fix: a popup save no longer undoes a network switch the background saved during it (closes #641)

The popup's saveState() and the background's updateState() each read the
stored record, change it and write it back, each ordered only within its own
context, so a write by one could land between the other's read and write and
be lost. Both now hold the browser's lock (navigator.locks) from the read to
the write, through withLock() in src/shared/browserApi.js, and the recovery
screen's reset takes it too. A page in a Firefox private window gets locks of
its own and is not covered. The lock also orders a page's own saves, so both
per-context queues are gone. The unit tests get a small lock from a Jest setup
file.

Model: opus-5-5

README.md

@@ -1389,6 +1389,19 @@ carries a `schemaVersion` — `STATE_SCHEMA_VERSION` in
 `saveState()` and the background's `updateState()` both do, so whichever context
 wrote last, the record says which build's shape it is in.
 
+Each write reads the record, changes it and writes it back, holding a lock from
+the read to the write: the browser's own (`navigator.locks`), taken through
+`withLock()` in `src/shared/browserApi.js`. Every page of the extension and its
+background share it, except a page in a Firefox private window, which Firefox
+gives locks of its own (see https://git.eeqj.de/sneak/AutistMask/issues/646).
+The popup's `saveState()`, the background's `updateState()` and the
+StateRecovery reset all take it, so among the pages and the background that
+share it, no write lands between another write's read and its write, where it
+would be lost. Chrome has it from version 69, older than any Chrome that runs a
+Manifest V3 extension, in pages and in the service worker; Firefox from version
+96, older than the 115 `manifest/firefox.json` declares. Where it is missing, a
+write fails rather than going ahead without it.
+
 Version 1 is the shape that shipped before versions existed, so a stored record
 with no `schemaVersion` is version 1 rather than a defect: it loads normally and
 is migrated in place by being stamped on the first write. An upgrade never shows

package.json

@@ -13,6 +13,11 @@
         "fmt": "prettier --write .",
         "fmt-check": "prettier --check ."
     },
+    "jest": {
+        "setupFiles": [
+            "<rootDir>/tests/support/navigatorLocks.js"
+        ]
+    },
     "devDependencies": {
         "@eslint/js": "10.0.1",
         "@tailwindcss/cli": "4.3.1",

src/background/state.js

@@ -16,17 +16,20 @@
 //                     across any number of awaits and no concurrent work can
 //                     move it.
 //   updateState(fn)   read fresh, apply fn to that fresh record, write it
-//                     back — all inside a queue, so two background writes
-//                     never interleave, and the read is one storage round trip
-//                     ahead of the write rather than a page lifetime ahead of
-//                     it (which is what made the popup's saveState() need a
+//                     back — all holding the lock every write of the stored
+//                     record takes, so no other write lands in between, by
+//                     the background or by any page except a page in a
+//                     Firefox private window (README, "Stored state and its
+//                     version"). The read is one storage round trip ahead of
+//                     the write rather than a page lifetime ahead of it
+//                     (which is what made the popup's saveState() need a
 //                     per-field merge against a baseline at all).
 //
 // A handler that must both read and write therefore does its network work
 // against a snapshot it owns, and applies the RESULT inside updateState().
 // It never publishes an object other in-flight work is holding.
 
-const { storageGet, storageSet } = require("../shared/browserApi");
+const { storageGet, storageSet, withLock } = require("../shared/browserApi");
 const { normalizePersisted } = require("../shared/persistedState");
 const {
     STATE_SCHEMA_VERSION,
@@ -51,11 +54,6 @@ async function getState() {
     return normalizePersisted(result.autistmask);
 }
 
-// Serializes the read-modify-write turns below. Two of them interleaved would
-// each read before the other wrote, and the second write would carry the first
-// one's fields back to their pre-turn values.
-let updateQueue = Promise.resolve();
-
 async function updateStateOnce(mutate) {
     const s = await getState();
     await mutate(s);
@@ -70,27 +68,22 @@ async function updateStateOnce(mutate) {
 
 // Apply `mutate` to a record read fresh from storage and write the result
 // back. `mutate` receives a detached, normalized profile and mutates it in
-// place; it may be async, but it must not do anything slow — the window
-// between the read and the write is the window in which another context's
-// write is lost, and keeping it to one storage round trip is what makes a
-// whole-record write safe here. Concretely: the write is the WHOLE record, so
-// a popup write that lands inside that window is reverted, in every field, by
-// the record this turn read before it. That is accepted because the window is
-// one round trip long and the popup is not writing while the worker is;
-// widening it is what would make it a real hazard.
+// place; it may be async, but it must not do anything slow. The write is the
+// WHOLE record, which is safe only because the lock (withLock() in
+// src/shared/browserApi.js) is held from the read to the write: two
+// background turns, or a turn and a page's save, never interleave
+// (https://git.eeqj.de/sneak/AutistMask/issues/641). Every page's save waits
+// while it is held, except a page in a Firefox private window, which Firefox
+// gives locks of its own (README, "Stored state and its version").
 //
 // `mutate` must also not call updateState() itself, directly or through
-// anything it awaits: the queue is strictly serial, so the inner turn waits on
-// the outer one, which is waiting on the inner one. That deadlocks the whole
-// background, not just the caller. Mutate the record you were handed.
+// anything it awaits: the inner turn waits for the lock the outer one holds,
+// and the outer one is waiting on the inner one. That deadlocks every write of
+// the stored record, not just the caller. Mutate the record you were handed.
 //
 // Resolves with the record that was written.
 function updateState(mutate) {
-    const turn = updateQueue.then(() => updateStateOnce(mutate));
-    // The queue must advance even when a turn rejects, or every update after
-    // it queues behind a promise that never settles.
-    updateQueue = turn.catch(() => {});
-    return turn;
+    return withLock("autistmask", () => updateStateOnce(mutate));
 }
 
 module.exports = { getState, updateState };

src/popup/index.js

@@ -220,7 +220,7 @@ async function widenApprovalWindow() {
 async function init() {
     // First, before anything can save: showView() saves on every navigation
     // without awaiting, so a save that fails from here on has somewhere to be
-    // reported rather than being swallowed by the save queue
+    // reported rather than reaching only the console
     // (https://git.eeqj.de/sneak/AutistMask/issues/362). Registered ahead of
     // the approval-window branch below too, since that window saves as well.
     //

src/popup/views/stateRecovery.js

@@ -24,7 +24,11 @@
 // than written again locally so that tests/popupElementIds.test.js sees these
 // lookups and holds every id below against the markup.
 const { $, VIEWS } = require("./helpers");
-const { storageGet, storageRemove } = require("../../shared/browserApi");
+const {
+    storageGet,
+    storageRemove,
+    withLock,
+} = require("../../shared/browserApi");
 const { log } = require("../../shared/log");
 
 // Typed in full before anything is erased, in the same spirit as the wallet
@@ -137,7 +141,11 @@ async function resetProfile() {
         return;
     }
     try {
-        await storageRemove("autistmask");
+        // Under the lock every write of the stored record takes, so the erase
+        // cannot land between another write's read and its write and be undone.
+        // A page in a Firefox private window is the exception: Firefox gives
+        // it locks of its own (README, "Stored state and its version").
+        await withLock("autistmask", () => storageRemove("autistmask"));
     } catch (e) {
         log.errorf("state recovery: reset failed:", e);
         setFlash("The saved data could not be erased. Nothing was changed.");

src/shared/browserApi.js

@@ -31,6 +31,11 @@
 // Everything is resolved on use rather than captured at module load. The MV3
 // service worker is torn down and re-evaluated repeatedly, and the unit
 // suite installs its stubs on `global.chrome` around a require().
+//
+// The module also holds withLock(), a wrapper around the browser's
+// `navigator.locks`, which is in neither namespace. It sits beside
+// storageGet() and storageSet() because every write of the stored record
+// takes it.
 
 // The extension API namespace, preferring `browser.*` where it exists.
 //
@@ -219,6 +224,33 @@ function storageRemove(keys) {
     return Promise.resolve(storage.remove(keys));
 }
 
+/**
+ * Run `fn` while holding the browser's lock called `name`
+ * (`navigator.locks`), and settle as `fn` settles. Every page of the extension
+ * and its background share these locks, except a page in a Firefox private
+ * window (README, "Stored state and its version"), so while one of them holds
+ * `name` another asking for it waits, in the order they asked. The lock is let
+ * go when `fn` settles, whether it resolved or rejected.
+ *
+ * Every write of the stored record holds the lock named after its key,
+ * "autistmask", from its read to its write: saveState() in
+ * src/shared/state.js, updateState() in src/background/state.js, and the
+ * reset in src/popup/views/stateRecovery.js.
+ *
+ * @param {string} name
+ * @param {function(): Promise<*>} fn
+ * @returns {Promise<*>} what `fn` resolved with.
+ * @throws rejects, without running `fn`, where `navigator.locks` is absent.
+ */
+function withLock(name, fn) {
+    if (typeof navigator === "undefined" || !navigator.locks) {
+        return Promise.reject(
+            new Error("navigator.locks is not available in this context"),
+        );
+    }
+    return navigator.locks.request(name, () => fn());
+}
+
 // `storage.session`, the browser's session storage: what is kept there lasts
 // until the browser closes. It survives the background worker being stopped
 // and started again, which module-level variables do not (README, Background
@@ -373,4 +405,5 @@ module.exports = {
     windowsGetLastFocused,
     windowsRemove,
     windowsUpdate,
+    withLock,
 };

src/shared/state.js

@@ -35,7 +35,7 @@ const {
     migrationNeeded,
 } = require("./stateSchema");
 
-const { storageGet, storageSet } = require("./browserApi");
+const { storageGet, storageSet, withLock } = require("./browserApi");
 const { log } = require("./log");
 
 // The live record the proxy below guards. Everything inside this module reads
@@ -458,8 +458,8 @@ function mergeNetworkEndpoints(base, ours, theirs) {
 // This page's own live `state` is deliberately NOT rehydrated from a field
 // another page changed — only the record written to storage is merged.
 // showView() fires saveState() on every navigation without awaiting it,
-// which is what makes the queue above necessary in the first place, and a
-// save that is slow to come back has no way to tell whether the field it
+// which is why saves from one page wait for each other (see saveState()), and
+// a save that is slow to come back has no way to tell whether the field it
 // is about to hand back is still the current answer or has since been
 // overtaken by something this very page did in the meantime; writing it
 // into `state` regardless reintroduced exactly the clobber this function
@@ -529,35 +529,21 @@ async function saveStateOnce() {
     rawState.hasWallet = rawState.wallets.length > 0;
 
     // What this save compared and wrote, not the page's state now: a change
-    // made during the save must still differ from the baseline, or the save
-    // queued after it finds nothing to store
+    // made during the save must still differ from the baseline, or the next
+    // save finds nothing to store
     // (https://git.eeqj.de/sneak/AutistMask/issues/448).
     baseline = current;
 }
 
-// showView() calls saveState() on every navigation without awaiting it, so
-// two saves from the SAME page can be in flight at once — e.g. a screen
-// shown, then immediately replaced before the first save's storageGet()
-// round trip has come back. Left concurrent, the first save's turn would
-// finish after the second's live-state mutation and then re-hydrate `state`
-// from what IT read, stomping the second, later change back to a stale
-// value — the same clobber this function exists to prevent, just between
-// two saves on one page instead of two pages. Queuing makes every save's
-// snapshot-diff-write-rehydrate run start to finish before the next one
-// begins, so each one only ever sees the true live state at its turn.
-let saveQueue = Promise.resolve();
-
 // Where a failed save is REPORTED, set once by the context that has a screen
 // to say it on (src/popup/index.js).
 //
 // A save that fails must not fail silently. showView() fires saveState() on
-// every navigation without awaiting it, and the queue below has to attach a
-// rejection handler to keep advancing — so a failing save was swallowed
-// entirely: no throw, no message, nothing on screen. The wallet kept running
-// against storage that was rejecting every write, which is the data-loss half
-// of https://git.eeqj.de/sneak/AutistMask/issues/362. The awaited callers were
-// no better off: `await saveState()` inside an unguarded event handler surfaces
-// in the console and nowhere the user looks.
+// every navigation without awaiting it, and `await saveState()` inside an
+// unguarded event handler is no better: either way, without this, a failure
+// would reach only the console, where the user never looks, and the wallet
+// would keep running against storage that rejects every write. That is the
+// data-loss half of https://git.eeqj.de/sneak/AutistMask/issues/362.
 //
 // This is the "tell the user" half; the other half is the floor in
 // normalizePersisted(), which stops the malformed-record cause from arising in
@@ -583,11 +569,20 @@ function reportSaveFailure(err) {
     }
 }
 
+// Each save runs start to finish holding the lock every write of the stored
+// record takes (withLock() in src/shared/browserApi.js), so no write by
+// another page or the background lands between its read and its write and is
+// lost (https://git.eeqj.de/sneak/AutistMask/issues/641). A page in a Firefox
+// private window is the exception: Firefox gives it locks of its own (README,
+// "Stored state and its version").
+//
+// The same lock orders this page's own saves. showView() calls saveState() on
+// every navigation without awaiting it, so two saves from one page can be
+// asked for at once; they take the lock in the order they were asked, and each
+// compares the page's state as it stands when its turn begins against the
+// baseline the save before it left.
 function saveState() {
-    const turn = saveQueue.then(saveStateOnce);
-    // The queue must advance even when a save rejects, or every save after
-    // it queues behind a promise that never settles.
-    saveQueue = turn.catch(() => {});
+    const turn = withLock("autistmask", saveStateOnce);
     // Every failed save is reported, whether or not the caller awaited this
     // one. The returned promise still rejects, so a caller that DOES await
     // keeps its own error handling.

tests/confirmTxAmount.test.js

@@ -158,7 +158,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const {
     Interface,

tests/confirmTxNetworkSwitch.test.js

@@ -189,7 +189,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const {
     BaseWallet,

tests/e2e/run.js

@@ -367,11 +367,14 @@ async function leaveTransactionDetail(page) {
     await openAddressDetail(page);
 }
 
-// Back out to Home from wherever the previous test finished.
+// Back out to Home from wherever the previous test finished, and wait for the
+// save that navigation makes, so a test reading the stored stack next reads
+// the one Home left.
 async function goHome(page) {
     await leaveTransactionDetail(page);
     await page.click("#btn-address-back");
     await visible(page, "#view-main");
+    await waitForPersisted(page, "currentView", "main", "back on Home");
 }
 
 // One field of the popup's state as it was actually persisted, read out of

tests/nativeCurrency.test.js

@@ -151,7 +151,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const { state } = require("../src/shared/state");
 const { NETWORKS } = require("../src/shared/networks");

tests/persistedEntryFloors.test.js

@@ -364,7 +364,7 @@ describe("a save that fails", () => {
         return storage;
     }
 
-    test("is reported, not swallowed by the save queue", async () => {
+    test("is reported when the caller does not await it", async () => {
         const storage = failingStorage(unversionedValidProfile());
         const { state, loadState, saveState, onSaveFailure } =
             loadStateModule(storage);

tests/sendAmountRule.test.js

@@ -97,7 +97,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const { state } = require("../src/shared/state");
 const send = require("../src/popup/views/send");

tests/sendDisplayFloor.test.js

@@ -151,7 +151,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const { refreshBalances } = require("../src/shared/balances");
 const { state } = require("../src/shared/state");

tests/sendMax.test.js

@@ -146,7 +146,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const { Transaction, Wallet, formatEther } = require("ethers");
 const { refreshBalances } = require("../src/shared/balances");

tests/stateMerge.test.js

@@ -160,7 +160,7 @@ describe("the approval-window reproduction", () => {
         await approvalWindow.state.loadState();
         approvalWindow.helpers.showView("approve-tx");
         // showView() does not await its own saveState(); an extra save
-        // joins the same queue and only resolves once that one has too,
+        // waits for the lock behind that one and so resolves only after it,
         // which is the black-box way to know it landed.
         await approvalWindow.state.saveState();
 

tests/stateWriteLock.test.js

@@ -0,0 +1,96 @@
+// A popup save reads the stored record, merges this page's changes into it
+// and writes it back. The background's write of a network the user approved
+// used to be able to land between that read and that write, and the popup's
+// write then put the old network back
+// (https://git.eeqj.de/sneak/AutistMask/issues/641). Every write of the record
+// now holds a lock from its read to its write.
+//
+// The popup and the background run here as the real modules over one shared
+// storage stub, and share the lock the way the background and a page outside
+// a Firefox private window share the browser's
+// (tests/support/navigatorLocks.js).
+
+const { makeStorageStub } = require("./support/storageStub");
+
+function loadContexts(storage) {
+    jest.resetModules();
+    globalThis.chrome = { storage: { local: storage.local } };
+    return {
+        popup: require("../src/shared/state"),
+        background: require("../src/background/state"),
+        applyChainSwitchFields: require("../src/shared/chainSwitchFields")
+            .applyChainSwitchFields,
+    };
+}
+
+// Lets every pending promise callback run, and then some.
+function nextMacrotask() {
+    return new Promise((resolve) => setImmediate(resolve));
+}
+
+afterEach(() => {
+    delete globalThis.chrome;
+    jest.restoreAllMocks();
+});
+
+test("a network the background switches to during a popup save stays stored", async () => {
+    const storage = makeStorageStub({ autistmask: { networkId: "sepolia" } });
+    const { popup, background, applyChainSwitchFields } = loadContexts(storage);
+    await popup.loadState();
+
+    // The popup navigates, so its save has a change of its own to write.
+    popup.state.currentView = "settings";
+
+    // The popup's save has read the record and is about to write it back when
+    // the user's approval of a site's switch to mainnet reaches the
+    // background. Without the lock the background's whole update runs before
+    // the next macrotask; with it, the update waits for the popup's write.
+    let backgroundSwitch;
+    const realSet = storage.local.set.getMockImplementation();
+    storage.local.set.mockImplementationOnce(async (items) => {
+        backgroundSwitch = background.updateState((fresh) =>
+            applyChainSwitchFields(fresh, "mainnet"),
+        );
+        await nextMacrotask();
+        return realSet(items);
+    });
+
+    await popup.saveState();
+    await backgroundSwitch;
+
+    const stored = storage.read("autistmask");
+    expect(stored.networkId).toBe("mainnet");
+    expect(stored.currentView).toBe("settings");
+});
+
+test("after a save that failed, the next save still keeps a network the background switches to during it", async () => {
+    jest.spyOn(console, "error").mockImplementation(() => {});
+    const storage = makeStorageStub({ autistmask: { networkId: "sepolia" } });
+    const { popup, background, applyChainSwitchFields } = loadContexts(storage);
+    await popup.loadState();
+    popup.state.currentView = "settings";
+
+    // The first save's write is refused, so it gives the lock back having
+    // failed.
+    storage.local.set.mockRejectedValueOnce(new Error("quota exceeded"));
+    await expect(popup.saveState()).rejects.toThrow("quota exceeded");
+
+    // The next save is between its read and its write when the background
+    // switches to mainnet, as in the test above.
+    let backgroundSwitch;
+    const realSet = storage.local.set.getMockImplementation();
+    storage.local.set.mockImplementationOnce(async (items) => {
+        backgroundSwitch = background.updateState((fresh) =>
+            applyChainSwitchFields(fresh, "mainnet"),
+        );
+        await nextMacrotask();
+        return realSet(items);
+    });
+
+    await popup.saveState();
+    await backgroundSwitch;
+
+    const stored = storage.read("autistmask");
+    expect(stored.networkId).toBe("mainnet");
+    expect(stored.currentView).toBe("settings");
+});

tests/support/navigatorLocks.js

@@ -0,0 +1,27 @@
+// `navigator.locks` for the unit tests, which run on node, where there is none.
+//
+// One lock per name: granted in the order it was asked for, and let go when
+// the callback settles, whether it resolved or rejected. That is what the
+// browser's own does for the one call the extension makes,
+// `navigator.locks.request(name, callback)`. Every module a test file loads
+// shares it, as the extension's background and its pages share the browser's,
+// except a page in a Firefox private window (README, "Stored state and its
+// version").
+//
+// Run before each test file by `setupFiles` in package.json.
+
+// For each name, a promise that settles once the last request for it has
+// let the lock go.
+const released = new Map();
+
+function request(name, callback) {
+    const previous = released.get(name) || Promise.resolve();
+    const result = previous.then(() => callback({ name, mode: "exclusive" }));
+    released.set(
+        name,
+        result.catch(() => {}),
+    );
+    return result;
+}
+
+globalThis.navigator = { locks: { request } };

tests/unknownScaleSend.test.js

@@ -120,7 +120,7 @@ global.document = {
     body: { prepend() {}, appendChild() {} },
     addEventListener() {},
 };
-global.navigator = { clipboard: { writeText() {} } };
+global.navigator.clipboard = { writeText() {} };
 
 const { AbiCoder, parseUnits } = require("ethers");
 const { fetchTokenBalances } = require("../src/shared/balances");