Merge pull request #68 from Tencent/feat/more-browser-actions

feat(extension): hover end to end capability support
This commit is contained in:
Zhang GH
2026-08-10 19:26:50 +08:00
committed by GitHub
45 changed files with 4906 additions and 254 deletions
@@ -9,6 +9,8 @@ import type {
} from "@/transport/types";
import { ToolDispatcher } from "../dispatcher";
type TestDispatcherCdp = NonNullable<ConstructorParameters<typeof ToolDispatcher>[0]["cdp"]>;
function fakeTransport() {
const handlers = new Set<FrameHandler>();
const stateHandlers = new Set<ConnectionStateHandler>();
@@ -129,7 +131,7 @@ describe("ToolDispatcher", () => {
setUserAgentOverride: vi.fn(async () => {}),
setTouchEmulationEnabled: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({ transport, sessions, cdp });
const dispatcher = new ToolDispatcher({ transport, sessions, cdp: cdp as TestDispatcherCdp });
dispatcher.start();
deliver(makeRequest("tool.console", { session_id: "aa11" }));
@@ -172,7 +174,7 @@ describe("ToolDispatcher", () => {
setUserAgentOverride: vi.fn(async () => {}),
setTouchEmulationEnabled: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({ transport, sessions, cdp });
const dispatcher = new ToolDispatcher({ transport, sessions, cdp: cdp as TestDispatcherCdp });
dispatcher.start();
deliver(makeRequest("tool.session_stop", { session_id: "aa11" }));
@@ -311,6 +313,277 @@ describe("ToolDispatcher", () => {
expect(onBrowserControlResumed).toHaveBeenCalledWith("aa11");
});
it("reasserts remembered hover before follow-up work and releases only after actions", async () => {
vi.stubGlobal("chrome", {
tabs: {
sendMessage: vi.fn(async () => undefined),
},
});
const { transport } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => {}),
},
});
const order: string[] = [];
const cdp = {
send: vi.fn(async <T>() => {
order.push("hover");
return {} as T;
}),
detachSession: vi.fn(async () => {}),
ensureNetworkCapture: vi.fn(async () => {}),
networkEntriesSince: vi.fn(() => ({
tab_id: 7,
entries: [],
next_since: 0,
truncated: false,
})),
setDeviceMetricsOverride: vi.fn(async () => {}),
clearDeviceMetricsOverride: vi.fn(async () => {}),
setUserAgentOverride: vi.fn(async () => {}),
setTouchEmulationEnabled: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({ transport, sessions, cdp: cdp as TestDispatcherCdp });
(
dispatcher as unknown as { rememberHover: (sessionId: string, result: unknown) => unknown }
).rememberHover("aa11", {
tab_id: 7,
x: 10,
y: 20,
});
const helpers = dispatcher as unknown as {
withHoverReassert: <T>(
params: { session_id: string; tab_id?: number },
work: () => Promise<T>,
options?: { releaseAfter?: boolean },
) => Promise<T>;
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
};
await helpers.withHoverReassert({ session_id: "aa11", tab_id: 7 }, async () => {
order.push("observe");
return {};
});
expect(order).toEqual(["hover", "observe"]);
expect(chrome.tabs.sendMessage).not.toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
await helpers.setHoverBypass("aa11", 7, true);
await helpers.withHoverReassert(
{ session_id: "aa11", tab_id: 7 },
async () => {
order.push("click");
return {};
},
{ releaseAfter: true },
);
expect(cdp.send).toHaveBeenLastCalledWith(7, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: 10,
y: 20,
});
expect(chrome.tabs.sendMessage).toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
});
it("does not reassert or disable hover latches from another session", async () => {
vi.stubGlobal("chrome", {
tabs: {
sendMessage: vi.fn(async () => undefined),
},
});
const { transport } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => {}),
},
});
const cdp = {
send: vi.fn(async <T>() => ({}) as T),
detachSession: vi.fn(async () => {}),
ensureNetworkCapture: vi.fn(async () => {}),
networkEntriesSince: vi.fn(() => ({
tab_id: 7,
entries: [],
next_since: 0,
truncated: false,
})),
setDeviceMetricsOverride: vi.fn(async () => {}),
clearDeviceMetricsOverride: vi.fn(async () => {}),
setUserAgentOverride: vi.fn(async () => {}),
setTouchEmulationEnabled: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({ transport, sessions, cdp: cdp 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>,
options?: { releaseAfter?: boolean },
) => Promise<T>;
releaseHoverLatch: (sessionId?: string, tabId?: number) => Promise<void>;
};
helpers.rememberHover("aa11", { tab_id: 7, x: 10, y: 20 });
await helpers.setHoverBypass("aa11", 7, true);
await helpers.withHoverReassert({ session_id: "bb22", tab_id: 7 }, async () => ({}), {
releaseAfter: true,
});
expect(cdp.send).not.toHaveBeenCalled();
expect(chrome.tabs.sendMessage).not.toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
await helpers.releaseHoverLatch("aa11", 7);
expect(chrome.tabs.sendMessage).toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
});
it("transfers hover overlay bypass ownership between sessions", async () => {
vi.stubGlobal("chrome", {
tabs: {
sendMessage: vi.fn(async () => undefined),
},
});
const { transport } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
const helpers = dispatcher as unknown as {
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
};
await helpers.setHoverBypass("aa11", 7, true);
await helpers.setHoverBypass("bb22", 7, true);
await helpers.setHoverBypass("aa11", 7, false);
expect(chrome.tabs.sendMessage).not.toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
await helpers.setHoverBypass("bb22", 7, false);
expect(chrome.tabs.sendMessage).toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
expect(chrome.tabs.sendMessage).toHaveBeenCalledTimes(2);
});
it("limits default-target hover reassertion to the active tab", async () => {
vi.stubGlobal("chrome", {
tabs: {
query: vi.fn(async () => [{ id: 9, windowId: 4242, active: true }]),
get: vi.fn(async (tabId: number) => ({ id: tabId, windowId: 4242, active: tabId === 9 })),
sendMessage: vi.fn(async () => undefined),
},
});
const { transport } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
const cdp = {
send: vi.fn(async <T>() => ({}) as T),
detachSession: vi.fn(async () => {}),
ensureNetworkCapture: vi.fn(async () => {}),
networkEntriesSince: vi.fn(() => ({
tab_id: 9,
entries: [],
next_since: 0,
truncated: false,
})),
setDeviceMetricsOverride: vi.fn(async () => {}),
clearDeviceMetricsOverride: vi.fn(async () => {}),
setUserAgentOverride: vi.fn(async () => {}),
setTouchEmulationEnabled: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({ transport, sessions, cdp: cdp as TestDispatcherCdp });
const helpers = dispatcher as unknown as {
rememberHover: (sessionId: string, result: unknown) => unknown;
withHoverReassert: <T>(
params: { session_id: string; tab_id?: number },
work: () => Promise<T>,
) => Promise<T>;
};
helpers.rememberHover("aa11", { tab_id: 7, x: 10, y: 20 });
helpers.rememberHover("aa11", { tab_id: 9, x: 30, y: 40 });
await helpers.withHoverReassert({ session_id: "aa11" }, async () => ({}));
expect(cdp.send).toHaveBeenCalledTimes(1);
expect(cdp.send).toHaveBeenCalledWith(9, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: 30,
y: 40,
});
});
it("releases the current session hover latch before navigation-style work", async () => {
vi.stubGlobal("chrome", {
tabs: {
sendMessage: vi.fn(async () => undefined),
},
});
const { transport } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => {}),
},
});
const dispatcher = new ToolDispatcher({ transport, sessions });
const helpers = dispatcher as unknown as {
rememberHover: (sessionId: string, result: unknown) => unknown;
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
withHoverReleaseForRequest: <T>(
params: { session_id: string; tab_id?: number },
work: () => Promise<T>,
) => Promise<T>;
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);
await helpers.withHoverReleaseForRequest({ session_id: "aa11", tab_id: 7 }, async () => ({}));
await helpers.withHoverReassert({ session_id: "aa11", tab_id: 7 }, async () => ({}));
expect(chrome.tabs.sendMessage).toHaveBeenCalledWith(
7,
expect.objectContaining({ enabled: false }),
);
});
it("disconnects the transport when send() fails so keepalive can rebuild", async () => {
const { transport, deliver } = fakeTransport();
const sessions = new SessionManager({
@@ -4,6 +4,7 @@ import type { CdpRunner } from "@/tools/shared";
import {
handleClick,
handleFill,
handleHover,
handlePress,
handleSelect,
modifiersBitfield,
@@ -435,6 +436,50 @@ describe("handleClick", () => {
});
});
describe("handleHover", () => {
it("keeps overlay bypass enabled after a successful hover when requested", async () => {
const bypassOverlay = vi.fn().mockResolvedValue(undefined);
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e3", 1234, { tabId: 4 });
const fake = makeFakeCdp({
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.getContentQuads": () => ({ quads: [[10, 20, 110, 20, 110, 60, 10, 60]] }),
"Runtime.evaluate": (params: unknown) => {
const expr = String((params as { expression?: string })?.expression ?? "");
if (expr.includes("overlayHostPresent") && !expr.includes("hitIndex")) {
return { result: { value: { overlayHostPresent: true, overlayHostConnected: true } } };
}
if (expr.includes("hitIndex")) {
return {
result: {
value: { overlayHostPresent: true, overlayHostConnected: true, hitIndex: 0 },
},
};
}
throw new Error(`unexpected Runtime.evaluate: ${expr.slice(0, 80)}`);
},
"Input.dispatchMouseEvent": () => ({}),
});
const res = await handleHover(
sm,
{ session_id: "aa11", ref: "@e3", settle_ms: 0 },
{
cdp: fake.cdp,
tabsApi: fake.tabsApi,
bypassOverlay,
keepOverlayBypassAfterHover: true,
},
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res).toMatchObject({ tab_id: 4, used_ref: "e3", x: 60, y: 40 });
expect(bypassOverlay).toHaveBeenCalledTimes(1);
expect(bypassOverlay).toHaveBeenCalledWith(4, true);
});
});
describe("handleFill", () => {
it("returns not_found for unknown ref", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
@@ -1523,7 +1523,7 @@ describe("buildVomScene", () => {
expect(renderVom(scene).text).toContain("[§ active: Reviews (12)]");
});
it("maps hover surface probes to matching node labels", () => {
it("maps hover surface probes to matching backend node ids", () => {
const axNodes: CdpAxNode[] = [
{
nodeId: "1",
@@ -1544,7 +1544,7 @@ describe("buildVomScene", () => {
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{ triggerLabel: "Products", triggerAction: "hover", subItems: ["Shoes", "Bags"] },
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["Shoes", "Bags"] },
],
nodes: [
{
@@ -1573,7 +1573,260 @@ describe("buildVomScene", () => {
expect(scene.surfaces).toEqual([
{ triggerId: 20, triggerAction: "hover", subItems: ["Shoes", "Bags"] },
]);
expect(renderVom(scene).text).toContain('@e1 button "Products" [hover: Shoes | Bags]');
expect(renderVom(scene).text).toContain('@e1 button "Products" [hover first: Shoes | Bags]');
});
it("maps hover surface probes to rendered descendants in the same trigger subtree", () => {
const axNodes: CdpAxNode[] = [
{
nodeId: "1",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 10,
childIds: ["2"],
},
{
nodeId: "2",
parentId: "1",
role: { type: "role", value: "button" },
name: { type: "computedString", value: "image" },
backendDOMNodeId: 21,
},
];
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["My profile"] },
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
},
],
});
expect(renderVom(scene).text).toContain('@e1 button "image" [hover first: My profile]');
});
it("deduplicates hover surface probes by original trigger backend id", () => {
const axNodes: CdpAxNode[] = [
{
nodeId: "1",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 10,
childIds: ["2"],
},
{
nodeId: "2",
parentId: "1",
role: { type: "role", value: "button" },
name: { type: "computedString", value: "image" },
backendDOMNodeId: 21,
},
];
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["My profile"] },
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["Sign out"] },
{ triggerBackendNodeId: 21, triggerAction: "hover", subItems: ["Settings"] },
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
},
],
});
expect(scene.surfaces).toEqual([
{ triggerId: 21, triggerAction: "hover", subItems: ["My profile"] },
]);
});
it("maps hover surface probes to DOM-recovered custom controls", () => {
const axNodes: CdpAxNode[] = [
{
nodeId: "1",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 10,
childIds: ["2"],
},
{
nodeId: "2",
parentId: "1",
role: { type: "role", value: "img" },
name: { type: "computedString", value: "image" },
backendDOMNodeId: 21,
},
];
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{
triggerBackendNodeId: 20,
triggerPoint: { x: 915, y: 25 },
triggerAction: "hover",
subItems: ["My profile", "Sign out"],
},
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
cursor: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
},
],
});
expect(scene.surfaces).toEqual([
{ triggerId: 21, triggerAction: "hover", subItems: ["My profile", "Sign out"] },
]);
expect(renderVom(scene).text).toContain(
'@e1 button "image" [hover first: My profile | Sign out]',
);
});
it("does not attach hover probes to distant geometry matches", () => {
const axNodes: CdpAxNode[] = [
{
nodeId: "1",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 10,
childIds: ["2"],
},
{
nodeId: "2",
parentId: "1",
role: { type: "role", value: "link" },
name: { type: "computedString", value: "0" },
backendDOMNodeId: 42,
},
];
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{
triggerBackendNodeId: 999,
triggerPoint: { x: 900, y: 20 },
triggerAction: "hover",
subItems: ["My profile"],
},
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 42,
parentBackendNodeId: 10,
tag: "a",
attrs: {},
rect: { x: 860, y: 120, w: 40, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
],
});
expect(scene.surfaces).toBeUndefined();
expect(renderVom(scene).text).not.toContain("[hover first:");
});
it("enriches names and active scope signals from AX properties", () => {
@@ -2046,7 +2299,7 @@ describe("handleSnapshot", () => {
});
const res = await handleObserve(
sm,
{ session_id: "aa11" },
{ session_id: "aa11", debug_surfaces: true },
{
cdp: {
send: send as unknown as <T = unknown>(
@@ -2067,6 +2320,7 @@ describe("handleSnapshot", () => {
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.debug).toEqual({ surface_probes: [] });
expect(send).toHaveBeenCalledWith(
4,
"Runtime.evaluate",