backup-metadata: keep going when an ML data request fails (closes #101)

Each ML data request of up to 200 files is now tried on its own. A request
that still fails after its retries is logged, its files are written with the
reason in `mlDataError`, and the command exits 1 once the dump is complete.
`fetchMLData`, used only here, is removed in favour of a per-batch loop over
`fetchMLDataBatch`.

Model: opus-5-5

README.md

@@ -471,6 +471,11 @@ accepted for backward compatibility but ignored. `backup-metadata --exif` (alias
 metadata. The listing and backup commands support `--json` for machine-readable
 output.
 
+`backup-metadata` fetches ML data in requests of up to 200 files. When a request
+still fails after its retries, the error is logged, each of its files is written
+with the reason in an `mlDataError` field instead of `mlData`, and the dump goes
+on. The exit code is non-zero if any ML data request failed.
+
 `helper fix-missing-thumbnails` regenerates thumbnails for baseline JPEG images
 only, because the bundled decoder (`jpeg-js`) decodes only JPEG. A non-JPEG
 image (PNG, HEIC) or a video is reported as `skipped` (unsupported format), kept

TODO.md

@@ -18,6 +18,12 @@ Tag v1.0.0.
 
 # Completed Steps
 
+- 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/cli-commands.ts

@@ -323,11 +323,11 @@ export const backupMetadataCommand = async (
     if (!client) return 1;
     const lib = await openReadLibrary(ctx, client);
     try {
-        await runMetadataBackup(lib, client, dir, {
+        const { failedMLBatches } = await runMetadataBackup(lib, client, dir, {
             exif: opts.exif || opts.all,
             onProgress: (msg) => ctx.stderr.write(msg + "\n"),
         });
-        return 0;
+        return failedMLBatches > 0 ? 1 : 0;
     } finally {
         await lib.close();
     }

src/metadata-backup.ts

@@ -5,7 +5,11 @@ import exifReader from "exif-reader";
 import type { Client } from "./client.js";
 import type { Library, Photo } from "./library/index.js";
 import { sanitizeFileName } from "./filename.js";
-import { fetchMLData } from "./mldata-fetch.js";
+import {
+    fetchMLDataBatch,
+    MLDATA_BATCH_SIZE,
+    type MLData,
+} from "./mldata-fetch.js";
 import type { EnteFile } from "./model/types.js";
 
 export type ProgressCallback = (message: string) => void;
@@ -137,13 +141,14 @@ const extractExif = async (
 // of plain JSON: account, per-collection, and per-file records including the
 // private and public magic metadata and (by default) the ML data. Collections
 // and files are enumerated from the library's cache rather than a fresh server
-// scan; the ML fetch and EXIF extraction are unchanged.
+// scan. Returns how many ML data requests failed; their files are still
+// written, with `mlDataError` in place of `mlData`.
 export const runMetadataBackup = async (
     lib: Library,
     client: Client,
     outDir: string,
     opts?: MetadataBackupOptions,
-): Promise<void> => {
+): Promise<{ failedMLBatches: number }> => {
     const log = opts?.onProgress ?? (() => {});
     const wantExif = opts?.exif ?? false;
 
@@ -208,12 +213,31 @@ export const runMetadataBackup = async (
         }
     }
 
+    // One failed request (retries exhausted) must not end the dump: its files
+    // get the reason in `mlDataError` and the other batches go on.
     log("Fetching ML data (face detections, CLIP embeddings)...");
-    const mlDataMap = await fetchMLData(
+    const mlDataMap = new Map<number, MLData>();
+    const mlDataErrors = new Map<number, string>();
+    let failedMLBatches = 0;
+    const fileIDs = [...fileKeys.keys()];
+    for (let i = 0; i < fileIDs.length; i += MLDATA_BATCH_SIZE) {
+        const batch = fileIDs.slice(i, i + MLDATA_BATCH_SIZE);
+        try {
+            const result = await fetchMLDataBatch(
                 client.getApiClient(),
-        [...fileKeys.keys()],
+                batch,
                 fileKeys,
             );
+            for (const [id, payload] of result) mlDataMap.set(id, payload);
+        } catch (err) {
+            const reason = err instanceof Error ? err.message : String(err);
+            failedMLBatches++;
+            log(
+                `ML data request for ${batch.length} file(s) failed: ${reason}`,
+            );
+            for (const id of batch) mlDataErrors.set(id, reason);
+        }
+    }
     log(`Got ML data for ${mlDataMap.size} file(s)`);
 
     const writtenFileIDs = new Set<number>();
@@ -233,6 +257,8 @@ export const runMetadataBackup = async (
 
         const ml = mlDataMap.get(file.id);
         if (ml) fileMeta.mlData = ml;
+        const mlError = mlDataErrors.get(file.id);
+        if (mlError) fileMeta.mlDataError = mlError;
 
         if (wantExif && !writtenFileIDs.has(file.id)) {
             log(`[${file.metadata.title}] Extracting EXIF...`);
@@ -253,4 +279,5 @@ export const runMetadataBackup = async (
     }
 
     log("Metadata backup complete.");
+    return { failedMLBatches };
 };

src/mldata-fetch.ts

@@ -5,9 +5,8 @@
 // comes back encrypted under the file's own key and gzipped; decrypting and
 // gunzipping yields the JSON payload
 // `{ face: { faces: [...] }, clip: { embedding } }`. Ente caps a request at 200
-// ids, so `fetchMLData` batches for callers that want many at once while
-// `fetchMLDataBatch` is the single-request unit the library submits to its
-// request pool.
+// ids, so callers that want many at once split them into batches of
+// `MLDATA_BATCH_SIZE` and call `fetchMLDataBatch` once per batch.
 
 import { gunzipSync } from "node:zlib";
 
@@ -69,25 +68,3 @@ export const fetchMLDataBatch = async (
     }
     return result;
 };
-
-// Fetch ML data for arbitrarily many ids, batching at `MLDATA_BATCH_SIZE`. Used
-// by the one-shot metadata backup; the library fetches through its request pool
-// with `fetchMLDataBatch` instead.
-export const fetchMLData = async (
-    api: ApiClient,
-    fileIDs: number[],
-    fileKeys: Map<number, Uint8Array>,
-): Promise<Map<number, MLData>> => {
-    const result = new Map<number, MLData>();
-    for (let i = 0; i < fileIDs.length; i += MLDATA_BATCH_SIZE) {
-        const batch = fileIDs.slice(i, i + MLDATA_BATCH_SIZE);
-        for (const [id, payload] of await fetchMLDataBatch(
-            api,
-            batch,
-            fileKeys,
-        )) {
-            result.set(id, payload);
-        }
-    }
-    return result;
-};

test/cli/metadata-backup.test.ts

@@ -38,7 +38,7 @@ import { join } from "node:path";
 import { tmpdir } from "node:os";
 import sodium from "libsodium-wrappers-sumo";
 import { SRP, SrpServer } from "fast-srp-hap";
-import { beforeAll, afterAll, describe, expect, it } from "vitest";
+import { beforeAll, afterAll, describe, expect, it, vi } from "vitest";
 import {
     init,
     toBase64,
@@ -53,8 +53,16 @@ import {
     runMetadataBackup,
     type MetadataBackupOptions,
 } from "../../src/metadata-backup.js";
+import { backupMetadataCommand } from "../../src/cli-commands.js";
 import type { KeyAttributes } from "../../src/auth/types.js";
 
+// One file per ML data request, so the two files of the mock account are
+// 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,
+}));
+
 const TEST_EMAIL = "metabackup@example.com";
 const TEST_PASSWORD = "metapass";
 const TEST_OPS = 2;
@@ -347,7 +355,8 @@ const buildMetaMock = async (): Promise<MetaMockState> => {
     };
 };
 
-const buildMetaFetch = (m: MetaMockState) => {
+// `failMLDataFor`: answer 500 to every ML data request that asks for this file.
+const buildMetaFetch = (m: MetaMockState, failMLDataFor?: number) => {
     let srpServer: SrpServer;
     return (async (
         input: RequestInfo | URL,
@@ -403,6 +412,8 @@ const buildMetaFetch = (m: MetaMockState) => {
         }
         if (path === "/files/data/fetch") {
             const body = JSON.parse(init?.body as string);
+            if ((body.fileIDs as number[]).includes(failMLDataFor!))
+                return new Response("server error", { status: 500 });
             const data = (body.fileIDs as number[])
                 .filter((id: number) => m.encryptedMLData[id])
                 .map((id: number) => ({
@@ -636,3 +647,63 @@ describe("quak backup-metadata", () => {
         expect(failedMeta.imageMetadataError).toEqual(expect.any(String));
     });
 });
+
+describe("quak backup-metadata when an ML data request fails", () => {
+    // Run the CLI command against the mock and return its exit code, stderr
+    // and output directory.
+    const runCommand = async (failMLDataFor?: number) => {
+        const client = await Client.login({
+            email: TEST_EMAIL,
+            password: TEST_PASSWORD,
+            apiOptions: {
+                fetch: buildMetaFetch(mock, failMLDataFor),
+                retry: { sleep: async () => {} },
+            },
+        });
+        const outDir = mkdtempSync(join(testDir, "ml-fail-"));
+        let stderr = "";
+        const code = await backupMetadataCommand(
+            {
+                stdout: { write: () => true },
+                stderr: { write: (text: string) => (stderr += text) },
+                sessionDir: testDir,
+                cacheDir: mkdtempSync(join(testDir, "cache-")),
+                loadSession: () => client,
+            },
+            outDir,
+            {},
+        );
+        return { code, stderr, outDir };
+    };
+
+    it("writes every file, marks the failed batch's files, and exits 1", async () => {
+        const { code, stderr, outDir } = await runCommand(200);
+
+        expect(code).toBe(1);
+        expect(stderr).toContain("ML data request for 1 file(s) failed");
+
+        const ok = JSON.parse(
+            readFileSync(
+                join(outDir, "collections", "10-Vacation", "100.json"),
+                "utf-8",
+            ),
+        );
+        expect(ok.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
+        expect(ok.mlDataError).toBeUndefined();
+
+        const failed = JSON.parse(
+            readFileSync(
+                join(outDir, "collections", "20-__Work", "200.json"),
+                "utf-8",
+            ),
+        );
+        expect(failed.metadata.title).toBe("diagram.png");
+        expect(failed.mlData).toBeUndefined();
+        expect(failed.mlDataError).toContain("500");
+    });
+
+    it("exits 0 when every ML data request succeeds", async () => {
+        const { code } = await runCommand();
+        expect(code).toBe(0);
+    });
+});