ML data that does not decrypt is recorded with its reason (closes #198)
check / check (push) Waiting to run

`fetchMLDataBatch` dropped an entry that did not decrypt, gunzip or parse,
so the file looked like one with no ML data and the run exited 0. It now
returns the reason beside the payloads, also for ML data that is not a
JSON object. The library gives the reasons from its last ML data fetch
that succeeded in `status().mlDataErrors` and the `fetchMLData` "done"
event; a fetch that fails leaves them as they were. `quak backup` writes
the reason as `mlDataError` and records the file in `failures.json`;
`backup-metadata` writes `mlDataError` and exits 1.

Judgement call: a file whose ML data is cached keeps it in its JSON when a
newer copy does not decode, as when the fetch fails.

Model: opus-5-5
This commit was merged in pull request #208.
This commit is contained in:
2026-10-16 07:23:16 +02:00
parent 8583863ec0
commit 7ec71bf7ec
13 changed files with 558 additions and 87 deletions
+51 -6
View File
@@ -489,15 +489,15 @@ describe("quak backup-metadata", () => {
});
});
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) => {
describe("quak backup-metadata when a file's ML data cannot be read", () => {
// Run the CLI command against `fetch`, the mock unless given, and return
// its exit code, stderr and output directory.
const runCommand = async (fetch = buildMetaFetch(mock)) => {
const client = await Client.login({
email: TEST_EMAIL,
password: TEST_PASSWORD,
apiOptions: {
fetch: buildMetaFetch(mock, failMLDataFor),
fetch,
retry: { sleep: async () => {} },
},
});
@@ -518,7 +518,9 @@ describe("quak backup-metadata when an ML data request fails", () => {
};
it("writes every file, marks the failed batch's files, and exits 1", async () => {
const { code, stderr, outDir } = await runCommand(200);
const { code, stderr, outDir } = await runCommand(
buildMetaFetch(mock, 200),
);
expect(code).toBe(1);
expect(stderr).toContain("ML data request for 1 file(s) failed");
@@ -543,6 +545,49 @@ describe("quak backup-metadata when an ML data request fails", () => {
expect(failed.mlDataError).toContain("500");
});
// The server sends ML data for diagram.png encrypted under a key that is
// not the file's, so quak cannot decrypt it.
it("writes the reason for ML data that does not decrypt, and exits 1", async () => {
const otherKey = sodium.crypto_secretstream_xchacha20poly1305_keygen();
const { header, ciphertext } = encryptBlob(
new Uint8Array(gzipSync(Buffer.from("{}"))),
otherKey,
);
const { code, stderr, outDir } = await runCommand(
buildMetaFetch({
...mock,
encryptedMLData: {
...mock.encryptedMLData,
200: {
encryptedData: toBase64(ciphertext),
decryptionHeader: toBase64(header),
},
},
}),
);
expect(code).toBe(1);
const reason = "secretstream chunk authentication failed";
expect(stderr).toContain(
`ML data of file 200 could not be read: ${reason}\n`,
);
const failed = JSON.parse(
readFileSync(
join(outDir, "collections", "20-__Work", "200.json"),
"utf-8",
),
);
expect(failed.mlData).toBeUndefined();
expect(failed.mlDataError).toBe(reason);
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]);
});
it("exits 0 when every ML data request succeeds", async () => {
const { code } = await runCommand();
expect(code).toBe(0);