Compare commits

...
Author SHA1 Message Date
Ljy-0827 918cd4670c feat(vom): support canvas reading 2026-08-28 17:15:26 +08:00
Ljy-0827 88da6ca8b8 feat(vom): actions refactor 2026-08-28 15:50:32 +08:00
Ljy-0827 4dfa7aef63 fix(vom): canvas bug fix 2026-08-28 15:33:00 +08:00
Ljy-0827 0ec0b1d227 feat(vom): canvas position calculation and projection 2026-08-28 15:33:00 +08:00
Ljy-0827 f33e1a7876 feat(vom): two channels to deal with canvas 2026-08-28 15:10:36 +08:00
Ljy-0827 6072db8c11 feat(vom): fixture test 2026-08-28 15:02:39 +08:00
Ljy-0827 ea05ad1f3d fix(vom): canvas recognition 2026-08-28 15:02:39 +08:00
Ljy-0827 7701282897 feat(vom): vom can distinguish important canvas area 2026-08-28 15:02:39 +08:00
Zhang GH 7aaa5a2d01 Merge pull request #147 from Tencent/fix/dsh-plugin-session-lifecycle
fix(dsh-plugin): stabilize skill loading and browser sessions
2026-08-28 12:11:08 +08:00
Hannah Liu 48f64ec0df Merge pull request #122 from Tencent/feat/vom-functional-refactor
feat(vom): refactor semantic structure generation for grouped observations | 重构语义结构生成,支持分组式 VOM 观察
2026-08-28 11:24:34 +08:00
Ljy-0827 0d7f976335 fix(vom): fix repeat names 2026-08-26 15:28:27 +08:00
Ljy-0827 d1d3eb6a94 fix(vom): bug fix 2026-08-26 15:28:27 +08:00
Ljy-0827 38fd7d3f4c fix(vom): safety policy and rebase bug fix 2026-08-26 15:28:27 +08:00
Ljy-0827 b5062ac19b feat(vom): fix name lost 2026-08-26 15:28:27 +08:00
Ljy-0827 41cb576256 feat(vom): function refactor 2026-08-26 15:28:27 +08:00
70 changed files with 7245 additions and 961 deletions

No files matched your search

@@ -13,6 +13,8 @@ describe("RefStore", () => {
backendNodeId: 42,
tabId: 7,
generation: 0,
kind: "dom",
capabilities: ["interact", "screenshot"],
});
expect(s.size()).toBe(1);
expect(s.isEmpty()).toBe(false);
@@ -48,4 +50,31 @@ describe("RefStore", () => {
cdpSessionId: "child-session",
});
});
it("preserves explicit capabilities for visual surface refs", () => {
const s = new RefStore();
s.set("e1", 42, {
tabId: 7,
kind: "surface",
capabilities: ["screenshot"],
});
expect(s.resolveEntry("e1")).toMatchObject({
kind: "surface",
capabilities: ["screenshot"],
});
});
it("never grants ordinary interaction to a surface through defaults or caller input", () => {
const s = new RefStore();
s.set("e1", 42, { tabId: 7, kind: "surface" });
s.set("e2", 43, {
tabId: 7,
kind: "surface",
capabilities: ["interact", "screenshot"],
});
expect(s.resolveEntry("e1")?.capabilities).toEqual(["screenshot"]);
expect(s.resolveEntry("e2")?.capabilities).toEqual(["screenshot"]);
});
});
@@ -0,0 +1,67 @@
import { describe, expect, it } from "vitest";
import { type SurfaceCaptureInput, SurfaceCaptureStore } from "../surface-capture-store";
function input(): SurfaceCaptureInput {
return {
sessionId: "aa11",
tabId: 7,
navigationIdentity: "navigation",
surface: {
ref: "e3",
frameId: "main",
backendNodeId: 99,
observationGeneration: 2,
},
topViewportRect: { x: 10, y: 20, w: 100, h: 50 },
imageWidth: 200,
imageHeight: 100,
viewportSignature: "viewport",
frameProjectionSignature: "frame",
};
}
describe("SurfaceCaptureStore", () => {
it("creates metadata-only, short-lived captures and consumes them once", () => {
let now = 1_000;
const store = new SurfaceCaptureStore({
now: () => now,
ttlMs: 500,
createId: () => "sc_test",
});
const capture = store.create(input());
expect(capture).toMatchObject({
id: "sc_test",
createdAt: 1_000,
expiresAt: 1_500,
consumed: false,
});
expect(capture).not.toHaveProperty("imageBase64");
expect(store.consume("sc_test")).toMatchObject({ ok: true });
expect(store.consume("sc_test")).toEqual({ ok: false, reason: "consumed" });
now = 1_600;
expect(store.size()).toBe(0);
});
it("rejects expired and unknown captures", () => {
let now = 1_000;
const store = new SurfaceCaptureStore({
now: () => now,
ttlMs: 10,
createId: () => "sc_expired",
});
store.create(input());
now = 1_010;
expect(store.consume("sc_expired")).toEqual({ ok: false, reason: "expired" });
expect(store.consume("sc_missing")).toEqual({ ok: false, reason: "not_found" });
});
it("clears every capture on session cleanup", () => {
const store = new SurfaceCaptureStore({ createId: () => "sc_clear" });
store.create(input());
store.clear();
expect(store.size()).toBe(0);
});
});
@@ -1,10 +1,12 @@
import { AGENT_WINDOW_HOME, type AgentWindowApi, chromeAgentWindowApi } from "./agent-window";
import { RefStore } from "./ref-store";
import { SurfaceCaptureStore } from "./surface-capture-store";
export interface SessionContext {
sessionId: string;
agentWindowId: number;
refStore: RefStore;
surfaceCaptures: SurfaceCaptureStore;
borrowedTabs: Map<number, BorrowedTab>;
createdAtMs: number;
}
@@ -186,6 +188,7 @@ export class SessionManager {
sessionId,
agentWindowId: windowId,
refStore: new RefStore(),
surfaceCaptures: new SurfaceCaptureStore({ now: this.now }),
borrowedTabs: new Map(),
createdAtMs: this.now(),
};
@@ -1,3 +1,5 @@
import type { Rect } from "@browser-skill/vom";
/**
* Per-session map from `@e<N>` snapshot refs to a CDP node address.
*
@@ -12,12 +14,17 @@
* inside the `SessionContext`.
*/
export type BackendNodeId = number;
export type RefCapability = "interact" | "screenshot";
export type RefTargetKind = "dom" | "surface";
export interface RefEntry {
backendNodeId: BackendNodeId;
tabId: number | null;
frameId?: string;
cdpSessionId?: string;
visibleRect?: Rect;
kind: RefTargetKind;
capabilities: RefCapability[];
generation: number;
}
@@ -28,8 +35,19 @@ export type RefInput =
tabId: number;
frameId?: string;
cdpSessionId?: string;
visibleRect?: Rect;
kind?: RefTargetKind;
capabilities?: RefCapability[];
};
function capabilitiesFor(
kind: RefTargetKind,
capabilities: RefCapability[] | undefined,
): RefCapability[] {
if (kind === "surface") return ["screenshot"];
return capabilities ?? ["interact", "screenshot"];
}
export class RefStore {
private readonly map = new Map<string, RefEntry>();
private generation = 0;
@@ -70,13 +88,20 @@ export class RefStore {
tabId?: number;
frameId?: string;
cdpSessionId?: string;
visibleRect?: Rect;
kind?: RefTargetKind;
capabilities?: RefCapability[];
} = {},
): void {
const kind = opts.kind ?? "dom";
this.map.set(normaliseRef(ref), {
backendNodeId: id,
tabId: opts.tabId ?? null,
...(opts.frameId ? { frameId: opts.frameId } : {}),
...(opts.cdpSessionId ? { cdpSessionId: opts.cdpSessionId } : {}),
...(opts.visibleRect ? { visibleRect: opts.visibleRect } : {}),
kind,
capabilities: capabilitiesFor(kind, opts.capabilities),
generation: this.generation,
});
}
@@ -94,14 +119,20 @@ export class RefStore {
return {
backendNodeId: input,
tabId: null,
kind: "dom",
capabilities: ["interact", "screenshot"],
generation: this.generation,
};
}
const kind = input.kind ?? "dom";
return {
backendNodeId: input.backendNodeId,
tabId: input.tabId,
...(input.frameId ? { frameId: input.frameId } : {}),
...(input.cdpSessionId ? { cdpSessionId: input.cdpSessionId } : {}),
...(input.visibleRect ? { visibleRect: input.visibleRect } : {}),
kind,
capabilities: capabilitiesFor(kind, input.capabilities),
generation: this.generation,
};
}
@@ -0,0 +1,100 @@
import type { Rect } from "@browser-skill/vom";
export const SURFACE_CAPTURE_TTL_MS = 30_000;
export interface SurfaceCapture {
id: string;
sessionId: string;
tabId: number;
navigationIdentity: string;
surface: {
ref: string;
frameId?: string;
backendNodeId: number;
observationGeneration: number;
};
topViewportRect: Rect;
imageWidth: number;
imageHeight: number;
viewportSignature: string;
frameProjectionSignature: string;
createdAt: number;
expiresAt: number;
consumed: boolean;
}
export type SurfaceCaptureInput = Omit<
SurfaceCapture,
"id" | "createdAt" | "expiresAt" | "consumed"
>;
export type SurfaceCaptureConsumeResult =
| { ok: true; capture: SurfaceCapture }
| { ok: false; reason: "not_found" | "expired" | "consumed" };
export interface SurfaceCaptureStoreOptions {
now?: () => number;
ttlMs?: number;
createId?: () => string;
}
function randomCaptureId(): string {
const bytes = crypto.getRandomValues(new Uint8Array(12));
return `sc_${Array.from(bytes, (byte) => byte.toString(16).padStart(2, "0")).join("")}`;
}
/** Per-session, metadata-only store for short-lived screenshot coordinate transactions. */
export class SurfaceCaptureStore {
private readonly captures = new Map<string, SurfaceCapture>();
private readonly now: () => number;
private readonly ttlMs: number;
private readonly createId: () => string;
constructor(options: SurfaceCaptureStoreOptions = {}) {
this.now = options.now ?? Date.now;
this.ttlMs = options.ttlMs ?? SURFACE_CAPTURE_TTL_MS;
this.createId = options.createId ?? randomCaptureId;
}
create(input: SurfaceCaptureInput): SurfaceCapture {
this.purgeExpired();
const createdAt = this.now();
const capture: SurfaceCapture = {
...input,
id: this.createId(),
createdAt,
expiresAt: createdAt + this.ttlMs,
consumed: false,
};
this.captures.set(capture.id, capture);
return capture;
}
consume(id: string): SurfaceCaptureConsumeResult {
const capture = this.captures.get(id);
if (!capture) return { ok: false, reason: "not_found" };
if (capture.expiresAt <= this.now()) {
this.captures.delete(id);
return { ok: false, reason: "expired" };
}
if (capture.consumed) return { ok: false, reason: "consumed" };
capture.consumed = true;
return { ok: true, capture };
}
clear(): void {
this.captures.clear();
}
size(): number {
this.purgeExpired();
return this.captures.size;
}
private purgeExpired(): void {
const now = this.now();
for (const [id, capture] of this.captures) {
if (capture.expiresAt <= now) this.captures.delete(id);
}
}
}
@@ -11,6 +11,7 @@ import {
parseKeySpec,
resolveKeyDescriptor,
} from "../interaction";
import { captureSurfaceEnvironment } from "../surface-target";
function fakeAgentWindow(ids: number[]) {
let i = 0;
@@ -33,6 +34,15 @@ function makeFakeCdp(handlers: Record<string, (params: unknown) => unknown>) {
if (!h && method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
if (
!h &&
method === "Runtime.evaluate" &&
String((params as { expression?: string })?.expression ?? "").includes(
"bsk-focus-target-probe",
)
) {
return { result: { value: { hasFocus: true, activeTag: "input" } } };
}
if (!h) throw new Error(`unexpected CDP call ${method}`);
return h(params);
};
@@ -44,6 +54,10 @@ function makeFakeCdp(handlers: Record<string, (params: unknown) => unknown>) {
params?: object,
) => Promise<T>,
trackSessionTab: vi.fn(),
getFrameGraph: vi.fn(async (tabId) => ({
rootFrameId: "main",
frames: [{ frameId: "main", target: { tabId } }],
})),
};
const tabsApi = {
get: vi.fn(
@@ -54,6 +68,71 @@ function makeFakeCdp(handlers: Record<string, (params: unknown) => unknown>) {
return { cdp, tabsApi, sent };
}
function fillRuntimeReadback(value: string) {
return (params: unknown) => {
const fn = String((params as { functionDeclaration?: string }).functionDeclaration ?? "");
if (fn.includes("bsk-input-readback")) {
return { result: { value: { supported: true, value } } };
}
return { result: { type: "undefined" } };
};
}
async function makeSurfaceClickFixture(onMouse?: (params: Record<string, unknown>) => void) {
const manager = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const context = await manager.start("aa11");
context.refStore.set("e3", 99, {
tabId: 4,
kind: "surface",
visibleRect: { x: 10, y: 20, w: 100, h: 40 },
});
const fake = makeFakeCdp({
"Page.getFrameTree": () => ({
frameTree: {
frame: { id: "main", loaderId: "loader-1", url: "https://fixture.test/" },
},
}),
"Page.getLayoutMetrics": () => ({
cssLayoutViewport: { clientWidth: 800, clientHeight: 600, pageX: 0, pageY: 0 },
cssVisualViewport: {
clientWidth: 800,
clientHeight: 600,
pageX: 0,
pageY: 0,
scale: 1,
},
}),
"DOM.getContentQuads": () => ({ quads: [[10, 20, 110, 20, 110, 60, 10, 60]] }),
"Runtime.evaluate": () => ({
result: { value: { overlayHostPresent: false, overlayHostConnected: false } },
}),
"Input.dispatchMouseEvent": (params) => {
onMouse?.(params as Record<string, unknown>);
return {};
},
});
const environment = await captureSurfaceEnvironment(fake.cdp, 4, undefined);
if ("code" in environment) throw new Error(environment.message);
const entry = context.refStore.resolveEntry("e3");
if (!entry) throw new Error("missing Surface ref");
const capture = context.surfaceCaptures.create({
sessionId: "aa11",
tabId: 4,
navigationIdentity: environment.navigationIdentity,
surface: {
ref: "e3",
backendNodeId: 99,
observationGeneration: entry.generation,
},
topViewportRect: { x: 10, y: 20, w: 100, h: 40 },
imageWidth: 200,
imageHeight: 80,
viewportSignature: environment.viewportSignature,
frameProjectionSignature: environment.frameProjectionSignature,
});
return { manager, context, fake, capture };
}
describe("modifiersBitfield", () => {
it("matches CDP's expected bit layout", () => {
expect(modifiersBitfield([])).toBe(0);
@@ -123,6 +202,29 @@ describe("handleClick", () => {
expect(fake.cdp.send).not.toHaveBeenCalled();
});
it("rejects screenshot-only visual surface refs before issuing CDP calls", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e3", 1234, {
tabId: 4,
kind: "surface",
capabilities: ["screenshot"],
});
const fake = makeFakeCdp({});
const res = await handleClick(
sm,
{ session_id: "aa11", ref: "@e3" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expect(res).toMatchObject({
code: "permission_denied",
data: { reason: "ref_capability_denied", required_capability: "interact" },
});
expect(fake.cdp.send).not.toHaveBeenCalled();
});
it("clicks by ref, computes the quad centre, dispatches three mouse events", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -167,6 +269,74 @@ describe("handleClick", () => {
});
});
it.each([
"left",
"middle",
"right",
] as const)("uses the common click executor for a %s-button Surface click", async (button) => {
const { manager, fake, capture } = await makeSurfaceClickFixture();
const result = await handleClick(
manager,
{
session_id: "aa11",
ref: "@e3",
capture_id: capture.id,
image_x: 50,
image_y: 20,
button,
click_count: 2,
modifiers: ["ctrl", "shift"],
},
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
if ("code" in result) throw new Error(JSON.stringify(result));
expect(result).toMatchObject({
used_ref: "e3",
capture_id: capture.id,
image_x: 50,
image_y: 20,
x: 35,
y: 30,
});
const mouse = fake.sent.filter((call) => call.method === "Input.dispatchMouseEvent");
expect(mouse).toHaveLength(3);
expect(mouse[1].params).toMatchObject({
type: "mousePressed",
button,
clickCount: 2,
modifiers: 2 | 8,
});
expect(mouse[2].params).toMatchObject({
type: "mouseReleased",
button,
clickCount: 2,
});
});
it("consumes a Surface capture when the common click executor fails", async () => {
let mouseCalls = 0;
const { manager, fake, capture } = await makeSurfaceClickFixture((params) => {
mouseCalls += 1;
if (params.type === "mousePressed") throw new Error("input failed");
});
const params = {
session_id: "aa11",
ref: "@e3",
capture_id: capture.id,
image_x: 50,
image_y: 20,
};
expect(
await handleClick(manager, params, { cdp: fake.cdp, tabsApi: fake.tabsApi }),
).toMatchObject({ code: "cdp_failed" });
expect(mouseCalls).toBe(2);
expect(
await handleClick(manager, params, { cdp: fake.cdp, tabsApi: fake.tabsApi }),
).toMatchObject({ data: { reason: "surface_capture_consumed" } });
});
it("resolves frame refs in their CDP session and dispatches input in top coordinates", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -586,7 +756,7 @@ describe("handleFill", () => {
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.focus": () => ({}),
"DOM.resolveNode": () => ({ object: { objectId: "obj-1" } }),
"Runtime.callFunctionOn": () => ({ result: { type: "undefined" } }),
"Runtime.callFunctionOn": fillRuntimeReadback("hello"),
"Input.insertText": () => ({}),
});
const res = await handleFill(
@@ -619,6 +789,9 @@ describe("handleFill", () => {
"DOM.resolveNode": () => ({ object: { objectId: "obj-2" } }),
"Runtime.callFunctionOn": (p) => {
const fn = (p as { functionDeclaration?: string }).functionDeclaration ?? "";
if (fn.includes("bsk-input-readback")) {
return { result: { value: { supported: true, value: "existingx" } } };
}
// No "this.value = ''" clearing on a no-clear path; only the
// post-input dispatchEvent.
expect(fn).not.toMatch(/this\.value\s*=\s*''/);
@@ -632,7 +805,7 @@ describe("handleFill", () => {
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.value_length).toBe(1);
expect(res.value_length).toBe(9);
});
it("treats contenteditable=true as fillable", async () => {
@@ -650,7 +823,7 @@ describe("handleFill", () => {
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.focus": () => ({}),
"DOM.resolveNode": () => ({ object: { objectId: "obj-3" } }),
"Runtime.callFunctionOn": () => ({ result: { type: "undefined" } }),
"Runtime.callFunctionOn": fillRuntimeReadback("rich"),
"Input.insertText": () => ({}),
});
const res = await handleFill(
@@ -661,6 +834,88 @@ describe("handleFill", () => {
expect("code" in res).toBe(false);
});
it("routes OOPIF focus, text, DOM events, and readback through the node target", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e1", 77, {
tabId: 4,
frameId: "child-frame",
cdpSessionId: "child-session",
});
const fake = makeFakeCdp({ "DOM.scrollIntoViewIfNeeded": () => ({}) });
fake.cdp.getFrameGraph = vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child-frame",
parentFrameId: "main",
ownerBackendNodeId: 12,
target: { tabId: 4, sessionId: "child-session" },
},
],
}));
const childCalls: string[] = [];
fake.cdp.sendToTarget = vi.fn(async (target, method, params) => {
expect(target).toEqual({ tabId: 4, sessionId: "child-session" });
childCalls.push(method);
if (method === "DOM.describeNode") {
return { node: { backendNodeId: 77, nodeName: "INPUT", attributes: [] } };
}
if (method === "DOM.scrollIntoViewIfNeeded" || method === "DOM.focus") return {};
if (method === "DOM.resolveNode") return { object: { objectId: "child-input" } };
if (method === "Input.insertText") {
expect(params).toEqual({ text: "中文输入" });
return {};
}
if (method === "Runtime.callFunctionOn") {
const fn = String((params as { functionDeclaration?: string }).functionDeclaration ?? "");
return fn.includes("bsk-input-readback")
? { result: { value: { supported: true, value: "中文输入" } } }
: { result: { type: "undefined" } };
}
throw new Error(`unexpected child call ${method}`);
}) as CdpRunner["sendToTarget"];
const res = await handleFill(
sm,
{ session_id: "aa11", ref: "@e1", value: "中文输入" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
if ("code" in res) throw new Error(JSON.stringify(res));
expect(res.value_length).toBe(4);
expect(childCalls).toContain("DOM.focus");
expect(childCalls).toContain("Input.insertText");
expect(childCalls.filter((method) => method === "Runtime.callFunctionOn")).toHaveLength(4);
expect(fake.sent.some((call) => call.method === "Input.insertText")).toBe(false);
});
it("returns input_not_applied when a controlled input resets the value", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e1", 8, { tabId: 4 });
const fake = makeFakeCdp({
"DOM.describeNode": () => ({ node: { backendNodeId: 8, nodeName: "INPUT" } }),
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.focus": () => ({}),
"DOM.resolveNode": () => ({ object: { objectId: "controlled" } }),
"Input.insertText": () => ({}),
"Runtime.callFunctionOn": fillRuntimeReadback(""),
});
const res = await handleFill(
sm,
{ session_id: "aa11", ref: "@e1", value: "rejected" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expect(res).toMatchObject({
code: "cdp_failed",
data: { reason: "input_not_applied", expected_value_length: 8, actual_value_length: 0 },
});
});
it("stops before Input.insertText when abort fires after clearing", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -855,6 +1110,125 @@ describe("handlePress", () => {
expect(res.key).toBe("Enter");
});
it("routes ref-targeted key events through the OOPIF session", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e1", 555, {
tabId: 4,
frameId: "child-frame",
cdpSessionId: "child-session",
});
const fake = makeFakeCdp({ "DOM.scrollIntoViewIfNeeded": () => ({}) });
fake.cdp.getFrameGraph = vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child-frame",
parentFrameId: "main",
ownerBackendNodeId: 12,
target: { tabId: 4, sessionId: "child-session" },
},
],
}));
const childCalls: string[] = [];
fake.cdp.sendToTarget = vi.fn(async (_target, method) => {
childCalls.push(method);
return {};
}) as CdpRunner["sendToTarget"];
const res = await handlePress(
sm,
{ session_id: "aa11", key: "Enter", ref: "@e1" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expectPressOk(res);
expect(childCalls).toEqual([
"DOM.scrollIntoViewIfNeeded",
"DOM.focus",
"Input.dispatchKeyEvent",
"Input.dispatchKeyEvent",
"Input.dispatchKeyEvent",
]);
expect(fake.sent.some((call) => call.method === "Input.dispatchKeyEvent")).toBe(false);
});
it("routes an untargeted press to the uniquely focused OOPIF session", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
const fake = makeFakeCdp({
"Runtime.evaluate": () => ({
result: { value: { hasFocus: true, activeTag: "iframe" } },
}),
});
fake.cdp.getFrameGraph = vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child-frame",
parentFrameId: "main",
target: { tabId: 4, sessionId: "child-session" },
},
],
}));
const childCalls: string[] = [];
fake.cdp.sendToTarget = vi.fn(async (_target, method) => {
childCalls.push(method);
if (method === "Runtime.evaluate") {
return { result: { value: { hasFocus: true, activeTag: "textarea" } } };
}
return {};
}) as CdpRunner["sendToTarget"];
const res = await handlePress(
sm,
{ session_id: "aa11", key: "a" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expectPressOk(res);
expect(childCalls).toEqual([
"Runtime.evaluate",
"Input.dispatchKeyEvent",
"Input.dispatchKeyEvent",
"Input.dispatchKeyEvent",
]);
});
it("refuses an untargeted press when focus ownership is ambiguous", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
const fake = makeFakeCdp({
"Runtime.evaluate": () => ({
result: { value: { hasFocus: true, activeTag: "input" } },
}),
});
fake.cdp.getFrameGraph = vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{ frameId: "child", target: { tabId: 4, sessionId: "child-session" } },
],
}));
fake.cdp.sendToTarget = vi.fn(async () => ({
result: { value: { hasFocus: true, activeTag: "textarea" } },
})) as CdpRunner["sendToTarget"];
const res = await handlePress(
sm,
{ session_id: "aa11", key: "Enter" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expect(res).toMatchObject({
code: "cdp_failed",
data: { reason: "focus_target_unresolved", candidate_count: 2 },
});
expect(fake.sent.some((call) => call.method === "Input.dispatchKeyEvent")).toBe(false);
});
it("stops before focus when abort fires after press scroll", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -0,0 +1,119 @@
import { describe, expect, it, vi } from "vitest";
import { dispatchMouseClick } from "../mouse-input";
import type { CdpRunner } from "../shared";
function fakeCdp(onSend?: (method: string, params: Record<string, unknown>) => void): {
cdp: CdpRunner;
events: Record<string, unknown>[];
} {
const events: Record<string, unknown>[] = [];
return {
events,
cdp: {
send: vi.fn(async (_tabId, method, params) => {
const event = params as Record<string, unknown>;
events.push(event);
onSend?.(method, event);
return {} as never;
}),
},
};
}
describe("dispatchMouseClick", () => {
it("emits one move, press, and release sequence", async () => {
const { cdp, events } = fakeCdp();
expect(
await dispatchMouseClick(
cdp,
4,
{ x: 12, y: 34 },
{
button: "left",
clickCount: 1,
modifiers: 0,
moveSettleMs: 0,
},
),
).toBe("completed");
expect(events).toEqual([
{
type: "mouseMoved",
x: 12,
y: 34,
modifiers: 0,
},
{
type: "mousePressed",
x: 12,
y: 34,
button: "left",
clickCount: 1,
modifiers: 0,
},
{
type: "mouseReleased",
x: 12,
y: 34,
button: "left",
clickCount: 1,
modifiers: 0,
},
]);
});
it("releases a pressed button when cancellation arrives", async () => {
const controller = new AbortController();
const { cdp, events } = fakeCdp((_method, event) => {
if (event.type === "mousePressed") controller.abort();
});
expect(
await dispatchMouseClick(
cdp,
4,
{ x: 1, y: 2 },
{
button: "left",
clickCount: 1,
modifiers: 0,
signal: controller.signal,
moveSettleMs: 0,
},
),
).toBe("cancelled");
expect(events.at(-1)).toMatchObject({ type: "mouseReleased" });
});
it("settles pointer-move hit testing before pressing", async () => {
vi.useFakeTimers();
try {
const { cdp, events } = fakeCdp();
const click = dispatchMouseClick(
cdp,
4,
{ x: 1, y: 2 },
{
button: "left",
clickCount: 1,
modifiers: 0,
moveSettleMs: 32,
},
);
await vi.advanceTimersByTimeAsync(31);
expect(events.map((event) => event.type)).toEqual(["mouseMoved"]);
await vi.advanceTimersByTimeAsync(1);
await click;
expect(events.map((event) => event.type)).toEqual([
"mouseMoved",
"mousePressed",
"mouseReleased",
]);
} finally {
vi.useRealTimers();
}
});
});
@@ -67,6 +67,9 @@ function makeFakeCdp(handlers: Record<string, (params?: object) => unknown>) {
if (!handler && method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
if (!handler && method === "Page.getFrameTree") {
return { frameTree: { frame: { id: "main", loaderId: "loader-1", url: "https://test/" } } };
}
if (!handler) throw new Error(`unexpected CDP call ${method}`);
return handler(params);
});
@@ -300,6 +303,82 @@ describe("handleScreenshot", () => {
expect(clip).toMatchObject({ x: 10, y: 20, width: 100, height: 40 });
});
it("captures a bounded visible crop for a visual surface without scrolling it", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e5", 999, {
tabId: 7,
kind: "surface",
capabilities: ["screenshot"],
});
const { cdp, sent } = makeFakeCdp({
"Page.getLayoutMetrics": () => ({
cssLayoutViewport: { clientWidth: 4096, clientHeight: 4096 },
}),
"DOM.getContentQuads": () => ({ quads: [[0, 0, 4096, 0, 4096, 4096, 0, 4096]] }),
"Page.captureScreenshot": () => ({ data: TINY_PNG }),
});
const res = await handleScreenshot(
sm,
{ session_id: "aa11", ref: "@e5", tab_id: 7 },
makeScreenshotDeps({
cdp,
get: vi.fn(async () => ({ id: 7, windowId: 100, active: false }) as chrome.tabs.Tab),
query: vi.fn(),
captureVisibleTab: vi.fn(),
}),
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(sent.some((call) => call.method === "DOM.scrollIntoViewIfNeeded")).toBe(false);
const clip = sent.find((call) => call.method === "Page.captureScreenshot")?.params as {
clip?: { width: number; height: number; scale: number };
};
expect(clip.clip).toMatchObject({ width: 4096, height: 4096 });
expect(clip.clip?.scale).toBeCloseTo(Math.sqrt(4_000_000 / (4096 * 4096)));
expect(res.capture).toMatchObject({
surface_ref: "@e5",
coordinate_space: "capture-image-pixel",
});
expect(ctx.surfaceCaptures.size()).toBe(1);
});
it("crops a visual surface screenshot to its observation-time visible region", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e5", 999, {
tabId: 7,
kind: "surface",
visibleRect: { x: 25, y: 30, w: 50, h: 40 },
});
const { cdp, sent } = makeFakeCdp({
"Page.getLayoutMetrics": () => ({
cssLayoutViewport: { clientWidth: 800, clientHeight: 600 },
}),
"DOM.getContentQuads": () => ({ quads: [[0, 0, 200, 0, 200, 100, 0, 100]] }),
"Page.captureScreenshot": () => ({ data: TINY_PNG }),
});
const res = await handleScreenshot(
sm,
{ session_id: "aa11", ref: "@e5", tab_id: 7 },
makeScreenshotDeps({
cdp,
get: vi.fn(async () => ({ id: 7, windowId: 100, active: false }) as chrome.tabs.Tab),
query: vi.fn(),
captureVisibleTab: vi.fn(),
}),
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
const clip = sent.find((call) => call.method === "Page.captureScreenshot")?.params as {
clip?: { x: number; y: number; width: number; height: number };
};
expect(clip.clip).toMatchObject({ x: 25, y: 30, width: 50, height: 40 });
expect(res.capture?.id).toMatch(/^sc_/);
});
it("returns not_found for unknown ref", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
@@ -1656,7 +1735,7 @@ describe("buildVomScene", () => {
const scene = buildVomScene(axNodes, captured);
expect(scene.nodes.find((n) => n.id === 20)).toEqual(
expect.objectContaining({ id: 20, role: "generic", cursor: "pointer" }),
expect.objectContaining({ id: 20, role: "button", name: "close", cursor: "pointer" }),
);
const rendered = renderVom(scene);
expect(rendered.text).toContain('@e1 button "close"');
@@ -1732,7 +1811,7 @@ describe("buildVomScene", () => {
};
const scene = buildVomScene(axNodes, captured);
expect(scene.nodes.find((n) => n.id === 20)?.role).toBe("generic");
expect(scene.nodes.find((n) => n.id === 20)).toBeUndefined();
expect(scene.nodes.find((n) => n.id === 30)?.role).toBe("link");
});
@@ -1801,9 +1880,9 @@ describe("buildVomScene", () => {
const scene = buildVomScene(axNodes, captured);
expect(scene.nodes.find((n) => n.id === 20)).toEqual(
expect.objectContaining({ id: 20, role: "generic", attrs: { "aria-label": "收藏" } }),
expect.objectContaining({ id: 20, role: "button", attrs: { "aria-label": "收藏" } }),
);
expect(scene.nodes.find((n) => n.id === 30)?.role).toBe("generic");
expect(scene.nodes.find((n) => n.id === 30)).toBeUndefined();
const rendered = renderVom(scene);
expect(rendered.text).toContain('@e1 button "收藏"');
expect(rendered.refs.map(({ ref, backendNodeId }) => ({ ref, backendNodeId }))).toEqual([
@@ -2131,7 +2210,7 @@ describe("buildVomScene", () => {
});
expect(scene.surfaces).toEqual([
{ triggerId: 21, triggerAction: "hover", subItems: ["My profile", "Sign out"] },
{ triggerId: 20, triggerAction: "hover", subItems: ["My profile", "Sign out"] },
]);
expect(renderVom(scene).text).toContain(
'@e1 button "image" [hover first: My profile | Sign out]',
@@ -2693,6 +2772,85 @@ describe("handleSnapshot", () => {
);
});
it("discovers rendered canvases only in observe and stores a screenshot-only ref", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
const root: CdpAxNode = {
nodeId: "1",
role: { type: "role", value: "RootWebArea" },
name: { type: "computedString", value: "Canvas app" },
backendDOMNodeId: 100,
};
const strings = ["body", "canvas", "static", "auto"];
const i = (value: string) => strings.indexOf(value);
const send = vi.fn(async (_tabId: number, method: string) => {
if (method === "Accessibility.enable" || method === "DOMSnapshot.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: [root] };
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
}
if (method === "DOMSnapshot.captureSnapshot") {
return {
strings,
documents: [
{
nodes: {
parentIndex: [-1, 0],
nodeName: [i("body"), i("canvas")],
backendNodeId: [100, 200],
attributes: [[], []],
},
layout: {
nodeIndex: [0, 1],
styles: [
[i("static"), i("auto"), i("auto")],
[i("static"), i("auto"), i("auto")],
],
bounds: [
[0, 0, 1000, 800],
[20, 30, 800, 500],
],
paintOrders: [0, 1],
},
},
],
};
}
throw new Error(`unexpected CDP method ${method}`);
});
const deps = {
cdp: {
send: send as unknown as <T = unknown>(
tabId: number,
method: string,
params?: object,
) => Promise<T>,
trackSessionTab: vi.fn(),
},
tabsApi: {
get: vi.fn(
async (tabId: number) => ({ id: tabId, windowId: 100, active: true }) as chrome.tabs.Tab,
),
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
},
conditionalSurfaceProbe: false,
};
const observed = await handleObserve(sm, { session_id: "aa11" }, deps);
if ("code" in observed) throw new Error(`unexpected error: ${JSON.stringify(observed)}`);
expect(observed.text).toContain('@e1 surface "canvas visual surface"');
expect(ctx.refStore.resolveEntry("e1")).toMatchObject({
backendNodeId: 200,
kind: "surface",
capabilities: ["screenshot"],
});
const snapshot = await handleSnapshot(sm, { session_id: "aa11" }, deps);
if ("code" in snapshot) throw new Error(`unexpected error: ${JSON.stringify(snapshot)}`);
expect(snapshot.text).not.toContain("visual surface");
expect(snapshot.ref_count).toBe(0);
});
it("allows passive snapshots of explicit user-window tabs", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
@@ -3155,6 +3313,98 @@ describe("handleSnapshot", () => {
});
});
it("decorates live observations with active controlled content", async () => {
const strings = [
"html",
"body",
"button",
"div",
"#text",
"role",
"tab",
"aria-selected",
"true",
"aria-controls",
"reviews-panel",
"id",
"static",
"auto",
"visible",
"1",
"A detailed review",
];
const index = (value: string) => strings.indexOf(value);
const style = [index("static"), index("auto"), index("auto"), index("visible"), index("1")];
const snapshot = {
strings,
documents: [
{
nodes: {
parentIndex: [-1, 0, 1, 1, 3],
nodeName: [index("html"), index("body"), index("button"), index("div"), index("#text")],
backendNodeId: [10, 11, 12, 13, 14],
attributes: [
[],
[],
[
index("role"),
index("tab"),
index("aria-selected"),
index("true"),
index("aria-controls"),
index("reviews-panel"),
],
[index("id"), index("reviews-panel")],
[],
],
nodeValue: [-1, -1, -1, -1, index("A detailed review")],
},
layout: {
nodeIndex: [0, 1, 2, 3, 4],
styles: [style, style, style, style, style],
bounds: [
[0, 0, 1000, 800],
[0, 0, 1000, 800],
[20, 20, 120, 40],
[20, 80, 500, 200],
[20, 80, 200, 20],
],
paintOrders: [0, 0, 1, 1, 1],
},
},
],
};
const ax: CdpAxNode[] = [
{
nodeId: "root",
backendDOMNodeId: 11,
role: { type: "role", value: "RootWebArea" },
childIds: ["reviews"],
},
{
nodeId: "reviews",
parentId: "root",
backendDOMNodeId: 12,
role: { type: "role", value: "tab" },
name: { type: "computedString", value: "Reviews" },
properties: [
{ name: "selected", value: { value: true } },
{ name: "controls", value: { value: "reviews-panel" } },
],
},
];
const result = await captureVomObservation(
makeOverlayDeps(ax, snapshot, VP_METRICS).cdp,
4,
"https://example.com",
);
expect(result.text).toContain('@e1 tab "Reviews"');
expect(result.text).toContain("[§ active: Reviews]");
expect(result.text).toContain("A detailed review");
});
it("does not leak form secrets through the record-safe observation payload", async () => {
const secrets = {
email: "user@example.com",
@@ -252,12 +252,23 @@ describe("handleSessionStop with auto-return", () => {
expect(aw.remove).not.toHaveBeenCalled();
});
it("clears the RefStore before window teardown", async () => {
it("clears refs and Surface captures before window teardown", async () => {
const aw = fakeAgentWindow([100]);
const sm = new SessionManager({ agentWindow: aw });
const ctx = await sm.start("aa11");
// Insert a fake ref so we can verify clear() ran.
ctx.refStore.set("e1", 123, { tabId: 7 });
ctx.surfaceCaptures.create({
sessionId: "aa11",
tabId: 7,
navigationIdentity: "navigation",
surface: { ref: "e1", backendNodeId: 123, observationGeneration: 0 },
topViewportRect: { x: 0, y: 0, w: 100, h: 50 },
imageWidth: 100,
imageHeight: 50,
viewportSignature: "viewport",
frameProjectionSignature: "frame",
});
const state: FakeState = {
tabs: new Map(),
windowsClosed: new Set(),
@@ -266,5 +277,6 @@ describe("handleSessionStop with auto-return", () => {
const { tabs, windows } = makeApis(state);
await handleSessionStop(sm, { session_id: "aa11" }, { tabManagement: { tabs, windows } });
expect(ctx.refStore.isEmpty()).toBe(true);
expect(ctx.surfaceCaptures.size()).toBe(0);
});
});
@@ -24,10 +24,16 @@ describe("lookupSnapshotRef", () => {
expect(lookupSnapshotRef(ctx, "@e3", 4)).toEqual({
backendNodeId: 1234,
refKey: "e3",
kind: "dom",
capabilities: ["interact", "screenshot"],
generation: 0,
});
expect(lookupSnapshotRef(ctx, "e3", 4)).toEqual({
backendNodeId: 1234,
refKey: "e3",
kind: "dom",
capabilities: ["interact", "screenshot"],
generation: 0,
});
});
@@ -53,6 +59,8 @@ describe("resolveSnapshotRef", () => {
tabId: 4,
frameId: "child-frame",
cdpSessionId: "child-session",
kind: "dom",
capabilities: ["interact", "screenshot"],
});
const expected = {
@@ -60,6 +68,9 @@ describe("resolveSnapshotRef", () => {
refKey: "e3",
frameId: "child-frame",
cdpSessionId: "child-session",
kind: "dom" as const,
capabilities: ["interact", "screenshot"] as const,
generation: 0,
};
expect(lookupSnapshotRef(ctx, "@e3", 4)).toEqual(expected);
expect(resolveSnapshotRef(ctx, "@e3", 4)).toEqual(expected);
@@ -105,6 +116,29 @@ describe("resolveSnapshotRef", () => {
expect(resolveSnapshotRef(ctx, "@e3", 4)).toEqual({
backendNodeId: 1234,
refKey: "e3",
kind: "dom",
capabilities: ["interact", "screenshot"],
generation: 0,
});
});
it("rejects an operation outside the ref's declared capabilities", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e3", 1234, {
tabId: 4,
kind: "surface",
capabilities: ["screenshot"],
});
expect(resolveSnapshotRef(ctx, "@e3", 4, "interact")).toMatchObject({
code: "permission_denied",
message: "ref @e3 does not support interact",
data: {
reason: "ref_capability_denied",
required_capability: "interact",
kind: "surface",
},
});
});
});
@@ -0,0 +1,52 @@
import { describe, expect, it } from "vitest";
import {
mapImagePointToViewport,
pointInRegion,
sameRect,
surfaceVisibleRect,
} from "../surface-coordinate";
describe("surface coordinate mapping", () => {
it("maps capture image pixels through the actual screenshot dimensions", () => {
expect(mapImagePointToViewport({ x: 100, y: 50, w: 400, h: 200 }, 800, 400, 200, 100)).toEqual({
x: 200,
y: 100,
});
});
it("rejects invalid image coordinates and dimensions", () => {
const rect = { x: 0, y: 0, w: 100, h: 50 };
expect(mapImagePointToViewport(rect, 100, 50, -1, 0)).toBeNull();
expect(mapImagePointToViewport(rect, 100, 50, 100, 0)).toBeNull();
expect(mapImagePointToViewport(rect, 100, 50, 0, 50)).toBeNull();
expect(mapImagePointToViewport(rect, 100, 50, Number.NaN, 0)).toBeNull();
expect(mapImagePointToViewport(rect, 100, 50, Number.POSITIVE_INFINITY, 0)).toBeNull();
expect(mapImagePointToViewport(rect, 0, 50, 0, 0)).toBeNull();
});
it("intersects live and observed visible regions and compares them strictly", () => {
const clipped = surfaceVisibleRect(
{ x: 0, y: 0, width: 200, height: 100 },
{ x: 25, y: 30, w: 50, h: 40 },
);
expect(clipped).toEqual({ x: 25, y: 30, w: 50, h: 40 });
expect(sameRect(clipped as NonNullable<typeof clipped>, { x: 25, y: 30, w: 50, h: 40 })).toBe(
true,
);
expect(sameRect(clipped as NonNullable<typeof clipped>, { x: 26, y: 30, w: 50, h: 40 })).toBe(
false,
);
});
it("checks the projected visible region rather than only its bounding box", () => {
const triangle = [
[
{ x: 0, y: 0 },
{ x: 100, y: 0 },
{ x: 0, y: 100 },
],
];
expect(pointInRegion({ x: 20, y: 20 }, triangle)).toBe(true);
expect(pointInRegion({ x: 90, y: 90 }, triangle)).toBe(false);
});
});
@@ -0,0 +1,306 @@
import { describe, expect, it, vi } from "vitest";
import { SessionManager } from "@/session-manager/manager";
import type { CdpRunner } from "../shared";
import {
captureSurfaceEnvironment,
resolveSurfacePointerTarget,
SURFACE_POINTER_MOVE_SETTLE_MS,
} from "../surface-target";
function fakeAgentWindow() {
return {
create: vi.fn(async () => 100),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => {}),
};
}
function fakeBrowser() {
let loaderId = "loader-1";
let pageY = 0;
let quad = [10, 20, 110, 20, 110, 60, 10, 60];
const sent: Array<{ method: string; params?: object }> = [];
const cdp: CdpRunner = {
send: vi.fn(async (_tabId: number, method: string, params?: object) => {
sent.push({ method, params });
if (method === "Page.getFrameTree") {
return {
frameTree: { frame: { id: "main", loaderId, url: "https://fixture.test/" } },
} as never;
}
if (method === "Page.getLayoutMetrics") {
return {
cssLayoutViewport: { clientWidth: 800, clientHeight: 600, pageX: 0, pageY },
cssVisualViewport: {
clientWidth: 800,
clientHeight: 600,
pageX: 0,
pageY,
scale: 1,
},
} as never;
}
if (method === "DOM.getContentQuads") return { quads: [quad] } as never;
throw new Error(`unexpected CDP call ${method}`);
}) as CdpRunner["send"],
trackSessionTab: vi.fn(),
};
return {
cdp,
sent,
setLoaderId: (value: string) => {
loaderId = value;
},
setPageY: (value: number) => {
pageY = value;
},
setQuad: (value: number[]) => {
quad = value;
},
};
}
async function setupCapture() {
const manager = new SessionManager({ agentWindow: fakeAgentWindow() });
const context = await manager.start("aa11");
context.refStore.set("e3", 99, {
tabId: 4,
kind: "surface",
visibleRect: { x: 10, y: 20, w: 100, h: 40 },
});
const browser = fakeBrowser();
const environment = await captureSurfaceEnvironment(browser.cdp, 4, undefined);
if ("code" in environment) throw new Error(environment.message);
const entry = context.refStore.resolveEntry("e3");
if (!entry) throw new Error("missing ref");
const capture = context.surfaceCaptures.create({
sessionId: "aa11",
tabId: 4,
navigationIdentity: environment.navigationIdentity,
surface: {
ref: "e3",
backendNodeId: 99,
observationGeneration: entry.generation,
},
topViewportRect: { x: 10, y: 20, w: 100, h: 40 },
imageWidth: 200,
imageHeight: 80,
viewportSignature: environment.viewportSignature,
frameProjectionSignature: environment.frameProjectionSignature,
});
return { manager, context, browser, capture };
}
function pointParams(captureId: string) {
return {
ref: "@e3",
captureId,
imageX: 50,
imageY: 20,
};
}
describe("Surface screenshot-bound pointer target", () => {
it("maps one fresh capture coordinate without executing an action", async () => {
const { context, browser, capture } = await setupCapture();
const result = await resolveSurfacePointerTarget(
context,
{ tabId: 4 },
pointParams(capture.id),
{ cdp: browser.cdp },
);
if ("code" in result) throw new Error(JSON.stringify(result));
expect(result).toMatchObject({
usedRef: "e3",
point: { x: 35, y: 30 },
moveSettleMs: SURFACE_POINTER_MOVE_SETTLE_MS,
capture: { id: capture.id, imageX: 50, imageY: 20 },
});
expect(browser.sent.some((call) => call.method === "Input.dispatchMouseEvent")).toBe(false);
const repeated = await resolveSurfacePointerTarget(
context,
{ tabId: 4 },
pointParams(capture.id),
{ cdp: browser.cdp },
);
expect(repeated).toMatchObject({
code: "permission_denied",
data: { reason: "surface_capture_consumed" },
});
});
it("rejects a new observation generation before sending input", async () => {
const { context, browser, capture } = await setupCapture();
context.refStore.replace([
[
"e3",
{
backendNodeId: 99,
tabId: 4,
kind: "surface" as const,
visibleRect: { x: 10, y: 20, w: 100, h: 40 },
},
],
]);
const result = await resolveSurfacePointerTarget(
context,
{ tabId: 4 },
pointParams(capture.id),
{ cdp: browser.cdp },
);
expect(result).toMatchObject({
code: "permission_denied",
data: { reason: "surface_capture_stale" },
});
expect(browser.sent.some((call) => call.method === "Input.dispatchMouseEvent")).toBe(false);
});
it("rejects navigation, scroll, and visible geometry changes", async () => {
for (const mutate of [
(browser: ReturnType<typeof fakeBrowser>) => browser.setLoaderId("loader-2"),
(browser: ReturnType<typeof fakeBrowser>) => browser.setPageY(20),
(browser: ReturnType<typeof fakeBrowser>) =>
browser.setQuad([11, 20, 111, 20, 111, 60, 11, 60]),
]) {
const { context, browser, capture } = await setupCapture();
mutate(browser);
const result = await resolveSurfacePointerTarget(
context,
{ tabId: 4 },
pointParams(capture.id),
{ cdp: browser.cdp },
);
expect(result).toMatchObject({
code: "permission_denied",
data: { reason: "surface_capture_stale" },
});
expect(browser.sent.some((call) => call.method === "Input.dispatchMouseEvent")).toBe(false);
}
});
it("consumes the capture when coordinate validation fails", async () => {
const invalid = await setupCapture();
const outside = await resolveSurfacePointerTarget(
invalid.context,
{ tabId: 4 },
{ ...pointParams(invalid.capture.id), imageX: 200 },
{ cdp: invalid.browser.cdp },
);
expect(outside).toMatchObject({
code: "invalid_params",
data: { reason: "surface_coordinate_invalid" },
});
expect(
await resolveSurfacePointerTarget(
invalid.context,
{ tabId: 4 },
pointParams(invalid.capture.id),
{ cdp: invalid.browser.cdp },
),
).toMatchObject({ data: { reason: "surface_capture_consumed" } });
});
it("maps image coordinates through an OOPIF frame projection", async () => {
const manager = new SessionManager({ agentWindow: fakeAgentWindow() });
const context = await manager.start("aa11");
context.refStore.set("e3", 99, {
tabId: 4,
frameId: "child",
cdpSessionId: "child-session",
kind: "surface",
visibleRect: { x: 120, y: 110, w: 100, h: 40 },
});
const graph = {
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 77,
target: { tabId: 4, sessionId: "child-session" },
},
],
};
const sent: Array<{ method: string; params?: object }> = [];
const cdp: CdpRunner = {
send: vi.fn(async (_tabId: number, method: string, params?: object) => {
sent.push({ method, params });
if (method === "Page.getFrameTree") {
return {
frameTree: {
frame: { id: "main", loaderId: "loader-1", url: "https://fixture.test/" },
},
} as never;
}
if (method === "Page.getLayoutMetrics") {
return {
cssLayoutViewport: { clientWidth: 800, clientHeight: 600, pageX: 0, pageY: 0 },
cssVisualViewport: {
clientWidth: 800,
clientHeight: 600,
pageX: 0,
pageY: 0,
scale: 1,
},
} as never;
}
if (method === "DOM.getBoxModel") {
return { model: { content: [100, 100, 300, 100, 300, 200, 100, 200] } } as never;
}
if (method === "Input.dispatchMouseEvent") return {} as never;
throw new Error(`unexpected root CDP call ${method}`);
}) as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "DOM.getContentQuads") {
return { quads: [[20, 10, 120, 10, 120, 50, 20, 50]] } as never;
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } } as never;
}
throw new Error(`unexpected child CDP call ${method}`);
}) as CdpRunner["sendToTarget"],
getFrameGraph: vi.fn(async () => graph),
trackSessionTab: vi.fn(),
};
const environment = await captureSurfaceEnvironment(cdp, 4, "child");
if ("code" in environment) throw new Error(environment.message);
const entry = context.refStore.resolveEntry("e3");
if (!entry) throw new Error("missing ref");
const capture = context.surfaceCaptures.create({
sessionId: "aa11",
tabId: 4,
navigationIdentity: environment.navigationIdentity,
surface: {
ref: "e3",
frameId: "child",
backendNodeId: 99,
observationGeneration: entry.generation,
},
topViewportRect: { x: 120, y: 110, w: 100, h: 40 },
imageWidth: 200,
imageHeight: 80,
viewportSignature: environment.viewportSignature,
frameProjectionSignature: environment.frameProjectionSignature,
});
const result = await resolveSurfacePointerTarget(
context,
{ tabId: 4 },
{
ref: "@e3",
captureId: capture.id,
imageX: 100,
imageY: 40,
},
{ cdp },
);
if ("code" in result) throw new Error(JSON.stringify(result));
expect(result).toMatchObject({ point: { x: 170, y: 130 } });
expect(sent.some((call) => call.method === "Input.dispatchMouseEvent")).toBe(false);
});
});
+281 -84
View File
@@ -11,7 +11,7 @@
// commands.
import { ChromiumCdp } from "@/browser-driver/chromium-cdp";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import { type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
import type { SessionContext, SessionManager } from "@/session-manager/manager";
import type {
ClickParams,
@@ -32,6 +32,7 @@ import { attachDialogs, markDialogCursor } from "./dialogs";
import { backendNodeToObject } from "./element-geometry";
import { rpcError } from "./errors";
import { resolveNodeGeometry, scrollElementAndFramesIntoView } from "./frame-geometry";
import { dispatchMouseClick } from "./mouse-input";
import {
type CdpRunner,
type ChromeTabsApi,
@@ -43,6 +44,7 @@ import {
resolveTargetTab,
} from "./shared";
import { resolveSnapshotRef } from "./snapshot-ref";
import { resolveSurfacePointerTarget } from "./surface-target";
export interface InteractionDeps {
cdp: CdpRunner;
@@ -159,7 +161,7 @@ async function resolveBackendNode(
};
}
if (hasRef) {
const resolved = resolveSnapshotRef(ctx, params.ref as string, target.tabId);
const resolved = resolveSnapshotRef(ctx, params.ref as string, target.tabId, "interact");
if (isRpcError(resolved)) return resolved;
return {
backendNodeId: resolved.backendNodeId,
@@ -215,15 +217,131 @@ async function resolveBackendNode(
}
}
interface InputDispatchContext {
target: CdpTarget;
cdp: CdpRunner;
backendNodeId?: number;
frameId?: string;
usedRef?: string;
usedSelector?: string;
}
function inputContextForNode(
cdp: CdpRunner,
node: Awaited<ReturnType<typeof resolveBackendNode>>,
): (InputDispatchContext & { backendNodeId: number }) | RpcError {
if (isRpcError(node)) return node;
return {
target: node.cdpTarget,
cdp: cdpRunnerForTarget(cdp, node.cdpTarget),
backendNodeId: node.backendNodeId,
frameId: node.frameId,
usedRef: node.usedRef,
usedSelector: node.usedSelector,
};
}
interface FocusProbe {
hasFocus: boolean;
activeTag: string;
}
/** Resolve keyboard input to the CDP target that currently owns focus. */
async function resolveFocusedInputContext(
cdp: CdpRunner,
tabId: number,
): Promise<InputDispatchContext | RpcError> {
if (!cdp.getFrameGraph) {
return rpcError(
"cdp_failed",
"focus_target_unresolved",
"press cannot determine the focused frame target",
);
}
let targets: CdpTarget[];
try {
const graph = await cdp.getFrameGraph(tabId);
const unique = new Map<string, CdpTarget>();
unique.set(cdpTargetKey({ tabId }), { tabId });
for (const frame of graph.frames) unique.set(cdpTargetKey(frame.target), frame.target);
targets = [...unique.values()];
} catch (err) {
return rpcError(
"cdp_failed",
"focus_target_unresolved",
err instanceof Error ? err.message : String(err),
);
}
const focused: Array<{ target: CdpTarget; probe: FocusProbe }> = [];
await Promise.all(
targets.map(async (candidate) => {
try {
const reply = await cdpRunnerForTarget(cdp, candidate).send<{
result?: { value?: FocusProbe };
}>(tabId, "Runtime.evaluate", {
expression: `(() => {
/* bsk-focus-target-probe */
const active = document.activeElement;
return {
hasFocus: document.hasFocus(),
activeTag: active instanceof Element ? active.tagName.toLowerCase() : ''
};
})()`,
returnByValue: true,
});
const probe = reply.result?.value;
if (probe?.hasFocus) focused.push({ target: candidate, probe });
} catch {
// A target may navigate or detach while the graph is being probed.
}
}),
);
// A top document whose active element is an iframe delegates focus to
// that frame. Removing those delegating targets leaves the deepest OOPIF
// target while same-process frames continue to use the shared root target.
const owners = focused.filter(
({ probe }) => probe.activeTag !== "iframe" && probe.activeTag !== "frame",
);
if (owners.length !== 1) {
return rpcError(
"cdp_failed",
"focus_target_unresolved",
owners.length === 0
? "press found no unique focused frame target"
: "press found multiple focused frame targets",
{ candidate_count: owners.length },
);
}
const target = owners[0].target;
return { target, cdp: cdpRunnerForTarget(cdp, target) };
}
// ---------------------------------------------------------------------------
// tool.click
// ---------------------------------------------------------------------------
interface ResolvedClickPointerTarget {
point: { x: number; y: number };
usedRef?: string;
usedSelector?: string;
moveSettleMs: number;
capture?: {
id: string;
imageX: number;
imageY: number;
};
}
export async function handleClick(
manager: SessionManager,
params: ClickParams,
deps: InteractionDeps = getDefaultDeps(),
): Promise<ClickResult | RpcError> {
const hasSurfacePointParams =
params.capture_id !== undefined || params.image_x !== undefined || params.image_y !== undefined;
const ctxOrErr = lookupSession(manager, params, "click");
if (isRpcError(ctxOrErr)) return ctxOrErr;
const ctx = ctxOrErr;
@@ -235,39 +353,67 @@ export async function handleClick(
if (denied) return denied;
const dialogCursor = markDialogCursor(deps.cdp, target.tabId);
const node = await resolveBackendNode(deps.cdp, ctx, target, params, "click");
if (isRpcError(node)) return node;
const button: MouseButton = params.button ?? "left";
const clickCount = params.click_count ?? 1;
if (!Number.isSafeInteger(clickCount) || clickCount < 1) {
return { code: "invalid_params", message: "click_count must be a positive integer" };
}
const modifiers = modifiersBitfield(params.modifiers);
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "click aborted" };
}
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
const geometry = await resolveNodeGeometry(
deps.cdp,
target.tabId,
{
target: node.cdpTarget,
backendNodeId: node.backendNodeId,
...(node.frameId ? { frameId: node.frameId } : {}),
},
{ scrollIntoView: true },
);
if (isRpcError(geometry)) return geometry;
const centre = geometry.actionPoint;
const pointerTarget: ResolvedClickPointerTarget | RpcError = hasSurfacePointParams
? await resolveSurfacePointerTarget(
ctx,
target,
{
ref: params.ref,
selector: params.selector,
captureId: params.capture_id,
imageX: params.image_x,
imageY: params.image_y,
},
{
cdp: deps.cdp,
signal: deps.signal,
},
)
: await (async () => {
const node = await resolveBackendNode(deps.cdp, ctx, target, params, "click");
if (isRpcError(node)) return node;
const geometry = await resolveNodeGeometry(
deps.cdp,
target.tabId,
{
target: node.cdpTarget,
backendNodeId: node.backendNodeId,
...(node.frameId ? { frameId: node.frameId } : {}),
},
{ scrollIntoView: true },
);
if (isRpcError(geometry)) return geometry;
return {
point: geometry.actionPoint,
usedRef: node.usedRef,
usedSelector: node.usedSelector,
moveSettleMs: 0,
};
})();
if (isRpcError(pointerTarget)) return pointerTarget;
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "click aborted" };
}
const button: MouseButton = params.button ?? "left";
const clickCount = params.click_count ?? 1;
if (clickCount < 1) {
return { code: "invalid_params", message: "click_count must be greater than zero" };
}
const modifiers = modifiersBitfield(params.modifiers);
const overlayBlocking = await checkOverlayAtPoint(deps.cdp, target.tabId, centre.x, centre.y);
const overlayBlocking = await checkOverlayAtPoint(
deps.cdp,
target.tabId,
pointerTarget.point.x,
pointerTarget.point.y,
);
let automationBypassEnabled = false;
if (overlayBlocking && deps.bypassOverlay) {
try {
@@ -279,47 +425,16 @@ export async function handleClick(
}
try {
// Move first so hover state activates, then press → release.
await deps.cdp.send(target.tabId, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: centre.x,
y: centre.y,
modifiers,
});
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "click aborted" };
}
await deps.cdp.send(target.tabId, "Input.dispatchMouseEvent", {
type: "mousePressed",
x: centre.x,
y: centre.y,
const dispatch = await dispatchMouseClick(deps.cdp, target.tabId, pointerTarget.point, {
button,
clickCount,
modifiers,
signal: deps.signal,
moveSettleMs: pointerTarget.moveSettleMs,
});
if (throwIfAborted(deps.signal)) {
try {
await deps.cdp.send(target.tabId, "Input.dispatchMouseEvent", {
type: "mouseReleased",
x: centre.x,
y: centre.y,
button,
clickCount,
modifiers,
});
} catch (err) {
console.debug("[bsk interaction] best-effort mouseReleased after abort failed", err);
}
if (dispatch === "cancelled") {
return { code: "cancelled", message: "click aborted" };
}
await deps.cdp.send(target.tabId, "Input.dispatchMouseEvent", {
type: "mouseReleased",
x: centre.x,
y: centre.y,
button,
clickCount,
modifiers,
});
} catch (err) {
return {
code: "cdp_failed",
@@ -337,10 +452,17 @@ export async function handleClick(
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
tab_id: target.tabId,
used_ref: node.usedRef,
used_selector: node.usedSelector,
x: centre.x,
y: centre.y,
used_ref: pointerTarget.usedRef,
used_selector: pointerTarget.usedSelector,
x: pointerTarget.point.x,
y: pointerTarget.point.y,
...(pointerTarget.capture
? {
capture_id: pointerTarget.capture.id,
image_x: pointerTarget.capture.imageX,
image_y: pointerTarget.capture.imageY,
}
: {}),
});
}
@@ -598,8 +720,9 @@ export async function handleFill(
const dialogCursor = markDialogCursor(deps.cdp, target.tabId);
const node = await resolveBackendNode(deps.cdp, ctx, target, params, "fill");
if (isRpcError(node)) return node;
const nodeCdp = cdpRunnerForTarget(deps.cdp, node.cdpTarget);
const input = inputContextForNode(deps.cdp, node);
if (isRpcError(input)) return input;
const nodeCdp = input.cdp;
try {
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
@@ -607,7 +730,7 @@ export async function handleFill(
target.tabId,
"DOM.describeNode",
{
backendNodeId: node.backendNodeId,
backendNodeId: input.backendNodeId,
},
);
if (!described.node || !isFillable(described.node)) {
@@ -620,15 +743,15 @@ export async function handleFill(
const scrollErr = await scrollElementAndFramesIntoView(
deps.cdp,
target.tabId,
node.cdpTarget,
node.backendNodeId,
node.frameId,
input.target,
input.backendNodeId,
input.frameId,
);
if (scrollErr) return scrollErr;
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: input.backendNodeId });
} catch (err) {
return {
code: "cdp_failed",
@@ -640,7 +763,7 @@ export async function handleFill(
return { code: "cancelled", message: "fill aborted" };
}
const objectIdOrErr = await backendNodeToObject(nodeCdp, target.tabId, node.backendNodeId);
const objectIdOrErr = await backendNodeToObject(nodeCdp, target.tabId, input.backendNodeId);
if (isRpcError(objectIdOrErr)) return objectIdOrErr;
const objectId = objectIdOrErr;
const clearBefore = params.clear_before ?? true;
@@ -671,7 +794,7 @@ export async function handleFill(
}
// CDP `Input.insertText` handles IME / multi-byte input out of the
// box, much more reliably than per-key `dispatchKeyEvent`.
await deps.cdp.send(target.tabId, "Input.insertText", { text: params.value });
await nodeCdp.send(target.tabId, "Input.insertText", { text: params.value });
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
@@ -684,6 +807,28 @@ export async function handleFill(
}`,
returnByValue: true,
});
// Give controlled inputs one bounded browser-render turn to accept or
// reject the dispatched value before reporting success.
await nodeCdp.send(target.tabId, "Runtime.callFunctionOn", {
objectId,
functionDeclaration: `function() {
/* bsk-input-sync */
return new Promise((resolve) => {
let settled = false;
const finish = () => {
if (settled) return;
settled = true;
clearTimeout(timer);
resolve();
};
const timer = setTimeout(finish, 100);
if (typeof requestAnimationFrame !== 'function') { finish(); return; }
requestAnimationFrame(() => requestAnimationFrame(finish));
});
}`,
awaitPromise: true,
returnByValue: true,
});
} catch (err) {
return {
code: "cdp_failed",
@@ -691,11 +836,56 @@ export async function handleFill(
};
}
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "fill aborted" };
}
let actualValue: string;
try {
const readback = await nodeCdp.send<{
result?: { value?: { supported?: boolean; value?: string } };
}>(target.tabId, "Runtime.callFunctionOn", {
objectId,
functionDeclaration: `function() {
/* bsk-input-readback */
if (this instanceof HTMLInputElement || this instanceof HTMLTextAreaElement) {
return { supported: true, value: this.value };
}
if (this.isContentEditable) {
return { supported: true, value: this.innerText ?? this.textContent ?? '' };
}
return { supported: false, value: '' };
}`,
returnByValue: true,
});
const state = readback.result?.value;
actualValue = typeof state?.value === "string" ? state.value : "";
const applied =
state?.supported === true &&
(clearBefore
? actualValue === params.value
: params.value.length === 0 || actualValue.includes(params.value));
if (!applied) {
return rpcError(
"cdp_failed",
"input_not_applied",
"the page did not retain the requested input value",
{ expected_value_length: params.value.length, actual_value_length: actualValue.length },
);
}
} catch (err) {
return rpcError(
"cdp_failed",
"input_not_applied",
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,
used_ref: input.usedRef,
used_selector: input.usedSelector,
value_length: actualValue.length,
});
}
@@ -870,31 +1060,38 @@ export async function handlePress(
};
}
let input: InputDispatchContext | RpcError;
// Optional focus before key dispatch.
if (params.ref || params.selector) {
const node = await resolveBackendNode(deps.cdp, ctx, target, params, "press");
if (isRpcError(node)) return node;
const nodeCdp = cdpRunnerForTarget(deps.cdp, node.cdpTarget);
const explicitInput = inputContextForNode(deps.cdp, node);
if (isRpcError(explicitInput)) return explicitInput;
input = explicitInput;
try {
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
const scrollErr = await scrollElementAndFramesIntoView(
deps.cdp,
target.tabId,
node.cdpTarget,
node.backendNodeId,
node.frameId,
explicitInput.target,
explicitInput.backendNodeId,
explicitInput.frameId,
);
if (scrollErr) return scrollErr;
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "press aborted" };
}
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
await explicitInput.cdp.send(target.tabId, "DOM.focus", {
backendNodeId: explicitInput.backendNodeId,
});
} catch (err) {
return {
code: "cdp_failed",
message: err instanceof Error ? err.message : String(err),
};
}
} else {
input = await resolveFocusedInputContext(deps.cdp, target.tabId);
if (isRpcError(input)) return input;
}
if (throwIfAborted(deps.signal)) {
@@ -908,7 +1105,7 @@ export async function handlePress(
try {
let cancelled = false;
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
await input.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
type: "rawKeyDown",
key: descriptor.key,
code: descriptor.code,
@@ -922,7 +1119,7 @@ export async function handlePress(
typeof descriptor.text === "string" &&
descriptor.text.length > 0
) {
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
await input.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
type: "char",
key: descriptor.key,
code: descriptor.code,
@@ -939,7 +1136,7 @@ export async function handlePress(
cancelled = true;
}
}
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
await input.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
type: "keyUp",
key: descriptor.key,
code: descriptor.code,
+96
View File
@@ -0,0 +1,96 @@
import type { MouseButton } from "@/transport/types";
import type { Point } from "./geometry";
import type { CdpRunner } from "./shared";
interface MouseClickDispatchOptions {
button: MouseButton;
clickCount: number;
modifiers: number;
signal?: AbortSignal;
moveSettleMs?: number;
}
type MouseClickDispatchResult = "completed" | "cancelled";
function waitForSettle(ms: number, signal: AbortSignal | undefined): Promise<boolean> {
if (ms <= 0) return Promise.resolve(signal?.aborted !== true);
if (signal?.aborted) return Promise.resolve(false);
return new Promise((resolve) => {
let settled = false;
const finish = (completed: boolean) => {
if (settled) return;
settled = true;
clearTimeout(timer);
signal?.removeEventListener("abort", onAbort);
resolve(completed);
};
const timer = setTimeout(() => finish(true), ms);
const onAbort = () => finish(false);
signal?.addEventListener("abort", onAbort, { once: true });
});
}
/**
* Dispatch one coherent CDP mouse click in top-viewport CSS coordinates.
*
* Keeping the sequence here prevents DOM and Surface interaction paths from
* duplicating cancellation and best-effort release behavior. Callers that
* target asynchronously hit-tested content may request a settle interval.
*/
export async function dispatchMouseClick(
cdp: CdpRunner,
tabId: number,
point: Point,
options: MouseClickDispatchOptions,
): Promise<MouseClickDispatchResult> {
const { button, clickCount, modifiers, signal, moveSettleMs = 0 } = options;
let pressed = false;
const release = () =>
cdp.send(tabId, "Input.dispatchMouseEvent", {
type: "mouseReleased",
x: point.x,
y: point.y,
button,
clickCount,
modifiers,
});
try {
await cdp.send(tabId, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: point.x,
y: point.y,
modifiers,
});
if (!(await waitForSettle(moveSettleMs, signal))) return "cancelled";
await cdp.send(tabId, "Input.dispatchMouseEvent", {
type: "mousePressed",
x: point.x,
y: point.y,
button,
clickCount,
modifiers,
});
pressed = true;
if (signal?.aborted) {
await release();
pressed = false;
return "cancelled";
}
await release();
pressed = false;
return "completed";
} catch (error) {
if (pressed) {
try {
await release();
} catch (releaseError) {
console.debug("[bsk mouse-input] best-effort mouse release failed", releaseError);
}
}
throw error;
}
}
File diff suppressed because it is too large. Load diff
+1
View File
@@ -243,6 +243,7 @@ export async function handleSessionStop(
// Step 2: clear the per-session RefStore (review M6/M7 parity).
ctx.refStore.clear();
ctx.surfaceCaptures.clear();
clearRecordingForSession(params.session_id);
+19 -1
View File
@@ -2,8 +2,9 @@
// compound CDP node identity via the session RefStore, and build stable
// `ref_not_found` errors for hard-failure tool paths.
import type { Rect } from "@browser-skill/vom";
import type { SessionContext } from "@/session-manager/manager";
import { normaliseRef } from "@/session-manager/ref-store";
import { normaliseRef, type RefCapability, type RefTargetKind } from "@/session-manager/ref-store";
import type { RpcError } from "@/transport/types";
import { rpcError } from "./errors";
@@ -12,6 +13,10 @@ export interface SnapshotRefLookup {
refKey: string;
frameId?: string;
cdpSessionId?: string;
visibleRect?: Rect;
kind: RefTargetKind;
capabilities: RefCapability[];
generation: number;
}
function refEntryForTab(ctx: SessionContext, refKey: string, tabId: number) {
@@ -37,6 +42,10 @@ export function lookupSnapshotRef(
refKey,
...(entry.frameId ? { frameId: entry.frameId } : {}),
...(entry.cdpSessionId ? { cdpSessionId: entry.cdpSessionId } : {}),
...(entry.visibleRect ? { visibleRect: entry.visibleRect } : {}),
kind: entry.kind,
capabilities: entry.capabilities,
generation: entry.generation,
};
}
@@ -49,6 +58,7 @@ export function resolveSnapshotRef(
ctx: SessionContext,
ref: string,
tabId: number,
requiredCapability?: RefCapability,
): SnapshotRefLookup | RpcError {
const looked = lookupSnapshotRef(ctx, ref, tabId);
if (looked === null) {
@@ -58,5 +68,13 @@ export function resolveSnapshotRef(
`ref ${ref} unknown for tab ${tabId} in session ${ctx.sessionId}`,
);
}
if (requiredCapability && !looked.capabilities.includes(requiredCapability)) {
return rpcError(
"permission_denied",
"ref_capability_denied",
`ref ${ref} does not support ${requiredCapability}`,
{ ref: looked.refKey, required_capability: requiredCapability, kind: looked.kind },
);
}
return looked;
}
@@ -0,0 +1,88 @@
import type { Rect } from "@browser-skill/vom";
import type { Point, Region, ViewportRect } from "./geometry";
const RECT_EPSILON = 0.01;
export function surfaceVisibleRect(
liveRect: ViewportRect,
observedRect: Rect | undefined,
): Rect | null {
const observed = observedRect ?? {
x: liveRect.x,
y: liveRect.y,
w: liveRect.width,
h: liveRect.height,
};
const x = Math.max(liveRect.x, observed.x);
const y = Math.max(liveRect.y, observed.y);
const right = Math.min(liveRect.x + liveRect.width, observed.x + observed.w);
const bottom = Math.min(liveRect.y + liveRect.height, observed.y + observed.h);
return right > x && bottom > y ? { x, y, w: right - x, h: bottom - y } : null;
}
export function sameRect(a: Rect, b: Rect): boolean {
return (
Math.abs(a.x - b.x) <= RECT_EPSILON &&
Math.abs(a.y - b.y) <= RECT_EPSILON &&
Math.abs(a.w - b.w) <= RECT_EPSILON &&
Math.abs(a.h - b.h) <= RECT_EPSILON
);
}
export function mapImagePointToViewport(
rect: Rect,
imageWidth: number,
imageHeight: number,
imageX: number,
imageY: number,
): Point | null {
if (
!Number.isFinite(imageX) ||
!Number.isFinite(imageY) ||
!Number.isSafeInteger(imageWidth) ||
!Number.isSafeInteger(imageHeight) ||
imageWidth <= 0 ||
imageHeight <= 0 ||
imageX < 0 ||
imageY < 0 ||
imageX >= imageWidth ||
imageY >= imageHeight ||
!Number.isFinite(rect.x) ||
!Number.isFinite(rect.y) ||
!Number.isFinite(rect.w) ||
!Number.isFinite(rect.h) ||
rect.w <= 0 ||
rect.h <= 0
) {
return null;
}
return {
x: rect.x + (imageX / imageWidth) * rect.w,
y: rect.y + (imageY / imageHeight) * rect.h,
};
}
function pointInPolygon(point: Point, polygon: Point[]): boolean {
for (let index = 0; index < polygon.length; index += 1) {
const a = polygon[index];
const b = polygon[(index + 1) % polygon.length];
const cross = (point.x - a.x) * (b.y - a.y) - (point.y - a.y) * (b.x - a.x);
const withinX = point.x >= Math.min(a.x, b.x) - 1e-9 && point.x <= Math.max(a.x, b.x) + 1e-9;
const withinY = point.y >= Math.min(a.y, b.y) - 1e-9 && point.y <= Math.max(a.y, b.y) + 1e-9;
if (Math.abs(cross) <= 1e-9 && withinX && withinY) return true;
}
let inside = false;
for (let index = 0, previous = polygon.length - 1; index < polygon.length; previous = index++) {
const a = polygon[index];
const b = polygon[previous];
const intersects =
a.y > point.y !== b.y > point.y &&
point.x < ((b.x - a.x) * (point.y - a.y)) / (b.y - a.y) + a.x;
if (intersects) inside = !inside;
}
return inside;
}
export function pointInRegion(point: Point, region: Region): boolean {
return region.some((polygon) => polygon.length >= 3 && pointInPolygon(point, polygon));
}
+260
View File
@@ -0,0 +1,260 @@
import type { CdpFrameGraph } from "@/browser-driver/frame-graph";
import type { SessionContext } from "@/session-manager/manager";
import type { RpcError } from "@/transport/types";
import { rpcError } from "./errors";
import { resolveNodeGeometry } from "./frame-geometry";
import { type CdpRunner, isRpcError, normaliseRef } from "./shared";
import { resolveSnapshotRef } from "./snapshot-ref";
import {
mapImagePointToViewport,
pointInRegion,
sameRect,
surfaceVisibleRect,
} from "./surface-coordinate";
export interface SurfaceCaptureEnvironment {
navigationIdentity: string;
viewportSignature: string;
frameProjectionSignature: string;
}
export interface SurfaceTargetResolverDeps {
cdp: CdpRunner;
signal?: AbortSignal;
}
export interface SurfacePointerTargetInput {
ref?: string;
selector?: string;
captureId?: string;
imageX?: number;
imageY?: number;
}
export interface ResolvedSurfacePointerTarget {
point: { x: number; y: number };
usedRef: string;
moveSettleMs: number;
capture: {
id: string;
imageX: number;
imageY: number;
};
}
// Canvas-style controls commonly update their pointer hit-test on the next
// animation frame. Leave a scheduling boundary after moving and before pressing.
export const SURFACE_POINTER_MOVE_SETTLE_MS = 32;
function stale(message: string): RpcError {
return rpcError("permission_denied", "surface_capture_stale", message);
}
function finiteObject(value: unknown): unknown {
if (Array.isArray(value)) return value.map(finiteObject);
if (typeof value !== "object" || value === null) return value;
return Object.fromEntries(
Object.entries(value)
.filter(
([, entry]) => entry !== undefined && (typeof entry !== "number" || Number.isFinite(entry)),
)
.sort(([a], [b]) => a.localeCompare(b))
.map(([key, entry]) => [key, finiteObject(entry)]),
);
}
function framePathSignature(graph: CdpFrameGraph, frameId: string | undefined): string | null {
if (!frameId) return "top";
const frames = new Map(graph.frames.map((frame) => [frame.frameId, frame]));
const path: Array<{
frameId: string;
parentFrameId?: string;
ownerBackendNodeId?: number;
targetSessionId?: string;
}> = [];
const seen = new Set<string>();
let current = frames.get(frameId);
while (current) {
if (seen.has(current.frameId)) return null;
seen.add(current.frameId);
path.push({
frameId: current.frameId,
...(current.parentFrameId ? { parentFrameId: current.parentFrameId } : {}),
...(current.ownerBackendNodeId !== undefined
? { ownerBackendNodeId: current.ownerBackendNodeId }
: {}),
...(current.target.sessionId ? { targetSessionId: current.target.sessionId } : {}),
});
if (!current.parentFrameId) return JSON.stringify(path);
const parent = frames.get(current.parentFrameId);
if (!parent) return null;
current = parent;
}
return null;
}
export async function captureSurfaceEnvironment(
cdp: CdpRunner,
tabId: number,
frameId: string | undefined,
): Promise<SurfaceCaptureEnvironment | RpcError> {
try {
const [tree, metrics, graph] = await Promise.all([
cdp.send<{
frameTree?: { frame?: { id?: string; loaderId?: string; url?: string } };
}>(tabId, "Page.getFrameTree", {}),
cdp.send<Record<string, unknown>>(tabId, "Page.getLayoutMetrics", {}),
frameId && cdp.getFrameGraph ? cdp.getFrameGraph(tabId) : Promise.resolve(null),
]);
const root = tree.frameTree?.frame;
if (!root?.id || !root.loaderId) {
return { code: "cdp_failed", message: "could not identify the current navigation" };
}
const frameProjectionSignature = frameId
? graph
? framePathSignature(graph, frameId)
: null
: "top";
if (!frameProjectionSignature) {
return { code: "cdp_failed", message: `could not identify frame projection for ${frameId}` };
}
return {
navigationIdentity: JSON.stringify({ id: root.id, loaderId: root.loaderId, url: root.url }),
viewportSignature: JSON.stringify(
finiteObject({
cssLayoutViewport: metrics.cssLayoutViewport,
cssVisualViewport: metrics.cssVisualViewport,
}),
),
frameProjectionSignature,
};
} catch (error) {
return { code: "cdp_failed", message: error instanceof Error ? error.message : String(error) };
}
}
function validatePointParams(input: SurfacePointerTargetInput): RpcError | null {
if (!input.captureId || typeof input.captureId !== "string") {
return { code: "invalid_params", message: "surface point click requires capture_id" };
}
if (typeof input.imageX !== "number" || !Number.isFinite(input.imageX)) {
return { code: "invalid_params", message: "image_x must be a finite number" };
}
if (typeof input.imageY !== "number" || !Number.isFinite(input.imageY)) {
return { code: "invalid_params", message: "image_y must be a finite number" };
}
if (!input.ref || input.selector) {
return {
code: "invalid_params",
message: "surface point click requires one Surface ref and does not accept a selector",
};
}
return null;
}
function captureConsumeError(reason: "not_found" | "expired" | "consumed"): RpcError {
const code = reason === "not_found" ? "not_found" : "permission_denied";
return rpcError(code, `surface_capture_${reason}`, `surface capture is ${reason}`);
}
function aborted(signal: AbortSignal | undefined): RpcError | null {
return signal?.aborted
? { code: "cancelled", message: "surface target resolution aborted" }
: null;
}
/** Resolve one fresh Surface capture coordinate into a validated top-viewport pointer target. */
export async function resolveSurfacePointerTarget(
ctx: SessionContext,
target: { tabId: number; url?: string },
input: SurfacePointerTargetInput,
deps: SurfaceTargetResolverDeps,
): Promise<ResolvedSurfacePointerTarget | RpcError> {
const invalid = validatePointParams(input);
if (invalid) return invalid;
const earlyAbort = aborted(deps.signal);
if (earlyAbort) return earlyAbort;
const consumed = ctx.surfaceCaptures.consume(input.captureId as string);
if (!consumed.ok) return captureConsumeError(consumed.reason);
const capture = consumed.capture;
const postConsumeAbort = aborted(deps.signal);
if (postConsumeAbort) return postConsumeAbort;
if (capture.sessionId !== ctx.sessionId || capture.tabId !== target.tabId) {
return stale("surface capture belongs to a different session or tab");
}
if (normaliseRef(input.ref as string) !== capture.surface.ref) {
return stale("surface ref does not match the capture");
}
const node = resolveSnapshotRef(ctx, input.ref as string, target.tabId, "screenshot");
if (isRpcError(node)) return stale(node.message);
if (
node.kind !== "surface" ||
node.backendNodeId !== capture.surface.backendNodeId ||
node.frameId !== capture.surface.frameId ||
node.generation !== capture.surface.observationGeneration
) {
return stale("surface observation generation or node identity changed");
}
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
try {
await deps.cdp.ensureAttachedToUrl?.(target.tabId, target.url);
} catch (error) {
return { code: "cdp_failed", message: error instanceof Error ? error.message : String(error) };
}
const environment = await captureSurfaceEnvironment(deps.cdp, target.tabId, node.frameId);
if (isRpcError(environment)) return environment;
if (
environment.navigationIdentity !== capture.navigationIdentity ||
environment.viewportSignature !== capture.viewportSignature ||
environment.frameProjectionSignature !== capture.frameProjectionSignature
) {
return stale("navigation, viewport, zoom, scroll, or frame projection changed");
}
const geometry = await resolveNodeGeometry(
deps.cdp,
target.tabId,
{
target: {
tabId: target.tabId,
...(node.cdpSessionId ? { sessionId: node.cdpSessionId } : {}),
},
backendNodeId: node.backendNodeId,
...(node.frameId ? { frameId: node.frameId } : {}),
},
{ scrollIntoView: false },
);
if (isRpcError(geometry)) return stale(geometry.message);
const currentRect = surfaceVisibleRect(geometry.topBounds, node.visibleRect);
if (!currentRect || !sameRect(currentRect, capture.topViewportRect)) {
return stale("surface visible region changed");
}
const point = mapImagePointToViewport(
capture.topViewportRect,
capture.imageWidth,
capture.imageHeight,
input.imageX as number,
input.imageY as number,
);
if (!point || !pointInRegion(point, geometry.topVisibleRegions)) {
return rpcError(
"invalid_params",
"surface_coordinate_invalid",
"image coordinate is outside the captured Surface",
);
}
return {
point,
usedRef: capture.surface.ref,
moveSettleMs: SURFACE_POINTER_MOVE_SETTLE_MS,
capture: {
id: capture.id,
imageX: input.imageX as number,
imageY: input.imageY as number,
},
};
}
@@ -36,7 +36,7 @@ function fakeSnapshotReply() {
},
layout: {
nodeIndex: [1, 2, 3],
// styles columns follow requested computedStyles order: [position, pointer-events]
// Legacy fixture: omitted style columns fall back to visible defaults.
styles: [
[i("static"), i("auto")],
[i("fixed"), i("auto")],
@@ -682,6 +682,84 @@ describe("captureViewModel", () => {
expect(nodes.find((n) => n.backendNodeId === 11)?.cursor).toBe("auto");
});
it("captures painted visibility as DOM fallback evidence", async () => {
const S = ["html", "body", "button", "static", "auto", "visible", "hidden", "1", "0"];
const i = (value: string) => S.indexOf(value);
const snapshot = {
strings: S,
documents: [
{
nodes: {
parentIndex: [-1, 0, 1, 1, 1],
nodeName: [i("html"), i("body"), i("button"), i("button"), i("button")],
backendNodeId: [10, 11, 12, 13, 14],
attributes: [[], [], [], [], []],
},
layout: {
nodeIndex: [1, 2, 3, 4],
styles: [
[i("static"), i("auto"), i("auto"), i("visible"), i("1")],
[i("static"), i("auto"), i("auto"), i("visible"), i("1")],
[i("static"), i("auto"), i("auto"), i("hidden"), i("1")],
[i("static"), i("auto"), i("auto"), i("visible"), i("0")],
],
bounds: [
[0, 0, 1000, 800],
[10, 10, 100, 30],
[10, 50, 100, 30],
[10, 90, 100, 30],
],
paintOrders: [0, 1, 2, 3],
},
},
],
};
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
expect(nodes.find((node) => node.backendNodeId === 12)?.rendered).toBe(true);
expect(nodes.find((node) => node.backendNodeId === 13)?.rendered).toBe(false);
expect(nodes.find((node) => node.backendNodeId === 14)?.rendered).toBe(false);
});
it("propagates fully transparent ancestor suppression to painted descendants", async () => {
const S = ["html", "body", "div", "canvas", "static", "auto", "visible", "1", "0"];
const i = (value: string) => S.indexOf(value);
const snapshot = {
strings: S,
documents: [
{
nodes: {
parentIndex: [-1, 0, 1, 2],
nodeName: [i("html"), i("body"), i("div"), i("canvas")],
backendNodeId: [10, 11, 12, 13],
attributes: [[], [], [], []],
},
layout: {
nodeIndex: [1, 2, 3],
styles: [
[i("static"), i("auto"), i("auto"), i("visible"), i("1")],
[i("static"), i("auto"), i("auto"), i("visible"), i("0")],
[i("static"), i("auto"), i("auto"), i("visible"), i("1")],
],
bounds: [
[0, 0, 1000, 800],
[10, 10, 200, 100],
[10, 10, 200, 100],
],
paintOrders: [0, 1, 2],
},
},
],
};
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
const canvas = nodes.find((node) => node.backendNodeId === 13);
expect(canvas?.rendered).toBe(true);
expect(canvas?.visuallySuppressed).toBe(true);
});
it("subtracts scroll offset to make rects viewport-relative", async () => {
const cdp = {
send: vi.fn(async (_t: number, method: string) => {
@@ -132,4 +132,67 @@ describe("captureFrameData", () => {
]),
);
});
it("keeps OOPIF semantics when viewport projection is unavailable", async () => {
const owner = { ...ownerNode(10, 50), rect: null, localRect: null };
const captured: CapturedViewModel = {
nodes: [owner],
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
frameNodes: new Map([["main", [owner]]]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
if (method === "DOM.getBoxModel") throw new Error("owner geometry unavailable");
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
throw new Error(`unexpected root ${method}`);
}) as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "Page.getLayoutMetrics") throw new Error("viewport unavailable");
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return childSnapshot("child", 101);
if (method === "Accessibility.getFullAXTree") {
return {
nodes: [
{
nodeId: "button",
backendDOMNodeId: 101,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Continue" },
},
],
};
}
throw new Error(`unexpected ${method}`);
}) as unknown as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4, sessionId: "child-session" },
},
],
})),
};
const documents = await captureFrameData(cdp, 4, captured);
const childDocument = documents.find((document) => document.frameId === "child");
expect(childDocument?.axNodes).toEqual([
expect.objectContaining({ backendDOMNodeId: 101, frameId: "child" }),
]);
expect(childDocument?.domNodes.find((node) => node.backendNodeId === 101)).toEqual(
expect.objectContaining({ rect: null, localRect: { x: 10, y: 20, w: 100, h: 40 } }),
);
});
});
@@ -0,0 +1,183 @@
import { describe, expect, it, vi } from "vitest";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import type { CdpRunner } from "../../shared";
import type { CapturedNode } from "../capture";
import type { FrameDocument, FrameOwnedAxNode } from "../frame-document";
import { probeTooltipNames } from "../name-enrichment";
import { buildSemanticGraph, resolveSemanticGraph } from "../semantic-graph";
import { stableIdentifierName } from "../semantic-graph/name-evidence";
import { frameBackendKey } from "../semantic-graph/types";
function document(
target: CdpTarget,
backendNodeId: number,
accessibleName?: string,
frameId = "child",
x = 10,
): FrameDocument<FrameOwnedAxNode> {
const node: CapturedNode = {
backendNodeId,
parentBackendNodeId: null,
frameId,
tag: "button",
attrs: {
id: "toolInsertRecord",
"data-test-id": "toolInsertRecord",
...(accessibleName ? { "aria-label": accessibleName } : {}),
},
rect: { x, y: 20, w: 40, h: 30 },
localRect: { x: 2, y: 3, w: 40, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
};
return {
frameId,
parentFrameId: "main",
contextScopeId: "child",
target,
axNodes: [],
domNodes: [node],
url: "https://example.com/frame",
};
}
function semantics(documents: FrameDocument<FrameOwnedAxNode>[]) {
return resolveSemanticGraph(
buildSemanticGraph({
documents,
viewport: { width: 800, height: 600 },
rootFrameId: documents[0]?.frameId,
}),
{ identifierFallback: false },
);
}
describe("tooltip name enrichment", () => {
it("uses the owning frame target and upgrades an identifier name from a tooltip", async () => {
const target = { tabId: 7, sessionId: "oopif-session" };
let hovered = false;
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method, params) => {
if (method === "Input.dispatchMouseEvent") {
hovered = (params as { x?: number }).x === 30;
}
return {};
}) as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "Page.createIsolatedWorld") return { executionContextId: 11 };
if (method === "DOM.resolveNode") return { object: { objectId: "button-501" } };
if (method === "Runtime.callFunctionOn") {
return { result: { value: hovered ? ["插入行"] : [] } };
}
return {};
}) as CdpRunner["sendToTarget"],
};
const documents = [document(target, 501)];
const graph = semantics(documents);
const names = await probeTooltipNames(cdp, 7, documents, graph);
expect(names.get(frameBackendKey("child", 501))).toBe("插入行");
expect(cdp.sendToTarget).toHaveBeenCalledWith(
target,
"Page.createIsolatedWorld",
expect.objectContaining({ frameId: "child" }),
);
const sendsBeforeCache = vi.mocked(cdp.send).mock.calls.length;
const targetSendsBeforeCache = vi.mocked(
cdp.sendToTarget as NonNullable<CdpRunner["sendToTarget"]>,
).mock.calls.length;
const cached = await probeTooltipNames(cdp, 7, documents, graph);
expect(cached.get(frameBackendKey("child", 501))).toBe("插入行");
expect(cdp.send).toHaveBeenCalledTimes(sendsBeforeCache);
expect(cdp.sendToTarget).toHaveBeenCalledTimes(targetSendsBeforeCache);
});
it("does not probe controls that already have a higher-confidence name", async () => {
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
sendToTarget: vi.fn(async () => ({ executionContextId: 12 })) as CdpRunner["sendToTarget"],
};
const documents = [document({ tabId: 8 }, 601, "Add a new record")];
const names = await probeTooltipNames(cdp, 8, documents, semantics(documents));
expect(names.size).toBe(0);
expect(cdp.send).not.toHaveBeenCalled();
expect(cdp.sendToTarget).not.toHaveBeenCalled();
});
it("does not collect supplemental names from form controls", async () => {
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
sendToTarget: vi.fn(async () => ({ executionContextId: 12 })) as CdpRunner["sendToTarget"],
};
const inputDocument = document({ tabId: 8 }, 602);
inputDocument.domNodes[0] = {
...inputDocument.domNodes[0],
tag: "input",
attrs: { type: "email" },
formValue: "user@example.com",
formDefaultValue: "",
formState: "filled",
};
const names = await probeTooltipNames(cdp, 8, [inputDocument], semantics([inputDocument]));
expect(names.size).toBe(0);
expect(cdp.send).not.toHaveBeenCalled();
expect(cdp.sendToTarget).not.toHaveBeenCalled();
});
it("keeps tooltip evidence isolated across sibling frame sessions", async () => {
let hoveredX = -10;
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method, params) => {
if (method === "Input.dispatchMouseEvent") {
hoveredX = (params as { x: number }).x;
}
return {};
}) as CdpRunner["send"],
sendToTarget: vi.fn(async (target, method, params) => {
if (method === "Page.createIsolatedWorld") {
return { executionContextId: target.sessionId === "left-session" ? 21 : 22 };
}
if (method === "DOM.resolveNode") {
return { object: { objectId: target.sessionId === "left-session" ? "left" : "right" } };
}
if (method === "Runtime.callFunctionOn") {
const objectId = (params as { objectId: string }).objectId;
const value =
objectId === "left" && hoveredX === 30
? ["Left action"]
: objectId === "right" && hoveredX === 130
? ["Right action"]
: [];
return { result: { value } };
}
return {};
}) as CdpRunner["sendToTarget"],
};
const documents = [
document({ tabId: 9, sessionId: "left-session" }, 701, undefined, "left", 10),
document({ tabId: 9, sessionId: "right-session" }, 701, undefined, "right", 110),
];
const names = await probeTooltipNames(cdp, 9, documents, semantics(documents));
expect(names.get(frameBackendKey("left", 701))).toBe("Left action");
expect(names.get(frameBackendKey("right", 701))).toBe("Right action");
});
});
describe("stable identifier evidence", () => {
it("accepts readable action identifiers and rejects framework-generated ids", () => {
expect(stableIdentifierName({ id: "toolInsertRecord" })).toBe("Insert record");
expect(stableIdentifierName({ id: "reactivateAccount" })).toBe("Reactivate account");
expect(stableIdentifierName({ id: "headlessui-menu-button-r1" })).toBeUndefined();
expect(stableIdentifierName({ id: "7f15a3bc91" })).toBeUndefined();
});
});
@@ -0,0 +1,256 @@
import type { VomScene } from "@browser-skill/vom";
import { describe, expect, it } from "vitest";
import type { CapturedNode } from "../capture";
import type { CapturedFrameDocument } from "../frame-capture";
import {
clusterRenderedSurfaces,
discoverRenderedSurfaces,
projectRenderedSurfaces,
} from "../rendered-surfaces";
import type { SemanticAxNode } from "../semantic-graph";
function domNode(backendNodeId: number, overrides: Partial<CapturedNode> = {}): CapturedNode {
return {
backendNodeId,
parentBackendNodeId: null,
frameId: "main",
ownerFrameBackendNodeId: null,
tag: "canvas",
attrs: {},
rect: { x: 10, y: 20, w: 800, h: 500 },
localRect: { x: 10, y: 20, w: 800, h: 500 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
rendered: true,
...overrides,
};
}
function document(
domNodes: CapturedNode[],
axNodes: SemanticAxNode[] = [],
): CapturedFrameDocument<SemanticAxNode> {
return {
frameId: domNodes[0]?.frameId ?? "main",
contextScopeId: domNodes[0]?.frameId ?? "main",
target: { tabId: 4 },
domNodes,
axNodes,
};
}
describe("rendered surface discovery", () => {
it("finds prominent rendered canvases and excludes hidden descendants", () => {
const visible = domNode(2, { parentBackendNodeId: 1 });
const hidden = domNode(3, { parentBackendNodeId: 4 });
const surfaces = discoverRenderedSurfaces(
[
document([
domNode(1, { tag: "main", rect: null, localRect: null }),
visible,
domNode(4, { tag: "section", attrs: { "aria-hidden": "true" }, rect: null }),
hidden,
]),
],
{ width: 1280, height: 720 },
);
expect(surfaces).toHaveLength(1);
expect(surfaces[0]).toMatchObject({ backendNodeId: 2 });
});
it("keeps tiny canvases as individually addressable exact discoveries", () => {
const surfaces = discoverRenderedSurfaces(
[document([domNode(2, { rect: { x: 1, y: 1, w: 8, h: 8 } })])],
{ width: 1280, height: 720 },
);
expect(surfaces).toEqual([expect.objectContaining({ backendNodeId: 2 })]);
});
it("keeps a surface when the canvas only has partial native accessibility content", () => {
const axNodes = [
{
nodeId: "canvas",
backendDOMNodeId: 2,
role: { type: "role", value: "presentation" },
childIds: ["button"],
frameId: "main",
},
{
nodeId: "button",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
frameId: "main",
},
] as SemanticAxNode[];
expect(
discoverRenderedSurfaces([document([domNode(2)], axNodes)], { width: 1280, height: 720 }),
).toEqual([expect.objectContaining({ backendNodeId: 2 })]);
});
it("discovers unnamed canvases without guessing labels from engineering attributes", () => {
const canvas = domNode(2, {
attrs: {
id: "must-not-be-a-label",
class: "must-not-be-a-label",
"data-testid": "must-not-be-a-label",
},
});
expect(discoverRenderedSurfaces([document([canvas])], { width: 1280, height: 720 })).toEqual([
expect.not.objectContaining({
label: expect.anything(),
}),
]);
});
it("treats blank explicit Canvas names as unnamed", () => {
expect(
discoverRenderedSurfaces(
[document([domNode(2, { attrs: { "aria-label": " ", title: "\n\t" } })])],
{ width: 1280, height: 720 },
),
).toEqual([expect.not.objectContaining({ label: expect.anything() })]);
});
it("excludes canvases inside BrowserSkill-owned DOM subtrees", () => {
const owner = domNode(1, { tag: "div", rect: null, localRect: null });
const canvas = domNode(2, { parentBackendNodeId: 1 });
expect(
discoverRenderedSurfaces(
[document([owner, canvas])],
{ width: 1280, height: 720 },
new Set([1]),
),
).toEqual([]);
});
it("excludes canvases suppressed by a fully transparent ancestor", () => {
const owner = domNode(1, {
tag: "div",
rect: { x: 0, y: 0, w: 900, h: 600 },
visuallySuppressed: true,
});
const canvas = domNode(2, { parentBackendNodeId: 1 });
expect(
discoverRenderedSurfaces([document([owner, canvas])], { width: 1280, height: 720 }),
).toEqual([]);
});
it("clips canvases to overflow ancestors and drops fully clipped canvases", () => {
const owner = domNode(1, {
tag: "div",
rect: { x: 10, y: 20, w: 100, h: 70 },
overflowX: "hidden",
overflowY: "hidden",
});
const partial = domNode(2, {
parentBackendNodeId: 1,
rect: { x: 55, y: 30, w: 140, h: 60 },
});
const fullyClipped = domNode(3, {
parentBackendNodeId: 1,
rect: { x: 140, y: 30, w: 80, h: 50 },
});
expect(
discoverRenderedSurfaces([document([owner, partial, fullyClipped])], {
width: 1280,
height: 720,
}),
).toEqual([
expect.objectContaining({
backendNodeId: 2,
visibleRect: { x: 55, y: 30, w: 55, h: 60 },
}),
]);
});
});
describe("rendered surface clustering and projection", () => {
it("collapses overlapping canvas layers and attaches them to the nearest retained parent", () => {
const body = domNode(1, { tag: "body", rect: null, localRect: null });
const surfaces = discoverRenderedSurfaces(
[
document([
body,
domNode(2, { parentBackendNodeId: 1, paintOrder: 1 }),
domNode(3, { parentBackendNodeId: 1, paintOrder: 2 }),
]),
],
{ width: 1280, height: 720 },
);
const groups = clusterRenderedSurfaces(surfaces);
const scene: VomScene = {
viewport: { width: 1280, height: 720 },
nodes: [
{
id: 10,
parentId: null,
backendNodeId: 1,
frameId: "main",
tag: "body",
role: "RootWebArea",
rect: null,
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
],
};
expect(groups).toHaveLength(1);
expect(groups[0]?.members).toHaveLength(2);
expect(groups[0]?.label).toBeUndefined();
expect(
projectRenderedSurfaces(
scene,
[document([body, ...surfaces.map((s) => domNode(s.backendNodeId))])],
groups,
),
).toMatchObject({
visualSurfaces: [expect.objectContaining({ parentId: 10, backendNodeId: 3, memberCount: 2 })],
});
});
it("does not merge a contained canvas with a larger independent canvas", () => {
const groups = clusterRenderedSurfaces([
...discoverRenderedSurfaces(
[
document([
domNode(1, { tag: "main", rect: null, localRect: null }),
domNode(2, { parentBackendNodeId: 1 }),
domNode(3, {
parentBackendNodeId: 1,
rect: { x: 30, y: 40, w: 200, h: 100 },
}),
]),
],
{ width: 1280, height: 720 },
),
]);
expect(groups).toHaveLength(2);
});
it("does not merge coincident canvases owned by different containers", () => {
const groups = clusterRenderedSurfaces(
discoverRenderedSurfaces(
[
document([
domNode(1, { tag: "section", rect: null, localRect: null }),
domNode(2, { tag: "section", rect: null, localRect: null }),
domNode(3, { parentBackendNodeId: 1 }),
domNode(4, { parentBackendNodeId: 2 }),
]),
],
{ width: 1280, height: 720 },
),
);
expect(groups).toHaveLength(2);
});
});
@@ -0,0 +1,782 @@
import { isVomReferenceNode, renderVom } from "@browser-skill/vom";
import { describe, expect, it } from "vitest";
import type { CapturedNode } from "../capture";
import type { FrameDocument } from "../frame-document";
import { buildSemanticVomScene, type SemanticAxNode } from "../semantic-graph";
function dom(
backendNodeId: number,
parentBackendNodeId: number | null,
tag: string,
attrs: Record<string, string> = {},
textContent?: string,
): CapturedNode {
return {
backendNodeId,
parentBackendNodeId,
tag,
attrs,
rect: { x: 0, y: 0, w: 100, h: 30 },
paintOrder: backendNodeId,
position: "static",
pointerEvents: "auto",
...(textContent ? { textContent } : {}),
};
}
function document(
frameId: string,
axNodes: SemanticAxNode[],
domNodes: CapturedNode[],
frame?: Pick<FrameDocument<SemanticAxNode>, "parentFrameId" | "ownerBackendNodeId">,
): FrameDocument<SemanticAxNode> {
return {
frameId,
contextScopeId: frameId,
target: { tabId: 1 },
axNodes,
domNodes,
...frame,
};
}
describe("semantic VOM graph", () => {
it("preserves backend-less AX structure without making it referenceable", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["toolbar"],
},
{
nodeId: "toolbar",
parentId: "root",
role: { type: "role", value: "toolbar" },
name: { type: "computedString", value: "Formatting" },
childIds: ["bold", "italic"],
},
{
nodeId: "bold",
parentId: "toolbar",
backendDOMNodeId: 2,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Bold" },
},
{
nodeId: "italic",
parentId: "toolbar",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Italic" },
},
],
[dom(1, null, "body"), dom(2, 1, "button"), dom(3, 1, "button")],
),
],
});
const toolbar = scene.nodes.find((node) => node.role === "toolbar");
const buttons = scene.nodes.filter((node) => node.role === "button");
expect(toolbar).toEqual(expect.objectContaining({ name: "Formatting", referenceable: false }));
expect(buttons.map((node) => node.parentId)).toEqual([toolbar?.id, toolbar?.id]);
expect(toolbar && isVomReferenceNode(toolbar)).toBe(false);
expect(renderVom(scene).refs.map((ref) => ref.backendNodeId)).toEqual([2, 3]);
});
it("resolves missing AX names through one DOM naming pipeline", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["labelled", "titled", "text"],
},
{
nodeId: "labelled",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "button" },
},
{
nodeId: "titled",
parentId: "root",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
},
{
nodeId: "text",
parentId: "root",
backendDOMNodeId: 4,
role: { type: "role", value: "button" },
},
],
[
dom(1, null, "body"),
dom(2, 1, "button", { "aria-label": "Add row" }),
dom(3, 1, "button", { title: "Settings" }),
dom(4, 1, "button"),
dom(5, 4, "span", {}, "Save"),
],
),
],
});
expect(scene.nodes.filter((node) => node.role === "button").map((node) => node.name)).toEqual([
"Add row",
"Settings",
"Save",
]);
});
it("aggregates AX text at the semantic text frontier", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["covered", "inline-only", "repeated", "labelled"],
},
{
nodeId: "covered",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "paragraph" },
childIds: ["covered-static"],
},
{
nodeId: "covered-static",
parentId: "covered",
role: { type: "role", value: "StaticText" },
name: { type: "computedString", value: "Covered text" },
childIds: ["covered-inline"],
},
{
nodeId: "covered-inline",
parentId: "covered-static",
role: { type: "role", value: "InlineTextBox" },
name: { type: "computedString", value: "Covered text" },
},
{
nodeId: "inline-only",
parentId: "root",
backendDOMNodeId: 3,
role: { type: "role", value: "paragraph" },
childIds: ["inline-leaf"],
},
{
nodeId: "inline-leaf",
parentId: "inline-only",
role: { type: "role", value: "InlineTextBox" },
name: { type: "computedString", value: "Inline fallback" },
},
{
nodeId: "repeated",
parentId: "root",
backendDOMNodeId: 4,
role: { type: "role", value: "paragraph" },
childIds: ["first-go", "second-go"],
},
{
nodeId: "first-go",
parentId: "repeated",
role: { type: "role", value: "StaticText" },
name: { type: "computedString", value: "Go" },
},
{
nodeId: "second-go",
parentId: "repeated",
role: { type: "role", value: "StaticText" },
name: { type: "computedString", value: "Go" },
},
{
nodeId: "labelled",
parentId: "root",
backendDOMNodeId: 5,
role: { type: "role", value: "button" },
childIds: ["visible-label"],
},
{
nodeId: "visible-label",
parentId: "labelled",
role: { type: "role", value: "StaticText" },
name: { type: "computedString", value: "Visible text" },
},
],
[
dom(1, null, "body"),
dom(2, 1, "p"),
dom(3, 1, "p"),
dom(4, 1, "p"),
dom(5, 1, "button", { "aria-label": "Explicit action" }),
],
),
],
});
expect(scene.nodes.find((node) => node.backendNodeId === 2)?.name).toBe("Covered text");
expect(scene.nodes.find((node) => node.backendNodeId === 3)?.name).toBe("Inline fallback");
expect(scene.nodes.find((node) => node.backendNodeId === 4)?.name).toBe("Go Go");
expect(scene.nodes.find((node) => node.backendNodeId === 5)?.name).toBe("Explicit action");
expect(renderVom(scene).text).not.toContain("Covered text Covered text");
});
it("uses stable identifiers only as a final name fallback", () => {
const base = document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["fallback", "labelled", "container"],
},
{
nodeId: "fallback",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "button" },
},
{
nodeId: "labelled",
parentId: "root",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Localized name" },
},
{
nodeId: "container",
parentId: "root",
backendDOMNodeId: 4,
role: { type: "role", value: "generic" },
},
],
[
dom(1, null, "body"),
dom(2, 1, "button", { "data-test-id": "toolInsertRecord" }),
dom(3, 1, "button", { id: "toolIgnoredFallback" }),
dom(4, 1, "div", { id: "toolbarContainer" }),
],
);
const staticScene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [base],
});
const enrichedScene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [base],
supplementalNames: new Map([["main\u00002", "插入行"]]),
});
expect(staticScene.nodes.find((node) => node.backendNodeId === 2)?.name).toBe("Insert record");
expect(staticScene.nodes.find((node) => node.backendNodeId === 3)?.name).toBe("Localized name");
expect(staticScene.nodes.find((node) => node.backendNodeId === 4)?.name).toBeUndefined();
expect(enrichedScene.nodes.find((node) => node.backendNodeId === 2)?.name).toBe("插入行");
expect(enrichedScene.nodes.find((node) => node.backendNodeId === 3)?.name).toBe(
"Localized name",
);
});
it("isolates equal backend node ids in sibling frames", () => {
const scene = buildSemanticVomScene({
viewport: { width: 1000, height: 800 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["owner-a", "owner-b"],
},
{
nodeId: "owner-a",
parentId: "root",
backendDOMNodeId: 10,
role: { type: "role", value: "Iframe" },
},
{
nodeId: "owner-b",
parentId: "root",
backendDOMNodeId: 20,
role: { type: "role", value: "Iframe" },
},
],
[dom(1, null, "body"), dom(10, 1, "iframe"), dom(20, 1, "iframe")],
),
document(
"frame-a",
[
{
nodeId: "button-a",
backendDOMNodeId: 5,
role: { type: "role", value: "button" },
childIds: ["text-a"],
},
{
nodeId: "text-a",
parentId: "button-a",
role: { type: "role", value: "StaticText" },
name: { type: "computedString", value: "Accept" },
childIds: ["inline-a"],
},
{
nodeId: "inline-a",
parentId: "text-a",
role: { type: "role", value: "InlineTextBox" },
name: { type: "computedString", value: "Accept" },
},
],
[dom(5, null, "button")],
{ parentFrameId: "main", ownerBackendNodeId: 10 },
),
document(
"frame-b",
[
{
nodeId: "button-b",
backendDOMNodeId: 5,
role: { type: "role", value: "button" },
childIds: ["text-b"],
},
{
nodeId: "text-b",
parentId: "button-b",
role: { type: "role", value: "StaticText" },
name: { type: "computedString", value: "Decline" },
childIds: ["inline-b"],
},
{
nodeId: "inline-b",
parentId: "text-b",
role: { type: "role", value: "InlineTextBox" },
name: { type: "computedString", value: "Decline" },
},
],
[dom(5, null, "button")],
{ parentFrameId: "main", ownerBackendNodeId: 20 },
),
],
});
const frameButtons = scene.nodes.filter((node) => node.backendNodeId === 5);
const owners = new Map(
scene.nodes
.filter((node) => node.backendNodeId === 10 || node.backendNodeId === 20)
.map((node) => [node.backendNodeId, node.id]),
);
expect(frameButtons.map((node) => node.frameId)).toEqual(["frame-a", "frame-b"]);
expect(frameButtons.map((node) => node.name)).toEqual(["Accept", "Decline"]);
expect(frameButtons.map((node) => node.parentId)).toEqual([owners.get(10), owners.get(20)]);
expect(renderVom(scene).refs.map((ref) => [ref.frameId, ref.backendNodeId])).toEqual([
["frame-a", 5],
["frame-b", 5],
]);
});
it("requires render evidence before promoting DOM fallback semantics", () => {
const hiddenOwner = {
...dom(10, 1, "iframe", { hidden: "" }),
rect: null,
localRect: null,
rendered: false,
};
const hiddenButton = {
...dom(2, 1, "button", { "aria-label": "Hidden action" }),
rendered: false,
};
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
},
],
[dom(1, null, "body"), hiddenButton, hiddenOwner],
),
document("hidden-frame", [], [dom(20, null, "button", {}, "Frame action")], {
parentFrameId: "main",
ownerBackendNodeId: 10,
}),
],
});
expect(scene.nodes.some((node) => node.backendNodeId === 2)).toBe(false);
expect(scene.nodes.some((node) => node.backendNodeId === 10)).toBe(false);
expect(scene.nodes.some((node) => node.frameId === "hidden-frame")).toBe(false);
expect(renderVom(scene).refs).toEqual([]);
});
it("retains rendered DOM fallback controls when AX semantics are unavailable", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[],
[dom(1, null, "body"), { ...dom(2, 1, "button", {}, "Save"), rendered: true }],
),
],
});
expect(renderVom(scene).refs).toEqual([
expect.objectContaining({ backendNodeId: 2, role: "button", name: "Save" }),
]);
});
it("lets explicit DOM structure override ignored AX metadata", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["toolbar"],
},
{
nodeId: "toolbar",
parentId: "root",
backendDOMNodeId: 2,
ignored: true,
role: { type: "role", value: "generic" },
childIds: ["wrapper"],
},
{
nodeId: "wrapper",
parentId: "toolbar",
backendDOMNodeId: 5,
role: { type: "role", value: "generic" },
childIds: ["bold", "italic"],
},
{
nodeId: "bold",
parentId: "wrapper",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Bold" },
},
{
nodeId: "italic",
parentId: "wrapper",
backendDOMNodeId: 4,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Italic" },
},
],
[
dom(1, null, "body"),
dom(2, 1, "div", { role: "toolbar" }),
dom(5, 2, "div"),
dom(3, 5, "button"),
dom(4, 5, "button"),
],
),
],
});
const toolbar = scene.nodes.find((node) => node.backendNodeId === 2);
const buttons = scene.nodes.filter((node) => [3, 4].includes(node.backendNodeId ?? -1));
expect(toolbar).toEqual(expect.objectContaining({ role: "toolbar" }));
expect(toolbar && isVomReferenceNode(toolbar)).toBe(false);
expect(scene.nodes.some((node) => node.role === "group")).toBe(false);
expect(buttons.map((node) => node.parentId)).toEqual([toolbar?.id, toolbar?.id]);
});
it("infers an unnamed group only from independent interaction branches", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["wrapper"],
},
{
nodeId: "wrapper",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "generic" },
childIds: ["first", "second"],
},
{
nodeId: "first",
parentId: "wrapper",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "First" },
},
{
nodeId: "second",
parentId: "wrapper",
backendDOMNodeId: 4,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Second" },
},
],
[dom(1, null, "body"), dom(2, 1, "div"), dom(3, 2, "button"), dom(4, 2, "button")],
),
],
});
const group = scene.nodes.find((node) => node.backendNodeId === 2);
const buttons = scene.nodes.filter((node) => [3, 4].includes(node.backendNodeId ?? -1));
expect(group).toEqual(expect.objectContaining({ role: "group" }));
expect(group?.name).toBeUndefined();
expect(group && isVomReferenceNode(group)).toBe(false);
expect(buttons.map((node) => node.parentId)).toEqual([group?.id, group?.id]);
const rendered = renderVom(scene);
const lines = rendered.text.split("\n");
const groupLine = lines.findIndex((line) => line.trim() === "group");
expect(groupLine).toBeGreaterThanOrEqual(0);
for (const ref of rendered.refs) {
expect(ref.line).toBeGreaterThan(groupLine);
expect(lines[ref.line]).toMatch(/^\s+@e\d+ button/);
}
});
it("never promotes a form value into its semantic name through supplemental evidence", () => {
const secret = "user@example.com";
const input = {
...dom(2, 1, "input", { type: "email" }),
formValue: secret,
formDefaultValue: "",
formState: "filled" as const,
};
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
supplementalNames: new Map([["main\u00002", secret]]),
identifierFallback: false,
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["email"],
},
{
nodeId: "email",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "textbox" },
value: { value: secret },
},
],
[dom(1, null, "body"), input],
),
],
});
const field = scene.nodes.find((node) => node.backendNodeId === 2);
expect(field?.name).toBeUndefined();
const rendered = renderVom(scene, { redactValues: true });
expect(rendered.text).toContain("•••");
expect(JSON.stringify(rendered)).not.toContain(secret);
});
it("keeps uncertain single-branch wrappers flat", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["wrapper"],
},
{
nodeId: "wrapper",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "generic" },
childIds: ["button"],
},
{
nodeId: "button",
parentId: "wrapper",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Only action" },
},
],
[dom(1, null, "body"), dom(2, 1, "div"), dom(3, 2, "button")],
),
],
});
expect(scene.nodes.some((node) => node.role === "group")).toBe(false);
expect(scene.nodes.find((node) => node.backendNodeId === 3)?.parentId).toBe(
scene.nodes.find((node) => node.backendNodeId === 1)?.id,
);
});
it("does not infer across mixed content boundaries", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["wrapper"],
},
{
nodeId: "wrapper",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "generic" },
childIds: ["first", "second", "paragraph"],
},
{
nodeId: "first",
parentId: "wrapper",
backendDOMNodeId: 3,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "First" },
},
{
nodeId: "second",
parentId: "wrapper",
backendDOMNodeId: 4,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Second" },
},
{
nodeId: "paragraph",
parentId: "wrapper",
backendDOMNodeId: 5,
role: { type: "role", value: "paragraph" },
},
],
[
dom(1, null, "body"),
dom(2, 1, "div"),
dom(3, 2, "button"),
dom(4, 2, "button"),
dom(5, 2, "p", {}, "Description"),
],
),
],
});
expect(scene.nodes.some((node) => node.role === "group")).toBe(false);
});
it("keeps only the innermost reliable inferred group", () => {
const scene = buildSemanticVomScene({
viewport: { width: 800, height: 600 },
rootFrameId: "main",
documents: [
document(
"main",
[
{
nodeId: "root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
childIds: ["outer"],
},
{
nodeId: "outer",
parentId: "root",
backendDOMNodeId: 2,
role: { type: "role", value: "generic" },
childIds: ["inner", "third"],
},
{
nodeId: "inner",
parentId: "outer",
backendDOMNodeId: 3,
role: { type: "role", value: "generic" },
childIds: ["first", "second"],
},
{
nodeId: "first",
parentId: "inner",
backendDOMNodeId: 4,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "First" },
},
{
nodeId: "second",
parentId: "inner",
backendDOMNodeId: 5,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Second" },
},
{
nodeId: "third",
parentId: "outer",
backendDOMNodeId: 6,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Third" },
},
],
[
dom(1, null, "body"),
dom(2, 1, "div"),
dom(3, 2, "div"),
dom(4, 3, "button"),
dom(5, 3, "button"),
dom(6, 2, "button"),
],
),
],
});
const groups = scene.nodes.filter((node) => node.role === "group");
expect(groups.map((node) => node.backendNodeId)).toEqual([3]);
expect(scene.nodes.find((node) => node.backendNodeId === 6)?.parentId).not.toBe(groups[0]?.id);
});
});
+59 -36
View File
@@ -1,16 +1,25 @@
// CDP capture adapter: DOMSnapshot.captureSnapshot + Page.getLayoutMetrics
// → CapturedNode[] + Viewport. This is the ONLY VOM module that touches
// raw CDP. The captureSnapshot reply is columnar (parallel arrays + a
// shared string table); we request exactly three computed styles so the
// `styles` columns are [position, pointer-events, cursor] in that order.
// shared string table); requested computed styles are decoded through
// STYLE_COL so capture and visibility policy share one explicit contract.
import type { Rect, Viewport } from "@browser-skill/vom";
import { evaluateHoverTrigger } from "@/lib/hover-trigger-policy";
import { isOverlayHostNode, OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
import { childFrameProjection, type GeometryProjection, projectRectToViewport } from "../geometry";
import type { CdpRunner } from "../shared";
import { clearHover, waitForHover } from "./hover-perception";
const REQUESTED_STYLES = ["position", "pointer-events", "cursor"] as const;
const REQUESTED_STYLES = [
"position",
"pointer-events",
"cursor",
"visibility",
"opacity",
"overflow-x",
"overflow-y",
] as const;
const STYLE_COL = Object.fromEntries(
REQUESTED_STYLES.map((name, index) => [name, index]),
) as Record<(typeof REQUESTED_STYLES)[number], number>;
@@ -38,6 +47,16 @@ export interface CapturedNode {
* `textContent`: the live parser always sets it, hand-built fixtures may not.
*/
cursor?: string;
overflowX?: string;
overflowY?: string;
/** True when this node or one of its DOM ancestors makes the subtree fully transparent/hidden. */
visuallySuppressed?: boolean;
/**
* Whether the live DOM snapshot provides a painted, non-hidden box for this
* node. Semantic resolution uses this only for DOM fallback nodes; AX-backed
* nodes remain authoritative even when they are outside the viewport.
*/
rendered?: boolean;
textContent?: string;
formState?: "empty" | "filled" | "default";
formValue?: string;
@@ -460,36 +479,6 @@ function hoverStateExpression(): string {
})()`;
}
async function wait(ms: number, signal?: AbortSignal): Promise<void> {
throwIfAborted(signal);
await new Promise<void>((resolve, reject) => {
const timer = setTimeout(() => {
signal?.removeEventListener("abort", onAbort);
resolve();
}, ms);
const onAbort = () => {
clearTimeout(timer);
signal?.removeEventListener("abort", onAbort);
reject(captureAbortError());
};
signal?.addEventListener("abort", onAbort, { once: true });
});
}
async function clearHover(cdp: CdpRunner, tabId: number): Promise<void> {
await cdp
.send(tabId, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: -10,
y: -10,
})
.catch(() =>
cdp.send(tabId, "Input.dispatchMouseEvent", { type: "mouseMoved", x: 0, y: 0 }).catch(() => {
// best effort
}),
);
}
function capturedText(node: CapturedNode): string | undefined {
const value =
node.attrs["aria-label"] ?? node.attrs.title ?? node.attrs.alt ?? node.textContent ?? "";
@@ -669,7 +658,7 @@ async function probeHoverSurfaces(
try {
await clearHover(cdp, tabId);
throwIfAborted(options.signal);
await wait(HOVER_SETTLE_MS, options.signal);
await waitForHover(HOVER_SETTLE_MS, options.signal);
const baselineReply = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
expression: hoverStateExpression(),
returnByValue: true,
@@ -684,7 +673,7 @@ async function probeHoverSurfaces(
y: candidate.y,
});
throwIfAborted(options.signal);
await wait(HOVER_SETTLE_MS, options.signal);
await waitForHover(HOVER_SETTLE_MS, options.signal);
const collected = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
expression: hoverStateExpression(),
returnByValue: true,
@@ -817,6 +806,10 @@ function parseDocumentNodes(
const posCol = STYLE_COL.position;
const peCol = STYLE_COL["pointer-events"];
const cursorCol = STYLE_COL.cursor;
const visibilityCol = STYLE_COL.visibility;
const opacityCol = STYLE_COL.opacity;
const overflowXCol = STYLE_COL["overflow-x"];
const overflowYCol = STYLE_COL["overflow-y"];
const inputValues = sparseIndexMap(dn.inputValue);
const textValues = sparseIndexMap(dn.textValue);
const checkedInputs = new Set(dn.inputChecked?.index ?? []);
@@ -842,6 +835,7 @@ function parseDocumentNodes(
// Build CapturedNodes.
const nodes: CapturedNode[] = [];
const visuallySuppressedByNodeIndex = new Array<boolean>(count).fill(false);
for (let n = 0; n < count; n++) {
if (excluded[n]) continue;
const backendNodeId = dn.backendNodeId[n];
@@ -861,6 +855,11 @@ function parseDocumentNodes(
let position = "static";
let pointerEvents = "auto";
let cursor = "auto";
let overflowX = "visible";
let overflowY = "visible";
let rendered = false;
let visuallySuppressed =
parentIdx >= 0 ? visuallySuppressedByNodeIndex[parentIdx] === true : false;
const li = layoutByNode.get(n);
if (li !== undefined) {
const b = dl?.bounds?.[li];
@@ -881,7 +880,21 @@ function parseDocumentNodes(
position = str(strings, styleRow[posCol]) || "static";
pointerEvents = str(strings, styleRow[peCol]) || "auto";
cursor = str(strings, styleRow[cursorCol]) || "auto";
const visibility = str(strings, styleRow[visibilityCol]) || "visible";
const opacity = str(strings, styleRow[opacityCol]) || "1";
overflowX = str(strings, styleRow[overflowXCol]) || "visible";
overflowY = str(strings, styleRow[overflowYCol]) || "visible";
visuallySuppressed ||=
visibility === "hidden" ||
visibility === "collapse" ||
(Number.parseFloat(opacity) || 0) <= 0;
rendered =
localRect !== null &&
visibility !== "hidden" &&
visibility !== "collapse" &&
(Number.parseFloat(opacity) || 0) > 0;
}
visuallySuppressedByNodeIndex[n] = visuallySuppressed;
// Skip non-element nodes (#text, #cdata-section, etc.) — they carry no
// geometry and are never queried by callers.
@@ -916,6 +929,10 @@ function parseDocumentNodes(
position,
pointerEvents,
cursor,
overflowX,
overflowY,
visuallySuppressed,
rendered,
textContent,
...(formValue !== undefined ? { formValue } : {}),
...(tag === "input" || tag === "textarea"
@@ -1020,7 +1037,13 @@ export async function captureViewModel(
options: CaptureViewModelOptions = {},
): Promise<CapturedViewModel> {
throwIfAborted(options.signal);
const metrics = await cdp.send<LayoutMetricsReply>(tabId, "Page.getLayoutMetrics", {});
let metrics: LayoutMetricsReply = {};
try {
metrics = await cdp.send<LayoutMetricsReply>(tabId, "Page.getLayoutMetrics", {});
} catch (error) {
if (isAbortError(error)) throw error;
console.debug("[bsk capture] layout metrics unavailable", error);
}
throwIfAborted(options.signal);
const dpr = devicePixelRatio(metrics);
const vpSrc = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
+24 -22
View File
@@ -33,25 +33,19 @@ async function discoverFrameGraph(cdp: CdpRunner, tabId: number): Promise<CdpFra
function transformFrameNodes(
nodes: CapturedNode[],
projection: GeometryProjection,
projection: GeometryProjection | null,
): CapturedNode[] {
return nodes.map((node) => ({
...node,
rect: (() => {
const bounds = projectRectToViewport(node.rect, projection);
return bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
})(),
rect: projection
? (() => {
const bounds = projectRectToViewport(node.rect, projection);
return bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
})()
: null,
}));
}
function frameOwnerNode(captured: CapturedViewModel, frame: CdpFrame): CapturedNode | undefined {
if (frame.ownerBackendNodeId === undefined) return undefined;
const parentNodes = frame.parentFrameId
? captured.frameNodes?.get(frame.parentFrameId)
: captured.nodes;
return parentNodes?.find((node) => node.backendNodeId === frame.ownerBackendNodeId);
}
async function captureMissingFrameDocuments(
cdp: CdpRunner,
tabId: number,
@@ -65,14 +59,20 @@ async function captureMissingFrameDocuments(
for (const frame of graph.frames) {
if (!frame.target.sessionId || captured.frameNodes.has(frame.frameId)) continue;
const owner = frameOwnerNode(captured, frame);
if (!owner?.rect || frame.ownerBackendNodeId === undefined) continue;
try {
const child = await captureViewModel(cdpRunnerForTarget(cdp, frame.target), tabId, {
signal,
});
const projection = await resolveFrameProjection(cdp, graph, frame.frameId);
if (!projection) continue;
let projection: GeometryProjection | null = null;
try {
projection = await resolveFrameProjection(cdp, graph, frame.frameId);
} catch (err) {
if (isAbortError(err)) throw err;
console.debug("[bsk observation] child frame geometry projection failed", {
frameId: frame.frameId,
err,
});
}
const rootFrameId = child.rootFrameId ?? frame.frameId;
const childFrames = child.frameNodes ?? new Map<string, CapturedNode[]>();
if (!childFrames.has(rootFrameId)) childFrames.set(rootFrameId, child.nodes);
@@ -85,11 +85,13 @@ async function captureMissingFrameDocuments(
for (const [childFrameId, nodes] of childFrames) {
captured.frameNodes.set(childFrameId, transformFrameNodes(nodes, projection));
}
captured.iframeNodes.set(
frame.ownerBackendNodeId,
captured.frameNodes.get(frame.frameId) ?? [],
);
captured.frameOwnerBackendNodeIds.set(frame.frameId, frame.ownerBackendNodeId);
if (frame.ownerBackendNodeId !== undefined) {
captured.iframeNodes.set(
frame.ownerBackendNodeId,
captured.frameNodes.get(frame.frameId) ?? [],
);
captured.frameOwnerBackendNodeIds.set(frame.frameId, frame.ownerBackendNodeId);
}
if (frame.parentFrameId) captured.frameParentIds.set(frame.frameId, frame.parentFrameId);
for (const [childFrameId, ownerBackendNodeId] of child.frameOwnerBackendNodeIds ?? []) {
captured.frameOwnerBackendNodeIds.set(childFrameId, ownerBackendNodeId);
@@ -0,0 +1,37 @@
import type { CdpRunner } from "../shared";
function abortError(): Error {
const error = new Error("hover perception aborted");
error.name = "AbortError";
return error;
}
export async function waitForHover(ms: number, signal?: AbortSignal): Promise<void> {
if (signal?.aborted) throw abortError();
await new Promise<void>((resolve, reject) => {
const timer = setTimeout(() => {
signal?.removeEventListener("abort", onAbort);
resolve();
}, ms);
const onAbort = () => {
clearTimeout(timer);
signal?.removeEventListener("abort", onAbort);
reject(abortError());
};
signal?.addEventListener("abort", onAbort, { once: true });
});
}
export async function clearHover(cdp: CdpRunner, tabId: number): Promise<void> {
await cdp
.send(tabId, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: -10,
y: -10,
})
.catch(() =>
cdp.send(tabId, "Input.dispatchMouseEvent", { type: "mouseMoved", x: 0, y: 0 }).catch(() => {
// Best effort cleanup.
}),
);
}
@@ -0,0 +1,296 @@
import { isVomReferenceNode } from "@browser-skill/vom";
import { type CdpRunner, sendToCdpTarget } from "../shared";
import type { FrameDocument, FrameOwnedAxNode } from "./frame-document";
import { clearHover, waitForHover } from "./hover-perception";
import { stableIdentifierName } from "./semantic-graph/name-evidence";
import { frameBackendKey, type ResolvedSemanticGraph } from "./semantic-graph/types";
const MAX_TOOLTIP_CANDIDATES = 8;
const MAX_TOOLTIP_PROBE_MS = 2_400;
const TOOLTIP_SETTLE_MS = 250;
const CACHE_TTL_MS = 5 * 60_000;
const MAX_CACHE_ENTRIES = 500;
const FORM_CONTROL_TAGS = new Set(["input", "select", "textarea"]);
interface TooltipCacheEntry {
name: string;
expiresAt: number;
}
interface TooltipCandidate<T extends FrameOwnedAxNode> {
document: FrameDocument<T>;
backendNodeId: number;
x: number;
y: number;
stableIdentifier: boolean;
}
export interface TooltipNameProbeOptions {
signal?: AbortSignal;
hoverProbeBypassOverlay?: (tabId: number, enabled: boolean) => Promise<void>;
}
const tooltipCache = new Map<string, TooltipCacheEntry>();
function cacheKey<T extends FrameOwnedAxNode>(
document: FrameDocument<T>,
backendNodeId: number,
): string {
return `${document.target.tabId}\u0000${document.frameId}\u0000${document.url ?? ""}\u0000${backendNodeId}`;
}
function cachedName<T extends FrameOwnedAxNode>(
document: FrameDocument<T>,
backendNodeId: number,
): string | undefined {
const key = cacheKey(document, backendNodeId);
const entry = tooltipCache.get(key);
if (!entry) return undefined;
if (entry.expiresAt <= Date.now()) {
tooltipCache.delete(key);
return undefined;
}
return entry.name;
}
function storeName<T extends FrameOwnedAxNode>(
document: FrameDocument<T>,
backendNodeId: number,
name: string,
): void {
if (tooltipCache.size >= MAX_CACHE_ENTRIES) {
const oldest = tooltipCache.keys().next().value;
if (oldest !== undefined) tooltipCache.delete(oldest);
}
tooltipCache.set(cacheKey(document, backendNodeId), {
name,
expiresAt: Date.now() + CACHE_TTL_MS,
});
}
function tooltipCollectorFunction(): string {
return `function() {
const ownRoot = this && typeof this.getRootNode === "function" ? this.getRootNode() : null;
const roots = ownRoot && ownRoot !== document ? [ownRoot, document] : [document];
const items = [];
const seen = new Set();
for (const root of roots) {
for (const el of Array.from(root.querySelectorAll("[role='tooltip']"))) {
const style = getComputedStyle(el);
const rect = el.getBoundingClientRect();
if (rect.width <= 0 || rect.height <= 0) continue;
if (style.display === "none" || style.visibility === "hidden" || style.opacity === "0") continue;
const text = String(el.getAttribute("aria-label") || el.getAttribute("title") || el.textContent || "")
.replace(/\\s+/g, " ")
.trim();
if (!text || text.length > 160 || seen.has(text)) continue;
seen.add(text);
items.push(text);
}
}
return items.slice(0, 20);
}`;
}
function cleanTooltipDiff(before: string[], after: string[]): string | undefined {
const existing = new Set(before.map((value) => value.toLowerCase()));
const added = [...new Set(after.map((value) => value.replace(/\s+/g, " ").trim()))].filter(
(value) => value && !existing.has(value.toLowerCase()),
);
return added.length === 1 ? added[0] : undefined;
}
function candidates<T extends FrameOwnedAxNode>(
documents: FrameDocument<T>[],
graph: ResolvedSemanticGraph,
): TooltipCandidate<T>[] {
const documentByFrame = new Map(documents.map((document) => [document.frameId, document]));
const byFrame = new Map<string, TooltipCandidate<T>[]>();
for (const node of graph.nodes.values()) {
if (
node.vom.name ||
FORM_CONTROL_TAGS.has(node.dom?.tag.toLowerCase() ?? "") ||
!node.referenceable ||
node.backendNodeId === undefined ||
!isVomReferenceNode({
...node.vom,
id: 0,
parentId: null,
backendNodeId: node.backendNodeId,
frameId: node.frameId,
referenceable: true,
})
) {
continue;
}
const document = documentByFrame.get(node.frameId);
const rect = node.dom?.rect;
if (!document || !rect || rect.w <= 0 || rect.h <= 0) continue;
if (
rect.x + rect.w <= 0 ||
rect.y + rect.h <= 0 ||
rect.x >= graph.viewport.width ||
rect.y >= graph.viewport.height
) {
continue;
}
if (
node.vom.disabled ||
node.vom.inert ||
node.vom.pointerEvents === "none" ||
node.vom.sensitive
) {
continue;
}
const frameCandidates = byFrame.get(node.frameId) ?? [];
frameCandidates.push({
document,
backendNodeId: node.backendNodeId,
x: (Math.max(0, rect.x) + Math.min(graph.viewport.width, rect.x + rect.w)) / 2,
y: (Math.max(0, rect.y) + Math.min(graph.viewport.height, rect.y + rect.h)) / 2,
stableIdentifier: stableIdentifierName(node.dom?.attrs ?? {}) !== undefined,
});
byFrame.set(node.frameId, frameCandidates);
}
const out: TooltipCandidate<T>[] = [];
for (const stableIdentifier of [true, false]) {
const queues = documents.map((document) =>
(byFrame.get(document.frameId) ?? []).filter(
(candidate) => candidate.stableIdentifier === stableIdentifier,
),
);
for (let index = 0; queues.some((queue) => index < queue.length); index += 1) {
for (const queue of queues) {
const candidate = queue[index];
if (candidate) out.push(candidate);
}
}
}
return out;
}
async function executionContextId<T extends FrameOwnedAxNode>(
cdp: CdpRunner,
document: FrameDocument<T>,
): Promise<number | undefined> {
const result = await sendToCdpTarget<{ executionContextId?: number }>(
cdp,
document.target,
"Page.createIsolatedWorld",
{
frameId: document.frameId,
worldName: "bsk-vom-tooltip",
grantUniveralAccess: false,
},
);
return result.executionContextId;
}
async function resolvedObjectId<T extends FrameOwnedAxNode>(
cdp: CdpRunner,
document: FrameDocument<T>,
contextId: number,
backendNodeId: number,
): Promise<string | undefined> {
const result = await sendToCdpTarget<{
object?: { objectId?: string };
}>(cdp, document.target, "DOM.resolveNode", {
backendNodeId,
executionContextId: contextId,
});
return result.object?.objectId;
}
async function tooltipTexts<T extends FrameOwnedAxNode>(
cdp: CdpRunner,
document: FrameDocument<T>,
objectId: string,
): Promise<string[]> {
const result = await sendToCdpTarget<{
result?: { value?: string[] };
}>(cdp, document.target, "Runtime.callFunctionOn", {
functionDeclaration: tooltipCollectorFunction(),
objectId,
returnByValue: true,
});
return result.result?.value ?? [];
}
async function releaseObject<T extends FrameOwnedAxNode>(
cdp: CdpRunner,
document: FrameDocument<T>,
objectId: string,
): Promise<void> {
await sendToCdpTarget(cdp, document.target, "Runtime.releaseObject", { objectId }).catch(
() => undefined,
);
}
export async function probeTooltipNames<T extends FrameOwnedAxNode>(
cdp: CdpRunner,
tabId: number,
documents: FrameDocument<T>[],
graph: ResolvedSemanticGraph,
options: TooltipNameProbeOptions = {},
): Promise<Map<string, string>> {
const names = new Map<string, string>();
const pending: TooltipCandidate<T>[] = [];
for (const candidate of candidates(documents, graph)) {
const cached = cachedName(candidate.document, candidate.backendNodeId);
if (cached) {
names.set(frameBackendKey(candidate.document.frameId, candidate.backendNodeId), cached);
} else if (pending.length < MAX_TOOLTIP_CANDIDATES) {
pending.push(candidate);
}
}
if (pending.length === 0) return names;
const started = Date.now();
const contexts = new Map<string, number>();
await options.hoverProbeBypassOverlay?.(tabId, true).catch(() => undefined);
try {
for (const candidate of pending) {
if (options.signal?.aborted) throw new DOMException("observation aborted", "AbortError");
if (Date.now() - started >= MAX_TOOLTIP_PROBE_MS) break;
let objectId: string | undefined;
try {
let contextId = contexts.get(candidate.document.frameId);
if (contextId === undefined) {
contextId = await executionContextId(cdp, candidate.document);
if (contextId === undefined) continue;
contexts.set(candidate.document.frameId, contextId);
}
objectId = await resolvedObjectId(
cdp,
candidate.document,
contextId,
candidate.backendNodeId,
);
if (!objectId) continue;
await clearHover(cdp, tabId);
const before = await tooltipTexts(cdp, candidate.document, objectId);
await cdp.send(tabId, "Input.dispatchMouseEvent", {
type: "mouseMoved",
x: candidate.x,
y: candidate.y,
});
await waitForHover(TOOLTIP_SETTLE_MS, options.signal);
const after = await tooltipTexts(cdp, candidate.document, objectId);
const name = cleanTooltipDiff(before, after);
if (!name) continue;
names.set(frameBackendKey(candidate.document.frameId, candidate.backendNodeId), name);
storeName(candidate.document, candidate.backendNodeId, name);
} catch (error) {
if (error instanceof Error && error.name === "AbortError") throw error;
} finally {
if (objectId) await releaseObject(cdp, candidate.document, objectId);
await clearHover(cdp, tabId);
}
}
} finally {
await clearHover(cdp, tabId);
await options.hoverProbeBypassOverlay?.(tabId, false).catch(() => undefined);
}
return names;
}
@@ -0,0 +1,65 @@
import type { Rect } from "@browser-skill/vom";
import type { RenderedSurface, RenderedSurfaceGroup } from "./types";
const STACK_IOU_RATIO = 0.9;
const STACK_SIZE_RATIO = 0.9;
function area(rect: Rect): number {
return Math.max(0, rect.w) * Math.max(0, rect.h);
}
function intersectionArea(a: Rect, b: Rect): number {
const width = Math.max(0, Math.min(a.x + a.w, b.x + b.w) - Math.max(a.x, b.x));
const height = Math.max(0, Math.min(a.y + a.h, b.y + b.h) - Math.max(a.y, b.y));
return width * height;
}
function sameVisualStack(a: RenderedSurface, b: RenderedSurface): boolean {
if (a.frameId !== b.frameId) return false;
if (a.parentBackendNodeId !== b.parentBackendNodeId) return false;
const aArea = area(a.visibleRect);
const bArea = area(b.visibleRect);
const intersection = intersectionArea(a.visibleRect, b.visibleRect);
const union = aArea + bArea - intersection;
const widthRatio =
Math.min(a.visibleRect.w, b.visibleRect.w) / Math.max(a.visibleRect.w, b.visibleRect.w);
const heightRatio =
Math.min(a.visibleRect.h, b.visibleRect.h) / Math.max(a.visibleRect.h, b.visibleRect.h);
return (
union > 0 &&
intersection / union >= STACK_IOU_RATIO &&
widthRatio >= STACK_SIZE_RATIO &&
heightRatio >= STACK_SIZE_RATIO
);
}
function toGroup(members: RenderedSurface[]): RenderedSurfaceGroup {
const representative = [...members].sort(
(a, b) => area(b.visibleRect) - area(a.visibleRect) || b.paintOrder - a.paintOrder,
)[0];
return {
frameId: representative.frameId,
members,
representative,
label: members.map((surface) => surface.label).find((label) => label !== undefined),
};
}
export function clusterRenderedSurfaces(surfaces: RenderedSurface[]): RenderedSurfaceGroup[] {
const groups: RenderedSurface[][] = [];
for (const surface of surfaces) {
const matching = groups.find((group) =>
group.some((member) => sameVisualStack(member, surface)),
);
if (matching) matching.push(surface);
else groups.push([surface]);
}
return groups
.map(toGroup)
.sort(
(a, b) =>
a.frameId.localeCompare(b.frameId) ||
a.representative.visibleRect.y - b.representative.visibleRect.y ||
a.representative.visibleRect.x - b.representative.visibleRect.x,
);
}
@@ -0,0 +1,113 @@
import type { Rect, Viewport } from "@browser-skill/vom";
import type { CapturedNode } from "../capture";
import type { CapturedFrameDocument } from "../frame-capture";
import type { SemanticAxNode } from "../semantic-graph";
import type { RenderedSurface } from "./types";
function clean(value: string | undefined): string | undefined {
const normalized = value?.replace(/\s+/g, " ").trim();
return normalized || undefined;
}
function intersectViewport(rect: Rect, viewport: Viewport): Rect | null {
return intersectRect(rect, { x: 0, y: 0, w: viewport.width, h: viewport.height });
}
function intersectRect(a: Rect, b: Rect): Rect | null {
const x = Math.max(a.x, b.x);
const y = Math.max(a.y, b.y);
const right = Math.min(a.x + a.w, b.x + b.w);
const bottom = Math.min(a.y + a.h, b.y + b.h);
if (right <= x || bottom <= y) return null;
return { x, y, w: right - x, h: bottom - y };
}
const CLIPPING_OVERFLOW = new Set(["auto", "clip", "hidden", "scroll"]);
function clipToOverflowAncestors(
node: CapturedNode,
rect: Rect,
nodesByBackend: ReadonlyMap<number, CapturedNode>,
): Rect | null {
let clipped: Rect | null = rect;
let parentBackendNodeId = node.parentBackendNodeId;
let guard = 0;
while (clipped && parentBackendNodeId !== null && guard <= nodesByBackend.size) {
const parent = nodesByBackend.get(parentBackendNodeId);
if (!parent) break;
if (parent.rect) {
const clipX = CLIPPING_OVERFLOW.has(parent.overflowX ?? "visible");
const clipY = CLIPPING_OVERFLOW.has(parent.overflowY ?? "visible");
if (clipX || clipY) {
const clipRect = {
x: clipX ? parent.rect.x : clipped.x,
y: clipY ? parent.rect.y : clipped.y,
w: clipX ? parent.rect.w : clipped.w,
h: clipY ? parent.rect.h : clipped.h,
};
clipped = intersectRect(clipped, clipRect);
}
}
parentBackendNodeId = parent.parentBackendNodeId;
guard += 1;
}
return clipped;
}
function excludedByDomPolicy(
node: CapturedNode,
nodesByBackend: Map<number, CapturedNode>,
excludedBackendNodeIds: ReadonlySet<number>,
): boolean {
let current: CapturedNode | undefined = node;
let guard = 0;
while (current && guard <= nodesByBackend.size) {
if (excludedBackendNodeIds.has(current.backendNodeId)) return true;
if (current.visuallySuppressed === true) return true;
const attrs = current.attrs;
if (
Object.prototype.hasOwnProperty.call(attrs, "hidden") ||
Object.prototype.hasOwnProperty.call(attrs, "inert") ||
(attrs["aria-hidden"] ?? "").toLowerCase() === "true"
) {
return true;
}
current =
current.parentBackendNodeId === null
? undefined
: nodesByBackend.get(current.parentBackendNodeId);
guard += 1;
}
return false;
}
export function discoverRenderedSurfaces(
documents: CapturedFrameDocument<SemanticAxNode>[],
viewport: Viewport,
excludedBackendNodeIds: ReadonlySet<number> = new Set(),
): RenderedSurface[] {
const surfaces: RenderedSurface[] = [];
for (const document of documents) {
const nodesByBackend = new Map(document.domNodes.map((node) => [node.backendNodeId, node]));
for (const node of document.domNodes) {
if (node.tag.toLowerCase() !== "canvas" || node.rendered !== true || !node.rect) continue;
if (excludedByDomPolicy(node, nodesByBackend, excludedBackendNodeIds)) continue;
const viewportRect = intersectViewport(node.rect, viewport);
const visibleRect = viewportRect
? clipToOverflowAncestors(node, viewportRect, nodesByBackend)
: null;
if (!visibleRect) continue;
const label = clean(node.attrs["aria-label"] ?? node.attrs.title);
surfaces.push({
renderingKind: "canvas",
frameId: document.frameId,
backendNodeId: node.backendNodeId,
parentBackendNodeId: node.parentBackendNodeId,
visibleRect,
paintOrder: node.paintOrder,
...(label ? { label } : {}),
});
}
}
return surfaces;
}
@@ -0,0 +1,4 @@
export { clusterRenderedSurfaces } from "./cluster";
export { discoverRenderedSurfaces } from "./discovery";
export { projectRenderedSurfaces } from "./project";
export type { RenderedSurface, RenderedSurfaceGroup } from "./types";
@@ -0,0 +1,100 @@
import type { VomScene, VomVisualSurface } from "@browser-skill/vom";
import type { CapturedFrameDocument } from "../frame-capture";
import type { SemanticAxNode } from "../semantic-graph";
import type { RenderedSurfaceGroup } from "./types";
function frameBackendKey(frameId: string, backendNodeId: number): string {
return `${frameId}\u0000${backendNodeId}`;
}
interface ProjectionIndex {
sceneByBackend: ReadonlyMap<string, number>;
documentByFrame: ReadonlyMap<string, CapturedFrameDocument<SemanticAxNode>>;
domByFrame: ReadonlyMap<
string,
ReadonlyMap<number, CapturedFrameDocument<SemanticAxNode>["domNodes"][number]>
>;
rootSceneIdByFrame: ReadonlyMap<string, number>;
}
function nearestSceneParent(index: ProjectionIndex, group: RenderedSurfaceGroup): number | null {
const document = index.documentByFrame.get(group.frameId);
const domByBackend = index.domByFrame.get(group.frameId) ?? new Map();
let parentBackendNodeId = group.representative.parentBackendNodeId;
let guard = 0;
while (parentBackendNodeId !== null && guard <= domByBackend.size) {
const sceneId = index.sceneByBackend.get(frameBackendKey(group.frameId, parentBackendNodeId));
if (sceneId !== undefined) return sceneId;
parentBackendNodeId = domByBackend.get(parentBackendNodeId)?.parentBackendNodeId ?? null;
guard += 1;
}
if (document?.parentFrameId && document.ownerBackendNodeId !== undefined) {
const owner = index.sceneByBackend.get(
frameBackendKey(document.parentFrameId, document.ownerBackendNodeId),
);
if (owner !== undefined) return owner;
}
return index.rootSceneIdByFrame.get(group.frameId) ?? null;
}
function buildProjectionIndex(
scene: VomScene,
documents: CapturedFrameDocument<SemanticAxNode>[],
): ProjectionIndex {
const rootSceneIdByFrame = new Map<string, number>();
for (const node of scene.nodes) {
if (
node.frameId &&
!rootSceneIdByFrame.has(node.frameId) &&
["rootwebarea", "webarea"].includes(node.role?.toLowerCase() ?? "")
) {
rootSceneIdByFrame.set(node.frameId, node.id);
}
}
return {
sceneByBackend: new Map(
scene.nodes.flatMap((node) =>
node.backendNodeId === undefined
? []
: [[frameBackendKey(node.frameId ?? "", node.backendNodeId), node.id] as const],
),
),
documentByFrame: new Map(documents.map((document) => [document.frameId, document])),
domByFrame: new Map(
documents.map((document) => [
document.frameId,
new Map(document.domNodes.map((node) => [node.backendNodeId, node])),
]),
),
rootSceneIdByFrame,
};
}
export function projectRenderedSurfaces(
scene: VomScene,
documents: CapturedFrameDocument<SemanticAxNode>[],
groups: RenderedSurfaceGroup[],
): VomScene {
const index = buildProjectionIndex(scene, documents);
const visualSurfaces: VomVisualSurface[] = [];
for (const group of groups) {
const parentId = nearestSceneParent(index, group);
visualSurfaces.push({
parentId,
backendNodeId: group.representative.backendNodeId,
frameId: group.frameId,
renderingKind: "canvas",
visibleRect: group.representative.visibleRect,
...(group.label ? { label: group.label } : {}),
memberCount: group.members.length,
});
}
return {
...scene,
...(visualSurfaces.length > 0 ? { visualSurfaces } : {}),
};
}
@@ -0,0 +1,18 @@
import type { Rect } from "@browser-skill/vom";
export interface RenderedSurface {
renderingKind: "canvas";
frameId: string;
backendNodeId: number;
parentBackendNodeId: number | null;
visibleRect: Rect;
paintOrder: number;
label?: string;
}
export interface RenderedSurfaceGroup {
frameId: string;
members: RenderedSurface[];
representative: RenderedSurface;
label?: string;
}
@@ -0,0 +1,154 @@
import type { Viewport } from "@browser-skill/vom";
import type { FrameDocument } from "../frame-document";
import {
frameAxKey,
frameBackendKey,
type SemanticAxNode,
type SemanticFrame,
type SemanticGraph,
type SemanticGraphNode,
type SemanticNodeId,
} from "./types";
export interface BuildSemanticGraphInput {
documents: FrameDocument<SemanticAxNode>[];
viewport: Viewport;
rootFrameId?: string;
excludedBackendNodeIds?: ReadonlySet<number>;
}
function domNodeId(frameId: string, backendNodeId: number): SemanticNodeId {
return JSON.stringify([frameId, "dom", backendNodeId]);
}
function axNodeId(frameId: string, nodeId: string): SemanticNodeId {
return JSON.stringify([frameId, "ax", nodeId]);
}
export function buildSemanticGraph(input: BuildSemanticGraphInput): SemanticGraph {
const rootFrameId =
input.rootFrameId ??
input.documents.find((document) => !document.parentFrameId)?.frameId ??
input.documents[0]?.frameId ??
"root";
const frames = new Map<string, SemanticFrame>();
const nodes = new Map<SemanticNodeId, SemanticGraphNode>();
const nodeIdsByFrame = new Map<string, SemanticNodeId[]>();
const nodeByFrameBackend = new Map<string, SemanticNodeId>();
const nodeByFrameAx = new Map<string, SemanticNodeId>();
for (const [frameOrder, document] of input.documents.entries()) {
frames.set(document.frameId, {
frameId: document.frameId,
...(document.parentFrameId ? { parentFrameId: document.parentFrameId } : {}),
...(document.ownerBackendNodeId !== undefined
? { ownerBackendNodeId: document.ownerBackendNodeId }
: {}),
contextScopeId: document.contextScopeId,
target: document.target,
...(document.url ? { url: document.url } : {}),
order: frameOrder,
});
const frameNodeIds: SemanticNodeId[] = [];
nodeIdsByFrame.set(document.frameId, frameNodeIds);
for (const [index, dom] of document.domNodes.entries()) {
const id = domNodeId(document.frameId, dom.backendNodeId);
const node: SemanticGraphNode = {
id,
frameId: document.frameId,
backendNodeId: dom.backendNodeId,
dom,
sourceOrder: index,
excluded:
document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(dom.backendNodeId) === true,
};
nodes.set(id, node);
frameNodeIds.push(id);
nodeByFrameBackend.set(frameBackendKey(document.frameId, dom.backendNodeId), id);
}
for (const [index, ax] of document.axNodes.entries()) {
const joinedId =
typeof ax.backendDOMNodeId === "number"
? nodeByFrameBackend.get(frameBackendKey(document.frameId, ax.backendDOMNodeId))
: undefined;
const id = joinedId ?? axNodeId(document.frameId, ax.nodeId);
const existing = nodes.get(id);
if (existing) {
existing.ax = ax;
existing.axNodeId = ax.nodeId;
} else {
nodes.set(id, {
id,
frameId: document.frameId,
...(typeof ax.backendDOMNodeId === "number"
? { backendNodeId: ax.backendDOMNodeId }
: {}),
axNodeId: ax.nodeId,
ax,
sourceOrder: document.domNodes.length + index,
excluded:
document.frameId === rootFrameId &&
typeof ax.backendDOMNodeId === "number" &&
input.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true,
});
frameNodeIds.push(id);
}
nodeByFrameAx.set(frameAxKey(document.frameId, ax.nodeId), id);
}
}
for (const document of input.documents) {
for (const dom of document.domNodes) {
const id = nodeByFrameBackend.get(frameBackendKey(document.frameId, dom.backendNodeId));
const node = id ? nodes.get(id) : undefined;
if (!node || dom.parentBackendNodeId === null) continue;
node.domParentId = nodeByFrameBackend.get(
frameBackendKey(document.frameId, dom.parentBackendNodeId),
);
}
for (const ax of document.axNodes) {
const id = nodeByFrameAx.get(frameAxKey(document.frameId, ax.nodeId));
const node = id ? nodes.get(id) : undefined;
if (!node || !ax.parentId) continue;
node.axParentId = nodeByFrameAx.get(frameAxKey(document.frameId, ax.parentId));
}
}
const axChildren = new Map<SemanticNodeId, SemanticNodeId[]>();
const excludedQueue: SemanticNodeId[] = [];
for (const node of nodes.values()) {
if (node.axParentId) {
const children = axChildren.get(node.axParentId) ?? [];
children.push(node.id);
axChildren.set(node.axParentId, children);
}
if (node.excluded) excludedQueue.push(node.id);
}
for (let index = 0; index < excludedQueue.length; index += 1) {
for (const childId of axChildren.get(excludedQueue[index]) ?? []) {
const child = nodes.get(childId);
if (!child || child.excluded) continue;
child.excluded = true;
excludedQueue.push(childId);
}
}
for (const frame of frames.values()) {
if (!frame.parentFrameId || frame.ownerBackendNodeId === undefined) continue;
frame.ownerNodeId = nodeByFrameBackend.get(
frameBackendKey(frame.parentFrameId, frame.ownerBackendNodeId),
);
}
return {
viewport: input.viewport,
rootFrameId,
frames,
nodes,
nodeIdsByFrame,
nodeByFrameBackend,
};
}
@@ -0,0 +1,59 @@
import type { Viewport, VomScene } from "@browser-skill/vom";
import type { FrameDocument } from "../frame-document";
import { buildSemanticGraph as buildGraph } from "./build";
import { projectSemanticGraph as projectGraph } from "./project";
import { resolveSemanticGraph as resolveGraph } from "./resolve";
import { normalizeSemanticStructure as normalizeStructure } from "./structure";
import type {
ResolvedSemanticGraph,
SemanticAxNode,
SemanticGraph,
StructuredSemanticGraph,
} from "./types";
export type { SemanticAxNode } from "./types";
export interface SemanticVomInput {
documents: FrameDocument<SemanticAxNode>[];
viewport: Viewport;
rootFrameId?: string;
excludedBackendNodeIds?: ReadonlySet<number>;
}
export function buildSemanticGraph(input: SemanticVomInput): SemanticGraph {
return buildGraph(input);
}
export function resolveSemanticGraph(
graph: SemanticGraph,
options: {
supplementalNames?: ReadonlyMap<string, string>;
identifierFallback?: boolean;
} = {},
): ResolvedSemanticGraph {
return resolveGraph(graph, options);
}
export function normalizeSemanticStructure(graph: ResolvedSemanticGraph): StructuredSemanticGraph {
return normalizeStructure(graph);
}
export function projectSemanticGraph(graph: StructuredSemanticGraph): VomScene {
return projectGraph(graph);
}
export function buildSemanticVomScene(
input: SemanticVomInput & {
supplementalNames?: ReadonlyMap<string, string>;
identifierFallback?: boolean;
},
): VomScene {
return projectSemanticGraph(
normalizeSemanticStructure(
resolveSemanticGraph(buildSemanticGraph(input), {
supplementalNames: input.supplementalNames,
identifierFallback: input.identifierFallback,
}),
),
);
}
@@ -0,0 +1,34 @@
const IDENTIFIER_ATTRS = ["data-testid", "data-test-id", "id"] as const;
const GENERIC_TOKENS = new Set(["btn", "button", "control", "icon", "item", "test", "tool"]);
const GENERATED_PREFIXES = new Set(["ember", "headlessui", "mui", "radix", "react", "rc"]);
function identifierTokens(value: string): string[] {
return value
.replace(/([a-z0-9])([A-Z])/g, "$1 $2")
.split(/[^a-zA-Z0-9]+/)
.map((token) => token.toLowerCase())
.filter(Boolean);
}
function readableIdentifier(value: string | undefined): string | undefined {
const raw = value?.trim();
if (!raw || raw.length < 3 || raw.length > 80) return undefined;
if (/^[a-f0-9]{8,}$/i.test(raw)) return undefined;
const tokens = identifierTokens(raw);
if (GENERATED_PREFIXES.has(tokens[0])) return undefined;
while (tokens.length > 1 && GENERIC_TOKENS.has(tokens[0])) tokens.shift();
while (tokens.length > 1 && GENERIC_TOKENS.has(tokens[tokens.length - 1])) tokens.pop();
if (tokens.length === 0 || !tokens.some((token) => /[a-z]{3,}/.test(token))) return undefined;
return tokens
.map((token, index) => (index === 0 ? `${token[0].toUpperCase()}${token.slice(1)}` : token))
.join(" ");
}
export function stableIdentifierName(attrs: Readonly<Record<string, string>>): string | undefined {
for (const name of IDENTIFIER_ATTRS) {
const label = readableIdentifier(attrs[name]);
if (label) return label;
}
return undefined;
}
@@ -0,0 +1,85 @@
import type { VomNode, VomScene } from "@browser-skill/vom";
import type { SemanticNodeId, StructuredSemanticGraph, StructuredSemanticNode } from "./types";
function retained(node: StructuredSemanticNode): boolean {
return node.structure.kind === "keep" || node.structure.kind === "inferred-group";
}
function connectedFrameIds(graph: StructuredSemanticGraph): Set<string> {
const connected = new Set<string>([graph.rootFrameId]);
const childrenByParent = new Map<string, string[]>();
for (const frame of graph.frames.values()) {
if (!frame.parentFrameId) continue;
const children = childrenByParent.get(frame.parentFrameId) ?? [];
children.push(frame.frameId);
childrenByParent.set(frame.parentFrameId, children);
}
const queue = [graph.rootFrameId];
for (let index = 0; index < queue.length; index += 1) {
for (const frameId of childrenByParent.get(queue[index]) ?? []) {
if (connected.has(frameId)) continue;
const frame = graph.frames.get(frameId);
if (!frame?.ownerNodeId) continue;
const owner = graph.nodes.get(frame.ownerNodeId);
if (!owner || !retained(owner)) continue;
connected.add(frame.frameId);
queue.push(frame.frameId);
}
}
return connected;
}
function domAncestors(
graph: StructuredSemanticGraph,
node: StructuredSemanticNode,
numericId: ReadonlyMap<SemanticNodeId, number>,
): number[] {
const ancestors: number[] = [];
const seen = new Set<SemanticNodeId>();
let current = node.domParentId;
while (current && !seen.has(current)) {
seen.add(current);
const id = numericId.get(current);
if (id !== undefined) ancestors.push(id);
current = graph.nodes.get(current)?.domParentId;
}
return ancestors;
}
export function projectSemanticGraph(graph: StructuredSemanticGraph): VomScene {
const connectedFrames = connectedFrameIds(graph);
const orderedNodes = [...graph.frames.values()]
.filter((frame) => connectedFrames.has(frame.frameId))
.sort((a, b) => a.order - b.order)
.flatMap((frame) =>
(graph.nodeIdsByFrame.get(frame.frameId) ?? [])
.map((id) => graph.nodes.get(id))
.filter((node): node is StructuredSemanticNode => node !== undefined && retained(node))
.sort((a, b) => a.sourceOrder - b.sourceOrder),
);
const numericId = new Map<SemanticNodeId, number>();
orderedNodes.forEach((node, index) => numericId.set(node.id, index + 1));
const nodes: VomNode[] = orderedNodes.map((node) => ({
...node.vom,
id: numericId.get(node.id) as number,
parentId: node.semanticParentId ? (numericId.get(node.semanticParentId) ?? null) : null,
...(node.backendNodeId !== undefined ? { backendNodeId: node.backendNodeId } : {}),
frameId: node.frameId,
contextScopeId: graph.frames.get(node.frameId)?.contextScopeId ?? node.frameId,
referenceable: node.referenceable,
...(node.dom
? {
domParentId:
node.domParentId === undefined ? null : (numericId.get(node.domParentId) ?? null),
domAncestorIds: domAncestors(graph, node, numericId),
}
: {}),
}));
return {
viewport: graph.viewport,
nodes,
rootFrameId: graph.rootFrameId,
};
}
@@ -0,0 +1,521 @@
import type { VomNode } from "@browser-skill/vom";
import { stableIdentifierName } from "./name-evidence";
import type {
ResolvedSemanticGraph,
ResolvedSemanticNode,
SemanticAxNode,
SemanticGraph,
SemanticGraphNode,
SemanticNodeId,
} from "./types";
import { frameBackendKey } from "./types";
const FORM_TAGS = new Set(["input", "textarea", "select"]);
const NATIVE_CONTROL_TAGS = new Set(["button", "input", "select", "textarea"]);
const TEXT_AX_ROLES = new Set(["statictext", "inlinetextbox", "labeltext", "text"]);
const INTERACTIVE_ROLES = new Set([
"button",
"checkbox",
"combobox",
"link",
"listbox",
"menuitem",
"menuitemcheckbox",
"menuitemradio",
"option",
"radio",
"searchbox",
"slider",
"spinbutton",
"switch",
"tab",
"textbox",
"treeitem",
]);
const SENSITIVE_INPUT_TYPES = new Set([
"password",
"credit-card",
"one-time-code",
"current-password",
"new-password",
]);
function clean(value: string | undefined): string | undefined {
const normalized = value?.replace(/\s+/g, " ").trim();
return normalized || undefined;
}
function axValue(field?: { value?: string | number | boolean }): string | undefined {
return field?.value === undefined ? undefined : clean(String(field.value));
}
function axProperty(node: SemanticAxNode | undefined, name: string): string | undefined {
return axValue(node?.properties?.find((property) => property.name === name)?.value);
}
function normalizeRole(value: string | undefined): string | undefined {
const role = clean(value)?.toLowerCase();
return role || undefined;
}
function nativeRole(tag: string, attrs: Record<string, string>): string | undefined {
if (tag === "button") return "button";
if (tag === "textarea") return "textbox";
if (tag === "select") return attrs.multiple === undefined ? "combobox" : "listbox";
if (tag === "a" && attrs.href) return "link";
if (tag === "iframe") return "Iframe";
if (tag === "dialog") return "dialog";
if (tag === "img") return "img";
if (tag === "table") return "table";
if (tag === "tr") return "row";
if (tag === "th") return "columnheader";
if (tag === "td") return "cell";
if (tag === "ul" || tag === "ol") return "list";
if (tag === "li") return "listitem";
if (/^h[1-6]$/.test(tag)) return "heading";
if (tag === "nav") return "navigation";
if (tag === "main") return "main";
if (tag === "form") return "form";
if (tag === "input") {
const type = (attrs.type ?? "text").toLowerCase();
if (type === "hidden") return undefined;
if (type === "checkbox") return "checkbox";
if (type === "radio") return "radio";
if (type === "range") return "slider";
if (type === "number") return "spinbutton";
if (type === "search") return "searchbox";
if (["button", "submit", "reset", "image"].includes(type)) return "button";
return "textbox";
}
return undefined;
}
function domRole(tag: string, attrs: Record<string, string>): string | undefined {
return normalizeRole(attrs.role) ?? nativeRole(tag, attrs);
}
function resolvedRole(node: SemanticGraphNode): {
value?: string;
source: ResolvedSemanticNode["roleSource"];
} {
const rawAxRole = clean(axValue(node.ax?.role));
const axRole = normalizeRole(rawAxRole);
const attrs = node.dom?.attrs ?? {};
const explicitDomRole = normalizeRole(attrs.role);
const nativeDomRole = nativeRole(node.dom?.tag.toLowerCase() ?? "", attrs);
const usableAxRole = node.ax?.ignored !== true;
if (usableAxRole && axRole && !["generic", "none", "presentation"].includes(axRole)) {
return { value: rawAxRole, source: "ax" };
}
if (explicitDomRole) return { value: explicitDomRole, source: "dom-explicit" };
if (nativeDomRole) return { value: nativeDomRole, source: "dom-native" };
if (rawAxRole) {
return { value: rawAxRole, source: usableAxRole ? "ax" : "ax-ignored" };
}
return { source: "none" };
}
function sensitive(node: SemanticGraphNode): boolean {
const attrs = node.dom?.attrs ?? {};
const type = (attrs.type ?? "").toLowerCase();
const autocomplete = (attrs.autocomplete ?? "").toLowerCase();
return (
type === "password" ||
autocomplete.startsWith("cc-") ||
SENSITIVE_INPUT_TYPES.has(autocomplete) ||
SENSITIVE_INPUT_TYPES.has(axProperty(node.ax, "inputType") ?? "")
);
}
function inputState(
node: SemanticGraphNode,
role: string | undefined,
value: string | undefined,
isSensitive: boolean,
): VomNode["inputState"] {
if (node.dom?.formState) return node.dom.formState;
const tag = node.dom?.tag.toLowerCase() ?? "";
if (!FORM_TAGS.has(tag) && !["textbox", "searchbox"].includes(role ?? "")) return undefined;
if (isSensitive) return value ? "filled" : "empty";
if (node.dom?.formValue !== undefined) {
if (node.dom.formValue === "") return "empty";
return node.dom.formValue === (node.dom.formDefaultValue ?? "") ? "default" : "filled";
}
return value ? "filled" : "empty";
}
function externalHrefHost(
href: string | undefined,
pageUrl: string | undefined,
): string | undefined {
if (!href || !pageUrl) return undefined;
try {
const page = new URL(pageUrl);
const target = new URL(href, page);
return target.origin === page.origin ? undefined : target.hostname;
} catch {
return undefined;
}
}
interface ResolveIndexes {
domChildren: Map<SemanticNodeId, SemanticNodeId[]>;
axChildren: Map<SemanticNodeId, SemanticNodeId[]>;
domIdIndex: Map<string, SemanticNodeId>;
labelForIndex: Map<string, SemanticNodeId[]>;
domText: (nodeId: SemanticNodeId) => string | undefined;
axText: (nodeId: SemanticNodeId) => string | undefined;
hasNativeDescendant: (nodeId: SemanticNodeId) => boolean;
}
function buildIndexes(graph: SemanticGraph): ResolveIndexes {
const domChildren = new Map<SemanticNodeId, SemanticNodeId[]>();
const axChildren = new Map<SemanticNodeId, SemanticNodeId[]>();
const domIdIndex = new Map<string, SemanticNodeId>();
const labelForIndex = new Map<string, SemanticNodeId[]>();
for (const node of graph.nodes.values()) {
if (node.domParentId) {
const children = domChildren.get(node.domParentId) ?? [];
children.push(node.id);
domChildren.set(node.domParentId, children);
}
if (node.axParentId) {
const children = axChildren.get(node.axParentId) ?? [];
children.push(node.id);
axChildren.set(node.axParentId, children);
}
const id = clean(node.dom?.attrs.id);
if (id) domIdIndex.set(`${node.frameId}\u0000${id}`, node.id);
const targetId = clean(node.dom?.attrs.for);
if (node.dom?.tag.toLowerCase() === "label" && targetId) {
const key = `${node.frameId}\u0000${targetId}`;
const labels = labelForIndex.get(key) ?? [];
labels.push(node.id);
labelForIndex.set(key, labels);
}
}
for (const [parentId, children] of axChildren) {
const order = graph.nodes.get(parentId)?.ax?.childIds ?? [];
const orderByAxId = new Map(order.map((nodeId, index) => [nodeId, index]));
children.sort((a, b) => {
const aIndex = orderByAxId.get(graph.nodes.get(a)?.axNodeId ?? "") ?? -1;
const bIndex = orderByAxId.get(graph.nodes.get(b)?.axNodeId ?? "") ?? -1;
return (
(aIndex < 0 ? Number.MAX_SAFE_INTEGER : aIndex) -
(bIndex < 0 ? Number.MAX_SAFE_INTEGER : bIndex)
);
});
}
const textMemo = new Map<SemanticNodeId, string | undefined>();
const resolvingText = new Set<SemanticNodeId>();
const domText = (nodeId: SemanticNodeId): string | undefined => {
if (textMemo.has(nodeId)) return textMemo.get(nodeId);
if (resolvingText.has(nodeId)) return undefined;
resolvingText.add(nodeId);
const node = graph.nodes.get(nodeId);
const parts: string[] = [];
const own = clean(node?.dom?.textContent);
if (own) parts.push(own);
for (const childId of domChildren.get(nodeId) ?? []) {
const child = graph.nodes.get(childId);
const childRole = child
? domRole(child.dom?.tag.toLowerCase() ?? "", child.dom?.attrs ?? {})
: undefined;
if (childRole && INTERACTIVE_ROLES.has(childRole.toLowerCase())) continue;
const childText = domText(childId);
if (childText) parts.push(childText);
if (parts.join(" ").length >= 240) break;
}
resolvingText.delete(nodeId);
const result = clean(parts.join(" ").slice(0, 240));
textMemo.set(nodeId, result);
return result;
};
const axTextMemo = new Map<SemanticNodeId, string | undefined>();
const resolvingAxText = new Set<SemanticNodeId>();
const axText = (nodeId: SemanticNodeId): string | undefined => {
if (axTextMemo.has(nodeId)) return axTextMemo.get(nodeId);
if (resolvingAxText.has(nodeId)) return undefined;
resolvingAxText.add(nodeId);
const complete = (value: string | undefined): string | undefined => {
resolvingAxText.delete(nodeId);
axTextMemo.set(nodeId, value);
return value;
};
const node = graph.nodes.get(nodeId);
const role = normalizeRole(axValue(node?.ax?.role)) ?? "";
if (TEXT_AX_ROLES.has(role)) {
const own = clean(axValue(node?.ax?.name) ?? axValue(node?.ax?.value));
if (own) return complete(own);
}
const parts: string[] = [];
for (const childId of axChildren.get(nodeId) ?? []) {
const child = graph.nodes.get(childId);
const childRole = normalizeRole(axValue(child?.ax?.role)) ?? "";
if (INTERACTIVE_ROLES.has(childRole)) continue;
const childText = axText(childId);
if (childText) parts.push(childText);
if (parts.join(" ").length >= 240) break;
}
return complete(clean(parts.join(" ").slice(0, 240)));
};
const nativeMemo = new Map<SemanticNodeId, boolean>();
const hasNativeDescendant = (nodeId: SemanticNodeId): boolean => {
const cached = nativeMemo.get(nodeId);
if (cached !== undefined) return cached;
nativeMemo.set(nodeId, false);
for (const childId of domChildren.get(nodeId) ?? []) {
const child = graph.nodes.get(childId);
const childRole =
(child?.ax?.ignored === true ? undefined : normalizeRole(axValue(child?.ax?.role))) ??
(child ? domRole(child.dom?.tag.toLowerCase() ?? "", child.dom?.attrs ?? {}) : undefined);
if (
(child?.dom && NATIVE_CONTROL_TAGS.has(child.dom.tag.toLowerCase())) ||
INTERACTIVE_ROLES.has(childRole ?? "") ||
hasNativeDescendant(childId)
) {
nativeMemo.set(nodeId, true);
return true;
}
}
return false;
};
return {
domChildren,
axChildren,
domIdIndex,
labelForIndex,
domText,
axText,
hasNativeDescendant,
};
}
function ariaLabelledText(node: SemanticGraphNode, indexes: ResolveIndexes): string | undefined {
const ids = (node.dom?.attrs["aria-labelledby"] ?? "").split(/\s+/).filter(Boolean);
const parts = ids.flatMap((id) => {
const target = indexes.domIdIndex.get(`${node.frameId}\u0000${id}`);
return target ? (indexes.domText(target) ?? []) : [];
});
return clean(parts.join(" "));
}
function nativeLabelText(
node: SemanticGraphNode,
graph: SemanticGraph,
indexes: ResolveIndexes,
): string | undefined {
const id = clean(node.dom?.attrs.id);
if (id) {
const labels = indexes.labelForIndex.get(`${node.frameId}\u0000${id}`) ?? [];
const explicit = clean(
labels
.map((labelId) => indexes.domText(labelId))
.filter(Boolean)
.join(" "),
);
if (explicit) return explicit;
}
let parentId = node.domParentId;
let guard = 0;
while (parentId && guard <= graph.nodes.size) {
const parent = graph.nodes.get(parentId);
if (!parent) break;
if (parent.dom?.tag.toLowerCase() === "label") return indexes.domText(parentId);
parentId = parent.domParentId;
guard += 1;
}
return undefined;
}
function precedingAxText(
node: SemanticGraphNode,
graph: SemanticGraph,
indexes: ResolveIndexes,
): string | undefined {
if (!node.axParentId) return undefined;
const siblings = indexes.axChildren.get(node.axParentId) ?? [];
const index = siblings.indexOf(node.id);
for (let offset = 1; offset <= 4 && index - offset >= 0; offset += 1) {
const sibling = graph.nodes.get(siblings[index - offset]);
const role = normalizeRole(axValue(sibling?.ax?.role)) ?? "";
if (INTERACTIVE_ROLES.has(role)) break;
if (!TEXT_AX_ROLES.has(role) && role !== "generic") continue;
const text = clean(axValue(sibling?.ax?.name) ?? axValue(sibling?.ax?.value))?.replace(
/[::]\s*$/,
"",
);
if (text && text.length <= 80) return text;
}
return undefined;
}
function precedingDomText(
node: SemanticGraphNode,
graph: SemanticGraph,
indexes: ResolveIndexes,
): string | undefined {
if (!node.domParentId) return undefined;
const siblings = indexes.domChildren.get(node.domParentId) ?? [];
const index = siblings.indexOf(node.id);
for (let offset = 1; offset <= 4 && index - offset >= 0; offset += 1) {
const sibling = graph.nodes.get(siblings[index - offset]);
const siblingRole = sibling
? domRole(sibling.dom?.tag.toLowerCase() ?? "", sibling.dom?.attrs ?? {})
: undefined;
if (siblingRole && INTERACTIVE_ROLES.has(siblingRole.toLowerCase())) break;
const text = indexes.domText(siblings[index - offset])?.replace(/[::]\s*$/, "");
if (text && text.length <= 80) return text;
}
return undefined;
}
function resolvedName(
node: SemanticGraphNode,
role: string | undefined,
graph: SemanticGraph,
indexes: ResolveIndexes,
supplementalNames: ReadonlyMap<string, string>,
identifierFallback: boolean,
): string | undefined {
const attrs = node.dom?.attrs ?? {};
const formControl = FORM_TAGS.has(node.dom?.tag.toLowerCase() ?? "");
const descendantText = indexes.domText(node.id);
const interactive =
INTERACTIVE_ROLES.has(role?.toLowerCase() ?? "") ||
NATIVE_CONTROL_TAGS.has(node.dom?.tag.toLowerCase() ?? "");
const candidates = [
node.ax?.ignored === true ? undefined : axValue(node.ax?.name),
ariaLabelledText(node, indexes),
clean(attrs["aria-label"]),
nativeLabelText(node, graph, indexes),
clean(attrs.title),
clean(attrs.alt),
node.ax?.ignored === true ? undefined : indexes.axText(node.id),
descendantText,
formControl ? precedingAxText(node, graph, indexes) : undefined,
formControl ? precedingDomText(node, graph, indexes) : undefined,
formControl ? clean(node.dom?.formPlaceholder ?? attrs.placeholder) : undefined,
formControl || !interactive || node.backendNodeId === undefined
? undefined
: clean(supplementalNames.get(frameBackendKey(node.frameId, node.backendNodeId))),
identifierFallback && interactive ? stableIdentifierName(attrs) : undefined,
];
let name = candidates.find((candidate) => candidate !== undefined);
const hasPopup = axProperty(node.ax, "hasPopup");
if (name && hasPopup && hasPopup !== "false") {
name =
axProperty(node.ax, "expanded") === "true" ? `${name} [expanded]` : `${name} [has-submenu]`;
}
if (!name && role?.toLowerCase() === "iframe") return clean(attrs.id);
return name;
}
function insideNative(node: SemanticGraphNode, graph: SemanticGraph): boolean {
let parentId = node.domParentId;
let guard = 0;
while (parentId && guard <= graph.nodes.size) {
const parent = graph.nodes.get(parentId);
if (!parent) break;
if (parent.dom && NATIVE_CONTROL_TAGS.has(parent.dom.tag.toLowerCase())) return true;
parentId = parent.domParentId;
guard += 1;
}
return false;
}
function nearbyText(
node: SemanticGraphNode,
graph: SemanticGraph,
indexes: ResolveIndexes,
): string | undefined {
if (!node.domParentId) return undefined;
const siblings = indexes.domChildren.get(node.domParentId) ?? [];
const index = siblings.indexOf(node.id);
if (index < 0) return undefined;
const texts = siblings
.slice(Math.max(0, index - 3), index + 4)
.filter((id) => id !== node.id)
.flatMap((id) => indexes.domText(id) ?? [])
.slice(0, 3);
return clean(texts.join(" "));
}
export function resolveSemanticGraph(
graph: SemanticGraph,
options: {
supplementalNames?: ReadonlyMap<string, string>;
identifierFallback?: boolean;
} = {},
): ResolvedSemanticGraph {
const indexes = buildIndexes(graph);
const supplementalNames = options.supplementalNames ?? new Map<string, string>();
const identifierFallback = options.identifierFallback ?? true;
const nodes = new Map<SemanticNodeId, ResolvedSemanticNode>();
for (const node of graph.nodes.values()) {
const roleResolution = resolvedRole(node);
const role = roleResolution.value;
const name = resolvedName(node, role, graph, indexes, supplementalNames, identifierFallback);
const isSensitive = sensitive(node);
const sourceValue = node.dom?.formValue ?? axValue(node.ax?.value);
const value = isSensitive ? undefined : sourceValue;
const attrs = { ...(node.dom?.attrs ?? {}) };
if (isSensitive) delete attrs.value;
const frame = graph.frames.get(node.frameId);
const tag = node.dom?.tag.toLowerCase() ?? "";
const vom: ResolvedSemanticNode["vom"] = {
tag,
rect: node.dom?.rect ?? null,
paintOrder: node.dom?.paintOrder ?? 0,
position: node.dom?.position || "static",
pointerEvents: node.dom?.pointerEvents || "auto",
...(node.dom?.cursor ? { cursor: node.dom.cursor } : {}),
...(role ? { role } : {}),
...(name ? { name } : {}),
...(value !== undefined ? { value } : {}),
...(clean(node.dom?.formPlaceholder ?? attrs.placeholder)
? { placeholder: clean(node.dom?.formPlaceholder ?? attrs.placeholder) }
: {}),
attrs,
...(clean(node.dom?.textContent) ? { text: clean(node.dom?.textContent) } : {}),
...(nearbyText(node, graph, indexes) ? { nearbyText: nearbyText(node, graph, indexes) } : {}),
inputState: inputState(node, role, sourceValue, isSensitive),
sensitive: isSensitive,
modal:
["dialog", "alertdialog"].includes(role?.toLowerCase() ?? "") ||
tag === "dialog" ||
(attrs["aria-modal"] ?? "").toLowerCase() === "true",
disabled:
Object.prototype.hasOwnProperty.call(attrs, "disabled") ||
(attrs["aria-disabled"] ?? "").toLowerCase() === "true",
inert: Object.prototype.hasOwnProperty.call(attrs, "inert"),
hasNativeDescendant: indexes.hasNativeDescendant(node.id),
insideNative: insideNative(node, graph),
...(role?.toLowerCase() === "link" ? { href: externalHrefHost(attrs.href, frame?.url) } : {}),
};
const selected = node.ax?.ignored === true ? undefined : axProperty(node.ax, "selected");
const expanded = node.ax?.ignored === true ? undefined : axProperty(node.ax, "expanded");
const controls = node.ax?.ignored === true ? undefined : axProperty(node.ax, "controls");
if (selected === "true" && !vom.attrs?.["aria-selected"]) {
vom.attrs = { ...(vom.attrs ?? {}), "aria-selected": "true" };
}
if (expanded === "true" && !vom.attrs?.["aria-expanded"]) {
vom.attrs = { ...(vom.attrs ?? {}), "aria-expanded": "true" };
}
if (controls && !vom.attrs?.["aria-controls"]) {
vom.attrs = { ...(vom.attrs ?? {}), "aria-controls": controls };
}
nodes.set(node.id, {
...node,
vom,
referenceable: node.backendNodeId !== undefined,
roleSource: roleResolution.source,
});
}
return { ...graph, nodes };
}
@@ -0,0 +1,456 @@
import {
applyVomInteractionRecovery,
isVomReferenceNode,
isVomStructuralRole,
type VomNode,
} from "@browser-skill/vom";
import type {
ResolvedSemanticGraph,
ResolvedSemanticNode,
SemanticNodeId,
StructureDecision,
StructuredSemanticGraph,
StructuredSemanticNode,
} from "./types";
const TRANSPARENT_ROLES = new Set(["", "generic", "none", "presentation", "inlinetextbox"]);
const ROOT_ROLES = new Set(["rootwebarea", "webarea"]);
const CONTENT_BOUNDARY_ROLES = new Set([
"article",
"dialog",
"document",
"feed",
"form",
"grid",
"heading",
"iframe",
"list",
"main",
"navigation",
"paragraph",
"region",
"section",
"table",
"tree",
]);
function hasMeaningfulRelations(node: ResolvedSemanticNode): boolean {
const attrs = node.vom.attrs ?? {};
return ["aria-controls", "aria-labelledby", "aria-owns", "aria-describedby"].some((name) =>
attrs[name]?.trim(),
);
}
function explicitStructural(node: ResolvedSemanticNode): boolean {
return (
isVomStructuralRole(node.vom.role) &&
node.roleSource !== "none" &&
node.roleSource !== "ax-ignored"
);
}
function hasUsableAxSemantics(node: ResolvedSemanticNode): boolean {
return node.ax !== undefined && node.ax.ignored !== true;
}
function isRenderedDomFallback(node: ResolvedSemanticNode): boolean {
if (!node.dom) return false;
const attrs = node.dom.attrs;
if (
Object.prototype.hasOwnProperty.call(attrs, "hidden") ||
Object.prototype.hasOwnProperty.call(attrs, "inert") ||
(attrs["aria-hidden"] ?? "").toLowerCase() === "true"
) {
return false;
}
return node.dom.rendered ?? (node.dom.localRect != null || node.dom.rect != null);
}
function initialParentId(
graph: ResolvedSemanticGraph,
node: ResolvedSemanticNode,
): SemanticNodeId | undefined {
let parentId = node.axParentId ?? node.domParentId;
if (node.axParentId && node.domParentId && node.axParentId !== node.domParentId) {
const axParent = graph.nodes.get(node.axParentId);
const axRole = axParent?.vom.role?.toLowerCase() ?? "";
const meaningfulAxParent =
axParent !== undefined &&
!ROOT_ROLES.has(axRole) &&
(explicitStructural(axParent) ||
!TRANSPARENT_ROLES.has(axRole) ||
Boolean(axParent.vom.name || axParent.vom.text || hasMeaningfulRelations(axParent)));
parentId = meaningfulAxParent ? node.axParentId : node.domParentId;
}
if (parentId) return parentId;
if (node.frameId === graph.rootFrameId) return undefined;
return graph.frames.get(node.frameId)?.ownerNodeId;
}
function orderedNodes(graph: ResolvedSemanticGraph): ResolvedSemanticNode[] {
return [...graph.frames.values()]
.sort((a, b) => a.order - b.order)
.flatMap((frame) =>
(graph.nodeIdsByFrame.get(frame.frameId) ?? [])
.map((id) => graph.nodes.get(id))
.filter((node): node is ResolvedSemanticNode => node !== undefined)
.sort((a, b) => a.sourceOrder - b.sourceOrder),
);
}
function recoveredNodes(
graph: ResolvedSemanticGraph,
nodes: ResolvedSemanticNode[],
): Map<SemanticNodeId, VomNode> {
const numericId = new Map(nodes.map((node, index) => [node.id, index + 1]));
const semanticId = new Map([...numericId].map(([id, numeric]) => [numeric, id]));
const provisional = nodes.map((node) => ({
...node.vom,
id: numericId.get(node.id) as number,
parentId: (() => {
const parent = initialParentId(graph, node);
return parent ? (numericId.get(parent) ?? null) : null;
})(),
...(node.backendNodeId !== undefined ? { backendNodeId: node.backendNodeId } : {}),
frameId: node.frameId,
contextScopeId: graph.frames.get(node.frameId)?.contextScopeId ?? node.frameId,
referenceable: node.referenceable,
}));
return new Map(
applyVomInteractionRecovery(provisional).flatMap((node) => {
const id = semanticId.get(node.id);
return id ? [[id, node] as const] : [];
}),
);
}
function redundantSourceNodes(
graph: ResolvedSemanticGraph,
nodes: ResolvedSemanticNode[],
recovered: ReadonlyMap<SemanticNodeId, VomNode>,
): Set<SemanticNodeId> {
const byKey = new Map<string, ResolvedSemanticNode[]>();
for (const node of nodes) {
const output = recovered.get(node.id) as VomNode;
const name = output.name?.trim().toLowerCase() ?? "";
if (!name || !isVomReferenceNode({ ...output, referenceable: true })) continue;
const key = `${node.frameId}\u0000${initialParentId(graph, node) ?? ""}\u0000${output.role?.toLowerCase() ?? ""}\u0000${name}\u0000${output.sensitive === true}`;
const matches = byKey.get(key) ?? [];
matches.push(node);
byKey.set(key, matches);
}
const redundant = new Set<SemanticNodeId>();
for (const matches of byKey.values()) {
const axOnly = matches.filter((node) => node.ax && !node.dom);
const domOnly = matches.filter((node) => node.dom && !node.ax);
if (matches.length === 2 && axOnly.length === 1 && domOnly.length === 1) {
redundant.add(domOnly[0].id);
}
}
return redundant;
}
function baseDecision(
graph: ResolvedSemanticGraph,
node: ResolvedSemanticNode,
output: VomNode,
frameOwnerIds: ReadonlySet<SemanticNodeId>,
redundant: ReadonlySet<SemanticNodeId>,
): StructureDecision {
if (node.excluded) return { kind: "excluded", reason: "excluded" };
if (redundant.has(node.id)) return { kind: "excluded", reason: "redundant-source" };
if (!hasUsableAxSemantics(node) && !isRenderedDomFallback(node)) {
return { kind: "excluded", reason: "non-rendered-dom-fallback" };
}
if (frameOwnerIds.has(node.id)) return { kind: "keep", reason: "frame-owner" };
if (node.frameId !== graph.rootFrameId && ROOT_ROLES.has(output.role?.toLowerCase() ?? "")) {
return { kind: "transparent", reason: "child-document-root" };
}
if (node.ax?.ignored === true && !node.dom) {
return { kind: "transparent", reason: "ax-ignored" };
}
const role = output.role?.toLowerCase() ?? "";
if (!TRANSPARENT_ROLES.has(role)) return { kind: "keep", reason: "semantic" };
if (
output.name ||
output.text ||
output.value ||
output.placeholder ||
hasMeaningfulRelations(node) ||
(output.rect && ["fixed", "sticky"].includes(output.position))
) {
return { kind: "keep", reason: "semantic" };
}
return { kind: "transparent", reason: "wrapper" };
}
function buildChildren(
nodes: ResolvedSemanticNode[],
relation: "axParentId" | "domParentId",
): Map<SemanticNodeId, SemanticNodeId[]> {
const children = new Map<SemanticNodeId, SemanticNodeId[]>();
for (const node of nodes) {
const parentId = node[relation];
if (!parentId) continue;
const siblings = children.get(parentId) ?? [];
siblings.push(node.id);
children.set(parentId, siblings);
}
return children;
}
function explicitDomAncestors(
graph: ResolvedSemanticGraph,
nodes: ResolvedSemanticNode[],
domChildren: ReadonlyMap<SemanticNodeId, SemanticNodeId[]>,
): Set<SemanticNodeId> {
const inside = new Set<SemanticNodeId>();
const roots = nodes.filter((node) => !node.domParentId);
const queue = roots.map((node) => node.id);
for (let index = 0; index < queue.length; index += 1) {
const parentId = queue[index];
const parent = graph.nodes.get(parentId);
const parentIsBoundary =
parent !== undefined &&
explicitStructural(parent) &&
!ROOT_ROLES.has(parent.vom.role?.toLowerCase() ?? "");
for (const childId of domChildren.get(parentId) ?? []) {
if (inside.has(parentId) || parentIsBoundary) inside.add(childId);
queue.push(childId);
}
}
return inside;
}
function reliableGroupCandidates(
graph: ResolvedSemanticGraph,
nodes: ResolvedSemanticNode[],
recovered: ReadonlyMap<SemanticNodeId, VomNode>,
decisions: ReadonlyMap<SemanticNodeId, StructureDecision>,
domChildren: ReadonlyMap<SemanticNodeId, SemanticNodeId[]>,
): Set<SemanticNodeId> {
const insideExplicitStructure = explicitDomAncestors(graph, nodes, domChildren);
const remainingChildren = new Map(
nodes.map((node) => [node.id, domChildren.get(node.id)?.length ?? 0]),
);
const summaries = new Map<SemanticNodeId, { blocked: boolean; interactions: number }>();
const queue = nodes
.filter((node) => (remainingChildren.get(node.id) ?? 0) === 0)
.map((node) => node.id);
for (let index = 0; index < queue.length; index += 1) {
const nodeId = queue[index];
const node = graph.nodes.get(nodeId);
const output = recovered.get(nodeId);
if (!node || !output) continue;
const role = output.role?.toLowerCase() ?? "";
const excluded = decisions.get(nodeId)?.kind === "excluded";
const blocked = excluded || explicitStructural(node) || CONTENT_BOUNDARY_ROLES.has(role);
const summary = excluded
? { blocked: true, interactions: 0 }
: isVomReferenceNode(output)
? { blocked: false, interactions: 1 }
: blocked
? { blocked: true, interactions: 0 }
: (domChildren.get(nodeId) ?? []).reduce(
(combined, childId) => {
const child = summaries.get(childId);
return {
blocked: combined.blocked || !child || child.blocked,
interactions: Math.min(2, combined.interactions + (child?.interactions ?? 0)),
};
},
{ blocked: false, interactions: 0 },
);
summaries.set(nodeId, summary);
const parentId = node.domParentId;
if (!parentId) continue;
const remaining = (remainingChildren.get(parentId) ?? 1) - 1;
remainingChildren.set(parentId, remaining);
if (remaining === 0) queue.push(parentId);
}
const candidates = new Set<SemanticNodeId>();
for (const node of nodes) {
const output = recovered.get(node.id) as VomNode;
const role = output.role?.toLowerCase() ?? "";
if (
!node.dom ||
node.dom.tag.toLowerCase() !== "div" ||
!TRANSPARENT_ROLES.has(role) ||
insideExplicitStructure.has(node.id) ||
decisions.get(node.id)?.kind === "excluded" ||
node.dom.attrs.hidden !== undefined ||
(node.dom.attrs["aria-hidden"] ?? "").toLowerCase() === "true" ||
node.dom.attrs.inert !== undefined
) {
continue;
}
const branches = (domChildren.get(node.id) ?? []).map((id) => summaries.get(id));
const blocked = branches.some((summary) => !summary || summary.blocked);
const contributingBranches = branches.filter(
(summary) => (summary?.interactions ?? 0) > 0,
).length;
const interactions = branches.reduce(
(count, summary) => Math.min(2, count + (summary?.interactions ?? 0)),
0,
);
if (!blocked && contributingBranches >= 2 && interactions >= 2) {
candidates.add(node.id);
}
}
return candidates;
}
function leafCandidates(
nodes: ResolvedSemanticNode[],
candidates: ReadonlySet<SemanticNodeId>,
domChildren: ReadonlyMap<SemanticNodeId, SemanticNodeId[]>,
): Set<SemanticNodeId> {
const parentById = new Map(
nodes.flatMap((node) => (node.domParentId ? ([[node.id, node.domParentId]] as const) : [])),
);
const childCount = new Map(nodes.map((node) => [node.id, domChildren.get(node.id)?.length ?? 0]));
const containsCandidate = new Set<SemanticNodeId>();
const queue = nodes.filter((node) => (childCount.get(node.id) ?? 0) === 0).map((node) => node.id);
const selected = new Set<SemanticNodeId>();
for (let index = 0; index < queue.length; index += 1) {
const nodeId = queue[index];
if (candidates.has(nodeId) && !containsCandidate.has(nodeId)) selected.add(nodeId);
const parentId = parentById.get(nodeId);
if (!parentId) continue;
if (candidates.has(nodeId) || containsCandidate.has(nodeId)) containsCandidate.add(parentId);
const remaining = (childCount.get(parentId) ?? 1) - 1;
childCount.set(parentId, remaining);
if (remaining === 0) queue.push(parentId);
}
return selected;
}
function nearestKept(
graph: ResolvedSemanticGraph,
startId: SemanticNodeId | undefined,
relation: "axParentId" | "domParentId",
kept: ReadonlySet<SemanticNodeId>,
memo: Map<SemanticNodeId, SemanticNodeId | undefined>,
): SemanticNodeId | undefined {
let currentId = startId;
const path: SemanticNodeId[] = [];
const seen = new Set<SemanticNodeId>();
let result: SemanticNodeId | undefined;
while (currentId && !seen.has(currentId)) {
if (kept.has(currentId)) {
result = currentId;
break;
}
if (memo.has(currentId)) {
result = memo.get(currentId);
break;
}
seen.add(currentId);
path.push(currentId);
currentId = graph.nodes.get(currentId)?.[relation];
}
for (const id of path) memo.set(id, result);
return result;
}
function finalParentId(
graph: ResolvedSemanticGraph,
node: ResolvedSemanticNode,
kept: ReadonlySet<SemanticNodeId>,
decisions: ReadonlyMap<SemanticNodeId, StructureDecision>,
axParentMemo: Map<SemanticNodeId, SemanticNodeId | undefined>,
domParentMemo: Map<SemanticNodeId, SemanticNodeId | undefined>,
): SemanticNodeId | undefined {
const axParent = nearestKept(graph, node.axParentId, "axParentId", kept, axParentMemo);
const domParent = nearestKept(graph, node.domParentId, "domParentId", kept, domParentMemo);
const axNode = axParent ? graph.nodes.get(axParent) : undefined;
const domNode = domParent ? graph.nodes.get(domParent) : undefined;
const axIsRoot = ROOT_ROLES.has(axNode?.vom.role?.toLowerCase() ?? "");
const axIsExplicit = axNode ? explicitStructural(axNode) && !axIsRoot : false;
const domIsStructural =
domNode !== undefined &&
(explicitStructural(domNode) || decisions.get(domNode.id)?.kind === "inferred-group");
if (axIsExplicit) return axParent;
if (domIsStructural) return domParent;
if (axParent && !axIsRoot) return axParent;
if (domParent) return domParent;
if (axParent) return axParent;
if (node.frameId === graph.rootFrameId) return undefined;
return graph.frames.get(node.frameId)?.ownerNodeId;
}
function recoveredVom(node: VomNode, inferredGroup: boolean): ResolvedSemanticNode["vom"] {
const {
id: _id,
parentId: _parentId,
backendNodeId: _backendNodeId,
frameId: _frameId,
contextScopeId: _contextScopeId,
referenceable: _referenceable,
...vom
} = node;
if (!inferredGroup) return vom;
const { name: _name, text: _text, nearbyText: _nearbyText, ...groupVom } = vom;
return { ...groupVom, role: "group" };
}
export function normalizeSemanticStructure(graph: ResolvedSemanticGraph): StructuredSemanticGraph {
const nodes = orderedNodes(graph);
const recovered = recoveredNodes(graph, nodes);
const redundant = redundantSourceNodes(graph, nodes, recovered);
const frameOwnerIds = new Set(
[...graph.frames.values()].flatMap((frame) => frame.ownerNodeId ?? []),
);
const decisions = new Map<SemanticNodeId, StructureDecision>();
for (const node of nodes) {
decisions.set(
node.id,
baseDecision(graph, node, recovered.get(node.id) as VomNode, frameOwnerIds, redundant),
);
}
const domChildren = buildChildren(nodes, "domParentId");
const candidates = reliableGroupCandidates(graph, nodes, recovered, decisions, domChildren);
for (const nodeId of leafCandidates(nodes, candidates, domChildren)) {
decisions.set(nodeId, {
kind: "inferred-group",
reason: "independent-interaction-branches",
});
}
const kept = new Set(
nodes
.filter((node) => {
const kind = decisions.get(node.id)?.kind;
return kind === "keep" || kind === "inferred-group";
})
.map((node) => node.id),
);
const axParentMemo = new Map<SemanticNodeId, SemanticNodeId | undefined>();
const domParentMemo = new Map<SemanticNodeId, SemanticNodeId | undefined>();
const structuredNodes = new Map<SemanticNodeId, StructuredSemanticNode>();
for (const node of nodes) {
const structure = decisions.get(node.id) as StructureDecision;
const inferredGroup = structure.kind === "inferred-group";
structuredNodes.set(node.id, {
...node,
vom: recoveredVom(recovered.get(node.id) as VomNode, inferredGroup),
structure,
...(kept.has(node.id)
? {
semanticParentId: finalParentId(
graph,
node,
kept,
decisions,
axParentMemo,
domParentMemo,
),
}
: {}),
});
}
return { ...graph, nodes: structuredNodes };
}
@@ -0,0 +1,88 @@
import type { Viewport, VomNode } from "@browser-skill/vom";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import type { CapturedNode } from "../capture";
export interface SemanticAxNode {
nodeId: string;
frameId?: string;
parentId?: string;
backendDOMNodeId?: number;
ignored?: boolean;
role?: { type: string; value?: string };
name?: { type: string; value?: string };
description?: { value?: string };
value?: { value?: string | number | boolean };
properties?: Array<{ name?: string; value?: { value?: string | number | boolean } }>;
childIds?: string[];
}
export type SemanticNodeId = string;
export interface SemanticFrame {
frameId: string;
parentFrameId?: string;
ownerBackendNodeId?: number;
ownerNodeId?: SemanticNodeId;
contextScopeId: string;
target: CdpTarget;
url?: string;
order: number;
}
export interface SemanticGraphNode {
id: SemanticNodeId;
frameId: string;
backendNodeId?: number;
axNodeId?: string;
ax?: SemanticAxNode;
dom?: CapturedNode;
axParentId?: SemanticNodeId;
domParentId?: SemanticNodeId;
sourceOrder: number;
excluded: boolean;
}
export interface SemanticGraph {
viewport: Viewport;
rootFrameId: string;
frames: Map<string, SemanticFrame>;
nodes: Map<SemanticNodeId, SemanticGraphNode>;
nodeIdsByFrame: Map<string, SemanticNodeId[]>;
nodeByFrameBackend: Map<string, SemanticNodeId>;
}
export interface ResolvedSemanticNode extends SemanticGraphNode {
vom: Omit<VomNode, "id" | "parentId" | "backendNodeId" | "frameId" | "contextScopeId">;
referenceable: boolean;
roleSource: "ax" | "ax-ignored" | "dom-explicit" | "dom-native" | "none";
}
export interface ResolvedSemanticGraph extends Omit<SemanticGraph, "nodes"> {
nodes: Map<SemanticNodeId, ResolvedSemanticNode>;
}
export type StructureDecision =
| { kind: "keep"; reason: "semantic" | "frame-owner" }
| { kind: "inferred-group"; reason: "independent-interaction-branches" }
| { kind: "transparent"; reason: "wrapper" | "child-document-root" | "ax-ignored" }
| {
kind: "excluded";
reason: "excluded" | "redundant-source" | "non-rendered-dom-fallback";
};
export interface StructuredSemanticNode extends ResolvedSemanticNode {
structure: StructureDecision;
semanticParentId?: SemanticNodeId;
}
export interface StructuredSemanticGraph extends Omit<ResolvedSemanticGraph, "nodes"> {
nodes: Map<SemanticNodeId, StructuredSemanticNode>;
}
export function frameBackendKey(frameId: string, backendNodeId: number): string {
return `${frameId}\u0000${backendNodeId}`;
}
export function frameAxKey(frameId: string, axNodeId: string): string {
return `${frameId}\u0000${axNodeId}`;
}
+22
View File
@@ -23,9 +23,12 @@ export type ErrorCode =
export type RpcErrorReason =
| "agent_window_scope"
| "element_not_visible"
| "ref_capability_denied"
| "ref_not_found"
| "selector_not_found"
| "target_not_fillable"
| "focus_target_unresolved"
| "input_not_applied"
| "target_not_select"
| "option_not_found"
| "single_select_value_count"
@@ -33,6 +36,11 @@ export type RpcErrorReason =
| "restricted_tab_url"
| "borrow_conflict"
| "screenshot_capture_failed"
| "surface_capture_not_found"
| "surface_capture_expired"
| "surface_capture_consumed"
| "surface_capture_stale"
| "surface_coordinate_invalid"
| "cleanup_failed";
export interface RpcErrorData {
@@ -298,9 +306,17 @@ export interface ScreenshotResult {
height: number;
format: string;
tab_id: number;
capture?: SurfaceCaptureInfo;
dialogs?: JavaScriptDialogInfo[];
}
export interface SurfaceCaptureInfo {
id: string;
surface_ref: string;
coordinate_space: "capture-image-pixel";
expires_at: number;
}
export interface SnapshotParams {
session_id: string;
tab_id?: number;
@@ -414,6 +430,9 @@ export interface ClickParams {
click_count?: number;
modifiers?: KeyModifier[];
timeout_ms?: number;
capture_id?: string;
image_x?: number;
image_y?: number;
}
export interface ClickResult {
@@ -422,6 +441,9 @@ export interface ClickResult {
used_selector?: string;
x: number;
y: number;
capture_id?: string;
image_x?: number;
image_y?: number;
dialogs?: JavaScriptDialogInfo[];
}
@@ -0,0 +1,136 @@
# Rendered Surface browser fixtures
These pages exercise Canvas discovery through a real browser DOMSnapshot and AX tree. They are deliberately framework- and site-independent.
## Serve
From the repository root:
```bash
python3 -m http.server 4173 --bind 127.0.0.1 \
--directory apps/extension/test-fixtures/rendered-surfaces
```
Use an Agent Window large enough to keep the primary matrix visible:
```bash
bsk session start --width 1440 --height 1100
bsk navigate http://127.0.0.1:4173/index.html --session <id>
bsk observe --session <id>
```
Always stop the session after the run.
## Pages
### `index.html`
Expected individual Surface labels:
- `fixture-basic-large`
- `fixture-tiny-8px`
- `fixture-pointer-events-none`
- `fixture-partial-ax`
- `fixture-contained-outer`
- `fixture-contained-inner`
- `fixture-different-parent-a`
- `fixture-different-parent-b`
Expected one grouped Surface:
- `fixture-layered-group`, with `layers=2`
Expected absent:
- `fixture-display-none`
- `fixture-visibility-hidden`
- `fixture-opacity-zero`
- `fixture-parent-opacity-zero`
- `fixture-hidden-attribute`
- `fixture-inert-parent`
- `fixture-aria-hidden-parent`
- `fixture-zero-size`
- `fixture-offscreen-right`
- `fixture-fully-overflow-clipped`
`fixture-partially-overflow-clipped` must remain present because part of it is visible. Its screenshot must contain only the browser's final composited view.
### `unlabeled.html`
This page contains eight Canvas elements but must render seven generic Surface markers because
the two coincident layers form one group.
- Every marker uses the stable fallback label `canvas visual surface`.
- Exactly one marker has `layers=2`.
- The two contained canvases remain separate markers.
- `id`, `class`, `data-testid`, nearby prose, and fallback AX content never become a Surface label.
- Blank `aria-label` and `title` values behave as no label.
- Fallback AX content does not suppress the corresponding Surface.
### `frames.html`
Expected Surface labels:
- `fixture-same-origin-frame`
- `fixture-cross-origin-frame`
- `fixture-nested-frame`
The cross-origin frame uses `http://localhost:4173` while the parent uses `http://127.0.0.1:4173`. With Chromium site isolation this exercises the OOPIF path without an external service.
Each frame Canvas also exposes a `pointer status` live region. A successful
screenshot-bound point click must report
`down button=0 buttons=1 hoverReady=true; click received` and turn the Canvas
yellow. The hover flag is set on the animation frame after `pointermove`, so the
fixture verifies both child-document delivery and the scheduling boundary
required before `pointerdown`, rather than merely validating projected
coordinates or a successful CDP response.
### `viewport.html`
Run with a `900x700` Agent Window.
- `fixture-partial-viewport` is partly visible and must be represented.
- `fixture-below-fold` is absent initially.
- After scrolling it into view and observing again, `fixture-below-fold` must be represented with a fresh ref.
### `input-frames.html`
This page exercises generic frame-aware input routing. It contains a top-level
input plus same-origin, cross-origin (OOPIF), and nested frame inputs. Each
frame includes an input, textarea, contenteditable editor, and a controlled
input that resets its value on the next animation frame.
- `fill` must route focus, text insertion, DOM events, and readback through the
ref's owning CDP target.
- `press --ref` must focus and dispatch every key event through that same target.
- Untargeted `press` must follow the actual focused target or refuse when focus
ownership cannot be determined uniquely.
- The rejecting input must return `input_not_applied`, never a successful
requested-value length.
### `canvas-input.html`
This is the PR3 end-to-end fixture. Its cross-origin frame contains a
visual-only three-row Canvas. A screenshot-bound click on row 3 exposes and
focuses a standard textbox; ordinary `fill` must then write and read back its
real value through the textbox's owning target. The fixture deliberately does
not provide a Canvas-specific fill action.
### `dynamic.html`
Use the normal DOM buttons and re-observe after each action:
- Initial state: `fixture-dynamic` absent.
- After **Insert canvas**: present.
- After **Resize to zero**: absent.
- After **Restore size**: present with a fresh ref.
- After **Remove canvas**: absent.
## Invariants
- `snapshot` must not emit any of these Surface markers.
- `observe` must emit only currently visible Canvas surfaces.
- Existing DOM/AX controls remain readable alongside Surface markers.
- Missing labels never prevent discovery; naming and discovery are independent.
- A Surface ref allows `screenshot --ref` and rejects ordinary click/fill/hover/select.
- No fixture URL, id, label, or layout constant may appear in production discovery code.
@@ -0,0 +1,20 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Canvas to standard input fixture</title>
<style>
body { padding: 16px; font: 14px system-ui, sans-serif; }
iframe { width: 300px; height: 220px; border: 2px solid #5d6d7e; }
</style>
</head>
<body>
<h1>Canvas to standard input fixture</h1>
<p>Select row 3 in the visual-only Canvas, then fill the exposed standard textbox.</p>
<iframe
title="cross-origin Canvas editor"
src="http://localhost:4173/frame.html?label=canvas-input-grid&interactive=1&editor=1"
></iframe>
</body>
</html>
@@ -0,0 +1,46 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Rendered Surface dynamic matrix</title>
<style>
html, body { margin: 0; font: 14px system-ui, sans-serif; }
body { padding: 16px; }
.controls { display: flex; gap: 8px; margin-bottom: 16px; }
button { padding: 8px 12px; }
canvas { display: block; width: 260px; height: 120px; background: #e8daef; border: 2px solid #7d3c98; }
</style>
</head>
<body>
<h1>Dynamic Canvas lifecycle</h1>
<div class="controls">
<button id="insert" type="button">Insert canvas</button>
<button id="zero" type="button">Resize to zero</button>
<button id="restore" type="button">Restore size</button>
<button id="remove" type="button">Remove canvas</button>
</div>
<div id="mount"></div>
<script>
const mount = document.querySelector("#mount");
const getCanvas = () => mount.querySelector("canvas");
document.querySelector("#insert").addEventListener("click", () => {
if (getCanvas()) return;
const canvas = document.createElement("canvas");
canvas.width = 260;
canvas.height = 120;
canvas.setAttribute("aria-label", "fixture-dynamic");
mount.append(canvas);
});
document.querySelector("#zero").addEventListener("click", () => {
const canvas = getCanvas();
if (canvas) canvas.style.cssText = "width:0;height:0;border:0";
});
document.querySelector("#restore").addEventListener("click", () => {
const canvas = getCanvas();
if (canvas) canvas.removeAttribute("style");
});
document.querySelector("#remove").addEventListener("click", () => getCanvas()?.remove());
</script>
</body>
</html>
@@ -0,0 +1,80 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<style>
html, body { margin: 0; font: 14px system-ui, sans-serif; }
body { padding: 12px; background: #fdfefe; }
canvas { display: block; width: 220px; height: 90px; background: #d5f5e3; border: 2px solid #1e8449; }
iframe { width: 280px; height: 150px; margin-top: 10px; border: 2px solid #85929e; }
#pointer-status { margin: 8px 0 0; min-height: 20px; }
</style>
</head>
<body>
<canvas id="frame-canvas" width="220" height="90"></canvas>
<script>
const params = new URLSearchParams(location.search);
const canvas = document.querySelector("#frame-canvas");
if (params.get("canvas") === "0") canvas.remove();
else {
canvas.setAttribute("aria-label", params.get("label") || "fixture-frame-default");
if (params.get("editor") === "1") {
const context = canvas.getContext("2d");
context.font = "14px system-ui, sans-serif";
context.textBaseline = "middle";
context.strokeStyle = "#1e8449";
context.fillStyle = "#145a32";
for (let row = 0; row < 3; row += 1) {
const top = row * 30;
context.strokeRect(0.5, top + 0.5, 219, 29);
context.fillText(`Row ${row + 1}`, 12, top + 15);
}
}
if (params.get("interactive") === "1") {
const status = document.createElement("p");
status.id = "pointer-status";
status.setAttribute("aria-live", "polite");
status.textContent = "pointer status: idle";
canvas.insertAdjacentElement("afterend", status);
let hoverReady = false;
canvas.addEventListener("pointermove", () => {
hoverReady = false;
requestAnimationFrame(() => {
hoverReady = true;
});
});
canvas.addEventListener("pointerdown", (event) => {
status.textContent = `pointer status: down button=${event.button} buttons=${event.buttons} hoverReady=${hoverReady}`;
if (event.buttons === 1 && hoverReady) canvas.style.background = "#f9e79f";
});
canvas.addEventListener("click", () => {
status.textContent += "; click received";
});
if (params.get("editor") === "1") {
canvas.addEventListener("click", (event) => {
const rect = canvas.getBoundingClientRect();
const canvasY = ((event.clientY - rect.top) / rect.height) * canvas.height;
const row = Math.min(2, Math.max(0, Math.floor(canvasY / 30)));
status.textContent += `; selected row=${row + 1}`;
document.querySelector("#canvas-cell-editor")?.remove();
if (row !== 2) return;
const editor = document.createElement("input");
editor.id = "canvas-cell-editor";
editor.setAttribute("aria-label", "selected canvas cell editor");
editor.placeholder = "Type into selected row 3";
canvas.insertAdjacentElement("afterend", editor);
editor.focus();
});
}
}
}
if (params.get("nested") === "1") {
const iframe = document.createElement("iframe");
iframe.title = "nested fixture frame";
iframe.src = "frame.html?label=fixture-nested-frame&interactive=1";
document.body.append(iframe);
}
</script>
</body>
</html>
@@ -0,0 +1,22 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Rendered Surface frame matrix</title>
<style>
html, body { margin: 0; font: 14px system-ui, sans-serif; }
body { padding: 16px; }
.frames { display: grid; grid-template-columns: repeat(3, 320px); gap: 16px; }
iframe { width: 300px; height: 300px; border: 2px solid #5d6d7e; }
</style>
</head>
<body>
<h1>Frame matrix</h1>
<div class="frames">
<iframe title="same-origin fixture" src="frame.html?label=fixture-same-origin-frame&interactive=1"></iframe>
<iframe title="cross-origin fixture" src="http://localhost:4173/frame.html?label=fixture-cross-origin-frame&interactive=1"></iframe>
<iframe title="nested fixture" src="frame.html?canvas=0&nested=1"></iframe>
</div>
</body>
</html>
@@ -0,0 +1,118 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Rendered Surface discovery matrix</title>
<style>
* { box-sizing: border-box; }
html, body { margin: 0; min-height: 100%; font: 14px/1.4 system-ui, sans-serif; }
body { padding: 16px; background: #f4f6f8; color: #17202a; }
h1 { margin: 0 0 12px; font-size: 20px; }
.matrix { display: grid; grid-template-columns: repeat(4, minmax(220px, 1fr)); gap: 12px; }
.case { min-height: 150px; padding: 10px; overflow: hidden; border: 1px solid #aeb6bf; border-radius: 6px; background: white; }
.case h2 { margin: 0 0 8px; font-size: 13px; }
canvas { display: block; background: #d6eaf8; border: 2px solid #2874a6; }
.stack { position: relative; width: 180px; height: 90px; }
.stack canvas { position: absolute; inset: 0; width: 180px; height: 90px; }
.stack canvas + canvas { background: rgb(244 208 63 / 45%); border-color: #b7950b; }
.contained { position: relative; width: 190px; height: 100px; }
.contained > canvas:first-child { width: 190px; height: 100px; }
.contained > canvas:last-child { position: absolute; left: 55px; top: 30px; width: 70px; height: 40px; background: #fadbd8; border-color: #c0392b; }
.same-place { position: relative; width: 180px; height: 90px; }
.same-place > div { position: absolute; inset: 0; }
.same-place canvas { width: 180px; height: 90px; }
.same-place > div:last-child canvas { border-color: #7d3c98; background: rgb(210 180 222 / 35%); }
.clip-box { width: 100px; height: 70px; overflow: hidden; border: 2px dashed #566573; }
.partially-clipped { width: 140px; height: 60px; transform: translateX(45px); }
.fully-clipped { width: 80px; height: 50px; transform: translateX(130px); }
.tiny { width: 8px; height: 8px; border-width: 1px; }
</style>
</head>
<body>
<h1>Rendered Surface discovery matrix</h1>
<main class="matrix">
<section class="case">
<h2>Visible named canvas</h2>
<canvas aria-label="fixture-basic-large" width="200" height="90"></canvas>
</section>
<section class="case">
<h2>Tiny canvas remains addressable</h2>
<canvas class="tiny" aria-label="fixture-tiny-8px" width="8" height="8"></canvas>
</section>
<section class="case">
<h2>Visible but pointer-events none</h2>
<canvas aria-label="fixture-pointer-events-none" width="180" height="80" style="pointer-events: none"></canvas>
</section>
<section class="case">
<h2>Partial AX/fallback content</h2>
<canvas aria-label="fixture-partial-ax" width="180" height="80">
<button type="button">Fallback button must not suppress the surface</button>
</canvas>
</section>
<section class="case">
<h2>Two real rendering layers</h2>
<div class="stack">
<canvas aria-label="fixture-layered-group" width="180" height="90"></canvas>
<canvas width="180" height="90"></canvas>
</div>
</section>
<section class="case">
<h2>Contained canvases are independent</h2>
<div class="contained">
<canvas aria-label="fixture-contained-outer" width="190" height="100"></canvas>
<canvas aria-label="fixture-contained-inner" width="70" height="40"></canvas>
</div>
</section>
<section class="case">
<h2>Same geometry, different parents</h2>
<div class="same-place">
<div><canvas aria-label="fixture-different-parent-a" width="180" height="90"></canvas></div>
<div><canvas aria-label="fixture-different-parent-b" width="180" height="90"></canvas></div>
</div>
</section>
<section class="case">
<h2>Partially overflow-clipped</h2>
<div class="clip-box">
<canvas class="partially-clipped" aria-label="fixture-partially-overflow-clipped" width="140" height="60"></canvas>
</div>
</section>
<section class="case">
<h2>Fully overflow-clipped</h2>
<div class="clip-box">
<canvas class="fully-clipped" aria-label="fixture-fully-overflow-clipped" width="80" height="50"></canvas>
</div>
</section>
<section class="case">
<h2>CSS-hidden variants</h2>
<canvas aria-label="fixture-display-none" width="80" height="40" style="display: none"></canvas>
<canvas aria-label="fixture-visibility-hidden" width="80" height="40" style="visibility: hidden"></canvas>
<canvas aria-label="fixture-opacity-zero" width="80" height="40" style="opacity: 0"></canvas>
</section>
<section class="case">
<h2>Hidden ancestor variants</h2>
<div style="opacity: 0"><canvas aria-label="fixture-parent-opacity-zero" width="80" height="40"></canvas></div>
<div hidden><canvas aria-label="fixture-hidden-attribute" width="80" height="40"></canvas></div>
<div inert><canvas aria-label="fixture-inert-parent" width="80" height="40"></canvas></div>
<div aria-hidden="true"><canvas aria-label="fixture-aria-hidden-parent" width="80" height="40"></canvas></div>
</section>
<section class="case">
<h2>Zero-size and offscreen</h2>
<canvas aria-label="fixture-zero-size" width="80" height="40" style="width: 0; height: 0; border: 0"></canvas>
<canvas aria-label="fixture-offscreen-right" width="80" height="40" style="position: fixed; left: 5000px; top: 0"></canvas>
</section>
</main>
</body>
</html>
@@ -0,0 +1,30 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<style>
body { margin: 0; padding: 12px; font: 14px system-ui, sans-serif; }
label, textarea, input, [contenteditable] { display: block; margin: 8px 0; }
input, textarea, [contenteditable] { width: 240px; padding: 6px; border: 1px solid #85929e; }
iframe { width: 280px; height: 190px; border: 2px solid #85929e; }
</style>
</head>
<body>
<label>Frame input <input aria-label="frame input" /></label>
<label>Frame textarea <textarea aria-label="frame textarea"></textarea></label>
<div contenteditable="true" aria-label="frame editor"></div>
<label>Rejecting input <input id="rejecting" aria-label="rejecting input" /></label>
<script>
const params = new URLSearchParams(location.search);
const rejecting = document.querySelector("#rejecting");
rejecting.addEventListener("input", () => requestAnimationFrame(() => { rejecting.value = ""; }));
if (params.get("nested") === "1") {
const iframe = document.createElement("iframe");
iframe.title = "nested input frame";
iframe.src = "input-frame.html";
document.body.append(iframe);
}
</script>
</body>
</html>
@@ -0,0 +1,23 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Frame input routing matrix</title>
<style>
body { padding: 16px; font: 14px system-ui, sans-serif; }
.frames { display: grid; grid-template-columns: repeat(3, 320px); gap: 16px; }
iframe { width: 300px; height: 430px; border: 2px solid #5d6d7e; }
input { padding: 6px; }
</style>
</head>
<body>
<h1>Frame input routing matrix</h1>
<label>Top input <input aria-label="top input" /></label>
<div class="frames">
<iframe title="same-origin inputs" src="input-frame.html"></iframe>
<iframe title="cross-origin inputs" src="http://localhost:4173/input-frame.html"></iframe>
<iframe title="nested inputs" src="input-frame.html?nested=1"></iframe>
</div>
</body>
</html>
@@ -0,0 +1,68 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Unlabeled Rendered Surface matrix</title>
<style>
* { box-sizing: border-box; }
html, body { margin: 0; min-height: 100%; font: 14px/1.4 system-ui, sans-serif; }
body { padding: 16px; background: #f4f6f8; color: #17202a; }
h1 { margin: 0 0 12px; font-size: 20px; }
.matrix { display: grid; grid-template-columns: repeat(3, minmax(240px, 1fr)); gap: 12px; }
.case { min-height: 150px; padding: 10px; overflow: hidden; border: 1px solid #aeb6bf; border-radius: 6px; background: white; }
.case h2 { margin: 0 0 8px; font-size: 13px; }
.case p { margin: 0 0 8px; }
canvas { display: block; background: #d6eaf8; border: 2px solid #2874a6; }
.stack { position: relative; width: 180px; height: 90px; }
.stack canvas { position: absolute; inset: 0; width: 180px; height: 90px; }
.stack canvas + canvas { background: rgb(244 208 63 / 45%); border-color: #b7950b; }
.contained { position: relative; width: 190px; height: 100px; }
.contained > canvas:first-child { width: 190px; height: 100px; }
.contained > canvas:last-child { position: absolute; left: 55px; top: 30px; width: 70px; height: 40px; background: #fadbd8; border-color: #c0392b; }
</style>
</head>
<body>
<h1>Unlabeled Rendered Surface matrix</h1>
<main class="matrix">
<section class="case">
<h2>Only engineering attributes</h2>
<canvas id="must-not-be-a-label" class="must-not-be-a-label" data-testid="must-not-be-a-label" width="200" height="90"></canvas>
</section>
<section class="case">
<h2>Blank explicit names</h2>
<canvas aria-label=" " title=" " width="180" height="80"></canvas>
</section>
<section class="case">
<h2>Nearby prose is not a Canvas name</h2>
<p>must-not-be-inferred-as-a-surface-label</p>
<canvas width="180" height="80"></canvas>
</section>
<section class="case">
<h2>Fallback AX content does not name or suppress the Canvas</h2>
<canvas width="180" height="80">
<button type="button">Fallback control remains separate</button>
</canvas>
</section>
<section class="case">
<h2>Unnamed rendering layers still cluster</h2>
<div class="stack">
<canvas width="180" height="90"></canvas>
<canvas width="180" height="90"></canvas>
</div>
</section>
<section class="case">
<h2>Unnamed contained canvases stay independent</h2>
<div class="contained">
<canvas width="190" height="100"></canvas>
<canvas width="70" height="40"></canvas>
</div>
</section>
</main>
</body>
</html>
@@ -0,0 +1,22 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Rendered Surface viewport matrix</title>
<style>
html, body { margin: 0; font: 14px system-ui, sans-serif; }
body { min-height: 1800px; padding: 16px; }
canvas { display: block; background: #fdebd0; border: 2px solid #ca6f1e; }
#partial { position: fixed; left: -70px; top: 120px; width: 180px; height: 100px; }
#below { position: absolute; left: 40px; top: 1350px; width: 240px; height: 120px; }
</style>
</head>
<body>
<h1>Viewport matrix</h1>
<p>The orange canvas on the left is intentionally clipped by the viewport.</p>
<canvas id="partial" aria-label="fixture-partial-viewport" width="180" height="100"></canvas>
<canvas id="below" aria-label="fixture-below-fold" width="240" height="120"></canvas>
</body>
</html>
+12 -2
View File
@@ -80,6 +80,16 @@ Prefer `@eN` refs from the latest snapshot over raw CSS selectors. Use `--ref` /
When VOM renders `[hover first: …]` on an element, the listed items are not currently clickable refs. Run `bsk hover <that-ref> --session <id>`, then immediately run `bsk snapshot` or `bsk observe` again and click the newly visible menu item ref. Do not click the trigger itself unless the user explicitly wants the trigger action.
When `bsk observe` renders `@eN surface ... [visual-only; requires=image-understanding; ...]`, the ref identifies rendered canvas content that is not represented by the text observation, not an interactable DOM control. Keep using any reliable DOM/AX text and controls that appear alongside it. If you lack multimodal or image-reading capability, do not take a screenshot and pretend to know its contents, and never guess coordinates; tell the user that they need to switch to a model with image-understanding capability.
If you can actually inspect image output, use `bsk screenshot --ref @eN --session <id>` to obtain the visible crop and its short-lived, single-use Surface capture id. Only when the task requires a point action and the image provides a clear target, bind that exact screenshot to the same general click command:
```bash
bsk click @eN --capture <capture-id> --image-x <px> --image-y <px> --session <id>
```
Coordinates are pixels in the returned capture image, not viewport CSS coordinates. Re-observing, navigating, scrolling, resizing, zooming, changing Frame projection, expiry, or reusing the capture makes the action fail; take a new Surface screenshot instead of adjusting or retrying coordinates. A point click does not reveal Canvas semantics and must not be followed by an assumed fill/press workflow. Without all three capture arguments, visual Surface refs remain screenshot-only and click/fill/hover/select reject them.
## Observation priority
Start with `bsk observe` to understand page structure, text, controls, element refs, and conditional hover/focus surfaces. Use `bsk snapshot` only when you need the stricter static accessibility tree or VOM is insufficient. Only escalate to raw HTML or screenshots when the latest observation cannot answer the question:
@@ -174,7 +184,7 @@ bsk emulate --session <id> --off
| `bsk snapshot` | First-choice static page understanding: accessibility tree with `@eN` element refs |
| `bsk observe` | Semantic VOM observation with bounded perception probes for conditional surfaces |
| `bsk get-html` | Raw HTML dump after snapshot is insufficient (high token cost) |
| `bsk screenshot` | PNG capture after snapshot is insufficient: full visible tab, or `--ref @eN` to crop to one element (`--out` path optional) |
| `bsk screenshot` | PNG capture after snapshot is insufficient: full visible tab, or `--ref @eN` to crop to one element (`--out` path optional); Surface crops return a short-lived capture id |
### Console & network debugging (read-only; require `--session`)
@@ -200,7 +210,7 @@ Both capture from the moment the tab is attached and read a bounded per-tab buff
| Command | Summary |
|---------|---------|
| `bsk click <ref-or-selector>` | Click element (`--button`, `--click-count`, `--modifiers`) |
| `bsk click <ref-or-selector>` | Click a DOM element (`--button`, `--click-count`, `--modifiers`), or perform one screenshot-bound Surface point click with `--capture`, `--image-x`, and `--image-y` |
| `bsk hover <ref-or-selector>` | Move the mouse to an element and wait for hover UI to settle (`--settle`, `--modifiers`) |
| `bsk fill <ref-or-selector> --value <text>` | Clear and type into input |
| `bsk select <ref-or-selector> --value <v>` | Set `<select>` option(s) by `value` (repeat `--value` for multi-select) |
+31
View File
@@ -136,6 +136,18 @@ pub struct ClickArgs {
#[arg(long, default_value = "30s", value_parser = parse_timeout_ms)]
pub timeout: u32,
/// Capture id returned by `bsk screenshot --ref <surface>`.
#[arg(long)]
pub capture: Option<String>,
/// X coordinate in capture-image pixels. Requires `--capture` and `--image-y`.
#[arg(long = "image-x", allow_hyphen_values = true)]
pub image_x: Option<f64>,
/// Y coordinate in capture-image pixels. Requires `--capture` and `--image-x`.
#[arg(long = "image-y", allow_hyphen_values = true)]
pub image_y: Option<f64>,
}
pub fn dispatch_click(args: ClickArgs, format: Format) -> Result<(), CliError> {
@@ -147,6 +159,14 @@ pub fn dispatch_click(args: ClickArgs, format: Format) -> Result<(), CliError> {
)?;
let modifiers = parse_modifiers(&args.modifiers)
.map_err(|e| CliError::Local(anyhow::anyhow!("--modifiers: {e}")))?;
let point_arg_count = usize::from(args.capture.is_some())
+ usize::from(args.image_x.is_some())
+ usize::from(args.image_y.is_some());
if point_arg_count != 0 && point_arg_count != 3 {
return Err(CliError::Local(anyhow::anyhow!(
"--capture, --image-x, and --image-y must be given together"
)));
}
let params = ClickParams {
session_id: args.session.clone(),
ref_,
@@ -160,6 +180,9 @@ pub fn dispatch_click(args: ClickArgs, format: Format) -> Result<(), CliError> {
Some(modifiers)
},
timeout_ms: Some(args.timeout),
capture_id: args.capture.clone(),
image_x: args.image_x,
image_y: args.image_y,
};
let reply: ClickResult = call(
info.sock_path,
@@ -183,6 +206,14 @@ pub fn dispatch_click(args: ClickArgs, format: Format) -> Result<(), CliError> {
"click ok tab={} target={target} at=({}, {})",
reply.tab_id, reply.x, reply.y
);
if let Some(capture_id) = &reply.capture_id {
println!(
"capture={} image=({}, {}) coordinate_space=capture-image-pixel",
capture_id,
reply.image_x.unwrap_or_default(),
reply.image_y.unwrap_or_default()
);
}
print_dialog_summaries(&reply.dialogs);
}
}
+111
View File
@@ -40,15 +40,23 @@ use bsk_protocol::ErrorCode;
pub mod reason {
pub const AGENT_WINDOW_SCOPE: &str = "agent_window_scope";
pub const ELEMENT_NOT_VISIBLE: &str = "element_not_visible";
pub const REF_CAPABILITY_DENIED: &str = "ref_capability_denied";
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 FOCUS_TARGET_UNRESOLVED: &str = "focus_target_unresolved";
pub const INPUT_NOT_APPLIED: &str = "input_not_applied";
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";
pub const TAB_NOT_ACTIVE: &str = "tab_not_active";
pub const BORROW_CONFLICT: &str = "borrow_conflict";
pub const SCREENSHOT_CAPTURE_FAILED: &str = "screenshot_capture_failed";
pub const SURFACE_CAPTURE_NOT_FOUND: &str = "surface_capture_not_found";
pub const SURFACE_CAPTURE_EXPIRED: &str = "surface_capture_expired";
pub const SURFACE_CAPTURE_CONSUMED: &str = "surface_capture_consumed";
pub const SURFACE_CAPTURE_STALE: &str = "surface_capture_stale";
pub const SURFACE_COORDINATE_INVALID: &str = "surface_coordinate_invalid";
pub const SESSION_BUSY: &str = crate::rpc_reason::SESSION_BUSY;
pub const RECORD_START_PAGE_UNREACHABLE: &str = "record_start_page_unreachable";
}
@@ -228,6 +236,27 @@ pub fn info_for_error(code: ErrorCode, data: Option<&serde_json::Value>) -> Rend
),
exit_code: base.exit_code,
},
(ErrorCode::CdpFailed, reason::FOCUS_TARGET_UNRESOLVED) => RenderInfo {
summary: "focused frame target could not be determined",
hint: Some(
"pass an explicit --ref or --selector so the key event can be routed safely",
),
exit_code: base.exit_code,
},
(ErrorCode::CdpFailed, reason::INPUT_NOT_APPLIED) => RenderInfo {
summary: "the page did not retain the requested input",
hint: Some(
"refresh the snapshot and retry; the page may be rejecting or resetting controlled input",
),
exit_code: base.exit_code,
},
(ErrorCode::PermissionDenied, reason::REF_CAPABILITY_DENIED) => RenderInfo {
summary: "snapshot ref does not support this operation",
hint: Some(
"visual Surface refs require image understanding; inspect `bsk screenshot --ref <ref> --session <id>`, then bind its capture id and image coordinates to `bsk click`",
),
exit_code: base.exit_code,
},
(ErrorCode::InvalidParams, reason::TARGET_NOT_SELECT) => RenderInfo {
summary: "target element is not a <select>",
hint: Some(
@@ -270,6 +299,41 @@ pub fn info_for_error(code: ErrorCode, data: Option<&serde_json::Value>) -> Rend
),
exit_code: base.exit_code,
},
(ErrorCode::NotFound, reason::SURFACE_CAPTURE_NOT_FOUND) => RenderInfo {
summary: "surface capture transaction was not found",
hint: Some(
"take a fresh surface screenshot and use its capture id with coordinates from that image",
),
exit_code: base.exit_code,
},
(ErrorCode::PermissionDenied, reason::SURFACE_CAPTURE_EXPIRED) => RenderInfo {
summary: "surface capture transaction has expired",
hint: Some(
"take a fresh surface screenshot, then click promptly with that capture id and image coordinates",
),
exit_code: base.exit_code,
},
(ErrorCode::PermissionDenied, reason::SURFACE_CAPTURE_CONSUMED) => RenderInfo {
summary: "surface capture transaction was already used",
hint: Some(
"each capture id is single-use; take a fresh surface screenshot before another point action",
),
exit_code: base.exit_code,
},
(ErrorCode::PermissionDenied, reason::SURFACE_CAPTURE_STALE) => RenderInfo {
summary: "page state changed since the surface screenshot",
hint: Some(
"take a fresh surface screenshot and choose coordinates from the new image before retrying",
),
exit_code: base.exit_code,
},
(ErrorCode::InvalidParams, reason::SURFACE_COORDINATE_INVALID) => RenderInfo {
summary: "surface image coordinate is invalid",
hint: Some(
"use finite pixel coordinates inside the captured image; its top-left corner is (0, 0)",
),
exit_code: base.exit_code,
},
(
ErrorCode::CdpFailed | ErrorCode::Timeout | ErrorCode::InvalidParams,
reason::RECORD_START_PAGE_UNREACHABLE,
@@ -377,6 +441,18 @@ mod tests {
assert!(!info.summary.contains("sandbox"));
}
#[test]
fn ref_capability_denied_explains_visual_surface_refs() {
let data = serde_json::json!({ "reason": reason::REF_CAPABILITY_DENIED });
let info = info_for_error(ErrorCode::PermissionDenied, Some(&data));
assert_eq!(info.summary, "snapshot ref does not support this operation");
assert!(
info.hint.unwrap().contains("capture id"),
"expected visual-surface-specific hint"
);
assert_eq!(info.exit_code, 1);
}
#[test]
fn session_busy_overrides_timeout_copy() {
let data = serde_json::json!({ "reason": reason::SESSION_BUSY });
@@ -419,6 +495,25 @@ mod tests {
assert_eq!(info.exit_code, 3);
}
#[test]
fn surface_capture_stale_requests_a_fresh_screenshot() {
let data = serde_json::json!({ "reason": reason::SURFACE_CAPTURE_STALE });
let info = info_for_error(ErrorCode::PermissionDenied, Some(&data));
assert_eq!(
info.summary,
"page state changed since the surface screenshot"
);
assert!(info.hint.unwrap().contains("fresh surface screenshot"));
}
#[test]
fn surface_coordinate_invalid_explains_image_pixel_bounds() {
let data = serde_json::json!({ "reason": reason::SURFACE_COORDINATE_INVALID });
let info = info_for_error(ErrorCode::InvalidParams, Some(&data));
assert_eq!(info.summary, "surface image coordinate is invalid");
assert!(info.hint.unwrap().contains("top-left corner is (0, 0)"));
}
#[test]
fn ref_not_found_overrides_not_found_copy() {
let data = serde_json::json!({ "reason": reason::REF_NOT_FOUND });
@@ -453,4 +548,20 @@ mod tests {
);
assert!(info.hint.unwrap().contains("exactly one"));
}
#[test]
fn focus_target_unresolved_overrides_cdp_copy() {
let data = serde_json::json!({ "reason": reason::FOCUS_TARGET_UNRESOLVED });
let info = info_for_error(ErrorCode::CdpFailed, Some(&data));
assert_eq!(info.summary, "focused frame target could not be determined");
assert!(info.hint.unwrap().contains("--ref"));
}
#[test]
fn input_not_applied_overrides_cdp_copy() {
let data = serde_json::json!({ "reason": reason::INPUT_NOT_APPLIED });
let info = info_for_error(ErrorCode::CdpFailed, Some(&data));
assert_eq!(info.summary, "the page did not retain the requested input");
assert!(info.hint.unwrap().contains("rejecting"));
}
}
+11 -1
View File
@@ -59,7 +59,7 @@ fn run(sock: PathBuf, args: ScreenshotArgs, format: Format) -> Result<(), CliErr
.map_err(CliError::Local)?;
match format {
Format::Json => {
let json = serde_json::json!({
let mut json = serde_json::json!({
"tab_id": reply.tab_id,
"width": reply.width,
"height": reply.height,
@@ -67,6 +67,10 @@ fn run(sock: PathBuf, args: ScreenshotArgs, format: Format) -> Result<(), CliErr
"path": out_path.to_string_lossy(),
"byte_size": bytes.len(),
});
if let Some(capture) = &reply.capture {
json["capture"] = serde_json::to_value(capture)
.map_err(|e| CliError::Local(anyhow::anyhow!(e)))?;
}
println!(
"{}",
serde_json::to_string_pretty(&json)
@@ -75,6 +79,12 @@ fn run(sock: PathBuf, args: ScreenshotArgs, format: Format) -> Result<(), CliErr
}
Format::Human => {
println!("{}", out_path.display());
if let Some(capture) = &reply.capture {
println!(
"capture={} surface={} coordinate_space={} expires_at={}",
capture.id, capture.surface_ref, capture.coordinate_space, capture.expires_at
);
}
print_dialog_summaries(&reply.dialogs);
}
}
+23
View File
@@ -188,6 +188,29 @@ fn parses_click_count_alias() {
assert_eq!(args.click_count, 2);
}
#[test]
fn parses_surface_capture_image_coordinates() {
let cli = parse(&[
"bsk",
"click",
"@e1",
"--session",
"s1",
"--capture",
"sc_test",
"--image-x",
"160.5",
"--image-y",
"-1",
]);
let Command::Click(args) = cli.command else {
panic!("expected click command");
};
assert_eq!(args.capture.as_deref(), Some("sc_test"));
assert_eq!(args.image_x, Some(160.5));
assert_eq!(args.image_y, Some(-1.0));
}
#[test]
fn parses_hover_with_settle() {
let cli = parse(&[
+2
View File
@@ -238,6 +238,7 @@ async fn screenshot_returns_image_base64_with_dimensions() {
height: 600,
format: "png".into(),
tab_id: 7,
capture: None,
dialogs: vec![],
})
.unwrap(),
@@ -286,6 +287,7 @@ async fn screenshot_forwards_ref_to_extension() {
height: 60,
format: "png".into(),
tab_id: 7,
capture: None,
dialogs: vec![],
})
.unwrap(),
+9
View File
@@ -354,6 +354,9 @@ async fn click_round_trips_ref_and_modifiers() {
used_selector: None,
x: 12.5,
y: 34.0,
capture_id: None,
image_x: None,
image_y: None,
dialogs: vec![],
})
.unwrap(),
@@ -373,6 +376,9 @@ async fn click_round_trips_ref_and_modifiers() {
click_count: Some(1),
modifiers: Some(vec![KeyModifier::Ctrl, KeyModifier::Shift]),
timeout_ms: Some(5_000),
capture_id: None,
image_x: None,
image_y: None,
},
)
.await
@@ -610,6 +616,9 @@ async fn m7_tools_propagate_extension_errors() {
click_count: None,
modifiers: None,
timeout_ms: Some(5_000),
capture_id: None,
image_x: None,
image_y: None,
},
)
.await
@@ -16,6 +16,13 @@
}
]
},
"capture_id": {
"description": "Short-lived capture id returned by a visual Surface screenshot.",
"type": [
"string",
"null"
]
},
"click_count": {
"description": "Number of consecutive mouse presses (double-click = 2).",
"type": [
@@ -25,6 +32,22 @@
"format": "uint32",
"minimum": 1.0
},
"image_x": {
"description": "X coordinate in the capture image's pixel coordinate space.",
"type": [
"number",
"null"
],
"format": "double"
},
"image_y": {
"description": "Y coordinate in the capture image's pixel coordinate space.",
"type": [
"number",
"null"
],
"format": "double"
},
"modifiers": {
"type": [
"array",
@@ -8,6 +8,12 @@
"y"
],
"properties": {
"capture_id": {
"type": [
"string",
"null"
]
},
"dialogs": {
"description": "Native JS dialogs observed and auto-handled during this call.",
"type": "array",
@@ -15,6 +21,20 @@
"$ref": "#/definitions/JavaScriptDialogInfo"
}
},
"image_x": {
"type": [
"number",
"null"
],
"format": "double"
},
"image_y": {
"type": [
"number",
"null"
],
"format": "double"
},
"tab_id": {
"type": "integer",
"format": "int64"
@@ -8,6 +8,16 @@
"tab_id"
],
"properties": {
"capture": {
"anyOf": [
{
"$ref": "#/definitions/SurfaceCaptureInfo"
},
{
"type": "null"
}
]
},
"dialogs": {
"type": "array",
"items": {
@@ -109,6 +119,31 @@
"prompt",
"beforeunload"
]
},
"SurfaceCaptureInfo": {
"type": "object",
"required": [
"coordinate_space",
"expires_at",
"id",
"surface_ref"
],
"properties": {
"coordinate_space": {
"type": "string"
},
"expires_at": {
"type": "integer",
"format": "uint64",
"minimum": 0.0
},
"id": {
"type": "string"
},
"surface_ref": {
"type": "string"
}
}
}
}
}
@@ -67,6 +67,15 @@ pub struct ClickParams {
#[serde(default, skip_serializing_if = "Option::is_none")]
#[schemars(range(min = 1))]
pub timeout_ms: Option<u32>,
/// Short-lived capture id returned by a visual Surface screenshot.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub capture_id: Option<String>,
/// X coordinate in the capture image's pixel coordinate space.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image_x: Option<f64>,
/// Y coordinate in the capture image's pixel coordinate space.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image_y: Option<f64>,
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize, JsonSchema)]
@@ -80,6 +89,12 @@ pub struct ClickResult {
/// agents can correlate with a follow-up `tool.screenshot`.
pub x: f64,
pub y: f64,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub capture_id: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image_x: Option<f64>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image_y: Option<f64>,
/// Native JS dialogs observed and auto-handled during this call.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub dialogs: Vec<JavaScriptDialogInfo>,
@@ -288,6 +303,9 @@ mod tests {
click_count: Some(1),
modifiers: Some(vec![KeyModifier::Ctrl]),
timeout_ms: Some(5_000),
capture_id: Some("sc_test".into()),
image_x: Some(160.0),
image_y: Some(90.0),
};
let v = serde_json::to_value(&p).unwrap();
assert_eq!(v.get("ref").and_then(|v| v.as_str()), Some("@e3"));
@@ -208,10 +208,20 @@ pub struct ScreenshotResult {
/// Always `"png"` in v0.1; reserved for future JPEG / WebP support.
pub format: String,
pub tab_id: i64,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub capture: Option<SurfaceCaptureInfo>,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub dialogs: Vec<JavaScriptDialogInfo>,
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize, JsonSchema)]
pub struct SurfaceCaptureInfo {
pub id: String,
pub surface_ref: String,
pub coordinate_space: String,
pub expires_at: u64,
}
#[cfg(test)]
mod tests {
use super::*;
@@ -293,6 +303,12 @@ mod tests {
height: 600,
format: "png".into(),
tab_id: 7,
capture: Some(SurfaceCaptureInfo {
id: "sc_test".into(),
surface_ref: "@e3".into(),
coordinate_space: "capture-image-pixel".into(),
expires_at: 1_700_000_030_000,
}),
dialogs: vec![],
};
let v = serde_json::to_value(&r).unwrap();
+68 -5
View File
@@ -497,7 +497,9 @@ export function registerTools(deps: ToolDeps): () => void {
? "Capture an indented aria-tree snapshot of the session's active tab. Interactive elements " +
"carry @eN refs for browser_click / browser_fill. Prefer browser_observe for a richer semantic view."
: "Produce a semantic VOM observation of the session's active tab (roles, states, perception " +
"probes) with @eN refs for browser_click / browser_fill. Read-only: never submits input.";
"probes) with @eN refs. Visual-only surfaces require image understanding and their refs are " +
"screenshot-only; keep using any DOM/AX semantics rendered alongside them. " +
"Read-only: never submits input.";
register(
defineTool({
name,
@@ -569,7 +571,8 @@ export function registerTools(deps: ToolDeps): () => void {
name: "browser_click",
description:
"Click an element in the session's active tab. Target is a snapshot ref (@e3) from the " +
"last browser_snapshot/browser_observe, or a CSS selector.",
"last browser_snapshot/browser_observe, or a CSS selector. A visual Surface requires the " +
"captureId and image coordinates returned by browser_screenshot.",
parameters: {
target: {
type: "string",
@@ -586,6 +589,23 @@ export function registerTools(deps: ToolDeps): () => void {
type: "integer",
description: "Number of consecutive presses (double-click = 2).",
},
modifiers: {
type: "array",
items: { type: "string", enum: ["alt", "ctrl", "meta", "shift"] },
description: "Keyboard modifiers held during the click.",
},
captureId: {
type: "string",
description: "Short-lived Surface capture id returned by browser_screenshot.",
},
imageX: {
type: "number",
description: "X coordinate in capture-image pixels; requires captureId and imageY.",
},
imageY: {
type: "number",
description: "Y coordinate in capture-image pixels; requires captureId and imageX.",
},
},
output: {
schema: {
@@ -596,6 +616,7 @@ export function registerTools(deps: ToolDeps): () => void {
tabId: { type: "integer", required: true },
x: { type: "number", required: true },
y: { type: "number", required: true },
captureId: { type: "string" },
},
},
render: (_args, value) => [
@@ -607,17 +628,44 @@ export function registerTools(deps: ToolDeps): () => void {
},
async execute(args, exec) {
if (args.target.trim().length === 0) throw new Error("target must be a non-empty string");
const pointArgCount =
Number(args.captureId !== undefined) +
Number(args.imageX !== undefined) +
Number(args.imageY !== undefined);
if (pointArgCount !== 0 && pointArgCount !== 3) {
throw new Error("captureId, imageX, and imageY must be given together");
}
const sessionId = registry.resolve(args.session, "browser_click");
const cmdArgs = ["click", "--session", sessionId];
if (args.button !== undefined) cmdArgs.push("--button", args.button);
if (args.clickCount !== undefined) cmdArgs.push("--click-count", String(args.clickCount));
if (args.modifiers !== undefined && args.modifiers.length > 0) {
cmdArgs.push("--modifiers", args.modifiers.join(","));
}
if (args.captureId !== undefined) {
cmdArgs.push(
"--capture",
args.captureId,
"--image-x",
String(args.imageX),
"--image-y",
String(args.imageY),
);
}
cmdArgs.push(args.target);
const reply = (await runBsk(deps, exec, cmdArgs, "click", sessionId)) as {
tab_id: number;
x: number;
y: number;
capture_id?: string;
};
return {
session: sessionId,
tabId: reply.tab_id,
x: reply.x,
y: reply.y,
...(reply.capture_id !== undefined ? { captureId: reply.capture_id } : {}),
};
return { session: sessionId, tabId: reply.tab_id, x: reply.x, y: reply.y };
},
presentCall: (args) => ({
card: "terminal",
@@ -760,12 +808,17 @@ export function registerTools(deps: ToolDeps): () => void {
name: "browser_screenshot",
description:
"Capture a PNG screenshot of the session's active tab, or crop to a snapshot ref element. " +
"This is the supported operation for visual surface refs emitted by browser_observe. Only use " +
"it to interpret a visual-only surface when you can inspect image output. If you lack multimodal " +
"or image-reading capability, tell the user to switch to a model with image understanding; do " +
"not guess content or coordinates. " +
"Returns the image itself when the deployment supports image input, otherwise a file path.",
parameters: {
session: SESSION_PARAM,
ref: {
type: "string",
description: "Snapshot ref (@e3) from the last snapshot/observe; crops to that element.",
description:
"Ref (@e3) from the last snapshot/observe; crops to that DOM element or visual surface.",
},
},
output: {
@@ -779,6 +832,8 @@ export function registerTools(deps: ToolDeps): () => void {
width: { type: "integer", required: true },
height: { type: "integer", required: true },
byteSize: { type: "integer", required: true },
captureId: { type: "string" },
captureExpiresAt: { type: "integer" },
image: {
type: "object",
additionalProperties: false,
@@ -798,7 +853,11 @@ export function registerTools(deps: ToolDeps): () => void {
value.image !== undefined
? `[session ${value.session}] screenshot of tab ${value.tabId} (${value.width}x${value.height}px)`
: `[session ${value.session}] screenshot saved to ${value.path} (${value.width}x${value.height}px, ${value.byteSize} bytes) — this deployment cannot inline images; read the file to view it`;
const blocks: ContentBlock[] = [{ type: "text", text }];
const captureText =
value.captureId !== undefined
? ` Surface capture ${value.captureId} uses capture-image-pixel coordinates and expires at ${value.captureExpiresAt}.`
: "";
const blocks: ContentBlock[] = [{ type: "text", text: text + captureText }];
if (value.image !== undefined) {
blocks.push({
type: "image",
@@ -837,6 +896,7 @@ export function registerTools(deps: ToolDeps): () => void {
height: number;
path: string;
byte_size: number;
capture?: { id: string; expires_at: number };
};
writtenPath = reply.path;
const data = await readFile(reply.path);
@@ -850,6 +910,9 @@ export function registerTools(deps: ToolDeps): () => void {
width: reply.width,
height: reply.height,
byteSize: reply.byte_size,
...(reply.capture !== undefined
? { captureId: reply.capture.id, captureExpiresAt: reply.capture.expires_at }
: {}),
...(ref !== undefined
? {
image: {
@@ -377,12 +377,12 @@ describe("interaction tools", () => {
emulate: { tab_id: 7, cleared: false },
};
it("browser_click maps target, button, and click count", async () => {
it("browser_click maps target, button, click count, and modifiers", async () => {
const { tools, calls } = setup(responses);
await startSession(tools);
const click = tools.get("browser_click");
const value = (await click?.execute(
{ target: "@e1", button: "right", clickCount: 2 },
{ target: "@e1", button: "right", clickCount: 2, modifiers: ["ctrl", "shift"] },
makeExec(),
)) as { session: string; x: number; y: number };
expect(value).toMatchObject({ session: "s1", x: 10, y: 20 });
@@ -394,6 +394,43 @@ describe("interaction tools", () => {
"right",
"--click-count",
"2",
"--modifiers",
"ctrl,shift",
"@e1",
]);
});
it("browser_click forwards a complete Surface capture coordinate transaction", async () => {
const { tools, calls } = setup({
...responses,
click: {
tab_id: 7,
used_ref: "e1",
x: 110,
y: 70,
capture_id: "sc_test",
image_x: 200,
image_y: 100,
},
});
await startSession(tools);
const click = tools.get("browser_click");
const value = await click?.execute(
{ target: "@e1", captureId: "sc_test", imageX: 200, imageY: 100 },
makeExec(),
);
expect(value).toMatchObject({ captureId: "sc_test", x: 110, y: 70 });
expect(calls[1].args).toEqual([
"click",
"--session",
"s1",
"--capture",
"sc_test",
"--image-x",
"200",
"--image-y",
"100",
"@e1",
]);
});
@@ -814,6 +851,32 @@ describe("browser_screenshot", () => {
expect(rendered?.every((block) => block.type === "text")).toBe(true);
});
it("returns Surface capture metadata alongside the screenshot", async () => {
const path = pngFile();
const { tools } = setup({
"session start": START_REPLY("s1"),
screenshot: {
tab_id: 7,
width: 800,
height: 600,
format: "png",
path,
byte_size: 8,
capture: { id: "sc_test", expires_at: 1700000030000 },
},
});
await startSession(tools);
const screenshot = tools.get("browser_screenshot");
const value = await screenshot?.execute({ ref: "@e1" }, makeExec());
expect(value).toMatchObject({
captureId: "sc_test",
captureExpiresAt: 1700000030000,
});
const rendered = screenshot?.output.render({ session: "s1" }, value as never);
expect(rendered?.[0]).toMatchObject({ type: "text", text: expect.stringContaining("sc_test") });
});
it("commits the image through the attachment store on an image-capable route", async () => {
const path = pngFile();
const services = {
+138
View File
@@ -29,6 +29,66 @@ function coreRefs(refs: ReturnType<typeof renderVom>["refs"]) {
}
describe("renderVom single-layer page", () => {
it("renders visual surfaces as screenshot-only refs", () => {
const input = scene([
node({ id: 1, role: "RootWebArea", frameId: "main" }),
node({ id: 2, parentId: 1, role: "Iframe", frameId: "main", backendNodeId: 20 }),
]);
input.visualSurfaces = [
{
parentId: 2,
backendNodeId: 99,
frameId: "child",
renderingKind: "canvas",
visibleRect: { x: 10, y: 20, w: 800, h: 500 },
label: "Data grid",
memberCount: 2,
},
];
const out = renderVom(input);
expect(out.text).toContain(
'@e1 surface "Data grid" [rendering=canvas; layers=2; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
);
expect(out.refs).toContainEqual(
expect.objectContaining({
ref: "e1",
backendNodeId: 99,
kind: "surface",
visibleRect: { x: 10, y: 20, w: 800, h: 500 },
capabilities: ["screenshot"],
}),
);
});
it("renders an unnamed visual surface with a stable generic label", () => {
const input = scene([node({ id: 1, role: "RootWebArea", frameId: "main" })]);
input.visualSurfaces = [
{
parentId: 1,
backendNodeId: 99,
frameId: "main",
renderingKind: "canvas",
visibleRect: { x: 10, y: 20, w: 800, h: 500 },
memberCount: 1,
},
];
const out = renderVom(input);
expect(out.text).toContain(
'@e1 surface "canvas visual surface" [rendering=canvas; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
);
expect(out.refs).toContainEqual(
expect.objectContaining({
ref: "e1",
name: "canvas visual surface",
kind: "surface",
capabilities: ["screenshot"],
}),
);
});
it("does not derive handle context across frame scopes", () => {
const out = renderVom(
scene([
@@ -333,6 +393,84 @@ describe("renderVom single-layer page", () => {
expect(coreRefs(out.refs)).toEqual([{ ref: "e1", backendNodeId: 2 }]);
});
it("does not treat implementation CSS classes as control names", () => {
const out = renderVom(
scene([
node({ id: 1, role: "RootWebArea", name: "Doc" }),
node({
id: 2,
parentId: 1,
role: "generic",
cursor: "pointer",
attrs: { onclick: "handleClick()" },
rect: { x: 20, y: 20, w: 40, h: 40 },
}),
node({
id: 3,
parentId: 2,
role: "img",
tag: "svg",
attrs: { class: "kocomz" },
}),
]),
);
expect(out.text).not.toContain("kocomz");
expect(out.refs).toEqual([]);
});
it("recovers icon controls only from explicit semantic icon evidence", () => {
const out = renderVom(
scene([
node({ id: 1, role: "RootWebArea", name: "Doc" }),
node({
id: 2,
parentId: 1,
role: "generic",
cursor: "pointer",
attrs: { onclick: "handleFilter()" },
rect: { x: 20, y: 20, w: 40, h: 40 },
}),
node({
id: 3,
parentId: 2,
role: "img",
tag: "svg",
attrs: { "aria-label": "Filter rows", class: "kocomz" },
}),
]),
);
expect(out.text).toContain('@e1 button "Filter rows"');
expect(coreRefs(out.refs)).toEqual([{ ref: "e1", backendNodeId: 2 }]);
});
it("keeps a semantic image as evidence for its clickable wrapper", () => {
const out = renderVom(
scene([
node({ id: 1, role: "RootWebArea", name: "Doc" }),
node({
id: 2,
parentId: 1,
role: "generic",
cursor: "pointer",
rect: { x: 20, y: 20, w: 40, h: 40 },
}),
node({
id: 3,
parentId: 2,
role: "img",
name: "Account",
cursor: "pointer",
tag: "div",
}),
]),
);
expect(out.text).toContain('@e1 button "Account"');
expect(coreRefs(out.refs)).toEqual([{ ref: "e1", backendNodeId: 2 }]);
});
it("keeps the deepest custom control when wrapper and child both look clickable", () => {
const out = renderVom(
scene([
+8 -1
View File
@@ -1,4 +1,9 @@
export { applyVomInteractionRecovery, isVomReferenceNode, renderVom } from "./render";
export {
applyVomInteractionRecovery,
isVomReferenceNode,
isVomStructuralRole,
renderVom,
} from "./render";
export type {
ActiveScopeBlock,
BlockingLayer,
@@ -10,6 +15,8 @@ export type {
VomNode,
VomOptions,
VomRef,
VomRefCapability,
VomResult,
VomScene,
VomVisualSurface,
} from "./types";
+107 -17
View File
@@ -9,6 +9,7 @@ import type {
VomOptions,
VomResult,
VomScene,
VomVisualSurface,
} from "./types";
const SKIP_ROLES = new Set(["generic", "none", "presentation", "inlinetextbox"]);
@@ -75,6 +76,10 @@ const STRUCTURAL_ROLES = new Set([
"webarea",
]);
export function isVomStructuralRole(role: string | undefined): boolean {
return STRUCTURAL_ROLES.has(role?.toLowerCase() ?? "");
}
const SENSITIVE_MASK = "•••";
const DEFAULT_MAX_DEPTH = Number.POSITIVE_INFINITY;
const DEFAULT_MAX_TOKENS = Number.POSITIVE_INFINITY;
@@ -193,13 +198,16 @@ function shouldRender(node: VomNode): boolean {
const role = normalizedRole(node);
if (SKIP_ROLES.has(role)) return false;
if (INTERACTIVE_ROLES.has(role)) return true;
if (STRUCTURAL_ROLES.has(role)) return true;
if (isVomStructuralRole(role)) return true;
return cleaned(node.name) !== undefined;
}
export function isVomReferenceNode(node: VomNode): boolean {
return INTERACTIVE_ROLES.has(normalizedRole(node)) || isUrlBearingStructuralAction(node);
return (
node.referenceable !== false &&
(INTERACTIVE_ROLES.has(normalizedRole(node)) || isUrlBearingStructuralAction(node))
);
}
function hasRecoveryHandler(node: VomNode): boolean {
@@ -219,14 +227,30 @@ function isContentEditable(node: VomNode): boolean {
return contentEditable === "true" || contentEditable === "plaintext-only";
}
function iconKeyword(value: string | undefined): string | undefined {
const cleanedValue = cleaned(value);
if (!cleanedValue) return undefined;
const last = cleanedValue
.split(/[#/.\s:_-]+/)
const ICON_REFERENCE_MARKERS = new Set(["glyph", "icon", "icons", "symbol"]);
const ICON_REFERENCE_DECORATORS = new Set(["fill", "filled", "line", "outline", "outlined"]);
function iconReferenceName(value: string | undefined): string | undefined {
const reference = cleaned(value);
if (!reference) return undefined;
const fragment = reference.includes("#") ? reference.slice(reference.lastIndexOf("#") + 1) : "";
const tokens = (fragment || reference)
?.split(/[#/.\s:_-]+/)
.filter(Boolean)
.pop();
return last && /^[a-z][a-z0-9_-]{1,32}$/i.test(last) ? last.toLowerCase() : undefined;
.map((token) => token.toLowerCase());
if (tokens.length === 0) return undefined;
if (fragment) {
const semanticTokens = tokens.filter(
(token) => !ICON_REFERENCE_MARKERS.has(token) && !ICON_REFERENCE_DECORATORS.has(token),
);
return semanticTokens.length > 0 ? semanticTokens.join(" ") : undefined;
}
const marker = tokens.findLastIndex((token) => ICON_REFERENCE_MARKERS.has(token));
if (marker < 0) return undefined;
const semanticTokens = tokens
.slice(marker + 1)
.filter((token) => !ICON_REFERENCE_DECORATORS.has(token));
return semanticTokens.length > 0 ? semanticTokens.join(" ") : undefined;
}
function iconHintFromSubtree(
@@ -238,12 +262,12 @@ function iconHintFromSubtree(
for (const child of children.get(node.id) ?? []) {
const attrs = child.attrs ?? {};
const hint =
iconKeyword(attrs["aria-label"]) ??
iconKeyword(attrs.title) ??
iconKeyword(attrs.href) ??
iconKeyword(attrs["xlink:href"]) ??
iconKeyword(attrs.class) ??
iconKeyword(child.text);
cleaned(attrs["aria-label"]) ??
cleaned(attrs.title) ??
(normalizedRole(child) === "img" ? cleaned(child.name) : undefined) ??
(["img", "svg", "use"].includes(normalizedTag(child))
? (iconReferenceName(attrs.href) ?? iconReferenceName(attrs["xlink:href"]))
: undefined);
if (hint) return hint;
const nested = iconHintFromSubtree(child, children, depth + 1);
if (nested) return nested;
@@ -269,6 +293,7 @@ function recoveredRole(
node: VomNode,
children?: Map<number | null, VomNode[]>,
): string | undefined {
const currentRole = normalizedRole(node);
const explicitRole = node.attrs?.role?.toLowerCase() ?? "";
const hasHandler = hasRecoveryHandler(node);
const focusable = isFocusable(node);
@@ -290,7 +315,9 @@ function recoveredRole(
: "button";
}
if (hasHandler && hasName) return "button";
if (node.cursor === "pointer" && hasName) return "button";
if ((!currentRole || SKIP_ROLES.has(currentRole)) && node.cursor === "pointer" && hasName) {
return "button";
}
return undefined;
}
@@ -711,6 +738,53 @@ interface RenderState {
duplicateRefNames: Set<string>;
surfaceMap: Map<number, CondSurface>;
scopeMap: Map<number, ActiveScopeBlock>;
visualSurfaces: Map<number | null, VomVisualSurface[]>;
}
function groupedByParent<T extends { parentId: number | null }>(
items: T[],
): Map<number | null, T[]> {
const grouped = new Map<number | null, T[]>();
for (const item of items) {
const siblings = grouped.get(item.parentId) ?? [];
siblings.push(item);
grouped.set(item.parentId, siblings);
}
return grouped;
}
function emitVisualEntries(parentId: number | null, depth: number, state: RenderState): void {
if (state.stopped) return;
for (const surface of state.visualSurfaces.get(parentId) ?? []) {
if (depth > state.maxDepth) {
state.truncated = true;
continue;
}
const ref = `e${state.nextRef}`;
const label = cleaned(surface.label) ?? `${surface.renderingKind} visual surface`;
const layers = surface.memberCount > 1 ? `; layers=${surface.memberCount}` : "";
const line = `${" ".repeat(depth)}@${ref} surface ${JSON.stringify(label)} [rendering=${surface.renderingKind}${layers}; visual-only; requires=image-understanding; use: bsk screenshot --ref @${ref}]`;
const nextTokens = state.tokens + estimateTokens(line);
if (nextTokens > state.maxTokens) {
state.truncated = true;
state.stopped = true;
return;
}
state.lines.push(line);
state.tokens = nextTokens;
state.refs.push({
ref,
backendNodeId: surface.backendNodeId,
frameId: surface.frameId,
visibleRect: surface.visibleRect,
role: "surface",
name: label,
kind: "surface",
capabilities: ["screenshot"],
line: state.lines.length - 1,
});
state.nextRef += 1;
}
}
function emitActiveScopeBlock(scope: ActiveScopeBlock, depth: number, state: RenderState): void {
@@ -786,6 +860,8 @@ function renderTree(
...(node.role ? { role: node.role } : {}),
...(name ? { name } : {}),
...(context.length > 0 ? { ctx: context.join(" > ") } : {}),
kind: "dom",
capabilities: ["interact", "screenshot"],
line: state.lines.length - 1,
});
state.nextRef += 1;
@@ -795,10 +871,12 @@ function renderTree(
if (scope) emitActiveScopeBlock(scope, depth + 1, state);
if ((ref && shouldSkipRedundantRefChildren(node)) || shouldSkipRedundantChildren(node, state)) {
emitVisualEntries(node.id, depth + 1, state);
continue;
}
renderTree(children, node.id, depth + 1, state);
}
emitVisualEntries(parentId, depth, state);
}
function renderNodes(
@@ -807,6 +885,7 @@ function renderNodes(
initialLines: string[],
surfaces: CondSurface[] = [],
activeScopeBlocks: ActiveScopeBlock[] = [],
visualSurfaces: VomVisualSurface[] = [],
): RenderState {
const children = buildChildren(nodes);
const state: RenderState = {
@@ -825,6 +904,7 @@ function renderNodes(
duplicateRefNames: duplicateReferenceNames(nodes),
surfaceMap: new Map(surfaces.map((surface) => [surface.triggerId, surface])),
scopeMap: new Map(activeScopeBlocks.map((scope) => [scope.triggerId, scope])),
visualSurfaces: groupedByParent(visualSurfaces),
};
renderTree(children, null, 1, state);
@@ -1030,7 +1110,16 @@ function renderDoubleLayer(scene: VomScene, layer: BlockingLayer, options: VomOp
"@layers 2 focus=L1",
`L1 ${layer.kind} cover=${Math.round(layer.coverage * 100)}%`,
];
const state = renderNodes(visibleNodes, options, header, scene.surfaces, scene.activeScopeBlocks);
const visibleSurface = (parentId: number | null): boolean =>
parentId === null || included.has(parentId);
const state = renderNodes(
visibleNodes,
options,
header,
scene.surfaces,
scene.activeScopeBlocks,
scene.visualSurfaces?.filter((surface) => visibleSurface(surface.parentId)),
);
state.lines.push(renderPageOcclusionLine(hiddenCount));
return {
@@ -1058,6 +1147,7 @@ export function renderVom(scene: VomScene, options: VomOptions = {}): VomResult
],
scene.surfaces,
scene.activeScopeBlocks,
scene.visualSurfaces,
);
return {
+20
View File
@@ -24,6 +24,8 @@ export interface VomNode {
backendNodeId?: number;
frameId?: string;
contextScopeId?: string;
/** False for semantic-only nodes that cannot be addressed through CDP. */
referenceable?: boolean;
role?: string;
name?: string;
@@ -59,6 +61,8 @@ export interface VomScene {
rootFrameId?: string;
surfaces?: CondSurface[];
activeScopeBlocks?: ActiveScopeBlock[];
/** Non-semantic rendered regions discovered alongside the AX/DOM tree. */
visualSurfaces?: VomVisualSurface[];
}
export interface VomOptions {
@@ -92,6 +96,22 @@ export interface VomRef {
ref: string;
backendNodeId: number;
frameId?: string;
/** Observation-time top-viewport crop for screenshot-only surfaces. */
visibleRect?: Rect;
kind?: "dom" | "surface";
capabilities?: VomRefCapability[];
}
export type VomRefCapability = "interact" | "screenshot";
export interface VomVisualSurface {
parentId: number | null;
backendNodeId: number;
frameId: string;
renderingKind: "canvas";
visibleRect: Rect;
label?: string;
memberCount: number;
}
export interface RenderedRef extends VomRef {
+12 -2
View File
@@ -80,6 +80,16 @@ Prefer `@eN` refs from the latest snapshot over raw CSS selectors. Use `--ref` /
When VOM renders `[hover first: …]` on an element, the listed items are not currently clickable refs. Run `bsk hover <that-ref> --session <id>`, then immediately run `bsk snapshot` or `bsk observe` again and click the newly visible menu item ref. Do not click the trigger itself unless the user explicitly wants the trigger action.
When `bsk observe` renders `@eN surface ... [visual-only; requires=image-understanding; ...]`, the ref identifies rendered canvas content that is not represented by the text observation, not an interactable DOM control. Keep using any reliable DOM/AX text and controls that appear alongside it. If you lack multimodal or image-reading capability, do not take a screenshot and pretend to know its contents, and never guess coordinates; tell the user that they need to switch to a model with image-understanding capability.
If you can actually inspect image output, use `bsk screenshot --ref @eN --session <id>` to obtain the visible crop and its short-lived, single-use Surface capture id. Only when the task requires a point action and the image provides a clear target, bind that exact screenshot to the same general click command:
```bash
bsk click @eN --capture <capture-id> --image-x <px> --image-y <px> --session <id>
```
Coordinates are pixels in the returned capture image, not viewport CSS coordinates. Re-observing, navigating, scrolling, resizing, zooming, changing Frame projection, expiry, or reusing the capture makes the action fail; take a new Surface screenshot instead of adjusting or retrying coordinates. A point click does not reveal Canvas semantics and must not be followed by an assumed fill/press workflow. Without all three capture arguments, visual Surface refs remain screenshot-only and click/fill/hover/select reject them.
## Observation priority
Start with `bsk observe` to understand page structure, text, controls, element refs, and conditional hover/focus surfaces. Use `bsk snapshot` only when you need the stricter static accessibility tree or VOM is insufficient. Only escalate to raw HTML or screenshots when the latest observation cannot answer the question:
@@ -174,7 +184,7 @@ bsk emulate --session <id> --off
| `bsk snapshot` | First-choice static page understanding: accessibility tree with `@eN` element refs |
| `bsk observe` | Semantic VOM observation with bounded perception probes for conditional surfaces |
| `bsk get-html` | Raw HTML dump after snapshot is insufficient (high token cost) |
| `bsk screenshot` | PNG capture after snapshot is insufficient: full visible tab, or `--ref @eN` to crop to one element (`--out` path optional) |
| `bsk screenshot` | PNG capture after snapshot is insufficient: full visible tab, or `--ref @eN` to crop to one element (`--out` path optional); Surface crops return a short-lived capture id |
### Console & network debugging (read-only; require `--session`)
@@ -200,7 +210,7 @@ Both capture from the moment the tab is attached and read a bounded per-tab buff
| Command | Summary |
|---------|---------|
| `bsk click <ref-or-selector>` | Click element (`--button`, `--click-count`, `--modifiers`) |
| `bsk click <ref-or-selector>` | Click a DOM element (`--button`, `--click-count`, `--modifiers`), or perform one screenshot-bound Surface point click with `--capture`, `--image-x`, and `--image-y` |
| `bsk hover <ref-or-selector>` | Move the mouse to an element and wait for hover UI to settle (`--settle`, `--modifiers`) |
| `bsk fill <ref-or-selector> --value <text>` | Clear and type into input |
| `bsk select <ref-or-selector> --value <v>` | Set `<select>` option(s) by `value` (repeat `--value` for multi-select) |