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
@@ -0,0 +1,125 @@
import { describe, expect, it } from "vitest";
import { evaluateHoverTrigger } from "../hover-trigger-policy";
describe("evaluateHoverTrigger", () => {
it("accepts explicit popup triggers", () => {
const decision = evaluateHoverTrigger({
tag: "button",
role: "button",
label: "Open user navigation menu",
attrs: { "aria-haspopup": "menu", "aria-expanded": "false" },
rect: { x: 900, y: 8, w: 32, h: 32 },
cursor: "pointer",
pointerEvents: "auto",
});
expect(decision.eligible).toBe(true);
expect(decision.reasons).toEqual(
expect.arrayContaining(["aria-haspopup", "collapsed", "popup-signal"]),
);
});
it("accepts compact topbar image buttons without popup attributes", () => {
const decision = evaluateHoverTrigger({
tag: "button",
role: "button",
label: "image",
attrs: {},
rect: { x: 900, y: 8, w: 32, h: 32 },
pointerEvents: "auto",
hasGraphicDescendant: true,
});
expect(decision.eligible).toBe(true);
expect(decision.reasons).toEqual(expect.arrayContaining(["icon-only", "topbar", "compact"]));
});
it("accepts compact topbar image links without popup attributes", () => {
const decision = evaluateHoverTrigger({
tag: "a",
role: "link",
label: "image",
attrs: {},
rect: { x: 900, y: 8, w: 32, h: 32 },
pointerEvents: "auto",
hasGraphicDescendant: true,
});
expect(decision.eligible).toBe(true);
expect(decision.reasons).toEqual(expect.arrayContaining(["icon-only", "topbar", "compact"]));
});
it("rejects topbar menu links without surface trigger evidence", () => {
const decision = evaluateHoverTrigger({
tag: "a",
role: "link",
label: "My profile",
attrs: {},
rect: { x: 820, y: 72, w: 96, h: 32 },
cursor: "pointer",
pointerEvents: "auto",
});
expect(decision.eligible).toBe(false);
});
it("rejects text navigation items even when their attributes contain popup words", () => {
const decision = evaluateHoverTrigger({
tag: "a",
role: "link",
label: "My profile",
attrs: { class: "dropdown-item profile-link" },
rect: { x: 820, y: 72, w: 96, h: 32 },
cursor: "pointer",
pointerEvents: "auto",
});
expect(decision.eligible).toBe(false);
});
it("rejects labelled dropdown list items as hover triggers", () => {
const decision = evaluateHoverTrigger({
tag: "li",
label: "文档C+D",
attrs: { class: "dropdown-item", tabindex: "0" },
rect: { x: 820, y: 48, w: 160, h: 32 },
cursor: "pointer",
pointerEvents: "auto",
});
expect(decision.eligible).toBe(false);
});
it("rejects ordinary controls without hover popup signals", () => {
const decision = evaluateHoverTrigger({
tag: "button",
role: "button",
label: "Search",
attrs: {},
rect: { x: 100, y: 240, w: 120, h: 36 },
pointerEvents: "auto",
});
expect(decision.eligible).toBe(false);
});
it("rejects unsafe or non-visible triggers", () => {
expect(
evaluateHoverTrigger({
tag: "input",
attrs: {},
rect: { x: 10, y: 10, w: 80, h: 24 },
pointerEvents: "auto",
}).eligible,
).toBe(false);
expect(
evaluateHoverTrigger({
tag: "button",
role: "button",
attrs: { hidden: "" },
rect: { x: 10, y: 10, w: 80, h: 24 },
pointerEvents: "auto",
}).eligible,
).toBe(false);
});
});
@@ -130,6 +130,30 @@ describe("reduceTraceSteps", () => {
});
});
it("keeps hover steps before menu clicks", () => {
const { steps } = reduceTraceSteps(
[
{
op: "hover",
target: { tag: "span", role: "button", name: "Account" },
page_url: "https://example.com/app",
},
{
op: "click",
target: { tag: "a", role: "link", name: "Profile" },
page_url: "https://example.com/app",
},
],
"https://example.com/app",
);
expect(steps.map((s) => s.op)).toEqual(["hover", "click"]);
expect(steps[0]).toMatchObject({
op: "hover",
page: "p1",
target: { name: "Account" },
});
});
it("resolveTraceStartUrl prefers explicit start URL", () => {
expect(
resolveTraceStartUrl(
+14
View File
@@ -228,6 +228,20 @@ export function resolveClickableElement(target: Element): Element | null {
return null;
}
export function resolveHoverElement(target: Element): Element | null {
const clickable = resolveClickableElement(target);
if (clickable) return clickable;
let node: Element | null = target;
let depth = 0;
while (node && node !== document.body && node !== document.documentElement && depth < 8) {
if (looksClickable(node)) return node;
node = node.parentElement;
depth += 1;
}
return null;
}
/**
* Teachable clicks: the LLM must get a label it can later find via snapshot
* (visible name), or at least a form `name_attr` for checkbox/radio.
@@ -0,0 +1,178 @@
export interface HoverTriggerRect {
x: number;
y: number;
w: number;
h: number;
}
export interface HoverTriggerSignals {
tag: string;
role?: string;
label?: string;
attrs?: Record<string, string | undefined>;
rect?: HoverTriggerRect | null;
cursor?: string;
pointerEvents?: string;
hasGraphicDescendant?: boolean;
cssHoverMatch?: boolean;
}
export interface HoverTriggerDecision {
eligible: boolean;
score: number;
reasons: string[];
}
const HOVER_TRIGGER_MIN_SCORE = 45;
const HOVER_POPUP_SIGNAL_RE =
/(menu|dropdown|popover|popup|avatar|profile|account|user|more|ellipsis|caret)/;
const HOVER_TEXT_ITEM_RE = /(^|[\s_-])(dropdown-item|menu-item|context-menu-item|option)($|[\s_-])/;
function attr(signals: HoverTriggerSignals, name: string): string | undefined {
return signals.attrs?.[name.toLowerCase()];
}
export function isUnsafeHoverTrigger(signals: HoverTriggerSignals): boolean {
const tag = signals.tag.toLowerCase();
if (["input", "textarea", "select", "option"].includes(tag)) return true;
if ((attr(signals, "contenteditable") ?? "").toLowerCase() === "true") return true;
if (attr(signals, "disabled") !== undefined || attr(signals, "inert") !== undefined) return true;
return (attr(signals, "aria-disabled") ?? "").toLowerCase() === "true";
}
export function hasHoverPopupSignal(signals: HoverTriggerSignals): boolean {
const attrs = signals.attrs ?? {};
const haystack = [
attrs.id,
attrs.class,
attrs["data-testid"],
attrs["data-test"],
attrs["data-cy"],
attrs["aria-label"],
attrs["aria-haspopup"],
attrs["aria-controls"],
attrs.title,
signals.role === "button" ? signals.label : undefined,
]
.filter(Boolean)
.join(" ")
.toLowerCase();
return HOVER_POPUP_SIGNAL_RE.test(haystack);
}
export function hasStrongHoverExpansionSignal(signals: HoverTriggerSignals): boolean {
return (
signals.cssHoverMatch === true ||
attr(signals, "aria-haspopup") !== undefined ||
(attr(signals, "aria-expanded") ?? "").toLowerCase() === "false"
);
}
export function hasDirectHoverInteractiveSignal(signals: HoverTriggerSignals): boolean {
const tag = signals.tag.toLowerCase();
const role = (signals.role ?? "").toLowerCase();
return (
["button", "a", "summary"].includes(tag) ||
["button", "link", "menuitem", "tab", "combobox"].includes(role) ||
attr(signals, "tabindex") !== undefined ||
signals.cursor === "pointer" ||
attr(signals, "onclick") !== undefined ||
attr(signals, "onmouseenter") !== undefined ||
attr(signals, "onmouseover") !== undefined ||
attr(signals, "aria-haspopup") !== undefined ||
attr(signals, "aria-expanded") === "false"
);
}
export function evaluateHoverTrigger(signals: HoverTriggerSignals): HoverTriggerDecision {
const rect = signals.rect;
if (
!rect ||
rect.w <= 0 ||
rect.h <= 0 ||
signals.pointerEvents === "none" ||
attr(signals, "hidden") !== undefined ||
attr(signals, "inert") !== undefined ||
(attr(signals, "aria-hidden") ?? "").toLowerCase() === "true" ||
isUnsafeHoverTrigger(signals)
) {
return { eligible: false, score: 0, reasons: [] };
}
const area = rect.w * rect.h;
if (area <= 0 || area > 160_000) {
return { eligible: false, score: 0, reasons: [] };
}
const reasons: string[] = [];
let score = 0;
const tag = signals.tag.toLowerCase();
const role = (signals.role ?? "").toLowerCase();
const label = signals.label?.trim();
const graphic = signals.hasGraphicDescendant === true;
const directInteractive = hasDirectHoverInteractiveSignal(signals);
const popupSignal = hasHoverPopupSignal(signals);
const isTextNavigationItem =
(tag === "a" ||
tag === "li" ||
role === "link" ||
role === "option" ||
role.startsWith("menuitem") ||
HOVER_TEXT_ITEM_RE.test(attr(signals, "class") ?? "")) &&
!graphic &&
!!label &&
label.toLowerCase() !== "image";
const compactTopbarIcon =
(role === "button" || role === "link" || tag === "button" || tag === "a") &&
graphic &&
rect.y < 120 &&
rect.w <= 96 &&
rect.h <= 96 &&
(!label || label.toLowerCase() === "image");
const surfaceTriggerEvidence =
(popupSignal && !isTextNavigationItem) ||
compactTopbarIcon ||
hasStrongHoverExpansionSignal(signals);
if (!directInteractive || !surfaceTriggerEvidence) {
return { eligible: false, score: 0, reasons: [] };
}
if (attr(signals, "aria-haspopup") !== undefined) {
score += 80;
reasons.push("aria-haspopup");
}
if ((attr(signals, "aria-expanded") ?? "").toLowerCase() === "false") {
score += 55;
reasons.push("collapsed");
}
if (popupSignal) {
score += 45;
reasons.push("popup-signal");
}
if (tag === "button" || role === "button") {
score += 30;
reasons.push("button");
}
if (signals.cursor === "pointer") {
score += 25;
reasons.push("pointer");
}
if (graphic && (!label || label.toLowerCase() === "image")) {
score += 40;
reasons.push("icon-only");
}
if (rect.y < 120) {
score += 25;
reasons.push("topbar");
}
if (rect.w <= 80 && rect.h <= 80) {
score += 20;
reasons.push("compact");
}
if (signals.cssHoverMatch) {
score += 40;
reasons.push("css-hover");
}
return { eligible: score >= HOVER_TRIGGER_MIN_SCORE, score, reasons };
}
+1 -1
View File
@@ -41,7 +41,7 @@ export interface RecordStartMessage {
}
export interface RecordStepPayload {
op: "click" | "fill" | "press" | "select" | "navigate";
op: "click" | "hover" | "fill" | "press" | "select" | "navigate";
target?: TargetDescriptor;
value?: string;
key?: string;
@@ -21,6 +21,14 @@ function toDraftStep(payload: RecordStepPayload): DraftTraceStep | null {
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "hover":
return payload.target
? {
op: "hover",
target: payload.target,
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "fill":
return payload.target
? {
+7
View File
@@ -139,6 +139,13 @@ function toV2Step(
},
effectForNavigation(step.navigated_to, urlToId),
);
case "hover":
return {
op: "hover",
id,
page,
target: step.target,
};
case "fill":
return {
op: "fill",