A network failure is printed and recorded with its reason (closes #196)

Node's `fetch` rejects every failure below HTTP as `fetch failed` and puts
the reason on `cause`. `describeError` in `src/errors.ts` gives the message
followed by the messages on the cause chain, and for an `AggregateError`,
which Node gives when every address of a host fails, the message of each
address. `run` prints it, and the backup logs and records it. `classify`
reads that text and calls a failure transient when `hasTransportCode`, now
exported by `src/retry.ts`, finds a transport errno on the chain. A failed
ML data fetch keeps its error as the cause. The bounded walk along the
chain moved from `src/retry.ts` to `src/errors.ts`.

A truncated download's message leaves the authentication failure to its
cause.

Model: opus-5-5

test/cli/backup-end-to-end.test.ts

@@ -329,6 +329,41 @@ const downloadOf = (input: RequestInfo | URL): number | undefined => {
         : undefined;
 };
 
+// The error Node gives for a connection to `address` that was refused.
+const refusedAt = (address: string): Error =>
+    Object.assign(new Error(`connect ECONNREFUSED ${address}`), {
+        code: "ECONNREFUSED",
+    });
+
+// What Node's `fetch` rejects with when the server refuses the connection, as
+// for every failure below HTTP: a TypeError that says only "fetch failed",
+// with the reason, and its errno, as its cause. When the server has several
+// addresses and each one refuses, the cause is an AggregateError with an empty
+// message, one error per address and the errno of the first. `reason` is the
+// error as quak prints it and records it in `failures.json`.
+const REFUSED = [
+    {
+        addresses: "its one address",
+        error: (): TypeError =>
+            new TypeError("fetch failed", { cause: refusedAt("1.2.3.4:443") }),
+        reason: "fetch failed: connect ECONNREFUSED 1.2.3.4:443",
+    },
+    {
+        addresses: "each of its two addresses",
+        error: (): TypeError =>
+            new TypeError("fetch failed", {
+                cause: Object.assign(
+                    new AggregateError([
+                        refusedAt("2001:db8::1:443"),
+                        refusedAt("1.2.3.4:443"),
+                    ]),
+                    { code: "ECONNREFUSED" },
+                ),
+            }),
+        reason: "fetch failed: connect ECONNREFUSED 2001:db8::1:443, connect ECONNREFUSED 1.2.3.4:443",
+    },
+];
+
 // The fake server, pushing onto `downloads` the ID of each file whose original
 // is downloaded.
 const recordingDownloads =
@@ -619,6 +654,115 @@ describe("quak backup", () => {
         expect(readdirSync(dir)).toEqual([]);
     });
 
+    // The server refuses every connection, at its one address or at each of
+    // several. quak tries each request again, here without waiting, and then
+    // the run stops at the refresh it starts with. The line it prints gives
+    // the reason Node's `fetch` put on the error's cause, so a cron log tells
+    // a refused connection from a name that did not resolve, and the exit
+    // code is 1.
+    it.each(REFUSED)(
+        "prints why the refresh could not reach the server at $addresses, and exits 1",
+        async ({ error, reason }) => {
+            const dir = mkdtempSync(join(root, "backup-"));
+            const fetch: typeof globalThis.fetch = async () => {
+                throw error();
+            };
+
+            const { code, stderr } = await backup(dir, {}, fetch);
+
+            expect(code).toBe(1);
+            expect(stderr).toBe(
+                "Starting backup...\n" +
+                    "Refreshing library...\n" +
+                    `quak: ${reason}\n`,
+            );
+        },
+    );
+
+    // The files CDN refuses every connection for toast.mp4, at its one
+    // address or at each of several. Once its retries are spent, the file
+    // goes into `failures.json` with the reason, as a transient failure,
+    // since a later run may well reach the CDN, and the lines the backup
+    // prints for it give the same reason. The rest of the account is backed
+    // up, and the exit code is 1.
+    it.each(REFUSED)(
+        "records why a download could not reach the server at $addresses in failures.json, as transient, and exits 1",
+        async ({ error, reason }) => {
+            let attempts = 0;
+            const fetch: typeof globalThis.fetch = async (input, init) => {
+                if (downloadOf(input) === 200) {
+                    attempts++;
+                    throw error();
+                }
+                return server(input, init);
+            };
+            const dir = mkdtempSync(join(root, "backup-"));
+
+            const { code, stderr } = await backup(dir, {}, fetch);
+
+            expect(code).toBe(1);
+            expect(attempts).toBe(UNATTENDED_RETRY_OPTIONS.attempts);
+            const failures = readJSON(join(dir, "failures.json"));
+            expect(Object.keys(failures.files)).toEqual(["200"]);
+            expect(failures.files["200"]).toMatchObject({
+                fileID: 200,
+                title: "toast.mp4",
+                classification: "transient",
+                attempts: 1,
+                error: reason,
+            });
+            expect(stderr).toContain(`FAILED original toast.mp4: ${reason}\n`);
+            expect(stderr).toContain(
+                `[Friend's Wedding] toast.mp4 (id 200): ${reason}\n`,
+            );
+            expect(readFileSync(join(dir, DAY, "2024-03-01.100.jpg"))).toEqual(
+                Buffer.from(JPEG_WITH_EXIF),
+            );
+            expect(existsSync(join(dir, DAY, "2024-03-01.200.mp4"))).toBe(
+                false,
+            );
+        },
+    );
+
+    // The name of Ente's API server does not resolve when quak fetches the ML
+    // data, after every original has been backed up. No file has ML data
+    // cached yet, so each goes into `failures.json` with the reason, as a
+    // transient failure, as a download that could not reach the server does,
+    // and the exit code is 1.
+    it("records why the ML data fetch could not reach the server in failures.json, as transient, and exits 1", async () => {
+        const fetch: typeof globalThis.fetch = async (input, init) => {
+            if (new URL(String(input)).pathname === "/files/data/fetch") {
+                throw new TypeError("fetch failed", {
+                    cause: Object.assign(
+                        new Error("getaddrinfo ENOTFOUND api.ente.io"),
+                        { code: "ENOTFOUND" },
+                    ),
+                });
+            }
+            return server(input, init);
+        };
+        const dir = mkdtempSync(join(root, "backup-"));
+
+        const { code, stderr } = await backup(dir, {}, fetch);
+
+        expect(code).toBe(1);
+        const error =
+            "ML data: fetch failed: getaddrinfo ENOTFOUND api.ente.io";
+        expect(stderr).toContain(`FAILED ${error}\n`);
+        const failures = readJSON(join(dir, "failures.json"));
+        expect(
+            Object.values(failures.files).map((f) => [
+                f.fileID,
+                f.classification,
+                f.error,
+            ]),
+        ).toEqual([
+            [100, "transient", error],
+            [200, "transient", error],
+            [300, "transient", error],
+        ]);
+    });
+
     // Something changed beach.jpg on disk after it was backed up. A run with
     // --verify hashes every stored original, finds that one no longer matches
     // the hash Ente recorded, says so, and downloads it again; it put back the

test/cli/run.test.ts

@@ -48,6 +48,78 @@ describe("run", () => {
         );
     });
 
+    // Node's `fetch` rejects every failure below HTTP with a TypeError that
+    // says only "fetch failed", and hangs the reason, with its errno, off
+    // `cause`. The printed line carries the reason, so a cron log tells a
+    // refused connection from a name that did not resolve.
+    it("prints the reason a fetch failed, from the error's cause", async () => {
+        const refused = new TypeError("fetch failed", {
+            cause: Object.assign(
+                new Error("connect ECONNREFUSED 1.2.3.4:443"),
+                { code: "ECONNREFUSED" },
+            ),
+        });
+        const result = await runToExit(Promise.reject(refused));
+        expect(result).toEqual({
+            code: 1,
+            stdout: "",
+            stderr: "quak: fetch failed: connect ECONNREFUSED 1.2.3.4:443\n",
+        });
+    });
+
+    // When the host has several addresses and every one refuses, Node's
+    // `fetch` gives as the cause an AggregateError with an empty message and
+    // one error per address. The printed line gives each address's reason.
+    it("prints the reason for each address a fetch could not reach", async () => {
+        const refusedAt = (address: string): Error =>
+            Object.assign(new Error(`connect ECONNREFUSED ${address}`), {
+                code: "ECONNREFUSED",
+            });
+        const refused = new TypeError("fetch failed", {
+            cause: Object.assign(
+                new AggregateError([
+                    refusedAt("2001:db8::1:443"),
+                    refusedAt("1.2.3.4:443"),
+                ]),
+                { code: "ECONNREFUSED" },
+            ),
+        });
+        const result = await runToExit(Promise.reject(refused));
+        expect(result).toEqual({
+            code: 1,
+            stdout: "",
+            stderr: "quak: fetch failed: connect ECONNREFUSED 2001:db8::1:443, connect ECONNREFUSED 1.2.3.4:443\n",
+        });
+    });
+
+    // An error that already quotes its cause's message is printed as it is.
+    it("does not print a cause's message twice", async () => {
+        const reset = new Error("read ECONNRESET");
+        const wrapped = new Error(`download: file 7: ${reset.message}`, {
+            cause: reset,
+        });
+        const result = await runToExit(Promise.reject(wrapped));
+        expect(result.stderr).toBe("quak: download: file 7: read ECONNRESET\n");
+    });
+
+    // OpenSSL ends its message for a failed TLS connection, such as one to a
+    // server that answers in plain HTTP, with a newline. The printed line is
+    // still one line.
+    it("prints a cause's message without the white space around it", async () => {
+        const wrongVersion = new TypeError("fetch failed", {
+            cause: Object.assign(
+                new Error(
+                    "C0B73A55A47F0000:error:0A00010B:SSL routines:ssl3_get_record:wrong version number:../deps/openssl/openssl/ssl/record/ssl3_record.c:354:\n",
+                ),
+                { code: "ERR_SSL_WRONG_VERSION_NUMBER" },
+            ),
+        });
+        const result = await runToExit(Promise.reject(wrongVersion));
+        expect(result.stderr).toBe(
+            "quak: fetch failed: C0B73A55A47F0000:error:0A00010B:SSL routines:ssl3_get_record:wrong version number:../deps/openssl/openssl/ssl/record/ssl3_record.c:354:\n",
+        );
+    });
+
     it("prints a thrown value that is not an Error", async () => {
         const result = await runToExit(Promise.reject("offline"));
         expect(result).toEqual({
@@ -57,6 +129,14 @@ describe("run", () => {
         });
     });
 
+    // A cause that is not an Error, such as a thrown string, is printed as a
+    // thrown value that is not an Error is.
+    it("prints a cause that is not an Error", async () => {
+        const wrapped = new Error("ML data", { cause: "offline" });
+        const result = await runToExit(Promise.reject(wrapped));
+        expect(result.stderr).toBe("quak: ML data: offline\n");
+    });
+
     it("on a 401 from the server says to run quak login, on one line, and exits 3", async () => {
         const result = await runToExit(
             Promise.reject(new ApiError("unauthorized", 401)),

test/download/download.test.ts

@@ -74,7 +74,11 @@ import {
 } from "vitest";
 import { init, toBase64, STREAM_CHUNK_SIZE } from "../../src/crypto/index.js";
 import { ApiClient } from "../../src/api/client.js";
-import { ApiError, TruncatedStreamError } from "../../src/errors.js";
+import {
+    ApiError,
+    describeError,
+    TruncatedStreamError,
+} from "../../src/errors.js";
 import type { RetryOptions } from "../../src/retry.js";
 import {
     downloadFile,
@@ -834,6 +838,11 @@ describe.each(entryPoints)(
             expect(((err as Error).cause as Error).message).toMatch(
                 /authentication failed/i,
             );
+            // As quak prints it and records it in `failures.json`, the error
+            // states the authentication failure once, from its cause.
+            expect(describeError(err)).toMatch(
+                /^download: stream truncated: response body ended with \d+ trailing bytes \(transfer stopped mid-chunk, or the data is corrupt\): secretstream chunk authentication failed$/,
+            );
 
             // And, as with every other failure, the destination is untouched
             // and no staged temp file survives.