Precache all thumbnails and pinned originals from Library.open (closes #48)

Two background fills start inside open() with no caller input, through the
shared pools (#45) at background priority, so on-demand work always preempts
them. Thumbnails: every file newest first until all are on disk, sharing the
pool with thumbnails.ensure. Originals: the pinned set — favorites, then the
latest-week window ending at the newest file — through the content pool. The
pinned set is the eviction predicate (#47): a pinned original is never evicted,
and a file that leaves the set (favorite removed, or window moved on a later
refresh) becomes an ordinary evictable original. Each refresh re-kicks the
fills to pick up new files and retry failures. Progress via open() onProgress
and status().

Model: opus-4-8

src/library/content.ts

@@ -328,12 +328,45 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
     }
 
     async ensureThumbnails(args: EnsureOptions): Promise<EnsureResult[]> {
-        const priority = poolPriorityOf(args.priority);
+        return this.ensureMany(
+            "thumbnail",
+            poolPriorityOf(args.priority),
+            args.fileIDs,
+            args.signal,
+            args.onProgress,
+        );
+    }
+
+    // Fill originals through the content pool for the precache (#48), always at
+    // background priority so an on-demand `original()` preempts the fill. A
+    // present original is a map lookup and no fetch; a per-file failure is
+    // returned, not thrown, so one bad file never halts a background sweep.
+    async ensureOriginals(args: {
+        fileIDs: number[];
+        signal?: AbortSignal;
+        onProgress?: (event: EnsureEvent) => void;
+    }): Promise<EnsureResult[]> {
+        return this.ensureMany(
+            "original",
+            "background",
+            args.fileIDs,
+            args.signal,
+            args.onProgress,
+        );
+    }
+
+    private async ensureMany(
+        kind: Kind,
+        priority: Priority,
+        fileIDs: number[],
+        signal: AbortSignal | undefined,
+        onProgress: ((event: EnsureEvent) => void) | undefined,
+    ): Promise<EnsureResult[]> {
         // Dedup the request list so a repeated fileID is fetched once and
         // reported once, in first-requested order.
         const seen = new Set<number>();
         const unique: number[] = [];
-        for (const id of args.fileIDs) {
+        for (const id of fileIDs) {
             if (!seen.has(id)) {
                 seen.add(id);
                 unique.push(id);
@@ -341,24 +374,20 @@ export class ContentCache implements PhotoContent, ThumbnailsAPI {
         }
         return Promise.all(
             unique.map((fileID) =>
-                this.ensureOne(fileID, priority, args.signal, args.onProgress),
+                this.ensureOne(fileID, kind, priority, signal, onProgress),
             ),
         );
     }
 
     private async ensureOne(
         fileID: number,
+        kind: Kind,
         priority: Priority,
         signal: AbortSignal | undefined,
         onProgress: ((event: EnsureEvent) => void) | undefined,
     ): Promise<EnsureResult> {
         try {
-            const result = await this.acquire(
+            const result = await this.acquire(fileID, kind, priority, signal);
-                fileID,
-                "thumbnail",
-                priority,
-                signal,
-            );
             const status = result.cached ? "skipped" : "done";
             onProgress?.({ fileID, status, path: result.path });
             return { fileID, path: result.path };

src/library/index.ts

@@ -48,6 +48,8 @@ import {
     type EnsureOptions,
     type EnsureResult,
 } from "./content.js";
+import { makeMLDataAPI, type MLDataAPI } from "./mlsearch.js";
+import { Precache } from "./precache.js";
 
 export {
     Album,
@@ -71,6 +73,7 @@ export {
     type EnsureResult,
     type EnsureEvent,
 } from "./content.js";
+export { type MLDataAPI, type SimilarResult } from "./mlsearch.js";
 import type { CollectionsPage, FilesPage } from "../client.js";
 import { MLDATA_BATCH_SIZE, type MLData } from "../mldata-fetch.js";
 import type { Collection, EnteFile } from "../model/types.js";
@@ -85,6 +88,23 @@ export {
 
 export const DEFAULT_REFRESH_INTERVAL_SECONDS = 3;
 
+// Project a metadata store into by-id records, filling each record's cache
+// paths from the content cache when one is given. Shared by the live read
+// projection and the precache's initial seeding at open().
+const deriveRecordsFromStore = (
+    store: MetadataStore,
+    cache?: ContentCache,
+): DerivedRecords => {
+    const collections = store.listCollections();
+    const files: EnteFile[] = [];
+    for (const c of collections) files.push(...store.listFiles(c.id));
+    return deriveRecords(
+        collections,
+        files,
+        cache ? (fileID) => cache.pathsFor(fileID) : undefined,
+    );
+};
+
 // The slice of `Client` the library depends on. Narrowing to an interface lets
 // tests drive a mock with no crypto or network; the real `Client` satisfies it
 // structurally.
@@ -113,9 +133,15 @@ export interface LibraryClient {
 // A progress event for one unit of background work. A metadata "refresh" or an
 // ML "fetchMLData" pass each fire "started" before their network work and then
 // exactly one of "done" or "failed"; "failed" carries the error message and
-// an ML "done" reports how many payloads it stored.
+// an ML "done" reports how many payloads it stored. The precache fills
+// ("precacheThumbnails"/"precacheOriginals", #48) fire "started"/"done" around
+// each sweep that has work, "done" reporting the count newly cached.
 export interface RefreshEvent {
-    operation: "refresh" | "fetchMLData";
+    operation:
+        | "refresh"
+        | "fetchMLData"
+        | "precacheThumbnails"
+        | "precacheOriginals";
     status: "started" | "done" | "failed";
     error?: string;
     fetched?: number;
@@ -145,9 +171,17 @@ export interface LibraryOptions {
     // down as the disk fills; `status().originalsLimitBytes` reports it.
     cacheOriginalsMaxBytes?: number;
     freeBelowBytes?: number;
-    // Whether an original is pinned and so never evicted (favorites + latest
+    // An extra pinned predicate OR-ed with the precache's own pinned set
-    // week; the precache unit #48 supplies the set).
+    // (favorites + latest week, #48). Pinned originals are never evicted.
     isOriginalPinned?: (fileID: number) => boolean;
+    // The aggressive local precache (#48), all starting inside `open()` with no
+    // caller input. Thumbnails: every file, newest first, until all are on
+    // disk. Originals: the favorites album then the latest `precacheOriginalsDays`
+    // window (the days ending at the newest file). Both default on; the days
+    // default to 7.
+    precacheThumbnails?: boolean;
+    precacheOriginals?: boolean;
+    precacheOriginalsDays?: number;
 }
 
 export interface LibraryStatus {
@@ -173,6 +207,13 @@ export interface LibraryStatus {
     // last write or open; undefined when no content cache is open.
     originalsUsedBytes?: number;
     originalsLimitBytes?: number;
+    // Precache progress (#48); undefined when no content cache is open. Totals
+    // are the files targeted (0 when a fill is disabled); "cached" is how many
+    // of them are on disk.
+    thumbnailsCached?: number;
+    thumbnailsTotal?: number;
+    originalsCached?: number;
+    originalsPinned?: number;
     closed: boolean;
 }
 
@@ -189,6 +230,10 @@ export class Library {
     // The thumbnail-prefetch surface (issue #46): drives the thumbnail pool
     // with priority, dedup, and abort.
     readonly thumbnails: ThumbnailsAPI;
+    // The content-similarity search surface over the CLIP index (issue #50).
+    // Present whether or not ML fetching is enabled; with no ML store it
+    // returns empty results.
+    readonly mldata: MLDataAPI;
 
     private readonly client: LibraryClient;
     private readonly store: MetadataStore;
@@ -200,7 +245,9 @@ export class Library {
     private readonly onProgress?: RefreshProgressCallback;
     private readonly pools: RequestPools;
     // The ML-data cache, present only when the client can fetch ML data.
-    private readonly mldata?: MLDataStore;
+    private readonly mlStore?: MLDataStore;
+    // The local precache (#48), present only when the content cache is.
+    private readonly precache?: Precache;
 
     private timer?: ReturnType<typeof setTimeout>;
     private refreshing = false;
@@ -234,6 +281,7 @@ export class Library {
         pools: RequestPools;
         mldata?: MLDataStore;
         cache?: ContentCache;
+        precache?: Precache;
     }) {
         this.client = args.client;
         this.store = args.store;
@@ -243,8 +291,9 @@ export class Library {
         this.intervalMs = args.intervalMs;
         this.onProgress = args.onProgress;
         this.pools = args.pools;
-        this.mldata = args.mldata;
+        this.mlStore = args.mldata;
         this.cache = args.cache;
+        this.precache = args.precache;
         this.lastRecords = this.deriveNow();
 
         // The read namespaces derive fresh from the store on each call, so they
@@ -265,6 +314,8 @@ export class Library {
                 return this.cache.ensureThumbnails(opts);
             },
         };
+        // Reads the ML store live so results grow as ML data is fetched.
+        this.mldata = makeMLDataAPI(() => this.mlStore);
     }
 
     // Load the cache and start the refresh loop. With an empty cache the first
@@ -302,7 +353,21 @@ export class Library {
         // the start and the first refresh raises no spurious path-change diff.
         const source = opts.contentSource ?? opts.client.contentSource?.();
         let cache: ContentCache | undefined;
+        let precache: Precache | undefined;
         if (source) {
+            // The precache owns the pinned set (favorites + latest week), which
+            // is the cache's eviction predicate. It is built and seeded from
+            // the loaded store first so the cache can wire `isPinned` to it, and
+            // then bound to the cache it fills. A caller-supplied predicate is
+            // OR-ed in so both survive.
+            precache = new Precache({
+                thumbnails: opts.precacheThumbnails,
+                originals: opts.precacheOriginals,
+                originalsDays: opts.precacheOriginalsDays,
+                onEvent: opts.onProgress,
+            });
+            precache.update(deriveRecordsFromStore(store));
+            const extraPinned = opts.isOriginalPinned;
             cache = new ContentCache({
                 pools,
                 source,
@@ -311,9 +376,12 @@ export class Library {
                 getFile: (fileID) => store.getFileByID(fileID),
                 cacheOriginalsMaxBytes: opts.cacheOriginalsMaxBytes,
                 freeBelowBytes: opts.freeBelowBytes,
-                isPinned: opts.isOriginalPinned,
+                isPinned: (fileID) =>
+                    precache!.isPinned(fileID) ||
+                    (extraPinned?.(fileID) ?? false),
             });
             await cache.open();
+            precache.bind(cache);
         }
 
         const lib = new Library({
@@ -327,8 +395,15 @@ export class Library {
             pools,
             mldata,
             cache,
+            precache,
         });
 
+        // Start filling from whatever the loaded store already holds; each
+        // refresh below re-kicks with the new files (and retries any that
+        // failed). An empty store starts empty here and fills after its first
+        // refresh.
+        precache?.start();
+
         if (store.loadedFromDisk) {
             // An existing copy already answers reads; refresh in the background
             // and start the interval once that first cycle settles.
@@ -386,8 +461,9 @@ export class Library {
         for (const c of collections) {
             files += this.store.listFiles(c.id).length;
         }
-        const ml = this.mldata?.stats();
+        const ml = this.mlStore?.stats();
         const originals = this.cache?.originalsStatus();
+        const pre = this.precache?.status();
         return {
             userID: this.store.userID,
             collections: collections.length,
@@ -400,6 +476,10 @@ export class Library {
             mlIndexed: ml?.indexed,
             originalsUsedBytes: originals?.usedBytes,
             originalsLimitBytes: originals?.limitBytes,
+            thumbnailsCached: pre?.thumbnailsCached,
+            thumbnailsTotal: pre?.thumbnailsTotal,
+            originalsCached: pre?.originalsCached,
+            originalsPinned: pre?.originalsPinned,
             closed: this.closed,
         };
     }
@@ -447,6 +527,7 @@ export class Library {
     // finish; it will not schedule another cycle once closed.
     close(): void {
         this.closed = true;
+        this.precache?.close();
         if (this.timer !== undefined) {
             clearTimeout(this.timer);
             this.timer = undefined;
@@ -564,7 +645,12 @@ export class Library {
                 if (change) this.notify(change);
             }
             this.lastRecords = next;
+            // Recompute the fill orders and pinned set against the new library.
+            this.precache?.update(next);
         }
+        // Re-kick the fills every cycle: a finished sweep starts afresh to pick
+        // up new files and retry any that failed, and a running one is left be.
+        this.precache?.start();
 
         // Persist whenever RAM holds changes disk has not accepted — including
         // changes an earlier cycle staged whose save failed. `unsaved` clears
@@ -583,7 +669,7 @@ export class Library {
     // advanced), through the metadata pool, and update the CLIP index. Guarded
     // so passes never overlap; a failure is reported, not thrown.
     private async runMLFetch(): Promise<void> {
-        const mldata = this.mldata;
+        const mldata = this.mlStore;
         // Bind so the call keeps the client as its receiver when invoked
         // through the pool below.
         const fetchMLData = this.client.fetchMLData?.bind(this.client);
@@ -660,15 +746,7 @@ export class Library {
     // Gather every file membership and project the store into by-id records,
     // filling each record's cache paths from the content cache when present.
     private deriveNow(): DerivedRecords {
-        const collections = this.store.listCollections();
+        return deriveRecordsFromStore(this.store, this.cache);
-        const files: EnteFile[] = [];
-        for (const c of collections) files.push(...this.store.listFiles(c.id));
-        const cache = this.cache;
-        return deriveRecords(
-            collections,
-            files,
-            cache ? (fileID) => cache.pathsFor(fileID) : undefined,
-        );
     }
 
     private notify(change: LibraryChange): void {

src/library/mlsearch.ts

@@ -0,0 +1,129 @@
+// The content-similarity search surface over the CLIP index (issue #50).
+//
+// This is `lib.mldata`. It answers three questions against the ML-data cache
+// (#49) without touching the network:
+//
+//   - `forFile` returns the whole stored payload (face boxes, landmarks,
+//     embedding) for a file, read from disk on demand — the only method here
+//     that touches the disk, and the only one that is async.
+//   - `similar` and `searchByEmbedding` rank fileIDs by cosine similarity over
+//     the packed `Float32Array` index alone. That index (~50k×512) already
+//     lives in RAM, so each query is a plain loop over it and nothing else.
+//
+// quak bundles no text encoder (owner-deferred), so `searchByEmbedding` takes
+// the query vector the caller has produced elsewhere; `similar` uses the
+// query file's own indexed embedding.
+
+import type { MLData } from "../mldata-fetch.js";
+import type { MLDataStore, MLIndex } from "./mldata.js";
+
+// How many nearest files a query returns when the caller names no limit.
+const DEFAULT_LIMIT = 20;
+
+// One ranked result: a fileID and its cosine similarity to the query, in
+// [-1, 1]. Callers wanting only the ids read `.fileID`.
+export interface SimilarResult {
+    fileID: number;
+    score: number;
+}
+
+export interface MLDataAPI {
+    // The whole stored ML payload for a file, or undefined when it is not
+    // cached. Reads the payload from disk, so it is async.
+    forFile(args: { fileID: number }): Promise<MLData | undefined>;
+    // The files nearest the given file by cosine over their CLIP embeddings,
+    // most similar first, excluding the file itself. Empty when the file has
+    // no indexed embedding.
+    similar(args: { fileID: number; limit?: number }): SimilarResult[];
+    // The files nearest a caller-supplied query embedding by cosine, most
+    // similar first. Empty when the query is the wrong length for the index,
+    // has zero magnitude, or the index is empty.
+    searchByEmbedding(args: {
+        embedding: ArrayLike<number>;
+        limit?: number;
+    }): SimilarResult[];
+}
+
+// Rank the packed index by cosine similarity to `query`, most similar first,
+// and return the top `limit`. `skip` (a query file's own id) is left out. Both
+// each row's magnitude and the query's are computed here rather than cached:
+// the index mutates as ML data is fetched, and one plain pass over ~50k×512
+// floats is fast enough that a norm cache would only add a staleness bug. A
+// zero-magnitude vector has no direction, so it is dropped rather than divided
+// by zero.
+const topByCosine = (
+    index: MLIndex,
+    query: ArrayLike<number>,
+    limit: number,
+    skip?: number,
+): SimilarResult[] => {
+    const { fileIDs, embeddingLength, embeddings } = index;
+    if (embeddingLength === 0 || query.length !== embeddingLength) return [];
+
+    // Every indexed read below is in range: the inner loops run to
+    // `embeddingLength`, the query is exactly that long (checked above), and
+    // the packed buffer holds `fileIDs.length * embeddingLength` floats.
+    // `noUncheckedIndexedAccess` still widens each read to `number | undefined`,
+    // so they are asserted non-null rather than paying a per-element guard in
+    // this hot ~50k×512 loop.
+    let queryNorm = 0;
+    for (let k = 0; k < embeddingLength; k++) {
+        const q = query[k]!;
+        queryNorm += q * q;
+    }
+    queryNorm = Math.sqrt(queryNorm);
+    if (queryNorm === 0) return [];
+
+    const results: SimilarResult[] = [];
+    for (let i = 0; i < fileIDs.length; i++) {
+        const id = fileIDs[i]!;
+        if (id === skip) continue;
+        const base = i * embeddingLength;
+        let dot = 0;
+        let norm = 0;
+        for (let k = 0; k < embeddingLength; k++) {
+            const v = embeddings[base + k]!;
+            dot += query[k]! * v;
+            norm += v * v;
+        }
+        if (norm === 0) continue;
+        results.push({
+            fileID: id,
+            score: dot / (queryNorm * Math.sqrt(norm)),
+        });
+    }
+
+    // Descending score, ties broken by ascending fileID for a stable order.
+    results.sort((a, b) => b.score - a.score || a.fileID - b.fileID);
+    return results.slice(0, Math.max(0, Math.trunc(limit)));
+};
+
+// Build the search surface over a store the library supplies lazily (the store
+// is absent when the client cannot fetch ML data). Reading it per call keeps
+// the surface current as the index grows.
+export const makeMLDataAPI = (
+    store: () => MLDataStore | undefined,
+): MLDataAPI => ({
+    forFile: ({ fileID }): Promise<MLData | undefined> => {
+        const s = store();
+        return s ? s.readPayload(fileID) : Promise.resolve(undefined);
+    },
+    similar: ({ fileID, limit }): SimilarResult[] => {
+        const s = store();
+        if (!s) return [];
+        const index = s.getIndex();
+        const pos = index.fileIDs.indexOf(fileID);
+        if (pos < 0) return [];
+        const base = pos * index.embeddingLength;
+        const query = index.embeddings.subarray(
+            base,
+            base + index.embeddingLength,
+        );
+        return topByCosine(index, query, limit ?? DEFAULT_LIMIT, fileID);
+    },
+    searchByEmbedding: ({ embedding, limit }): SimilarResult[] => {
+        const s = store();
+        if (!s) return [];
+        return topByCosine(s.getIndex(), embedding, limit ?? DEFAULT_LIMIT);
+    },
+});

src/library/precache.ts

@@ -0,0 +1,265 @@
+// The aggressive local precache (issue #48), started from `Library.open` with
+// no caller input.
+//
+// Two background fills run concurrently through the shared request pools (#45):
+//
+//   - Thumbnails: every file in the account, newest first, through the
+//     thumbnail pool until all are on disk. Never evicted. The pool is the same
+//     one `thumbnails.ensure` uses, so a visible or ahead request always jumps
+//     ahead of this background fill and a fileID both want is fetched once.
+//
+//   - Originals (the pinned set): through the content pool, the favorites album
+//     first, then every file whose `takenAt` falls in the latest
+//     `originalsDays` window — the days ending at the newest file in the
+//     account. The pinned set is the eviction predicate (#47): a pinned
+//     original is never evicted, and a file that leaves the set (a favorite
+//     removed, or the window moving past it on a later refresh) becomes an
+//     ordinary, evictable original with its bytes left in place.
+//
+// Both fills yield to on-demand work: every fetch goes to its pool at
+// background priority, which the pool serves only after on-demand requests. A
+// file already cached costs one map lookup (`pathsFor`) and no fetch. Each
+// sweep is driven in bounded chunks so the pool's waiting queue never grows to
+// the whole account, keeping on-demand preemption and per-admit cost cheap on a
+// large library. Failures are not fatal: an uncached file is retried on the
+// next sweep, which `Library` re-kicks after every refresh.
+
+import type { EnsureResult } from "./content.js";
+import type { DerivedRecords } from "./records.js";
+
+const ONE_DAY_MS = 24 * 60 * 60 * 1000;
+
+export const DEFAULT_PRECACHE_ORIGINALS_DAYS = 7;
+
+// How many files a sweep submits to a pool before awaiting them. Bounds the
+// pool's waiting queue so on-demand work is never stuck behind the whole
+// account; the values track each pool's concurrency (#45).
+const THUMBNAIL_CHUNK = 25;
+const ORIGINAL_CHUNK = 5;
+
+// The precache metrics `Library.status()` surfaces.
+export interface PrecacheStatus {
+    thumbnailsCached: number;
+    thumbnailsTotal: number;
+    originalsCached: number;
+    originalsPinned: number;
+}
+
+// A background-fill progress event. Each active sweep fires "started" before
+// its fetches and "done" (with the count newly on disk) after; a sweep with
+// nothing left to fetch is silent.
+export interface PrecacheEvent {
+    operation: "precacheThumbnails" | "precacheOriginals";
+    status: "started" | "done";
+    fetched?: number;
+}
+
+// The slice of the content cache the precache drives. The real `ContentCache`
+// satisfies it; tests inject a fake.
+export interface PrecacheCache {
+    pathsFor(fileID: number): { originalPath?: string; thumbnailPath?: string };
+    ensureThumbnails(args: {
+        fileIDs: number[];
+        priority: "background";
+        signal?: AbortSignal;
+    }): Promise<EnsureResult[]>;
+    ensureOriginals(args: {
+        fileIDs: number[];
+        signal?: AbortSignal;
+    }): Promise<EnsureResult[]>;
+}
+
+export interface PrecacheOptions {
+    // Default true; false disables the fill and, for originals, the pinning.
+    thumbnails?: boolean;
+    originals?: boolean;
+    // The latest-week window length in days; default 7.
+    originalsDays?: number;
+    onEvent?: (event: PrecacheEvent) => void;
+}
+
+export class Precache {
+    private readonly doThumbnails: boolean;
+    private readonly doOriginals: boolean;
+    private readonly originalsDays: number;
+    private readonly onEvent?: (event: PrecacheEvent) => void;
+
+    private cache?: PrecacheCache;
+    // Every file in the account, newest first (the thumbnail fill order).
+    private thumbOrder: number[] = [];
+    // The pinned originals in fetch order: favorites first, then the window.
+    private originalsOrder: number[] = [];
+    private pinned = new Set<number>();
+
+    // A sweep runs at most once per fill at a time; a re-kick while one runs is
+    // a no-op, and the next refresh re-kicks after it finishes.
+    private thumbRunning = false;
+    private originalsRunning = false;
+    private readonly aborter = new AbortController();
+    private closed = false;
+
+    constructor(opts: PrecacheOptions = {}) {
+        this.doThumbnails = opts.thumbnails ?? true;
+        this.doOriginals = opts.originals ?? true;
+        this.originalsDays =
+            opts.originalsDays ?? DEFAULT_PRECACHE_ORIGINALS_DAYS;
+        this.onEvent = opts.onEvent;
+    }
+
+    // Attach the cache the fills fetch through. `isPinned` works before this is
+    // called, so the cache can be constructed with `isPinned` wired in and then
+    // bound here.
+    bind(cache: PrecacheCache): void {
+        this.cache = cache;
+    }
+
+    // Whether an original is pinned (favorites + the latest-week window), the
+    // eviction predicate (#47). False for every file when originals precaching
+    // is disabled.
+    isPinned(fileID: number): boolean {
+        return this.pinned.has(fileID);
+    }
+
+    // Recompute the fill orders and the pinned set from the current projection.
+    // Called at open and after every refresh that changes the library.
+    update(records: DerivedRecords): void {
+        const photos = [...records.photos.values()].sort(
+            (a, b) => b.takenAt - a.takenAt || b.fileID - a.fileID,
+        );
+
+        this.thumbOrder = this.doThumbnails ? photos.map((p) => p.fileID) : [];
+
+        const pinned = new Set<number>();
+        const order: number[] = [];
+        if (this.doOriginals) {
+            // Favorites first, in the album's own newest-first order.
+            for (const album of records.albums.values()) {
+                if (album.type !== "favorites") continue;
+                for (const id of album.fileIDs) {
+                    if (!pinned.has(id)) {
+                        pinned.add(id);
+                        order.push(id);
+                    }
+                }
+            }
+            // Then the latest-week window, ending at the newest file. Photos
+            // are newest first, so stop once one falls before the window start.
+            const newest = photos[0];
+            if (newest !== undefined) {
+                const windowStart =
+                    newest.takenAt - this.originalsDays * ONE_DAY_MS;
+                for (const p of photos) {
+                    if (p.takenAt < windowStart) break;
+                    if (!pinned.has(p.fileID)) {
+                        pinned.add(p.fileID);
+                        order.push(p.fileID);
+                    }
+                }
+            }
+        }
+        this.pinned = pinned;
+        this.originalsOrder = order;
+    }
+
+    status(): PrecacheStatus {
+        const cache = this.cache;
+        let thumbnailsCached = 0;
+        let originalsCached = 0;
+        if (cache) {
+            for (const id of this.thumbOrder)
+                if (cache.pathsFor(id).thumbnailPath !== undefined)
+                    thumbnailsCached++;
+            for (const id of this.originalsOrder)
+                if (cache.pathsFor(id).originalPath !== undefined)
+                    originalsCached++;
+        }
+        return {
+            thumbnailsCached,
+            thumbnailsTotal: this.thumbOrder.length,
+            originalsCached,
+            originalsPinned: this.originalsOrder.length,
+        };
+    }
+
+    // Kick both fills. Idempotent: a fill already sweeping is left alone. Safe
+    // to call after every refresh; a finished fill starts a fresh sweep that
+    // picks up new files and retries any that failed before.
+    start(): void {
+        if (this.closed || !this.cache) return;
+        if (this.doThumbnails) this.kickThumbnails();
+        if (this.doOriginals) this.kickOriginals();
+    }
+
+    // Stop the fills. In-flight fetches are left to settle; queued ones drop.
+    close(): void {
+        this.closed = true;
+        this.aborter.abort();
+    }
+
+    private kickThumbnails(): void {
+        if (this.thumbRunning) return;
+        this.thumbRunning = true;
+        void this.sweep(
+            "precacheThumbnails",
+            () => this.thumbOrder,
+            (id) => this.cache!.pathsFor(id).thumbnailPath !== undefined,
+            THUMBNAIL_CHUNK,
+            (chunk) =>
+                this.cache!.ensureThumbnails({
+                    fileIDs: chunk,
+                    priority: "background",
+                    signal: this.aborter.signal,
+                }),
+        ).finally(() => {
+            this.thumbRunning = false;
+        });
+    }
+
+    private kickOriginals(): void {
+        if (this.originalsRunning) return;
+        this.originalsRunning = true;
+        void this.sweep(
+            "precacheOriginals",
+            () => this.originalsOrder,
+            (id) => this.cache!.pathsFor(id).originalPath !== undefined,
+            ORIGINAL_CHUNK,
+            (chunk) =>
+                this.cache!.ensureOriginals({
+                    fileIDs: chunk,
+                    signal: this.aborter.signal,
+                }),
+        ).finally(() => {
+            this.originalsRunning = false;
+        });
+    }
+
+    // One fill sweep: skip files already on disk (one lookup each), fetch the
+    // rest in bounded chunks, and report progress only when there was work.
+    private async sweep(
+        operation: PrecacheEvent["operation"],
+        order: () => number[],
+        present: (fileID: number) => boolean,
+        chunkSize: number,
+        fetch: (chunk: number[]) => Promise<EnsureResult[]>,
+    ): Promise<void> {
+        const todo = order().filter((id) => !present(id));
+        if (todo.length === 0) return;
+        this.emit({ operation, status: "started" });
+        let fetched = 0;
+        for (let i = 0; i < todo.length && !this.closed; i += chunkSize) {
+            const results = await fetch(todo.slice(i, i + chunkSize));
+            for (const r of results) if (r.path !== undefined) fetched++;
+        }
+        this.emit({ operation, status: "done", fetched });
+    }
+
+    private emit(event: PrecacheEvent): void {
+        if (!this.onEvent) return;
+        // A misbehaving callback must not break the fill loop.
+        try {
+            this.onEvent(event);
+        } catch {
+            // ignore
+        }
+    }
+}

test/cli/backup.test.ts

@@ -142,6 +142,10 @@ const openLibrary = (source: ContentSource): Promise<Library> =>
         cacheDirectory: join(root, "cache"),
         contentSource: source,
         refreshIntervalSeconds: 3600,
+        // These tests count exact fetches; the background precache (#48) would
+        // add its own, so it is off here (it is covered in precache.test.ts).
+        precacheThumbnails: false,
+        precacheOriginals: false,
     });
 
 const readLedger = (

test/library/content-library.test.ts

@@ -99,6 +99,10 @@ describe("Library content wiring", () => {
             cacheDirectory: join(root, "cache"),
             contentSource: source,
             refreshIntervalSeconds: 3600,
+            // On-demand wiring only; the background precache (#48) is covered
+            // in precache.test.ts and would race the exact-count assertions.
+            precacheThumbnails: false,
+            precacheOriginals: false,
         });
 
         const photo = lib.photos.byID({ fileID: 1 });
@@ -122,6 +126,10 @@ describe("Library content wiring", () => {
             cacheDirectory: join(root, "cache"),
             contentSource: source,
             refreshIntervalSeconds: 3600,
+            // On-demand wiring only; the background precache (#48) is covered
+            // in precache.test.ts and would race the exact-count assertions.
+            precacheThumbnails: false,
+            precacheOriginals: false,
         });
 
         const results = await lib.thumbnails.ensure({

test/library/mlsearch.test.ts

@@ -0,0 +1,108 @@
+/**
+ * Tests for the content-similarity search surface over the CLIP index
+ * (issue #50).
+ *
+ * The surface is `lib.mldata`: `forFile` reads the full stored payload from
+ * disk, while `similar` and `searchByEmbedding` rank fileIDs by cosine
+ * similarity over the in-RAM `Float32Array` index alone (no disk, no network).
+ * The fixture uses axis-aligned vectors so the correct cosine ranking is
+ * obvious by inspection; cosine ignores magnitude, so `[2, 0, 0]` ranks above
+ * `[0.8, 0.6, 0]` for a `[1, 0, 0]` query.
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { mkdtempSync, rmSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+
+import { MLDataStore } from "../../src/library/mldata.js";
+import { makeMLDataAPI, type MLDataAPI } from "../../src/library/mlsearch.js";
+import type { MLData } from "../../src/mldata-fetch.js";
+
+// A payload shaped like Ente's: a CLIP embedding plus face data that only the
+// on-disk payload carries (never the RAM index).
+const payload = (embedding: number[]): MLData => ({
+    face: { faces: [{ faceID: "f", detection: { box: { x: 0.5 } } }] },
+    clip: { embedding },
+});
+
+// A small fixture index. Directions are chosen so every cosine ranking below
+// is unambiguous.
+const fixture = (): Map<number, MLData> =>
+    new Map([
+        [10, payload([1, 0, 0])],
+        [20, payload([0.8, 0.6, 0])],
+        [30, payload([0, 1, 0])],
+        [40, payload([-1, 0, 0])],
+        [50, payload([2, 0, 0])],
+    ]);
+
+describe("lib.mldata content-similarity search", () => {
+    let dir: string;
+    let store: MLDataStore;
+    let api: MLDataAPI;
+
+    beforeEach(async () => {
+        dir = mkdtempSync(join(tmpdir(), "quak-mlsearch-"));
+        store = await MLDataStore.open(dir);
+        const updation = new Map([...fixture().keys()].map((id) => [id, 1]));
+        await store.storeFetched(fixture(), updation);
+        api = makeMLDataAPI(() => store);
+    });
+
+    afterEach(() => {
+        rmSync(dir, { recursive: true, force: true });
+    });
+
+    it("forFile returns the whole stored payload, or undefined when uncached", async () => {
+        const full = await api.forFile({ fileID: 20 });
+        expect(full).toBeDefined();
+        // Face data lives only in the payload, never in the RAM index.
+        expect(full?.face).toBeDefined();
+        expect(full?.clip).toEqual({ embedding: [0.8, 0.6, 0] });
+        expect(await api.forFile({ fileID: 999 })).toBeUndefined();
+    });
+
+    it("similar ranks other files by cosine and excludes the query itself", () => {
+        // Query is file 10 = [1, 0, 0]. By cosine: 50 (1.0) > 20 (0.8) >
+        // 30 (0) > 40 (-1); 10 itself is left out.
+        const ranked = api.similar({ fileID: 10 });
+        expect(ranked.map((r) => r.fileID)).toEqual([50, 20, 30, 40]);
+        // Cosine ignores magnitude: [2,0,0] is a perfect match for [1,0,0].
+        expect(ranked[0]).toMatchObject({ fileID: 50 });
+        expect(ranked[0].score).toBeCloseTo(1, 5);
+    });
+
+    it("similar honours limit and returns [] for an unindexed file", () => {
+        expect(
+            api.similar({ fileID: 10, limit: 2 }).map((r) => r.fileID),
+        ).toEqual([50, 20]);
+        expect(api.similar({ fileID: 999 })).toEqual([]);
+    });
+
+    it("searchByEmbedding ranks the index by cosine to the query vector", () => {
+        // Query [0, 1, 0]: 30 (1.0) > 20 (0.6) > {10, 40, 50} all 0, broken by
+        // ascending fileID.
+        const ranked = api.searchByEmbedding({ embedding: [0, 1, 0] });
+        expect(ranked.map((r) => r.fileID)).toEqual([30, 20, 10, 40, 50]);
+        expect(ranked[0].score).toBeCloseTo(1, 5);
+
+        expect(
+            api
+                .searchByEmbedding({ embedding: [0, 1, 0], limit: 2 })
+                .map((r) => r.fileID),
+        ).toEqual([30, 20]);
+    });
+
+    it("searchByEmbedding returns [] for a wrong-length or zero query", () => {
+        expect(api.searchByEmbedding({ embedding: [1, 0] })).toEqual([]);
+        expect(api.searchByEmbedding({ embedding: [0, 0, 0] })).toEqual([]);
+    });
+
+    it("degrades to empty results when no ML store is present", async () => {
+        const none = makeMLDataAPI(() => undefined);
+        expect(await none.forFile({ fileID: 10 })).toBeUndefined();
+        expect(none.similar({ fileID: 10 })).toEqual([]);
+        expect(none.searchByEmbedding({ embedding: [1, 0, 0] })).toEqual([]);
+    });
+});

test/library/precache.test.ts

@@ -0,0 +1,436 @@
+/**
+ * The aggressive local precache (issue #48), driven from `Library.open`.
+ *
+ * Two background fills start with no caller input: every thumbnail in the
+ * account newest first, and the originals of the pinned set (the favorites
+ * album then the latest `precacheOriginalsDays` window ending at the newest
+ * file). Both run through the shared pools at background priority, so on-demand
+ * work always preempts them; both report through `status()`. The pinned set is
+ * the eviction predicate (#47), so a pinned original is never evicted and a
+ * file that leaves the set becomes an ordinary, evictable original.
+ *
+ * The unit tests drive `Precache` against a fake cache that records what it was
+ * asked to fetch (order and kind) with no pool or network; the integration
+ * tests drive the real wiring through `Library.open` with a stub content
+ * source, and the eviction test drives the real `ContentCache`.
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { mkdtempSync, rmSync, existsSync, utimesSync } from "node:fs";
+import { writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+
+import { Precache, type PrecacheCache } from "../../src/library/precache.js";
+import {
+    deriveRecords,
+    type DerivedRecords,
+} from "../../src/library/records.js";
+import {
+    ContentCache,
+    type ContentSource,
+    type EnsureResult,
+    type StatFsFn,
+} from "../../src/library/content.js";
+import { RequestPools } from "../../src/library/pools.js";
+import { Library } from "../../src/library/index.js";
+import type { Collection, EnteFile } from "../../src/model/types.js";
+import type { CollectionsPage, FilesPage } from "../../src/client.js";
+
+const DAY_MICROS = 24 * 60 * 60 * 1000 * 1000;
+
+const collection = (
+    id: number,
+    type: Collection["type"] = "album",
+): Collection => ({
+    id,
+    ownerID: 1,
+    key: new Uint8Array([id & 0xff]),
+    name: `album-${id}`,
+    type,
+    updationTime: 1,
+    isShared: false,
+});
+
+// A file whose creationTime (microseconds) places it `daysAgo` days before a
+// fixed reference instant, so the latest-week window is deterministic.
+const REFERENCE_MICROS = 1_000 * DAY_MICROS;
+const file = (id: number, collectionID: number, daysAgo: number): EnteFile => ({
+    id,
+    collectionID,
+    ownerID: 1,
+    key: new Uint8Array([id & 0xff]),
+    metadata: {
+        title: `file-${id}.jpg`,
+        fileType: "image",
+        creationTime: REFERENCE_MICROS - daysAgo * DAY_MICROS,
+        modificationTime: 0,
+    },
+    file: { decryptionHeader: "aGVhZGVy" },
+    thumbnail: { decryptionHeader: "dGh1bWI=" },
+    updationTime: 1,
+});
+
+const records = (
+    collections: Collection[],
+    files: EnteFile[],
+): DerivedRecords => deriveRecords(collections, files);
+
+// A fake cache: records every fetch (kind + order) and reports the files it has
+// stored via `pathsFor`. `presentThumbs`/`presentOriginals` seed already-cached
+// files so the precache skips them with a single lookup.
+class FakeCache implements PrecacheCache {
+    readonly thumbFetched: number[] = [];
+    readonly originalFetched: number[] = [];
+    readonly presentThumbs = new Set<number>();
+    readonly presentOriginals = new Set<number>();
+
+    pathsFor(fileID: number): {
+        originalPath?: string;
+        thumbnailPath?: string;
+    } {
+        const out: { originalPath?: string; thumbnailPath?: string } = {};
+        if (this.presentThumbs.has(fileID))
+            out.thumbnailPath = `/thumbs/${fileID}`;
+        if (this.presentOriginals.has(fileID))
+            out.originalPath = `/originals/${fileID}`;
+        return out;
+    }
+
+    async ensureThumbnails(args: {
+        fileIDs: number[];
+        priority: "background";
+    }): Promise<EnsureResult[]> {
+        return args.fileIDs.map((fileID) => {
+            this.thumbFetched.push(fileID);
+            this.presentThumbs.add(fileID);
+            return { fileID, path: `/thumbs/${fileID}` };
+        });
+    }
+
+    async ensureOriginals(args: {
+        fileIDs: number[];
+    }): Promise<EnsureResult[]> {
+        return args.fileIDs.map((fileID) => {
+            this.originalFetched.push(fileID);
+            this.presentOriginals.add(fileID);
+            return { fileID, path: `/originals/${fileID}` };
+        });
+    }
+}
+
+// Resolve once a predicate holds, polling the microtask queue; fails fast
+// rather than hanging the suite.
+const until = async (predicate: () => boolean): Promise<void> => {
+    for (let i = 0; i < 1000; i++) {
+        if (predicate()) return;
+        await new Promise((r) => setTimeout(r, 1));
+    }
+    throw new Error("condition not met in time");
+};
+
+describe("Precache unit", () => {
+    it("precaches every thumbnail newest first, skipping present ones", async () => {
+        const cols = [collection(1)];
+        const files = [
+            file(1, 1, 0),
+            file(2, 1, 1),
+            file(3, 1, 2),
+            file(4, 1, 3),
+        ];
+        const cache = new FakeCache();
+        cache.presentThumbs.add(3); // already on disk: skipped
+        const pre = new Precache({ originals: false });
+        pre.bind(cache);
+        pre.update(records(cols, files));
+        pre.start();
+
+        await until(() => cache.thumbFetched.length === 3);
+        // Newest first (file 1 is newest), file 3 skipped by a lookup.
+        expect(cache.thumbFetched).toEqual([1, 2, 4]);
+        expect(cache.originalFetched).toEqual([]);
+    });
+
+    it("pins favorites then the latest-week window and precaches their originals in that order", async () => {
+        const cols = [collection(1), collection(2, "favorites")];
+        // File 10 is an old favorite (30 days old); files 1..3 are within the
+        // 7-day window; file 4 is outside it.
+        const files = [
+            file(1, 1, 0),
+            file(2, 1, 2),
+            file(3, 1, 6),
+            file(4, 1, 20),
+            file(10, 2, 30), // favorite, old
+        ];
+        const cache = new FakeCache();
+        const pre = new Precache({ originalsDays: 7 });
+        pre.bind(cache);
+        pre.update(records(cols, files));
+        pre.start();
+
+        await until(() => cache.originalFetched.length === 4);
+        // Favorite (10) first, then the window newest-first (1, 2, 3). File 4
+        // is outside the window and never pinned.
+        expect(cache.originalFetched).toEqual([10, 1, 2, 3]);
+        expect(pre.isPinned(10)).toBe(true);
+        expect(pre.isPinned(1)).toBe(true);
+        expect(pre.isPinned(4)).toBe(false);
+    });
+
+    it("drops a file from the pinned set when the window moves past it", () => {
+        const cols = [collection(1)];
+        const cache = new FakeCache();
+        const pre = new Precache({ originalsDays: 7 });
+        pre.bind(cache);
+
+        pre.update(records(cols, [file(1, 1, 0), file(2, 1, 3)]));
+        expect(pre.isPinned(2)).toBe(true);
+
+        // A newer file arrives; the window's newest end moves forward so the
+        // 3-day-old file 2 (now 13 days behind the newest) falls out.
+        pre.update(
+            records(cols, [file(3, 1, -10), file(1, 1, 0), file(2, 1, 3)]),
+        );
+        expect(pre.isPinned(3)).toBe(true);
+        expect(pre.isPinned(2)).toBe(false);
+    });
+
+    it("reports progress through status()", async () => {
+        const cols = [collection(1), collection(2, "favorites")];
+        const files = [file(1, 1, 0), file(2, 1, 1), file(10, 2, 0)];
+        const cache = new FakeCache();
+        const pre = new Precache({ originalsDays: 7 });
+        pre.bind(cache);
+        pre.update(records(cols, files));
+
+        const before = pre.status();
+        expect(before.thumbnailsTotal).toBe(3);
+        expect(before.thumbnailsCached).toBe(0);
+        expect(before.originalsPinned).toBe(3); // files 1, 2, 10 all in window
+        expect(before.originalsCached).toBe(0);
+
+        pre.start();
+        await until(
+            () =>
+                cache.thumbFetched.length === 3 &&
+                cache.originalFetched.length === 3,
+        );
+        const after = pre.status();
+        expect(after.thumbnailsCached).toBe(3);
+        expect(after.originalsCached).toBe(3);
+    });
+
+    it("honours the disable flags", async () => {
+        const cols = [collection(1)];
+        const files = [file(1, 1, 0)];
+        const cache = new FakeCache();
+        const pre = new Precache({ thumbnails: false, originals: false });
+        pre.bind(cache);
+        pre.update(records(cols, files));
+        pre.start();
+
+        await new Promise((r) => setTimeout(r, 20));
+        expect(cache.thumbFetched).toEqual([]);
+        expect(cache.originalFetched).toEqual([]);
+        expect(pre.isPinned(1)).toBe(false);
+        expect(pre.status().thumbnailsTotal).toBe(0);
+    });
+});
+
+// ---- Integration through the real ContentCache and Library ----
+
+const enteFile = (id: number, collectionID: number): EnteFile =>
+    file(id, collectionID, 0);
+
+describe("Precache eviction integration", () => {
+    let root: string;
+
+    beforeEach(() => {
+        root = mkdtempSync(join(tmpdir(), "quak-precache-evict-"));
+    });
+    afterEach(() => {
+        if (root && existsSync(root))
+            rmSync(root, { recursive: true, force: true });
+    });
+
+    it("never evicts a pinned original the precache put in place", async () => {
+        const cacheDir = join(root, "cache");
+        // File 1 is the favorites album's only file (pinned regardless of age);
+        // files 2 and 3 sit outside the latest-week window, so only file 1 is
+        // pinned. The by-id map serves the bytes for each fetch.
+        const cols = [collection(1), collection(2, "favorites")];
+        const files = [file(1, 2, 30), file(2, 1, 40), file(3, 1, 50)];
+        const byID = new Map<number, EnteFile>(files.map((f) => [f.id, f]));
+        const source: ContentSource = {
+            original: async ({ destination }) => {
+                await writeFile(destination, Buffer.alloc(10, 1));
+                return { bytesWritten: 10 };
+            },
+            thumbnail: async ({ destination }) => {
+                await writeFile(destination, Buffer.alloc(10, 1));
+                return { bytesWritten: 10 };
+            },
+        };
+        const statfs: StatFsFn = async () => ({
+            bsize: 1,
+            bavail: 1_000_000_000,
+        });
+        const pre = new Precache({ originalsDays: 7 });
+        const cache = new ContentCache({
+            pools: new RequestPools(),
+            source,
+            cacheDirectory: cacheDir,
+            getFile: (id) => byID.get(id),
+            statfs,
+            cacheOriginalsMaxBytes: 25, // holds two 10-byte originals
+            freeBelowBytes: 0,
+            isPinned: (id) => pre.isPinned(id),
+        });
+        pre.bind(cache);
+        pre.update(records(cols, files));
+        expect(pre.isPinned(1)).toBe(true);
+        expect(pre.isPinned(2)).toBe(false);
+        await cache.open();
+
+        // Fill three originals; the 25-byte cap forces an eviction on the
+        // third, and the pinned file 1 must survive it even though it is the
+        // least-recently-used.
+        await cache.original(1);
+        utimesSync(join(cacheDir, "originals", "1.jpg"), 1000, 1000); // oldest
+        await cache.original(2);
+        utimesSync(join(cacheDir, "originals", "2.jpg"), 2000, 2000);
+        await cache.original(3);
+
+        expect(existsSync(join(cacheDir, "originals", "1.jpg"))).toBe(true);
+        expect(existsSync(join(cacheDir, "originals", "2.jpg"))).toBe(false);
+        expect(existsSync(join(cacheDir, "originals", "3.jpg"))).toBe(true);
+    });
+});
+
+describe("Precache preemption", () => {
+    let root: string;
+
+    beforeEach(() => {
+        root = mkdtempSync(join(tmpdir(), "quak-precache-preempt-"));
+    });
+    afterEach(() => {
+        if (root && existsSync(root))
+            rmSync(root, { recursive: true, force: true });
+    });
+
+    it("lets an on-demand original preempt the background originals fill", async () => {
+        const byID = new Map<number, EnteFile>([
+            [1, enteFile(1, 1)],
+            [2, enteFile(2, 1)],
+            [3, enteFile(3, 1)],
+        ]);
+        const finished: number[] = [];
+        let openGate!: () => void;
+        const gate = new Promise<void>((r) => (openGate = r));
+        let sawFirst!: () => void;
+        const firstStarted = new Promise<void>((r) => (sawFirst = r));
+        let started = 0;
+        const source: ContentSource = {
+            original: async ({ file: f, destination }) => {
+                if (++started === 1) sawFirst();
+                await gate;
+                await writeFile(destination, Buffer.alloc(10, 1));
+                finished.push(f.id);
+                return { bytesWritten: 10 };
+            },
+            thumbnail: async ({ destination }) => {
+                await writeFile(destination, Buffer.alloc(10, 1));
+                return { bytesWritten: 10 };
+            },
+        };
+        // One content slot, so file 1 holds it while 2 and 3 wait.
+        const cache = new ContentCache({
+            pools: new RequestPools({ contentConcurrency: 1 }),
+            source,
+            cacheDirectory: join(root, "cache"),
+            getFile: (id) => byID.get(id),
+            statfs: async () => ({ bsize: 1, bavail: 1_000_000_000 }),
+            freeBelowBytes: 0,
+        });
+        await cache.open();
+
+        const pA = cache.ensureOriginals({ fileIDs: [1] }); // background
+        await firstStarted; // file 1 now holds the only slot
+        const pB = cache.original(2); // on-demand, queued behind file 1
+        const pC = cache.ensureOriginals({ fileIDs: [3] }); // background, queued
+        await new Promise((r) => setTimeout(r, 5)); // let both enqueue
+        openGate();
+        await Promise.all([pA, pB, pC]);
+
+        // On-demand file 2 was served before the background file 3.
+        expect(finished).toEqual([1, 2, 3]);
+    });
+});
+
+describe("Precache through Library.open", () => {
+    let root: string;
+
+    beforeEach(() => {
+        root = mkdtempSync(join(tmpdir(), "quak-precache-lib-"));
+    });
+    afterEach(() => {
+        if (root && existsSync(root))
+            rmSync(root, { recursive: true, force: true });
+    });
+
+    class MockClient {
+        served = false;
+        whoami(): { email: string; userID: number } {
+            return { email: "u@example.com", userID: 7 };
+        }
+        async collectionsSince(): Promise<CollectionsPage> {
+            if (this.served) return { collections: [], deleted: [], cursor: 1 };
+            this.served = true;
+            return {
+                collections: [collection(1), collection(2, "favorites")],
+                deleted: [],
+                cursor: 1,
+            };
+        }
+        async filesSince(args: { collectionID: number }): Promise<FilesPage> {
+            const files =
+                args.collectionID === 1
+                    ? [enteFile(1, 1), enteFile(2, 1)]
+                    : [enteFile(3, 2)];
+            return { files, deleted: [], cursor: 1 };
+        }
+    }
+
+    it("starts both precaches from open() and reports them in status()", async () => {
+        const thumbFetched = new Set<number>();
+        const origFetched = new Set<number>();
+        const source: ContentSource = {
+            original: async ({ file: f, destination }) => {
+                origFetched.add(f.id);
+                await writeFile(destination, Buffer.alloc(10, 1));
+                return { bytesWritten: 10 };
+            },
+            thumbnail: async ({ file: f, destination }) => {
+                thumbFetched.add(f.id);
+                await writeFile(destination, Buffer.alloc(10, 1));
+                return { bytesWritten: 10 };
+            },
+        };
+        const lib = await Library.open({
+            client: new MockClient(),
+            cacheDirectory: join(root, "cache"),
+            contentSource: source,
+            refreshIntervalSeconds: 3600,
+        });
+
+        // Every file's thumbnail is precached; the favorite (file 3) and the
+        // week's files (1, 2) all have their originals precached.
+        await until(() => thumbFetched.size === 3 && origFetched.size === 3);
+        const status = lib.status();
+        expect(status.thumbnailsTotal).toBe(3);
+        expect(status.thumbnailsCached).toBe(3);
+        expect(status.originalsPinned).toBe(3);
+        expect(status.originalsCached).toBe(3);
+        lib.close();
+    });
+});