
-            /^FAILED album 2: could not be decrypted: /,
-        );
-        expect(stderr.text.split("\n").at(-2)).toBe(
-            `quak: 2 file(s) and 1 album(s) failed; see ${join(backupDir(), "failures.json")} and the FAILED lines`,
-        );
-    });
-
     it("names each album it cannot decrypt in the --json result", async () => {
         expect(await backup(brokenAccount(), { json: true })).toBe(1);
 
@@ -567,7 +548,7 @@ describe("the read commands with records quak cannot decrypt", () => {
         expect(await collectionsCommand(context(ente), {})).toBe(0);
         expect(stdout.text).toBe("1\talbum\tTrip\n");
 
-        expect(await filesCommand(context(ente), "1", {})).toBe(0);
+        expect(await filesCommand(context(ente), { collection: "1" })).toBe(0);
         expect(stdout.text).toBe("10\timage\tphoto-10.jpg\n");
     });
 });

test/cli/backup.test.ts

@@ -52,7 +52,6 @@ import { tmpdir } from "node:os";
 import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
 
 import { runBackup, type BackupLibrary } from "../../src/backup.js";
-import { DISCOVER_CATEGORIES } from "../../src/clip-keyword-vectors.js";
 import { Library } from "../../src/library/index.js";
 import type { ContentSource } from "../../src/library/content.js";
 import type { CollectionsPage, FilesPage } from "../../src/client.js";
@@ -947,19 +946,9 @@ describe("the backup lock", () => {
     });
 });
 
-// Also serves ML data: file 100 has `ML_PAYLOAD`, whose CLIP embedding is that
+// Also serves ML data: file 100 has `ML_PAYLOAD`, the other two have none.
-// of a photo of a sunset (see clip-keywords.test.ts), and the other two have
+// While `mlError` is set, every ML data request fails with it.
-// none. While `mlError` is set, every ML data request fails with it.
+const ML_PAYLOAD = { face: { faces: [] }, clip: { embedding: [0.5, 0.25] } };
-const SUNSET_EMBEDDING: number[] = JSON.parse(
-    readFileSync(
-        new URL("../clip-keywords-sunset.json", import.meta.url),
-        "utf-8",
-    ),
-).embedding;
-const ML_PAYLOAD = {
-    face: { faces: [] },
-    clip: { embedding: SUNSET_EMBEDDING },
-};
 
 class MLClient extends MockClient {
     mlError?: string;
@@ -979,99 +968,16 @@ const fileJSON = (outDir: string, fileID: number): Record<string, unknown> =>
     JSON.parse(readFileSync(saved(outDir, `${fileID}.json`), "utf-8"));
 
 describe("ML data in each file's JSON", () => {
-    // The JSON holds the ML data without its CLIP embedding, and in its place
+    it("writes a file's ML data, and no ML field for a file that has none", async () => {
-    // the keywords the embedding gives.
-    it("writes a file's ML data and keywords, and no ML field for a file that has none", async () => {
         const lib = await openLibrary(stubSource(), new MLClient());
         const outDir = join(root, "backup");
 
         const result = await lib.backup({ downloadDirectory: outDir });
 
         expect(result.failed).toBe(0);
-        expect(fileJSON(outDir, 100).mlData).toEqual({ face: { faces: [] } });
+        expect(fileJSON(outDir, 100).mlData).toEqual(ML_PAYLOAD);
-        expect(fileJSON(outDir, 100).keywords).toEqual(["Sunset"]);
         expect(fileJSON(outDir, 101)).not.toHaveProperty("mlData");
         expect(fileJSON(outDir, 101)).not.toHaveProperty("mlDataError");
-        expect(fileJSON(outDir, 101)).not.toHaveProperty("keywords");
-        await lib.close();
-    });
-
-    // A file's ML data can hold faces and no CLIP embedding. Its JSON then has
-    // the ML data and no keywords.
-    it("writes no keywords for ML data without a CLIP embedding", async () => {
-        const faces = { face: { faces: [{ faceID: "101_1", score: 0.9 }] } };
-
-        // Gives file 101 ML data holding only faces.
-        class FacesClient extends MockClient {
-            async fetchMLData(args: { fileIDs: number[] }): Promise<{
-                payloads: Map<number, MLData>;
-                errors: Map<number, unknown>;
-            }> {
-                const payloads = new Map<number, MLData>();
-                if (args.fileIDs.includes(101)) payloads.set(101, faces);
-                return { payloads, errors: new Map() };
-            }
-        }
-        const lib = await openLibrary(stubSource(), new FacesClient());
-        const outDir = join(root, "backup");
-
-        const result = await lib.backup({ downloadDirectory: outDir });
-
-        expect(result.failed).toBe(0);
-        expect(fileJSON(outDir, 101).mlData).toEqual(faces);
-        expect(fileJSON(outDir, 101)).not.toHaveProperty("keywords");
-        await lib.close();
-    });
-
-    // Ente's photos app keeps videos out of some Discover categories, Identity
-    // among them. Here a photo and a video share one CLIP embedding, Identity's
-    // own text embedding, so the photo gets the keyword Identity and the video
-    // does not.
-    it("keeps a video out of a category that leaves out videos", async () => {
-        const identity = DISCOVER_CATEGORIES.find(
-            (c) => c.title === "Identity",
-        )!;
-        expect(identity.showVideo).toBe(false);
-        const toast = file(102, 1, "toast.mp4");
-        const video = {
-            ...toast,
-            metadata: { ...toast.metadata, fileType: "video" as const },
-        };
-
-        // Serves beach.jpg and the video in the Vacation album, and gives
-        // each ML data holding only that embedding.
-        class VideoClient extends MockClient {
-            override async filesSince(args: {
-                collectionID: number;
-            }): Promise<FilesPage> {
-                const files =
-                    args.collectionID === 1
-                        ? [file(100, 1, "beach.jpg"), video]
-                        : [];
-                return { files, deleted: [], cursor: 1 };
-            }
-            async fetchMLData(args: { fileIDs: number[] }): Promise<{
-                payloads: Map<number, MLData>;
-                errors: Map<number, unknown>;
-            }> {
-                const payloads = new Map<number, MLData>();
-                for (const id of args.fileIDs) {
-                    payloads.set(id, {
-                        clip: { embedding: identity.textEmbedding },
-                    });
-                }
-                return { payloads, errors: new Map() };
-            }
-        }
-        const lib = await openLibrary(stubSource(), new VideoClient());
-        const outDir = join(root, "backup");
-
-        const result = await lib.backup({ downloadDirectory: outDir });
-
-        expect(result.failed).toBe(0);
-        expect(fileJSON(outDir, 100).keywords).toContain("Identity");
-        expect(fileJSON(outDir, 102)).toHaveProperty("keywords");
-        expect(fileJSON(outDir, 102).keywords).not.toContain("Identity");
         await lib.close();
     });
 
@@ -1087,7 +993,7 @@ describe("ML data in each file's JSON", () => {
         const result = await lib.backup({ downloadDirectory: outDir });
 
         // File 100's ML data was cached by the first run and is kept.
-        expect(fileJSON(outDir, 100).mlData).toEqual({ face: { faces: [] } });
+        expect(fileJSON(outDir, 100).mlData).toEqual(ML_PAYLOAD);
         expect(fileJSON(outDir, 100)).not.toHaveProperty("mlDataError");
         for (const fileID of [101, 200]) {
             expect(fileJSON(outDir, fileID).mlDataError).toBe(
@@ -1120,7 +1026,7 @@ describe("ML data in each file's JSON", () => {
 
         expect(result.failed).toBe(0);
         expect(result.skipped).toBe(3);
-        expect(fileJSON(outDir, 100).mlData).toEqual({ face: { faces: [] } });
+        expect(fileJSON(outDir, 100).mlData).toEqual(ML_PAYLOAD);
         for (const fileID of [100, 101, 200]) {
             expect(fileJSON(outDir, fileID)).not.toHaveProperty("mlDataError");
         }
@@ -1889,11 +1795,12 @@ describe("backup album folders", () => {
         expect(readLedger(outDir).files["5"]).toMatchObject({ attempts: 1 });
     });
 
-    // The extensions of these titles leave no room for the ID and the "a"
+    // The extensions of these titles leave no room for the ID, so each is cut
-    // before them, so each is cut short to 250 bytes, which leaves one, for
+    // short and the name before the ID keeps only the bytes that cut leaves
-    // the "a". File 1's extension is 303 bytes and file 2's 271. Neither
+    // over. File 1's extension is 303 bytes and is cut to 251, which leaves
-    // extension is only letters and digits, so both originals are saved with
+    // none. File 2's is 271 bytes and is cut to 250, since "€" takes three
-    // `.bin`, a name that fits.
+    // bytes, which leaves one, for the "a". Neither extension is only letters
+    // and digits, so both originals are saved with `.bin`, a name that fits.
     it("cuts the extension of a title short when it leaves no room for the ID", async () => {
         const outDir = join(root, "backup");
         const lib = libraryOf([
@@ -1908,7 +1815,7 @@ describe("backup album folders", () => {
 
         const result = await runBackup(lib, { downloadDirectory: outDir });
 
-        const link = `a (1).${"L".repeat(249)}`;
+        const link = ` (1).${"L".repeat(250)}`;
         const link2 = `a (2).${"€".repeat(83)}`;
         expect(Buffer.byteLength(link)).toBe(255);
         expect(Buffer.byteLength(link2)).toBe(255);
@@ -1923,9 +1830,9 @@ describe("backup album folders", () => {
 
     // Files 1 and 3 share a title, so each gets its ID before the
     // extension. File 2's title is too long, and its extension leaves no
-    // room for the ID and the "x" before it. Were the ID put at the end of
+    // room for the ID. Were the ID put at the end of file 2's title cut
-    // file 2's title cut short, its link would have file 1's name, and the
+    // short, its link would have file 1's name, and the link made second
-    // link made second would replace the first.
+    // would replace the first.
     it("keeps names unique when a title's extension leaves no room for the ID", async () => {
         const outDir = join(root, "backup");
         const shared = `x.${"Q".repeat(245)} (2)`;
@@ -1945,8 +1852,8 @@ describe("backup album folders", () => {
         expect(result.failed).toBe(0);
         expect(tree(outDir)).toEqual([
             "Trip/",
+            `Trip/ (2).${"Q".repeat(250)} -> ${linkTo("2.bin")}`,
             `Trip/x (1).${"Q".repeat(245)} (2) -> ${linkTo("1.bin")}`,
-            `Trip/x (2).${"Q".repeat(249)} -> ${linkTo("2.bin")}`,
             `Trip/x (3).${"Q".repeat(245)} (2) -> ${linkTo("3.bin")}`,
             "Trip.json",
         ]);

test/cli/bin.test.ts

@@ -1,8 +1,6 @@
 /**
- * Tests for the retry options `bin/quak.ts` loads the saved session with
+ * Tests for the retry options `bin/quak.ts` loads the saved session with:
- * (`quak backup` gets the unattended ones, every other command the default),
+ * `quak backup` gets the unattended ones, every other command the default.
- * each with the callbacks that log its requests and retries, and for
- * `quak files` taking its collection ID as an optional argument.
  *
  * Each test runs `bin/quak.ts`, as the smoke test does, with its session loader
  * replaced by one that records the options it is given and reports no session,
@@ -28,19 +26,14 @@ vi.mock("../../src/cli-session.js", () => ({
 const argv = process.argv;
 const dir = mkdtempSync(join(tmpdir(), "quak-bin-test-"));
 
-// Run `quak <args>` to completion and return what it wrote on stderr, which is
+// Run `quak <args>` to completion. The "Not logged in" message and the exit
-// kept off the terminal. The exit is swallowed.
+// are swallowed.
-const quak = async (...args: string[]): Promise<string> => {
+const quak = async (...args: string[]): Promise<void> => {
-    let written = "";
+    vi.spyOn(process.stderr, "write").mockImplementation(() => true);
-    vi.spyOn(process.stderr, "write").mockImplementation((text) => {
-        written += String(text);
-        return true;
-    });
     vi.spyOn(process, "exit").mockImplementation(() => undefined as never);
     process.argv = ["node", "quak", ...args];
     vi.resetModules();
     await import("../../bin/quak.js");
-    return written;
 };
 
 afterEach(() => {
@@ -66,32 +59,13 @@ describe("bin/quak.ts session loading", () => {
                     attempts,
                     baseDelayMs,
                     maxDelayMs,
-                    onRetry: expect.any(Function),
                 }),
-                onRequest: expect.any(Function),
             },
         ]);
     });
 
-    it("loads the session for another command with the default retry options", async () => {
+    it("loads the session for another command with the default options", async () => {
         await quak("collections");
-        expect(loaded).toEqual([
+        expect(loaded).toEqual([undefined]);
-            {
-                retry: { onRetry: expect.any(Function) },
-                onRequest: expect.any(Function),
-            },
-        ]);
-    });
-});
-
-// The command line takes `files` with or without a collection ID, and the
-// command runs as far as its session check either way (issue #211).
-describe("bin/quak.ts files", () => {
-    it("runs without a collection ID", async () => {
-        expect(await quak("files")).toMatch(/^Not logged in/);
-    });
-
-    it("runs with a collection ID", async () => {
-        expect(await quak("files", "7")).toMatch(/^Not logged in/);
     });
 });

test/cli/commands.test.ts

@@ -51,24 +51,13 @@ import {
     listMissingThumbnailsCommand,
     fixMissingThumbnailsCommand,
 } from "../../src/cli-commands.js";
-import { stderrLog } from "../../src/cli-log.js";
 import { run } from "../../src/cli-run.js";
 import { loadSession } from "../../src/cli-session.js";
-import {
+import type { Client, ClientSnapshot, LoginOptions } from "../../src/client.js";
-    Client,
-    type ClientSnapshot,
-    type LoginOptions,
-} from "../../src/client.js";
 import { savePath, type ContentSource } from "../../src/library/content.js";
 import type { Collection, EnteFile } from "../../src/model/types.js";
 import { encryptBlob, init, toBase64 } from "../../src/crypto/index.js";
 import { defaultCacheDirectory } from "../../src/library/index.js";
-import {
-    buildAccount,
-    buildMetaFetch,
-    encryptSecretbox,
-    encryptStreamBlob,
-} from "../ente-server.js";
 import { HEIC_WITH_EXIF } from "../exif-heic.js";
 import {
     asLivePhoto,
@@ -122,31 +111,25 @@ const FILES: Record<number, EnteFile[]> = {
 // An original is 7 bytes and a thumbnail 3. `failID` makes that file's
 // original fail; `emptyThumbID` makes the server report that file's
 // thumbnail as empty. `withNewFile` adds new.jpg (102) to Vacation, advancing
-// the collection's updationTime as the server does. `beachInWork` adds
+// the collection's updationTime as the server does, and `refreshError` makes
-// beach.jpg (100) to Work as well, so that one file is in both albums.
+// listing collections fail with that message.
-// `refreshError` makes listing collections fail with that message.
 const fakeClient = (
     opts: {
         failID?: number;
         emptyThumbID?: number;
         withNewFile?: boolean;
-        beachInWork?: boolean;
         refreshError?: string;
     } = {},
 ) => {
     const collections = opts.withNewFile
         ? [{ ...COLLECTIONS[0], updationTime: 2 }, COLLECTIONS[1]]
         : COLLECTIONS;
-    let files = FILES;
+    const files = opts.withNewFile
-    if (opts.withNewFile) {
+        ? {
-        files = {
+              ...FILES,
-            ...files,
+              1: [...FILES[1], { ...file(102, 1, "new.jpg"), updationTime: 2 }],
-            1: [...files[1], { ...file(102, 1, "new.jpg"), updationTime: 2 }],
-        };
-    }
-    if (opts.beachInWork) {
-        files = { ...files, 2: [...files[2], file(100, 2, "beach.jpg")] };
           }
+        : FILES;
     const source: ContentSource = {
         original: async ({ file: f, destination }) => {
             if (f.id === opts.failID) throw new Error("HTTP 500 from server");
@@ -188,15 +171,6 @@ const fakeClient = (
     return fake as unknown as Client;
 };
 
-// What a read command prints on stderr while the refresh it waits for fetches
-// the files of each of the fake's two albums, on an empty cache.
-const FETCHED_BOTH_ALBUMS =
-    "Fetched the files of 1 of 2 collections\n" +
-    "Fetched the files of 2 of 2 collections\n";
-
-// The same for an account with one album.
-const FETCHED_ONE_ALBUM = "Fetched the files of 1 of 1 collections\n";
-
 // Collects everything written to it.
 class Output {
     text = "";
@@ -209,11 +183,9 @@ let root: string;
 let stdout: Output;
 let stderr: Output;
 
-// The commands log at the default level, info, as `quak` without `-v` or `-q`
-// does; the levels have their own tests, in `log.test.ts`.
 const context = (client: Client | null = fakeClient()): CliContext => ({
     stdout,
-    log: stderrLog(stderr, "info"),
+    stderr,
     sessionDir: join(root, "session"),
     cacheDir: join(root, "cache"),
     loadSession: () => client,
@@ -266,7 +238,7 @@ describe("session file", () => {
         const dir = join(root, "backup");
         expect(await whoamiCommand(ctx)).toBe(3);
         expect(await collectionsCommand(ctx, {})).toBe(3);
-        expect(await filesCommand(ctx, "1", {})).toBe(3);
+        expect(await filesCommand(ctx, { collection: "1" })).toBe(3);
         expect(await getCommand(ctx, "100", {})).toBe(3);
         expect(await getThumbCommand(ctx, "100", {})).toBe(3);
         expect(await backupMetadataCommand(ctx, dir, {})).toBe(3);
@@ -513,14 +485,17 @@ describe("collections", () => {
 
 describe("files", () => {
     it("prints one tab-separated line per file", async () => {
-        expect(await filesCommand(context(), "1", {})).toBe(0);
+        expect(await filesCommand(context(), { collection: "1" })).toBe(0);
         expect(stdout.text).toBe(
             "100\timage\tbeach.jpg\n" + "101\timage\tsunset.jpg\n",
         );
     });
 
     it("prints a JSON array with --json", async () => {
-        const code = await filesCommand(context(), "2", { json: true });
+        const code = await filesCommand(context(), {
+            collection: "2",
+            json: true,
+        });
         expect(code).toBe(0);
         expect(JSON.parse(stdout.text)).toEqual([
             {
@@ -534,42 +509,8 @@ describe("files", () => {
     });
 
     it("exits 1 for an unknown collection", async () => {
-        expect(await filesCommand(context(), "9", {})).toBe(1);
+        expect(await filesCommand(context(), { collection: "9" })).toBe(1);
-        expect(stderr.text).toBe(
+        expect(stderr.text).toBe("Collection 9 not found\n");
-            FETCHED_BOTH_ALBUMS + "Collection 9 not found\n",
-        );
-    });
-
-    // Without a collection ID it lists every file in the account once (issue
-    // #211). beach.jpg is in Vacation and Work, and Vacation comes first, so it
-    // is listed once, as Vacation's.
-    it("without a collection ID prints every file once", async () => {
-        const ctx = context(fakeClient({ beachInWork: true }));
-        expect(await filesCommand(ctx, undefined, {})).toBe(0);
-        expect(stdout.text).toBe(
-            "100\timage\tbeach.jpg\n" +
-                "101\timage\tsunset.jpg\n" +
-                "200\timage\tdiagram.png\n",
-        );
-        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS);
-    });
-
-    it("without a collection ID gives each file the first album holding it with --json", async () => {
-        const ctx = context(fakeClient({ beachInWork: true }));
-        expect(await filesCommand(ctx, undefined, { json: true })).toBe(0);
-        expect(
-            JSON.parse(stdout.text).map(
-                (row: { id: number; collectionID: number }) => [
-                    row.id,
-                    row.collectionID,
-                ],
-            ),
-        ).toEqual([
-            [100, 1],
-            [101, 1],
-            [200, 2],
-        ]);
-        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS);
     });
 });
 
@@ -578,27 +519,27 @@ describe("get and get-thumb", () => {
         const out = join(root, "diagram.png");
         expect(await getCommand(context(), "200", { out })).toBe(0);
         expect(readFileSync(out)).toEqual(Buffer.alloc(7, 200));
-        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + `7 bytes -> ${out}\n`);
+        expect(stderr.text).toBe(`7 bytes -> ${out}\n`);
     });
 
     it("get-thumb finds a file in any album without --collection", async () => {
         const out = join(root, "thumb.jpg");
         expect(await getThumbCommand(context(), "200", { out })).toBe(0);
         expect(readFileSync(out)).toEqual(Buffer.alloc(3, 200));
-        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + `3 bytes -> ${out}\n`);
+        expect(stderr.text).toBe(`3 bytes -> ${out}\n`);
     });
 
     it("get exits 1 when no album has the file", async () => {
         const out = join(root, "x");
         expect(await getCommand(context(), "999", { out })).toBe(1);
-        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + "File 999 not found\n");
+        expect(stderr.text).toBe("File 999 not found\n");
         expect(existsSync(out)).toBe(false);
     });
 
     it("get-thumb exits 1 when no album has the file", async () => {
         const out = join(root, "x");
         expect(await getThumbCommand(context(), "999", { out })).toBe(1);
-        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + "File 999 not found\n");
+        expect(stderr.text).toBe("File 999 not found\n");
         expect(existsSync(out)).toBe(false);
     });
 });
@@ -646,7 +587,7 @@ describe("names from an album name or a title over 255 bytes", () => {
         expect(Buffer.byteLength(name)).toBe(255);
         expect(code).toBe(0);
         expect(readdirSync(dir)).toEqual([name]);
-        expect(stderr.text).toBe(FETCHED_ONE_ALBUM + `7 bytes -> ${name}\n`);
+        expect(stderr.text).toBe(`7 bytes -> ${name}\n`);
     });
 
     it("get-thumb cuts the title short so that thumb_ and it fit in 255 bytes, and exits 0", async () => {
@@ -658,7 +599,7 @@ describe("names from an album name or a title over 255 bytes", () => {
         expect(Buffer.byteLength(name)).toBe(255);
         expect(code).toBe(0);
         expect(readdirSync(dir)).toEqual([name]);
-        expect(stderr.text).toBe(FETCHED_ONE_ALBUM + `3 bytes -> ${name}\n`);
+        expect(stderr.text).toBe(`3 bytes -> ${name}\n`);
     });
 
     it("backup-metadata cuts the album name short so that its folder's name fits in 255 bytes, and exits 0", async () => {
@@ -700,12 +641,9 @@ describe("names from an album name or a title over 255 bytes", () => {
 // one live photo, 300, downloaded through the real download layer
 // (test/live-photo.ts).
 describe("a live photo", () => {
-    const livePhotoClient = async (
+    const livePhotoClient = async (image = IMAGE): Promise<Client> => {
-        image = IMAGE,
-        title = "IMG_0300.HEIC",
-    ): Promise<Client> => {
         const { file: live, body } = await asLivePhoto(
-            file(300, 1, title),
+            file(300, 1, "IMG_0300.HEIC"),
             livePhotoZip({ "image.heic": image, "video.mov": VIDEO }),
             livePhotoHash(image, VIDEO),
         );
@@ -747,50 +685,11 @@ describe("a live photo", () => {
             Buffer.from(VIDEO),
         );
         expect(stderr.text).toBe(
-            FETCHED_ONE_ALBUM +
             `${IMAGE.length} bytes -> IMG_0300.heic\n` +
                 `${VIDEO.length} bytes -> IMG_0300.mov\n`,
         );
     });
 
-    // Run `get` without `--out` in a new directory for a live photo titled
-    // `title`, and return its exit code and the names it wrote.
-    const getInNewDirectory = async (
-        title: string,
-    ): Promise<{ code: number; names: string[] }> => {
-        const ctx = context(await livePhotoClient(IMAGE, title));
-        const dir = mkdtempSync(join(root, "cwd-"));
-        const previous = process.cwd();
-        process.chdir(dir);
-        try {
-            const code = await getCommand(ctx, "300", {});
-            return { code, names: readdirSync(dir).sort() };
-        } finally {
-            process.chdir(previous);
-        }
-    };
-    const imageName = `${"t".repeat(250)}.heic`;
-    const videoName = `${"t".repeat(251)}.mov`;
-
-    // The title fits, but ".heic" is one byte longer than ".jpg", so the
-    // image's name is cut short once its extension is in it.
-    it("get cuts its image's name short for a 255-byte title ending in .jpg, and exits 0", async () => {
-        const title = `${"t".repeat(251)}.jpg`;
-
-        const result = await getInNewDirectory(title);
-
-        expect(Buffer.byteLength(title)).toBe(255);
-        expect(Buffer.byteLength(imageName)).toBe(255);
-        expect(Buffer.byteLength(videoName)).toBe(255);
-        expect(result).toEqual({ code: 0, names: [imageName, videoName] });
-    });
-
-    it("get cuts the names of its image and video short for a 300-byte title with no extension, and exits 0", async () => {
-        const result = await getInNewDirectory("t".repeat(300));
-
-        expect(result).toEqual({ code: 0, names: [imageName, videoName] });
-    });
-
     it("get --out writes the image there and the video beside it", async () => {
         const out = join(root, "photo.jpg");
         const video = join(root, "photo.mov");
@@ -802,7 +701,6 @@ describe("a live photo", () => {
         expect(readFileSync(out)).toEqual(Buffer.from(IMAGE));
         expect(readFileSync(video)).toEqual(Buffer.from(VIDEO));
         expect(stderr.text).toBe(
-            FETCHED_ONE_ALBUM +
             `${IMAGE.length} bytes -> ${out}\n${VIDEO.length} bytes -> ${video}\n`,
         );
     });
@@ -817,7 +715,6 @@ describe("a live photo", () => {
         expect(existsSync(out)).toBe(false);
         expect(existsSync(join(root, "photo.mov"))).toBe(false);
         expect(stderr.text).toBe(
-            FETCHED_ONE_ALBUM +
             `File 300 is a live photo, and its video would also be written to ${out}\n`,
         );
     });
@@ -913,40 +810,6 @@ describe("backup", () => {
         );
     });
 
-    // A failed file is an error line both where the backup fails it and in
-    // the list at the end. The last line is fatal, so `-q`, which prints
-    // fatal lines only, still says why the backup exits 1.
-    it("logs a failed file at error, and ends with one fatal line counting the failures", async () => {
-        const dir = join(root, "backup");
-        const last = `quak: 1 file(s) and 0 album(s) failed; see ${join(dir, "failures.json")} and the FAILED lines\n`;
-        const ctx = context(fakeClient({ failID: 101 }));
-        expect(
-            await backupCommand(
-                { ...ctx, log: stderrLog(stderr, "error") },
-                dir,
-                {},
-            ),
-        ).toBe(1);
-        expect(stderr.text).toBe(
-            "FAILED original sunset.jpg: HTTP 500 from server\n" +
-                "\nFailed files:\n" +
-                "  [Vacation] sunset.jpg (id 101): HTTP 500 from server\n" +
-                last,
-        );
-
-        stderr.text = "";
-        expect(
-            await backupCommand(
-                { ...ctx, log: stderrLog(stderr, "fatal") },
-                dir,
-                { json: true },
-            ),
-        ).toBe(1);
-        expect(stderr.text).toBe(last);
-    });
-
-    // `--json` shapes stdout only: the log lines stay on stderr, and the JSON
-    // takes the place of the summary.
     it("prints the result as JSON with --json, still exiting 1 on a failure", async () => {
         const ctx = context(fakeClient({ failID: 101 }));
         const code = await backupCommand(ctx, join(root, "backup"), {
@@ -961,31 +824,7 @@ describe("backup", () => {
             failed: 1,
         });
         expect(result.errors[0].fileID).toBe(101);
-        expect(stderr.text).toContain(
+        expect(stderr.text).toBe("Starting backup...\n");
-            "Fetching original sunset.jpg (101)...\n",
-        );
-        expect(stderr.text).not.toContain("Backup complete");
-    });
-
-    // On an empty cache the library's first refresh fetches the files of
-    // every album before the backup can start, which on a large account takes
-    // a while; each album it has fetched the files of is counted on stderr,
-    // with `--json` too.
-    it("counts on stderr each album whose files its first refresh fetched, with --json too", async () => {
-        const start =
-            "Starting backup...\n" +
-            FETCHED_BOTH_ALBUMS +
-            "Refreshing library...\n";
-        for (const json of [false, true]) {
-            stderr.text = "";
-            const dir = mkdtempSync(join(root, "backup-"));
-            const ctx = {
-                ...context(),
-                cacheDir: mkdtempSync(join(root, "cache-")),
-            };
-            expect(await backupCommand(ctx, dir, { json })).toBe(0);
-            expect(stderr.text.slice(0, start.length)).toBe(start);
-        }
     });
 
     it("--verify downloads again an original that does not match its hash, prints the counts, and exits 0", async () => {
@@ -1075,7 +914,6 @@ describe("backup", () => {
                 backupCommand(ctx, dir, {}),
                 new PassThrough(),
                 runStderr,
-                stderrLog(runStderr, "info"),
                 resolve,
             );
         });
@@ -1316,9 +1154,7 @@ describe("helper list-missing-thumbnails", () => {
         expect(stderr.text).toContain("No missing thumbnails found.\n");
     });
 
-    // `--json` shapes stdout only: the progress stays on stderr, and the JSON
+    it("prints a JSON array with --json and no progress", async () => {
-    // takes the place of the count and the list.
-    it("prints a JSON array with --json, and its progress on stderr", async () => {
         const ctx = context(fakeClient({ emptyThumbID: 200 }));
         expect(await listMissingThumbnailsCommand(ctx, { json: true })).toBe(0);
         expect(JSON.parse(stdout.text)).toEqual([
@@ -1329,37 +1165,7 @@ describe("helper list-missing-thumbnails", () => {
                 reason: "empty thumbnail (0 bytes)",
             },
         ]);
-        expect(stderr.text).toContain(FETCHED_BOTH_ALBUMS);
+        expect(stderr.text).toBe("");
-        expect(stderr.text).toContain("[Work] Checking thumbnails...\n");
-        expect(stderr.text).not.toContain("with missing thumbnails");
-    });
-});
-
-describe("helper fix-missing-thumbnails", () => {
-    // File 999 is in no album, so fixing it fails. The list of failed files
-    // is at error, and the last line is fatal, so `-q`, which prints fatal
-    // lines only, still says why the command exits 1.
-    it("lists a failed file at error, and ends with one fatal line counting the failures", async () => {
-        const last = `quak: 1 file(s) failed; see the "Failed files:" list, or the JSON with --json\n`;
-        const ctx = { ...context(), log: stderrLog(stderr, "error") };
-        expect(await fixMissingThumbnailsCommand(ctx, { file: ["999"] })).toBe(
-            1,
-        );
-        expect(stderr.text).toBe(
-            "\nFailed files:\n" +
-                "  999\tunknown\tfile not found in any collection\n" +
-                last,
-        );
-
-        stderr.text = "";
-        const quiet = { ...context(), log: stderrLog(stderr, "fatal") };
-        expect(
-            await fixMissingThumbnailsCommand(quiet, {
-                file: ["999"],
-                json: true,
-            }),
-        ).toBe(1);
-        expect(stderr.text).toBe(last);
     });
 });
 
@@ -1389,12 +1195,11 @@ describe("backup-metadata --exif", () => {
     });
 });
 
-// Each test first runs `files` so the cache holds the account as it was, then
+// Each test first runs `collections` so the cache holds the account as it was,
-// changes the server under it. (`collections` would not do: it reads the
+// then changes the server under it.
-// collection list alone and stores nothing.)
 describe("backup-metadata and the thumbnail helpers refresh first", () => {
     beforeEach(async () => {
-        expect(await filesCommand(context(), "1", {})).toBe(0);
+        expect(await collectionsCommand(context(), {})).toBe(0);
         stdout.text = "";
         stderr.text = "";
     });
@@ -1453,10 +1258,10 @@ describe("backup-metadata and the thumbnail helpers refresh first", () => {
     });
 });
 
-// `files`, `get`, `get-thumb` and `helper fix-missing-thumbnails --file` take
+// `files --collection`, `get`, `get-thumb` and `helper fix-missing-thumbnails
-// an ID only when it is written in decimal digits and is a safe integer.
+// --file` take an ID only when it is written in decimal digits and is a safe
-// `Number()` alone reads `0x10` as 16, `1e3` as 1000 and an empty string as 0,
+// integer. `Number()` alone reads `0x10` as 16, `1e3` as 1000 and an empty
-// so the command would act on a file the user never named.
+// string as 0, so the command would act on a file the user never named.
 // Anything else is refused with one line naming it, and exit 1, before any
 // request.
 //
@@ -1510,18 +1315,21 @@ describe("an ID given on the command line", () => {
 
     it("files looks up a decimal collection ID", async () => {
         const ctx = emptyAccount();
-        expect(await filesCommand(ctx, "1", {})).toBe(1);
+        expect(await filesCommand(ctx, { collection: "1" })).toBe(1);
         expect(stderr.text).toBe("Collection 1 not found\n");
         expect(requests).not.toHaveLength(0);
     });
 
-    it.each(NOT_IDS)("files refuses %j before any request", async (arg) => {
+    it.each(NOT_IDS)(
+        "files refuses --collection %j before any request",
+        async (arg) => {
             const ctx = emptyAccount();
-        expect(await filesCommand(ctx, arg, {})).toBe(1);
+            expect(await filesCommand(ctx, { collection: arg })).toBe(1);
             expect(stderr.text).toBe(`Invalid collection ID: ${arg}\n`);
             expect(stdout.text).toBe("");
             expect(requests).toHaveLength(0);
-    });
+        },
+    );
 
     it("get looks up a decimal file ID", async () => {
         expect(await getCommand(emptyAccount(), "100", {})).toBe(1);
@@ -1576,168 +1384,3 @@ describe("an ID given on the command line", () => {
         },
     );
 });
-
-// An account with many albums (issue #210). On an empty cache `collections`
-// used to wait for a refresh that fetched and decrypted the files of every
-// album, one album after another, before it printed anything, so on such an
-// account it seemed to hang. The account here has 40 albums of one photo each,
-// encrypted as Ente's clients encrypt them, on the fake Ente server of
-// `test/ente-server.ts`, which also records the path of each request quak
-// sends. The session is the one logging in to that server saves.
-describe("an account with many albums", () => {
-    const ALBUMS = 40;
-    const PASSWORD = "many-albums";
-    const paths: string[] = [];
-    let server: typeof globalThis.fetch;
-    let snapshot: ClientSnapshot;
-
-    // Album n is named `Album n` and holds one photo, n * 100, titled
-    // `photo-n.jpg`.
-    beforeAll(async () => {
-        await sodium.ready;
-        const account = await buildAccount(PASSWORD);
-        const collections: Record<string, unknown>[] = [];
-        const filesByCollection: Record<number, Record<string, unknown>[]> = {};
-        for (let id = 1; id <= ALBUMS; id++) {
-            const albumKey = sodium.crypto_secretbox_keygen();
-            const albumKeyBox = encryptSecretbox(albumKey, account.masterKey);
-            const name = encryptSecretbox(
-                new TextEncoder().encode(`Album ${id}`),
-                albumKey,
-            );
-            collections.push({
-                id,
-                owner: { id: USER_ID },
-                encryptedKey: toBase64(albumKeyBox.ciphertext),
-                keyDecryptionNonce: toBase64(albumKeyBox.nonce),
-                encryptedName: toBase64(name.ciphertext),
-                nameDecryptionNonce: toBase64(name.nonce),
-                type: "album",
-                updationTime: 1,
-            });
-            const photoKey =
-                sodium.crypto_secretstream_xchacha20poly1305_keygen();
-            const photoKeyBox = encryptSecretbox(photoKey, albumKey);
-            const metadata = encryptStreamBlob(
-                new TextEncoder().encode(
-                    JSON.stringify({
-                        title: `photo-${id}.jpg`,
-                        fileType: 0,
-                        creationTime: 1000,
-                        modificationTime: 1000,
-                    }),
-                ),
-                photoKey,
-            );
-            filesByCollection[id] = [
-                {
-                    id: id * 100,
-                    collectionID: id,
-                    ownerID: USER_ID,
-                    encryptedKey: toBase64(photoKeyBox.ciphertext),
-                    keyDecryptionNonce: toBase64(photoKeyBox.nonce),
-                    metadata: {
-                        encryptedData: toBase64(metadata.ciphertext),
-                        decryptionHeader: toBase64(metadata.header),
-                    },
-                    // These tests fetch no original and no thumbnail.
-                    file: { decryptionHeader: "" },
-                    thumbnail: { decryptionHeader: "" },
-                    updationTime: 1,
-                },
-            ];
-        }
-        const ente = buildMetaFetch({
-            verifier: account.verifier,
-            srpAttributes: account.srpAttributes,
-            keyAttributes: account.keyAttributes,
-            encryptedToken: account.encryptedToken,
-            collections,
-            filesByCollection,
-            encryptedMLData: {},
-            fileCiphertexts: {},
-        });
-        server = (async (input: RequestInfo | URL, init?: RequestInit) => {
-            const url =
-                typeof input === "string"
-                    ? input
-                    : input instanceof URL
-                      ? input.href
-                      : input.url;
-            paths.push(new URL(url).pathname);
-            return ente(input, init);
-        }) as typeof globalThis.fetch;
-        const client = await Client.login({
-            email: "many@example.com",
-            password: PASSWORD,
-            apiOptions: { fetch: server },
-        });
-        snapshot = client.toJSON();
-    });
-
-    beforeEach(() => {
-        paths.length = 0;
-    });
-
-    // A context whose saved session sends its requests to the fake server.
-    const accountContext = (): CliContext => {
-        const ctx = context();
-        saveSession(ctx.sessionDir, snapshot);
-        return {
-            ...ctx,
-            loadSession: (path) => loadSession(path, { fetch: server }),
-        };
-    };
-
-    it("collections lists every album from one request, fetching no album's files", async () => {
-        const ctx = accountContext();
-        expect(await collectionsCommand(ctx, {})).toBe(0);
-
-        let albums = "";
-        for (let id = 1; id <= ALBUMS; id++)
-            albums += `${id}\talbum\tAlbum ${id}\n`;
-        expect(stdout.text).toBe(albums);
-        expect(stderr.text).toBe("");
-        expect(paths).toEqual(["/collections/v2"]);
-
-        // It stored nothing that would make a refresh skip an album's files:
-        // `files` after it still finds the album's photo.
-        stdout.text = "";
-        expect(await filesCommand(ctx, "7", {})).toBe(0);
-        expect(stdout.text).toBe("700\timage\tphoto-7.jpg\n");
-    });
-
-    it("files counts on stderr each album whose files its refresh fetched", async () => {
-        expect(await filesCommand(accountContext(), "7", {})).toBe(0);
-
-        expect(stdout.text).toBe("700\timage\tphoto-7.jpg\n");
-        let progress = "";
-        for (let n = 1; n <= ALBUMS; n++) {
-            progress += `Fetched the files of ${n} of ${ALBUMS} collections\n`;
-        }
-        expect(stderr.text).toBe(progress);
-    });
-
-    // `--json` shapes stdout only, so the refresh's progress is still counted
-    // on stderr.
-    it("files --json counts on stderr each album whose files its refresh fetched", async () => {
-        expect(await filesCommand(accountContext(), "7", { json: true })).toBe(
-            0,
-        );
-
-        expect(JSON.parse(stdout.text)).toEqual([
-            {
-                id: 700,
-                title: "photo-7.jpg",
-                fileType: "image",
-                creationTime: 1000,
-                collectionID: 7,
-            },
-        ]);
-        let progress = "";
-        for (let n = 1; n <= ALBUMS; n++) {
-            progress += `Fetched the files of ${n} of ${ALBUMS} collections\n`;
-        }
-        expect(stderr.text).toBe(progress);
-    });
-});

test/cli/log.test.ts

@@ -1,357 +0,0 @@
-/**
- * Tests for the CLI's log levels, set with `-v`/`--verbose` and `-q`/`--quiet`
- * (`src/cli-log.ts`, issue #212).
- *
- * Every line quak prints on stderr is a log line at one of six levels, from
- * the quietest: fatal, error, warning, info, debug, trace. A run prints the
- * lines at its own level and at every quieter one. The level is info unless
- * asked otherwise: `-v` raises it to debug, `-vv` to trace, and more repeats
- * stay at trace. `-q` lowers it to fatal, so a run prints only the line a
- * command prints as it fails with a non-zero exit code. stdout holds the
- * command's output at every level.
- *
- * Most tests run `bin/quak.ts`, as the smoke test does, against an account of
- * one album holding one photo: the saved session is in a temporary directory,
- * and `fetch` is a fake of the Ente server that serves the album and the photo
- * encrypted as Ente's clients encrypt them. Each run has a cache directory of
- * its own, so its refresh fetches the album's files, as on a first run.
- */
-
-import { mkdtempSync, rmSync } from "node:fs";
-import { tmpdir } from "node:os";
-import { join } from "node:path";
-import sodium from "libsodium-wrappers-sumo";
-import {
-    afterAll,
-    afterEach,
-    beforeAll,
-    describe,
-    expect,
-    it,
-    vi,
-} from "vitest";
-
-import { ApiClient } from "../../src/api/client.js";
-import { saveSession } from "../../src/cli-commands.js";
-import { logRefresh, logRequests, type Log } from "../../src/cli-log.js";
-import { init, toBase64 } from "../../src/crypto/index.js";
-import { encryptSecretbox, encryptStreamBlob } from "../ente-server.js";
-
-// `bin/quak.ts` reads the saved session from the data directory env-paths
-// gives it, which here is a temporary directory made before the first run.
-const paths = vi.hoisted(() => ({ data: "" }));
-vi.mock("env-paths", () => ({ default: () => paths }));
-
-const USER_ID = 42;
-const root = mkdtempSync(join(tmpdir(), "quak-log-test-"));
-const argv = process.argv;
-
-class ExitCalled extends Error {}
-
-// Run `quak <args>` to its exit, with a cache of its own, and return its exit
-// code and what it wrote on stdout and on stderr, which are kept off the
-// terminal. `process.exit` is stubbed to throw, so nothing runs after it, as
-// nothing does after a real exit.
-const quak = async (
-    ...args: string[]
-): Promise<{ code: number; stdout: string; stderr: string }> => {
-    let stdout = "";
-    let stderr = "";
-    let code = NaN;
-    vi.spyOn(process.stdout, "write").mockImplementation((text) => {
-        stdout += String(text);
-        return true;
-    });
-    vi.spyOn(process.stderr, "write").mockImplementation((text) => {
-        stderr += String(text);
-        return true;
-    });
-    vi.spyOn(process, "exit").mockImplementation((exitCode) => {
-        code = Number(exitCode ?? 0);
-        throw new ExitCalled();
-    });
-    const cache = mkdtempSync(join(root, "cache-"));
-    process.argv = ["node", "quak", "--cache-dir", cache, ...args];
-    vi.resetModules();
-    await expect(import("../../bin/quak.js")).rejects.toBeInstanceOf(
-        ExitCalled,
-    );
-    return { code, stdout, stderr };
-};
-
-// Album 1, "Trips", of user 42, holding photo 100, "beach.jpg". The album's
-// key is encrypted with the account's master key, the photo's key with the
-// album's, and the photo's metadata with its own key. Only the session and
-// these two records are needed: the tests never log in.
-beforeAll(async () => {
-    await init();
-    await sodium.ready;
-    const masterKey = sodium.crypto_secretbox_keygen();
-    const keyPair = sodium.crypto_box_keypair();
-    paths.data = join(root, "session");
-    saveSession(paths.data, {
-        email: "log@example.com",
-        userID: USER_ID,
-        token: "token",
-        masterKey: toBase64(masterKey),
-        secretKey: toBase64(keyPair.privateKey),
-        publicKey: toBase64(keyPair.publicKey),
-    });
-
-    const albumKey = sodium.crypto_secretbox_keygen();
-    const albumKeyBox = encryptSecretbox(albumKey, masterKey);
-    const name = encryptSecretbox(new TextEncoder().encode("Trips"), albumKey);
-    const album = {
-        id: 1,
-        owner: { id: USER_ID },
-        encryptedKey: toBase64(albumKeyBox.ciphertext),
-        keyDecryptionNonce: toBase64(albumKeyBox.nonce),
-        encryptedName: toBase64(name.ciphertext),
-        nameDecryptionNonce: toBase64(name.nonce),
-        type: "album",
-        updationTime: 1,
-    };
-    const photoKey = sodium.crypto_secretstream_xchacha20poly1305_keygen();
-    const photoKeyBox = encryptSecretbox(photoKey, albumKey);
-    const metadata = encryptStreamBlob(
-        new TextEncoder().encode(
-            JSON.stringify({
-                title: "beach.jpg",
-                fileType: 0,
-                creationTime: 1000,
-                modificationTime: 1000,
-            }),
-        ),
-        photoKey,
-    );
-    const photo = {
-        id: 100,
-        collectionID: 1,
-        ownerID: USER_ID,
-        encryptedKey: toBase64(photoKeyBox.ciphertext),
-        keyDecryptionNonce: toBase64(photoKeyBox.nonce),
-        metadata: {
-            encryptedData: toBase64(metadata.ciphertext),
-            decryptionHeader: toBase64(metadata.header),
-        },
-        // These tests fetch no original and no thumbnail.
-        file: { decryptionHeader: "" },
-        thumbnail: { decryptionHeader: "" },
-        updationTime: 1,
-    };
-
-    const json = (body: unknown): Response =>
-        new Response(JSON.stringify(body), {
-            headers: { "content-type": "application/json" },
-        });
-    vi.stubGlobal("fetch", async (input: string) => {
-        const { pathname } = new URL(input);
-        if (pathname === "/collections/v2") {
-            return json({ collections: [album] });
-        }
-        if (pathname === "/collections/v2/diff") {
-            return json({ diff: [photo], hasMore: false });
-        }
-        return new Response("not found", { status: 404 });
-    });
-});
-
-afterEach(() => {
-    process.argv = argv;
-    vi.restoreAllMocks();
-});
-
-afterAll(() => {
-    vi.unstubAllGlobals();
-    rmSync(root, { recursive: true, force: true });
-});
-
-// What `quak files` writes on stdout at every level.
-const FILES = "100\timage\tbeach.jpg\n";
-
-// What it writes on stderr at each level. Info is the refresh's progress, one
-// line for the one album whose files it fetched. Debug adds the start and end
-// of the refresh, and trace each request with the status of its answer.
-const INFO = "Fetched the files of 1 of 1 collections\n";
-const DEBUG = "Refresh started\n" + INFO + "Refresh done\n";
-const TRACE =
-    "Refresh started\n" +
-    "GET https://api.ente.io/collections/v2?sinceTime=0: HTTP 200\n" +
-    "GET https://api.ente.io/collections/v2/diff?collectionID=1&sinceTime=0: HTTP 200\n" +
-    INFO +
-    "Refresh done\n";
-
-describe("the log level", () => {
-    it("is info by default", async () => {
-        expect(await quak("files")).toEqual({
-            code: 0,
-            stdout: FILES,
-            stderr: INFO,
-        });
-    });
-
-    it("is debug with -v", async () => {
-        expect(await quak("-v", "files")).toEqual({
-            code: 0,
-            stdout: FILES,
-            stderr: DEBUG,
-        });
-    });
-
-    it("is trace with -vv", async () => {
-        expect(await quak("-vv", "files")).toEqual({
-            code: 0,
-            stdout: FILES,
-            stderr: TRACE,
-        });
-    });
-
-    it("stays at trace with -vvv", async () => {
-        expect((await quak("-vvv", "files")).stderr).toBe(TRACE);
-    });
-
-    it("counts --verbose --verbose as -vv", async () => {
-        expect((await quak("--verbose", "--verbose", "files")).stderr).toBe(
-            TRACE,
-        );
-    });
-
-    // Both are options of the program, taken before or after the command's
-    // name, as `--cache-dir` is.
-    it("is set by an option after the command's name too", async () => {
-        expect((await quak("files", "-v")).stderr).toBe(DEBUG);
-        expect((await quak("files", "--json", "-vv")).stderr).toBe(TRACE);
-        expect((await quak("files", "-q")).stderr).toBe("");
-    });
-});
-
-describe("-q", () => {
-    it("prints nothing on stderr when the command works", async () => {
-        expect(await quak("-q", "files")).toEqual({
-            code: 0,
-            stdout: FILES,
-            stderr: "",
-        });
-    });
-
-    // The refresh's progress is left out; the line saying why the command
-    // failed is the fatal one, and it is printed.
-    it("prints only the line a failing command exits with", async () => {
-        expect(await quak("-q", "files", "9")).toEqual({
-            code: 1,
-            stdout: "",
-            stderr: "Collection 9 not found\n",
-        });
-    });
-
-    it("is refused with -v, in one line, before the command runs", async () => {
-        for (const args of [
-            ["-q", "-v", "files"],
-            ["files", "--verbose", "--quiet"],
-        ]) {
-            const { code, stdout, stderr } = await quak(...args);
-            expect(code).toBe(1);
-            expect(stdout).toBe("");
-            expect(stderr).toBe(
-                "error: option '-q, --quiet' cannot be used with option '-v, --verbose'\n",
-            );
-        }
-    });
-});
-
-// `--help` lists both options, and each command's help lists them too, since
-// each command takes them.
-describe("--help", () => {
-    it("lists -v and -q for the program and for each command", async () => {
-        for (const args of [["--help"], ["files", "--help"]]) {
-            const { stdout } = await quak(...args);
-            expect(stdout).toContain("-v, --verbose");
-            expect(stdout).toContain("-q, --quiet");
-        }
-    });
-});
-
-// The library writes no lines itself. Its layers report through callbacks,
-// and the CLI logs what they report.
-describe("what the library reports", () => {
-    const collect = (): { log: Log; lines: string[] } => {
-        const lines: string[] = [];
-        return { log: (level, line) => lines.push(`${level}: ${line}`), lines };
-    };
-
-    // A request answered 503 and retried: each attempt is a request, logged
-    // at trace with its status, and the retry is logged at debug with how
-    // long it waits and why.
-    it("logs each request at trace and each retry at debug", async () => {
-        const { log, lines } = collect();
-        const answers = [
-            new Response("unavailable", { status: 503 }),
-            new Response("{}", {
-                headers: { "content-type": "application/json" },
-            }),
-        ];
-        const client = new ApiClient({
-            ...logRequests(log, {
-                sleep: async () => {},
-                random: () => 0.5,
-            }),
-            fetch: async () => answers.shift()!,
-        });
-
-        await client.getJSON("/collections/v2", { sinceTime: 0 });
-
-        const url = "https://api.ente.io/collections/v2?sinceTime=0";
-        expect(lines).toEqual([
-            `trace: GET ${url}: HTTP 503`,
-            "debug: Attempt 1 failed, retrying in 250 ms: HTTP 503",
-            `trace: GET ${url}: HTTP 200`,
-        ]);
-    });
-
-    it("logs a request that failed with its error", async () => {
-        const { log, lines } = collect();
-        const client = new ApiClient({
-            ...logRequests(log, { attempts: 1 }),
-            fetch: async () => {
-                throw new TypeError("fetch failed", {
-                    cause: new Error("connect ECONNREFUSED 1.2.3.4:443"),
-                });
-            },
-        });
-
-        await expect(client.getJSON("/collections/v2")).rejects.toThrow();
-
-        expect(lines).toEqual([
-            "trace: GET https://api.ente.io/collections/v2: fetch failed: connect ECONNREFUSED 1.2.3.4:443",
-        ]);
-    });
-
-    // Each operation is named in plain words, as the README names it.
-    it("logs a refresh's progress at info, and its start and end at debug", () => {
-        const { log, lines } = collect();
-        const onProgress = logRefresh(log);
-
-        onProgress({ operation: "refresh", status: "started" });
-        onProgress({
-            operation: "refresh",
-            status: "progress",
-            fetched: 1,
-            total: 2,
-        });
-        onProgress({
-            operation: "refresh",
-            status: "failed",
-            error: "HTTP 503",
-        });
-        onProgress({ operation: "fetchMLData", status: "started" });
-        onProgress({ operation: "fetchMLData", status: "done", fetched: 3 });
-
-        expect(lines).toEqual([
-            "debug: Refresh started",
-            "info: Fetched the files of 1 of 2 collections",
-            "debug: Refresh failed: HTTP 503",
-            "debug: ML data fetch started",
-            "debug: ML data fetch done",
-        ]);
-    });
-});

test/cli/metadata-backup.test.ts

@@ -41,14 +41,12 @@ import { beforeAll, afterAll, describe, expect, it, vi } from "vitest";
 import { init, toBase64, encryptBlob } from "../../src/crypto/index.js";
 import * as jpegJs from "jpeg-js";
 import { Client } from "../../src/client.js";
-import { DISCOVER_CATEGORIES } from "../../src/clip-keyword-vectors.js";
 import { Library } from "../../src/library/index.js";
 import {
     runMetadataBackup,
     type MetadataBackupOptions,
 } from "../../src/metadata-backup.js";
 import { backupMetadataCommand } from "../../src/cli-commands.js";
-import { stderrLog, type LogLevel } from "../../src/cli-log.js";
 import {
     buildAccount,
     buildMetaFetch,
@@ -57,8 +55,8 @@ import {
     type MetaMockState,
 } from "../ente-server.js";
 
-// One file per ML data request, so each file of the mock account is fetched in
+// One file per ML data request, so the two files of the mock account are
-// a request of its own and one of them can fail on its own.
+// fetched in two requests and one of them can fail on its own.
 vi.mock("../../src/mldata-fetch.js", async (importOriginal) => ({
     ...(await importOriginal<typeof import("../../src/mldata-fetch.js")>()),
     MLDATA_BATCH_SIZE: 1,
@@ -67,21 +65,6 @@ vi.mock("../../src/mldata-fetch.js", async (importOriginal) => ({
 const TEST_EMAIL = "metabackup@example.com";
 const TEST_PASSWORD = "metapass";
 
-// The CLIP embedding of a photo of a sunset (see clip-keywords.test.ts), which
-// the ML data of beach.jpg holds.
-const SUNSET_EMBEDDING: number[] = JSON.parse(
-    readFileSync(
-        new URL("../clip-keywords-sunset.json", import.meta.url),
-        "utf-8",
-    ),
-).embedding;
-
-// Identity, a Discover category of Ente's photos app that leaves out videos.
-const IDENTITY = DISCOVER_CATEGORIES.find((c) => c.title === "Identity")!;
-
-// ML data holding faces and no CLIP embedding, which file 302 has.
-const FACES_ONLY = { face: { faces: [{ faceID: "face-def", score: 0.9 }] } };
-
 let mock: MetaMockState;
 let testDir: string;
 
@@ -220,65 +203,6 @@ const buildMetaMock = async (): Promise<MetaMockState> => {
         updationTime: 1710000000000000,
     };
 
-    // A file in coll 10 with the ML data given. `fileType` is Ente's number: 0
-    // an image, 1 a video.
-    const vacationFile = (
-        id: number,
-        title: string,
-        fileType: number,
-        mlData: object,
-    ) => {
-        const fileKey = sodium.crypto_secretstream_xchacha20poly1305_keygen();
-        const { ciphertext: encKey, nonce } = encryptSecretbox(fileKey, ck1);
-        const meta = encryptStreamBlob(
-            new TextEncoder().encode(
-                JSON.stringify({
-                    title,
-                    fileType,
-                    creationTime: 1700000000000000,
-                    modificationTime: 1700000000000000,
-                }),
-            ),
-            fileKey,
-        );
-        const ml = encryptBlob(
-            new Uint8Array(gzipSync(Buffer.from(JSON.stringify(mlData)))),
-            fileKey,
-        );
-        return {
-            raw: {
-                id,
-                collectionID: 10,
-                ownerID: 42,
-                encryptedKey: toBase64(encKey),
-                keyDecryptionNonce: toBase64(nonce),
-                metadata: {
-                    encryptedData: toBase64(meta.ciphertext),
-                    decryptionHeader: toBase64(meta.header),
-                },
-                file: {
-                    decryptionHeader: toBase64(sodium.randombytes_buf(24)),
-                },
-                thumbnail: {
-                    decryptionHeader: toBase64(sodium.randombytes_buf(24)),
-                },
-                updationTime: 1700000000000000,
-            },
-            mlData: {
-                encryptedData: toBase64(ml.ciphertext),
-                decryptionHeader: toBase64(ml.header),
-            },
-        };
-    };
-    // Files 300 and 301 in coll 10: a photo and a video whose ML data holds
-    // only a CLIP embedding, Identity's own text embedding.
-    const identityML = { clip: { embedding: IDENTITY.textEmbedding } };
-    const identityPhoto = vacationFile(300, "passport.jpg", 0, identityML);
-    const identityVideo = vacationFile(301, "passport.mp4", 1, identityML);
-    // File 302 in coll 10: a photo whose ML data holds faces and no CLIP
-    // embedding.
-    const facesPhoto = vacationFile(302, "party.jpg", 0, FACES_ONLY);
-
     // Encrypt ML data for file 100 (gzipped JSON, encrypted with file key)
     const mlPayload = JSON.stringify({
         face: {
@@ -305,7 +229,7 @@ const buildMetaMock = async (): Promise<MetaMockState> => {
         clip: {
             version: 1,
             client: "test",
-            embedding: SUNSET_EMBEDDING,
+            embedding: [0.5, 0.6, 0.7],
         },
     });
     const gzipped = gzipSync(Buffer.from(mlPayload));
@@ -345,23 +269,12 @@ const buildMetaMock = async (): Promise<MetaMockState> => {
         keyAttributes: account.keyAttributes,
         encryptedToken: account.encryptedToken,
         collections: [rawColl1, rawColl2],
-        filesByCollection: {
+        filesByCollection: { 10: [rawFile1], 20: [rawFile2] },
-            10: [
-                rawFile1,
-                identityPhoto.raw,
-                identityVideo.raw,
-                facesPhoto.raw,
-            ],
-            20: [rawFile2],
-        },
         encryptedMLData: {
             100: {
                 encryptedData: toBase64(mlCiphertext),
                 decryptionHeader: toBase64(mlHeader),
             },
-            300: identityPhoto.mlData,
-            301: identityVideo.mlData,
-            302: facesPhoto.mlData,
         },
         fileCiphertexts: { 100: encFileBody1 },
     };
@@ -518,9 +431,7 @@ describe("quak backup-metadata", () => {
         expect(account.email).toBe(TEST_EMAIL);
     });
 
-    // The CLIP embedding is left out of the ML data, and the keywords it gives
+    it("fetches and decrypts ML data by default", async () => {
-    // are written in its place.
-    it("fetches and decrypts ML data by default, with keywords for the CLIP embedding", async () => {
         const outDir = join(testDir, "ml-data");
         await runBackup(outDir);
 
@@ -540,41 +451,8 @@ describe("quak backup-metadata", () => {
         expect(fileMeta.mlData.face.faces[0].faceID).toBe("face-abc");
         expect(fileMeta.mlData.face.faces[0].score).toBeCloseTo(0.98);
         expect(fileMeta.mlData.face.faces[0].detection.box.x).toBeCloseTo(0.1);
-        expect(fileMeta.mlData).not.toHaveProperty("clip");
+        expect(fileMeta.mlData.clip).toBeDefined();
-        expect(fileMeta.keywords).toEqual(["Sunset"]);
+        expect(fileMeta.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
-    });
-
-    // Ente's photos app keeps videos out of some Discover categories, Identity
-    // among them. Files 300 and 301, a photo and a video, share one CLIP
-    // embedding, Identity's own text embedding, so the photo gets the keyword
-    // Identity and the video does not.
-    it("keeps a video out of a category that leaves out videos", async () => {
-        expect(IDENTITY.showVideo).toBe(false);
-        const outDir = join(testDir, "video-keywords");
-        await runBackup(outDir);
-
-        const vacation = join(outDir, "collections", "10-Vacation");
-        const fileJSON = (fileID: number) =>
-            JSON.parse(readFileSync(join(vacation, `${fileID}.json`), "utf-8"));
-        expect(fileJSON(300).keywords).toContain("Identity");
-        expect(fileJSON(301)).toHaveProperty("keywords");
-        expect(fileJSON(301).keywords).not.toContain("Identity");
-    });
-
-    // A file's ML data can hold faces and no CLIP embedding. File 302's JSON
-    // then has the ML data and no keywords.
-    it("writes no keywords for ML data without a CLIP embedding", async () => {
-        const outDir = join(testDir, "no-clip");
-        await runBackup(outDir);
-
-        const fileMeta = JSON.parse(
-            readFileSync(
-                join(outDir, "collections", "10-Vacation", "302.json"),
-                "utf-8",
-            ),
-        );
-        expect(fileMeta.mlData).toEqual(FACES_ONLY);
-        expect(fileMeta).not.toHaveProperty("keywords");
     });
 
     it("extracts EXIF from downloaded files when --exif is set", async () => {
@@ -612,12 +490,9 @@ describe("quak backup-metadata", () => {
 });
 
 describe("quak backup-metadata when a file's ML data cannot be read", () => {
-    // Run the CLI command against `fetch`, the mock unless given, logging at
+    // Run the CLI command against `fetch`, the mock unless given, and return
-    // `level`, and return its exit code, stderr and output directory.
+    // its exit code, stderr and output directory.
-    const runCommand = async (
+    const runCommand = async (fetch = buildMetaFetch(mock)) => {
-        fetch = buildMetaFetch(mock),
-        level: LogLevel = "info",
-    ) => {
         const client = await Client.login({
             email: TEST_EMAIL,
             password: TEST_PASSWORD,
@@ -631,10 +506,7 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
         const code = await backupMetadataCommand(
             {
                 stdout: { write: () => true },
-                log: stderrLog(
+                stderr: { write: (text: string) => (stderr += text) },
-                    { write: (text: string) => (stderr += text) },
-                    level,
-                ),
                 sessionDir: testDir,
                 cacheDir: mkdtempSync(join(testDir, "cache-")),
                 loadSession: () => client,
@@ -645,16 +517,13 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
         return { code, stderr, outDir };
     };
 
-    // The failed request is logged at error, so it is the first line printed
-    // at that level.
     it("writes every file, marks the failed batch's files, and exits 1", async () => {
         const { code, stderr, outDir } = await runCommand(
             buildMetaFetch(mock, 200),
-            "error",
         );
 
         expect(code).toBe(1);
-        expect(stderr).toMatch(/^ML data request for 1 file\(s\) failed: /);
+        expect(stderr).toContain("ML data request for 1 file(s) failed");
 
         const ok = JSON.parse(
             readFileSync(
@@ -662,7 +531,7 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
                 "utf-8",
             ),
         );
-        expect(ok.keywords).toEqual(["Sunset"]);
+        expect(ok.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
         expect(ok.mlDataError).toBeUndefined();
 
         const failed = JSON.parse(
@@ -677,9 +546,7 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
     });
 
     // The server sends ML data for diagram.png encrypted under a key that is
-    // not the file's, so quak cannot decrypt it. That is logged at error, and
+    // not the file's, so quak cannot decrypt it.
-    // the last line is fatal, so `-q`, which prints fatal lines only, still
-    // says why the command exits 1.
     it("writes the reason for ML data that does not decrypt, and exits 1", async () => {
         const otherKey = sodium.crypto_secretstream_xchacha20poly1305_keygen();
         const { header, ciphertext } = encryptBlob(
@@ -697,14 +564,12 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
                     },
                 },
             }),
-            "error",
         );
 
         expect(code).toBe(1);
         const reason = "secretstream chunk authentication failed";
-        expect(stderr).toBe(
+        expect(stderr).toContain(
-            `ML data of file 200 could not be read: ${reason}\n` +
+            `ML data of file 200 could not be read: ${reason}\n`,
-                `quak: the ML data of 1 file(s) could not be read; see mlDataError in their JSON in ${outDir}\n`,
         );
         const failed = JSON.parse(
             readFileSync(
@@ -720,7 +585,7 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
                 "utf-8",
             ),
         );
-        expect(ok.keywords).toEqual(["Sunset"]);
+        expect(ok.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
     });
 
     it("exits 0 when every ML data request succeeds", async () => {

test/cli/read.test.ts

@@ -3,13 +3,10 @@
  * issue #36, issue #52).
  *
  * The `collections`, `files`, `get`, and `get-thumb` commands must answer for
- * current server state, not the local cache. `files`, `get` and `get-thumb`
+ * current server state, not the local cache, so each helper forces a
- * force a `Library.fresh()` round-trip before they read; the stand-in library
+ * `Library.fresh()` round-trip before it reads. The stand-in library below
- * below serves nothing until `fresh()` has been awaited, so a helper that read
+ * serves nothing until `fresh()` has been awaited, so a helper that read
- * without refreshing would come back empty and fail here. `collections` asks
+ * without refreshing would come back empty and fail here.
- * the library for the collection list alone (`freshCollections()`, issue
- * #210), and must not wait for a refresh, which would fetch the files of every
- * collection.
  *
  * `collections` and `files` also list in the library's enumeration order
  * (`listCollections`/`listFiles`) — the order the pre-library CLI printed — not
@@ -63,13 +60,10 @@ const file = (
 });
 
 // A library that reveals its records only after `fresh()` has been awaited, and
-// serves them in the enumeration order it was given. `freshCollections()`
+// serves them in the enumeration order it was given. `photos.byID` returns a
-// answers the collection list in that order without a refresh. `photos.byID`
+// stand-in `Photo` carrying just the fileID the helper passes through.
-// returns a stand-in `Photo` carrying just the fileID the helper passes
-// through.
 class FakeLibrary implements FreshReadLibrary {
     freshCalls = 0;
-    freshCollectionsCalls = 0;
     private refreshed = false;
 
     constructor(
@@ -83,18 +77,12 @@ class FakeLibrary implements FreshReadLibrary {
         return {};
     }
 
-    async freshCollections(): Promise<Collection[]> {
+    listCollections(): Collection[] {
-        this.freshCollectionsCalls++;
+        return this.refreshed ? this.collections : [];
-        return this.collections;
     }
 
     getCollection(id: number): Collection | undefined {
-        if (!this.refreshed) return undefined;
+        return this.listCollections().find((c) => c.id === id);
-        return this.collections.find((c) => c.id === id);
-    }
-
-    listCollections(): Collection[] {
-        return this.refreshed ? this.collections : [];
     }
 
     listFiles(collectionID: number): EnteFile[] {
@@ -118,7 +106,7 @@ class FakeLibrary implements FreshReadLibrary {
 }
 
 describe("CLI read helpers (issue #36 amendment, issue #52)", () => {
-    it("freshCollections reads the collection list alone, in enumeration order", async () => {
+    it("freshCollections refreshes first, then lists in enumeration order", async () => {
         // Enumeration order 2, 1, 3; a newest-first sort would be 3, 2, 1.
         const lib = new FakeLibrary(
             [collection(2, 200), collection(1, 300), collection(3, 100)],
@@ -126,8 +114,7 @@ describe("CLI read helpers (issue #36 amendment, issue #52)", () => {
         );
         const rows = await freshCollections(lib);
 
-        expect(lib.freshCollectionsCalls).toBe(1);
+        expect(lib.freshCalls).toBe(1);
-        expect(lib.freshCalls).toBe(0);
         expect(rows.map((c) => c.id)).toEqual([2, 1, 3]);
         // The projection's newest-first order is a different sequence, so this
         // is not accidentally that order.
@@ -179,30 +166,6 @@ describe("CLI read helpers (issue #36 amendment, issue #52)", () => {
         ]);
     });
 
-    // Without a collection ID, `files` lists every file in the account once
-    // (issue #211). File 11 is in collections 1 and 2; collection 2 is
-    // enumerated first, so 11 is listed once, with collection 2's record.
-    it("freshFiles without a collection ID lists every file once, from the first collection holding it", async () => {
-        const files = [
-            file(10, 1, 1_700_000_000_000_000),
-            file(11, 1, 1_700_000_000_000_001),
-            file(20, 2, 1_700_000_000_000_002),
-            file(11, 2, 1_700_000_000_000_001),
-        ];
-        const lib = new FakeLibrary(
-            [collection(2, 100), collection(1, 200)],
-            files,
-        );
-
-        const rows = await freshFiles(lib);
-        expect(lib.freshCalls).toBe(1);
-        expect(rows?.map((f) => [f.id, f.collectionID])).toEqual([
-            [20, 2],
-            [11, 2],
-            [10, 1],
-        ]);
-    });
-
     it("freshFiles returns undefined for an unknown collection", async () => {
         const lib = new FakeLibrary([collection(1, 100)], []);
         const rows = await freshFiles(lib, 999);

test/cli/run.test.ts

@@ -6,7 +6,6 @@ import { PassThrough } from "node:stream";
 import { describe, it, expect } from "vitest";
 
 import { ApiError } from "../../src/api/client.js";
-import { stderrLog } from "../../src/cli-log.js";
 import { run } from "../../src/cli-run.js";
 
 // A stream whose written text is kept in `text`; writes finish at once, so
@@ -24,13 +23,7 @@ const runToExit = async (
     const stdout = collector();
     const stderr = collector();
     const code = await new Promise<number>((resolve) => {
-        void run(
+        void run(command, stdout.stream, stderr.stream, resolve);
-            command,
-            stdout.stream,
-            stderr.stream,
-            stderrLog(stderr.stream, "info"),
-            resolve,
-        );
     });
     return { code, stdout: stdout.text(), stderr: stderr.text() };
 };

test/clip-keywords-sunset.json

@@ -1,109 +0,0 @@
-{
-    "photo": "https://upload.wikimedia.org/wikipedia/commons/d/db/Sunset_off_the_Massachusetts_coast_-_NOAA.jpg",
-    "sha256": "be62f3289c9bf7b75af68cd6978021d54e8a531d5d4cc493f6e9fbf5e1ab74d3",
-    "embedding": [
-        -0.0021123015, -0.04437615, -0.062354308, 0.006249992, 0.022141185,
-        0.011159019, 0.01227392, -0.00030532264, 0.03186437, 0.09196922,
-        0.039111234, -0.037084445, -0.032962628, -0.019820206, -0.013141825,
-        0.0047183544, 0.017137334, 0.046581306, 0.0047622235, 0.04982521,
-        0.023128154, 0.032080866, 0.037709303, 0.019241406, 0.0032100384,
-        -0.014275843, 0.049337693, 0.025953151, 0.014263995, -0.0062328726,
-        -0.040504098, -0.015083303, -0.008123875, -0.006233639, -0.05352683,
-        -0.0048083956, 0.0763486, -0.013155067, 0.025114346, 0.022016674,
-        0.0001588023, -0.010341572, -0.0037518279, -0.019181008, 0.04549337,
-        -0.0010725886, 0.004636866, 0.017177915, -0.0117317885, 0.0026097358,
-        0.030738998, 0.013158572, -0.08856403, -0.0121391015, 0.011477229,
-        -0.0033104012, 0.035524756, -0.018607879, -0.0071739843, -0.031906743,
-        0.0056713386, -0.0044195866, 0.00292471, 0.00061686034, -0.043075223,
-        0.09040427, 0.001522537, -0.011445652, 0.009609886, -0.0053201183,
-        -0.0057452377, 0.00972853, -0.0024397348, -0.021255083, 0.015893811,
-        -0.006020548, -0.09428023, 0.014277583, -0.017975299, -0.011878315,
-        0.011825521, 0.00014203975, -0.0020437292, -0.05305343, -0.024840152,
-        -0.011336872, -0.002796541, -0.00036171873, 0.004530499, 0.044486605,
-        0.021602718, -0.01292857, 0.024530916, 0.019559948, -0.039928272,
-        -0.0681174, 0.049101, 0.02461532, 0.0365531, -0.04070358, -0.011011939,
-        -0.0027188526, -0.020370876, 0.012904856, 0.043157287, -0.051658224,
-        -0.3726012, 0.019549074, -0.0499252, -0.04800559, -0.011493859,
-        0.02893256, 0.060341954, 0.0013929688, -0.051283866, -0.024286803,
-        0.044124287, -0.005995806, -0.062817656, 0.007369614, -0.021470634,
-        -0.028147545, 0.00411659, 0.04234773, 0.03787647, 0.008579682,
-        -0.038568925, -0.027498025, -0.028416378, 0.0022012168, 0.010906191,
-        -0.013745787, 0.018267838, 0.013531097, -0.061559845, 0.004682517,
-        -0.005993303, 0.0028113858, -0.0028286583, 0.0026029332, -0.06693403,
-        -0.0072381413, -0.02419584, 0.0037009937, -0.0011296495, -0.030310456,
-        0.0005999609, 0.009945354, 0.024915686, 0.038672045, 0.023009432,
-        -0.05093051, -0.09101409, -0.06686167, -0.06211481, -0.022600474,
-        0.0024902367, -0.0067171026, -0.016769778, -0.0032803628, 0.008623083,
-        -0.0016110836, 0.014925073, 0.033811048, 0.012829449, -0.052575592,
-        0.03728281, -0.0051201633, 0.021238064, -0.031086605, -0.0043402985,
-        0.25054494, -0.028396713, -0.010725523, -0.023445267, 0.021751683,
-        0.003130971, 0.012270548, -0.014836475, 0.014466885, 0.0021478906,
-        -0.088153616, 0.015356315, 0.039639276, -0.040283255, 0.014923924,
-        -0.029303031, -0.004475201, 0.047299225, -0.06726505, -0.012491676,
-        -0.002080582, 0.03506341, 0.04146718, 0.0074114986, -0.009582633,
-        0.006623749, -0.05454898, -0.0034387247, -0.014780821, 0.03698328,
-        -0.034441486, 0.22032379, -0.021792699, 0.008001907, 0.0341019,
-        0.0025784625, -0.0071689896, -0.014151225, -0.050547987, -0.030372301,
-        -0.03288388, -0.042987447, -0.0033656165, 0.021502906, -0.0030374376,
-        -0.024413, -0.03506603, 0.030891743, 0.0069994032, 0.004887366,
-        0.030707076, 0.0065348223, 0.0008240555, 0.016809713, -0.024151647,
-        -0.0040458064, 0.044567548, 0.03908212, -0.061782435, 0.0026002831,
-        0.02003242, -0.0115451, -0.045135964, -0.0663542, 0.005240975,
-        0.0010777109, -0.009276002, -0.011919081, 0.027654119, -0.013634551,
-        0.0129154315, -0.013195512, 0.040571272, -0.099290505, -0.04656693,
-        -0.20979854, 0.04181004, -0.06769166, -0.04121946, 0.018260444,
-        0.005617506, -0.15694222, 0.032472793, 0.014189598, 0.008345103,
-        -0.041118417, 0.0074527003, -0.011494104, 0.004906474, -0.0027100458,
-        0.0009994594, -0.041061398, -0.045274835, 0.015187793, 0.034275036,
-        -0.02813289, 0.02098019, -0.015043198, 0.03716667, 0.013542642,
-        -0.008104835, 0.014965486, -0.027978558, 0.021163663, -0.006942737,
-        -0.034969814, -0.038961593, 0.016802894, -0.012318175, -0.047821593,
-        -0.01933216, 0.0064432374, 0.0322358, -0.020437784, 0.02659447,
-        -0.03022022, -0.019443465, -0.094178624, -0.017009107, 0.03860671,
-        -0.00023695534, -0.033089854, -0.014677462, 0.012356399, 0.018040499,
-        -0.19360113, 0.011710817, -0.019871691, 0.020124774, 0.024948105,
-        -0.024573864, -0.028349072, -0.041731454, 0.032646254, 0.015098165,
-        0.0018447012, -0.01129152, -0.02481687, 0.036048, 0.20797811,
-        0.04317757, -0.017239755, 0.033431605, -0.011384422, 0.0099174455,
-        -0.19739223, -0.008901062, -0.056426458, 0.014591864, 0.0044474266,
-        0.008209326, -0.012241819, 0.042553645, -0.021552453, 0.008611734,
-        0.048944127, -0.013872049, 0.019179989, 0.008183264, -0.053223096,
-        -0.027327595, -0.0033542586, -0.012353858, -0.010941209, 0.010212546,
-        0.029714134, -0.011385593, -0.0013529479, 0.014505385, 0.01148663,
-        0.012613636, -0.0074430504, -0.014008101, -0.028146038, -0.042778917,
-        0.02143165, 0.016812252, -0.06286215, 0.02085532, -0.035128277,
-        0.0241282, 0.01397908, -0.034992814, 0.013153766, 0.0068236147,
-        0.013594184, -0.06859393, 0.051849406, 0.029675119, -0.0037699796,
-        -0.00013216575, 0.02916647, 0.031859048, -0.015006051, 0.0001439966,
-        0.0026584554, -0.0046948595, 0.039754897, 0.034873154, 0.0012870439,
-        -0.011516082, -0.074089095, 0.019241294, 0.00076195505, 0.0027334464,
-        -0.036206458, -0.0011109262, -0.048838835, -0.00204685, 0.01179991,
-        0.0068136845, 0.009852495, 0.017308988, 0.03159545, 0.058803353,
-        0.038116634, 0.008836143, -0.010460637, -0.010994099, -0.0012926942,
-        -0.048370842, 0.037696566, -0.08093239, -0.0041242186, -0.005866373,
-        0.02048607, -0.12549639, 0.011705739, -0.0021425558, 0.018078592,
-        -0.038228087, 0.004245971, -0.11560507, 0.01381203, -0.02734893,
-        0.029595908, 0.101082794, -0.042842254, -0.08397301, -0.1546237,
-        -0.037624564, 0.0069606556, -0.008020479, 0.0043268185, 0.016504597,
-        0.044554908, -0.05240209, 0.020519335, -0.050994243, -0.019861093,
-        0.022066997, -0.0188911, 0.012919696, -0.022872692, -0.012961374,
-        -0.020071112, 0.0074553066, 0.06402014, 0.04065211, 0.014139608,
-        0.06221546, -0.02574805, 0.010114545, 0.020619567, 0.032264773,
-        -0.009148828, 0.022849955, -0.016593235, -0.032456633, -0.006737303,
-        -0.0037493357, -0.065912865, -0.0024181998, -0.0037048983, -0.019304488,
-        0.009085037, 0.057529982, -0.0378338, 0.01792042, 0.01885012,
-        -0.0043600523, 0.017382368, -0.027792772, 0.006749118, -0.0053297766,
-        -0.011628587, 0.015736576, 0.024801968, 0.011543913, -0.01159873,
-        -0.000759976, 0.042183932, 0.05764386, -0.06422416, 0.010577374,
-        -0.02261249, 0.02282793, -0.05141075, -0.11287078, -0.020670144,
-        -0.020953743, 0.030885734, -0.012597732, -0.121472664, 0.028447151,
-        -0.0415664, -0.010061708, 0.06441338, 0.0271207, -0.0016693748,
-        -0.0045694243, 0.020342957, 0.030528478, 0.007129517, -0.0029600926,
-        -0.007061397, 0.06036486, -0.004736018, -0.0090786135, -0.07601116,
-        -0.039556272, -0.051269546, -0.019473685, 0.029858151, 0.028464556,
-        0.012424476, 0.013742254, 0.008742927, 0.006065751, -0.009892663,
-        0.07699999, -0.003443197, 0.0027863425, 0.029197995, 0.0211013,
-        0.01098379, 0.016684106, -0.028917195, 0.008122037, 0.0265241,
-        -0.04461223
-    ]
-}

test/clip-keywords.test.ts

@@ -1,129 +0,0 @@
-// `clipKeywords`: the keywords quak writes for a file in place of its CLIP
-// embedding.
-//
-// Ente's ML data for a file holds a CLIP embedding, 512 numbers its image
-// model gave the photo. Ente's photos app puts a file in a category of its
-// Discover section when the cosine similarity of that embedding and the text
-// embedding of the category's query is at least the category's minimum score,
-// and keeps videos out of some categories. `clipKeywords` applies that rule
-// and returns the titles of the categories a file falls in, highest score
-// first; `quak backup` and `quak backup-metadata` write them as `keywords`.
-
-import { readFileSync } from "node:fs";
-import { describe, expect, it } from "vitest";
-
-import { DISCOVER_CATEGORIES } from "../src/clip-keyword-vectors.js";
-import { clipKeywords } from "../src/clip-keywords.js";
-
-// 512 numbers: the ones given, then zeros.
-const vector = (...start: number[]): number[] => [
-    ...start,
-    ...new Array<number>(512 - start.length).fill(0),
-];
-
-const withEmbedding = (embedding: unknown) => ({
-    face: { faces: [] },
-    clip: { embedding },
-});
-
-// Two made-up categories, each with a text embedding along one axis. The
-// embedding [3, 4] has a cosine similarity of 3/5 with "Across" and 4/5 with
-// "Up". Videos are kept out of "Across".
-const ACROSS = {
-    title: "Across",
-    query: "across",
-    minScore: 0.6,
-    showVideo: false,
-    textEmbedding: vector(1),
-};
-const UP = {
-    title: "Up",
-    query: "up",
-    minScore: 0.5,
-    showVideo: true,
-    textEmbedding: vector(0, 1),
-};
-
-describe("clipKeywords", () => {
-    it("gives each category whose minimum score the similarity reaches, highest score first", () => {
-        expect(
-            clipKeywords(withEmbedding(vector(3, 4)), false, [ACROSS, UP]),
-        ).toEqual(["Up", "Across"]);
-    });
-
-    it("leaves out a category when the similarity is just below its minimum score", () => {
-        const stricter = { ...ACROSS, minScore: 0.6 + 1e-9 };
-
-        expect(
-            clipKeywords(withEmbedding(vector(3, 4)), false, [stricter, UP]),
-        ).toEqual(["Up"]);
-    });
-
-    it("keeps a video out of a category that leaves out videos", () => {
-        expect(
-            clipKeywords(withEmbedding(vector(3, 4)), true, [ACROSS, UP]),
-        ).toEqual(["Up"]);
-    });
-
-    it("gives an empty list for an embedding that falls in no category", () => {
-        expect(
-            clipKeywords(withEmbedding(vector(0, 0, 1)), false, [ACROSS, UP]),
-        ).toEqual([]);
-    });
-
-    it.each([
-        ["no CLIP embedding", { face: { faces: [] } }],
-        ["a CLIP part that is not an object", { clip: null }],
-        ["a CLIP part without an embedding", { clip: {} }],
-        ["an embedding of 511 numbers", withEmbedding(vector(3, 4).slice(1))],
-        ["an embedding with NaN in it", withEmbedding(vector(3, NaN))],
-        ["an embedding with Infinity in it", withEmbedding(vector(Infinity))],
-        ["an embedding of strings", withEmbedding(vector(3, 4).map(String))],
-        ["an embedding of zeros", withEmbedding(vector())],
-    ])("gives no keywords for ML data with %s", (_, mlData) => {
-        expect(clipKeywords(mlData, false, [ACROSS, UP])).toBeUndefined();
-    });
-});
-
-// The CLIP embedding Ente's image model gives a public-domain NOAA photo of a
-// sunset, made by bin/clip-keyword-vectors from the photo at `photo`.
-const SUNSET: { photo: string; sha256: string; embedding: number[] } =
-    JSON.parse(
-        readFileSync(
-            new URL("clip-keywords-sunset.json", import.meta.url),
-            "utf-8",
-        ),
-    );
-
-describe("Ente's Discover categories", () => {
-    it("are the 16 of Ente's photos app, each with a text embedding of norm 1", () => {
-        expect(DISCOVER_CATEGORIES.map((c) => c.title)).toEqual([
-            "Identity",
-            "Screenshots",
-            "QR Codes",
-            "Receipts",
-            "Notes",
-            "Memes",
-            "Visiting Cards",
-            "Babies",
-            "Pets",
-            "Selfies",
-            "Wallpapers",
-            "Food",
-            "Celebrations",
-            "Sunset",
-            "Hills",
-            "Greenery",
-        ]);
-        for (const category of DISCOVER_CATEGORIES) {
-            expect(category.textEmbedding).toHaveLength(512);
-            expect(Math.hypot(...category.textEmbedding)).toBeCloseTo(1, 5);
-        }
-    });
-
-    it("give a photo of a sunset the keyword Sunset and no other", () => {
-        expect(
-            clipKeywords({ clip: { embedding: SUNSET.embedding } }, false),
-        ).toEqual(["Sunset"]);
-    });
-});

test/download/download.test.ts

@@ -1923,53 +1923,6 @@ describe("downloadFile live photos", () => {
         ]);
     });
 
-    // A file system refuses a file name over 255 bytes. Each name is cut
-    // short once its own extension is in it.
-    const imageName = `${"t".repeat(250)}.heic`;
-    const videoName = `${"t".repeat(251)}.mov`;
-
-    // The title fits, but ".heic" is one byte longer than ".jpg".
-    it("cuts the image's name short for a 255-byte title ending in .jpg when no outPath is given", async () => {
-        const title = `${"t".repeat(251)}.jpg`;
-        const t = setup(livePhotoZip(), { ...livePhoto, title });
-
-        const result = await inDirectory(t.dir, () =>
-            downloadFile(t.api, t.file),
-        );
-
-        expect(Buffer.byteLength(title)).toBe(255);
-        expect(Buffer.byteLength(imageName)).toBe(255);
-        expect(Buffer.byteLength(videoName)).toBe(255);
-        expect(result.path).toBe(imageName);
-        expect(result.videoPath).toBe(videoName);
-        expect(readdirSync(t.dir).sort()).toEqual([imageName, videoName]);
-    });
-
-    it("cuts the names of the image and the video short for a 300-byte title with no extension when no outPath is given", async () => {
-        const t = setup(livePhotoZip(), {
-            ...livePhoto,
-            title: "t".repeat(300),
-        });
-
-        const result = await inDirectory(t.dir, () =>
-            downloadFile(t.api, t.file),
-        );
-
-        expect(result.path).toBe(imageName);
-        expect(result.videoPath).toBe(videoName);
-        expect(readdirSync(t.dir).sort()).toEqual([imageName, videoName]);
-    });
-
-    // The caller's path is used as is; only the extension is each part's own.
-    it("keeps an outPath too long for a file name as given", async () => {
-        const t = setup(livePhotoZip(), livePhoto);
-        const outPath = join(t.dir, `${"t".repeat(251)}.jpg`);
-
-        await expect(downloadFile(t.api, t.file, outPath)).rejects.toThrow(
-            /ENAMETOOLONG/,
-        );
-    });
-
     it("gives each part its own extension from the ZIP, letters and digits only", async () => {
         const zip = livePhotoZip({ "image.JPG": IMAGE, "video.m-4v": VIDEO });
         const t = setup(zip, livePhoto);

test/filename/filename.test.ts

@@ -15,7 +15,6 @@
 import { describe, expect, it } from "vitest";
 
 import {
-    defaultFileName,
     safeExtension,
     sanitizeFileName,
     shortenKeepingExtension,
@@ -142,17 +141,9 @@ describe("shortenKeepingExtension", () => {
         );
     });
 
-    // A name cut down to its extension would start with a dot, and so be
+    it("cuts the extension short when it alone does not fit", () => {
-    // hidden.
-    it("keeps the first character before the extension, cutting the extension short to leave room for it", () => {
         expect(shortenKeepingExtension(`b.${"e".repeat(300)}`, 255)).toBe(
-            `b.${"e".repeat(253)}`,
+            `.${"e".repeat(254)}`,
-        );
-        expect(shortenKeepingExtension(`ab.${"e".repeat(300)}`, 255)).toBe(
-            `a.${"e".repeat(253)}`,
-        );
-        expect(shortenKeepingExtension(`é.${"e".repeat(300)}`, 255)).toBe(
-            `é.${"e".repeat(252)}`,
         );
         // "€" takes three bytes, so the extension is cut to 253 and the
         // part before it keeps the two bytes left over, for the "a".
@@ -170,59 +161,6 @@ describe("shortenKeepingExtension", () => {
         ).toBe(`${"t".repeat(247)} (7).jpg`);
         expect(
             shortenKeepingExtension(`b.${"e".repeat(300)}`, 255, " (7)"),
-        ).toBe(`b (7).${"e".repeat(249)}`);
+        ).toBe(` (7).${"e".repeat(250)}`);
-    });
-});
-
-describe("defaultFileName", () => {
-    it("is the title when it is safe and fits", () => {
-        expect(defaultFileName("IMG_0001.HEIC", 42)).toBe("IMG_0001.HEIC");
-    });
-
-    it("replaces unsafe characters, and is file-<id> for an empty title", () => {
-        expect(defaultFileName("../x.jpg", 42)).toBe("__x.jpg");
-        expect(defaultFileName("", 42)).toBe("file-42");
-    });
-
-    it("cuts a title over 255 bytes short, keeping its extension", () => {
-        expect(defaultFileName(`${"t".repeat(296)}.jpg`, 42)).toBe(
-            `${"t".repeat(251)}.jpg`,
-        );
-        expect(defaultFileName(`b.${"e".repeat(300)}`, 42)).toBe(
-            `b.${"e".repeat(253)}`,
-        );
-    });
-
-    it("puts `prefix` before the title and leaves room for it", () => {
-        expect(defaultFileName("beach.jpg", 42, { prefix: "thumb_" })).toBe(
-            "thumb_beach.jpg",
-        );
-        expect(
-            defaultFileName(`${"t".repeat(296)}.jpg`, 42, { prefix: "thumb_" }),
-        ).toBe(`thumb_${"t".repeat(245)}.jpg`);
-    });
-
-    // A live photo's image and video are each named with their own
-    // extension, and the name is cut short once that extension is in it.
-    it("puts `ext` in place of the title's extension before cutting the name short", () => {
-        expect(defaultFileName("IMG_0001.HEIC", 42, { ext: ".mov" })).toBe(
-            "IMG_0001.mov",
-        );
-        expect(defaultFileName("", 42, { ext: ".mov" })).toBe("file-42.mov");
-        expect(
-            defaultFileName(`${"t".repeat(251)}.jpg`, 42, { ext: ".heic" }),
-        ).toBe(`${"t".repeat(250)}.heic`);
-        expect(defaultFileName("t".repeat(300), 42, { ext: ".heic" })).toBe(
-            `${"t".repeat(250)}.heic`,
-        );
-    });
-
-    // Cutting `CONSOLE` or `NULL` short before a long extension leaves `CON`
-    // or `NUL`, so the name gets the `_` `sanitizeFileName` gives a device
-    // name, and the part before the extension gives up a byte for it.
-    it("never returns a Windows device name, even once cut short", () => {
-        const ext = `.${"e".repeat(251)}`;
-        expect(defaultFileName(`CONSOLE${ext}`, 42)).toBe(`_CO${ext}`);
-        expect(defaultFileName(`NULL${ext}`, 42)).toBe(`_NU${ext}`);
     });
 });

test/library/fresh.test.ts

@@ -14,9 +14,6 @@
  *     three.
  *  3. A refresh that fails rejects the fresh read (currency was unavailable),
  *     while the default reads stay silent and keep serving the last good copy.
- *  4. `freshCollections()` reads the collection list alone, with one request
- *     and no collection's files, and stores nothing, so the next refresh still
- *     fetches the files of every collection (issue #210).
  *
  * The client is the same metadata-only mock the background-refresh tests use:
  * no crypto, no network, scripted pages, and a record of each call. A long
@@ -273,70 +270,3 @@ describe("Library.fresh", () => {
         }
     });
 });
-
-describe("Library.freshCollections", () => {
-    let dir: string;
-    let cacheDirectory: string;
-
-    beforeEach(() => {
-        dir = mkdtempSync(join(tmpdir(), "quak-fresh-collections-"));
-        cacheDirectory = join(dir, "cache");
-    });
-
-    afterEach(() => {
-        rmSync(dir, { recursive: true, force: true });
-    });
-
-    // A refresh fetches a collection's files only when the collection is new
-    // or its updationTime has advanced past the stored copy's. Had the
-    // collection list been stored, the next refresh would take every
-    // collection for one it already holds the files of, and fetch none.
-    it("asks for the collection list alone and stores nothing", async () => {
-        const client = new MockClient();
-        const page = {
-            collections: [collection(2, 100), collection(1, 110)],
-            deleted: [],
-            cursor: 110,
-        };
-        client.collectionsQueue.push(page, page);
-        client.filesFor(1, {
-            files: [file(1001, 1, 90)],
-            deleted: [],
-            cursor: 90,
-        });
-        client.filesFor(2, {
-            files: [file(2001, 2, 95)],
-            deleted: [],
-            cursor: 95,
-        });
-
-        const lib = await Library.open({
-            client,
-            cacheDirectory,
-            refreshOnOpen: false,
-            refreshIntervalSeconds: SLOW_INTERVAL,
-        });
-        try {
-            // One request, the whole list in the server's order, and no
-            // collection's files.
-            const collections = await lib.freshCollections();
-            expect(collections.map((c) => c.id)).toEqual([2, 1]);
-            expect(collections.map((c) => c.name)).toEqual([
-                "album-2",
-                "album-1",
-            ]);
-            expect(client.collectionsSinceTimes).toEqual([0]);
-            expect(client.filesCalls).toEqual([]);
-            expect(lib.listCollections()).toEqual([]);
-
-            // The next refresh still asks from the beginning and fetches the
-            // files of both collections.
-            const reads = await lib.fresh();
-            expect(client.collectionsSinceTimes).toEqual([0, 0]);
-            expect(reads.photos.byID({ fileID: 1001 })?.fileID).toBe(1001);
-            expect(reads.photos.byID({ fileID: 2001 })?.fileID).toBe(2001);
-        } finally {
-            await lib.close();
-        }
-    });
-});

test/library/library.test.ts

@@ -26,9 +26,6 @@
  *    opening.
  * 8. A save failure that leaves RAM ahead of disk keeps `status().lastError`
  *    set and keeps retrying the write; a later empty refresh does not clear it.
- * 9. With `refreshOnOpen: false`, `open()` starts no refresh at all, and a
- *    refresh reports through `onProgress` each collection whose files it
- *    fetched.
  *
  * The client is a mock: no crypto, no network. It serves scripted pages and
  * records the `sinceTime` each call carried so cursor threading is provable.
@@ -584,107 +581,6 @@ describe("Library.open and background refresh", () => {
         }
     });
 
-    // A caller that asks for each refresh it needs, as the CLI's read commands
-    // do, opens without one: on an empty cache the refresh `open()` would
-    // await fetches the files of every collection, which `quak collections`
-    // never needs (issue #210).
-    it("starts no refresh as it opens when refreshOnOpen is false", async () => {
-        const client = new MockClient();
-        client.collectionsQueue.push({
-            collections: [collection(1, 100)],
-            deleted: [],
-            cursor: 100,
-        });
-
-        const lib = await Library.open({
-            client,
-            cacheDirectory,
-            refreshOnOpen: false,
-            refreshIntervalSeconds: Infinity,
-        });
-        try {
-            expect(client.collectionsSinceTimes).toEqual([]);
-            expect(lib.listCollections()).toEqual([]);
-            expect(lib.status().lastRefreshAt).toBeUndefined();
-
-            // The refresh comes when the caller asks for it.
-            await lib.fresh();
-            expect(client.collectionsSinceTimes).toEqual([0]);
-            expect(lib.listCollections().map((c) => c.id)).toEqual([1]);
-        } finally {
-            await lib.close();
-        }
-    });
-
-    // A refresh fetches the files of each collection that changed, one
-    // collection after another, and stores nothing until it has them all. On
-    // a large account that takes a while, so it reports each collection whose
-    // files it has fetched, and how many it will fetch in all (issue #210).
-    it("reports each collection whose files a refresh fetched", async () => {
-        const events: RefreshEvent[] = [];
-        const client = new MockClient();
-        client.collectionsQueue.push({
-            collections: [
-                collection(1, 100),
-                collection(2, 100),
-                collection(3, 100),
-            ],
-            deleted: [],
-            cursor: 100,
-        });
-
-        const lib = await Library.open({
-            client,
-            cacheDirectory,
-            refreshIntervalSeconds: Infinity,
-            onProgress: (e) => events.push(e),
-        });
-        try {
-            expect(events).toEqual([
-                { operation: "refresh", status: "started" },
-                {
-                    operation: "refresh",
-                    status: "progress",
-                    fetched: 1,
-                    total: 3,
-                },
-                {
-                    operation: "refresh",
-                    status: "progress",
-                    fetched: 2,
-                    total: 3,
-                },
-                {
-                    operation: "refresh",
-                    status: "progress",
-                    fetched: 3,
-                    total: 3,
-                },
-                { operation: "refresh", status: "done" },
-            ]);
-
-            // Only collection 2 changed since, so the next refresh fetches
-            // its files alone and counts one.
-            events.length = 0;
-            client.collectionsQueue.push({
-                collections: [collection(2, 200)],
-                deleted: [],
-                cursor: 200,
-            });
-            await lib.fresh();
-            expect(events.filter((e) => e.status === "progress")).toEqual([
-                {
-                    operation: "refresh",
-                    status: "progress",
-                    fetched: 1,
-                    total: 1,
-                },
-            ]);
-        } finally {
-            await lib.close();
-        }
-    });
-
     it("keeps a save failure visible until a save actually succeeds", async () => {
         const saveSpy = vi
             .spyOn(MetadataStore.prototype, "save")

test/retry/retry.test.ts

@@ -555,36 +555,6 @@ describe("withRetry", () => {
         expect(delays).toHaveLength(2);
     });
 
-    it("tells `onRetry` of each attempt it retries, before the wait", async () => {
-        // A caller that logs retries, as the CLI does with `-v`, learns why
-        // each attempt failed and how long the next one is put off. The last
-        // attempt is not retried, so it is not reported.
-        const { sleep, delays } = recordingSleep();
-        const retries: [string, number, number][] = [];
-        let calls = 0;
-        const failure = withRetry(
-            () => {
-                calls++;
-                return Promise.reject(new ApiError(`attempt ${calls}`, 503));
-            },
-            {
-                attempts: 3,
-                sleep,
-                random: () => 0.5,
-                onRetry: (err, attempt, delayMs) => {
-                    retries.push([(err as Error).message, attempt, delayMs]);
-                },
-            },
-        );
-
-        await expect(failure).rejects.toThrow("attempt 3");
-        expect(retries).toEqual([
-            ["attempt 1", 1, 250],
-            ["attempt 2", 2, 500],
-        ]);
-        expect(delays).toEqual([250, 500]);
-    });
-
     it("does not retry at all when attempts is 1", async () => {
         const { sleep, delays } = recordingSleep();
         let calls = 0;
@@ -738,7 +708,6 @@ describe("retry defaults", () => {
         expect(resolved.maxDelayMs).toBe(DEFAULT_RETRY_OPTIONS.maxDelayMs);
         expect(typeof resolved.sleep).toBe("function");
         expect(typeof resolved.random).toBe("function");
-        expect(typeof resolved.onRetry).toBe("function");
     });
 
     it("resolves to the defaults when given nothing", () => {

test/thumbnails/thumbnails.test.ts

@@ -544,22 +544,11 @@ describe("listMissingThumbnails", () => {
         const client = await login(counted.fetch, { ...noWait });
         const lib = await openLib(client);
 
-        const errors: string[] = [];
+        const missing = await listMissingThumbnails(lib, client);
-        const missing = await listMissingThumbnails(
-            lib,
-            client,
-            (msg, level) => {
-                if (level === "error") errors.push(msg);
-            },
-        );
         lib.close();
 
-        // Only the genuinely empty thumbnail is reported. The file that
+        // Only the genuinely empty thumbnail is reported.
-        // could not be checked is reported as an error.
         expect(missing.map((m) => m.fileID)).toEqual([101]);
-        expect(errors).toEqual([
-            expect.stringMatching(/^\[.*\] Could not check file-102\.jpg: /),
-        ]);
         // And the 500 was retried rather than accepted as an answer: four
         // attempts is the library default.
         expect(counted.matched()).toBe(4);
@@ -710,15 +699,7 @@ describe("fixMissingThumbnails", () => {
         const client = await login(buildThumbFetch(fixMock));
         const lib = await openLib(client);
 
-        const errors: string[] = [];
+        const results = await fixMissingThumbnails(lib, client, [101, 102]);
-        const results = await fixMissingThumbnails(
-            lib,
-            client,
-            [101, 102],
-            (msg, level) => {
-                if (level === "error") errors.push(msg);
-            },
-        );
         lib.close();
 
         expect(results.length).toBe(2);
@@ -726,10 +707,6 @@ describe("fixMissingThumbnails", () => {
         const failure = results.find((r) => r.fileID === 102)!;
         expect(success.status).toBe("fixed");
         expect(failure.status).toBe("failed");
-        // The failed file, and only it, is reported as an error.
-        expect(errors).toEqual([
-            expect.stringMatching(/^\[.*\] FAILED file-102\.jpg: /),
-        ]);
     });
 
     it("skips a non-JPEG image and a video as unsupported, not failed (issue #17)", async () => {