Compare commits

..
Author SHA1 Message Date
drakezhang 50a64d45c0 chore(release): 0.2.0 2026-09-02 18:08:34 +08:00
56 changed files with 247 additions and 3084 deletions
+2
View File
@@ -9,6 +9,8 @@ Starting from 0.2.0, CLI / Extension / DSH Plugin share the same version number.
## [0.2.0] - 2026-09-02
## [0.2.0] - 2026-09-XX
### Added
- File transfer: upload and download support across CLI, Extension, and DSH Plugin
- File transfer: drag-and-drop upload (`drop-to-upload`)
@@ -254,69 +254,6 @@ describe("ChromiumCdp", () => {
expect(cdp.isAttached(7)).toBe(false);
});
it.each([
false,
true,
])("waits for detach before reconnecting a returned tab (detach rejects: %s)", async (rejectDetach) => {
const { api } = fakeApi();
const attached = new Set<number>();
let finishDetach!: () => void;
vi.mocked(api.attach).mockImplementation(async ({ tabId }) => {
if (attached.has(tabId!)) throw new Error("Another debugger is already attached");
attached.add(tabId!);
});
vi.mocked(api.detach).mockImplementation(async ({ tabId }) => {
attached.delete(tabId!);
});
vi.mocked(api.detach).mockImplementationOnce(
({ tabId }) =>
new Promise<void>((resolve, reject) => {
finishDetach = () => {
attached.delete(tabId!);
if (rejectDetach) reject(new Error("tab already detached"));
else resolve();
};
}),
);
const cdp = new ChromiumCdp(api);
cdp.trackSessionTab("aa11", 7);
await cdp.ensureAttached(7);
const returning = cdp.releaseSessionTab("aa11", 7);
await vi.waitFor(() => expect(api.detach).toHaveBeenCalledOnce());
let duplicateDetachFinished = false;
const duplicateDetach = cdp.detach(7).then(() => {
duplicateDetachFinished = true;
});
cdp.trackSessionTab("bb22", 7);
// Register rejection handlers immediately; the pre-fix driver rejects
// both commands while the browser still has the previous attachment.
const pending = Promise.allSettled([
cdp.send(7, "Runtime.evaluate", { expression: "document.title" }),
cdp.send(7, "DOM.getDocument"),
]);
await cdp.send(8, "DOM.getDocument");
const finishedEarly = duplicateDetachFinished;
finishDetach();
await Promise.all([returning, duplicateDetach]);
expect(await pending).toEqual([
{ status: "fulfilled", value: { ok: true } },
{ status: "fulfilled", value: { ok: true } },
]);
expect(finishedEarly).toBe(false);
expect(vi.mocked(api.attach).mock.calls.filter(([target]) => target.tabId === 7)).toHaveLength(
2,
);
expect(cdp.isAttached(7)).toBe(true);
expect(cdp.isAttached(8)).toBe(true);
await cdp.detachSession("bb22");
expect(api.detach).toHaveBeenCalledTimes(2);
expect(cdp.isAttached(7)).toBe(false);
expect(attached.has(7)).toBe(false);
expect(cdp.isAttached(8)).toBe(true);
});
it("detachAll() iterates every cached tab", async () => {
const { api } = fakeApi();
const cdp = new ChromiumCdp(api);
@@ -714,155 +651,6 @@ describe("ChromiumCdp", () => {
expect(cdp.networkEntriesSince(33, 0, 50, 1000).entries[0].url).toBeUndefined();
});
it("releases only the returning session's claim on a tab", async () => {
const { api } = fakeApi();
const cdp = new ChromiumCdp(api);
await cdp.ensureAttached(1);
await cdp.ensureAttached(2);
cdp.trackSessionTab("aa11", 1);
cdp.trackSessionTab("bb22", 1);
cdp.trackSessionTab("aa11", 2);
await cdp.releaseSessionTab("unknown", 1);
await cdp.releaseSessionTab("aa11", 1);
expect(api.detach).not.toHaveBeenCalled();
await cdp.releaseSessionTab("bb22", 1);
await cdp.releaseSessionTab("bb22", 1);
expect(api.detach).toHaveBeenCalledExactlyOnceWith({ tabId: 1 });
expect(cdp.isAttached(2)).toBe(true);
await cdp.detachSession("aa11");
expect(api.detach).toHaveBeenCalledTimes(2);
expect(api.detach).toHaveBeenLastCalledWith({ tabId: 2 });
});
it.each([
false,
true,
])("releases a tab with an attachment in flight (new owner: %s)", async (newOwner) => {
const { api } = fakeApi();
let finishAttach!: () => void;
vi.mocked(api.attach).mockImplementationOnce(
() =>
new Promise<void>((resolve) => {
finishAttach = resolve;
}),
);
const cdp = new ChromiumCdp(api);
cdp.trackSessionTab("aa11", 1);
const attaching = cdp.ensureAttached(1);
const releasing = cdp.releaseSessionTab("aa11", 1);
if (newOwner) cdp.trackSessionTab("bb22", 1);
finishAttach();
await Promise.all([attaching, releasing]);
expect(cdp.isAttached(1)).toBe(newOwner);
expect(api.detach).toHaveBeenCalledTimes(newOwner ? 0 : 1);
});
it("stops accepting dialogs on a returned tab even when another session keeps CDP attached", async () => {
const { api, onEvent } = fakeApi();
let controlled = true;
const cdp = new ChromiumCdp(api, { shouldAutoAcceptDialog: () => controlled });
cdp.trackSessionTab("aa11", 1);
cdp.trackSessionTab("bb22", 1);
await cdp.ensureAttached(1);
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", {
type: "confirm",
message: "before return",
});
await vi.waitFor(() => expect(cdp.dialogsSince(1, 0)).toHaveLength(1));
vi.mocked(api.sendCommand).mockClear();
controlled = false;
await cdp.releaseSessionTab("aa11", 1);
expect(cdp.isAttached(1)).toBe(true);
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", {
type: "confirm",
message: "after return",
});
await Promise.resolve();
expect(api.sendCommand).not.toHaveBeenCalled();
expect(cdp.dialogsSince(1, 0)).toHaveLength(1);
controlled = true;
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", {
type: "alert",
message: "borrowed again",
});
await vi.waitFor(() => expect(cdp.dialogsSince(1, 0)).toHaveLength(2));
expect(api.sendCommand).toHaveBeenCalledExactlyOnceWith(
{ tabId: 1 },
"Page.handleJavaScriptDialog",
{ accept: true },
);
});
it("ignores dialog events after detach, including a pending eligibility check", async () => {
const { api, onEvent } = fakeApi();
let resolveEligibility!: (value: boolean) => void;
const shouldAutoAcceptDialog = vi.fn(
() =>
new Promise<boolean>((resolve) => {
resolveEligibility = resolve;
}),
);
const cdp = new ChromiumCdp(api, { shouldAutoAcceptDialog });
await cdp.ensureAttached(1);
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "alert" });
await cdp.detach(1);
resolveEligibility(true);
await Promise.resolve();
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "alert" });
expect(shouldAutoAcceptDialog).toHaveBeenCalledOnce();
expect(api.sendCommand).not.toHaveBeenCalledWith(
expect.anything(),
"Page.handleJavaScriptDialog",
expect.anything(),
);
expect(cdp.dialogsSince(1, 0)).toEqual([]);
});
it("does not accept dialogs when the tab's current scope cannot be determined", async () => {
const { api, onEvent } = fakeApi();
const shouldAutoAcceptDialog = vi.fn(async () => {
throw new Error("tab is gone");
});
const cdp = new ChromiumCdp(api, { shouldAutoAcceptDialog });
await cdp.ensureAttached(1);
vi.mocked(api.sendCommand).mockClear();
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "confirm" });
await Promise.resolve();
expect(shouldAutoAcceptDialog).toHaveBeenCalledWith(1);
expect(api.sendCommand).not.toHaveBeenCalled();
expect(cdp.dialogsSince(1, 0)).toEqual([]);
});
it("does not restore dialog state when an acceptance completes after detach", async () => {
const { api, onEvent } = fakeApi();
const cdp = new ChromiumCdp(api);
await cdp.ensureAttached(1);
let finishAccept!: () => void;
vi.mocked(api.sendCommand).mockImplementationOnce(
() =>
new Promise<void>((resolve) => {
finishAccept = resolve;
}),
);
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "alert" });
await cdp.detach(1);
finishAccept();
await Promise.resolve();
expect(cdp.dialogsSince(1, 0)).toEqual([]);
expect(cdp.dialogCursor(1)).toBe(0);
});
it("detachSession only detaches tabs no other session owns", async () => {
const { api } = fakeApi();
const cdp = new ChromiumCdp(api);
@@ -165,7 +165,6 @@ export class ChromiumCdp {
private readonly api: CdpDebuggerApi;
private readonly attachedTabs = new Set<number>();
private readonly attachInFlight = new Map<number, Promise<void>>();
private readonly detachInFlight = new Map<number, Promise<void>>();
private readonly tabOwners = new Map<number, Set<string>>();
private readonly dialogBuffers = new Map<number, JavaScriptDialogInfo[]>();
private readonly dialogSequences = new Map<number, number>();
@@ -183,13 +182,7 @@ export class ChromiumCdp {
private networkSubscription: { dispose(): void } | null = null;
private frameTargetSubscription: { dispose(): void } | null = null;
constructor(
api: CdpDebuggerApi = chromeDebuggerApi,
private readonly options: {
/** CDP observation alone does not authorize dismissing user dialogs. */
shouldAutoAcceptDialog?: (tabId: number) => boolean | Promise<boolean>;
} = {},
) {
constructor(api: CdpDebuggerApi = chromeDebuggerApi) {
this.api = api;
this.bindAutoDetach();
this.bindDialogHandler();
@@ -200,10 +193,6 @@ export class ChromiumCdp {
/** Attach to `tabId` if we haven't already in this driver. */
async ensureAttached(tabId: number): Promise<void> {
// Returning a tab clears the cache before Chrome finishes detaching.
// New observers must wait before opening the next connection to that tab.
const detaching = this.detachInFlight.get(tabId);
if (detaching) await detaching;
if (this.attachedTabs.has(tabId)) return;
const existing = this.attachInFlight.get(tabId);
if (existing) {
@@ -436,11 +425,6 @@ export class ChromiumCdp {
/** Detach if attached; never throws. */
async detach(tabId: number): Promise<void> {
const existing = this.detachInFlight.get(tabId);
if (existing) {
await existing;
return;
}
this.attachInFlight.delete(tabId);
if (!this.attachedTabs.has(tabId)) return;
this.attachedTabs.delete(tabId);
@@ -448,19 +432,13 @@ export class ChromiumCdp {
this.clearConsoleState(tabId);
this.clearNetworkState(tabId);
this.clearFrameState(tabId);
const detach = (async () => {
try {
await this.api.detach({ tabId });
} catch (err) {
// Tab may already be gone — Chrome auto-detaches on close. Log
// at debug so production builds aren't noisy.
console.debug("[bsk cdp] detach failed (likely tab already closed)", err);
}
})().finally(() => {
this.detachInFlight.delete(tabId);
});
this.detachInFlight.set(tabId, detach);
await detach;
try {
await this.api.detach({ tabId });
} catch (err) {
// Tab may already be gone — Chrome auto-detaches on close. Log
// at debug so production builds aren't noisy.
console.debug("[bsk cdp] detach failed (likely tab already closed)", err);
}
}
/** True iff `ensureAttached(tabId)` has succeeded since the last detach. */
@@ -475,17 +453,6 @@ export class ChromiumCdp {
this.tabOwners.set(tabId, owners);
}
/** Release one session's claim, preserving attachments still used by another. */
async releaseSessionTab(sessionId: string, tabId: number): Promise<void> {
const owners = this.tabOwners.get(tabId);
if (!owners?.delete(sessionId) || owners.size > 0) return;
this.tabOwners.delete(tabId);
// An observation may still be attaching when the tab is returned. Wait
// for it so detach cannot miss the attachment or remove a new owner's claim.
await this.attachInFlight.get(tabId)?.catch(() => {});
if (!this.tabOwners.has(tabId)) await this.detach(tabId);
}
/** Subscribe to all CDP events. Returned disposable removes the listener. */
onEvent(handler: (source: CdpDebuggee, method: string, params: unknown) => void): {
dispose(): void;
@@ -672,23 +639,13 @@ export class ChromiumCdp {
}
private async onJavaScriptDialogOpening(tabId: number, params: unknown): Promise<void> {
if (!this.attachedTabs.has(tabId) && !this.attachInFlight.has(tabId)) return;
const parsed = parseDialogOpeningParams(params);
try {
if (
this.options.shouldAutoAcceptDialog &&
!(await this.options.shouldAutoAcceptDialog(tabId))
) {
return;
}
// The tab may have been returned while its current scope was checked.
if (!this.attachedTabs.has(tabId) && !this.attachInFlight.has(tabId)) return;
const handleParams: { accept: boolean; promptText?: string } = { accept: true };
if (parsed.type === "prompt") {
handleParams.promptText = parsed.defaultPrompt ?? "";
}
await this.api.sendCommand({ tabId }, "Page.handleJavaScriptDialog", handleParams);
if (!this.attachedTabs.has(tabId) && !this.attachInFlight.has(tabId)) return;
const sequence = (this.dialogSequences.get(tabId) ?? 0) + 1;
this.dialogSequences.set(tabId, sequence);
this.appendDialog(tabId, {
@@ -878,9 +835,15 @@ export class ChromiumCdp {
/** Detach tabs only when no other live session has claimed them. */
async detachSession(sessionId: string): Promise<void> {
await Promise.all(
Array.from(this.tabOwners.keys(), (tabId) => this.releaseSessionTab(sessionId, tabId)),
);
const tabsToDetach: number[] = [];
for (const [tabId, owners] of this.tabOwners) {
owners.delete(sessionId);
if (owners.size === 0) {
this.tabOwners.delete(tabId);
tabsToDetach.push(tabId);
}
}
await Promise.all(tabsToDetach.map((tabId) => this.detach(tabId)));
}
}
@@ -45,32 +45,10 @@ function portHarness() {
describe("RecordFrameAgent", () => {
afterEach(() => {
vi.unstubAllGlobals();
document.documentElement.removeAttribute(RECORD_DOCUMENT_ATTRIBUTE);
document.body.replaceChildren();
});
it("starts when crypto.randomUUID is unavailable", async () => {
const harness = portHarness();
const getRandomValues = vi.fn((bytes: Uint8Array) => {
bytes.fill(0x11);
return bytes;
});
vi.stubGlobal("crypto", { getRandomValues });
vi.stubGlobal("chrome", {
runtime: {
connect: vi.fn(() => harness.port),
sendMessage: vi.fn(),
},
});
const agent = new RecordFrameAgent();
await expect(
agent.start({ type: RECORD_FRAME_START, requestId: "rec-http", startedAtMs: 10 }),
).resolves.toEqual({ ok: true });
expect(getRandomValues).toHaveBeenCalled();
});
it("keeps a failed stop retryable and flushes the final dirty fill", async () => {
const harness = portHarness();
const sendMessage = vi
@@ -1,4 +1,3 @@
import { createRandomUuid } from "@/lib/random-uuid";
import {
isAcceptedRecordStepAck,
RECORD_STEP,
@@ -19,7 +18,7 @@ export class RecordStepDelivery {
constructor(
requestId: string,
send: SendRecordStepMessage = (message) => chrome.runtime.sendMessage(message),
producerId: string = createRandomUuid(),
producerId: string = crypto.randomUUID(),
) {
this.#requestId = requestId;
this.#producerId = producerId;
@@ -1,4 +1,3 @@
import { createRandomUuid } from "@/lib/random-uuid";
import {
markRecordingDocument,
type RecordingDocumentMarker,
@@ -68,7 +67,7 @@ export class RecordFrameAgent {
async #start(
message: RecordFrameStartMessage,
): Promise<{ ok: true } | { ok: false; error: string }> {
const producerId = createRandomUuid();
const producerId = crypto.randomUUID();
const root = await waitForDocumentElement();
if (this.#disposed) return { ok: false, error: "recording document is disposed" };
const marker = markRecordingDocument(producerId, root);
+8 -62
View File
@@ -25,7 +25,7 @@ import { recordFrameCoordinator } from "@/lib/recording/frame-coordinator";
import { attachSessionsLiveFlag } from "@/lib/sessions-live-flag";
import { createDisconnectCleanup } from "@/session-manager/disconnect-cleanup";
import { attachSessionEventHandler } from "@/session-manager/event-handler";
import { isAgentControlledTab, SessionManager } from "@/session-manager/manager";
import { SessionManager } from "@/session-manager/manager";
import {
attachBorrowNotificationButtonHandler,
attachBorrowNotificationClickHandler,
@@ -41,8 +41,6 @@ import {
attachRecordStepListener,
type RecordRuntimeDeps,
} from "@/tools/record";
import { chromeTabsApi } from "@/tools/shared";
import { chromeTabMutationApi } from "@/tools/tabs";
import { detectBrowserMeta } from "@/transport/handshake";
import type { Transport } from "@/transport/transport";
import { WSTransport } from "@/transport/ws-transport";
@@ -51,12 +49,7 @@ export default defineBackground(() => {
const controller = new ConnectionController();
const transport = new WSTransport({ url: __BSK_DAEMON_WS_URL__ });
const sessions = new SessionManager();
const cdp = new ChromiumCdp(undefined, {
shouldAutoAcceptDialog: async (tabId) => {
const tab = await chrome.tabs.get(tabId);
return sessions.findByWindowId(tab.windowId) !== null;
},
});
const cdp = new ChromiumCdp();
const sessionsLive = attachSessionsLiveFlag({ manager: sessions });
let overlayGeneration = 0;
const controlModes = new Map<string, OverlayMode>();
@@ -87,24 +80,6 @@ export default defineBackground(() => {
};
}
/**
* Authoritative overlay state for a specific tab. Agent Window tabs are
* free by default; only tabs explicitly claimed through session startup,
* `tab_create`, or `tab_borrow` receive the control overlay.
*/
function overlayStateForTab(tabId?: number, windowId?: number): OverlayAgentStateMessage {
if (typeof tabId === "number" && typeof windowId === "number") {
const ctx = sessions.findByWindowId(windowId);
if (ctx && isAgentControlledTab(ctx, tabId)) return overlayStateForWindow(windowId);
}
return {
type: OVERLAY_AGENT_STATE,
sessionId: null,
mode: "hidden",
generation: overlayGeneration,
};
}
async function pushOverlayStateToTab(
tabId: number,
state: OverlayAgentStateMessage,
@@ -116,18 +91,13 @@ export default defineBackground(() => {
}
}
async function pushOverlayStateForTab(tabId: number, windowId?: number): Promise<void> {
const state = overlayStateForTab(tabId, windowId);
await pushOverlayStateToTab(tabId, state);
}
async function pushOverlayStateForWindow(windowId: number): Promise<void> {
const state = overlayStateForWindow(windowId);
const tabs = await chrome.tabs.query({ windowId });
await Promise.all(
tabs.map((tab) => {
if (typeof tab.id !== "number") return Promise.resolve();
return pushOverlayStateForTab(tab.id, windowId);
}),
tabs.map((tab) =>
typeof tab.id === "number" ? pushOverlayStateToTab(tab.id, state) : Promise.resolve(),
),
);
}
@@ -166,30 +136,13 @@ export default defineBackground(() => {
if (typeof tab.windowId !== "number") return;
pushOverlayStateForAgentWindow(tab.windowId);
});
// Newly observed tabs are free unless the agent's own creation path has
// already claimed their concrete id. This listener only renders that
// state; it never infers or mutates ownership from event ordering.
chrome.tabs.onCreated.addListener((tab) => {
if (typeof tab.windowId !== "number" || typeof tab.id !== "number") return;
if (!sessions.findByWindowId(tab.windowId)) return;
void pushOverlayStateForTab(tab.id, tab.windowId);
});
chrome.tabs.onRemoved.addListener((tabId, removeInfo) => {
sessions.forgetClosedTab(tabId, { isWindowClosing: removeInfo.isWindowClosing });
});
// Re-sync the storage.session flag on SW startup so a previous SW's
// stale `true` does not keep waking us on every page load until the
// first mutation (review M4/M5 round 3 m-R3-1).
void sessionsLive.refresh();
const cleanupAfterDisconnect = createDisconnectCleanup({
manager: sessions,
// Same contract as the dispatcher's `tool.session_stop`: without these
// deps the agent-tab cleanup and the window-release path are dead code.
sessionStopDeps: {
cdp,
tabManagement: { tabs: chromeTabMutationApi },
tabsQuery: chromeTabsApi,
},
sessionStopDeps: { cdp },
onSessionsChanged: () => {
void sessionsLive.syncFromManager();
},
@@ -223,9 +176,6 @@ export default defineBackground(() => {
recording: recordDeps,
onSessionsChanged: onOverlaySessionStateChanged,
onBrowserControlResumed,
onAgentTabClaimed: (tabId, windowId) => {
void pushOverlayStateForTab(tabId, windowId);
},
approveBorrow: (ctx) =>
requestBorrowConfirmation(ctx.tabId, {
...(ctx.signal !== undefined ? { signal: ctx.signal } : {}),
@@ -359,11 +309,7 @@ export default defineBackground(() => {
}
if (msg.kind === OVERLAY_MSG_READY) {
// Resolve from explicit tab ownership before sending so free tabs never
// flash the control mask.
if (typeof sender.tab?.id === "number") {
void pushOverlayStateForTab(sender.tab.id, sender.tab.windowId);
}
sendResponse(overlayStateForWindow(sender.tab?.windowId));
return false;
}
@@ -122,8 +122,8 @@ describe("App", () => {
expect(screen.queryByText(/^扩展 v/)).toBeNull();
expect(screen.queryByText(/^daemon v/)).toBeNull();
expect(screen.getByTitle("扩展版本").textContent).toBe(`Ext ${EXTENSION_VERSION}`);
expect(screen.getByTitle("bsk 版本").textContent).toBe(`CLI ${mockDaemonVersion}`);
expect(screen.getByTitle("扩展版本").textContent).toBe(EXTENSION_VERSION);
expect(screen.getByTitle("bsk 版本").textContent).toBe(mockDaemonVersion);
expect(screen.getByText("03c3e47f")).toBeTruthy();
const copyButton = screen.getByRole("button", { name: "复制实例 ID" });
@@ -1,30 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import { createRandomUuid } from "../random-uuid";
describe("createRandomUuid", () => {
afterEach(() => {
vi.unstubAllGlobals();
});
it("uses crypto.randomUUID when it is available", () => {
const randomUUID = vi.fn(() => "00000000-0000-4000-8000-000000000000");
vi.stubGlobal("crypto", { randomUUID, getRandomValues: vi.fn() });
expect(createRandomUuid()).toBe("00000000-0000-4000-8000-000000000000");
expect(randomUUID).toHaveBeenCalledOnce();
});
it("falls back to getRandomValues and sets UUID v4 bits", () => {
const bytes = new Uint8Array(16).fill(0xff);
const getRandomValues = vi.fn((target: Uint8Array) => {
target.set(bytes);
return target;
});
vi.stubGlobal("crypto", { getRandomValues });
const uuid = createRandomUuid();
expect(uuid).toBe("ffffffff-ffff-4fff-bfff-ffffffffffff");
expect(getRandomValues).toHaveBeenCalledOnce();
});
});
+2 -4
View File
@@ -3,10 +3,8 @@
* between the content-script control overlay and the background SW.
*
* Content script → background:
* - `{ kind: "overlay.ready" }` → background decides the per-tab state first
* (see overlayStateForTab) and pushes the authoritative overlay state for
* that tab. It also proactively pushes on tab create and control-mode
* change, so a tab usually receives state before it ever sends ready.
* - `{ kind: "overlay.ready" }` → background replies with the authoritative
* overlay state for the sender's window.
* - `{ kind: "overlay.interrupt", sessionId }` → background asks the
* daemon (via a `session.user_interrupt` WS event) to cancel
* every inflight + queued tool call for that session with
-26
View File
@@ -1,26 +0,0 @@
/**
* Generate a UUID v4 in browser contexts where randomUUID() is unavailable.
*
* Crypto.randomUUID() is restricted to secure contexts, while
* crypto.getRandomValues() is available to content scripts on ordinary HTTP
* origins. BrowserSkill records many intranet pages served over HTTP, so the
* fallback is required for recording to work on those pages.
*/
export function createRandomUuid(): string {
const cryptoApi = globalThis.crypto;
if (typeof cryptoApi.randomUUID === "function") return cryptoApi.randomUUID();
const bytes = new Uint8Array(16);
cryptoApi.getRandomValues(bytes);
bytes[6] = (bytes[6]! & 0x0f) | 0x40;
bytes[8] = (bytes[8]! & 0x3f) | 0x80;
const hex = Array.from(bytes, (byte) => byte.toString(16).padStart(2, "0")).join("");
return [
hex.slice(0, 8),
hex.slice(8, 12),
hex.slice(12, 16),
hex.slice(16, 20),
hex.slice(20),
].join("-");
}
@@ -1,4 +1,3 @@
import { createRandomUuid } from "../random-uuid";
import {
isRecordFrameQueryMessage,
RECORD_FRAME_PORT,
@@ -189,7 +188,7 @@ export class RecordFrameCoordinator {
const recording = this.#recordings.get(requestId);
if (!recording) return true;
recording.finishing = true;
const commandId = createRandomUuid();
const commandId = crypto.randomUUID();
const results = await Promise.all(
[...recording.agents.values()].map((agent) => this.#stopAgent(agent, requestId, commandId)),
);
@@ -9,7 +9,7 @@ describe("disconnect session cleanup", () => {
const manager = new SessionManager({
agentWindow: {
create: vi.fn(async () => nextWindowId++),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
remove,
},
});
@@ -41,7 +41,7 @@ describe("disconnect session cleanup", () => {
const manager = new SessionManager({
agentWindow: {
create: vi.fn(async () => 100),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
remove: vi.fn(() => removeGate),
},
});
@@ -39,7 +39,7 @@ describe("attachSessionEventHandler", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await manager.start("aa11");
@@ -73,7 +73,7 @@ describe("attachSessionEventHandler", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const ctx = await manager.start("aa11");
@@ -87,7 +87,6 @@ describe("attachSessionEventHandler", () => {
windowEvents: events.api,
});
manager.forgetClosedTab(7, { isWindowClosing: true });
events.emit(4242);
for (let i = 0; i < 4; i += 1) await Promise.resolve();
@@ -114,7 +113,7 @@ describe("attachSessionEventHandler", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const transport = fakeTransport();
@@ -130,7 +129,7 @@ describe("attachSessionEventHandler", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const transport = fakeTransport();
@@ -1,6 +1,6 @@
import { describe, expect, it, vi } from "vitest";
import type { AgentWindowApi, AgentWindowCreateOptions } from "../agent-window";
import { isAgentControlledTab, SessionManager } from "../manager";
import { SessionManager } from "../manager";
function fakeAgentWindow(): AgentWindowApi & {
createMock: ReturnType<typeof vi.fn>;
@@ -13,7 +13,7 @@ function fakeAgentWindow(): AgentWindowApi & {
return id;
});
const removeMock = vi.fn(async (_id: number) => {});
const ensureActiveTabMock = vi.fn(async (_windowId: number, _url: string) => 0);
const ensureActiveTabMock = vi.fn(async (_windowId: number, _url: string) => {});
return {
create: createMock,
remove: removeMock,
@@ -151,76 +151,6 @@ describe("SessionManager", () => {
expect(sm.list()).toEqual([]);
});
describe("explicit tab claims", () => {
it("claims the exact home tab returned by AgentWindowApi", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
const ctx = await sm.start("aa11");
expect(ctx.agentCreatedTabs).toEqual(new Set([0]));
expect(isAgentControlledTab(ctx, 0)).toBe(true);
});
it("keeps every other tab free without classification state", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
const ctx = await sm.start("aa11");
expect(isAgentControlledTab(ctx, 99)).toBe(false);
expect(ctx).not.toHaveProperty("userTabs");
expect(ctx).not.toHaveProperty("pendingAgentTabCount");
});
it("treats a committed borrow as an explicit claim", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
const ctx = await sm.start("aa11");
const reservation = sm.tryReserveBorrow(42, ctx.sessionId);
if ("borrowedBy" in reservation) throw new Error("unexpected borrow conflict");
reservation.commit({ tabId: 42, originalWindowId: 7, originalIndex: 3 });
expect(isAgentControlledTab(ctx, 42)).toBe(true);
});
it("forgets an agent-created tab after Chrome removes it", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(42);
sm.forgetClosedTab(42);
expect(ctx.agentCreatedTabs.has(42)).toBe(false);
expect(isAgentControlledTab(ctx, 0)).toBe(true);
});
it("forgets closed borrows idempotently without affecting other tabs or sessions", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
const a = await sm.start("aa11");
const b = await sm.start("bb22");
a.borrowedTabs.set(42, { tabId: 42, originalWindowId: 7, originalIndex: 0 });
a.borrowedTabs.set(43, { tabId: 43, originalWindowId: 7, originalIndex: 1 });
b.borrowedTabs.set(44, { tabId: 44, originalWindowId: 8, originalIndex: 0 });
sm.forgetClosedTab(42);
sm.forgetClosedTab(42);
sm.forgetClosedTab(999);
expect(isAgentControlledTab(a, 42)).toBe(false);
expect(sm.findBorrowingSession(42, null)).toBeNull();
expect([...a.borrowedTabs.keys()]).toEqual([43]);
expect([...b.borrowedTabs.keys()]).toEqual([44]);
expect(sm.list()).toHaveLength(2);
});
it("prevents an in-flight borrow from reclaiming a closed tab", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
const ctx = await sm.start("aa11");
const reservation = sm.tryReserveBorrow(42, ctx.sessionId);
if ("borrowedBy" in reservation) throw new Error("unexpected borrow conflict");
sm.forgetClosedTab(42);
expect(() =>
reservation.commit({ tabId: 42, originalWindowId: 7, originalIndex: 0 }),
).toThrow(/reservation disappeared/);
reservation.release();
expect(sm.findBorrowingSession(42, null)).toBeNull();
expect(ctx.borrowedTabs.has(42)).toBe(false);
});
});
describe("findBorrowingSession", () => {
it("returns null when no session has borrowed the tab", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
@@ -14,11 +14,8 @@ export interface AgentWindowApi {
* Guarantee the Agent Window has an active, CDP-navigable tab.
* `chrome://` pages (including the New Tab page) reject `Page.navigate`,
* so sessions bootstrap with `about:blank` instead.
*
* Resolves with the id of the activated (or newly created) tab, so callers
* can track the session's home tab without re-querying Chrome.
*/
ensureActiveTab(windowId: number, url: string): Promise<number>;
ensureActiveTab(windowId: number, url: string): Promise<void>;
}
/** Creation hints for a new Agent Window. */
@@ -52,19 +49,15 @@ export const chromeAgentWindowApi: AgentWindowApi = {
// cancellation success while the Agent Window remains open.
await chrome.windows.remove(windowId);
},
async ensureActiveTab(windowId: number, url: string): Promise<number> {
async ensureActiveTab(windowId: number, url: string): Promise<void> {
const tabs = await chrome.tabs.query({ windowId });
const first = tabs.find((t) => typeof t.id === "number");
if (first?.id !== undefined) {
if (first?.id) {
if (!first.active) {
await chrome.tabs.update(first.id, { active: true });
}
return first.id;
return;
}
const created = await chrome.tabs.create({ windowId, url, active: true });
if (typeof created?.id !== "number") {
throw new Error("[bh] chrome.tabs.create returned no tab id");
}
return created.id;
await chrome.tabs.create({ windowId, url, active: true });
},
};
+1 -29
View File
@@ -6,20 +6,9 @@ export interface SessionContext {
agentWindowId: number;
refStore: RefStore;
borrowedTabs: Map<number, BorrowedTab>;
/**
* Tabs explicitly claimed by the agent because it created them. This
* includes the Agent Window's home tab and tabs created by `tool.tab_create`.
* Tabs opened through Chrome UI never enter this set.
*/
agentCreatedTabs: Set<number>;
createdAtMs: number;
}
/** Whether this session has explicitly claimed control of `tabId`. */
export function isAgentControlledTab(ctx: SessionContext, tabId: number): boolean {
return ctx.agentCreatedTabs.has(tabId) || ctx.borrowedTabs.has(tabId);
}
export interface BorrowedTab {
tabId: number;
originalWindowId: number;
@@ -117,19 +106,6 @@ export class SessionManager {
return Array.from(this.sessions.values());
}
/**
* Forget a tab Chrome has removed, including any uncommitted borrow.
* Whole-window closures keep committed borrows until the window-removed
* handler reports which user tabs could not be returned.
*/
forgetClosedTab(tabId: number, { isWindowClosing = false } = {}): void {
this.borrowReservations.delete(tabId);
for (const ctx of this.sessions.values()) {
ctx.agentCreatedTabs.delete(tabId);
if (!isWindowClosing) ctx.borrowedTabs.delete(tabId);
}
}
/**
* Look up whether `tabId` is currently borrowed by some *other*
* session than the one calling. Used by M8 `tab_borrow` to refuse
@@ -203,7 +179,7 @@ export class SessionManager {
const { signal: _signal, ...createOptions } = opts;
windowId = await this.agentWindow.create(AGENT_WINDOW_HOME, createOptions);
throwIfSessionStartAborted(opts.signal);
const homeTabId = await this.agentWindow.ensureActiveTab(windowId, AGENT_WINDOW_HOME);
await this.agentWindow.ensureActiveTab(windowId, AGENT_WINDOW_HOME);
throwIfSessionStartAborted(opts.signal);
const ctx: SessionContext = {
@@ -211,10 +187,6 @@ export class SessionManager {
agentWindowId: windowId,
refStore: new RefStore(),
borrowedTabs: new Map(),
// The home tab is the session's first explicit claim. Every other
// tab remains free until `tab_create` or `tab_borrow` identifies it
// by its concrete Chrome tab id.
agentCreatedTabs: new Set([homeTabId]),
createdAtMs: this.now(),
};
this.sessions.set(sessionId, ctx);
@@ -13,7 +13,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -55,7 +55,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -117,7 +117,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -140,7 +140,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create,
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -158,7 +158,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -172,47 +172,6 @@ describe("ToolDispatcher", () => {
expect(sent[0]).toEqual({ id: "r-1", result: {} });
});
it("wires the production tab APIs into tool.session_stop so a surviving user tab releases the window", async () => {
// Regression guard for the deps that session_stop reads directly: when
// `tabManagement.tabs` / `tabsQuery` are not injected by the dispatcher,
// the agent-tab cleanup and the release decision silently no-op and the
// Agent Window is closed even though a user tab is still open (issue #57).
const removeTab = vi.fn(async () => {});
const closeWindow = vi.fn(async () => {});
// After cleanup the window still holds one tab (id 99) that is neither
// the home tab nor an agent-created tab — i.e. a genuine user tab.
vi.stubGlobal("chrome", {
tabs: {
remove: removeTab,
query: vi.fn(async () => [{ id: 99, windowId: 4242, active: true }]),
},
});
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 4242),
remove: closeWindow,
ensureActiveTab: vi.fn(async () => 1),
},
});
await sessions.start("aa11");
// Register the exact tab id returned by the agent's creation path.
sessions.get("aa11")?.agentCreatedTabs.add(7);
const dispatcher = new ToolDispatcher({ transport, sessions });
dispatcher.start();
deliver(makeRequest("tool.session_stop", { session_id: "aa11" }));
await flushMicrotasks();
// The agent tab is closed through the real chrome.tabs surface...
expect(removeTab).toHaveBeenCalledWith(7);
// ...and the window is released rather than closed, so the user's tab survives.
expect(closeWindow).not.toHaveBeenCalled();
expect(sessions.has("aa11")).toBe(false);
expect(sent[0]).toEqual({ id: "r-1", result: { window_released: true } });
});
it("routes tool.console through the CDP console buffer", async () => {
vi.stubGlobal("chrome", {
tabs: {
@@ -224,7 +183,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -287,7 +246,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const ctx = await sessions.start("aa11");
@@ -380,7 +339,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -416,7 +375,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove,
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -464,7 +423,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -484,7 +443,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -508,7 +467,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -525,7 +484,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -542,7 +501,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const onSessionsChanged = vi.fn();
@@ -559,32 +518,16 @@ describe("ToolDispatcher", () => {
});
it("invokes onBrowserControlResumed for browser-control tools but not passive reads", async () => {
vi.stubGlobal("chrome", {
tabs: {
create: vi.fn(async (props: chrome.tabs.CreateProperties) => ({
id: 7,
windowId: props.windowId,
url: props.url,
active: props.active,
})),
},
});
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const onBrowserControlResumed = vi.fn();
const onAgentTabClaimed = vi.fn();
const dispatcher = new ToolDispatcher({
transport,
sessions,
onBrowserControlResumed,
onAgentTabClaimed,
});
const dispatcher = new ToolDispatcher({ transport, sessions, onBrowserControlResumed });
dispatcher.start();
deliver(makeRequest("tool.session_start", { session_id: "aa11" }));
@@ -601,7 +544,6 @@ describe("ToolDispatcher", () => {
});
await flushMicrotasks();
expect(onBrowserControlResumed).toHaveBeenCalledWith("aa11");
expect(onAgentTabClaimed).toHaveBeenCalledWith(7, 1);
});
it("reasserts remembered hover before follow-up work and releases only after actions", async () => {
@@ -615,7 +557,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const order: string[] = [];
@@ -697,7 +639,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const cdp = {
@@ -747,135 +689,6 @@ describe("ToolDispatcher", () => {
);
});
it.each([
{ tab_id: 7, code: "not_found" },
{ tab_id: undefined, code: "invalid_params" },
])("keeps hover when tab_return is rejected with $code", async ({ tab_id, code }) => {
const sendMessage = vi.fn(async () => undefined);
vi.stubGlobal("chrome", {
tabs: {
sendMessage,
get: vi.fn(async () => ({ id: 7, windowId: 100, active: true })),
query: vi.fn(async () => [{ id: 7, windowId: 100, active: true }]),
},
});
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 100),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
},
});
await sessions.start("aa11");
const cdp = {
send: vi.fn(async <T>() => ({}) as T),
detachSession: vi.fn(async () => {}),
releaseSessionTab: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({
transport,
sessions,
cdp: cdp as unknown as TestDispatcherCdp,
});
const helpers = dispatcher as unknown as {
rememberHover: (sessionId: string, result: unknown) => unknown;
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
withHoverReassert: <T>(
params: { session_id: string; tab_id?: number },
work: () => Promise<T>,
) => Promise<T>;
};
helpers.rememberHover("aa11", { tab_id: 7, x: 10, y: 20 });
await helpers.setHoverBypass("aa11", 7, true);
dispatcher.start();
deliver(makeRequest("tool.tab_return", { session_id: "aa11", tab_id }));
await vi.waitFor(() => expect(sent).toHaveLength(1));
expect(sent[0]).toMatchObject({ error: { code } });
expect(cdp.releaseSessionTab).not.toHaveBeenCalled();
expect(sendMessage).not.toHaveBeenCalledWith(7, expect.objectContaining({ enabled: false }));
await helpers.withHoverReassert({ session_id: "aa11", tab_id: 7 }, async () => ({}));
expect(cdp.send).toHaveBeenCalledExactlyOnceWith(7, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: 10,
y: 20,
});
dispatcher.stop();
});
it("releases the returned tab's hover before moving it and leaves other tabs alone", async () => {
const sendMessage = vi.fn(async () => undefined);
const move = vi.fn(async () => {
expect(sendMessage).toHaveBeenCalledWith(7, expect.objectContaining({ enabled: false }));
return { id: 7, windowId: 200, index: 4 };
});
vi.stubGlobal("chrome", {
tabs: { sendMessage, move },
windows: { get: vi.fn(async () => ({ id: 200 })) },
});
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 100),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
},
});
const ctx = await sessions.start("aa11");
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
const cdp = {
send: vi.fn(async <T>() => ({}) as T),
detachSession: vi.fn(async () => {}),
releaseSessionTab: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({
transport,
sessions,
cdp: cdp as unknown as TestDispatcherCdp,
});
const helpers = dispatcher as unknown as {
rememberHover: (sessionId: string, result: unknown) => unknown;
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
withHoverReassert: <T>(
params: { session_id: string; tab_id?: number },
work: () => Promise<T>,
) => Promise<T>;
};
for (const [sessionId, tabId] of [
["aa11", 7],
["aa11", 8],
["bb22", 9],
] as const) {
helpers.rememberHover(sessionId, { tab_id: tabId, x: 10, y: 20 });
await helpers.setHoverBypass(sessionId, tabId, true);
}
dispatcher.start();
deliver(makeRequest("tool.tab_return", { session_id: "aa11", tab_id: 7 }));
await vi.waitFor(() => expect(sent).toHaveLength(1));
expect(sent[0]).toMatchObject({ result: { tab_id: 7, returned_to_window_id: 200 } });
expect(cdp.releaseSessionTab).toHaveBeenCalledExactlyOnceWith("aa11", 7);
await helpers.withHoverReassert({ session_id: "aa11", tab_id: 7 }, async () => ({}));
expect(cdp.send).not.toHaveBeenCalled();
for (const [sessionId, tabId] of [
["aa11", 8],
["bb22", 9],
] as const) {
expect(sendMessage).not.toHaveBeenCalledWith(
tabId,
expect.objectContaining({ enabled: false }),
);
await helpers.withHoverReassert({ session_id: sessionId, tab_id: tabId }, async () => ({}));
expect(cdp.send).toHaveBeenLastCalledWith(tabId, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: 10,
y: 20,
});
}
dispatcher.stop();
});
it("transfers hover overlay bypass ownership between sessions", async () => {
vi.stubGlobal("chrome", {
tabs: {
@@ -887,7 +700,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -924,7 +737,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -976,7 +789,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -1010,7 +823,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
transport.send = () => {
@@ -1032,7 +845,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 5555),
remove,
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
transport.send = () => {
@@ -1060,7 +873,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(() => createPromise),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -1111,7 +924,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -1132,7 +945,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(() => createPromise),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
@@ -20,7 +20,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -12,7 +12,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -13,7 +13,7 @@ function sessions() {
agentWindow: {
create: vi.fn(async () => 100),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
}
@@ -1,573 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import { SessionManager } from "@/session-manager/manager";
import type { CdpRunner } from "@/tools/shared";
import { handleFill } from "../interaction";
interface ScriptParams {
functionDeclaration: string;
arguments?: Array<{ value: unknown }>;
}
async function setup(markup = '<input value="old">') {
document.body.innerHTML = markup;
const element = document.body.firstElementChild as HTMLInputElement;
const manager = new SessionManager({
agentWindow: {
create: async () => 100,
remove: async () => {},
ensureActiveTab: async () => 4,
},
});
const ctx = await manager.start("aa11");
ctx.refStore.set("e1", 12, { tabId: 4 });
const script = vi.fn(async (params: ScriptParams): Promise<unknown> => {
try {
const fn = new Function(`return (${params.functionDeclaration})`)();
return {
result: {
value: await fn.apply(
element,
(params.arguments ?? []).map((arg) => arg.value),
),
},
};
} catch {
return { exceptionDetails: { text: "test page script failed" } };
}
});
// Number/email controls have a browser caret even though their selection
// getters return null. Model that caret instead of assuming it is at the end.
const hiddenCaret = { start: 0, end: 0 };
const moveToEnd = vi.fn(async () => {
if (typeof element.selectionStart === "number") {
element.setSelectionRange(element.value.length, element.value.length);
} else {
hiddenCaret.start = hiddenCaret.end = element.value.length;
}
});
const insert = vi.fn(async (text: string) => {
const focused = document.activeElement as HTMLInputElement;
if (focused.readOnly || focused.disabled) return;
const start = focused.selectionStart ?? hiddenCaret.start;
const end = focused.selectionEnd ?? hiddenCaret.end;
const value = focused.value.slice(0, start) + text + focused.value.slice(end);
focused.value = focused.maxLength >= 0 ? value.slice(0, focused.maxLength) : value;
hiddenCaret.start = hiddenCaret.end = Math.min(start + text.length, focused.value.length);
focused.dispatchEvent(new Event("input", { bubbles: true }));
});
const release = vi.fn(async () => ({}));
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
switch (method) {
case "DOM.describeNode":
return {
node: {
nodeName: element.tagName,
attributes: Array.from(element.attributes).flatMap((attr) => [attr.name, attr.value]),
},
};
case "DOM.scrollIntoViewIfNeeded":
return {};
case "DOM.focus":
element.focus();
return {};
case "DOM.resolveNode":
return { object: { objectId: "fill-target" } };
case "Runtime.callFunctionOn":
return script(params as ScriptParams);
case "Input.insertText":
await insert((params as { text: string }).text);
return {};
case "Input.dispatchKeyEvent":
if ((params as { commands?: string[] }).commands?.includes("moveToEndOfDocument")) {
await moveToEnd();
}
return {};
case "Runtime.releaseObject":
return release();
default:
throw new Error(`unexpected ${method}`);
}
});
return {
element,
hiddenCaret,
moveToEnd,
script,
insert,
release,
send,
fill: (value = "hello", clearBefore = true, signal?: AbortSignal) =>
handleFill(
manager,
{ session_id: "aa11", ref: "e1", value, clear_before: clearBefore },
{
cdp: { send: send as CdpRunner["send"] },
tabsApi: {
get: async (id) => ({ id, windowId: 100, active: true }) as chrome.tabs.Tab,
query: async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab],
},
signal,
},
),
};
}
afterEach(() => {
vi.restoreAllMocks();
document.body.innerHTML = "";
});
describe("fill result verification", () => {
it.each([
"readonly",
"disabled",
])("preserves a %s field before rejecting it", async (attribute) => {
const h = await setup(`<input ${attribute} value="old">`);
expect(await h.fill()).toMatchObject({
code: "invalid_params",
data: { reason: "target_not_fillable" },
});
expect(h.element.value).toBe("old");
expect(h.insert).not.toHaveBeenCalled();
expect(h.release).toHaveBeenCalledOnce();
});
it.each([
"checkbox",
"radio",
"range",
"date",
"file",
])("rejects an unsupported %s input before clearing", async (type) => {
const h = await setup(`<input type="${type}">`);
const before = h.element.value;
expect(await h.fill()).toMatchObject({
code: "invalid_params",
data: { reason: "target_not_fillable" },
});
expect(h.element.value).toBe(before);
expect(h.insert).not.toHaveBeenCalled();
});
it("rejects an overlong value before clearing", async () => {
const h = await setup('<input maxlength="3" value="old">');
expect(await h.fill()).toMatchObject({
code: "invalid_params",
message: /maxlength/,
data: { reason: "fill_value_invalid" },
});
expect(h.element.value).toBe("old");
expect(h.insert).not.toHaveBeenCalled();
});
it.each([
true,
false,
])("classifies a DOM.focus rejection on a disabled=%s target", async (disabled) => {
const h = await setup(`<input ${disabled ? "disabled" : ""} value="old">`);
const send = h.send.getMockImplementation()!;
h.send.mockImplementation(async (tabId, method, params) => {
if (method === "DOM.focus") throw new Error("Element is not focusable");
return send(tabId, method, params);
});
expect(await h.fill()).toMatchObject({
code: disabled ? "invalid_params" : "cdp_failed",
data: { reason: disabled ? "target_not_fillable" : "fill_failed" },
});
expect(h.element.value).toBe("old");
expect(h.insert).not.toHaveBeenCalled();
expect(h.release).toHaveBeenCalledOnce();
});
it("fills a background document without requiring foreground browser focus", async () => {
const h = await setup();
vi.spyOn(document, "hasFocus").mockReturnValue(false);
expect(await h.fill()).toMatchObject({ value_length: 5 });
expect(h.element.value).toBe("hello");
});
it("restores focus once after clearing without typing into another field", async () => {
const h = await setup();
const other = document.createElement("input");
document.body.append(other);
h.element.addEventListener("input", () => other.focus());
expect(await h.fill()).toMatchObject({ value_length: 5 });
expect(h.element.value).toBe("hello");
expect(other.value).toBe("");
expect(h.send.mock.calls.filter(([, method]) => method === "DOM.focus")).toHaveLength(2);
});
it.each([
"focus",
"value",
])("rechecks %s after restoring focus, without retrying again", async (action) => {
const h = await setup();
const other = document.createElement("input");
document.body.append(other);
h.element.addEventListener(
"input",
() => {
other.focus();
h.element.addEventListener("focus", () => {
if (action === "focus") queueMicrotask(() => other.focus());
else h.element.value = "changed";
});
},
{ once: true },
);
expect(await h.fill()).toMatchObject({
code: "cdp_failed",
data: { reason: action === "focus" ? "fill_focus_lost" : "fill_target_changed" },
});
expect(other.value).toBe("");
expect(h.insert).not.toHaveBeenCalled();
expect(h.send.mock.calls.filter(([, method]) => method === "DOM.focus")).toHaveLength(2);
});
it.each([
"remove",
"readonly",
"restore",
"microtask-restore",
])("stops when clearing causes the page to %s the target", async (action) => {
const h = await setup();
h.element.addEventListener("input", () => {
if (action === "remove") h.element.remove();
if (action === "readonly") h.element.readOnly = true;
if (action === "restore") h.element.value = "restored";
if (action === "microtask-restore")
queueMicrotask(() => {
h.element.value = "restored";
});
});
expect(await h.fill()).toMatchObject({
code: "cdp_failed",
data: { reason: "fill_target_changed" },
});
expect(h.insert).not.toHaveBeenCalled();
});
it("fails when insertText is acknowledged without changing the value", async () => {
const h = await setup();
h.insert.mockImplementation(async () => {});
expect(await h.fill()).toMatchObject({
code: "cdp_failed",
data: { reason: "fill_value_mismatch" },
});
expect(h.release).toHaveBeenCalledOnce();
});
it("detects truncation when maxlength changes after preparation", async () => {
const h = await setup();
h.element.addEventListener(
"input",
() => {
h.element.maxLength = 3;
},
{ once: true },
);
expect(await h.fill()).toMatchObject({
code: "cdp_failed",
data: { reason: "fill_value_mismatch" },
});
expect(h.element.value).toBe("hel");
});
it.each([
"input",
"change",
"microtask-change",
])("detects a value reverted by the %s handler", async (event) => {
const h = await setup();
h.element.addEventListener(event === "microtask-change" ? "change" : event, () => {
if (event === "microtask-change")
queueMicrotask(() => {
h.element.value = "";
});
else h.element.value = "";
});
expect(await h.fill()).toMatchObject({ code: "cdp_failed", message: /expected value/ });
});
it("compares content rather than length without including field values in the error", async () => {
const h = await setup('<input type="password">');
h.element.addEventListener("change", () => {
h.element.value = "other-secret";
});
const result = await h.fill("given-secret");
expect(result).toMatchObject({ code: "cdp_failed", message: /expected value/ });
expect(JSON.stringify(result)).not.toMatch(/given-secret|other-secret/);
});
it("does not report success for a target replaced by a change handler", async () => {
const h = await setup();
h.element.addEventListener("change", () => h.element.replaceWith(h.element.cloneNode()));
expect(await h.fill()).toMatchObject({
code: "cdp_failed",
data: { reason: "fill_target_changed" },
});
});
it.each([
1, 2, 3, 4, 5,
])("rejects script exceptions at phase %s and releases the target", async (phase) => {
const h = await setup();
vi.spyOn(document, "hasFocus").mockReturnValue(false);
const run = h.script.getMockImplementation()!;
let count = 0;
h.script.mockImplementation(async (params) =>
++count === phase ? { exceptionDetails: { text: "page secret" } } : run(params),
);
const result = await h.fill();
expect(result).toMatchObject({ code: "cdp_failed", data: { reason: "fill_failed" } });
expect(JSON.stringify(result)).not.toContain("page secret");
if (phase <= 3) expect(h.insert).not.toHaveBeenCalled();
expect(h.release).toHaveBeenCalledOnce();
});
it.each([1, 2, 3, 5])("rejects missing results at phase %s", async (phase) => {
const h = await setup();
vi.spyOn(document, "hasFocus").mockReturnValue(false);
const run = h.script.getMockImplementation()!;
let count = 0;
h.script.mockImplementation(async (params) =>
++count === phase ? { result: { type: "undefined" } } : run(params),
);
expect(await h.fill()).toMatchObject({ code: "cdp_failed" });
if (phase <= 3) expect(h.insert).not.toHaveBeenCalled();
});
it.each(["input", "change"])("checks state after nested microtasks from %s", async (event) => {
const h = await setup();
h.element.addEventListener(event, () => {
queueMicrotask(() =>
queueMicrotask(() => {
h.element.value = "reverted";
}),
);
});
expect(await h.fill()).toMatchObject({ code: "cdp_failed" });
if (event === "input") expect(h.insert).not.toHaveBeenCalled();
});
it.each([
"<input>",
'<input type="password">',
"<textarea></textarea>",
])("verifies successful text in %s", async (markup) => {
const h = await setup(markup);
expect(await h.fill("你好🙂")).toMatchObject({ value_length: 4 });
expect(h.element.value).toBe("你好🙂");
expect(h.release).toHaveBeenCalledOnce();
});
it("verifies append against the old value plus the requested text", async () => {
const h = await setup();
h.element.focus();
h.element.setSelectionRange(3, 3);
expect(await h.fill("!", false)).toMatchObject({ value_length: 4 });
expect(h.element.value).toBe("old!");
});
it.each([
["<textarea></textarea>", "a\r\nb", "a\nb"],
["<input>", "a\nb", "a b"],
["<input>", "a\r\nb", "a b"],
[
'<input type="email" multiple>',
" a@example.com , b@example.com ",
"a@example.com,b@example.com",
],
])("accepts native normalization for %s", async (markup, requested, normalized) => {
if (markup.startsWith("<textarea")) {
// Happy DOM does not implement Chrome's textarea line-ending normalization.
const setter = Object.getOwnPropertyDescriptor(HTMLTextAreaElement.prototype, "value")!.set!;
vi.spyOn(HTMLTextAreaElement.prototype, "value", "set").mockImplementation(function (
this: HTMLTextAreaElement,
value,
) {
setter.call(this, value.replace(/\r\n?/g, "\n"));
});
}
const h = await setup(markup);
h.insert.mockImplementation(async () => {
h.element.value = normalized;
});
expect(await h.fill(requested)).toMatchObject({ value_length: normalized.length });
});
it("does not count an editable padding break as an extra typed character", async () => {
const h = await setup('<div contenteditable="true" tabindex="0"></div>');
// These two layout/editability properties are missing in Happy DOM.
let innerText = "";
Object.defineProperty(h.element, "isContentEditable", { get: () => true });
Object.defineProperty(h.element, "innerText", { get: () => innerText });
h.insert.mockImplementation(async () => {
h.element.innerHTML = "one<div><br></div>";
innerText = "one\n\n";
});
expect(await h.fill("one\n")).toMatchObject({ value_length: 4 });
});
it.each([
[0, 0],
[1, 1],
[0, 3],
])("appends after moving selection %s:%s to the end", async (start, end) => {
const h = await setup();
h.element.focus();
h.element.setSelectionRange(start, end);
expect(await h.fill("🙂", false)).toMatchObject({ value_length: 5 });
expect(h.element.value).toBe("old🙂");
});
it.each(
["number", "email"].flatMap((type) =>
[
[0, 0],
[1, 1],
[0, 2],
].map(([start, end]) => ({ type, start, end })),
),
)("appends to $type from selection $start:$end without using its unsupported API", async ({
type,
start,
end,
}) => {
const h = await setup(`<input type="${type}" value="12">`);
Object.assign(h.hiddenCaret, { start, end });
vi.spyOn(h.element, "selectionStart", "get").mockReturnValue(null);
vi.spyOn(h.element, "selectionEnd", "get").mockReturnValue(null);
const selection = vi.spyOn(h.element, "setSelectionRange").mockImplementation(() => {
throw new DOMException("unsupported", "InvalidStateError");
});
expect(await h.fill("3", false)).toMatchObject({ value_length: 3 });
expect(h.element.value).toBe("123");
expect(selection).not.toHaveBeenCalled();
});
it.each([
"number",
"email",
])("does not report successful %s append when the caret command is ignored", async (type) => {
const h = await setup(`<input type="${type}" value="12">`);
vi.spyOn(h.element, "selectionStart", "get").mockReturnValue(null);
vi.spyOn(h.element, "selectionEnd", "get").mockReturnValue(null);
h.moveToEnd.mockResolvedValueOnce(undefined);
expect(await h.fill("3", false)).toMatchObject({
code: "cdp_failed",
data: { reason: "fill_value_mismatch" },
});
expect(h.element.value).toBe("312");
expect(h.insert).toHaveBeenCalledOnce();
});
it("rejects invalid number text before clearing", async () => {
const h = await setup('<input type="number" value="12">');
expect(await h.fill("abc")).toMatchObject({
code: "invalid_params",
data: { reason: "fill_value_invalid" },
});
expect(h.element.value).toBe("12");
expect(h.insert).not.toHaveBeenCalled();
});
it("reports page formatting as unconfirmed without retrying the write", async () => {
const h = await setup();
h.element.addEventListener("change", () => {
h.element.value = h.element.value.toUpperCase();
});
expect(await h.fill()).toMatchObject({
code: "cdp_failed",
data: { reason: "fill_value_mismatch" },
});
expect(h.element.value).toBe("HELLO");
expect(h.insert).toHaveBeenCalledOnce();
});
it.each([
["focus", false],
["focus", true],
["value", false],
["value", true],
["cancel", false],
["cancel", true],
["throw", false],
["throw", true],
] as const)("stops when positioning triggers %s (clear=%s) and releases the key", async (action, clearBefore) => {
const h = await setup();
vi.spyOn(document, "hasFocus").mockReturnValue(false);
const controller = new AbortController();
const other = document.createElement("input");
document.body.append(other);
const send = h.send.getMockImplementation()!;
h.send.mockImplementation(async (tabId, method, params) => {
const reply = await send(tabId, method, params);
if (
method === "Input.dispatchKeyEvent" &&
(params as { type: string }).type === "rawKeyDown"
) {
if (action === "focus") other.focus();
if (action === "value") h.element.value = "changed";
if (action === "cancel") controller.abort();
if (action === "throw") throw new Error("dispatch failed");
}
return reply;
});
const result = await h.fill("!", clearBefore, controller.signal);
expect(result).toMatchObject({ code: action === "cancel" ? "cancelled" : "cdp_failed" });
expect(h.insert).not.toHaveBeenCalled();
expect(other.value).toBe("");
expect(h.send).toHaveBeenCalledWith(
4,
"Input.dispatchKeyEvent",
expect.objectContaining({ type: "keyUp" }),
);
expect(h.release).toHaveBeenCalledOnce();
});
it.each([true, false])("verifies an empty request with clear_before=%s", async (clearBefore) => {
const h = await setup();
expect(await h.fill("", clearBefore)).toMatchObject({ value_length: clearBefore ? 0 : 3 });
expect(h.element.value).toBe(clearBefore ? "" : "old");
expect(h.insert).not.toHaveBeenCalled();
});
it("cancels after insertion without sending change events", async () => {
const h = await setup();
const controller = new AbortController();
h.insert.mockImplementation(async () => controller.abort());
expect(await h.fill("hello", true, controller.signal)).toMatchObject({ code: "cancelled" });
expect(h.script).toHaveBeenCalledTimes(2);
expect(h.release).toHaveBeenCalledOnce();
});
it("cancels after resolving the remote object without clearing the field", async () => {
const h = await setup();
const controller = new AbortController();
const send = h.send.getMockImplementation()!;
h.send.mockImplementation(async (tabId, method, params) => {
const result = await send(tabId, method, params);
if (method === "DOM.resolveNode") controller.abort();
return result;
});
expect(await h.fill("hello", true, controller.signal)).toMatchObject({ code: "cancelled" });
expect(h.element.value).toBe("old");
expect(h.script).not.toHaveBeenCalled();
expect(h.release).toHaveBeenCalledOnce();
});
it("honors cancellation during verification", async () => {
const h = await setup();
const controller = new AbortController();
h.element.addEventListener("change", () => controller.abort());
expect(await h.fill("hello", true, controller.signal)).toMatchObject({ code: "cancelled" });
expect(h.release).toHaveBeenCalledOnce();
});
it("keeps the verified outcome when releasing the remote object fails", async () => {
const h = await setup();
h.release.mockRejectedValueOnce(new Error("target closed"));
expect(await h.fill()).toMatchObject({ value_length: 5 });
});
});
@@ -21,7 +21,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -540,21 +540,6 @@ describe("handleHover", () => {
});
});
function successfulFillScript(params: unknown) {
const script = params as { arguments?: Array<{ value: unknown }>; functionDeclaration: string };
const args = script.arguments ?? [];
return {
result: {
value:
args.length === 2
? { before: "", expected: args[0].value }
: script.functionDeclaration.startsWith("function(expected)")
? { connected: true, matches: true, valueLength: String(args[0].value).length }
: "ready",
},
};
}
describe("handleFill", () => {
it("returns not_found for unknown ref", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
@@ -601,8 +586,7 @@ describe("handleFill", () => {
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.focus": () => ({}),
"DOM.resolveNode": () => ({ object: { objectId: "obj-1" } }),
"Runtime.callFunctionOn": successfulFillScript,
"Runtime.releaseObject": () => ({}),
"Runtime.callFunctionOn": () => ({ result: { type: "undefined" } }),
"Input.insertText": () => ({}),
});
const res = await handleFill(
@@ -616,12 +600,13 @@ describe("handleFill", () => {
expect(res.used_ref).toBe("e1");
const insert = fake.sent.find((c) => c.method === "Input.insertText");
expect(insert?.params).toEqual({ text: "hello" });
// Foreground replacement needs no extra caret-positioning round trip.
// clear_before defaults to true → callFunctionOn invoked once to
// clear, once to fire input/change after typing.
const callFns = fake.sent.filter((c) => c.method === "Runtime.callFunctionOn");
expect(callFns).toHaveLength(4);
expect(callFns.length).toBeGreaterThanOrEqual(2);
});
it("passes clear_before=false to preparation and verifies the result", async () => {
it("clear_before=false skips the wipe call", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e1", 1, { tabId: 4 });
@@ -633,12 +618,12 @@ describe("handleFill", () => {
"DOM.focus": () => ({}),
"DOM.resolveNode": () => ({ object: { objectId: "obj-2" } }),
"Runtime.callFunctionOn": (p) => {
const args = (p as { arguments?: Array<{ value: unknown }> }).arguments ?? [];
if (args.length === 2) expect(args[1].value).toBe(false);
return successfulFillScript(p);
const fn = (p as { functionDeclaration?: string }).functionDeclaration ?? "";
// No "this.value = ''" clearing on a no-clear path; only the
// post-input dispatchEvent.
expect(fn).not.toMatch(/this\.value\s*=\s*''/);
return { result: { type: "undefined" } };
},
"Input.dispatchKeyEvent": () => ({}),
"Runtime.releaseObject": () => ({}),
"Input.insertText": () => ({}),
});
const res = await handleFill(
@@ -665,8 +650,7 @@ describe("handleFill", () => {
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.focus": () => ({}),
"DOM.resolveNode": () => ({ object: { objectId: "obj-3" } }),
"Runtime.callFunctionOn": successfulFillScript,
"Runtime.releaseObject": () => ({}),
"Runtime.callFunctionOn": () => ({ result: { type: "undefined" } }),
"Input.insertText": () => ({}),
});
const res = await handleFill(
@@ -21,7 +21,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -12,7 +12,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -28,7 +28,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -1,26 +1,8 @@
import { describe, expect, it, vi } from "vitest";
import { SessionManager } from "@/session-manager/manager";
import { handleSessionStop } from "../session";
import type { ChromeTabsApi } from "../shared";
import { type AgentOverlayResetApi, type ChromeWindowsApi, type TabMutationApi } from "../tabs";
/** Build a read-only query api over a FakeState. */
function makeQuery(state: FakeState): ChromeTabsApi {
return {
get: vi.fn(async (id) => {
const t = state.tabs.get(id);
if (!t) throw new Error(`tab ${id} not found`);
return t;
}),
query: vi.fn(async (q: chrome.tabs.QueryInfo) => {
const w = q.windowId;
return Array.from(state.tabs.values()).filter(
(t) => typeof w !== "number" || t.windowId === w,
);
}),
};
}
function fakeAgentWindow(ids: number[]) {
let i = 0;
const create = vi.fn(async () => {
@@ -29,7 +11,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
});
const remove = vi.fn(async () => {});
const ensureActiveTab = vi.fn(async () => 0);
const ensureActiveTab = vi.fn(async () => {});
return { create, remove, ensureActiveTab };
}
@@ -48,9 +30,7 @@ function makeApis(
} {
const tabs: TabMutationApi = {
create: vi.fn(),
remove: vi.fn(async (id: number) => {
state.tabs.delete(id);
}),
remove: vi.fn(async () => {}),
update: vi.fn(async (_id, _p) => undefined),
get: vi.fn(async (id) => {
const t = state.tabs.get(id);
@@ -257,15 +237,11 @@ describe("handleSessionStop with auto-return", () => {
moves: [],
};
const { tabs, windows } = makeApis(state, { moveThrowsFor: new Set([1]) });
const cdp = {
detachSession: vi.fn(async () => {}),
releaseSessionTab: vi.fn(async () => {}),
};
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ cdp, tabManagement: { tabs, windows } },
{ tabManagement: { tabs, windows } },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.return_failures?.map((f) => f.tab_id)).toEqual([1]);
@@ -273,8 +249,6 @@ describe("handleSessionStop with auto-return", () => {
expect(sm.has("aa11")).toBe(true);
expect(ctx.borrowedTabs.has(1)).toBe(true);
expect(ctx.borrowedTabs.has(2)).toBe(false);
expect(cdp.releaseSessionTab).toHaveBeenCalledExactlyOnceWith("aa11", 2);
expect(cdp.detachSession).not.toHaveBeenCalled();
expect(aw.remove).not.toHaveBeenCalled();
});
@@ -293,275 +267,4 @@ describe("handleSessionStop with auto-return", () => {
await handleSessionStop(sm, { session_id: "aa11" }, { tabManagement: { tabs, windows } });
expect(ctx.refStore.isEmpty()).toBe(true);
});
it.each([
"before teardown",
"during its return",
"after its return failed",
"before its turn in the return loop",
])("finishes stopping when a borrowed tab closes %s", async (timing) => {
const aw = fakeAgentWindow([100]);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.borrowedTabs.set(1, { tabId: 1, originalWindowId: 200, originalIndex: 0 });
ctx.borrowedTabs.set(2, { tabId: 2, originalWindowId: 200, originalIndex: 1 });
const state: FakeState = {
tabs: new Map([
[1, { id: 1, windowId: 100 } as chrome.tabs.Tab],
[2, { id: 2, windowId: 100 } as chrome.tabs.Tab],
]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
const cdp = { detachSession: vi.fn(async () => {}) };
const closeTab = (tabId: number) => {
state.tabs.delete(tabId);
sm.forgetClosedTab(tabId);
};
const baseMove = tabs.move;
tabs.move = vi.fn(async (tabId, props) => {
if (tabId === 1 && timing === "during its return") closeTab(1);
if (tabId === 1 && timing === "after its return failed") {
throw new Error("simulated move failure");
}
if (tabId === 2 && timing === "after its return failed") closeTab(1);
if (tabId === 1 && timing === "before its turn in the return loop") closeTab(2);
if (!state.tabs.has(tabId)) throw new Error(`tab ${tabId} not found`);
return baseMove(tabId, props);
});
if (timing === "before teardown") closeTab(1);
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{
cdp,
tabManagement: {
tabs,
windows,
agentOverlayReset: { resetAgentOverlays: vi.fn(async () => {}) },
},
tabsQuery: makeQuery(state),
},
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
const closedTabId = timing === "before its turn in the return loop" ? 2 : 1;
expect(res.returned_tab_ids).toEqual([closedTabId === 1 ? 2 : 1]);
expect(res.return_failures).toBeUndefined();
expect(ctx.borrowedTabs.size).toBe(0);
expect(sm.has("aa11")).toBe(false);
expect(cdp.detachSession).toHaveBeenCalledWith("aa11");
expect(aw.remove).toHaveBeenCalledWith(100);
if (timing === "before teardown" || timing === "before its turn in the return loop") {
expect(tabs.move).not.toHaveBeenCalledWith(closedTabId, expect.anything());
}
});
});
describe("handleSessionStop window release (issue #57)", () => {
const agentWindowId = 100;
it("releases the window when user-created tabs remain", async () => {
const aw = fakeAgentWindow([agentWindowId]);
// ensureActiveTab returns the home tab id (10). We override the fake to
// return a known id.
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(11);
ctx.agentCreatedTabs.add(12);
// user tab 99 (created via Chrome UI, NOT in agentCreatedTabs)
const state: FakeState = {
tabs: new Map([
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
[12, { id: 12, windowId: agentWindowId } as chrome.tabs.Tab],
[99, { id: 99, windowId: agentWindowId } as chrome.tabs.Tab],
]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
const query = makeQuery(state);
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ tabManagement: { tabs, windows }, tabsQuery: query },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.window_released).toBe(true);
// agent tabs + home removed, user tab 99 kept
expect((tabs.remove as ReturnType<typeof vi.fn>).mock.calls.map((c) => c[0]).sort()).toEqual([
10, 11, 12,
]);
expect(state.tabs.has(99)).toBe(true);
// window released (dropOnly), not closed
expect(aw.remove).not.toHaveBeenCalled();
expect(sm.has("aa11")).toBe(false);
});
it("closes the window (not release) when no user tabs remain", async () => {
const aw = fakeAgentWindow([agentWindowId]);
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(11);
const state: FakeState = {
tabs: new Map([
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
const query = makeQuery(state);
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ tabManagement: { tabs, windows }, tabsQuery: query },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.window_released).toBeFalsy();
expect(aw.remove).toHaveBeenCalledWith(agentWindowId);
expect(sm.has("aa11")).toBe(false);
});
it("is non-fatal when an agent tab is already gone", async () => {
const aw = fakeAgentWindow([agentWindowId]);
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(11); // no longer in state → remove throws
const state: FakeState = {
tabs: new Map([[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab]]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
(tabs.remove as ReturnType<typeof vi.fn>).mockImplementation(async (id: number) => {
if (id === 11) throw new Error("tab 11 already closed");
state.tabs.delete(id); // home (10) removed normally
});
const query = makeQuery(state);
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ tabManagement: { tabs, windows }, tabsQuery: query },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
// user tab 10? no — 10 is home, removed. window would be empty → close.
expect(res.window_released).toBeFalsy();
expect(aw.remove).toHaveBeenCalled();
});
it("degrades to close-window when tabsQuery is missing", async () => {
const aw = fakeAgentWindow([agentWindowId]);
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(11);
const state: FakeState = {
tabs: new Map([
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ tabManagement: { tabs, windows } }, // no tabsQuery
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
// No query available → conservatively close the window.
expect(res.window_released).toBeFalsy();
expect(aw.remove).toHaveBeenCalledWith(agentWindowId);
});
it("degrades to close-window when tabsQuery.query throws", async () => {
const aw = fakeAgentWindow([agentWindowId]);
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(11);
const state: FakeState = {
tabs: new Map([[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab]]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
const query = makeQuery(state);
(query.query as ReturnType<typeof vi.fn>).mockImplementation(async () => {
throw new Error("query failed");
});
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ tabManagement: { tabs, windows }, tabsQuery: query },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.window_released).toBeFalsy();
expect(aw.remove).toHaveBeenCalled();
});
it("tracks agentCreatedTabs across tab_create / tab_close", async () => {
const aw = fakeAgentWindow([agentWindowId]);
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
// Simulate handleTabCreate adding, then handleTabClose removing.
ctx.agentCreatedTabs.add(11);
expect(ctx.agentCreatedTabs.has(11)).toBe(true);
ctx.agentCreatedTabs.delete(11); // as handleTabClose does on success
expect(ctx.agentCreatedTabs.has(11)).toBe(false);
// Unknown id delete is a safe no-op (user-closed tab).
expect(() => ctx.agentCreatedTabs.delete(999)).not.toThrow();
});
it("closes the window (not release) when an agent tab fails to close", async () => {
// Regression: a leaked agent tab (still in agentCreatedTabs, but
// still present because Step 4 remove() threw) must NOT be mistaken
// for a user tab. Otherwise the window would be released (dropOnly)
// and the agent tab would leak (issue #57 regression).
const aw = fakeAgentWindow([agentWindowId]);
aw.ensureActiveTab = vi.fn(async () => 10);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
ctx.agentCreatedTabs.add(11); // Step 4 remove() will throw for this tab
const state: FakeState = {
tabs: new Map([
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
]),
windowsClosed: new Set(),
moves: [],
};
const { tabs, windows } = makeApis(state);
(tabs.remove as ReturnType<typeof vi.fn>).mockImplementation(async (id: number) => {
if (id === 11) throw new Error("tab 11 failed to close");
state.tabs.delete(id); // home (10) removed normally; 11 lingers
});
const query = makeQuery(state);
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ tabManagement: { tabs, windows }, tabsQuery: query },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
// The leaked agent tab must NOT keep the window open.
expect(res.window_released).toBeFalsy();
expect(aw.remove).toHaveBeenCalledWith(agentWindowId);
expect(sm.has("aa11")).toBe(false);
});
});
@@ -12,7 +12,7 @@ function fakeAgentWindow() {
return {
create: vi.fn(async () => 100),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -11,7 +11,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
},
remove: async () => {},
ensureActiveTab: async () => 1,
ensureActiveTab: async () => {},
};
}
+1 -181
View File
@@ -1,7 +1,5 @@
import { describe, expect, it, vi } from "vitest";
import { type CdpDebuggerApi, ChromiumCdp } from "@/browser-driver/chromium-cdp";
import { SessionManager } from "@/session-manager/manager";
import { handleHover } from "../interaction";
import {
type AgentOverlayResetApi,
type ChromeWindowsApi,
@@ -25,7 +23,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -223,7 +221,6 @@ describe("handleTabCreate", () => {
active: true,
});
expect(res).toMatchObject({ tab_id: 10, window_id: 100 });
expect(sm.get("aa11")?.agentCreatedTabs.has(10)).toBe(true);
});
it("forwards explicit url + index + active=false", async () => {
@@ -259,41 +256,6 @@ describe("handleTabCreate", () => {
const res = await handleTabCreate(sm, { session_id: "aa11", index: -1 }, { tabs: api });
expect(res).toMatchObject({ code: "invalid_params" });
});
it("does not claim any tab when chrome.tabs.create fails", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
const state: FakeTabState = { tabs: new Map(), nextTabId: 10, windowsClosed: new Set() };
const { api, spies } = makeTabMutationApi(state);
spies.create.mockRejectedValueOnce(new Error("chrome.tabs.create failed"));
const res = await handleTabCreate(sm, { session_id: "aa11" }, { tabs: api });
expect(res).toMatchObject({ code: "protocol_error" });
expect(sm.get("aa11")?.agentCreatedTabs).toEqual(new Set([1]));
});
it("claims the returned id even when a user tab appears during tab creation", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
const state: FakeTabState = { tabs: new Map(), nextTabId: 10, windowsClosed: new Set() };
const { api, spies } = makeTabMutationApi(state);
let resolveCreate!: (tab: chrome.tabs.Tab) => void;
const createResult = new Promise<chrome.tabs.Tab>((resolve) => {
resolveCreate = resolve;
});
spies.create.mockImplementationOnce(() => createResult);
const pending = handleTabCreate(sm, { session_id: "aa11" }, { tabs: api });
// A user can create an unrelated same-window tab while Chrome is still
// resolving the agent request. There is no pending slot for it to steal.
expect(ctx.agentCreatedTabs.has(99)).toBe(false);
resolveCreate({ id: 10, windowId: 100, active: true } as chrome.tabs.Tab);
await expect(pending).resolves.toMatchObject({ tab_id: 10 });
expect(ctx.agentCreatedTabs.has(10)).toBe(true);
expect(ctx.agentCreatedTabs.has(99)).toBe(false);
});
});
describe("handleTabClose", () => {
@@ -549,148 +511,6 @@ describe("handleTabBorrow", () => {
});
describe("handleTabReturn", () => {
it.each([
"not_found",
"cdp_failed",
])("detaches after selector resolution fails with %s", async (code) => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
const state: FakeTabState = {
tabs: new Map([[7, { id: 7, windowId: 100 } as chrome.tabs.Tab]]),
nextTabId: 50,
windowsClosed: new Set(),
};
const { api } = makeTabMutationApi(state);
const { api: windows } = makeWindowsApi(state);
const debuggerApi = {
attach: vi.fn(async () => {}),
detach: vi.fn(async () => {}),
sendCommand: vi.fn(async (_target: unknown, method: string) => {
if (method === "DOM.getDocument") return { root: { nodeId: 1 } };
if (method === "DOM.querySelector") {
if (code === "cdp_failed") throw new Error("selector query failed");
return { nodeId: 0 };
}
return {};
}),
onEvent: { addListener: vi.fn(), removeListener: vi.fn() },
onDetach: { addListener: vi.fn(), removeListener: vi.fn() },
};
const cdp = new ChromiumCdp(debuggerApi as unknown as CdpDebuggerApi);
const hover = await handleHover(
sm,
{ session_id: "aa11", tab_id: 7, selector: "#missing" },
{
cdp,
tabsApi: { get: api.get, query: vi.fn(async () => []) },
},
);
expect(hover).toMatchObject({ code });
expect(cdp.isAttached(7)).toBe(true);
const returned = await handleTabReturn(
sm,
{ session_id: "aa11", tab_id: 7 },
{
tabs: api,
windows,
cdp,
agentOverlayReset: { resetAgentOverlays: vi.fn(async () => {}) },
},
);
expect(returned).toMatchObject({ returned_to_window_id: 200 });
expect(ctx.borrowedTabs.has(7)).toBe(false);
expect(cdp.isAttached(7)).toBe(false);
expect(debuggerApi.detach).toHaveBeenCalledExactlyOnceWith({ tabId: 7 });
cdp.dispose();
});
it("honours cancellation while preparing a validated return", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
const state: FakeTabState = {
tabs: new Map([[7, { id: 7, windowId: 100 } as chrome.tabs.Tab]]),
nextTabId: 50,
windowsClosed: new Set(),
};
const { api, spies } = makeTabMutationApi(state);
const { api: windows } = makeWindowsApi(state);
const controller = new AbortController();
const beforeReturn = vi.fn(async () => {
controller.abort();
});
const result = await handleTabReturn(
sm,
{ session_id: "aa11", tab_id: 7 },
{
tabs: api,
windows,
signal: controller.signal,
beforeReturn,
},
);
expect(result).toMatchObject({ code: "cancelled" });
expect(beforeReturn).toHaveBeenCalledExactlyOnceWith("aa11", 7);
expect(spies.move).not.toHaveBeenCalled();
expect(ctx.borrowedTabs.has(7)).toBe(true);
});
it.each([
"original",
"fallback",
"cleanup_failed",
"failed",
"cancelled",
])("releases CDP only after a successful return (%s)", async (mode) => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
const state: FakeTabState = {
tabs: new Map([[7, { id: 7, windowId: 100 } as chrome.tabs.Tab]]),
nextTabId: 50,
windowsClosed: new Set(),
};
const { api, spies } = makeTabMutationApi(state);
const { api: windowsApi } = makeWindowsApi(state, { lastFocused: 500 });
const success = mode !== "failed" && mode !== "cancelled";
if (mode === "fallback") spies.move.mockRejectedValueOnce(new Error("original move failed"));
if (mode === "failed") spies.move.mockRejectedValue(new Error("move failed"));
let windowAtRelease: number | undefined;
const cdp = {
releaseSessionTab: vi.fn(async () => {
windowAtRelease = state.tabs.get(7)?.windowId;
if (mode === "cleanup_failed") throw new Error("debugger release failed");
}),
};
const controller = new AbortController();
if (mode === "cancelled") controller.abort();
const result = await handleTabReturn(
sm,
{ session_id: "aa11", tab_id: 7 },
{
tabs: api,
windows: windowsApi,
cdp,
signal: controller.signal,
agentOverlayReset: { resetAgentOverlays: vi.fn(async () => {}) },
},
);
expect("code" in result).toBe(!success);
expect(ctx.borrowedTabs.has(7)).toBe(!success);
expect(cdp.releaseSessionTab).toHaveBeenCalledTimes(success ? 1 : 0);
if (success) {
expect(cdp.releaseSessionTab).toHaveBeenCalledWith("aa11", 7);
expect(windowAtRelease).toBe(mode === "fallback" ? 500 : 200);
expect(spies.move).toHaveBeenCalledTimes(mode === "fallback" ? 2 : 1);
}
});
it("returns the tab to its original window/index and clears borrowedTabs", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -12,7 +12,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -11,7 +11,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
});
const remove = vi.fn(async () => {});
const ensureActiveTab = vi.fn(async () => 1);
const ensureActiveTab = vi.fn(async () => {});
return { create, remove, ensureActiveTab };
}
+5 -31
View File
@@ -69,7 +69,6 @@ import {
import { chromeTabsApi, lookupSession, resolveTargetTab } from "./shared";
import {
type BorrowConfirmationApprover,
chromeTabMutationApi,
handleTabBorrow,
handleTabClose,
handleTabCreate,
@@ -119,8 +118,6 @@ export interface DispatcherDeps {
onSessionsChanged?: () => void;
/** Invoked before a tool that dispatches page input or mutates browser state is forwarded. */
onBrowserControlResumed?: (sessionId: string) => void;
/** Invoked after a tab is explicitly claimed so its overlay can be refreshed immediately. */
onAgentTabClaimed?: (tabId: number, windowId: number) => void;
/** User approval for `tool.tab_borrow` (overlay in content script). */
approveBorrow?: BorrowConfirmationApprover;
/** i18n notification copy for `tool.request_help` (resolved per-call). */
@@ -150,7 +147,6 @@ export class ToolDispatcher {
private readonly recording?: RecordRuntimeDeps;
private readonly onSessionsChanged?: () => void;
private readonly onBrowserControlResumed?: (sessionId: string) => void;
private readonly onAgentTabClaimed?: (tabId: number, windowId: number) => void;
private readonly approveBorrow?: BorrowConfirmationApprover;
private readonly helpNotificationCopy?: () => { title: string; body: string };
private subscription: { dispose(): void } | null = null;
@@ -171,7 +167,6 @@ export class ToolDispatcher {
this.recording = deps.recording;
this.onSessionsChanged = deps.onSessionsChanged;
this.onBrowserControlResumed = deps.onBrowserControlResumed;
this.onAgentTabClaimed = deps.onAgentTabClaimed;
this.approveBorrow = deps.approveBorrow;
this.helpNotificationCopy = deps.helpNotificationCopy;
}
@@ -307,25 +302,13 @@ export class ToolDispatcher {
await this.releaseHoverLatch((req.params as SessionStopParams).session_id);
return handleSessionStop(this.sessions, req.params as SessionStopParams, {
cdp: this.cdp,
// Must be wired in production: the agent-tab cleanup and the
// window-release decision (issue #57) read these deps directly
// and silently no-op when they are absent.
tabManagement: { tabs: chromeTabMutationApi },
tabsQuery: chromeTabsApi,
signal,
});
}
case "tool.tab_list":
return handleTabList(this.sessions, req.params as TabListParams, chromeTabsApi, signal);
case "tool.tab_create": {
const result = await handleTabCreate(this.sessions, req.params as TabCreateParams, {
signal,
});
if (!isRpcError(result)) {
this.onAgentTabClaimed?.(result.tab_id, result.window_id);
}
return result;
}
case "tool.tab_create":
return handleTabCreate(this.sessions, req.params as TabCreateParams, { signal });
case "tool.tab_close":
return this.withHoverReleaseForRequest(
req.params as TabCloseParams,
@@ -334,22 +317,13 @@ export class ToolDispatcher {
);
case "tool.tab_select":
return handleTabSelect(this.sessions, req.params as TabSelectParams, { signal });
case "tool.tab_borrow": {
const result = await handleTabBorrow(this.sessions, req.params as TabBorrowParams, {
case "tool.tab_borrow":
return handleTabBorrow(this.sessions, req.params as TabBorrowParams, {
signal,
approveBorrow: this.approveBorrow,
});
if (!isRpcError(result)) {
this.onAgentTabClaimed?.(result.tab_id, result.agent_window_id);
}
return result;
}
case "tool.tab_return":
return handleTabReturn(this.sessions, req.params as TabReturnParams, {
signal,
cdp: this.cdp,
beforeReturn: (sessionId, tabId) => this.releaseHoverLatch(sessionId, tabId),
});
return handleTabReturn(this.sessions, req.params as TabReturnParams, { signal });
case "tool.window_resize":
return handleWindowResize(
this.sessions,
+38 -278
View File
@@ -183,8 +183,6 @@ export async function resolveBackendNode(
}
// selector path
try {
// Selector lookup itself attaches CDP, even when no element is found.
cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
const doc = await cdp.send<{ root?: { nodeId?: number } }>(target.tabId, "DOM.getDocument", {
depth: 0,
});
@@ -609,53 +607,6 @@ type SelectMutationResult =
// tool.fill
// ---------------------------------------------------------------------------
type FillFailureReason =
| "target_not_fillable"
| "fill_value_invalid"
| "fill_target_changed"
| "fill_focus_lost"
| "fill_value_mismatch"
| "fill_failed";
type FillPreparation =
| { before: string; expected: string }
| { reason: FillFailureReason; error: string };
type FillReadiness = "ready" | "background" | "fill_target_changed" | "fill_focus_lost";
function fillError(reason: FillFailureReason, message: string): RpcError {
return rpcError(
reason === "target_not_fillable" || reason === "fill_value_invalid"
? "invalid_params"
: "cdp_failed",
reason,
message,
);
}
interface FillScriptReply<T> {
result?: { value?: T };
exceptionDetails?: unknown;
}
const FILL_EDITABLE_FUNCTION = `function() {
const tag = this.tagName.toLowerCase();
const supported = tag === 'input'
? ['text', 'search', 'tel', 'url', 'email', 'password', 'number'].includes(this.type)
: tag === 'textarea' || this.isContentEditable;
return this.isConnected && supported && !this.readOnly && !this.matches(':disabled');
}`;
// Chrome renders a trailing editable newline with an empty <div><br></div>.
// innerText includes the padding break; it is not an extra typed character.
const FILL_VALUE_FUNCTION = `function() {
if (!this.isContentEditable) return this.value;
const value = this.innerText;
const tail = this.lastChild;
const padding = tail && tail.nodeName === 'DIV' && tail.childNodes.length === 1 && tail.firstChild.nodeName === 'BR';
return padding && value.endsWith('\\n\\n') ? value.slice(0, -1) : value;
}`;
export async function handleFill(
manager: SessionManager,
params: FillParams,
@@ -707,8 +658,12 @@ export async function handleFill(
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
} catch (err) {
return fillError("fill_failed", err instanceof Error ? err.message : String(err));
return {
code: "cdp_failed",
message: err instanceof Error ? err.message : String(err),
};
}
if (throwIfAborted(deps.signal)) {
@@ -721,252 +676,57 @@ export async function handleFill(
const clearBefore = params.clear_before ?? true;
try {
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
try {
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
} catch (error) {
// Chrome rejects DOM.focus for disabled controls, including inherited
// fieldset state. Classify the live target before treating this as a
// browser failure; the normal path needs no extra round trip.
const editable = await nodeCdp.send<FillScriptReply<boolean>>(
target.tabId,
"Runtime.callFunctionOn",
{ objectId, functionDeclaration: FILL_EDITABLE_FUNCTION, returnByValue: true },
);
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
if (!editable.exceptionDetails && editable.result?.value === false) {
return fillError(
"target_not_fillable",
"fill target is not editable or its input type is unsupported",
);
}
throw error;
}
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
// Check editability before clearing. Keep the expected result tied to
// this object, including the existing value on the append path.
const prepared = await nodeCdp.send<FillScriptReply<FillPreparation>>(
target.tabId,
"Runtime.callFunctionOn",
{
if (clearBefore) {
// Clear input/textarea value or wipe contenteditable innerText,
// then fire `input` so frameworks observe the empty state.
await nodeCdp.send(target.tabId, "Runtime.callFunctionOn", {
objectId,
functionDeclaration: `function(value, clearBefore) {
const tag = this.tagName.toLowerCase();
const native = tag === 'input' || tag === 'textarea';
if (!(${FILL_EDITABLE_FUNCTION}).call(this)) return { reason: 'target_not_fillable', error: 'fill target is not editable or its input type is unsupported' };
if (this.getRootNode().activeElement !== this) return { reason: 'fill_focus_lost', error: 'fill target does not have focus' };
const before = clearBefore ? '' : (${FILL_VALUE_FUNCTION}).call(this);
let expected = before + value;
if (native) {
// Use the browser's own value sanitization (e.g. textarea
// line endings) without changing the live control.
const normalizer = this.ownerDocument.createElement(tag);
if (tag === 'input') {
normalizer.type = this.type;
normalizer.multiple = this.multiple;
}
// insertText treats line breaks in a single-line input as spaces.
if (tag === 'input') expected = expected.replace(/\\r\\n|\\r|\\n/g, ' ');
normalizer.value = expected;
if (expected !== '' && normalizer.value === '' && this.type === 'number') {
return { reason: 'fill_value_invalid', error: 'fill value is not valid for a number input' };
}
expected = normalizer.value;
if (this.type !== 'number' && this.maxLength >= 0 && expected.length > this.maxLength) {
return { reason: 'fill_value_invalid', error: 'fill value exceeds the target maxlength' };
}
} else {
expected = expected.replace(/\\r\\n?/g, '\\n');
functionDeclaration: `function() {
if (this.isContentEditable) { this.textContent = ''; }
else {
const proto = this instanceof HTMLTextAreaElement
? HTMLTextAreaElement.prototype
: HTMLInputElement.prototype;
const descriptor = Object.getOwnPropertyDescriptor(proto, 'value');
if (descriptor && descriptor.set) descriptor.set.call(this, '');
else this.value = '';
}
if (clearBefore) {
if (native) {
const proto = tag === 'textarea' ? HTMLTextAreaElement.prototype : HTMLInputElement.prototype;
Object.getOwnPropertyDescriptor(proto, 'value').set.call(this, '');
} else {
this.textContent = '';
}
this.dispatchEvent(new Event('input', { bubbles: true }));
}
return { before, expected };
this.dispatchEvent(new Event('input', { bubbles: true }));
}`,
arguments: [{ value: params.value }, { value: clearBefore }],
returnByValue: true,
},
);
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
if (prepared.exceptionDetails) {
return fillError("fill_failed", "fill preparation script failed");
}
const preparation = prepared.result?.value;
if (preparation && "error" in preparation) {
return fillError(preparation.reason, preparation.error);
}
if (typeof preparation?.before !== "string" || typeof preparation?.expected !== "string") {
return fillError("fill_failed", "fill preparation returned an unexpected result");
}
// A separate call runs after the clearing event's microtasks drain.
// DOM focus works in background tabs. Use document.hasFocus() only to
// detect deferred focus events, never to reject background input.
const checkReady = async (): Promise<FillReadiness | RpcError> => {
const reply = await nodeCdp.send<FillScriptReply<FillReadiness>>(
target.tabId,
"Runtime.callFunctionOn",
{
objectId,
functionDeclaration: `function(before) {
if (!(${FILL_EDITABLE_FUNCTION}).call(this) ||
(${FILL_VALUE_FUNCTION}).call(this) !== before) return 'fill_target_changed';
if (this.getRootNode().activeElement !== this) return 'fill_focus_lost';
return this.ownerDocument.hasFocus() ? 'ready' : 'background';
}`,
arguments: [{ value: preparation.before }],
returnByValue: true,
},
);
const state = reply.result?.value;
if (
reply.exceptionDetails ||
(state !== "ready" &&
state !== "background" &&
state !== "fill_target_changed" &&
state !== "fill_focus_lost")
) {
return fillError(
"fill_failed",
"fill readiness script failed or returned an unexpected result",
);
}
return state;
};
let ready = await checkReady();
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
// Restore focus once only if clearing left this same target editable
// and unchanged. Recheck after focus handlers have run.
if (clearBefore && ready === "fill_focus_lost") {
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
ready = await checkReady();
});
}
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
if (typeof ready !== "string") return ready;
if (ready !== "ready" && ready !== "background") {
return fillError(ready, "fill target changed or lost focus before typing");
}
if (params.value !== "" && (!clearBefore || ready === "background")) {
// Native editing commands also support number/email inputs, whose
// selection APIs cannot set a caret, and multiline contenteditables.
// Also do this for background replacement: CDP input focuses the
// renderer, delivering deferred focus events before it inserts text.
// Use a command-only event so this does not invoke an End shortcut.
try {
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
type: "rawKeyDown",
commands: ["moveToEndOfDocument"],
});
} finally {
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", { type: "keyUp" });
}
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
// Focus and key handlers can change the target or move focus too.
ready = await checkReady();
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
if (typeof ready !== "string") return ready;
if (ready !== "ready" && ready !== "background") {
return fillError(ready, "fill target changed or lost focus while positioning the caret");
}
}
// CDP `Input.insertText` handles IME / multi-byte input out of the
// box, much more reliably than per-key `dispatchKeyEvent`.
if (params.value !== "") {
await deps.cdp.send(target.tabId, "Input.insertText", { text: params.value });
}
await deps.cdp.send(target.tabId, "Input.insertText", { text: params.value });
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
// Keep the existing notifications, then read in a separate call so
// nested microtasks queued by the page cannot race the verification.
const notified = await nodeCdp.send<FillScriptReply<unknown>>(
target.tabId,
"Runtime.callFunctionOn",
{
objectId,
functionDeclaration: `function() {
this.dispatchEvent(new Event('input', { bubbles: true }));
this.dispatchEvent(new Event('change', { bubbles: true }));
}`,
returnByValue: true,
},
);
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
if (notified.exceptionDetails) {
return fillError("fill_failed", "fill notification script failed");
}
const verified = await nodeCdp.send<
FillScriptReply<{ connected: boolean; matches: boolean; valueLength: number }>
>(target.tabId, "Runtime.callFunctionOn", {
// Fire `input` + `change` so React / Vue controlled inputs commit.
await nodeCdp.send(target.tabId, "Runtime.callFunctionOn", {
objectId,
functionDeclaration: `function(expected) {
const value = (${FILL_VALUE_FUNCTION}).call(this);
return { connected: this.isConnected, matches: value === expected, valueLength: value.length };
}`,
arguments: [{ value: preparation.expected }],
functionDeclaration: `function() {
this.dispatchEvent(new Event('input', { bubbles: true }));
this.dispatchEvent(new Event('change', { bubbles: true }));
}`,
returnByValue: true,
});
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
const verification = verified.result?.value;
if (
verified.exceptionDetails ||
typeof verification?.connected !== "boolean" ||
typeof verification?.matches !== "boolean" ||
typeof verification?.valueLength !== "number"
) {
return fillError(
"fill_failed",
"fill verification script failed or returned an unexpected result",
);
}
if (!verification.connected) {
return fillError("fill_target_changed", "fill target was removed or replaced during input");
}
if (!verification.matches) {
return fillError(
"fill_value_mismatch",
"fill could not verify the expected value; observe the page before deciding whether to retry",
);
}
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
tab_id: target.tabId,
used_ref: node.usedRef,
used_selector: node.usedSelector,
value_length: verification.valueLength,
});
} catch (err) {
return fillError("fill_failed", err instanceof Error ? err.message : String(err));
} finally {
await nodeCdp.send(target.tabId, "Runtime.releaseObject", { objectId }).catch(() => undefined);
return {
code: "cdp_failed",
message: err instanceof Error ? err.message : String(err),
};
}
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
tab_id: target.tabId,
used_ref: node.usedRef,
used_selector: node.usedSelector,
value_length: params.value.length,
});
}
// ---------------------------------------------------------------------------
+8 -94
View File
@@ -2,7 +2,6 @@ import { type SessionManager, SessionStartCleanupError } from "@/session-manager
import type { RpcError } from "@/transport/types";
import { rpcError } from "./errors";
import { clearRecordingForSession } from "./record";
import type { CdpRunner, ChromeTabsApi } from "./shared";
import { isRpcError } from "./shared";
import { returnBorrowedTab, type TabManagementDeps } from "./tabs";
@@ -74,17 +73,11 @@ export interface SessionStopResult {
/** Tab ids whose return path failed; those entries remain borrowed so
* shutdown can be retried without closing the Agent Window. */
return_failures?: Array<{ tab_id: number; code: string; message: string }>;
/**
* True when the Agent Window was *released* to the user (instead of being
* closed) because it still contained user-created tabs after the agent's own
* tabs were closed. Single-session scope.
*/
window_released?: boolean;
}
export interface SessionStopDeps {
signal?: AbortSignal;
cdp?: Pick<CdpRunner, "releaseSessionTab"> & {
cdp?: {
detachSession(sessionId: string): Promise<void>;
};
/**
@@ -94,13 +87,6 @@ export interface SessionStopDeps {
* without a real browser.
*/
tabManagement?: TabManagementDeps;
/**
* Read-only Chrome tabs API used to *query* remaining tabs before deciding
* whether to release the window. Kept separate from `tabManagement.tabs`
* (a `TabMutationApi` that has no `query`) so the mutation interface stays
* pure. Tests can inject a fake `ChromeTabsApi` too.
*/
tabsQuery?: ChromeTabsApi;
}
/**
@@ -166,10 +152,8 @@ export async function handleSessionStart(
* cleanly (review parity with M6).
* 3. Detach CDP sessions the extension still holds for this
* session (no-op if M6/M7 didn't attach to any tab).
* 4. Close the agent-created tabs and the home tab (design §3.2).
* 5. If any tab remains — those are user-created tabs — release the
* window to the user (dropOnly) instead of closing it, so user
* tabs survive. Otherwise close the window as before.
* 4. Close the Agent Window. SessionManager.stop() removes the
* Chrome window and forgets the context.
*
* Failures in step 1 keep the Agent Window open: a failed borrowed tab
* may still be there, so closing the window would risk losing user
@@ -204,19 +188,15 @@ export async function handleSessionStop(
const returnFailures: SessionStopResult["return_failures"] = [];
const borrowedIds = Array.from(ctx.borrowedTabs.keys());
for (const tabId of borrowedIds) {
// A close event may have removed this borrow while another tab returned.
if (!ctx.borrowedTabs.has(tabId)) continue;
try {
const tabManagement = {
...(deps.tabManagement ?? {}),
cdp: deps.cdp ?? deps.tabManagement?.cdp,
signal: deps.signal,
isAgentWindowId:
deps.tabManagement?.isAgentWindowId ??
((windowId: number) => manager.findByWindowId(windowId) !== null),
};
const outcome = await returnBorrowedTab(ctx, tabId, tabManagement);
if (!ctx.borrowedTabs.has(tabId)) continue;
if (typeof outcome === "object" && "code" in outcome) {
console.warn(`[bsk session_stop] auto-return failed for tab ${tabId}`, outcome);
returnFailures?.push({
@@ -229,7 +209,6 @@ export async function handleSessionStop(
ctx.borrowedTabs.delete(tabId);
}
} catch (err) {
if (!ctx.borrowedTabs.has(tabId)) continue;
const message = err instanceof Error ? err.message : String(err);
console.warn(`[bsk session_stop] auto-return threw for tab ${tabId}: ${message}`);
returnFailures?.push({
@@ -240,15 +219,8 @@ export async function handleSessionStop(
}
}
// A previously failed tab may have closed during a later return. Only
// confirmed close events remove borrows; ordinary move failures stay retryable.
const pendingReturnFailures = returnFailures.filter((failure) =>
ctx.borrowedTabs.has(failure.tab_id),
);
if (deps.signal?.aborted) {
const nonCancelFailures = pendingReturnFailures.filter(
(failure) => failure.code !== "cancelled",
);
const nonCancelFailures = returnFailures?.filter((failure) => failure.code !== "cancelled");
if (nonCancelFailures && nonCancelFailures.length > 0) {
return {
...(returnedTabIds.length > 0 ? { returned_tab_ids: returnedTabIds } : {}),
@@ -260,8 +232,8 @@ export async function handleSessionStop(
const result: SessionStopResult = {};
if (returnedTabIds.length > 0) result.returned_tab_ids = returnedTabIds;
if (pendingReturnFailures.length > 0) {
result.return_failures = pendingReturnFailures;
if (returnFailures && returnFailures.length > 0) {
result.return_failures = returnFailures;
// A failed return means at least one borrowed user tab may still be
// inside the Agent Window. Keep the session/window alive so the user
// can retry `bsk session stop` or explicitly `bsk tab return` after the
@@ -281,66 +253,8 @@ export async function handleSessionStop(
return { code: "cancelled", message: "session_stop aborted before window close" };
}
// Step 4: close every tab explicitly created by the agent, including the
// home tab. `tabsApi` is a
// TabMutationApi (remove only); `queryApi` is a separate read-only
// ChromeTabsApi. If neither is injected, we conservatively fall back to
// closing the window (see Step 5).
const tabsApi = deps.tabManagement?.tabs;
const queryApi = deps.tabsQuery;
if (tabsApi) {
// Close each agent-created tab that still exists.
const agentCreatedTabIds = Array.from(ctx.agentCreatedTabs);
for (const tabId of agentCreatedTabIds) {
try {
await tabsApi.remove(tabId);
ctx.agentCreatedTabs.delete(tabId);
} catch (err) {
// Tab may already be gone (closed by the user). Non-fatal.
console.warn(`[bsk session_stop] failed to close agent tab ${tabId}`, err);
}
}
}
// Step 5: decide whether to release (keep) the window or close it.
let shouldRelease = false;
if (queryApi) {
try {
const liveWindowTabs = await queryApi.query({ windowId: ctx.agentWindowId });
// Only genuine *user* tabs count toward keeping the window open.
// An agent tab that failed to close in Step 4 may still be present
// here; if we counted it as a reason to release (dropOnly), the
// window would be kept and that agent tab would leak (issue #57
// regression). Exclude any id still tracked in agentCreatedTabs.
const userTabs = liveWindowTabs.filter((t) => {
if (t.id === undefined) return false;
return !ctx.agentCreatedTabs.has(t.id);
});
const leakedAgentTabs = liveWindowTabs.filter(
(t) => t.id !== undefined && ctx.agentCreatedTabs.has(t.id),
);
if (leakedAgentTabs.length > 0) {
console.warn(
`[bsk session_stop] ${leakedAgentTabs.length} agent tab(s) failed to close; forcing window close instead of release`,
leakedAgentTabs.map((t) => t.id),
);
}
shouldRelease = userTabs.length > 0;
} catch {
// Query failed (e.g. window already gone) — conservatively close it.
shouldRelease = false;
}
}
if (shouldRelease) {
// Keep the window + its user tabs; only drop the session binding.
await manager.stop(params.session_id, { dropOnly: true });
result.window_released = true;
} else {
// Window is empty (or we couldn't verify state) — close it.
await manager.stop(params.session_id);
}
// Step 4: close the Agent Window and drop the context.
await manager.stop(params.session_id);
return result;
}
-1
View File
@@ -57,7 +57,6 @@ export interface CdpRunner {
getFrameGraph?(tabId: number): Promise<CdpFrameGraph>;
ensureAttachedToUrl?(tabId: number, expectedUrl: string | undefined): Promise<void>;
trackSessionTab?(sessionId: string, tabId: number): void;
releaseSessionTab?(sessionId: string, tabId: number): Promise<void>;
onEvent?(handler: (source: CdpDebuggee, method: string, params: unknown) => void): {
dispose(): void;
};
+28 -45
View File
@@ -10,7 +10,7 @@ import {
import type { SessionContext, SessionManager } from "@/session-manager/manager";
import type { RpcError } from "@/transport/types";
import { rpcError } from "./errors";
import { type CdpRunner, isRpcError, lookupSession } from "./shared";
import { isRpcError, lookupSession } from "./shared";
export type TabScope = "user" | "agent" | "all";
@@ -287,10 +287,6 @@ export interface TabManagementDeps {
approveBorrow?: BorrowConfirmationApprover;
/** Clears Agent-scoped overlays after a borrowed tab is returned. */
agentOverlayReset?: AgentOverlayResetApi;
/** Releases this session's CDP claim after a borrowed tab is returned. */
cdp?: Pick<CdpRunner, "releaseSessionTab">;
/** Runs after tab_return validation, before moving the borrowed tab. */
beforeReturn?: (sessionId: string, tabId: number) => Promise<void>;
/**
* Reports whether `windowId` is any live session's Agent Window.
* `tab_return`'s fallback window picker uses this to avoid moving a
@@ -373,7 +369,6 @@ function buildCreateProps(
* Returns the created tab on success, or an `RpcError` on failure.
*/
async function createTabAndCleanup(
ctx: SessionContext,
deps: TabManagementDeps,
createProps: chrome.tabs.CreateProperties,
): Promise<CreatedChromeTab | RpcError> {
@@ -386,28 +381,25 @@ async function createTabAndCleanup(
message: err instanceof Error ? err.message : String(err),
};
}
if (typeof tab.id !== "number") {
return { code: "protocol_error", message: "chrome.tabs.create returned no tab id" };
}
// Claim the concrete id returned by Chrome. Ownership never depends on
// matching this request to an asynchronous onCreated event.
ctx.agentCreatedTabs.add(tab.id);
if (aborted(deps.signal, "tab_create")) {
try {
await getTabsApi(deps).remove(tab.id);
ctx.agentCreatedTabs.delete(tab.id);
} catch (cleanupErr) {
// Keep the claim when cleanup fails so session_stop can retry instead
// of releasing an agent-owned tab to the user.
return rpcError(
"protocol_error",
"cleanup_failed",
`tab_create aborted but cleanup of tab ${tab.id} failed: ${describeError(cleanupErr)}`,
{ resource_type: "tab", resource_id: tab.id },
);
// We already opened the tab; close it on abort so we don't leak.
if (typeof tab.id === "number") {
try {
await getTabsApi(deps).remove(tab.id);
} catch (cleanupErr) {
return rpcError(
"protocol_error",
"cleanup_failed",
`tab_create aborted but cleanup of tab ${tab.id} failed: ${describeError(cleanupErr)}`,
{ resource_type: "tab", resource_id: tab.id },
);
}
}
return { code: "cancelled", message: "tab_create aborted" };
}
if (typeof tab.id !== "number") {
return { code: "protocol_error", message: "chrome.tabs.create returned no tab id" };
}
return { ...tab, id: tab.id };
}
@@ -434,7 +426,7 @@ export async function handleTabCreate(
const paramErr = validateTabCreateParams(params);
if (paramErr) return paramErr;
const tab = await createTabAndCleanup(ctx, deps, buildCreateProps(ctx, params));
const tab = await createTabAndCleanup(deps, buildCreateProps(ctx, params));
if (isRpcError(tab)) return tab;
return {
@@ -534,9 +526,6 @@ export async function handleTabClose(
}
try {
await getTabsApi(deps).remove(params.tab_id);
// Keep the tracking set accurate so session_stop won't try to close a
// tab that's already gone (design §3.1).
ctx.agentCreatedTabs.delete(params.tab_id);
} catch (err) {
return {
code: "protocol_error",
@@ -764,6 +753,13 @@ async function executeBorrowCore(
);
if (moveErr) return moveErr;
// Best-effort activation — failure is non-fatal.
try {
await p.tabsApi.update(p.tabId, { active: true });
} catch (err) {
console.debug("[bsk tab_borrow] activate after move failed", err);
}
return { originalWindowId, originalIndex };
}
@@ -827,12 +823,6 @@ export async function handleTabBorrow(
message: err instanceof Error ? err.message : String(err),
};
}
// Activate after commit so overlay/event observers see the tab as claimed.
try {
await tabsApi.update(params.tab_id, { active: true });
} catch (err) {
console.debug("[bsk tab_borrow] activate after move failed", err);
}
return {
tab_id: params.tab_id,
original_window_id: coreResult.originalWindowId,
@@ -949,22 +939,16 @@ async function cleanupUnusedFallbackWindow(
}
}
async function releaseReturnedTabState(
function resetAgentOverlaysInReturnedTab(
ctx: SessionContext,
tabId: number,
deps: TabManagementDeps,
): Promise<void> {
): void {
void getAgentOverlayResetApi(deps)
.resetAgentOverlays(tabId, ctx.sessionId)
.catch((err) => {
console.debug("[bsk tab_return] agent overlay reset failed", err);
});
try {
await deps.cdp?.releaseSessionTab?.(ctx.sessionId, tabId);
} catch (err) {
// A successful move must not be retried because debugger cleanup failed.
console.debug("[bsk tab_return] CDP release failed", err);
}
}
/**
@@ -1038,7 +1022,7 @@ export async function returnBorrowedTab(
});
const movedTab = Array.isArray(moved) ? moved[0] : moved;
const finalIndex = typeof movedTab?.index === "number" ? movedTab.index : targetIndex;
await releaseReturnedTabState(ctx, tabId, deps);
resetAgentOverlaysInReturnedTab(ctx, tabId, deps);
return {
tabId,
toWindowId: targetWindowId,
@@ -1080,7 +1064,7 @@ export async function returnBorrowedTab(
});
const movedTab = Array.isArray(moved) ? moved[0] : moved;
const finalIndex = typeof movedTab?.index === "number" ? movedTab.index : target.index;
await releaseReturnedTabState(ctx, tabId, deps);
resetAgentOverlaysInReturnedTab(ctx, tabId, deps);
return {
tabId,
toWindowId: target.windowId,
@@ -1126,7 +1110,6 @@ export async function handleTabReturn(
message: `tab_return: tab ${params.tab_id} is not borrowed by this session`,
};
}
await deps.beforeReturn?.(ctx.sessionId, params.tab_id);
const outcome = await returnBorrowedTab(ctx, params.tab_id, {
...deps,
isAgentWindowId:
@@ -215,29 +215,21 @@ function makeCdp(snapshot: unknown) {
if (method === "Runtime.evaluate") {
return {
result: {
deepSerializedValue: {
type: "array",
value: [
value: {
controls: [
{
type: "array",
value: [
{ type: "node", value: { backendNodeId: 13 } },
{
type: "string",
value: JSON.stringify({
state: "filled",
sensitive: true,
placeholder: "secret",
}),
},
],
state: "filled",
sensitive: true,
defaultValue: "hunter2",
value: "hunter2",
placeholder: "secret",
},
],
childFrames: [],
},
},
};
}
if (method === "Runtime.releaseObjectGroup") return {};
throw new Error(`unexpected ${method}`);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
@@ -281,11 +273,8 @@ describe("captureViewModel", () => {
expect(cdp.send).toHaveBeenCalledWith(
4,
"Runtime.evaluate",
expect.objectContaining({
serializationOptions: expect.objectContaining({ serialization: "deep" }),
}),
expect.objectContaining({ returnByValue: true }),
);
expect(cdp.send).toHaveBeenCalledWith(4, "Runtime.releaseObjectGroup", expect.anything());
expect(cdp.send).not.toHaveBeenCalledWith(4, "DOM.resolveNode", expect.anything());
expect(cdp.send).not.toHaveBeenCalledWith(4, "Runtime.callFunctionOn", expect.anything());
});
@@ -1,270 +0,0 @@
import { describe, expect, it, vi } from "vitest";
import { type CdpRunner, cdpRunnerForTarget } from "../../shared";
import { captureViewModel } from "../capture";
interface Control {
id: number;
value: string;
type?: string;
}
function snapshot(groups: Control[][]) {
const strings: string[] = [];
const str = (value: string) => {
let index = strings.indexOf(value);
if (index < 0) index = strings.push(value) - 1;
return index;
};
const documents = groups.map((controls, groupIndex) => ({
frameId: `frame-${groupIndex}`,
nodes: {
parentIndex: [-1, 0, ...controls.map(() => 1)],
nodeName: [str("html"), str("body"), ...controls.map(() => str("input"))],
backendNodeId: [8000 + groupIndex * 2, 8001 + groupIndex * 2, ...controls.map((c) => c.id)],
attributes: [
[],
[],
...controls.map((c) => [
str("type"),
str(c.type ?? "text"),
str("placeholder"),
str("snapshot placeholder"),
]),
],
inputValue: {
index: controls.map((_, i) => i + 2),
value: controls.map((c) => str(c.value)),
},
contentDocumentIndex: { index: [] as number[], value: [] as number[] },
},
}));
const root = documents[0].nodes;
for (let i = 1; i < documents.length; i++) {
root.contentDocumentIndex.index.push(root.backendNodeId.length);
root.contentDocumentIndex.value.push(i);
root.parentIndex.push(1);
root.nodeName.push(str("iframe"));
root.backendNodeId.push(9000 + i);
root.attributes.push([]);
}
return { strings, documents };
}
function state(value: string) {
return {
value,
defaultValue: "",
placeholder: "live placeholder",
state: value ? "filled" : "empty",
sensitive: false,
};
}
function reply(entries: Array<[number, unknown]>) {
return {
result: {
deepSerializedValue: {
type: "array",
value: entries.map(([backendNodeId, fields]) => ({
type: "array",
value: [
{ type: "node", value: { backendNodeId } },
{ type: "string", value: JSON.stringify(fields) },
],
})),
},
},
};
}
function fakeCdp(groups: Control[][], evaluate: (params: Record<string, unknown>) => unknown) {
const snap = snapshot(groups);
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
if (method === "DOMSnapshot.captureSnapshot") return snap;
if (method === "Runtime.evaluate") return evaluate(params as Record<string, unknown>);
return {};
});
return { send, cdp: { send: send as CdpRunner["send"] } };
}
describe("form state identity", () => {
it("matches reordered controls by identity and preserves controls missing from the batch", async () => {
// The snapshot includes a shadow input. The runtime query skips it,
// encounters a new input, and sees the remaining inputs in a new order.
const { cdp } = fakeCdp(
[
[
{ id: 10, value: "" },
{ id: 11, value: "old email" },
{ id: 12, value: "old city" },
],
],
() =>
reply([
[99, state("new control")],
[12, state("上海")],
[11, state("alice@example.com")],
]),
);
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 10)).toMatchObject({
formValue: "",
formState: "empty",
formPlaceholder: "snapshot placeholder",
});
expect(captured.nodes.find((n) => n.backendNodeId === 11)).toMatchObject({
formValue: "alice@example.com",
});
expect(captured.nodes.find((n) => n.backendNodeId === 12)).toMatchObject({ formValue: "上海" });
expect(captured.nodes.some((n) => n.backendNodeId === 99)).toBe(false);
});
it("does not shift state between frames when one frame is absent from the runtime batch", async () => {
const { cdp } = fakeCdp(
[
[],
[{ id: 11, value: "inaccessible frame" }],
[{ id: 21, value: "old second" }],
[{ id: 31, value: "old third" }],
],
() =>
reply([
[31, state("third frame")],
[21, state("second frame")],
]),
);
const captured = await captureViewModel(cdp, 7);
const controls = [...captured.iframeNodes.values()].flat();
expect(controls.find((n) => n.backendNodeId === 11)?.formValue).toBe("inaccessible frame");
expect(controls.find((n) => n.backendNodeId === 21)?.formValue).toBe("second frame");
expect(controls.find((n) => n.backendNodeId === 31)?.formValue).toBe("third frame");
});
it("keeps identical backend ids in different OOPIF targets separate", async () => {
const sendToTarget = vi.fn(async (target, method) => {
if (method === "DOMSnapshot.captureSnapshot") return snapshot([[{ id: 11, value: "old" }]]);
if (method === "Runtime.evaluate") return reply([[11, state(target.sessionId)]]);
return {};
});
const send = vi.fn(async () => {
throw new Error("unexpected top-level target");
});
const cdp = { send, sendToTarget } as unknown as CdpRunner;
for (const sessionId of ["left-frame", "right-frame"]) {
const captured = await captureViewModel(cdpRunnerForTarget(cdp, { tabId: 7, sessionId }), 7);
expect(captured.nodes.find((n) => n.backendNodeId === 11)?.formValue).toBe(sessionId);
expect(sendToTarget).toHaveBeenCalledWith(
{ tabId: 7, sessionId },
"Runtime.releaseObjectGroup",
expect.anything(),
);
}
expect(send).not.toHaveBeenCalled();
});
it.each([
"unsupported",
"legacy",
"malformed",
"invalid-state",
])("preserves snapshot data when enrichment is %s", async (mode) => {
const { cdp, send } = fakeCdp([[{ id: 11, value: "snapshot value" }]], () => {
if (mode === "unsupported") throw new Error("serialization unsupported");
if (mode === "legacy") return { result: { value: { controls: [state("wrong value")] } } };
const result = reply([
[11, mode === "invalid-state" ? { value: "wrong value" } : state("wrong value")],
]);
if (mode === "malformed")
result.result.deepSerializedValue.value[0].value[1].value = "not json";
return result;
});
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 11)).toMatchObject({
formValue: "snapshot value",
formPlaceholder: "snapshot placeholder",
});
expect(send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
});
it("releases the batch's remote objects when capture is cancelled", async () => {
const controller = new AbortController();
const { cdp, send } = fakeCdp([[{ id: 11, value: "old" }]], () => {
controller.abort();
return reply([[11, state("new")]]);
});
await expect(captureViewModel(cdp, 7, { signal: controller.signal })).rejects.toMatchObject({
name: "AbortError",
});
expect(send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
});
it("skips entries without node identity while still applying valid entries", async () => {
const { cdp } = fakeCdp(
[
[
{ id: 11, value: "snapshot value" },
{ id: 12, value: "old value" },
],
],
() => {
const result = reply([
[11, state("wrong value")],
[12, state("live value")],
]);
const element = result.result.deepSerializedValue.value[0].value[0];
delete (element.value as { backendNodeId?: number }).backendNodeId;
return result;
},
);
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 11)?.formValue).toBe("snapshot value");
expect(captured.nodes.find((n) => n.backendNodeId === 12)?.formValue).toBe("live value");
});
it.each([
"password",
"text",
])("redacts a sensitive %s control after identity matching", async (type) => {
const { cdp } = fakeCdp([[{ id: 11, value: "secret", type }]], () =>
reply([[11, { ...state("secret"), sensitive: true }]]),
);
const captured = await captureViewModel(cdp, 7);
const control = captured.nodes.find((n) => n.backendNodeId === 11);
expect(control?.formState).toBe("filled");
expect(control?.formValue).toBeUndefined();
expect(control?.formDefaultValue).toBeUndefined();
expect(control?.attrs.value).toBeUndefined();
});
it("keeps one bounded batch without per-control CDP queries", async () => {
const controls = Array.from({ length: 251 }, (_, i) => ({ id: i + 1, value: "old" }));
const elements = controls.map((c) => ({
backendNodeId: c.id,
tagName: "INPUT",
type: "text",
value: `live ${c.id}`,
defaultValue: "",
placeholder: "",
}));
const { cdp, send } = fakeCdp([controls], (params) => {
const doc = {
querySelectorAll: (selector: string) =>
selector === "input,textarea,select" ? elements : [],
};
const entries = new Function("document", `return ${params.expression}`)(doc) as Array<
[{ backendNodeId: number }, string]
>;
expect(entries).toHaveLength(250);
return reply(entries.map(([element, json]) => [element.backendNodeId, JSON.parse(json)]));
});
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 250)?.formValue).toBe("live 250");
expect(captured.nodes.find((n) => n.backendNodeId === 251)?.formValue).toBe("old");
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(1);
expect(
send.mock.calls.filter(([, method]) => method === "Runtime.releaseObjectGroup"),
).toHaveLength(1);
expect(send).not.toHaveBeenCalledWith(7, "DOM.resolveNode", expect.anything());
expect(send).not.toHaveBeenCalledWith(7, "Runtime.callFunctionOn", expect.anything());
});
});
+26 -57
View File
@@ -190,9 +190,9 @@ interface CapturedFormState {
sensitive?: boolean;
}
interface DeepSerializedValue {
type: string;
value?: unknown;
interface CapturedFrameFormState {
controls: CapturedFormState[];
childFrames: CapturedFrameFormState[];
}
function formStateBatchExpression(maxControls: number): string {
@@ -215,63 +215,43 @@ function formStateBatchExpression(maxControls: number): string {
...(sensitive ? {} : { value: rawValue, defaultValue }),
};
};
const controls = [];
const collect = (doc) => {
const controls = [];
for (const el of Array.from(doc.querySelectorAll(controlSelector))) {
if (remaining <= 0) break;
// Deep serialization supplies the node's backend id. Keep the
// state as JSON so decoding needs no general-purpose V8 deserializer.
controls.push([el, JSON.stringify(controlState(el))]);
controls.push(controlState(el));
remaining -= 1;
}
const childFrames = [];
for (const frame of Array.from(doc.querySelectorAll("iframe"))) {
if (remaining <= 0) break;
let childDoc = null;
try { childDoc = frame.contentDocument; } catch { childDoc = null; }
if (childDoc) collect(childDoc);
childFrames.push(childDoc && remaining > 0 ? collect(childDoc) : { controls: [], childFrames: [] });
}
return { controls, childFrames };
};
collect(document);
return controls;
return collect(document);
})()`;
}
function formStatesByBackendId(result: RuntimeEvaluateReply): Map<number, CapturedFormState> {
const states = new Map<number, CapturedFormState>();
const serialized = result.result?.deepSerializedValue;
if (serialized?.type !== "array" || !Array.isArray(serialized.value)) return states;
for (const entry of serialized.value as DeepSerializedValue[]) {
if (entry?.type !== "array" || !Array.isArray(entry.value)) continue;
const [element, json] = entry.value as DeepSerializedValue[];
if (element?.type !== "node" || json?.type !== "string" || typeof json.value !== "string") {
continue;
}
const backendNodeId = (element.value as { backendNodeId?: number } | undefined)?.backendNodeId;
if (typeof backendNodeId !== "number" || !Number.isSafeInteger(backendNodeId)) continue;
try {
const state = JSON.parse(json.value) as CapturedFormState | null;
if (
!state ||
!["empty", "filled", "default"].includes(state.state ?? "") ||
typeof state.sensitive !== "boolean" ||
typeof state.placeholder !== "string" ||
(!state.sensitive &&
(typeof state.value !== "string" || typeof state.defaultValue !== "string"))
) {
continue;
}
states.set(backendNodeId, state);
} catch {
// A malformed entry must not overwrite the snapshot's own state.
}
function flattenFrameFormStates(
frame: CapturedFrameFormState | undefined,
out: CapturedFormState[][] = [],
): CapturedFormState[][] {
if (!frame) return out;
out.push(Array.isArray(frame.controls) ? frame.controls : []);
for (const child of Array.isArray(frame.childFrames) ? frame.childFrames : []) {
flattenFrameFormStates(child, out);
}
return states;
return out;
}
function applyFormStates(nodes: CapturedNode[], states: Map<number, CapturedFormState>): void {
function applyFormStates(nodes: CapturedNode[], states: CapturedFormState[]): void {
let index = 0;
for (const node of nodes) {
if (!isFormControlTag(node.tag)) continue;
const state = states.get(node.backendNodeId);
const state = states[index];
index += 1;
if (!state) continue;
node.formState = state.state;
node.formPlaceholder = state.placeholder ?? "";
@@ -296,37 +276,26 @@ async function enrichFormControlStates(
nodes.some((node) => isFormControlTag(node.tag)),
);
if (!hasControls) return;
const objectGroup = `bsk-vom-forms-${crypto.randomUUID()}`;
try {
throwIfAborted(signal);
const result = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
expression: formStateBatchExpression(MAX_FORM_ENRICH_CONTROLS),
objectGroup,
serializationOptions: {
serialization: "deep",
maxDepth: 3,
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
},
returnByValue: true,
});
throwIfAborted(signal);
// Backend ids are scoped to this capture's CDP target. OOPIF targets
// use their own captureViewModel call and never share this lookup.
const states = formStatesByBackendId(result);
for (const nodes of frameNodeGroups) {
applyFormStates(nodes, states);
const frameStates = flattenFrameFormStates(runtimeValue<CapturedFrameFormState>(result));
for (let i = 0; i < frameNodeGroups.length; i += 1) {
applyFormStates(frameNodeGroups[i], frameStates[i] ?? []);
}
} catch (error) {
if (isAbortError(error)) throw error;
// Best-effort enrichment. DOMSnapshot/AX data still carries the nodes.
} finally {
await cdp.send(tabId, "Runtime.releaseObjectGroup", { objectGroup }).catch(() => undefined);
}
}
interface RuntimeEvaluateReply {
result?: {
value?: unknown;
deepSerializedValue?: DeepSerializedValue;
};
}
-5
View File
@@ -26,11 +26,6 @@ export type RpcErrorReason =
| "ref_not_found"
| "selector_not_found"
| "target_not_fillable"
| "fill_value_invalid"
| "fill_target_changed"
| "fill_focus_lost"
| "fill_value_mismatch"
| "fill_failed"
| "target_not_select"
| "option_not_found"
| "single_select_value_count"
-4
View File
@@ -172,10 +172,6 @@ intended. Read `bsk upload --help` and `bsk download --help` for all flags and e
- Stale ref: observe again and retry the intended action once.
- Unknown tab or session: list current tabs/sessions; never guess identifiers.
- Timeout: inspect current page state before deciding whether one longer purposeful wait is useful.
- Fill result unconfirmed (`fill_value_mismatch`): observe the field first; the page may have
formatted the value. Continue if the visible result satisfies the user's intent. Otherwise correct
the remaining difference; do not blindly repeat fill or immediately request human help. For other
fill errors, follow the returned hint and inspect current state before retrying.
- Unsupported command: continue with available capabilities; suggest updating only when the missing
command is necessary.
- Unrecoverable failure: report the blocker and stop the session in a finally-style path.
+1 -91
View File
@@ -43,11 +43,6 @@ pub mod reason {
pub const REF_NOT_FOUND: &str = "ref_not_found";
pub const SELECTOR_NOT_FOUND: &str = "selector_not_found";
pub const TARGET_NOT_FILLABLE: &str = "target_not_fillable";
pub const FILL_VALUE_INVALID: &str = "fill_value_invalid";
pub const FILL_TARGET_CHANGED: &str = "fill_target_changed";
pub const FILL_FOCUS_LOST: &str = "fill_focus_lost";
pub const FILL_VALUE_MISMATCH: &str = "fill_value_mismatch";
pub const FILL_FAILED: &str = "fill_failed";
pub const TARGET_NOT_SELECT: &str = "target_not_select";
pub const OPTION_NOT_FOUND: &str = "option_not_found";
pub const SINGLE_SELECT_VALUE_COUNT: &str = "single_select_value_count";
@@ -252,42 +247,7 @@ pub fn info_for_error(code: ErrorCode, data: Option<&serde_json::Value>) -> Rend
(ErrorCode::InvalidParams, reason::TARGET_NOT_FILLABLE) => RenderInfo {
summary: "target element is not fillable",
hint: Some(
"observe the page and choose an enabled, editable text input, textarea, or contenteditable; use the appropriate interaction for other control types",
),
exit_code: base.exit_code,
},
(ErrorCode::InvalidParams, reason::FILL_VALUE_INVALID) => RenderInfo {
summary: "the requested text does not fit the field constraints",
hint: Some(
"check the field's input type and maxlength; use a compatible value without silently truncating or changing the user's intended data",
),
exit_code: base.exit_code,
},
(ErrorCode::CdpFailed, reason::FILL_TARGET_CHANGED) => RenderInfo {
summary: "the fill target changed during the action",
hint: Some(
"observe the current page and field value; if the intended result is missing, use a fresh editable target before retrying",
),
exit_code: base.exit_code,
},
(ErrorCode::CdpFailed, reason::FILL_FOCUS_LOST) => RenderInfo {
summary: "the page moved focus away from the fill target",
hint: Some(
"observe the page for a dialog or rerender and resolve it before retrying; fill manages field focus and does not require bringing the browser to the foreground",
),
exit_code: base.exit_code,
},
(ErrorCode::CdpFailed, reason::FILL_VALUE_MISMATCH) => RenderInfo {
summary: "the fill result could not be confirmed",
hint: Some(
"observe the field before retrying; the page may have formatted the value. Continue if the visible result satisfies the user's intent; otherwise correct the remaining difference. Do not blindly repeat fill or immediately request human help",
),
exit_code: base.exit_code,
},
(ErrorCode::CdpFailed, reason::FILL_FAILED) => RenderInfo {
summary: "fill encountered a browser or page-script error",
hint: Some(
"observe the page before retrying because the field may already have changed; retry only if the intended result is missing and the target is still available",
"choose an input, textarea, or contenteditable element from the latest snapshot",
),
exit_code: base.exit_code,
},
@@ -482,56 +442,6 @@ mod tests {
ErrorCode::NoBrowserConnected,
];
#[test]
fn fill_reasons_provide_recovery_without_changing_exit_codes() {
for (code, reason, hint_fragment) in [
(
ErrorCode::InvalidParams,
reason::TARGET_NOT_FILLABLE,
"enabled, editable",
),
(
ErrorCode::InvalidParams,
reason::FILL_VALUE_INVALID,
"maxlength",
),
(
ErrorCode::CdpFailed,
reason::FILL_TARGET_CHANGED,
"fresh editable target",
),
(
ErrorCode::CdpFailed,
reason::FILL_FOCUS_LOST,
"does not require bringing the browser",
),
(
ErrorCode::CdpFailed,
reason::FILL_VALUE_MISMATCH,
"Continue if the visible result satisfies",
),
(
ErrorCode::CdpFailed,
reason::FILL_FAILED,
"may already have changed",
),
] {
let data = serde_json::json!({ "reason": reason });
let info = info_for_error(code, Some(&data));
assert!(info.hint.unwrap().contains(hint_fragment), "{reason}");
assert_eq!(info.exit_code, info_for(code).exit_code);
}
let mismatch = serde_json::json!({ "reason": reason::FILL_VALUE_MISMATCH });
let info = info_for_error(ErrorCode::CdpFailed, Some(&mismatch));
assert_eq!(info.summary, "the fill result could not be confirmed");
assert!(info.hint.unwrap().contains("Do not blindly repeat fill"));
let unknown = serde_json::json!({ "reason": "future_fill_reason" });
assert_eq!(
info_for_error(ErrorCode::CdpFailed, Some(&unknown)),
info_for(ErrorCode::CdpFailed)
);
}
#[test]
fn element_not_visible_overrides_permission_denied_copy() {
let data = serde_json::json!({ "reason": reason::ELEMENT_NOT_VISIBLE });
+2 -5
View File
@@ -761,7 +761,6 @@ fn stage_windows_replacement(
.with_context(|| format!("write {}", paths.script_path.display()))?;
const CREATE_NO_WINDOW: u32 = 0x0800_0000;
const CREATE_NEW_PROCESS_GROUP: u32 = 0x0000_0200;
let command = format!("\"{}\"", paths.script_path.display());
if let Err(err) = Command::new("cmd.exe")
.args(["/D", "/S", "/C"])
@@ -769,7 +768,7 @@ fn stage_windows_replacement(
.stdin(Stdio::null())
.stdout(Stdio::null())
.stderr(Stdio::null())
.creation_flags(CREATE_NO_WINDOW | CREATE_NEW_PROCESS_GROUP)
.creation_flags(CREATE_NO_WINDOW)
.spawn()
{
let _ = std::fs::remove_file(&paths.binary_path);
@@ -807,7 +806,7 @@ fn windows_replacement_script(target: &Path, staged_binary: &Path, restart_daemo
:retry\r\n\
move /Y \"{staged_binary}\" \"{target}\" >nul 2>nul\r\n\
if errorlevel 1 (\r\n\
ping -n 2 127.0.0.1 >nul\r\n\
timeout /t 1 /nobreak >nul\r\n\
goto retry\r\n\
)\r\n\
{restart}\
@@ -1008,8 +1007,6 @@ mod tests {
assert!(script.contains(":retry"));
assert!(script.contains("move /Y"));
assert!(script.contains("ping -n 2 127.0.0.1"));
assert!(!script.contains("timeout"));
assert!(script.contains(r#"start "" /B "C:\Program Files\bsk.exe" daemon start"#));
assert!(script.contains(r#"del /F /Q "%~f0""#));
}
@@ -97,10 +97,6 @@ Continue from returned sequence cursors instead of rereading the same buffer.
- Unknown tab: list tabs instead of guessing.
- Unknown session: list owned sessions or start one; never try foreign ids.
- Timeout: inspect current state before deciding whether one longer purposeful wait is useful.
- Fill result unconfirmed: observe the field first; the page may have formatted the value. Continue
if the visible result satisfies the user's intent. Otherwise correct the remaining difference;
do not blindly repeat fill or immediately request human help. For other fill errors, follow the
returned hint and inspect current state before retrying.
- Unrecoverable failure: report the blocker and stop the owned session.
Arbitrary page-script evaluation and interaction recording are intentionally unsupported. Do not
@@ -636,9 +636,7 @@ function defineBrowserOperations(deps: ToolDeps, register: DefinitionRegistrar):
session: SESSION_PARAM,
noClear: {
type: "boolean",
description:
"Append to the end of the existing value instead of clearing it. " +
"The tool moves the caret automatically; no prior click or selection is needed.",
description: "Skip the default wipe-the-field-first pass (append instead).",
},
},
output: {
@@ -124,28 +124,6 @@ describe("parseBskJson", () => {
expect(() => parseBskJson({ ...base, code: 1, stderr: "boom" }, "x")).toThrow(/boom/);
});
it("surfaces fill recovery guidance to the model without retrying", async () => {
const hint =
"observe the field before retrying; the page may have formatted the value. Continue if the visible result satisfies the user's intent";
const reply = {
...base,
code: 3,
stdout: JSON.stringify({
code: "cdp_failed",
message: "fill could not verify the expected value",
data: { reason: "fill_value_mismatch" },
hint,
}),
};
let calls = 0;
const result = await runWithSessionBusyRetry(async () => {
calls++;
return reply;
});
expect(calls).toBe(1);
expect(() => parseBskJson(result, "fill")).toThrow(hint);
});
it("reports killed-by-interrupt children (null exit code) as interrupted", () => {
expect(() => parseBskJson({ ...base, code: null }, "navigate")).toThrow(/interrupted/);
});
-7
View File
@@ -13,10 +13,6 @@
"default": "./src/react.tsx"
}
},
"scripts": {
"test": "vitest run",
"test:watch": "vitest"
},
"peerDependencies": {
"react": "^19.0.0"
},
@@ -24,8 +20,5 @@
"i18next": "^24.2.2",
"i18next-browser-languagedetector": "^8.0.2",
"react-i18next": "^15.3.4"
},
"devDependencies": {
"vitest": "^4.1.6"
}
}
+2 -107
View File
@@ -24,9 +24,6 @@ declare const chrome:
) => void;
};
};
i18n?: {
getUILanguage(): string;
};
}
| undefined;
@@ -34,116 +31,14 @@ function getChromeLocal(): ChromeStorageLocal | undefined {
return typeof chrome !== "undefined" ? chrome.storage?.local : undefined;
}
/** Regions whose written Chinese defaults to Traditional. */
const TRADITIONAL_CHINESE_REGIONS = new Set(["tw", "hk", "mo"]);
/**
* Group resource keys by primary language subtag, so a bare `ko` can find
* `ko-KR` without anyone maintaining a side map by hand.
*/
function buildPrimarySubtagIndex(resourceKeys: string[]): Map<string, string[]> {
const index = new Map<string, string[]>();
for (const key of resourceKeys) {
const primary = key.split(/[-_]/)[0].toLowerCase();
const bucket = index.get(primary);
if (bucket) {
bucket.push(key);
} else {
index.set(primary, [key]);
}
}
return index;
}
/**
* Chinese is the one language where a single primary subtag maps to several
* resources, because Simplified and Traditional differ by script rather than
* by region. Every other language resolves straight from the index.
*/
function resolveChineseVariant(parts: string[], candidates: string[]): string {
const byRegion = (region: string): string | undefined =>
candidates.find((key) => key.toLowerCase().endsWith(`-${region}`));
// 1. Script subtag is the most accurate signal (zh-Hans / zh-Hant).
if (parts.includes("hans")) {
return byRegion("cn") ?? candidates[0];
}
if (parts.includes("hant")) {
return byRegion("tw") ?? candidates[candidates.length - 1];
}
// 2. Fall back to the region subtag, which is what Chrome actually reports.
// Skip parts[0] — the primary subtag `zh` is also two characters long.
const region = parts.slice(1).find((part) => part.length === 2);
if (region && TRADITIONAL_CHINESE_REGIONS.has(region)) {
return byRegion("tw") ?? candidates[0];
}
// 3. Bare `zh` and any other region default to Simplified.
return byRegion("cn") ?? candidates[0];
}
/**
* Build a normalizer driven entirely by the resource keys i18next ships, so
* registering a new translation needs no change here.
*
* For a detected BCP 47 tag, in order:
*
* 1. it already names a resource (`ko-KR`) → unchanged
* 2. one resource shares its language (`ko` → `ko-KR`) → that resource
* 3. several do (`zh` → `zh-CN` / `zh-TW`) → script, then region
* 4. nothing is shipped for the language → unchanged
*
* Case 4 leaves the tag untouched so i18next applies `fallbackLng`, rather
* than silently routing an untranslated language to the wrong bundle.
*/
export function createLanguageNormalizer(resourceKeys: string[]): (code: string) => string {
const keySet = new Set(resourceKeys);
const index = buildPrimarySubtagIndex(resourceKeys);
return (code: string): string => {
if (keySet.has(code)) {
return code;
}
const parts = code.split(/[-_]/).map((part) => part.toLowerCase());
const candidates = index.get(parts[0]);
if (!candidates?.length) {
return code;
}
if (candidates.length === 1) {
return candidates[0];
}
if (parts[0] === "zh") {
return resolveChineseVariant(parts, candidates);
}
return candidates[0];
};
}
/**
* i18next detector that prefers `chrome.i18n.getUILanguage()`, Chrome's
* authoritative source for the extension UI language. The popup runs on a
* `chrome-extension://` origin where `navigator.language` can disagree with it.
*/
export const chromeUiLanguageDetector = {
name: "chromeUILanguage",
lookup(): string | undefined {
if (typeof chrome !== "undefined" && chrome.i18n?.getUILanguage) {
return chrome.i18n.getUILanguage();
}
return undefined;
},
};
/** Avoid page-origin localStorage; use extension storage + navigator only. */
export function getLanguageDetectionOptions(resourceKeys: string[]): {
export function getLanguageDetectionOptions(): {
order: string[];
caches: string[];
convertDetectedLanguage: (lng: string) => string;
} {
return {
order: ["chromeUILanguage", "navigator"],
order: ["navigator"],
caches: [],
// Normalise the detected tag before i18next resolves it against `resources`.
convertDetectedLanguage: createLanguageNormalizer(resourceKeys),
};
}
+4 -17
View File
@@ -2,11 +2,7 @@ import i18n from "i18next";
import LanguageDetector from "i18next-browser-languagedetector";
import { initReactI18next } from "react-i18next";
import {
bindChromeStorageLanguageSync,
chromeUiLanguageDetector,
getLanguageDetectionOptions,
} from "./chrome-storage-sync";
import { bindChromeStorageLanguageSync, getLanguageDetectionOptions } from "./chrome-storage-sync";
import enUSCommon from "./locales/en-US/common.json";
import enUSExtension from "./locales/en-US/extension.json";
import zhCNCommon from "./locales/zh-CN/common.json";
@@ -23,21 +19,12 @@ const resources = {
},
} as const;
const languageDetector = new LanguageDetector();
languageDetector.addDetector(chromeUiLanguageDetector);
// Drive locale normalisation off the keys we actually ship, so registering a
// translation is the only step needed to support a new language.
const resourceKeys = Object.keys(resources);
i18n
.use(languageDetector)
.use(LanguageDetector)
.use(initReactI18next)
.init({
resources,
// English is the international default; Chinese users still get Chinese.
// `zh` → zh-CN also covers zh-TW/zh-HK until a Traditional resource exists.
fallbackLng: { en: ["en-US"], zh: ["zh-CN"], default: ["en-US"] },
fallbackLng: "zh-CN",
defaultNS: "common",
ns: ["common", "extension"],
@@ -45,7 +32,7 @@ i18n
escapeValue: false,
},
detection: getLanguageDetectionOptions(resourceKeys),
detection: getLanguageDetectionOptions(),
react: {
useSuspense: false,
@@ -1,126 +0,0 @@
import { describe, expect, it, vi } from "vitest";
import {
chromeUiLanguageDetector,
createLanguageNormalizer,
getLanguageDetectionOptions,
} from "../src/chrome-storage-sync";
/** What `packages/i18n` ships today — kept in sync with `resources` in i18n.ts. */
const SHIPPED_RESOURCE_KEYS = ["zh-CN", "en-US"];
/**
* Locks the locale-resolution table from issue #168: the UI must follow the
* browser language instead of falling through to Chinese for every locale
* other than `en-US`.
*/
describe("createLanguageNormalizer", () => {
const normalize = createLanguageNormalizer(SHIPPED_RESOURCE_KEYS);
const cases: Array<[detected: string, resource: string]> = [
// English — every variant maps to the single en-US resource.
["en", "en-US"],
["en-US", "en-US"],
["en-GB", "en-US"],
["en-CN", "en-US"],
["en-AU", "en-US"],
// Chinese — only `zh-CN` ships today, so every variant resolves to it
// directly rather than leaking into the fallback chain. Traditional picks
// up `zh-TW` automatically once that bundle is registered (see below).
["zh", "zh-CN"],
["zh-CN", "zh-CN"],
["zh-SG", "zh-CN"],
["zh-Hans", "zh-CN"],
["zh-Hans-CN", "zh-CN"],
["zh-Hans-SG", "zh-CN"],
["zh-TW", "zh-CN"],
["zh-HK", "zh-CN"],
["zh-MO", "zh-CN"],
["zh-Hant", "zh-CN"],
["zh-Hant-TW", "zh-CN"],
["zh-Hant-HK", "zh-CN"],
// No translation shipped — returned unchanged so i18next applies the
// `default` fallback (en-US) rather than Chinese.
["ja", "ja"],
["ja-JP", "ja-JP"],
["fr-FR", "fr-FR"],
["de-DE", "de-DE"],
];
it.each(cases)("maps %s to %s", (detected, resource) => {
expect(normalize(detected)).toBe(resource);
});
it("is case-insensitive", () => {
expect(normalize("EN-us")).toBe("en-US");
expect(normalize("zh-hant-tw")).toBe("zh-CN");
});
});
/**
* The point of the factory: supporting a new language means registering its
* bundle in `resources` — never touching the normalizer.
*/
describe("createLanguageNormalizer extensibility", () => {
it("auto-resolves a newly registered language", () => {
const normalize = createLanguageNormalizer(["en-US", "zh-CN", "ko-KR"]);
expect(normalize("ko")).toBe("ko-KR");
expect(normalize("ko-KR")).toBe("ko-KR");
});
it("disambiguates zh once a Traditional bundle ships", () => {
const normalize = createLanguageNormalizer(["en-US", "zh-CN", "zh-TW"]);
expect(normalize("zh-Hant")).toBe("zh-TW");
expect(normalize("zh-Hant-TW")).toBe("zh-TW");
expect(normalize("zh-TW")).toBe("zh-TW");
expect(normalize("zh-HK")).toBe("zh-TW");
expect(normalize("zh-MO")).toBe("zh-TW");
expect(normalize("zh-Hans")).toBe("zh-CN");
expect(normalize("zh-CN")).toBe("zh-CN");
expect(normalize("zh")).toBe("zh-CN");
});
it("leaves unregistered languages to fallbackLng", () => {
const normalize = createLanguageNormalizer(["en-US", "zh-CN"]);
expect(normalize("pt-BR")).toBe("pt-BR");
expect(normalize("ru")).toBe("ru");
});
});
describe("chromeUiLanguageDetector", () => {
it("prefers chrome.i18n.getUILanguage() when available", () => {
vi.stubGlobal("chrome", { i18n: { getUILanguage: () => "en-GB" } });
expect(chromeUiLanguageDetector.lookup()).toBe("en-GB");
});
it("returns undefined outside a Chrome extension context", () => {
vi.stubGlobal("chrome", undefined);
expect(chromeUiLanguageDetector.lookup()).toBeUndefined();
});
it("returns undefined when the i18n API is unavailable", () => {
vi.stubGlobal("chrome", {});
expect(chromeUiLanguageDetector.lookup()).toBeUndefined();
});
});
describe("getLanguageDetectionOptions", () => {
it("orders the Chrome UI language ahead of navigator", () => {
expect(getLanguageDetectionOptions(SHIPPED_RESOURCE_KEYS).order).toEqual([
"chromeUILanguage",
"navigator",
]);
});
it("normalises whatever the detectors report", () => {
const { convertDetectedLanguage } = getLanguageDetectionOptions(SHIPPED_RESOURCE_KEYS);
expect(convertDetectedLanguage("en-GB")).toBe("en-US");
expect(convertDetectedLanguage("zh-TW")).toBe("zh-CN");
expect(convertDetectedLanguage("ja-JP")).toBe("ja-JP");
});
it("does not write to page-origin storage", () => {
expect(getLanguageDetectionOptions(SHIPPED_RESOURCE_KEYS).caches).toEqual([]);
});
});
-8
View File
@@ -1,8 +0,0 @@
import { defineConfig } from "vitest/config";
export default defineConfig({
test: {
environment: "node",
include: ["tests/**/*.test.ts"],
},
});
-4
View File
@@ -189,10 +189,6 @@ importers:
react-i18next:
specifier: ^15.3.4
version: 15.7.4(i18next@24.2.3(typescript@5.9.3))(react@19.2.6)(typescript@5.9.3)
devDependencies:
vitest:
specifier: ^4.1.6
version: 4.1.6(@types/node@25.8.0)(happy-dom@15.11.7)(vite@8.0.13(@types/node@25.8.0)(esbuild@0.27.7)(jiti@2.7.0))
packages/ui:
dependencies:
+23 -38
View File
@@ -51,9 +51,7 @@ const { values, positionals } = parseArgs({
});
if (values.help) {
console.log(
readFileSync(new URL(import.meta.url), "utf8").match(/\/\*\*([\s\S]*?)\*\//)?.[1] ?? "",
);
console.log(readFileSync(new URL(import.meta.url), "utf8").match(/\/\*\*([\s\S]*?)\*\//)?.[1] ?? "");
process.exit(0);
}
@@ -62,7 +60,9 @@ const pushAfter = values.push;
const pushTagsOnly = values["push-tags"];
const noCommit = values["no-commit"];
const onlyRaw = values.only;
const components = onlyRaw ? onlyRaw.split(",").map((s) => s.trim().toLowerCase()) : ALL_COMPONENTS;
const components = onlyRaw
? onlyRaw.split(",").map((s) => s.trim().toLowerCase())
: ALL_COMPONENTS;
for (const c of components) {
if (!ALL_COMPONENTS.includes(c)) {
@@ -95,9 +95,7 @@ if (pushTagsOnly) {
const newVersion = positionals[0];
if (!newVersion) {
console.error(
"Usage: node scripts/release.mjs <version> [--dry-run] [--push] [--only cli,ext,dsh]",
);
console.error("Usage: node scripts/release.mjs <version> [--dry-run] [--push] [--only cli,ext,dsh]");
process.exit(1);
}
@@ -112,9 +110,8 @@ if (!/^\d+\.\d+\.\d+(-[\w.]+)?$/.test(newVersion)) {
function readCurrentVersions() {
const cargo = readFileSync(VERSION_FILES.cargo, "utf8");
const cargoVer =
cargo.match(/^\[workspace\.package\]\s*\nversion\s*=\s*"([^"]+)"/m)?.[1] ??
cargo.match(/^version\s*=\s*"([^"]+)"/m)?.[1];
const cargoVer = cargo.match(/^\[workspace\.package\]\s*\nversion\s*=\s*"([^"]+)"/m)?.[1]
?? cargo.match(/^version\s*=\s*"([^"]+)"/m)?.[1];
const extPkg = JSON.parse(readFileSync(VERSION_FILES.extension, "utf8"));
const dshPkg = JSON.parse(readFileSync(VERSION_FILES.dshPlugin, "utf8"));
@@ -173,17 +170,19 @@ function updateChangelog(version) {
}
const today = new Date().toISOString().slice(0, 10);
const escapedVer = version.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
// First: fill in any date-placeholder line for this version (e.g. "## [0.2.0] - 2026-09-XX")
const versionPlaceholder = new RegExp(`^## \\[${escapedVer}\\]\\s*-\\s*\\d{4}-\\d{2}-XX`, "m");
if (versionPlaceholder.test(content)) {
content = content.replace(versionPlaceholder, `## [${version}] - ${today}`);
const unreleased = /^## \[Unreleased\]/m;
if (unreleased.test(content)) {
content = content.replace(
unreleased,
`## [Unreleased]\n\n## [${version}] - ${today}`,
);
} else {
// Otherwise: insert a new section after [Unreleased]
const unreleased = /^## \[Unreleased\]/m;
if (unreleased.test(content)) {
content = content.replace(unreleased, `## [Unreleased]\n\n## [${version}] - ${today}`);
const versionPlaceholder = new RegExp(
`^## \\[${version.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")}\\]\\s*-\\s*\\d{4}-\\d{2}-XX`,
"m",
);
if (versionPlaceholder.test(content)) {
content = content.replace(versionPlaceholder, `## [${version}] - ${today}`);
}
}
@@ -196,25 +195,13 @@ function updateChangelog(version) {
const writes = [
{ path: VERSION_FILES.cargo, content: bumpCargo(newVersion), label: "Cargo.toml" },
{
path: VERSION_FILES.extension,
content: bumpPackageJson(VERSION_FILES.extension, newVersion),
label: "Extension package.json",
},
{
path: VERSION_FILES.dshPlugin,
content: bumpPackageJson(VERSION_FILES.dshPlugin, newVersion),
label: "DSH Plugin package.json",
},
{ path: VERSION_FILES.extension, content: bumpPackageJson(VERSION_FILES.extension, newVersion), label: "Extension package.json" },
{ path: VERSION_FILES.dshPlugin, content: bumpPackageJson(VERSION_FILES.dshPlugin, newVersion), label: "DSH Plugin package.json" },
];
const changelogUpdate = updateChangelog(newVersion);
if (changelogUpdate) {
writes.push({
path: changelogUpdate.path,
content: changelogUpdate.content,
label: "CHANGELOG.md",
});
writes.push({ path: changelogUpdate.path, content: changelogUpdate.content, label: "CHANGELOG.md" });
}
for (const w of writes) {
@@ -250,9 +237,7 @@ if (noCommit || dryRun) {
}
console.log("\nCommitting...");
run(
"git add Cargo.toml Cargo.lock apps/extension/package.json packages/dsh-plugin-browserskill/package.json CHANGELOG.md 2>/dev/null || true",
);
run("git add Cargo.toml Cargo.lock apps/extension/package.json packages/dsh-plugin-browserskill/package.json CHANGELOG.md 2>/dev/null || true");
run(`git commit -m "chore(release): ${newVersion}"`);
console.log("Tagging...");
-4
View File
@@ -172,10 +172,6 @@ intended. Read `bsk upload --help` and `bsk download --help` for all flags and e
- Stale ref: observe again and retry the intended action once.
- Unknown tab or session: list current tabs/sessions; never guess identifiers.
- Timeout: inspect current page state before deciding whether one longer purposeful wait is useful.
- Fill result unconfirmed (`fill_value_mismatch`): observe the field first; the page may have
formatted the value. Continue if the visible result satisfies the user's intent. Otherwise correct
the remaining difference; do not blindly repeat fill or immediately request human help. For other
fill errors, follow the returned hint and inspect current state before retrying.
- Unsupported command: continue with available capabilities; suggest updating only when the missing
command is necessary.
- Unrecoverable failure: report the blocker and stop the session in a finally-style path.