mirror of
https://github.com/Tencent/BrowserSkill.git
synced 2026-09-10 13:01:23 +08:00
feat: add bsk record for semantic user-action traces
Capture user actions in the Agent Window and export a record-only trace (pages[] + navigate/click/fill/select/press steps with target descriptors). Adds the record overlay UI aligned with the control overlay, and wires record start/stop/await through CLI, daemon, protocol, and extension.
This commit is contained in:
@@ -0,0 +1,117 @@
|
||||
import { beforeEach, describe, expect, it } from "vitest";
|
||||
import {
|
||||
describeEventTarget,
|
||||
describeTarget,
|
||||
isMeaningfulClickTarget,
|
||||
} from "../describe-target";
|
||||
|
||||
describe("describeTarget", () => {
|
||||
beforeEach(() => {
|
||||
document.body.innerHTML = "";
|
||||
});
|
||||
|
||||
it("prefers aria-label and button role", () => {
|
||||
document.body.innerHTML = `<button aria-label="发布">go</button>`;
|
||||
const el = document.querySelector("button")!;
|
||||
expect(describeTarget(el)).toEqual({
|
||||
tag: "button",
|
||||
role: "button",
|
||||
name: "发布",
|
||||
});
|
||||
});
|
||||
|
||||
it("uses label text and name_attr for inputs", () => {
|
||||
document.body.innerHTML = `
|
||||
<label for="svc">服务名称</label>
|
||||
<input id="svc" name="serviceName" />
|
||||
`;
|
||||
const el = document.querySelector("input")!;
|
||||
expect(describeTarget(el)).toEqual({
|
||||
tag: "input",
|
||||
role: "textbox",
|
||||
name: "服务名称",
|
||||
name_attr: "serviceName",
|
||||
});
|
||||
});
|
||||
|
||||
it("never invents CSS selectors or @eN", () => {
|
||||
document.body.innerHTML = `<a href="/x">详情</a>`;
|
||||
const desc = describeTarget(document.querySelector("a")!);
|
||||
expect(JSON.stringify(desc)).not.toMatch(/@e\d+|nth-of-type|#/);
|
||||
expect(desc).toEqual({ tag: "a", role: "link", name: "详情" });
|
||||
});
|
||||
|
||||
it("prefers heading text inside SERP-style links", () => {
|
||||
document.body.innerHTML = `
|
||||
<a href="https://www.tencent.com">
|
||||
<h3>Tencent 腾讯</h3>
|
||||
<cite>https://www.tencent.com</cite>
|
||||
</a>
|
||||
`;
|
||||
expect(describeTarget(document.querySelector("a")!).name).toBe("Tencent 腾讯");
|
||||
});
|
||||
});
|
||||
|
||||
describe("LLM textbook click targets", () => {
|
||||
beforeEach(() => {
|
||||
document.body.innerHTML = "";
|
||||
});
|
||||
|
||||
it("rejects tag-only targets the LLM cannot find", () => {
|
||||
expect(isMeaningfulClickTarget({ tag: "div" })).toBe(false);
|
||||
});
|
||||
|
||||
it("treats a short visible name as the teaching signal", () => {
|
||||
expect(isMeaningfulClickTarget({ tag: "div", name: "发布" })).toBe(true);
|
||||
});
|
||||
|
||||
it("ignores anonymous layout chrome and lifts child clicks to the named button", () => {
|
||||
document.body.innerHTML = `
|
||||
<div id="noise">background</div>
|
||||
<button type="button"><span id="icon">发布</span></button>
|
||||
`;
|
||||
expect(describeEventTarget(document.querySelector("#noise"))).toBeNull();
|
||||
expect(describeEventTarget(document.querySelector("#icon"))).toEqual({
|
||||
tag: "button",
|
||||
role: "button",
|
||||
name: "发布",
|
||||
});
|
||||
});
|
||||
|
||||
it("does not attach layout sibling text as nearby_label on buttons", () => {
|
||||
document.body.innerHTML = `
|
||||
<div>background</div>
|
||||
<button type="button" id="pub">发布</button>
|
||||
`;
|
||||
expect(describeTarget(document.querySelector("#pub")!)).toEqual({
|
||||
tag: "button",
|
||||
role: "button",
|
||||
name: "发布",
|
||||
});
|
||||
});
|
||||
|
||||
it("keeps nearby_label for form fields from a preceding label-like sibling", () => {
|
||||
document.body.innerHTML = `
|
||||
<div>服务名称</div>
|
||||
<input id="svc" />
|
||||
`;
|
||||
expect(describeTarget(document.querySelector("#svc")!)).toEqual(
|
||||
expect.objectContaining({
|
||||
tag: "input",
|
||||
nearby_label: "服务名称",
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it("does not treat plain text blocks as clicks", () => {
|
||||
document.body.innerHTML = `<p id="copy">说明文字</p>`;
|
||||
expect(describeEventTarget(document.querySelector("#copy"))).toBeNull();
|
||||
});
|
||||
|
||||
it("records custom button-like controls by their visible label", () => {
|
||||
document.body.innerHTML = `<div class="btn" id="pub" style="cursor: pointer">发布</div>`;
|
||||
expect(describeEventTarget(document.querySelector("#pub"))).toEqual(
|
||||
expect.objectContaining({ tag: "div", name: "发布" }),
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,80 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { appendRecordedPayload, observeRecordedNavigation } from "../recording-step-buffer";
|
||||
|
||||
describe("recording-step-buffer", () => {
|
||||
it("stores semantic click without summary", () => {
|
||||
const buffer = { steps: [], pendingNavigation: false };
|
||||
appendRecordedPayload(buffer, {
|
||||
op: "click",
|
||||
target: { tag: "button", role: "button", name: "发布" },
|
||||
expects_navigation: true,
|
||||
});
|
||||
expect(buffer.steps).toEqual([
|
||||
{
|
||||
op: "click",
|
||||
target: { tag: "button", role: "button", name: "发布" },
|
||||
},
|
||||
]);
|
||||
expect(buffer.pendingNavigation).toBe(true);
|
||||
});
|
||||
|
||||
it("annotates navigated_to on action-caused navigation instead of wait_for_navigation", () => {
|
||||
const buffer = {
|
||||
steps: [
|
||||
{
|
||||
op: "click" as const,
|
||||
target: { tag: "button", role: "button", name: "发布" },
|
||||
},
|
||||
],
|
||||
currentUrl: "https://example.com/a",
|
||||
pendingNavigation: true,
|
||||
pendingNavigationDeadline: Date.now() + 5_000,
|
||||
};
|
||||
observeRecordedNavigation(buffer, "https://example.com/b", true);
|
||||
expect(buffer.steps).toEqual([
|
||||
{
|
||||
op: "click",
|
||||
target: { tag: "button", role: "button", name: "发布" },
|
||||
navigated_to: "https://example.com/b",
|
||||
},
|
||||
]);
|
||||
expect(JSON.stringify(buffer.steps)).not.toContain("wait_for_navigation");
|
||||
});
|
||||
|
||||
it("annotates navigated_to onto a select that auto-submits a navigation", () => {
|
||||
const buffer = {
|
||||
steps: [
|
||||
{
|
||||
op: "select" as const,
|
||||
target: { tag: "select", role: "combobox", name: "分类" },
|
||||
values: ["tech"],
|
||||
},
|
||||
],
|
||||
currentUrl: "https://example.com/list",
|
||||
pendingNavigation: true,
|
||||
pendingNavigationDeadline: Date.now() + 5_000,
|
||||
};
|
||||
observeRecordedNavigation(buffer, "https://example.com/list?cat=tech", true);
|
||||
expect(buffer.steps).toEqual([
|
||||
{
|
||||
op: "select",
|
||||
target: { tag: "select", role: "combobox", name: "分类" },
|
||||
values: ["tech"],
|
||||
navigated_to: "https://example.com/list?cat=tech",
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
it("emits navigate for uncaused URL changes", () => {
|
||||
const buffer = {
|
||||
steps: [],
|
||||
currentUrl: "https://example.com/a",
|
||||
pendingNavigation: false,
|
||||
};
|
||||
observeRecordedNavigation(buffer, "https://example.com/b", false);
|
||||
expect(buffer.steps[0]).toMatchObject({
|
||||
op: "navigate",
|
||||
url: "https://example.com/b",
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,141 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { DraftTraceStep } from "@/transport/types";
|
||||
import { reduceTraceSteps, resolveTraceStartUrl, shouldRecordPress } from "../trace-reducer";
|
||||
|
||||
describe("shouldRecordPress", () => {
|
||||
it("keeps Enter and Escape", () => {
|
||||
expect(shouldRecordPress("Enter")).toBe(true);
|
||||
expect(shouldRecordPress("Escape")).toBe(true);
|
||||
});
|
||||
|
||||
it("drops modifiers, clipboard shortcuts, and bare typing", () => {
|
||||
expect(shouldRecordPress("Meta")).toBe(false);
|
||||
expect(shouldRecordPress("c", ["meta"])).toBe(false);
|
||||
expect(shouldRecordPress("a", ["ctrl"])).toBe(false);
|
||||
expect(shouldRecordPress("x")).toBe(false);
|
||||
expect(shouldRecordPress("中")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("reduceTraceSteps", () => {
|
||||
it("builds steps with pages dictionary and page id references", () => {
|
||||
const drafts: DraftTraceStep[] = [
|
||||
{
|
||||
op: "navigate",
|
||||
url: "https://example.com/search?q=hello&utm_source=x",
|
||||
page_url: "https://example.com/search?q=hello&utm_source=x",
|
||||
},
|
||||
{
|
||||
op: "fill",
|
||||
target: { tag: "input", role: "textbox", name: "搜索", name_attr: "q" },
|
||||
value: "browser skill",
|
||||
page_url: "https://example.com/search?q=hello&utm_source=x",
|
||||
},
|
||||
{
|
||||
op: "press",
|
||||
key: "Enter",
|
||||
target: { tag: "input", role: "textbox", name: "搜索", name_attr: "q" },
|
||||
navigated_to: "https://example.com/results/42",
|
||||
page_url: "https://example.com/search?q=hello&utm_source=x",
|
||||
},
|
||||
{
|
||||
op: "click",
|
||||
target: { tag: "button", role: "button", name: "发布" },
|
||||
navigated_to: "https://example.com/p/99",
|
||||
page_url: "https://example.com/results/42",
|
||||
},
|
||||
{
|
||||
op: "press",
|
||||
key: "a",
|
||||
page_url: "https://example.com/p/99",
|
||||
},
|
||||
];
|
||||
|
||||
const { pages, steps } = reduceTraceSteps(
|
||||
drafts,
|
||||
"https://example.com/search?q=hello&utm_source=x",
|
||||
);
|
||||
expect(JSON.stringify(steps)).not.toContain("parameters");
|
||||
expect(JSON.stringify(steps)).not.toContain("intent");
|
||||
expect(JSON.stringify(steps)).not.toContain("summary");
|
||||
expect(steps.map((s) => s.op)).toEqual(["navigate", "fill", "press", "click"]);
|
||||
expect(pages.map((p) => p.url)).toEqual([
|
||||
"https://example.com/search?q=hello&utm_source=x",
|
||||
"https://example.com/results/42",
|
||||
"https://example.com/p/99",
|
||||
]);
|
||||
|
||||
expect(steps[0]).toMatchObject({
|
||||
id: 1,
|
||||
op: "navigate",
|
||||
page: "p1",
|
||||
to: "https://example.com/search?q=hello&utm_source=x",
|
||||
});
|
||||
|
||||
expect(steps[1]).toMatchObject({
|
||||
op: "fill",
|
||||
page: "p1",
|
||||
value: "browser skill",
|
||||
});
|
||||
|
||||
expect(steps[2]).toMatchObject({
|
||||
op: "press",
|
||||
key: "Enter",
|
||||
page: "p1",
|
||||
effect: { navigated_to: "p2" },
|
||||
});
|
||||
|
||||
expect(steps[3]).toMatchObject({
|
||||
op: "click",
|
||||
page: "p2",
|
||||
effect: { navigated_to: "p3" },
|
||||
});
|
||||
});
|
||||
|
||||
it("collapses consecutive navigations", () => {
|
||||
const { steps } = reduceTraceSteps([
|
||||
{ op: "navigate", url: "https://a.example/redirect1" },
|
||||
{ op: "navigate", url: "https://a.example/final" },
|
||||
]);
|
||||
expect(steps).toHaveLength(1);
|
||||
expect(steps[0]).toMatchObject({
|
||||
op: "navigate",
|
||||
to: "https://a.example/final",
|
||||
});
|
||||
});
|
||||
|
||||
it("maps select navigated_to onto effect.navigated_to (page id)", () => {
|
||||
const { pages, steps } = reduceTraceSteps(
|
||||
[
|
||||
{
|
||||
op: "select",
|
||||
target: { tag: "select", role: "combobox", name: "分类" },
|
||||
values: ["tech"],
|
||||
labels: ["技术"],
|
||||
navigated_to: "https://example.com/list?cat=tech",
|
||||
page_url: "https://example.com/list",
|
||||
},
|
||||
],
|
||||
"https://example.com/list",
|
||||
);
|
||||
expect(pages.map((p) => p.url)).toEqual([
|
||||
"https://example.com/list",
|
||||
"https://example.com/list?cat=tech",
|
||||
]);
|
||||
expect(steps[0]).toMatchObject({
|
||||
op: "select",
|
||||
page: "p1",
|
||||
selection: [{ value: "tech", label: "技术" }],
|
||||
effect: { navigated_to: "p2" },
|
||||
});
|
||||
});
|
||||
|
||||
it("resolveTraceStartUrl prefers explicit start URL", () => {
|
||||
expect(
|
||||
resolveTraceStartUrl(
|
||||
[{ op: "navigate", url: "https://example.com/other" }],
|
||||
"https://example.com/start",
|
||||
),
|
||||
).toBe("https://example.com/start");
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,342 @@
|
||||
/**
|
||||
* Build a semantic TargetDescriptor for an interacted element.
|
||||
*
|
||||
* Trace steps are an LLM *textbook*: each click must say what to look for
|
||||
* on screen (usually a short visible name). Tag-only noise like
|
||||
* `{ "tag": "div" }` / “点击div” is useless and must not be recorded.
|
||||
*/
|
||||
|
||||
export interface TargetDescriptor {
|
||||
role?: string;
|
||||
name?: string;
|
||||
tag: string;
|
||||
name_attr?: string;
|
||||
placeholder?: string;
|
||||
nearby_label?: string;
|
||||
}
|
||||
|
||||
/** Max length for a label that is still a useful “find this on screen” hint. */
|
||||
const ACTIONABLE_LABEL_MAX = 48;
|
||||
|
||||
function normalizeWhitespace(value: string): string {
|
||||
return value.replace(/\s+/g, " ").trim();
|
||||
}
|
||||
|
||||
function truncate(value: string, max = 80): string {
|
||||
const trimmed = normalizeWhitespace(value);
|
||||
if (trimmed.length <= max) return trimmed;
|
||||
return `${trimmed.slice(0, max - 1)}…`;
|
||||
}
|
||||
|
||||
/** Short, human label an LLM can search for in a snapshot. */
|
||||
export function isActionableLabel(name: string): boolean {
|
||||
const trimmed = normalizeWhitespace(name);
|
||||
if (!trimmed) return false;
|
||||
if (trimmed.length > ACTIONABLE_LABEL_MAX) return false;
|
||||
if (/^https?:\/\//i.test(trimmed)) return false;
|
||||
return true;
|
||||
}
|
||||
|
||||
function labelledByText(el: Element): string | null {
|
||||
const ids = el.getAttribute("aria-labelledby");
|
||||
if (!ids) return null;
|
||||
const parts = ids
|
||||
.split(/\s+/)
|
||||
.map((id) => document.getElementById(id)?.textContent ?? "")
|
||||
.map(normalizeWhitespace)
|
||||
.filter(Boolean);
|
||||
return parts.length ? truncate(parts.join(" ")) : null;
|
||||
}
|
||||
|
||||
function associatedLabelText(el: Element): string | null {
|
||||
if (!(el instanceof HTMLElement) || !el.id) return null;
|
||||
const label = document.querySelector(`label[for="${CSS.escape(el.id)}"]`);
|
||||
if (!label) return null;
|
||||
const text = normalizeWhitespace(label.textContent ?? "");
|
||||
return text ? truncate(text) : null;
|
||||
}
|
||||
|
||||
function wrappingLabelText(el: Element): string | null {
|
||||
const label = el.closest("label");
|
||||
if (!label) return null;
|
||||
const clone = label.cloneNode(true) as HTMLElement;
|
||||
for (const control of clone.querySelectorAll("input,textarea,select,button")) {
|
||||
control.remove();
|
||||
}
|
||||
const text = normalizeWhitespace(clone.textContent ?? "");
|
||||
return text ? truncate(text) : null;
|
||||
}
|
||||
|
||||
function placeholderOrTitle(el: Element): string | null {
|
||||
if (el instanceof HTMLInputElement || el instanceof HTMLTextAreaElement) {
|
||||
const ph = normalizeWhitespace(el.placeholder);
|
||||
if (ph) return truncate(ph);
|
||||
}
|
||||
const title = normalizeWhitespace(el.getAttribute("title") ?? "");
|
||||
return title ? truncate(title) : null;
|
||||
}
|
||||
|
||||
function ownText(el: Element): string | null {
|
||||
if (el instanceof HTMLInputElement || el instanceof HTMLTextAreaElement) {
|
||||
return null;
|
||||
}
|
||||
const text = normalizeWhitespace(el.textContent ?? "");
|
||||
return text ? truncate(text) : null;
|
||||
}
|
||||
|
||||
/** Prefer a compact title inside links (e.g. SERP result `<h3>`), not the whole blob. */
|
||||
function compactLinkName(el: Element): string | null {
|
||||
const heading = el.querySelector("h1, h2, h3, h4");
|
||||
if (heading) {
|
||||
const text = normalizeWhitespace(heading.textContent ?? "");
|
||||
if (text) return truncate(text);
|
||||
}
|
||||
const img = el.querySelector("img[alt]");
|
||||
if (img instanceof HTMLImageElement) {
|
||||
const alt = normalizeWhitespace(img.alt);
|
||||
if (alt) return truncate(alt);
|
||||
}
|
||||
const clone = el.cloneNode(true) as HTMLElement;
|
||||
for (const junk of clone.querySelectorAll("cite, script, style, svg, noscript")) {
|
||||
junk.remove();
|
||||
}
|
||||
const text = normalizeWhitespace(clone.textContent ?? "");
|
||||
if (!text) return null;
|
||||
const withoutUrl = text.replace(/https?:\/\/\S+/g, "").trim();
|
||||
return truncate(withoutUrl || text);
|
||||
}
|
||||
|
||||
/** Visible accessible name preference order for LLM textbooks. */
|
||||
export function accessibleName(el: Element): string | undefined {
|
||||
const ariaLabel = normalizeWhitespace(el.getAttribute("aria-label") ?? "");
|
||||
if (ariaLabel) return truncate(ariaLabel);
|
||||
|
||||
const labelledBy = labelledByText(el);
|
||||
if (labelledBy) return labelledBy;
|
||||
|
||||
const forLabel = associatedLabelText(el);
|
||||
if (forLabel) return forLabel;
|
||||
|
||||
const wrapLabel = wrappingLabelText(el);
|
||||
if (wrapLabel) return wrapLabel;
|
||||
|
||||
const alt =
|
||||
el instanceof HTMLImageElement
|
||||
? normalizeWhitespace(el.alt)
|
||||
: normalizeWhitespace(el.getAttribute("alt") ?? "");
|
||||
if (alt) return truncate(alt);
|
||||
|
||||
const ph = placeholderOrTitle(el);
|
||||
if (ph) return ph;
|
||||
|
||||
const tag = el.tagName.toLowerCase();
|
||||
if (tag === "a" || el.getAttribute("role") === "link") {
|
||||
const linkName = compactLinkName(el);
|
||||
if (linkName) return linkName;
|
||||
}
|
||||
|
||||
const text = ownText(el);
|
||||
if (text) return text;
|
||||
|
||||
if (el instanceof HTMLInputElement || el instanceof HTMLButtonElement) {
|
||||
const value = normalizeWhitespace(el.value);
|
||||
if (value && (el instanceof HTMLButtonElement || el.type === "submit" || el.type === "button")) {
|
||||
return truncate(value);
|
||||
}
|
||||
}
|
||||
|
||||
return undefined;
|
||||
}
|
||||
|
||||
const INTERACTIVE_SELECTOR = [
|
||||
"a[href]",
|
||||
"button",
|
||||
"summary",
|
||||
"select",
|
||||
'input:not([type="hidden"])',
|
||||
"textarea",
|
||||
'[role="button"]',
|
||||
'[role="link"]',
|
||||
'[role="tab"]',
|
||||
'[role="menuitem"]',
|
||||
'[role="menuitemcheckbox"]',
|
||||
'[role="menuitemradio"]',
|
||||
'[role="option"]',
|
||||
'[role="checkbox"]',
|
||||
'[role="radio"]',
|
||||
'[role="switch"]',
|
||||
'[role="treeitem"]',
|
||||
'[role="combobox"]',
|
||||
'[contenteditable]:not([contenteditable="false"])',
|
||||
].join(",");
|
||||
|
||||
const INTERACTIVE_ROLES = new Set([
|
||||
"button",
|
||||
"link",
|
||||
"tab",
|
||||
"menuitem",
|
||||
"menuitemcheckbox",
|
||||
"menuitemradio",
|
||||
"option",
|
||||
"checkbox",
|
||||
"radio",
|
||||
"switch",
|
||||
"treeitem",
|
||||
"combobox",
|
||||
"textbox",
|
||||
"searchbox",
|
||||
"slider",
|
||||
]);
|
||||
|
||||
function looksClickable(el: Element): boolean {
|
||||
if (!(el instanceof HTMLElement)) return false;
|
||||
if (el.matches(INTERACTIVE_SELECTOR)) return true;
|
||||
const role = normalizeWhitespace(el.getAttribute("role") ?? "").toLowerCase();
|
||||
if (role && INTERACTIVE_ROLES.has(role)) return true;
|
||||
if (el.tabIndex >= 0) return true;
|
||||
try {
|
||||
if (getComputedStyle(el).cursor === "pointer") return true;
|
||||
} catch {
|
||||
// happy-dom / detached nodes
|
||||
}
|
||||
const cls = typeof el.className === "string" ? el.className : "";
|
||||
if (/\b(btn|button|link|clickable|action)\b/i.test(cls)) return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the element a click should describe for the LLM textbook.
|
||||
* Never falls back to an anonymous layout `div`.
|
||||
*/
|
||||
export function resolveClickableElement(target: Element): Element | null {
|
||||
const interactive = target.closest(INTERACTIVE_SELECTOR);
|
||||
if (interactive instanceof Element) return interactive;
|
||||
|
||||
let node: Element | null = target;
|
||||
let depth = 0;
|
||||
while (node && node !== document.body && node !== document.documentElement && depth < 8) {
|
||||
const name = accessibleName(node);
|
||||
if (name && isActionableLabel(name) && 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.
|
||||
* Recording “点击div” with no name fails this bar.
|
||||
*/
|
||||
export function isMeaningfulClickTarget(target: TargetDescriptor): boolean {
|
||||
const name = target.name?.trim();
|
||||
if (name && isActionableLabel(name)) return true;
|
||||
if (
|
||||
(target.role === "checkbox" || target.role === "radio" || target.tag === "input") &&
|
||||
target.name_attr
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
export function inferRole(el: Element): string | undefined {
|
||||
const explicit = normalizeWhitespace(el.getAttribute("role") ?? "").toLowerCase();
|
||||
if (explicit) return explicit;
|
||||
|
||||
const tag = el.tagName.toLowerCase();
|
||||
if (tag === "button") return "button";
|
||||
if (tag === "a" && el.hasAttribute("href")) return "link";
|
||||
if (tag === "select") return "combobox";
|
||||
if (tag === "textarea") return "textbox";
|
||||
if (tag === "img") return "img";
|
||||
if (tag === "summary") return "button";
|
||||
if (el instanceof HTMLElement && (el.isContentEditable || el.contentEditable === "true")) {
|
||||
return "textbox";
|
||||
}
|
||||
if (el instanceof HTMLInputElement) {
|
||||
const type = el.type.toLowerCase();
|
||||
if (type === "checkbox") return "checkbox";
|
||||
if (type === "radio") return "radio";
|
||||
if (type === "submit" || type === "button" || type === "image" || type === "reset") {
|
||||
return "button";
|
||||
}
|
||||
if (type === "range") return "slider";
|
||||
return "textbox";
|
||||
}
|
||||
return undefined;
|
||||
}
|
||||
|
||||
/**
|
||||
* Nearby labels help the LLM name form fields. Only apply to fillable
|
||||
* controls — never to buttons/links, where a previous layout sibling
|
||||
* (e.g. a chrome `<div>`) would pollute the textbook target.
|
||||
*/
|
||||
function nearbyLabelText(el: Element): string | undefined {
|
||||
if (
|
||||
!(
|
||||
el instanceof HTMLInputElement ||
|
||||
el instanceof HTMLTextAreaElement ||
|
||||
el instanceof HTMLSelectElement
|
||||
)
|
||||
) {
|
||||
return undefined;
|
||||
}
|
||||
if (el.id) {
|
||||
const byFor = document.querySelector(`label[for="${CSS.escape(el.id)}"]`);
|
||||
const text = byFor ? normalizeWhitespace(byFor.textContent ?? "") : "";
|
||||
if (text) return truncate(text, ACTIONABLE_LABEL_MAX);
|
||||
}
|
||||
const wrapped = el.closest("label");
|
||||
if (wrapped) {
|
||||
const clone = wrapped.cloneNode(true) as HTMLLabelElement;
|
||||
for (const control of clone.querySelectorAll("input, textarea, select, button")) {
|
||||
control.remove();
|
||||
}
|
||||
const text = normalizeWhitespace(clone.textContent ?? "");
|
||||
if (text) return truncate(text, ACTIONABLE_LABEL_MAX);
|
||||
}
|
||||
const prev = el.previousElementSibling;
|
||||
if (prev && /^(LABEL|SPAN|DIV|P|DT)$/i.test(prev.tagName)) {
|
||||
const text = normalizeWhitespace(prev.textContent ?? "");
|
||||
if (text && text.length <= ACTIONABLE_LABEL_MAX) return text;
|
||||
}
|
||||
return undefined;
|
||||
}
|
||||
|
||||
export function describeTarget(el: Element): TargetDescriptor {
|
||||
const tag = el.tagName.toLowerCase();
|
||||
const role = inferRole(el);
|
||||
const name = accessibleName(el);
|
||||
const nameAttr =
|
||||
el instanceof HTMLInputElement ||
|
||||
el instanceof HTMLTextAreaElement ||
|
||||
el instanceof HTMLSelectElement ||
|
||||
el instanceof HTMLButtonElement
|
||||
? normalizeWhitespace(el.name) || undefined
|
||||
: normalizeWhitespace(el.getAttribute("name") ?? "") || undefined;
|
||||
const placeholder =
|
||||
el instanceof HTMLInputElement || el instanceof HTMLTextAreaElement
|
||||
? normalizeWhitespace(el.placeholder) || undefined
|
||||
: normalizeWhitespace(el.getAttribute("placeholder") ?? "") || undefined;
|
||||
const nearby = nearbyLabelText(el);
|
||||
|
||||
return {
|
||||
tag,
|
||||
...(role ? { role } : {}),
|
||||
...(name ? { name } : {}),
|
||||
...(nameAttr ? { name_attr: nameAttr } : {}),
|
||||
...(placeholder ? { placeholder } : {}),
|
||||
...(nearby && nearby !== name ? { nearby_label: nearby } : {}),
|
||||
};
|
||||
}
|
||||
|
||||
export function describeEventTarget(target: EventTarget | null): TargetDescriptor | null {
|
||||
if (!(target instanceof Element)) return null;
|
||||
const clickable = resolveClickableElement(target);
|
||||
if (!clickable) return null;
|
||||
const desc = describeTarget(clickable);
|
||||
return isMeaningfulClickTarget(desc) ? desc : null;
|
||||
}
|
||||
@@ -0,0 +1,111 @@
|
||||
/**
|
||||
* Wire protocol for user-action recording, sent between the background
|
||||
* service worker and a tab's content script.
|
||||
*/
|
||||
|
||||
import type { TargetDescriptor } from "./describe-target";
|
||||
|
||||
export const RECORD_START = "bsk-record-start";
|
||||
export const RECORD_STEP = "bsk-record-step";
|
||||
export const RECORD_STOP = "bsk-record-stop";
|
||||
export const RECORD_CANCEL = "bsk-record-cancel";
|
||||
export const RECORD_FINISH = "bsk-record-finish";
|
||||
export const RECORD_QUERY = "bsk-record-query";
|
||||
|
||||
export interface RecordStartAck {
|
||||
ok: true;
|
||||
}
|
||||
|
||||
export type RecordStopAck = { ok: true } | { ok: false; error: string };
|
||||
|
||||
export interface RecordQueryMessage {
|
||||
type: typeof RECORD_QUERY;
|
||||
}
|
||||
|
||||
export interface RecordQueryResponse {
|
||||
active: boolean;
|
||||
requestId?: string;
|
||||
}
|
||||
|
||||
export interface RecordStartMessage {
|
||||
type: typeof RECORD_START;
|
||||
requestId: string;
|
||||
}
|
||||
|
||||
export interface RecordStepPayload {
|
||||
op: "click" | "fill" | "press" | "select" | "navigate";
|
||||
target?: TargetDescriptor;
|
||||
value?: string;
|
||||
key?: string;
|
||||
modifiers?: Array<"alt" | "ctrl" | "meta" | "shift">;
|
||||
values?: string[];
|
||||
labels?: string[];
|
||||
url?: string;
|
||||
redacted?: boolean;
|
||||
/** Page URL when the step was captured. */
|
||||
page_url?: string;
|
||||
/** Capture-only hint; never persisted unless converted to navigated_to. */
|
||||
expects_navigation?: boolean;
|
||||
/** Whether an observed URL change was synchronously caused by the action. */
|
||||
navigation_caused_by_action?: boolean;
|
||||
}
|
||||
|
||||
export interface RecordStepMessage {
|
||||
type: typeof RECORD_STEP;
|
||||
requestId: string;
|
||||
step: RecordStepPayload;
|
||||
}
|
||||
|
||||
export interface RecordStopMessage {
|
||||
type: typeof RECORD_STOP;
|
||||
requestId: string;
|
||||
}
|
||||
|
||||
export interface RecordCancelMessage {
|
||||
type: typeof RECORD_CANCEL;
|
||||
requestId: string;
|
||||
}
|
||||
|
||||
export interface RecordFinishMessage {
|
||||
type: typeof RECORD_FINISH;
|
||||
requestId: string;
|
||||
}
|
||||
|
||||
export function isRecordStartMessage(msg: unknown): msg is RecordStartMessage {
|
||||
if (typeof msg !== "object" || msg === null) return false;
|
||||
const m = msg as Record<string, unknown>;
|
||||
return m.type === RECORD_START && typeof m.requestId === "string";
|
||||
}
|
||||
|
||||
export function isRecordStopMessage(msg: unknown): msg is RecordStopMessage {
|
||||
if (typeof msg !== "object" || msg === null) return false;
|
||||
const m = msg as Record<string, unknown>;
|
||||
return m.type === RECORD_STOP && typeof m.requestId === "string";
|
||||
}
|
||||
|
||||
export function isRecordCancelMessage(msg: unknown): msg is RecordCancelMessage {
|
||||
if (typeof msg !== "object" || msg === null) return false;
|
||||
const m = msg as Record<string, unknown>;
|
||||
return m.type === RECORD_CANCEL && typeof m.requestId === "string";
|
||||
}
|
||||
|
||||
export function isRecordFinishMessage(msg: unknown): msg is RecordFinishMessage {
|
||||
if (typeof msg !== "object" || msg === null) return false;
|
||||
const m = msg as Record<string, unknown>;
|
||||
return m.type === RECORD_FINISH && typeof m.requestId === "string";
|
||||
}
|
||||
|
||||
export function isRecordQueryMessage(msg: unknown): msg is RecordQueryMessage {
|
||||
if (typeof msg !== "object" || msg === null) return false;
|
||||
const m = msg as Record<string, unknown>;
|
||||
return m.type === RECORD_QUERY;
|
||||
}
|
||||
|
||||
export function isRecordStepMessage(msg: unknown): msg is RecordStepMessage {
|
||||
if (typeof msg !== "object" || msg === null) return false;
|
||||
const m = msg as Record<string, unknown>;
|
||||
if (m.type !== RECORD_STEP || typeof m.requestId !== "string") return false;
|
||||
const step = m.step;
|
||||
if (typeof step !== "object" || step === null) return false;
|
||||
return typeof (step as RecordStepPayload).op === "string";
|
||||
}
|
||||
@@ -0,0 +1,128 @@
|
||||
import type { DraftTraceStep } from "@/transport/types";
|
||||
import type { RecordStepPayload } from "./record-bridge";
|
||||
|
||||
export interface RecordingStepBuffer {
|
||||
steps: DraftTraceStep[];
|
||||
currentUrl?: string;
|
||||
pendingNavigation: boolean;
|
||||
pendingNavigationDeadline?: number;
|
||||
}
|
||||
|
||||
const NAVIGATION_TRIGGER_WINDOW_MS = 3_000;
|
||||
|
||||
function toDraftStep(payload: RecordStepPayload): DraftTraceStep | null {
|
||||
const pageUrl = payload.page_url;
|
||||
switch (payload.op) {
|
||||
case "click":
|
||||
return payload.target
|
||||
? {
|
||||
op: "click",
|
||||
target: payload.target,
|
||||
...(pageUrl ? { page_url: pageUrl } : {}),
|
||||
}
|
||||
: null;
|
||||
case "fill":
|
||||
return payload.target
|
||||
? {
|
||||
op: "fill",
|
||||
target: payload.target,
|
||||
value: payload.value ?? "",
|
||||
...(payload.redacted ? { redacted: true } : {}),
|
||||
...(pageUrl ? { page_url: pageUrl } : {}),
|
||||
}
|
||||
: null;
|
||||
case "press":
|
||||
return payload.key
|
||||
? {
|
||||
op: "press",
|
||||
key: payload.key,
|
||||
...(payload.target ? { target: payload.target } : {}),
|
||||
...(payload.modifiers?.length ? { modifiers: payload.modifiers } : {}),
|
||||
...(pageUrl ? { page_url: pageUrl } : {}),
|
||||
}
|
||||
: null;
|
||||
case "select":
|
||||
return payload.target && payload.values
|
||||
? {
|
||||
op: "select",
|
||||
target: payload.target,
|
||||
values: payload.values,
|
||||
...(payload.labels?.length ? { labels: payload.labels } : {}),
|
||||
...(pageUrl ? { page_url: pageUrl } : {}),
|
||||
}
|
||||
: null;
|
||||
case "navigate":
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
function annotateLastStepNavigation(buffer: RecordingStepBuffer, url: string): boolean {
|
||||
for (let i = buffer.steps.length - 1; i >= 0; i -= 1) {
|
||||
const step = buffer.steps[i];
|
||||
if (!step) continue;
|
||||
if (step.op === "click" || step.op === "press" || step.op === "select") {
|
||||
buffer.steps[i] = { ...step, navigated_to: url };
|
||||
return true;
|
||||
}
|
||||
break;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
export function observeRecordedNavigation(
|
||||
buffer: RecordingStepBuffer,
|
||||
url: string,
|
||||
causedByAction?: boolean,
|
||||
): void {
|
||||
if (!url || url === buffer.currentUrl) return;
|
||||
buffer.currentUrl = url;
|
||||
const pendingIsCurrent =
|
||||
buffer.pendingNavigation &&
|
||||
(buffer.pendingNavigationDeadline === undefined ||
|
||||
buffer.pendingNavigationDeadline >= Date.now());
|
||||
|
||||
if (causedByAction === true || (causedByAction === undefined && pendingIsCurrent)) {
|
||||
buffer.pendingNavigation = false;
|
||||
buffer.pendingNavigationDeadline = undefined;
|
||||
if (!annotateLastStepNavigation(buffer, url)) {
|
||||
buffer.steps.push({
|
||||
op: "navigate",
|
||||
url,
|
||||
page_url: url,
|
||||
});
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
buffer.pendingNavigation = false;
|
||||
buffer.pendingNavigationDeadline = undefined;
|
||||
buffer.steps.push({
|
||||
op: "navigate",
|
||||
url,
|
||||
page_url: url,
|
||||
});
|
||||
}
|
||||
|
||||
export function appendRecordedPayload(
|
||||
buffer: RecordingStepBuffer,
|
||||
payload: RecordStepPayload,
|
||||
): void {
|
||||
if (payload.op === "navigate") {
|
||||
if (payload.url) {
|
||||
observeRecordedNavigation(buffer, payload.url, payload.navigation_caused_by_action);
|
||||
}
|
||||
return;
|
||||
}
|
||||
const step = toDraftStep({
|
||||
...payload,
|
||||
page_url: payload.page_url ?? buffer.currentUrl,
|
||||
});
|
||||
if (!step) return;
|
||||
buffer.steps.push(step);
|
||||
if (step.op === "click" || step.op === "press" || step.op === "select" || step.op === "fill") {
|
||||
buffer.pendingNavigation = payload.expects_navigation === true;
|
||||
buffer.pendingNavigationDeadline = buffer.pendingNavigation
|
||||
? Date.now() + NAVIGATION_TRIGGER_WINDOW_MS
|
||||
: undefined;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,218 @@
|
||||
import type { DraftTraceStep, PageRef, SelectedOption, Step } from "@/transport/types";
|
||||
|
||||
const CLIPBOARD_KEYS = new Set(["a", "c", "v", "x", "A", "C", "V", "X"]);
|
||||
const MODIFIER_ONLY_KEYS = new Set(["Meta", "Control", "Alt", "Shift", "OS", "Hyper", "Super"]);
|
||||
|
||||
export function shouldRecordPress(
|
||||
key: string,
|
||||
modifiers?: Array<"alt" | "ctrl" | "meta" | "shift">,
|
||||
): boolean {
|
||||
if (MODIFIER_ONLY_KEYS.has(key)) return false;
|
||||
const mods = modifiers ?? [];
|
||||
const hasCtrlOrMeta = mods.includes("ctrl") || mods.includes("meta");
|
||||
if (hasCtrlOrMeta && CLIPBOARD_KEYS.has(key)) return false;
|
||||
if (key === "Enter" || key === "Escape") return true;
|
||||
// Drop bare character typing — FillSession already records the value.
|
||||
if (key.length === 1 && !hasCtrlOrMeta && !mods.includes("alt")) return false;
|
||||
return false;
|
||||
}
|
||||
|
||||
function shouldIncludeDraft(step: DraftTraceStep): boolean {
|
||||
if (step.op === "fill" && !(step.value ?? "").trim() && !step.redacted) return false;
|
||||
if (step.op === "press" && !shouldRecordPress(step.key, step.modifiers)) return false;
|
||||
return true;
|
||||
}
|
||||
|
||||
/** Collapse consecutive navigations to the last hop. */
|
||||
function collapseNavigations(steps: DraftTraceStep[]): DraftTraceStep[] {
|
||||
const out: DraftTraceStep[] = [];
|
||||
for (const step of steps) {
|
||||
const prev = out[out.length - 1];
|
||||
if (step.op === "navigate" && prev?.op === "navigate") {
|
||||
out[out.length - 1] = step;
|
||||
continue;
|
||||
}
|
||||
out.push(step);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
function collectUrls(steps: DraftTraceStep[], startUrl?: string): string[] {
|
||||
const urls: string[] = [];
|
||||
if (startUrl) urls.push(startUrl);
|
||||
for (const step of steps) {
|
||||
if (step.op === "navigate") {
|
||||
urls.push(step.url);
|
||||
continue;
|
||||
}
|
||||
if ("page_url" in step && step.page_url) urls.push(step.page_url);
|
||||
if ("navigated_to" in step && step.navigated_to) urls.push(step.navigated_to);
|
||||
}
|
||||
const seen = new Set<string>();
|
||||
const unique: string[] = [];
|
||||
for (const url of urls) {
|
||||
if (!url || seen.has(url)) continue;
|
||||
seen.add(url);
|
||||
unique.push(url);
|
||||
}
|
||||
return unique;
|
||||
}
|
||||
|
||||
function buildPageRegistry(
|
||||
steps: DraftTraceStep[],
|
||||
startUrl?: string,
|
||||
): { pages: PageRef[]; urlToId: Map<string, string> } {
|
||||
const urls = collectUrls(steps, startUrl);
|
||||
const urlToId = new Map<string, string>();
|
||||
const pages = urls.map((url, index) => {
|
||||
const id = `p${index + 1}`;
|
||||
urlToId.set(url, id);
|
||||
return { id, url };
|
||||
});
|
||||
return { pages, urlToId };
|
||||
}
|
||||
|
||||
function pageIdFor(
|
||||
url: string | undefined,
|
||||
urlToId: Map<string, string>,
|
||||
fallbackUrl?: string,
|
||||
): string {
|
||||
if (url && urlToId.has(url)) return urlToId.get(url)!;
|
||||
if (fallbackUrl && urlToId.has(fallbackUrl)) return urlToId.get(fallbackUrl)!;
|
||||
return urlToId.values().next().value ?? "p1";
|
||||
}
|
||||
|
||||
function pageUrlForDraft(step: DraftTraceStep, fallbackUrl?: string): string | undefined {
|
||||
if (step.op === "navigate") return step.page_url ?? step.url;
|
||||
if ("page_url" in step && step.page_url) return step.page_url;
|
||||
return fallbackUrl;
|
||||
}
|
||||
|
||||
function effectForNavigation(
|
||||
navigatedTo: string | undefined,
|
||||
urlToId: Map<string, string>,
|
||||
): Step["effect"] {
|
||||
if (!navigatedTo) return undefined;
|
||||
const pageId = urlToId.get(navigatedTo);
|
||||
if (!pageId) return undefined;
|
||||
return { navigated_to: pageId };
|
||||
}
|
||||
|
||||
function withEffect(step: Step, effect: Step["effect"]): Step {
|
||||
if (!effect) return step;
|
||||
return { ...step, effect };
|
||||
}
|
||||
|
||||
function toSelection(values: string[], labels?: string[]): SelectedOption[] {
|
||||
return values.map((value, index) => ({
|
||||
value,
|
||||
...(labels?.[index] ? { label: labels[index] } : {}),
|
||||
}));
|
||||
}
|
||||
|
||||
function toV2Step(
|
||||
step: DraftTraceStep,
|
||||
id: number,
|
||||
urlToId: Map<string, string>,
|
||||
fallbackUrl?: string,
|
||||
): Step | null {
|
||||
if (!shouldIncludeDraft(step)) return null;
|
||||
|
||||
const pageUrl = pageUrlForDraft(step, fallbackUrl);
|
||||
const page = pageIdFor(pageUrl, urlToId, fallbackUrl);
|
||||
|
||||
switch (step.op) {
|
||||
case "navigate":
|
||||
return {
|
||||
op: "navigate",
|
||||
id,
|
||||
page: pageIdFor(step.url, urlToId, fallbackUrl),
|
||||
to: step.url,
|
||||
};
|
||||
case "click":
|
||||
return withEffect(
|
||||
{
|
||||
op: "click",
|
||||
id,
|
||||
page,
|
||||
target: step.target,
|
||||
},
|
||||
effectForNavigation(step.navigated_to, urlToId),
|
||||
);
|
||||
case "fill":
|
||||
return {
|
||||
op: "fill",
|
||||
id,
|
||||
page,
|
||||
target: step.target,
|
||||
value: step.value,
|
||||
...(step.redacted ? { redacted: true } : {}),
|
||||
};
|
||||
case "press":
|
||||
return withEffect(
|
||||
{
|
||||
op: "press",
|
||||
id,
|
||||
page,
|
||||
key: step.key,
|
||||
...(step.target ? { target: step.target } : {}),
|
||||
...(step.modifiers?.length ? { modifiers: step.modifiers } : {}),
|
||||
},
|
||||
effectForNavigation(step.navigated_to, urlToId),
|
||||
);
|
||||
case "select":
|
||||
return withEffect(
|
||||
{
|
||||
op: "select",
|
||||
id,
|
||||
page,
|
||||
target: step.target,
|
||||
selection: toSelection(step.values, step.labels),
|
||||
},
|
||||
effectForNavigation(step.navigated_to, urlToId),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
export interface ReducedTrace {
|
||||
pages: PageRef[];
|
||||
steps: Step[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Compile capture drafts into record-only trace v2 steps.
|
||||
* Variable inputs are NOT classified here — executing agents infer that at run time.
|
||||
*/
|
||||
export function reduceTraceSteps(steps: DraftTraceStep[], startUrl?: string): ReducedTrace {
|
||||
const collapsed = collapseNavigations(steps);
|
||||
const { pages, urlToId } = buildPageRegistry(collapsed, startUrl);
|
||||
const out: Step[] = [];
|
||||
let id = 1;
|
||||
let lastUrl = startUrl;
|
||||
for (const draft of collapsed) {
|
||||
if (draft.op === "navigate") lastUrl = draft.url;
|
||||
else if ("navigated_to" in draft && draft.navigated_to) lastUrl = draft.navigated_to;
|
||||
else if ("page_url" in draft && draft.page_url) lastUrl = draft.page_url;
|
||||
const step = toV2Step(draft, id, urlToId, lastUrl);
|
||||
if (!step) continue;
|
||||
out.push(step);
|
||||
id += 1;
|
||||
}
|
||||
return { pages, steps: out };
|
||||
}
|
||||
|
||||
export function resolveTraceStartUrl(
|
||||
drafts: DraftTraceStep[],
|
||||
startUrl?: string,
|
||||
pages?: PageRef[],
|
||||
): string {
|
||||
if (startUrl) return startUrl;
|
||||
const navigate = drafts.find((step): step is Extract<DraftTraceStep, { op: "navigate" }> => {
|
||||
return step.op === "navigate";
|
||||
});
|
||||
if (navigate) return navigate.url;
|
||||
for (const draft of drafts) {
|
||||
if ("page_url" in draft && draft.page_url) return draft.page_url;
|
||||
}
|
||||
return pages?.[0]?.url ?? "about:blank";
|
||||
}
|
||||
Reference in New Issue
Block a user