Check downloaded originals against their recorded content hash (closes #68)

downloadFile, shared by quak get, the content cache and backup, hashes
the decrypted bytes (unkeyed BLAKE2b-512, standard base64) and stores
nothing on a mismatch, failing with an error naming the file ID. A live
photo ZIP is unpacked as it streams with fflate's Unzip, in small
slices so memory stays bounded however far an entry expands, and its
image and video hashed separately as <imageHash>:<videoHash>.
decryptFile reads the older imageHash/videoHash fields for live
photos. A file with no recorded hash is stored unchecked.

Model: opus-5-5

README.md

@@ -681,11 +681,6 @@ Under `cacheDirectory`:
         fetched.json              per-file fetch bookkeeping
 ```
 
-When `metadata.json` belongs to a different account than the client's,
-`Library.open` deletes it and `mldata/` and starts from an empty cache. Cached
-originals and thumbnails are kept; they are reached only through the files the
-current account's records name.
-
 A stored file appears only via an atomic temp-then-rename, so its presence means
 it is complete. Every downloaded original (by `quak get`, the cache, or
 `backup`) whose metadata records a content hash (`FileMetadata.hash`) is hashed

TODO.md

@@ -26,17 +26,12 @@ Tag v1.0.0.
   hashed separately as `<imageHash>:<videoHash>`. `decryptFile` reads older
   clients' `imageHash` and `videoHash` fields for live photos. A file with no
   recorded hash is stored unchecked.
-- 2026-09-23: Kept one account's cache from mixing with another's (issue 104).
-  When `metadata.json` in the cache directory was written for a different,
-  non-zero user ID than the client's, `Library.open` deletes it and `mldata/`
-  and starts empty, so the first refresh enumerates from 0. This only happens
-  with `--cache-dir` or an explicit `cacheDirectory`; the default path already
-  includes the user ID. A test opens one account's cache as another account.
 - 2026-09-23: `backup-metadata` no longer stops on one failed ML data request
   (issue 101). Each request of up to 200 files is tried on its own; a failed one
   is logged, its files are written with the reason in `mlDataError`, and the
   command exits 1 once the dump is complete. `fetchMLData`, which only this
   command used, is gone; the command calls `fetchMLDataBatch` per batch.
+
 - 2026-09-23: Single-sourced the version string (issue 5). `package.json` is the
   only place it is written: `src/index.ts` imports it for `VERSION` and
   `bin/quak.ts` passes `VERSION` to commander. tsc copies `package.json` to

src/library/index.ts

@@ -26,7 +26,6 @@
 // store marked unsaved until a later save actually lands, so a stuck disk is
 // never masked by a subsequent empty refresh.
 
-import { rm } from "node:fs/promises";
 import { join } from "node:path";
 import envPaths from "env-paths";
 
@@ -346,20 +345,9 @@ export class Library {
         const cacheDirectory =
             opts.cacheDirectory ??
             join(envPaths("quak", { suffix: "" }).cache, String(userID));
-        const metadataPath = join(cacheDirectory, "metadata.json");
+        const store = await MetadataStore.load(
-        let store = await MetadataStore.load(metadataPath);
+            join(cacheDirectory, "metadata.json"),
-        // A cache directory given explicitly can hold another account's cache.
+        );
-        // Its records and cursor are not this account's, so delete it and the
-        // ML data beside it and start empty. A user ID of 0 means the cache
-        // was never refreshed and so holds nothing to discard.
-        if (store.userID !== 0 && store.userID !== userID) {
-            await rm(metadataPath, { force: true });
-            await rm(join(cacheDirectory, "mldata"), {
-                recursive: true,
-                force: true,
-            });
-            store = await MetadataStore.load(metadataPath);
-        }
         const intervalMs =
             (opts.refreshIntervalSeconds ?? DEFAULT_REFRESH_INTERVAL_SECONDS) *
             1000;

test/library/mldata.test.ts

@@ -13,8 +13,6 @@
  *   2. `Library` wiring: after each refresh the library fetches ML data through
  *      the metadata pool for every known file not yet cached, is incremental on
  *      later refreshes, and refetches a file whose `updationTime` advanced.
- *      Opening a cache directory written by another account starts empty,
- *      its ML data included (issue #104).
  *
  * Embedding values are chosen to be exactly representable as float32 so the
  * round-trip through `clip.f32` compares equal.
@@ -500,63 +498,4 @@ describe("Library ML-data fetch on refresh", () => {
             await lib.close();
         }
     });
-
-    it("starts empty when the cache directory holds another account's cache", async () => {
-        // Account A fills the cache directory: metadata and ML data.
-        const clientA = new MLMockClient();
-        clientA.collectionsQueue.push({
-            collections: [collection(1, 100)],
-            deleted: [],
-            cursor: 100,
-        });
-        clientA.filesFor(1, {
-            files: [file(1001, 1, 90)],
-            deleted: [],
-            cursor: 90,
-        });
-        clientA.mlByFile.set(1001, payload([0.5, 0.25, 0.75]));
-        const libA = await Library.open({
-            client: clientA,
-            cacheDirectory,
-            refreshIntervalSeconds: 3600,
-        });
-        try {
-            await vi.waitFor(
-                () => expect(libA.status().lastMLFetchAt).toBeGreaterThan(0),
-                { timeout: 2000, interval: 5 },
-            );
-        } finally {
-            await libA.close();
-        }
-
-        // Account B opens the same directory.
-        const clientB = new MLMockClient();
-        clientB.userID = USER_ID + 1;
-        const sinceTimes: number[] = [];
-        const realCollectionsSince = clientB.collectionsSince.bind(clientB);
-        clientB.collectionsSince = async (args) => {
-            sinceTimes.push(args.sinceTime);
-            return realCollectionsSince(args);
-        };
-        const libB = await Library.open({
-            client: clientB,
-            cacheDirectory,
-            refreshIntervalSeconds: 3600,
-        });
-        try {
-            expect(sinceTimes[0]).toBe(0);
-            expect(libB.status().userID).toBe(USER_ID + 1);
-            expect(libB.listCollections()).toEqual([]);
-            expect(libB.getFile(1, 1001)).toBeUndefined();
-            expect(await libB.mldata.forFile({ fileID: 1001 })).toBeUndefined();
-            expect(
-                libB.mldata.searchByEmbedding({ embedding: [0.5, 0.25, 0.75] }),
-            ).toEqual([]);
-            expect(
-                existsSync(join(cacheDirectory, "mldata", "1001.json")),
-            ).toBe(false);
-        } finally {
-            await libB.close();
-        }
-    });
 });