Merge pull request 'next → main: Photo save path, download and EXIF; version from git; example script' (#134 ) from next into main

Reviewed-on: #134
2026-10-22 18:55:49 +02:00
26 changed files with 1493 additions and 5146 deletions
@@ -26,43 +26,6 @@ declares one.
 # Completed Steps
 - 2026-10-26: On an empty cache, `quak helper fix-missing-thumbnails --file`
  stops fetching collections' files once it finds every file it names
  (https://git.eeqj.de/sneak/quak/issues/223). It used to wait for a refresh,
  which on an empty cache fetched the files of every collection. Now it reads
  the collection list, then one collection's files at a time, the most recently
  updated first. It stores none of the collections or file records it reads. It
  fetches each original through `lib.originalOf()`, which keeps it in the cache.
  Once the cache holds the account's collections, it still waits for a refresh.
 - 2026-10-26: On an empty cache, `quak get` and `quak get-thumb` stop fetching
  collections' files once they find the file
  (https://git.eeqj.de/sneak/quak/issues/222). They used to wait for a refresh,
  which on an empty cache fetched the files of every collection. Now they read
  the collection list, then one collection's files at a time. They store none of
  the collections or file records they read, and fetch the original or thumbnail
  through the new `lib.originalOf()` and `lib.thumbnailOf()`. Once the cache
  holds the account's collections, they still wait for a refresh.
 - 2026-10-26: `quak files` with a collection ID fetches that collection's files
  alone (https://git.eeqj.de/sneak/quak/issues/217). It used to wait for a
  refresh, which on an empty cache fetched the files of every collection. It now
  reads the collection list through `lib.freshCollections()`, then the one
  collection's files through the new `lib.freshFiles()`. It stores nothing, and
  the files print in the server's order.
 - 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,
@@ -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 "$@"
@@ -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()
@@ -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 {
@@ -498,9 +497,8 @@ 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 +514,7 @@ 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) {
@@ -37,16 +37,9 @@ import {
    thumbnailName,
 } from "./cli-output.js";
 import { type Log, logRefresh } from "./cli-log.js";
-import {
+import { freshCollections, freshFiles, freshFile } from "./cli-read.js";
    cachedFilesByID,
    freshCollections,
    freshFiles,
    freshFile,
    freshFilesByID,
 } from "./cli-read.js";
 import { withExtension } from "./filename.js";
 import { runMetadataBackup } from "./metadata-backup.js";
 import type { Collection, EnteFile } from "./model/types.js";
 import { listMissingThumbnails, fixMissingThumbnails } from "./thumbnails.js";
 export interface CliContext {
@@ -135,15 +128,12 @@ const readLibraryClient = (client: Client): LibraryClient => ({
    contentSource: () => client.contentSource(),
 });
-// Open a library for a single point command. The aggressive background
+// Open a library for a single point command: the aggressive background precache
-// precache (issue #48) is off, because a one-shot `collections` or `get` must
+// (issue #48) is off — a one-shot `collections` or `get` must not start
-// not start downloading the whole account. No refresh starts as the library
+// downloading the whole account — and no refresh starts as it opens or on a
-// opens or on a timer. Each command asks for the refresh it needs.
+// timer: each command asks for the one it needs, and `collections` needs none
-// `collections` and `files` with a collection ID need none (issues #210 and
+// (issue #210). While a refresh runs, each collection whose files it has
-// #217). Nor do `get` and `get-thumb` on an empty cache (issue #222). Nor does
+// fetched is logged, so a large account shows progress rather than nothing.
 // `helper fix-missing-thumbnails --file` on an empty cache (issue #223). 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),
@@ -292,11 +282,11 @@ export const filesCommand = async (
    const lib = await openReadLibrary(ctx, client);
    try {
-        // Ask the server for current state (issue #36 amendment, issue #52).
+        // Force a server round-trip and list in enumeration order (issue #36
-        // Each file prints from its own decrypted metadata (raw title,
+        // amendment, issue #52). Each file prints from its own decrypted
-        // microsecond creationTime) via cli-output. The files print in the
+        // metadata (raw title, microsecond creationTime) via cli-output, and in
-        // order `freshFiles` returns them, not the projection's newest-first
+        // the pre-library CLI's enumeration order, not the projection's
-        // order.
+        // newest-first order.
        const files = await freshFiles(lib, collectionID);
        if (!files) {
            ctx.log("fatal", `Collection ${collectionID} not found`);
@@ -333,13 +323,14 @@ export const getCommand = async (
    try {
        // Force a server round-trip so the file resolves against current state
        // (issue #36 amendment, issue #52).
-        const file = await freshFile(lib, fileID);
+        const resolved = await freshFile(lib, fileID);
-        if (!file) {
+        if (!resolved) {
            ctx.log("fatal", `File ${fileID} not found`);
            return 1;
        }
        const { photo, file } = resolved;
-        const result = await lib.originalOf(file);
+        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) {
@@ -390,13 +381,14 @@ export const getThumbCommand = async (
    try {
        // Force a server round-trip so the file resolves against current state
        // (issue #36 amendment, issue #52).
-        const file = await freshFile(lib, fileID);
+        const resolved = await freshFile(lib, fileID);
-        if (!file) {
+        if (!resolved) {
            ctx.log("fatal", `File ${fileID} not found`);
            return 1;
        }
        const { photo, file } = resolved;
-        const result = await lib.thumbnailOf(file);
+        const result = await photo.thumbnail();
        // Default name is thumb_<file's own title>, as the pre-library CLI
        // used (not the projection title) (issue #52).
        const outPath = opts.out ?? thumbnailName(file);
@@ -573,13 +565,10 @@ export const fixMissingThumbnailsCommand = async (
    }
    const lib = await openReadLibrary(ctx, client);
    try {
-        let found: Map<number, { file: EnteFile; collection: Collection }>;
+        // Refresh first so files added since the cache was written are found;
-        if (fileIDs.length > 0) {
+        // a failed refresh throws.
            found = await freshFilesByID(lib, fileIDs);
        } else {
            // Refresh first so files added since the cache was written are
            // checked; a failed refresh throws.
        await lib.fresh();
        if (fileIDs.length === 0) {
            ctx.log("info", "Scanning for missing thumbnails...");
            const missing = await listMissingThumbnails(
                lib,
@@ -592,14 +581,12 @@ export const fixMissingThumbnailsCommand = async (
                return 0;
            }
            ctx.log("info", `Found ${fileIDs.length} file(s) to fix.`);
            found = cachedFilesByID(lib, fileIDs);
        }
        const results = await fixMissingThumbnails(
            lib,
            client,
            fileIDs,
            found,
            (msg, level) => ctx.log(level ?? "info", msg),
        );
@@ -4,7 +4,7 @@
 // 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 "What quak prints" in the README). Every
+// `-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
@@ -2,40 +2,38 @@
 //
 // `collections`, `files`, `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). `get`,
+// local cache last happened to hold (owner amendment, issue #36). `files`,
-// `get-thumb` and `files` without a collection ID therefore force a server
+// `get` and `get-thumb` therefore force a server round-trip through
-// round-trip through `Library.fresh()` and only then read, so a change made
+// `Library.fresh()` and only then read — so a collection, file, or metadata
-// elsewhere is visible. `collections` asks the library for the collection list
+// change made elsewhere is visible. `collections` asks the library for the
-// alone through `Library.freshCollections()` (issue #210): a refresh would also
+// collection list alone through `Library.freshCollections()` (issue #210): a
-// fetch the files of every collection, which on a large account takes long and
+// refresh would also fetch the files of every collection, which on a large
-// which `collections` does not print. `files` with a collection ID reads that
+// account takes long and which `collections` does not print.
 // list too, then that one collection's files through `Library.freshFiles()`
 // (issue #217). On an empty cache, `get` and `get-thumb` read that list, then
 // one collection's files at a time, until they find the file (issue #222).
 // `helper fix-missing-thumbnails --file` does the same until it finds every
 // file it names (issue #223).
 //
-// `collections` and `files` with a collection ID list in the server's order.
+// `collections` lists in the server's order and `files` in the library's own
-// `files` without one lists in the library's own enumeration order
+// enumeration order (`listFiles()`), the orders the pre-library CLI printed,
-// (`listFiles()`). Neither command uses the `albums`/`photos` projection's
+// rather than the `albums`/`photos` projection's newest-first order, which
-// newest-first order, which re-sorts the rows. The field values still come
+// re-sorts the rows. The field values still come from each record's raw
-// from each record's raw metadata via `cli-output.ts`. `files` without a
+// metadata via `cli-output.ts`. `files` without a collection ID lists every
-// collection ID lists every file in the account once (issue #211): the library
+// file in the account once (issue #211): the library keeps a record of a file
-// keeps a record of a file for each collection that holds it, and only the
+// for each collection that holds it, and only the first collection's record is
-// first collection's record is listed.
+// 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 each fresh
+// structurally; a test can drive them with a stand-in that records the
-// read and serves records in a known enumeration order.
+// `fresh()` and `freshCollections()` calls and serves records in a known
 // enumeration order.
 export interface FreshReadLibrary {
    fresh(): Promise<unknown>;
    freshCollections(): Promise<Collection[]>;
-    freshFiles(collection: Collection): Promise<EnteFile[]>;
+    getCollection(id: number): Collection | undefined;
    listCollections(): Collection[];
    listFiles(collectionID: number): EnteFile[];
    getFileByID(fileID: number): EnteFile | undefined;
    photos: Pick<PhotosAPI, "byID">;
 }
 // Every live collection, current as of one collections request, in the
@@ -44,21 +42,21 @@ export const freshCollections = (
    lib: FreshReadLibrary,
 ): Promise<Collection[]> => lib.freshCollections();
-// The files of one collection, as the server holds them now, in the server's
+// 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
-// a collection ID, every file in the account as of a forced refresh, each once,
+// a collection ID, every file in the account, each once, as held by the first
-// as held by the first collection that holds it.
+// collection that holds it.
 export const freshFiles = async (
    lib: FreshReadLibrary,
    collectionID?: number,
 ): Promise<EnteFile[] | undefined> => {
    if (collectionID !== undefined) {
        const collections = await lib.freshCollections();
        const collection = collections.find((c) => c.id === collectionID);
        return collection ? lib.freshFiles(collection) : undefined;
    }
    await lib.fresh();
    if (collectionID !== undefined) {
        return lib.getCollection(collectionID)
            ? lib.listFiles(collectionID)
            : undefined;
    }
    const listed = new Set<number>();
    const files: EnteFile[] = [];
    for (const collection of lib.listCollections()) {
@@ -71,80 +69,16 @@ export const freshFiles = async (
    return files;
 };
-// One file as the server holds it now, or `undefined` when no collection holds
+// One file, current as of a forced refresh, resolved to both its content
-// it. When the cache holds the account's collections, it refreshes and looks
+// handle (`Photo`, for fetching bytes) and its raw record (`EnteFile`, for the
-// the file up in the cache. On an empty cache, it reads the collection list,
+// default output name and field values). `undefined` when the file is unknown.
 // then one collection's files at a time, and stops at the first collection
 // that holds the file. That search stores nothing.
 export const freshFile = async (
    lib: FreshReadLibrary,
    fileID: number,
-): Promise<EnteFile | undefined> => {
+): Promise<{ photo: Photo; file: EnteFile } | undefined> => {
    // Only a refresh stores collections, so a cache holding any holds them all.
    if (lib.listCollections().length > 0) {
    await lib.fresh();
-        return lib.getFileByID(fileID);
+    const photo = lib.photos.byID({ fileID });
-    }
+    const file = lib.getFileByID(fileID);
-    for (const collection of await lib.freshCollections()) {
+    if (!photo || !file) return undefined;
-        const files = await lib.freshFiles(collection);
+    return { photo, file };
        const file = files.find((f) => f.id === fileID);
        if (file) return file;
    }
    return undefined;
 };
 // The most recently updated collection first, and the higher ID first on a
 // tie. `Library.albums.list()` lists albums in this order.
 const byNewestCollection = (a: Collection, b: Collection): number =>
    b.updationTime - a.updationTime || b.id - a.id;
 // Each file named by `fileIDs` that the cache holds, mapped to its record and
 // the collection it was found in. Collections are searched in
 // `byNewestCollection` order, and a file is found in the first that holds it.
 // So `helper fix-missing-thumbnails` names a file after the same album as
 // `helper list-missing-thumbnails`. It reads the cache alone, so the caller
 // refreshes first.
 export const cachedFilesByID = (
    lib: FreshReadLibrary,
    fileIDs: number[],
 ): Map<number, { file: EnteFile; collection: Collection }> => {
    const wanted = new Set(fileIDs);
    const found = new Map<number, { file: EnteFile; collection: Collection }>();
    const collections = [...lib.listCollections()].sort(byNewestCollection);
    for (const collection of collections) {
        for (const file of lib.listFiles(collection.id)) {
            if (wanted.has(file.id) && !found.has(file.id)) {
                found.set(file.id, { file, collection });
            }
        }
    }
    return found;
 };
 // Each file named by `fileIDs` as the server holds it now, mapped to its record
 // and collection as `cachedFilesByID` maps it. When the cache holds the
 // account's collections, it refreshes and looks the files up in the cache. On
 // an empty cache, it reads the collection list, then one collection's files at
 // a time, and stops once it has found every file. That search stores nothing.
 export const freshFilesByID = async (
    lib: FreshReadLibrary,
    fileIDs: number[],
 ): Promise<Map<number, { file: EnteFile; collection: Collection }>> => {
    // Only a refresh stores collections, so a cache holding any holds them all.
    if (lib.listCollections().length > 0) {
        await lib.fresh();
        return cachedFilesByID(lib, fileIDs);
    }
    const wanted = new Set(fileIDs);
    const found = new Map<number, { file: EnteFile; collection: Collection }>();
    const collections = await lib.freshCollections();
    for (const collection of [...collections].sort(byNewestCollection)) {
        if (found.size === wanted.size) break;
        for (const file of await lib.freshFiles(collection)) {
            if (wanted.has(file.id) && !found.has(file.id)) {
                found.set(file.id, { file, collection });
            }
        }
    }
    return found;
 };
@@ -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);
 };
@@ -581,34 +581,14 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        fileID: number,
        opts?: ContentOptions,
    ): Promise<ContentResult> {
-        const file = this.fileOrThrow(fileID);
+        return this.get(fileID, "original", "on-demand", opts?.onProgress);
        return this.get(file, "original", "on-demand", opts?.onProgress);
    }
    async thumbnail(
        fileID: number,
        opts?: ContentOptions,
    ): Promise<ContentResult> {
-        const file = this.fileOrThrow(fileID);
+        return this.get(fileID, "thumbnail", "on-demand", opts?.onProgress);
        return this.get(file, "thumbnail", "on-demand", opts?.onProgress);
    }
    // The original of `file`, fetched and cached as `original` does. `file` is
    // used as given, so `getFile` need not know it.
    async originalOf(
        file: EnteFile,
        opts?: ContentOptions,
    ): Promise<ContentResult> {
        return this.get(file, "original", "on-demand", opts?.onProgress);
    }
    // The thumbnail of `file`, fetched and cached as `thumbnail` does. `file`
    // is used as given, so `getFile` need not know it.
    async thumbnailOf(
        file: EnteFile,
        opts?: ContentOptions,
    ): Promise<ContentResult> {
        return this.get(file, "thumbnail", "on-demand", opts?.onProgress);
    }
    // Put the original at the save path of `file` under the download directory
@@ -635,7 +615,7 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        destination: string,
    ): Promise<ContentResult> {
        const result = await this.acquire(
-            this.fileOrThrow(fileID),
+            fileID,
            "original",
            "on-demand",
            undefined,
@@ -658,7 +638,8 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        fileID: number,
        destination: string,
    ): Promise<{ path: string; videoPath?: string }> {
-        const file = this.fileOrThrow(fileID);
+        const file = this.getFile(fileID);
        if (!file) throw new Error(`content cache: unknown file ${fileID}`);
        return this.pools.content.run(
            async () => {
                const fetched = await this.fetchInto(
@@ -740,8 +721,7 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        onProgress: ((event: EnsureEvent) => void) | undefined,
    ): Promise<EnsureResult> {
        try {
-            const file = this.fileOrThrow(fileID);
+            const result = await this.acquire(fileID, kind, priority, signal);
            const result = await this.acquire(file, kind, priority, signal);
            const status = result.cached ? "skipped" : "done";
            onProgress?.({ fileID, status, path: result.path });
            return { fileID, path: result.path };
@@ -756,16 +736,8 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        }
    }
    // The record `getFile` gives for `fileID`. It throws for a file `getFile`
    // does not know.
    private fileOrThrow(fileID: number): EnteFile {
        const file = this.getFile(fileID);
        if (!file) throw new Error(`content cache: unknown file ${fileID}`);
        return file;
    }
    private async get(
-        file: EnteFile,
+        fileID: number,
        kind: Kind,
        priority: Priority,
        onProgress: ((event: ContentEvent) => void) | undefined,
@@ -773,7 +745,7 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        const onByte: ProgressCallback | undefined = onProgress
            ? (bytesDone) => onProgress({ status: "downloading", bytesDone })
            : undefined;
-        const result = await this.acquire(file, kind, priority, undefined, {
+        const result = await this.acquire(fileID, kind, priority, undefined, {
            onByte,
        });
        onProgress?.(
@@ -795,7 +767,7 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
    // photo's original is present only with its video, and is returned with
    // it.
    private async acquire(
-        file: EnteFile,
+        fileID: number,
        kind: Kind,
        priority: Priority,
        signal: AbortSignal | undefined,
@@ -806,7 +778,8 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
        videoPath?: string;
        cached: boolean;
    }> {
-        const fileID = file.id;
+        const file = this.getFile(fileID);
        if (!file) throw new Error(`content cache: unknown file ${fileID}`);
        const isLivePhoto =
            kind === "original" && file.metadata.fileType === "livePhoto";
@@ -20,10 +20,9 @@
 //
 // `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. `freshFiles()`
+// for a caller such as `quak collections` that needs no more. A caller that
-// is the fresh read of one collection's files, and stores nothing either
+// asks for each refresh it needs can also open the library with
-// (issue #217). A caller that asks for each refresh it needs can also open the
+// `refreshOnOpen: false`, so that `open()` starts none.
 // 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
@@ -66,8 +65,6 @@ import {
    ContentCache,
    savePath,
    storedAtSavePath,
    type ContentOptions,
    type ContentResult,
    type ContentSource,
    type ThumbnailsAPI,
    type EnsureOptions,
@@ -628,54 +625,6 @@ export class Library {
        return collections;
    }
    // The fresh read of one collection's files (issue #217): every live file
    // in it that decrypts, in the server's order. `collection` is a record
    // `freshCollections()` returned, whose key decrypts the files. It fetches
    // no other collection's files. Like `freshCollections()`, it stores
    // nothing. It returns each file once, as the latest copy the server sent,
    // where the first copy was.
    async freshFiles(collection: Collection): Promise<EnteFile[]> {
        if (this.closed) throw new Error("the library is closed");
        const { files } = await this.client.filesSince({
            collectionID: collection.id,
            collectionKey: collection.key,
            sinceTime: 0,
        });
        const byID = new Map<number, EnteFile>();
        for (const file of files) byID.set(file.id, file);
        return [...byID.values()];
    }
    // The original of `file`, fetched and cached as `Photo.original()` does.
    // `file` is used as given, so the store need not hold it. On an empty
    // cache, `quak get` passes a file that `freshFiles()` returned.
    async originalOf(
        file: EnteFile,
        opts?: ContentOptions,
    ): Promise<ContentResult> {
        if (!this.cache) {
            throw new Error(
                "originalOf requires a library opened with a content cache",
            );
        }
        return this.cache.originalOf(file, opts);
    }
    // The thumbnail of `file`, fetched and cached as `Photo.thumbnail()` does.
    // `file` is used as given, so the store need not hold it. On an empty
    // cache, `quak get-thumb` passes a file that `freshFiles()` returned.
    async thumbnailOf(
        file: EnteFile,
        opts?: ContentOptions,
    ): Promise<ContentResult> {
        if (!this.cache) {
            throw new Error(
                "thumbnailOf requires a library opened with a content cache",
            );
        }
        return this.cache.thumbnailOf(file, opts);
    }
    // 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
@@ -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;
@@ -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";
@@ -98,8 +97,7 @@ 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
@@ -232,16 +230,8 @@ 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;
@@ -5,7 +5,7 @@ import type { Client } from "./client.js";
 import type { Library } from "./library/index.js";
 import { ApiError } from "./api/client.js";
 import { encryptBlob, toBase64 } from "./crypto/index.js";
-import type { Collection, EnteFile } from "./model/types.js";
+import type { EnteFile } from "./model/types.js";
 // The server refuses a thumbnail larger than the one it already records for the
 // file (`thumbnail.size`, the encrypted size), so these encodings are tried
@@ -226,18 +226,16 @@ const encryptThumbnailWithin = (
    return undefined;
 };
-// Regenerate and upload a thumbnail for each requested file. `found` holds the
+// Regenerate and upload a thumbnail for each requested file. Originals are read
-// record of each requested file that a collection holds, and the collection it
+// through the library's content cache (`photo.original()`); the generated
-// was found in. Each original is read through the library's content cache, by
+// thumbnail is JPEG-encoded, encrypted under the file's own key, and registered
-// `lib.originalOf(file)`. The new thumbnail is a JPEG, encrypted under the
+// with the server — the encrypt-and-upload path is unchanged. Each file is
 // file's own key. It is uploaded, then registered with the server. Each file is
 // resolved to one outcome (fixed / skipped / failed) and a failure on one file
 // never stops the others.
 export const fixMissingThumbnails = async (
    lib: Library,
    client: Client,
    fileIDs: number[],
    found: Map<number, { file: EnteFile; collection: Collection }>,
    onProgress?: ProgressCallback,
 ): Promise<ThumbnailFixResult[]> => {
    const log = onProgress ?? (() => {});
@@ -245,8 +243,31 @@ export const fixMissingThumbnails = async (
    const api = client.getApiClient();
    const { userID } = client.whoami();
    // Resolve each requested fileID to its file record and owning album by
    // enumerating the library, each file taken from the first album that holds
    // it. The raw `EnteFile` carries the per-file key the thumbnail is
    // encrypted under, which the projected records deliberately do not.
    const wanted = new Set(fileIDs);
    const fileMap = new Map<
        number,
        { file: EnteFile; collectionName: string }
    >();
    for (const album of lib.albums.list()) {
        for (const photo of album.photos.list()) {
            if (!wanted.has(photo.fileID) || fileMap.has(photo.fileID))
                continue;
            const file = lib.getFile(album.collectionID, photo.fileID);
            if (file) {
                fileMap.set(photo.fileID, {
                    file,
                    collectionName: album.name,
                });
            }
        }
    }
    for (const fileID of fileIDs) {
-        const entry = found.get(fileID);
+        const entry = fileMap.get(fileID);
        if (!entry) {
            results.push({
                fileID,
@@ -258,8 +279,7 @@ export const fixMissingThumbnails = async (
            continue;
        }
-        const { file } = entry;
+        const { file, collectionName } = entry;
        const collectionName = entry.collection.name;
        const title = file.metadata.title;
        const skipReason = reasonToSkip(file, userID);
@@ -277,10 +297,15 @@ export const fixMissingThumbnails = async (
        const maxSize = file.thumbnail.size!;
        try {
            const photo = lib.photos.byID({ fileID });
            if (!photo) {
                throw new Error("file not present in the library cache");
            }
            log(
                `[${collectionName}] Downloading ${title} for thumbnail generation...`,
            );
-            const { path } = await lib.originalOf(file);
+            const { path } = await photo.original();
            const fileBytes = new Uint8Array(readFileSync(path));
            if (!isJpeg(fileBytes)) {
@@ -86,17 +86,10 @@ 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
@@ -418,7 +411,7 @@ describe("the first backup of the account", () => {
        expect(downloads.sort()).toEqual([100, 200, 300]);
    });
-    // The tree under "The backup directory" in the README. Each original is at
+    // The tree "Backup layout" in the README describes. Each original is at
    // its save path, `YYYY/YYYY-MM/YYYY-MM-DD/YYYY-MM-DD.<fileID>.<ext>`, with
    // the extension of its title; the live photo is its image and its video,
    // each with the extension it had inside the ZIP, and a `.livephoto.json`
@@ -493,10 +486,7 @@ 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 +497,6 @@ 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");
@@ -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");
        }
@@ -194,6 +194,9 @@ 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 = "";
@@ -532,7 +535,9 @@ describe("files", () => {
    it("exits 1 for an unknown collection", async () => {
        expect(await filesCommand(context(), "9", {})).toBe(1);
-        expect(stderr.text).toBe("Collection 9 not found\n");
+        expect(stderr.text).toBe(
            FETCHED_BOTH_ALBUMS + "Collection 9 not found\n",
        );
    });
    // Without a collection ID it lists every file in the account once (issue
@@ -573,27 +578,27 @@ 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(`7 bytes -> ${out}\n`);
+        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + `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(`3 bytes -> ${out}\n`);
+        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + `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("File 999 not found\n");
+        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + "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("File 999 not found\n");
+        expect(stderr.text).toBe(FETCHED_BOTH_ALBUMS + "File 999 not found\n");
        expect(existsSync(out)).toBe(false);
    });
 });
@@ -641,7 +646,7 @@ 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(`7 bytes -> ${name}\n`);
+        expect(stderr.text).toBe(FETCHED_ONE_ALBUM + `7 bytes -> ${name}\n`);
    });
    it("get-thumb cuts the title short so that thumb_ and it fit in 255 bytes, and exits 0", async () => {
@@ -653,7 +658,7 @@ 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(`3 bytes -> ${name}\n`);
+        expect(stderr.text).toBe(FETCHED_ONE_ALBUM + `3 bytes -> ${name}\n`);
    });
    it("backup-metadata cuts the album name short so that its folder's name fits in 255 bytes, and exits 0", async () => {
@@ -742,6 +747,7 @@ describe("a live photo", () => {
            Buffer.from(VIDEO),
        );
        expect(stderr.text).toBe(
            FETCHED_ONE_ALBUM +
                `${IMAGE.length} bytes -> IMG_0300.heic\n` +
                `${VIDEO.length} bytes -> IMG_0300.mov\n`,
        );
@@ -796,6 +802,7 @@ describe("a live photo", () => {
        expect(readFileSync(out)).toEqual(Buffer.from(IMAGE));
        expect(readFileSync(video)).toEqual(Buffer.from(VIDEO));
        expect(stderr.text).toBe(
            FETCHED_ONE_ALBUM +
                `${IMAGE.length} bytes -> ${out}\n${VIDEO.length} bytes -> ${video}\n`,
        );
    });
@@ -810,6 +817,7 @@ 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`,
        );
    });
@@ -1353,23 +1361,6 @@ describe("helper fix-missing-thumbnails", () => {
        ).toBe(1);
        expect(stderr.text).toBe(last);
    });
    // beach.jpg (100) is in Vacation (1) and Work (2), both updated at the same
    // time. The fixer names a file after the first album holding it in the
    // order of `Library.albums.list()`. On a tie, the album with the higher ID
    // comes first, so beach.jpg is named after Work.
    it("names a photo in two albums after the same album on an empty cache as on a cache that holds the account", async () => {
        const ctx = context(fakeClient({ beachInWork: true }));
        const opts = { file: ["100"], json: true };
        const inWork = [{ fileID: 100, collection: "Work", status: "skipped" }];
        expect(await fixMissingThumbnailsCommand(ctx, opts)).toBe(0);
        expect(JSON.parse(stdout.text)).toMatchObject(inWork);
        expect(await filesCommand(ctx, undefined, {})).toBe(0);
        stdout.text = "";
        expect(await fixMissingThumbnailsCommand(ctx, opts)).toBe(0);
        expect(JSON.parse(stdout.text)).toMatchObject(inWork);
    });
 });
 describe("backup-metadata --exif", () => {
@@ -1399,11 +1390,11 @@ describe("backup-metadata --exif", () => {
 });
 // Each test first runs `files` so the cache holds the account as it was, then
-// changes the server under it. (`collections` and `files` with a collection ID
+// changes the server under it. (`collections` would not do: it reads the
-// would not do: they store nothing.)
+// collection list alone and stores nothing.)
 describe("backup-metadata and the thumbnail helpers refresh first", () => {
    beforeEach(async () => {
-        expect(await filesCommand(context(), undefined, {})).toBe(0);
+        expect(await filesCommand(context(), "1", {})).toBe(0);
        stdout.text = "";
        stderr.text = "";
    });
@@ -1586,83 +1577,20 @@ describe("an ID given on the command line", () => {
    );
 });
-// An account with many albums (issues #210, #217 and #222). On an empty cache
+// An account with many albums (issue #210). On an empty cache `collections`
-// `collections`, `files` with a collection ID and `get` used to wait for a
+// used to wait for a refresh that fetched and decrypted the files of every
-// refresh that fetched and decrypted the files of every album, one album after
+// album, one album after another, before it printed anything, so on such an
-// another. So did `helper fix-missing-thumbnails --file` (issue #223). On such
+// account it seemed to hang. The account here has 40 albums of one photo each,
-// an account they seemed to hang. The account here has 40 albums of one photo
+// encrypted as Ente's clients encrypt them, on the fake Ente server of
-// 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
-// `test/ente-server.ts`. The tests record the path and query of each request
+// sends. The session is the one logging in to that server saves.
 // 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 requests: string[] = [];
+    const paths: string[] = [];
    let server: typeof globalThis.fetch;
    let snapshot: ClientSnapshot;
    // What `files` without a collection ID prints on an empty cache: every
    // album's photo on stdout, and on stderr each album whose files its
    // refresh fetched.
    let everyPhoto = "";
    let progress = "";
    for (let n = 1; n <= ALBUMS; n++) {
        everyPhoto += `${n * 100}\timage\tphoto-${n}.jpg\n`;
        progress += `Fetched the files of ${n} of ${ALBUMS} collections\n`;
    }
    // The key of each album, by album ID.
    const albumKeys = new Map<number, Uint8Array>();
    // A photo in album `collectionID` as the server sends it, and its original
    // encrypted as the server stores it. The original's bytes are the title.
    // These tests fetch no thumbnail. The server records a thumbnail size, so
    // `helper fix-missing-thumbnails` downloads the original before it skips
    // the photo as not a JPEG.
    const photoRow = (photo: {
        id: number;
        collectionID: number;
        title: string;
        updationTime: number;
    }): { row: Record<string, unknown>; original: Uint8Array } => {
        const photoKey = sodium.crypto_secretstream_xchacha20poly1305_keygen();
        const photoKeyBox = encryptSecretbox(
            photoKey,
            albumKeys.get(photo.collectionID)!,
        );
        const metadata = encryptStreamBlob(
            new TextEncoder().encode(
                JSON.stringify({
                    title: photo.title,
                    fileType: 0,
                    creationTime: 1000,
                    modificationTime: 1000,
                }),
            ),
            photoKey,
        );
        const original = encryptStreamBlob(
            new TextEncoder().encode(photo.title),
            photoKey,
        );
        const row = {
            id: photo.id,
            collectionID: photo.collectionID,
            ownerID: USER_ID,
            encryptedKey: toBase64(photoKeyBox.ciphertext),
            keyDecryptionNonce: toBase64(photoKeyBox.nonce),
            metadata: {
                encryptedData: toBase64(metadata.ciphertext),
                decryptionHeader: toBase64(metadata.header),
            },
            file: { decryptionHeader: toBase64(original.header) },
            thumbnail: { decryptionHeader: "" },
            info: { thumbSize: 1000 },
            updationTime: photo.updationTime,
        };
        return { row, original: original.ciphertext };
    };
    // Album n is named `Album n` and holds one photo, n * 100, titled
    // `photo-n.jpg`.
    beforeAll(async () => {
@@ -1670,10 +1598,8 @@ describe("an account with many albums", () => {
        const account = await buildAccount(PASSWORD);
        const collections: Record<string, unknown>[] = [];
        const filesByCollection: Record<number, Record<string, unknown>[]> = {};
        const fileCiphertexts: Record<number, Uint8Array> = {};
        for (let id = 1; id <= ALBUMS; id++) {
            const albumKey = sodium.crypto_secretbox_keygen();
            albumKeys.set(id, albumKey);
            const albumKeyBox = encryptSecretbox(albumKey, account.masterKey);
            const name = encryptSecretbox(
                new TextEncoder().encode(`Album ${id}`),
@@ -1689,14 +1615,37 @@ describe("an account with many albums", () => {
                type: "album",
                updationTime: 1,
            });
-            const { row, original } = photoRow({
+            const photoKey =
                sodium.crypto_secretstream_xchacha20poly1305_keygen();
            const photoKeyBox = encryptSecretbox(photoKey, albumKey);
            const metadata = encryptStreamBlob(
                new TextEncoder().encode(
                    JSON.stringify({
                        title: `photo-${id}.jpg`,
                        fileType: 0,
                        creationTime: 1000,
                        modificationTime: 1000,
                    }),
                ),
                photoKey,
            );
            filesByCollection[id] = [
                {
                    id: id * 100,
                    collectionID: id,
-                title: `photo-${id}.jpg`,
+                    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,
-            });
+                },
-            filesByCollection[id] = [row];
+            ];
            fileCiphertexts[id * 100] = original;
        }
        const ente = buildMetaFetch({
            verifier: account.verifier,
@@ -1706,7 +1655,7 @@ describe("an account with many albums", () => {
            collections,
            filesByCollection,
            encryptedMLData: {},
-            fileCiphertexts,
+            fileCiphertexts: {},
        });
        server = (async (input: RequestInfo | URL, init?: RequestInit) => {
            const url =
@@ -1715,8 +1664,7 @@ describe("an account with many albums", () => {
                    : input instanceof URL
                      ? input.href
                      : input.url;
-            const { pathname, search } = new URL(url);
+            paths.push(new URL(url).pathname);
            requests.push(pathname + search);
            return ente(input, init);
        }) as typeof globalThis.fetch;
        const client = await Client.login({
@@ -1728,17 +1676,16 @@ describe("an account with many albums", () => {
    });
    beforeEach(() => {
-        requests.length = 0;
+        paths.length = 0;
    });
-    // A context whose saved session sends its requests to `fetch`, by default
+    // A context whose saved session sends its requests to the fake server.
-    // the fake server.
+    const accountContext = (): CliContext => {
    const accountContext = (fetch = server): CliContext => {
        const ctx = context();
        saveSession(ctx.sessionDir, snapshot);
        return {
            ...ctx,
-            loadSession: (path) => loadSession(path, { fetch }),
+            loadSession: (path) => loadSession(path, { fetch: server }),
        };
    };
@@ -1751,219 +1698,46 @@ describe("an account with many albums", () => {
            albums += `${id}\talbum\tAlbum ${id}\n`;
        expect(stdout.text).toBe(albums);
        expect(stderr.text).toBe("");
-        expect(requests).toEqual(["/collections/v2?sinceTime=0"]);
+        expect(paths).toEqual(["/collections/v2"]);
        // It stored nothing that would make a refresh skip an album's files:
-        // `files` after it still lists every album's photo.
+        // `files` after it still finds the album's photo.
        stdout.text = "";
        expect(await filesCommand(ctx, undefined, {})).toBe(0);
        expect(stdout.text).toBe(everyPhoto);
    });
    it("files with a collection ID asks for the album list and that album's files alone", async () => {
        expect(await filesCommand(accountContext(), "7", {})).toBe(0);
        expect(stdout.text).toBe("700\timage\tphoto-7.jpg\n");
        expect(stderr.text).toBe("");
        expect(requests).toEqual([
            "/collections/v2?sinceTime=0",
            "/collections/v2/diff?collectionID=7&sinceTime=0",
        ]);
    });
    // Here the server sends album 7's files in two pages. Photo 700 changed
    // between them, so both pages hold a copy of it.
    it("files with a collection ID lists only the later copy of a photo sent in two pages", async () => {
        const firstPage = [
            photoRow({
                id: 700,
                collectionID: 7,
                title: "photo-7.jpg",
                updationTime: 1,
            }).row,
            photoRow({
                id: 701,
                collectionID: 7,
                title: "photo-701.jpg",
                updationTime: 1,
            }).row,
        ];
        const secondPage = [
            photoRow({
                id: 700,
                collectionID: 7,
                title: "photo-7-edited.jpg",
                updationTime: 2,
            }).row,
        ];
        const paged = (async (input: RequestInfo | URL, init?: RequestInit) => {
            const url = new URL(input instanceof Request ? input.url : input);
            if (
                url.pathname !== "/collections/v2/diff" ||
                url.searchParams.get("collectionID") !== "7"
            ) {
                return server(input, init);
            }
            const first = url.searchParams.get("sinceTime") === "0";
            return new Response(
                JSON.stringify({
                    diff: first ? firstPage : secondPage,
                    hasMore: first,
                }),
            );
        }) as typeof globalThis.fetch;
        expect(await filesCommand(accountContext(paged), "7", {})).toBe(0);
        // Photo 700 is listed once, with the later title, before photo 701.
        expect(stdout.text).toBe(
            "700\timage\tphoto-7-edited.jpg\n701\timage\tphoto-701.jpg\n",
        );
    });
    // The cache stays empty, so a later `files` without a collection ID still
    // fetches the files of all 40 albums.
    it("files with a collection ID stores nothing in the cache", async () => {
        const ctx = accountContext();
        expect(await filesCommand(ctx, "7", {})).toBe(0);
-        expect(existsSync(join(root, "cache", "metadata.json"))).toBe(false);
+        expect(stdout.text).toBe("700\timage\tphoto-7.jpg\n");
        stdout.text = "";
        expect(await filesCommand(ctx, undefined, {})).toBe(0);
        expect(stdout.text).toBe(everyPhoto);
        expect(stderr.text).toBe(progress);
    });
    // Photo 200 is in album 2, so `get` asks for no file of album 3 or later.
    // The last request downloads the photo's original.
    it("get on an empty cache asks for the albums' files only until one holds the photo", async () => {
        const out = join(root, "photo.jpg");
        expect(await getCommand(accountContext(), "200", { out })).toBe(0);
        expect(readFileSync(out, "utf-8")).toBe("photo-2.jpg");
        expect(stderr.text).toBe(`11 bytes -> ${out}\n`);
        expect(requests).toEqual([
            "/collections/v2?sinceTime=0",
            "/collections/v2/diff?collectionID=1&sinceTime=0",
            "/collections/v2/diff?collectionID=2&sinceTime=0",
            "/?fileID=200",
        ]);
        expect(existsSync(join(root, "cache", "metadata.json"))).toBe(false);
    });
    // `files` first fills the cache, so `get` waits for a refresh. No album has
    // changed since, so the refresh asks for no album's files.
    it("get on a cache that holds the account asks for no unchanged album's files, also for a photo in no album", async () => {
        const ctx = accountContext();
        expect(await filesCommand(ctx, undefined, {})).toBe(0);
        requests.length = 0;
        stderr.text = "";
        const out = join(root, "photo.jpg");
        expect(await getCommand(ctx, "4000", { out })).toBe(0);
        expect(readFileSync(out, "utf-8")).toBe("photo-40.jpg");
        expect(stderr.text).toBe(`12 bytes -> ${out}\n`);
        expect(requests).toEqual([
            "/collections/v2?sinceTime=1",
            "/?fileID=4000",
        ]);
        requests.length = 0;
        stderr.text = "";
        expect(await getCommand(ctx, "999", { out })).toBe(1);
        expect(stderr.text).toBe("File 999 not found\n");
        expect(requests).toEqual(["/collections/v2?sinceTime=1"]);
    });
    // The helper searches the most recently updated album first. All 40 were
    // updated at the same time, and on a tie the higher ID comes first. Photo
    // 3900 is in album 39, so the helper asks for no file of album 38 or
    // earlier. The last request downloads the photo's original.
    it("fix-missing-thumbnails --file on an empty cache asks for the albums' files only until one holds the photo", async () => {
        const opts = { file: ["3900"], json: true };
        expect(await fixMissingThumbnailsCommand(accountContext(), opts)).toBe(
            0,
        );
        const reason =
            "unsupported image format (only baseline JPEG can be regenerated)";
        expect(JSON.parse(stdout.text)).toEqual([
            {
                fileID: 3900,
                title: "photo-39.jpg",
                collection: "Album 39",
                status: "skipped",
                reason,
            },
        ]);
        expect(stderr.text).toBe(
            "[Album 39] Downloading photo-39.jpg for thumbnail generation...\n" +
                `[Album 39] Skipping photo-39.jpg: ${reason}\n`,
        );
        expect(requests).toEqual([
            "/collections/v2?sinceTime=0",
            "/collections/v2/diff?collectionID=40&sinceTime=0",
            "/collections/v2/diff?collectionID=39&sinceTime=0",
            "/?fileID=3900",
        ]);
        expect(existsSync(join(root, "cache", "metadata.json"))).toBe(false);
    });
    // `files` first fills the cache, so the helper waits for a refresh. No
    // album has changed since, so the refresh asks for no album's files.
    it("fix-missing-thumbnails --file on a cache that holds the account asks for no unchanged album's files, also for a photo in no album", async () => {
        const ctx = accountContext();
        expect(await filesCommand(ctx, undefined, {})).toBe(0);
        requests.length = 0;
        stdout.text = "";
        stderr.text = "";
        const opts = { file: ["3900"], json: true };
        expect(await fixMissingThumbnailsCommand(ctx, opts)).toBe(0);
        const reason =
            "unsupported image format (only baseline JPEG can be regenerated)";
        expect(JSON.parse(stdout.text)).toEqual([
            {
                fileID: 3900,
                title: "photo-39.jpg",
                collection: "Album 39",
                status: "skipped",
                reason,
            },
        ]);
        expect(stderr.text).toBe(
            "[Album 39] Downloading photo-39.jpg for thumbnail generation...\n" +
                `[Album 39] Skipping photo-39.jpg: ${reason}\n`,
        );
        expect(requests).toEqual([
            "/collections/v2?sinceTime=1",
            "/?fileID=3900",
        ]);
        requests.length = 0;
        stdout.text = "";
        const notFound = { file: ["999"], json: true };
        expect(await fixMissingThumbnailsCommand(ctx, notFound)).toBe(1);
        expect(JSON.parse(stdout.text)).toMatchObject([
            { fileID: 999, reason: "file not found in any collection" },
        ]);
        expect(requests).toEqual(["/collections/v2?sinceTime=1"]);
    });
    it("files counts on stderr each album whose files its refresh fetched", async () => {
-        expect(await filesCommand(accountContext(), undefined, {})).toBe(0);
+        expect(await filesCommand(accountContext(), "7", {})).toBe(0);
-        expect(stdout.text).toBe(everyPhoto);
+        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 () => {
-        const opts = { json: true };
+        expect(await filesCommand(accountContext(), "7", { json: true })).toBe(
-        expect(await filesCommand(accountContext(), undefined, opts)).toBe(0);
+            0,
        );
-        expect(JSON.parse(stdout.text)).toHaveLength(ALBUMS);
+        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);
    });
 });
@@ -234,15 +234,13 @@ describe("-q", () => {
        });
    });
-    // No album holds file 999, so fixing it fails. The summary from
+    // The refresh's progress is left out; the line saying why the command
-    // `--- Done ---` to the end of the `Failed files:` list is left out. The
+    // failed is the fatal one, and it is printed.
    // 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 () => {
-        const fix = ["helper", "fix-missing-thumbnails", "--file", "999"];
+        expect(await quak("-q", "files", "9")).toEqual({
        expect(await quak("-q", ...fix)).toEqual({
            code: 1,
            stdout: "",
-            stderr: `quak: 1 file(s) failed; see the "Failed files:" list, or the JSON with --json\n`,
+            stderr: "Collection 9 not found\n",
        });
    });
@@ -41,7 +41,6 @@ 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,
@@ -57,8 +56,8 @@ 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 +66,6 @@ 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 +204,6 @@ 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 +230,7 @@ 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 +270,12 @@ 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 +432,7 @@ 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 +452,8 @@ 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 () => {
@@ -662,7 +541,7 @@ 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(
@@ -720,7 +599,7 @@ 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 () => {
@@ -3,25 +3,20 @@
 * issue #36, issue #52).
 *
 * The `collections`, `files`, `get`, and `get-thumb` commands must answer for
- * current server state, not the local cache. `get`, `get-thumb` and `files`
+ * current server state, not the local cache. `files`, `get` and `get-thumb`
- * without a collection ID force a `Library.fresh()` round-trip before they
+ * force a `Library.fresh()` round-trip before they read; the stand-in library
- * read. The stand-in library below serves no cached record until `fresh()` has
+ * below serves nothing until `fresh()` has been awaited, so a helper that read
- * been awaited, so a helper that read without refreshing would come back empty
+ * without refreshing would come back empty and fail here. `collections` asks
- * and fail here. `collections` asks the library for the collection list alone
+ * the library for the collection list alone (`freshCollections()`, issue
- * (`freshCollections()`, issue #210). `files` with a collection ID asks for
+ * #210), and must not wait for a refresh, which would fetch the files of every
- * that list, then for that one collection's files (`freshFiles()`, issue
+ * collection.
 * #217). Neither may wait for a refresh, which would fetch the files of every
 * collection. On an empty cache, `get` and `get-thumb` ask for that list, then
 * for one collection's files at a time, until they find the file (issue #222).
 * `helper fix-missing-thumbnails --file` does the same until it finds every
 * file it names, reading the most recently updated collection first (issue
 * #223).
 *
- * `collections` and `files` also list in the order the library gives them, not
+ * `collections` and `files` also list in the library's enumeration order
 * (`listCollections`/`listFiles`) — the order the pre-library CLI printed — not
 * the albums/photos projection's newest-first order. The fixtures are seeded in
- * an order that a newest-first sort would rearrange, so a regression to the
+ * an enumeration order that a newest-first sort would rearrange, so a
- * projection order would fail here too. Field values still come from the raw
+ * regression to the projection order would fail here too. Field values still
- * metadata via `cli-output.ts`.
+ * come from the raw metadata via `cli-output.ts`.
 */
 import { describe, it, expect } from "vitest";
@@ -30,10 +25,10 @@ import {
    freshCollections,
    freshFiles,
    freshFile,
    freshFilesByID,
    type FreshReadLibrary,
 } from "../../src/cli-read.js";
 import { fileListRow } from "../../src/cli-output.js";
 import type { Photo } from "../../src/library/index.js";
 import type { Collection, EnteFile } from "../../src/model/types.js";
 const collection = (id: number, updationTime: number): Collection => ({
@@ -67,15 +62,14 @@ const file = (
    updationTime: creationTime,
 });
-// A library that reveals its cached records only after `fresh()` has been
+// A library that reveals its records only after `fresh()` has been awaited, and
-// awaited, and serves them in the enumeration order it was given.
+// serves them in the enumeration order it was given. `freshCollections()`
-// `freshCollections()` and `freshFiles()` answer in that order without a
+// answers the collection list in that order without a refresh. `photos.byID`
-// refresh.
+// returns a stand-in `Photo` carrying just the fileID the helper passes
 // through.
 class FakeLibrary implements FreshReadLibrary {
    freshCalls = 0;
    freshCollectionsCalls = 0;
    // The ID of each collection `freshFiles()` was asked for.
    freshFilesCalls: number[] = [];
    private refreshed = false;
    constructor(
@@ -94,9 +88,9 @@ class FakeLibrary implements FreshReadLibrary {
        return this.collections;
    }
-    async freshFiles(collection: Collection): Promise<EnteFile[]> {
+    getCollection(id: number): Collection | undefined {
-        this.freshFilesCalls.push(collection.id);
+        if (!this.refreshed) return undefined;
-        return this.files.filter((f) => f.collectionID === collection.id);
+        return this.collections.find((c) => c.id === id);
    }
    listCollections(): Collection[] {
@@ -113,6 +107,14 @@ class FakeLibrary implements FreshReadLibrary {
        if (!this.refreshed) return undefined;
        return this.files.find((f) => f.id === fileID);
    }
    photos = {
        byID: ({ fileID }: { fileID: number }): Photo | undefined => {
            if (!this.refreshed) return undefined;
            if (!this.files.some((f) => f.id === fileID)) return undefined;
            return { fileID } as unknown as Photo;
        },
    };
 }
 describe("CLI read helpers (issue #36 amendment, issue #52)", () => {
@@ -136,24 +138,18 @@ describe("CLI read helpers (issue #36 amendment, issue #52)", () => {
        expect(rows.map((c) => c.id)).not.toEqual(newestFirst);
    });
-    it("freshFiles with a collection ID reads that collection's files alone and keeps their order and raw fields", async () => {
+    it("freshFiles refreshes first, lists in enumeration order, keeps raw fields", async () => {
-        // Given in the order 10, 11, 12; creationTimes ascending, so a
+        // Enumeration order by id 10, 11, 12; creationTimes ascending, so a
        // newest-first sort would reverse them.
        const files = [
            file(10, 1, 1_700_000_000_000_000),
            file(11, 1, 1_700_000_000_000_001),
            file(12, 1, 1_700_000_000_000_002),
            file(20, 2, 1_700_000_000_000_003),
        ];
-        const lib = new FakeLibrary(
+        const lib = new FakeLibrary([collection(1, 100)], files);
            [collection(1, 100), collection(2, 200)],
            files,
        );
        const rows = await freshFiles(lib, 1);
-        expect(lib.freshCalls).toBe(0);
+        expect(lib.freshCalls).toBe(1);
        expect(lib.freshCollectionsCalls).toBe(1);
        expect(lib.freshFilesCalls).toEqual([1]);
        expect(rows?.map((f) => f.id)).toEqual([10, 11, 12]);
        // Field values come from raw metadata: microsecond creationTime and the
@@ -210,117 +206,27 @@ describe("CLI read helpers (issue #36 amendment, issue #52)", () => {
    it("freshFiles returns undefined for an unknown collection", async () => {
        const lib = new FakeLibrary([collection(1, 100)], []);
        const rows = await freshFiles(lib, 999);
-        expect(lib.freshCalls).toBe(0);
+        expect(lib.freshCalls).toBe(1);
        expect(lib.freshFilesCalls).toEqual([]);
        expect(rows).toBeUndefined();
    });
-    // Three collections, each holding one file.
+    it("freshFile refreshes first, then resolves the photo and its raw record", async () => {
-    const threeCollections = (): FakeLibrary =>
+        const f = file(10, 1, 1_700_000_000_000_000);
-        new FakeLibrary(
+        const lib = new FakeLibrary([collection(1, 100)], [f]);
-            [collection(1, 100), collection(2, 200), collection(3, 300)],
+
-            [
+        const resolved = await freshFile(lib, 10);
-                file(10, 1, 1_700_000_000_000_000),
+        expect(lib.freshCalls).toBe(1);
-                file(20, 2, 1_700_000_000_000_001),
+        expect(resolved?.photo.fileID).toBe(10);
-                file(30, 3, 1_700_000_000_000_002),
+        expect(resolved?.file.metadata.title).toBe("file-10.jpg");
-            ],
+        expect(resolved?.file.metadata.creationTime).toBe(
            1_700_000_000_000_000,
        );
    it("freshFile on an empty cache reads each collection's files in the server's order until one holds the file", async () => {
        const lib = threeCollections();
        const found = await freshFile(lib, 20);
        expect(lib.freshCalls).toBe(0);
        expect(lib.freshCollectionsCalls).toBe(1);
        expect(lib.freshFilesCalls).toEqual([1, 2]);
        expect(found?.metadata.title).toBe("file-20.jpg");
        expect(found?.metadata.creationTime).toBe(1_700_000_000_000_001);
    });
-    // The stand-in's cache holds what the server holds once `fresh()` has run.
+    it("freshFile returns undefined for an unknown file", async () => {
-    it("freshFile on a cache that holds the collections refreshes, then looks the file up in the cache", async () => {
+        const lib = new FakeLibrary([collection(1, 100)], []);
-        const lib = threeCollections();
+        const resolved = await freshFile(lib, 404);
-        await lib.fresh();
+        expect(lib.freshCalls).toBe(1);
-
+        expect(resolved).toBeUndefined();
        const found = await freshFile(lib, 30);
        expect(lib.freshCalls).toBe(2);
        expect(lib.freshCollectionsCalls).toBe(0);
        expect(lib.freshFilesCalls).toEqual([]);
        expect(found?.collectionID).toBe(3);
    });
    it("freshFile on an empty cache returns undefined for an unknown file, after reading every collection's files", async () => {
        const lib = threeCollections();
        const found = await freshFile(lib, 404);
        expect(lib.freshCalls).toBe(0);
        expect(lib.freshFilesCalls).toEqual([1, 2, 3]);
        expect(found).toBeUndefined();
    });
    // The server lists collections 1, 2 and 3, and collection 3 was updated
    // most recently. File 11 is in collections 1 and 2.
    const fileInTwoCollections = (): FakeLibrary =>
        new FakeLibrary(
            [collection(1, 100), collection(2, 200), collection(3, 300)],
            [
                file(10, 1, 1_700_000_000_000_000),
                file(11, 1, 1_700_000_000_000_001),
                file(11, 2, 1_700_000_000_000_001),
                file(20, 2, 1_700_000_000_000_002),
                file(30, 3, 1_700_000_000_000_003),
            ],
        );
    it("freshFilesByID on an empty cache reads the most recently updated collection's files first, until it has found every file", async () => {
        const lib = fileInTwoCollections();
        const found = await freshFilesByID(lib, [11, 20]);
        expect(lib.freshCalls).toBe(0);
        expect(lib.freshCollectionsCalls).toBe(1);
        expect(lib.freshFilesCalls).toEqual([3, 2]);
        expect(found.get(11)?.collection.id).toBe(2);
        expect(found.get(11)?.file.collectionID).toBe(2);
        expect(found.get(20)?.collection.id).toBe(2);
    });
    // Collection 1 was updated last, though collections 2 and 3 have higher
    // IDs. File 11 is in collections 1 and 2.
    it("freshFilesByID on an empty cache reads the most recently updated collection first, though its ID is the lowest", async () => {
        const lib = new FakeLibrary(
            [collection(1, 400), collection(2, 200), collection(3, 300)],
            [
                file(11, 1, 1_700_000_000_000_001),
                file(11, 2, 1_700_000_000_000_001),
            ],
        );
        const found = await freshFilesByID(lib, [11]);
        expect(lib.freshFilesCalls).toEqual([1]);
        expect(found.get(11)?.collection.id).toBe(1);
        expect(found.get(11)?.file.collectionID).toBe(1);
    });
    // The stand-in's cache holds what the server holds once `fresh()` has run.
    it("freshFilesByID on a cache that holds the collections refreshes, then finds each file in the most recently updated collection that holds it", async () => {
        const lib = fileInTwoCollections();
        await lib.fresh();
        const found = await freshFilesByID(lib, [11, 404]);
        expect(lib.freshCalls).toBe(2);
        expect(lib.freshCollectionsCalls).toBe(0);
        expect(lib.freshFilesCalls).toEqual([]);
        expect(found.get(11)?.collection.id).toBe(2);
        expect(found.get(11)?.file.collectionID).toBe(2);
        expect(found.has(404)).toBe(false);
    });
    it("freshFilesByID on an empty cache reads every collection's files when a file is in none of them", async () => {
        const lib = fileInTwoCollections();
        const found = await freshFilesByID(lib, [10, 404]);
        expect(lib.freshFilesCalls).toEqual([3, 2, 1]);
        expect(found.get(10)?.collection.id).toBe(1);
        expect(found.has(404)).toBe(false);
    });
 });
@@ -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
    ]
 }
@@ -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"]);
    });
 });
@@ -253,12 +253,6 @@ describe("Library content wiring", () => {
        await expect(
            lib.thumbnails.ensure({ fileIDs: [1], priority: "visible" }),
        ).rejects.toThrow(/content cache/i);
        await expect(lib.originalOf(file(1, 1))).rejects.toThrow(
            /content cache/i,
        );
        await expect(lib.thumbnailOf(file(1, 1))).rejects.toThrow(
            /content cache/i,
        );
        await lib.close();
    });
 });
@@ -375,25 +375,6 @@ describe("ContentCache.original / thumbnail", () => {
        await cache.open();
        await expect(cache.original(999)).rejects.toThrow(/unknown file/i);
    });
    // `getFile` knows no file here, so the cache can fetch only the file it is
    // given.
    it("originalOf and thumbnailOf fetch and cache the file they are given", async () => {
        const { cache, source } = buildCache({ files: [] });
        await cache.open();
        const original = await cache.originalOf(file(5));
        const thumbnail = await cache.thumbnailOf(file(5));
        expect(source.originalCalls).toEqual([5]);
        expect(source.thumbnailCalls).toEqual([5]);
        expect(original.path).toBe(join(cacheDir, "originals", "5.jpg"));
        expect(thumbnail.path).toBe(join(cacheDir, "thumbnails", "5.jpg"));
        expect(cache.pathsFor(5)).toEqual({
            originalPath: original.path,
            thumbnailPath: thumbnail.path,
        });
    });
 });
 describe("ContentCache.ensureThumbnails", () => {
@@ -6,12 +6,10 @@
 * working thumbnails, others return 404 or empty bodies. The tests
 * verify that the detection and repair logic handles each case correctly.
 *
- * `listMissingThumbnails` takes an open `Library` to enumerate the files. Both
+ * As of issue #52 both helpers take an open `Library` for enumeration and the
- * helpers take the `Client` for the API operations: the thumbnail existence
+ * `Client` for the API operations that stay unchanged (the thumbnail existence
- * check, and the encrypt-and-upload path. `fixMissingThumbnails` takes the
+ * check, and the encrypt-and-upload path). `fixMissingThumbnails` reads each
- * record of each file, which these tests look up with `cachedFilesByID`. It
+ * original through the library's content cache (`photo.original()`).
 * reads each original through the library's content cache, by
 * `lib.originalOf(file)`.
 *
 * `fixMissingThumbnails` is the most complex function in quak: it
 * downloads the original file, generates a JPEG thumbnail with jpeg-js,
@@ -43,7 +41,6 @@ import {
 import { SRP, SrpServer } from "fast-srp-hap";
 import { Client } from "../../src/client.js";
 import { Library } from "../../src/library/index.js";
 import { cachedFilesByID } from "../../src/cli-read.js";
 import {
    listMissingThumbnails,
    fixMissingThumbnails,
@@ -659,12 +656,7 @@ describe("fixMissingThumbnails", () => {
        const client = await login(buildThumbFetch(fixMock));
        const lib = await openLib(client);
-        const results = await fixMissingThumbnails(
+        const results = await fixMissingThumbnails(lib, client, [101]);
            lib,
            client,
            [101],
            cachedFilesByID(lib, [101]),
        );
        lib.close();
        expect(results.length).toBe(1);
@@ -701,12 +693,7 @@ describe("fixMissingThumbnails", () => {
        const client = await login(buildThumbFetch(fixMock));
        const lib = await openLib(client);
-        const results = await fixMissingThumbnails(
+        const results = await fixMissingThumbnails(lib, client, [999]);
            lib,
            client,
            [999],
            cachedFilesByID(lib, [999]),
        );
        lib.close();
        expect(results.length).toBe(1);
@@ -728,7 +715,6 @@ describe("fixMissingThumbnails", () => {
            lib,
            client,
            [101, 102],
            cachedFilesByID(lib, [101, 102]),
            (msg, level) => {
                if (level === "error") errors.push(msg);
            },
@@ -759,7 +745,6 @@ describe("fixMissingThumbnails", () => {
            lib,
            client,
            [101, 103, 104],
            cachedFilesByID(lib, [101, 103, 104]),
        );
        lib.close();
@@ -794,12 +779,7 @@ describe("fixMissingThumbnails", () => {
        const client = await login(counted.fetch);
        const lib = await openLib(client);
-        const results = await fixMissingThumbnails(
+        const results = await fixMissingThumbnails(lib, client, [101]);
            lib,
            client,
            [101],
            cachedFilesByID(lib, [101]),
        );
        lib.close();
        expect(results[0]!.status).toBe("skipped");
@@ -820,12 +800,7 @@ describe("fixMissingThumbnails", () => {
        const client = await login(counted.fetch);
        const lib = await openLib(client);
-        const results = await fixMissingThumbnails(
+        const results = await fixMissingThumbnails(lib, client, [101]);
            lib,
            client,
            [101],
            cachedFilesByID(lib, [101]),
        );
        lib.close();
        expect(results[0]!.status).toBe("skipped");
@@ -866,12 +841,7 @@ describe("fixMissingThumbnails", () => {
        const client = await login(buildThumbFetch(fixMock));
        const lib = await openLib(client);
-        const results = await fixMissingThumbnails(
+        const results = await fixMissingThumbnails(lib, client, [101]);
            lib,
            client,
            [101],
            cachedFilesByID(lib, [101]),
        );
        lib.close();
        expect(results[0]!.status).toBe("fixed");