merge: e2e page loads retried on a machine out of buffers (improvement/e2e-goto-retry)

net::ERR_NO_BUFFER_SPACE stopped a release at its first page with nothing else running, and the
unchanged rerun passed. Every page load of the suite now goes through one helper, held by a test.

frontend/e2e/README.md

@@ -24,6 +24,10 @@ outlives an `expect` timeout); Node does not, so a request from the test side fa
 that one error again and passes every other failure straight on. Don't run two e2e suites on the
 same machine at once.
 
+**A page load the machine had no buffer for** — on the same host a page load can fail at once with
+`net::ERR_NO_BUFFER_SPACE`. Every page load goes through `gotoRetrying` (same file), which tries that
+one error again; a test that calls `page.goto` itself fails `src/lib/e2eRetryConnect.test.ts`.
+
 **Browsers** — every flow runs in three projects: `chromium` (Desktop Chrome), `webkit` (Desktop
 Safari) and `ipad` (iPad gen 7 landscape: 1080×810, touch, mobile) — except `a11y`, `member` and
 `devices`, which run on chromium only (`CHROMIUM_ONLY`; why is in the `docs/gates.md` row). Install the engines once per

frontend/e2e/global.setup.ts

@@ -4,7 +4,7 @@ import { mkdirSync, readFileSync, writeFileSync } from "node:fs";
 import { dirname, resolve } from "node:path";
 import { fileURLToPath } from "node:url";
 import { MEMBER_STORAGE, SEED_FILE } from "./helpers";
-import { retryConnect } from "./retryConnect";
+import { gotoRetrying, retryConnect } from "./retryConnect";
 
 /**
  * One-time setup for the characterization net (the `setup` project the tests depend on):
@@ -52,7 +52,7 @@ async function signIn(page: Page, email: string, path: string): Promise<void> {
   // and player flows this net locks all open "/" expecting the feed; the opt-out is the one
   // Settings → Appearance → Startup writes. Both flags are the account's local state, held for the
   // account the browser records as their owner (`siftlode.owner`, see storage.ts claimLocalData).
-  await page.goto("/");
+  await gotoRetrying(page, "/");
   await page.evaluate((id: number) => {
     localStorage.setItem("siftlode.owner", String(id));
     localStorage.setItem("siftlode.lang", "en");

frontend/e2e/helpers.ts

@@ -1,5 +1,6 @@
 import { readFileSync } from "node:fs";
 import { expect, type Page } from "@playwright/test";
+import { gotoRetrying } from "./retryConnect";
 
 /** The plain member's saved session (global.setup.ts signs it in); `member.spec.ts` and
  *  `devices.spec.ts` run from it. */
@@ -16,7 +17,7 @@ export function seeded(key: string): string[] {
 
 /** Open the app and wait for the authenticated shell (the nav rail) to be ready. */
 export async function openApp(page: Page, path = "/"): Promise<void> {
-  await page.goto(path);
+  await gotoRetrying(page, path);
   await expect(page.getByTestId("nav-feed")).toBeVisible();
 }
 

frontend/e2e/retryConnect.ts

@@ -11,6 +11,19 @@ const METHODS = new Set(["get", "post", "put", "patch", "delete", "head", "fetch
 const NO_CONNECTION = /\bconnect ETIMEDOUT\b/;
 const WAITS_MS = [500, 1000, 2000, 4000, 8000];
 
+/** `attempt` again after each wait while it fails with `transient`; any other failure goes on. */
+async function tryAgain<R>(attempt: () => Promise<R>, transient: RegExp): Promise<R> {
+  for (let i = 0; ; i++) {
+    try {
+      return await attempt();
+    } catch (e) {
+      const wait = WAITS_MS[i];
+      if (wait === undefined || !transient.test(String((e as Error)?.message))) throw e;
+      await new Promise((r) => setTimeout(r, wait));
+    }
+  }
+}
+
 /** `ctx` with its request methods trying a connect that timed out again (see above). */
 export function retryConnect<T extends object>(ctx: T): T {
   return new Proxy(ctx, {
@@ -18,17 +31,19 @@ export function retryConnect<T extends object>(ctx: T): T {
       const v: unknown = Reflect.get(target, key, target);
       if (typeof v !== "function") return v;
       if (typeof key !== "string" || !METHODS.has(key)) return v.bind(target);
-      return async (...args: unknown[]) => {
+      return (...args: unknown[]) =>
-        for (let i = 0; ; i++) {
+        tryAgain(() => Promise.resolve(v.apply(target, args)), NO_CONNECTION);
-          try {
-            return await v.apply(target, args);
-          } catch (e) {
-            const wait = WAITS_MS[i];
-            if (wait === undefined || !NO_CONNECTION.test(String((e as Error)?.message))) throw e;
-            await new Promise((r) => setTimeout(r, wait));
-          }
-        }
-      };
     },
   });
 }
+
+// A page load has a failure of its own on the same machine: `net::ERR_NO_BUFFER_SPACE`, the socket
+// call refused for the moment. It stopped a release's e2e at its first page (0.116.3, with nothing
+// else running; 0.107.3 aborted on it too), and the unchanged rerun passed. A browser does not try
+// a main document again by itself, and the request never left, so this does. The suite's every page
+// load goes through here (`e2eRetryConnect.test.ts`).
+const NO_BUFFER = /\bERR_NO_BUFFER_SPACE\b/;
+
+export function gotoRetrying<R>(page: { goto(url: string): Promise<R> }, url: string): Promise<R> {
+  return tryAgain(() => page.goto(url), NO_BUFFER);
+}

frontend/e2e/speed.measure.ts

@@ -1,7 +1,7 @@
 import { test, type Page } from "@playwright/test";
 import { execFileSync } from "node:child_process";
 import { mkdirSync, writeFileSync } from "node:fs";
-import { retryConnect } from "./retryConnect";
+import { gotoRetrying, retryConnect } from "./retryConnect";
 
 /**
  * The speed baseline: numbers, not assertions — read by `scripts/audit_metrics.py --speed`, which
@@ -78,7 +78,7 @@ test("speed baseline", async ({ browser, page: page0 }) => {
   for (let i = 0; i < RUNS; i++) {
     const ctx = await browser.newContext();
     const page = await ctx.newPage();
-    await page.goto("/");
+    await gotoRetrying(page, "/");
     // Timed inside the page, every frame: an `expect` would read the clock on its own retry
     // schedule (100 ms … 1 s steps), not when the card appeared.
     const at = await page.waitForFunction(
@@ -108,7 +108,7 @@ test("speed baseline", async ({ browser, page: page0 }) => {
     for (let i = 0; i < RUNS; i++) {
       const ctx = await browser.newContext({ storageState: { cookies: [], origins: [] } });
       const page = await ctx.newPage();
-      await page.goto(`/watch/${token}`);
+      await gotoRetrying(page, `/watch/${token}`);
       await page.waitForFunction(() => document.querySelector("video, audio"), null, {
         polling: "raf",
         timeout: 30_000,

frontend/e2e/stylesheet.spec.ts

@@ -1,5 +1,6 @@
 import { test, expect, type Page } from "@playwright/test";
 import { openApp } from "./helpers";
+import { gotoRetrying } from "./retryConnect";
 
 // A request can be lost on the way on a loaded machine or a poor line. A lost stylesheet leaves the
 // whole page unstyled, and every test that finds its elements by testid still passes on it: only an
@@ -53,7 +54,7 @@ test("the app gets back a stylesheet lost on the way", async ({ page }) => {
 test("a public /watch link gets back a stylesheet lost on the way", async ({ page }) => {
   const lost = await loseEachStylesheetOnce(page);
   // No such link: the page says so, and it is the same entry with the same stylesheet.
-  await page.goto("/watch/no-such-token");
+  await gotoRetrying(page, "/watch/no-such-token");
   await expect(page.locator("#root")).not.toBeEmpty();
   expect(lost.length).toBeGreaterThan(0);
   await expectStyled(page);

frontend/src/lib/e2eRetryConnect.test.ts

@@ -1,7 +1,8 @@
 // The e2e suite's request wrapper (e2e/retryConnect.ts): a connect that never came about is tried
 // again, as every TCP stack would; any other failure, or an answer, goes straight to the test.
+import { readdirSync, readFileSync } from "node:fs";
 import { describe, expect, it, vi } from "vitest";
-import { retryConnect } from "../../e2e/retryConnect";
+import { gotoRetrying, retryConnect } from "../../e2e/retryConnect";
 
 const noConnection = () => new Error("apiRequestContext.get: connect ETIMEDOUT 127.0.0.1:8080");
 
@@ -39,3 +40,43 @@ describe("retryConnect", () => {
     vi.useRealTimers();
   });
 });
+
+// The text Playwright gave when this stopped a release's e2e at its first page load (2026-11-04).
+const noBuffer = () => new Error("page.goto: net::ERR_NO_BUFFER_SPACE at http://127.0.0.1:8080/");
+
+describe("gotoRetrying", () => {
+  it("tries a page load the machine had no buffer for again", async () => {
+    vi.useFakeTimers();
+    const goto = vi.fn().mockRejectedValueOnce(noBuffer()).mockResolvedValue("response");
+    const answer = gotoRetrying({ goto }, "/feed");
+    await vi.runAllTimersAsync();
+    await expect(answer).resolves.toBe("response");
+    expect(goto).toHaveBeenCalledTimes(2);
+    expect(goto).toHaveBeenLastCalledWith("/feed");
+    vi.useRealTimers();
+  });
+
+  it("passes any other failure straight on, untried", async () => {
+    const goto = vi.fn().mockRejectedValue(new Error("page.goto: net::ERR_CONNECTION_REFUSED"));
+    await expect(gotoRetrying({ goto }, "/")).rejects.toThrow("ERR_CONNECTION_REFUSED");
+    expect(goto).toHaveBeenCalledTimes(1);
+  });
+
+  it("gives up after its last wait, with the error", async () => {
+    vi.useFakeTimers();
+    const goto = vi.fn().mockRejectedValue(noBuffer());
+    const settled = expect(gotoRetrying({ goto }, "/")).rejects.toThrow("ERR_NO_BUFFER_SPACE");
+    await vi.runAllTimersAsync();
+    await settled;
+    expect(goto).toHaveBeenCalledTimes(6);
+    vi.useRealTimers();
+  });
+
+  it("is the only way the suite loads a page", () => {
+    const dir = new URL("../../e2e/", import.meta.url);
+    const direct = readdirSync(dir)
+      .filter((f) => f.endsWith(".ts") && f !== "retryConnect.ts")
+      .filter((f) => /\.(goto|reload)\(/.test(readFileSync(new URL(f, dir), "utf-8")));
+    expect(direct).toEqual([]);
+  });
+});