feat: vendor and censor the phishing blocklist at build time (closes #219)

tests/e2e/harness.js

@@ -13,7 +13,7 @@ const os = require("os");
 const path = require("path");
 
 const { chromium } = require("playwright-core");
-const { installNetworkStubs } = require("./network");
+const { installNetworkStubs, WORKER_PROBE_URL } = require("./network");
 
 const REPO_ROOT = path.resolve(__dirname, "..", "..");
 const EXT_PATH = path.join(REPO_ROOT, "dist", "chrome");
@@ -129,42 +129,109 @@ function attachErrorListeners(ctx, errors) {
     // if it ever stops being.
 }
 
+function sleep(ms) {
+    return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+// The most recently seen background worker, waiting for one if none has
+// appeared yet. Most recent rather than first: Chrome stops an idle MV3
+// worker and starts a fresh one on the next event, and a handle to a
+// stopped worker cannot be evaluated in.
 async function serviceWorker(ctx) {
-    const [existing] = ctx.serviceWorkers();
-    if (existing) return existing;
+    const workers = ctx.serviceWorkers();
+    const latest = workers[workers.length - 1];
+    if (latest) return latest;
     return ctx.waitForEvent("serviceworker", { timeout: 30000 });
 }
 
-// How long to wait for the background worker's first outbound request.
-//
-// The margin that actually decides whether this check is sound is not
-// this timeout — it is whether the route handler is installed before the
-// worker fetches. Measured over several runs: route installation
-// completes 11-23ms after the context comes up, and the worker's
-// blocklist fetch arrives 525-883ms after that, so the route wins by
-// roughly 25-50x. This 30s figure is only slack for a loaded machine on
-// top of that; losing the race fails the run rather than passing it
-// quietly, which was verified by forcing a 3s delay before route
-// installation.
+// How long to wait for the probe request the worker is asked to make.
 const WORKER_TRAFFIC_TIMEOUT_MS = 30000;
 
 // ctx.route() only sees service-worker requests when Playwright runs with
 // PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1, which script/test-e2e
-// sets. Without it the worker's traffic — notably the phishing blocklist
-// fetch src/background/index.js issues at startup — goes to the real
-// internet, and nothing says so, because src/shared/phishingDomains.js
-// swallows fetch failures. A harness whose isolation can lapse in silence
-// is worthless, so this does not take the flag on trust: the background
-// worker's own startup fetch has to show up in the route handler, or the
-// suite refuses to run.
+// sets. Without it every fetch the background worker makes goes to the
+// real internet and nothing says so. A harness whose isolation can lapse
+// in silence is worthless, so this does not take the flag on trust: a
+// request the worker itself issues has to show up in the route handler,
+// or the suite refuses to run.
 //
-// Deliberately NOT a synthetic probe fetched through worker.evaluate():
-// evaluating in an extension worker this early kills it (the call fails
-// with "Target page, context or browser has been closed" and the worker
-// disappears), which would break the very thing being measured. Observing
-// traffic the extension already generates costs nothing and cannot
-// perturb it.
-async function assertWorkerTrafficIntercepted(stubs) {
+// The anchor is a probe the harness asks the worker for, not traffic the
+// extension generates on its own. It used to be the phishing blocklist
+// fetch src/background/index.js issued at startup; that fetch is gone —
+// the blocklist is vendored at build time and the extension contacts
+// nobody when it starts — so there is no longer any startup traffic to
+// observe and the check generates its own.
+//
+// Evaluating in the worker straight after launch does not work, and that
+// is not a stale observation: it was tried again here and failed with
+// "Target page, context or browser has been closed" on the first run.
+// Chrome stops the freshly registered worker as soon as it has nothing to
+// do, and the extension no longer gives it anything to do — which is the
+// same change that removed the old anchor. So the probe wakes the worker
+// before it evaluates in it, by sending it a message from an extension
+// page and waiting for the reply: delivering a message is what starts a
+// stopped worker, and a worker that has just answered one is alive.
+// The evaluated fetch is not awaited, so nothing in the worker is held
+// open by the probe either.
+async function wakeWorker(ctx) {
+    const sw = await serviceWorker(ctx);
+    const extensionId = new URL(sw.url()).host;
+    const page = await ctx.newPage();
+    try {
+        await page.goto(
+            "chrome-extension://" + extensionId + "/src/popup/index.html",
+        );
+        // eth_chainId is answered from local state: it wakes the worker
+        // and changes nothing.
+        await page.evaluate(
+            () =>
+                new Promise((resolve) => {
+                    chrome.runtime.sendMessage(
+                        {
+                            type: "AUTISTMASK_RPC",
+                            method: "eth_chainId",
+                            params: [],
+                        },
+                        () => resolve(null),
+                    );
+                }),
+        );
+    } finally {
+        await page.close();
+    }
+}
+
+async function probeFromWorker(ctx, url) {
+    let lastError = null;
+    for (let attempt = 0; attempt < 5; attempt++) {
+        try {
+            await wakeWorker(ctx);
+            const sw = await serviceWorker(ctx);
+            await sw.evaluate((u) => {
+                // Deliberately not awaited and never rejected: what is
+                // being observed is that the request reaches the route
+                // handler, and an unhandled rejection in the worker would
+                // be collected as a suite error if it did not.
+                fetch(u).catch(() => {});
+            }, url);
+            return;
+        } catch (e) {
+            lastError = e;
+            await sleep(500);
+        }
+    }
+    throw new Error(
+        "could not ask the background worker to fetch " +
+            url +
+            ", so service-worker interception was never tested. Last " +
+            "error: " +
+            (lastError && lastError.message),
+    );
+}
+
+async function assertWorkerTrafficIntercepted(ctx, stubs) {
+    await probeFromWorker(ctx, WORKER_PROBE_URL);
+
     const seen = await stubs.waitForServiceWorkerTraffic(
         WORKER_TRAFFIC_TIMEOUT_MS,
     );
@@ -177,19 +244,16 @@ async function assertWorkerTrafficIntercepted(stubs) {
     throw new Error(
         "observed no service-worker request in the route handler within " +
             WORKER_TRAFFIC_TIMEOUT_MS +
-            "ms. Under working interception the background worker's " +
-            "startup blocklist fetch (src/background/index.js) reaches the " +
-            "handler about half a second after the route is installed. " +
-            "Two causes are plausible and this check cannot distinguish " +
+            "ms, although the background worker was asked to fetch " +
+            WORKER_PROBE_URL +
+            ". Two causes are plausible and this check cannot distinguish " +
             "them: (1) service-worker interception is not in effect, so " +
-            "that traffic went to the real internet unobserved — the suite " +
+            "that request went to the real internet unobserved — the suite " +
             "must be run through script/test-e2e, which sets " +
             "PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1, and a " +
             "Playwright upgrade may have dropped or renamed that flag; " +
-            "(2) no worker request was made in the first place — the route " +
-            "lost the startup race, or the worker no longer fetches at " +
-            "startup, in which case this check needs a new anchor because " +
-            "there is no longer any worker traffic to observe. Either way " +
+            "(2) the probe never ran, because the worker was torn down " +
+            "between being handed over and being evaluated in. Either way " +
             "the fix is a replacement mechanism or an honest downgrade of " +
             "the isolation claims in tests/e2e/network.js and README.md — " +
             "not deleting this check",
@@ -241,7 +305,7 @@ async function launch(routeOpts) {
         routeOpts.report = (text) => errors.record("network", text);
         const stubs = await installNetworkStubs(ctx, routeOpts);
 
-        await assertWorkerTrafficIntercepted(stubs);
+        await assertWorkerTrafficIntercepted(ctx, stubs);
 
         // The extension id is derived from the unpacked path, so it
         // changes and must never be hardcoded. It is the host part of the