refactor(observation): isolate document processing from capture orchestration

This commit is contained in:
Ljy-0827
2026-09-09 15:54:41 +08:00
committed by drakezhang
parent 36d0d91419
commit 388b3ae2d5
17 changed files with 1273 additions and 2298 deletions
File diff suppressed because it is too large Load Diff
+222 -11
View File
@@ -1,4 +1,3 @@
import type { CapturedSceneInput } from "./vom/facts";
// Observation handlers — `tool.snapshot`, `tool.get_html`, `tool.screenshot`,
// and semantic `tool.observe` (design §7). Each handler resolves the target
// tab (defaulting to the Agent Window's active tab when omitted) and
@@ -36,6 +35,7 @@ import { attachDialogs, markDialogCursor } from "./dialogs";
import { rpcError } from "./errors";
import { resolveNodeGeometry } from "./frame-geometry";
import { screenshotPageRect } from "./geometry/coordinate-types";
import { cssViewport, GeometryContext } from "./geometry/frame-context";
import {
type ChromeTabsApi,
enforceToolTargetScope,
@@ -49,9 +49,15 @@ import {
type ToolEffect,
} from "./shared";
import { resolveSnapshotRef } from "./snapshot-ref";
import { type CapturedNode, type CapturedSurfaceProbe, probeHoverSurfaces } from "./vom/capture";
import { captureObservationFacts, semanticCapture } from "./vom/capture-coordinator";
import type { FrameDocument as CapturedFrameDocument } from "./vom/frame-document";
import {
type CapturedNode,
type CapturedSurfaceProbe,
type CapturedViewModel,
captureViewModel,
collectOverlayExcludedBackendIds,
probeHoverSurfaces,
} from "./vom/capture";
import { type CapturedFrameDocument, captureFrameData } from "./vom/frame-capture";
import { withOverlayBypass } from "./vom/hover-perception";
import { probeTooltipNames } from "./vom/name-enrichment";
import {
@@ -525,7 +531,7 @@ function buildActiveScopeBlocks(nodes: VomNode[], signals: VomNodeDomSignals): A
function buildConditionalSurfaces(
nodes: VomNode[],
captured: CapturedSceneInput,
captured: CapturedViewModel,
probes: CapturedSurfaceProbe[],
): CondSurface[] {
if (probes.length === 0) return [];
@@ -655,9 +661,163 @@ export interface BuildVomSceneOptions {
export type VomFrameDocument = CapturedFrameDocument<CdpAxNode>;
function legacyFrameDocuments(
axNodes: CdpAxNode[],
captured: CapturedViewModel,
pageUrl?: string,
rootTarget: VomFrameDocument["target"] = { tabId: 0 },
): VomFrameDocument[] {
const rootFrameId = captured.rootFrameId ?? "root";
const documents: VomFrameDocument[] = [
{
frameId: rootFrameId,
contextScopeId: rootFrameId,
target: rootTarget,
...(pageUrl ? { url: pageUrl } : {}),
axNodes: [],
domNodes: captured.nodes.map((node) => ({ ...node, frameId: node.frameId ?? rootFrameId })),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(rootFrameId),
},
];
const pending = [...captured.iframeNodes.entries()];
let progress = true;
let nextSyntheticFrame = 1;
while (pending.length > 0 && progress) {
progress = false;
for (let index = pending.length - 1; index >= 0; index -= 1) {
const [ownerBackendNodeId, domNodes] = pending[index];
const parent = documents.find((document) =>
document.domNodes.some((node) => node.backendNodeId === ownerBackendNodeId),
);
if (!parent) continue;
const frameId =
domNodes.find((node) => node.frameId)?.frameId ?? `legacy-frame-${nextSyntheticFrame++}`;
documents.push({
frameId,
parentFrameId: parent.frameId,
ownerBackendNodeId,
contextScopeId: frameId,
target: parent.target,
axNodes: [],
domNodes: domNodes.map((node) => ({ ...node, frameId: node.frameId ?? frameId })),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(frameId),
});
pending.splice(index, 1);
progress = true;
}
}
const documentByFrameId = new Map(documents.map((document) => [document.frameId, document]));
const backendFrame = new Map<number, string>();
const childFrameByOwner = new Map<number, string>();
for (const document of documents) {
if (document.ownerBackendNodeId !== undefined) {
childFrameByOwner.set(document.ownerBackendNodeId, document.frameId);
}
for (const node of document.domNodes) backendFrame.set(node.backendNodeId, document.frameId);
}
const axById = new Map(axNodes.map((node) => [node.nodeId, node]));
const ownership = new Map<string, string>();
const resolving = new Set<string>();
const frameForAx = (node: CdpAxNode): string => {
const cached = ownership.get(node.nodeId);
if (cached) return cached;
let frameId: string | undefined;
if (node.frameId && documentByFrameId.has(node.frameId)) frameId = node.frameId;
if (!frameId && typeof node.backendDOMNodeId === "number") {
frameId = backendFrame.get(node.backendDOMNodeId);
}
if (!frameId && node.parentId && !resolving.has(node.nodeId)) {
const parent = axById.get(node.parentId);
if (parent) {
frameId =
typeof parent.backendDOMNodeId === "number"
? childFrameByOwner.get(parent.backendDOMNodeId)
: undefined;
if (!frameId) {
resolving.add(node.nodeId);
frameId = frameForAx(parent);
resolving.delete(node.nodeId);
}
}
}
frameId ??= rootFrameId;
ownership.set(node.nodeId, frameId);
return frameId;
};
for (const node of axNodes) frameForAx(node);
for (const node of axNodes) {
const frameId = ownership.get(node.nodeId) ?? rootFrameId;
const document = documentByFrameId.get(frameId) ?? documents[0];
document.axNodes.push({
...node,
frameId,
...(node.parentId && ownership.get(node.parentId) === frameId
? { parentId: node.parentId }
: { parentId: undefined }),
...(node.childIds
? { childIds: node.childIds.filter((childId) => ownership.get(childId) === frameId) }
: {}),
});
}
return documents;
}
function withLegacyBackendIds(scene: VomScene): VomScene {
const used = new Set<number>();
const idMap = new Map<number, number>();
let nextVirtualId = -1;
for (const node of scene.nodes) {
const preferred = node.backendNodeId;
const id = preferred !== undefined && !used.has(preferred) ? preferred : nextVirtualId--;
used.add(id);
idMap.set(node.id, id);
}
return {
...scene,
nodes: scene.nodes.map((node) => ({
...node,
id: idMap.get(node.id) as number,
parentId: node.parentId === null ? null : (idMap.get(node.parentId) ?? null),
...(node.domParentId !== undefined
? { domParentId: node.domParentId === null ? null : (idMap.get(node.domParentId) ?? null) }
: {}),
...(node.domAncestorIds
? { domAncestorIds: node.domAncestorIds.flatMap((id) => idMap.get(id) ?? []) }
: {}),
})),
...(scene.surfaces
? {
surfaces: scene.surfaces.map((surface) => ({
...surface,
triggerId: idMap.get(surface.triggerId) ?? surface.triggerId,
})),
}
: {}),
...(scene.activeScopeBlocks
? {
activeScopeBlocks: scene.activeScopeBlocks.map((block) => ({
...block,
triggerId: idMap.get(block.triggerId) ?? block.triggerId,
})),
}
: {}),
};
}
export function buildVomScene(
axNodes: CdpAxNode[],
captured: CapturedViewModel,
options: BuildVomSceneOptions = {},
): VomScene {
return withLegacyBackendIds(
buildFrameVomScene(legacyFrameDocuments(axNodes, captured, options.pageUrl), captured, options),
);
}
export function buildFrameVomScene(
documents: VomFrameDocument[],
captured: CapturedSceneInput,
captured: CapturedViewModel,
options: BuildVomSceneOptions = {},
): VomScene {
const scene = buildSemanticVomScene({
@@ -673,7 +833,7 @@ export function buildFrameVomScene(
function attachCapturedSceneAnnotations(
scene: VomScene,
documents: VomFrameDocument[],
captured: CapturedSceneInput,
captured: CapturedViewModel,
surfaceProbes: CapturedSurfaceProbe[],
): VomScene {
const rootDocument = documents.find((document) => document.frameId === scene.rootFrameId);
@@ -823,6 +983,45 @@ export async function handleGetHtml(
}
}
function emptyCapturedViewModel(viewport = { width: 0, height: 0 }): CapturedViewModel {
return { viewport, nodes: [], iframeNodes: new Map(), excludedBackendNodeIds: new Set() };
}
async function fallbackCapturedViewModel(
cdp: CdpRunner,
tabId: number,
geometry: GeometryContext,
signal?: AbortSignal,
): Promise<CapturedViewModel> {
throwIfAborted(signal, "observation");
let viewport = { width: 0, height: 0 };
try {
const metrics = await geometry.layoutMetrics({ tabId });
throwIfAborted(signal, "observation");
const source = cssViewport(metrics);
viewport = { width: source.width, height: source.height };
} catch (error) {
if (isAbortError(error)) throw error;
}
const excludedBackendNodeIds = await collectOverlayExcludedBackendIds(cdp, tabId, signal);
throwIfAborted(signal, "observation");
return { ...emptyCapturedViewModel(viewport), excludedBackendNodeIds };
}
async function captureForVom(
cdp: CdpRunner,
tabId: number,
options: CaptureVomObservationOptions,
geometry: GeometryContext,
): Promise<CapturedViewModel> {
try {
return await captureViewModel(cdp, tabId, { signal: options.signal, geometry });
} catch (error) {
if (isAbortError(error)) throw error;
return fallbackCapturedViewModel(cdp, tabId, geometry, options.signal);
}
}
export interface HoverProbeOutcome {
/** Whether any active hover was dispatched during this observation. */
performed: boolean;
@@ -855,7 +1054,7 @@ const NO_HOVER_PROBES: HoverProbeOutcome = {
async function runHoverProbes(
cdp: CdpRunner,
tabId: number,
captured: CapturedSceneInput,
captured: CapturedViewModel,
documents: VomFrameDocument[],
staticSemantics: ReturnType<typeof resolveSemanticGraph>,
options: CaptureVomObservationOptions,
@@ -894,9 +1093,21 @@ export async function captureVomObservation(
throwIfAborted(options.signal, "observation");
await cdp.ensureAttachedToUrl?.(tabId, url);
throwIfAborted(options.signal, "observation");
const facts = await captureObservationFacts<CdpAxNode>(cdp, tabId, options.signal, url);
const { captured, documents: normalizedDocuments } = semanticCapture(facts);
const geometry = new GeometryContext(cdp, tabId, undefined, options.signal);
const captured = await captureForVom(cdp, tabId, options, geometry);
throwIfAborted(options.signal, "observation");
const documents = await captureFrameData<CdpAxNode>(
cdp,
tabId,
captured,
options.signal,
geometry,
);
throwIfAborted(options.signal, "observation");
const normalizedDocuments =
documents.length === 1 && captured.iframeNodes.size > 0
? legacyFrameDocuments(documents[0].axNodes, captured, url, documents[0].target)
: documents;
const semanticGraph = buildSemanticGraph({
documents: normalizedDocuments,
viewport: captured.viewport,
@@ -926,7 +1137,7 @@ export async function captureVomObservation(
);
// Reserve space using the renderer's character-based token estimate. Like VOM
// headers, this integrity notice remains visible even under a tiny token budget.
const geometryNotice = facts.issues.some((issue) => issue.stage === "geometry")
const geometryNotice = captured.frameGeometryIssues?.length
? "@warning iframe geometry incomplete: some frame content has no top-level coordinates.\n"
: "";
const rendered = renderVom(decoratedScene, {
@@ -1,914 +0,0 @@
import { describe, expect, it, vi } from "vitest";
import type { CdpFrame, CdpTarget } from "@/browser-driver/frame-graph";
import { cdpTargetKey } from "@/browser-driver/frame-graph";
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import { captureObservationFacts, semanticCapture } from "../capture-coordinator";
import { buildSemanticGraph } from "../semantic-graph/build";
import { REQUESTED_STYLES } from "../snapshot";
function fixture(
options: { frames?: CdpFrame[]; fail?: string; omitDocument?: string; overlay?: string } = {},
) {
const frames = options.frames ?? [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "same",
parentFrameId: "main",
ownerBackendNodeId: 3,
target: { tabId: 4 },
},
{
frameId: "nested",
parentFrameId: "same",
ownerBackendNodeId: 13,
target: { tabId: 4 },
},
{
frameId: "remote",
parentFrameId: "main",
ownerBackendNodeId: 4,
target: { tabId: 4, sessionId: "remote" },
},
];
const elements = new Map(
frames.map((frame, i) => [frame.frameId, frame.target.sessionId ? 1 : i * 10 + 1]),
);
const logs: Array<{ target: CdpTarget; method: string; params: Record<string, unknown> }> = [];
const send = vi.fn(
async <T>(target: CdpTarget, method: string, params: object = {}): Promise<T> => {
logs.push({ target, method, params: params as Record<string, unknown> });
const args = params as Record<string, string | number>;
if (options.fail === `${target.sessionId ?? "main"}:${method}`)
throw new Error("fixture failure");
let result: unknown = {};
if (method === "Page.getLayoutMetrics")
result = { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
if (method === "DOMSnapshot.captureSnapshot") {
expect((params as { computedStyles: unknown }).computedStyles).toEqual(REQUESTED_STYLES);
result = {
strings: [
"#document",
"html",
"button",
OVERLAY_HOST_MARKER_ATTR,
"",
"visible",
"1",
"static",
"auto",
],
documents: frames
.filter(
(frame) =>
cdpTargetKey(frame.target) === cdpTargetKey(target) &&
frame.frameId !== options.omitDocument,
)
.map((frame) => {
const element = elements.get(frame.frameId)!;
return {
frameId: frame.frameId,
nodes: {
backendNodeId: [element - 1, element + 10000, element, element + 1],
nodeName: [0, 1, 1, 2],
nodeType: [9, 10, 1, 1],
parentIndex: [-1, 0, 0, 2],
attributes: [[], [], [], frame.frameId === options.overlay ? [3, 4] : []],
},
layout: {
nodeIndex: [2, 3],
bounds: [
[0, 0, 1000, 800],
[10, 20, 100, 40],
],
styles: [
[7, 8, 8, 5, 6],
[7, 8, 8, 5, 6],
],
},
};
}),
};
}
if (method === "Accessibility.getFullAXTree") {
const frameId = String(args.frameId);
result = {
nodes: [
{
nodeId: `${frameId}-button`,
frameId,
backendDOMNodeId: elements.get(frameId)! + 1,
role: { value: "button" },
name: { value: frameId },
},
],
};
}
return result as T;
},
);
const cdp: CdpRunner = {
getFrameGraph: async () => ({ rootFrameId: frames[0].frameId, frames }),
send: (tabId, method, params) =>
(send as NonNullable<CdpRunner["sendToTarget"]>)({ tabId }, method, params),
sendToTarget: send as NonNullable<CdpRunner["sendToTarget"]>,
};
return { cdp, logs, elements };
}
describe("captureObservationFacts", () => {
it("collects each target once and scopes equal backend IDs", async () => {
const { cdp, logs } = fixture();
const facts = await captureObservationFacts(cdp, 4);
expect(logs.filter((call) => call.method === "DOMSnapshot.captureSnapshot")).toHaveLength(2);
expect(logs.filter((call) => call.method === "Accessibility.enable")).toHaveLength(2);
expect(logs.filter((call) => call.method === "Accessibility.getFullAXTree")).toHaveLength(4);
const main = facts.documents.find((doc) => doc.frame.frameId === "main")!;
const remote = facts.documents.find((doc) => doc.frame.frameId === "remote")!;
expect(main.index.nodes.get(2)).not.toBe(remote.index.nodes.get(2));
expect(main.index.nodes.get(2)?.parentBackendNodeId).toBe(1);
expect(main.index.nodes.get(10001)?.nodeType).toBe(10);
expect(remote.axNodes[0].frameId).toBe("remote");
expect(main.index.nodes.get(2)).toBe(main.domNodes.find((node) => node.backendNodeId === 2));
expect(facts.finishedAt).toBeGreaterThanOrEqual(facts.startedAt);
});
it("does not retry failed or missing documents and retains valid AX-only semantics", async () => {
const { cdp, logs } = fixture({
fail: "remote:DOMSnapshot.captureSnapshot",
omitDocument: "same",
});
const facts = await captureObservationFacts(cdp, 4);
const remote = facts.documents.find((doc) => doc.frame.frameId === "remote")!;
expect(remote.domNodes).toHaveLength(0);
expect(remote.axNodes).toHaveLength(1);
expect(logs.filter((call) => call.method === "DOMSnapshot.captureSnapshot")).toHaveLength(2);
expect(facts.issues).toContainEqual(
expect.objectContaining({ frameId: "same", stage: "dom", reason: "capture-unavailable" }),
);
expect(facts.issues).toContainEqual(
expect.objectContaining({ target: { tabId: 4, sessionId: "remote" }, stage: "dom" }),
);
});
it("excludes overlay AX in its own document without excluding equal IDs elsewhere", async () => {
const facts = await captureObservationFacts(fixture({ overlay: "remote" }).cdp, 4);
const { documents } = semanticCapture(facts);
const graph = buildSemanticGraph({
documents,
viewport: facts.viewport,
rootFrameId: facts.rootFrameId,
});
expect(
[...graph.nodes.values()].find(
(node) => node.frameId === "remote" && node.backendNodeId === 2,
)?.excluded,
).toBe(true);
expect(
[...graph.nodes.values()].find((node) => node.frameId === "main" && node.backendNodeId === 2)
?.excluded,
).toBe(false);
});
it.each([
"cancel",
"worker-abort",
] as const)("joins target cleanup and stops claiming targets after %s", async (mode) => {
const frames = Array.from({ length: 5 }, (_, i) => ({
frameId: `f${i}`,
target: { tabId: 4, ...(i ? { sessionId: `s${i}` } : {}) },
}));
const { cdp } = fixture({ frames });
const original = cdp.sendToTarget!;
const pending = new Map<string, { resolve: () => void; reject: (error: Error) => void }>();
const calls: Array<{ target: string; method: string }> = [];
let release: (() => void) | undefined;
let released = false;
const send: NonNullable<CdpRunner["sendToTarget"]> = async <T>(
target: CdpTarget,
method: string,
params?: object,
) => {
calls.push({ target: target.sessionId ?? "main", method });
if (method === "DOMSnapshot.captureSnapshot" && target.sessionId) {
await new Promise<void>((resolve, reject) =>
pending.set(target.sessionId!, { resolve, reject }),
);
}
if (method === "Runtime.releaseObjectGroup") {
await new Promise<void>((resolve) => {
release = resolve;
});
released = true;
}
const result = await original<T>(target, method, params);
if (method === "DOMSnapshot.captureSnapshot" && !target.sessionId)
(result as { strings: string[] }).strings[2] = "input";
return result;
};
cdp.sendToTarget = send;
cdp.send = (tabId, method, params) => send({ tabId }, method, params);
const controller = new AbortController();
let settled = false;
const capture = captureObservationFacts(cdp, 4, controller.signal);
const rejected = expect(capture).rejects.toMatchObject({ name: "AbortError" });
void capture.then(
() => {
settled = true;
},
() => {
settled = true;
},
);
await vi.waitFor(() => {
expect(pending.size).toBe(3);
expect(release).toBeDefined();
});
if (mode === "cancel") controller.abort();
// Cancellation may race with an ordinary transport rejection. Without an
// external signal, an escaping AbortError still terminates the worker pool.
pending
.get("s1")!
.reject(
mode === "cancel"
? new Error("transport closed")
: new DOMException("target aborted", "AbortError"),
);
pending.get("s2")!.resolve();
pending.get("s3")!.resolve();
await vi.waitFor(() => {
if (mode === "worker-abort")
expect(
calls.some(
(call) => call.target === "s3" && call.method === "Accessibility.getFullAXTree",
),
).toBe(true);
else
expect(
calls.some(
(call) => call.target === "s3" && call.method === "DOMSnapshot.captureSnapshot",
),
).toBe(true);
});
// Allow worker rejection and the outer promise chain to run while cleanup
// is deliberately held. The old fail-fast pool settles here.
await new Promise((resolve) => setTimeout(resolve, 0));
expect(settled).toBe(false);
expect(released).toBe(false);
expect(calls.some((call) => call.target === "s4")).toBe(false);
if (mode === "cancel")
expect(
calls.some(
(call) => call.method === "Accessibility.enable" || call.method === "DOM.getDocument",
),
).toBe(false);
release!();
await rejected;
expect(released).toBe(true);
expect(calls.some((call) => call.target === "s4")).toBe(false);
});
it("bounds collection across many targets and stops scheduling after cancellation", async () => {
const frames = Array.from({ length: 12 }, (_, i) => ({
frameId: `f${i}`,
target: { tabId: 4, ...(i ? { sessionId: `s${i}` } : {}) },
}));
const { cdp } = fixture({ frames });
let active = 0,
peak = 0;
const original = cdp.sendToTarget!;
const send: NonNullable<CdpRunner["sendToTarget"]> = async (target, method, params) => {
active++;
peak = Math.max(peak, active);
try {
await new Promise((resolve) => setTimeout(resolve, 1));
return await original(target, method, params);
} finally {
active--;
}
};
cdp.sendToTarget = send;
cdp.send = (tabId, method, params) => send({ tabId }, method, params);
await captureObservationFacts(cdp, 4);
// This fixture has no frame edges, so no concurrent owner requests.
expect(peak).toBeLessThanOrEqual(4);
expect(peak).toBeGreaterThan(1);
const controller = new AbortController();
controller.abort();
await expect(captureObservationFacts(cdp, 4, controller.signal)).rejects.toMatchObject({
name: "AbortError",
});
expect(active).toBe(0);
});
});
function childSnapshot(frameId: string, backendNodeId: number) {
const strings = [frameId, "body", "button", "static", "auto", "pointer"];
return {
strings,
documents: [
{
frameId,
nodes: {
parentIndex: [-1, 0],
nodeName: [1, 2],
backendNodeId: [backendNodeId - 1, backendNodeId],
attributes: [[], []],
},
layout: {
nodeIndex: [0, 1],
styles: [
[3, 4, 4],
[3, 4, 5],
],
bounds: [
[0, 0, 300, 200],
[10, 20, 100, 40],
],
paintOrders: [0, 1],
},
},
],
};
}
describe("OOPIF capture", () => {
it("captures and positions multiple OOPIF documents missing from the root snapshot", async () => {
const sendToTarget = vi.fn(async (target, method) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200, pageX: 0, pageY: 0 } };
}
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
return target.sessionId === "left-session"
? childSnapshot("left", 101)
: childSnapshot("right", 201);
}
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
throw new Error(`unexpected ${method}`);
});
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method, params) => {
if (method === "Accessibility.enable" || method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return childSnapshot("main", 1);
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
if (method === "DOM.getBoxModel") {
const backendNodeId = (params as { backendNodeId?: number })?.backendNodeId;
const x = backendNodeId === 10 ? 50 : 500;
return { model: { content: [x, 100, x + 300, 100, x + 300, 300, x, 300] } };
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
throw new Error(`unexpected root ${method}`);
}) as CdpRunner["send"],
sendToTarget: sendToTarget as unknown as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "left",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4, sessionId: "left-session" },
},
{
frameId: "right",
parentFrameId: "main",
ownerBackendNodeId: 20,
target: { tabId: 4, sessionId: "right-session" },
},
],
})),
};
const { documents: trees } = semanticCapture(await captureObservationFacts(cdp, 4));
expect(trees.map((tree) => tree.frameId)).toEqual(["main", "left", "right"]);
expect(
trees
.find((doc) => doc.frameId === "left")
?.domNodes?.find((node) => node.backendNodeId === 101)?.rect,
).toEqual({ x: 60, y: 120, w: 100, h: 40 });
expect(
trees
.find((doc) => doc.frameId === "right")
?.domNodes?.find((node) => node.backendNodeId === 201)?.rect,
).toEqual({ x: 510, y: 120, w: 100, h: 40 });
expect(
new Map(
trees
.filter((doc) => doc.ownerBackendNodeId !== undefined)
.map((doc) => [doc.frameId, doc.ownerBackendNodeId]),
),
).toEqual(
new Map([
["left", 10],
["right", 20],
]),
);
expect(
new Map(
trees.filter((doc) => doc.parentFrameId).map((doc) => [doc.frameId, doc.parentFrameId]),
),
).toEqual(
new Map([
["left", "main"],
["right", "main"],
]),
);
});
it("retains nested owner failures when merging a captured OOPIF", async () => {
const child = childSnapshot("child", 101);
const nested = childSnapshot("nested", 201);
const document = child.documents[0];
const snapshot = {
strings: child.strings,
documents: [
{
...document,
nodes: { ...document.nodes, contentDocumentIndex: { index: [1], value: [1] } },
},
nested.documents[0],
],
};
const reply = async (_target: unknown, method: string) => {
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200 } };
if (method === "DOMSnapshot.captureSnapshot")
return typeof _target === "number" ? childSnapshot("main", 11) : snapshot;
if (method === "DOM.getBoxModel")
return { model: { content: [50, 100, 350, 100, 350, 300, 50, 300] } };
if (method === "DOM.resolveNode") throw new Error("nested owner replaced");
return {};
};
const cdp: CdpRunner = {
send: vi.fn(reply) as CdpRunner["send"],
sendToTarget: vi.fn(reply) as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "nested",
parentFrameId: "child",
ownerBackendNodeId: 101,
target: { tabId: 4, sessionId: "child-session" },
},
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4, sessionId: "child-session" },
},
],
})),
};
const captured = await captureObservationFacts(cdp, 4);
expect(
captured.issues
.filter((issue) => issue.projectionIssue)
.map((issue) => issue.projectionIssue),
).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4, sessionId: "child-session" }, frameId: "nested" },
ownerBackendNodeId: 101,
},
]);
expect(
captured.documents.find((doc) => doc.frame.frameId === "nested")?.domNodes[1],
).toMatchObject({
rect: null,
localRect: { x: 10, y: 20, w: 100, h: 40 },
});
});
it("keeps OOPIF semantics when viewport projection is unavailable", async () => {
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "Accessibility.enable" || method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return childSnapshot("main", 1);
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 ${method}`);
}) as unknown as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4, sessionId: "child-session" },
},
],
})),
};
const { documents } = semanticCapture(await captureObservationFacts(cdp, 4));
const childDocument = documents.find((document) => document.frameId === "child");
expect(childDocument?.axNodes).toEqual([
expect.objectContaining({ backendDOMNodeId: 101, frameId: "child" }),
]);
expect(childDocument?.domNodes.find((node) => node.backendNodeId === 101)).toEqual(
expect.objectContaining({ rect: null, localRect: { x: 10, y: 20, w: 100, h: 40 } }),
);
});
});
// Six sibling frames and one nested frame exercise scheduling through the real capture entry.
function siblingCaptureFixture(
beforeReply: (method: string, params: Record<string, unknown>) => Promise<void> = async () => {},
) {
const document = (id: number, owners: number[], childIndexes: number[]) => ({
frameId: `frame-${id}`,
nodes: {
parentIndex: [-1, ...owners.map(() => 0)],
nodeName: [0, ...owners.map(() => 1)],
backendNodeId: [1000 + id, ...owners],
attributes: [[], ...owners.map(() => [])],
contentDocumentIndex: { index: owners.map((_, i) => i + 1), value: childIndexes },
},
layout: {
nodeIndex: [0, ...owners.map((_, i) => i + 1)],
bounds: [[0, 0, 200, 100], ...owners.map(() => [0, 0, 200, 100])],
},
});
const snapshot = {
strings: ["body", "iframe"],
documents: [
document(0, [100, 101, 102, 103, 104, 105], [1, 2, 3, 4, 5, 6]),
document(1, [200], [7]),
...Array.from({ length: 6 }, (_, i) => document(i + 2, [], [])),
],
};
let active = 0;
let peak = 0;
const send = vi.fn(async (_tabId: number, method: string, params: object = {}) => {
const args = params as Record<string, unknown>;
active++;
peak = Math.max(peak, active);
try {
await beforeReply(method, args);
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
if (method === "DOM.getBoxModel")
return { model: { content: [0, 0, 200, 0, 200, 100, 0, 100] } };
if (method === "DOM.resolveNode") return { object: { objectId: String(args.backendNodeId) } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 200, height: 100 } } };
return {};
} finally {
active--;
}
});
return {
snapshot,
cdp: { send: send as CdpRunner["send"] },
send,
peak: () => peak,
active: () => active,
measured: () =>
send.mock.calls
.filter(([, method]) => method === "DOM.getBoxModel")
.map(([, , params]) => (params as { backendNodeId: number }).backendNodeId),
};
}
describe("snapshot document provenance", () => {
it.each([
"new-child",
"new-root",
"stale-owner",
])("retains current snapshot evidence with %s graph data", async (mode) => {
const f = siblingCaptureFixture();
const cdp: CdpRunner = {
...f.cdp,
getFrameGraph: async () => ({
rootFrameId: mode === "new-root" ? "old-root" : "frame-0",
frames: [
{ frameId: mode === "new-root" ? "old-root" : "frame-0", target: { tabId: 4 } },
...(mode === "stale-owner"
? [
{
frameId: "frame-1",
parentFrameId: "frame-0",
ownerBackendNodeId: 999,
target: { tabId: 4 },
},
]
: []),
],
}),
};
const facts = await captureObservationFacts(cdp, 4);
expect(facts.rootFrameId).toBe("frame-0");
expect(facts.documents.find((doc) => doc.frame.frameId === "frame-1")).toMatchObject({
frame: { ownerBackendNodeId: 100 },
domNodes: [
expect.objectContaining({ rect: { x: 0, y: 0, w: 200, h: 100 } }),
expect.anything(),
],
});
expect(
facts.documents.find((doc) => doc.frame.frameId === "frame-7")?.domNodes[0].rect,
).not.toBeNull();
expect(f.measured()).not.toContain(999);
expect(
f.send.mock.calls.filter(([, method]) => method === "DOMSnapshot.captureSnapshot"),
).toHaveLength(1);
expect(
f.send.mock.calls.some(
([, method, params]) =>
method === "Accessibility.getFullAXTree" &&
(params as { frameId?: string }).frameId === "frame-7",
),
).toBe(true);
});
it("uses snapshot URLs before graph URLs and limits the caller URL to the root", async () => {
const f = siblingCaptureFixture();
f.snapshot.strings.push("https://current.test/page", "https://child.test/page");
Object.assign(f.snapshot.documents[0], { documentURL: 2 });
Object.assign(f.snapshot.documents[1], { documentURL: 3 });
const facts = await captureObservationFacts(
{
...f.cdp,
getFrameGraph: async () => ({
rootFrameId: "frame-0",
frames: [{ frameId: "frame-0", target: { tabId: 4 }, url: "https://old.test/" }],
}),
},
4,
undefined,
"https://caller.test/",
);
expect(facts.documents.find((doc) => doc.frame.frameId === "frame-0")?.frame.url).toBe(
"https://current.test/page",
);
expect(facts.documents.find((doc) => doc.frame.frameId === "frame-1")?.frame.url).toBe(
"https://child.test/page",
);
expect(
facts.documents.find((doc) => doc.frame.frameId === "frame-2")?.frame.url,
).toBeUndefined();
});
it("accepts a migrated snapshot claim without merging AX from the old target", async () => {
const f = siblingCaptureFixture();
const cdp: CdpRunner = {
...f.cdp,
getFrameGraph: async () => ({
rootFrameId: "frame-0",
frames: [
{ frameId: "frame-0", target: { tabId: 4 } },
{
frameId: "frame-1",
parentFrameId: "frame-0",
ownerBackendNodeId: 100,
target: { tabId: 4, sessionId: "old" },
},
],
}),
sendToTarget: async <T>(_target: CdpTarget, method: string): Promise<T> =>
(method === "Accessibility.getFullAXTree"
? { nodes: [{ nodeId: "stale", role: { value: "button" }, name: { value: "stale" } }] }
: {}) as T,
};
const facts = await captureObservationFacts(cdp, 4);
const current = facts.documents.find((doc) => doc.frame.frameId === "frame-1");
expect(current?.frame.target).toEqual({ tabId: 4 });
expect(current?.domNodes.length).toBeGreaterThan(0);
expect(current?.axNodes).toEqual([]);
});
it.each([
0, 1,
])("rejects duplicate snapshot frame identity at document %i without overwriting", async (index) => {
const f = siblingCaptureFixture();
f.snapshot.documents.push(f.snapshot.documents[index]);
if (index === 0) {
await expect(captureObservationFacts(f.cdp, 4)).rejects.toThrow(
"root document ownership is ambiguous",
);
} else {
const facts = await captureObservationFacts(f.cdp, 4);
expect(facts.documents.map((doc) => doc.frame.frameId)).not.toContain("frame-1");
expect(facts.documents.map((doc) => doc.frame.frameId)).not.toContain("frame-7");
expect(
facts.documents.find((doc) => doc.frame.frameId === "frame-2")?.domNodes.length,
).toBeGreaterThan(0);
}
});
it("retains the caller URL in the root AX-only fallback", async () => {
const cdp: CdpRunner = {
getFrameGraph: async () => {
throw new Error("no graph");
},
send: async <T>(_tabId: number, method: string): Promise<T> => {
if (method === "DOMSnapshot.captureSnapshot") throw new Error("no snapshot");
return (
method === "Accessibility.getFullAXTree"
? { nodes: [{ nodeId: "root", role: { value: "RootWebArea" } }] }
: {}
) as T;
},
};
const facts = await captureObservationFacts(cdp, 4, undefined, "https://page.test/");
expect(facts.documents[0].frame.url).toBe("https://page.test/");
expect(facts.documents[0].axNodes).toHaveLength(1);
});
it("retains disconnected document data without inventing top-level geometry", async () => {
const f = siblingCaptureFixture();
f.snapshot.documents[0].nodes.contentDocumentIndex = { index: [], value: [] };
const facts = await captureObservationFacts(f.cdp, 4);
expect(
facts.documents.find((doc) => doc.frame.frameId === "frame-1")?.domNodes[0],
).toMatchObject({ rect: null, localRect: { x: 0, y: 0, w: 200, h: 100 } });
expect(f.measured()).toEqual([]);
expect(facts.issues).toContainEqual(
expect.objectContaining({ frameId: "frame-1", stage: "ownership" }),
);
});
it.each([
false,
true,
])("isolates competing target claims independent of batch order %s", async (reverse) => {
const f = siblingCaptureFixture();
const remote = {
frameId: "frame-1",
parentFrameId: "frame-0",
ownerBackendNodeId: 100,
target: { tabId: 4, sessionId: "remote" },
};
const main = { frameId: "frame-0", target: { tabId: 4 } };
const cdp: CdpRunner = {
...f.cdp,
getFrameGraph: async () => ({
rootFrameId: "frame-0",
frames: reverse ? [remote, main] : [main, remote],
}),
sendToTarget: async <T>(_target: CdpTarget, method: string): Promise<T> =>
(method === "DOMSnapshot.captureSnapshot"
? { ...f.snapshot, documents: [f.snapshot.documents[1]] }
: method === "Page.getLayoutMetrics"
? { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } }
: {}) as T,
};
const facts = await captureObservationFacts(cdp, 4);
expect(facts.documents.map((doc) => doc.frame.frameId)).not.toContain("frame-1");
expect(facts.documents.map((doc) => doc.frame.frameId)).not.toContain("frame-7");
expect(
facts.documents.find((doc) => doc.frame.frameId === "frame-2")?.domNodes[0].rect,
).not.toBeNull();
expect(facts.issues).toContainEqual(
expect.objectContaining({ frameId: "frame-1", stage: "ownership" }),
);
});
});
describe("sibling frame measurement scheduling", () => {
it("bounds concurrent reads, fills free slots and preserves breadth-first output despite reordered replies", async () => {
const pending = new Map<number, () => void>();
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.getBoxModel" && Number(params.backendNodeId) < 200)
await new Promise<void>((resolve) => pending.set(Number(params.backendNodeId), resolve));
});
const capture = captureObservationFacts(fixture.cdp, 4);
await vi.waitFor(() => expect(pending.size).toBe(4));
expect(fixture.measured()).toEqual([100, 101, 102, 103]);
pending.get(103)!();
await vi.waitFor(() => expect(pending.has(104)).toBe(true));
pending.get(104)!();
await vi.waitFor(() => expect(pending.has(105)).toBe(true));
expect(fixture.measured()).not.toContain(200);
for (const id of [105, 102, 101, 100]) pending.get(id)!();
const captured = await capture;
expect(
captured.issues
.filter((issue) => issue.stage === "geometry")
.map((issue) => issue.projectionIssue),
).toEqual([]);
expect(fixture.peak()).toBe(4);
expect(fixture.active()).toBe(0);
expect(fixture.measured()).toEqual([100, 101, 102, 103, 104, 105, 200]);
expect(captured.documents.map((doc) => doc.frame.frameId)).toEqual(
Array.from({ length: 8 }, (_, i) => `frame-${i}`),
);
expect(
captured.documents.find((doc) => doc.frame.frameId === "frame-7")?.domNodes[0].rect,
).toEqual({ x: 0, y: 0, w: 200, h: 100 });
for (const method of [
"DOM.getBoxModel",
"DOM.resolveNode",
"Runtime.callFunctionOn",
"Runtime.releaseObject",
])
expect(fixture.send.mock.calls.filter(([, name]) => name === method)).toHaveLength(7);
});
it("does not measure descendants of a failed owner and retains sibling geometry and local nodes", async () => {
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.resolveNode" && params.backendNodeId === 100)
throw new Error("owner replaced");
});
const captured = await captureObservationFacts(fixture.cdp, 4);
expect(
captured.issues
.filter((issue) => issue.stage === "geometry")
.map((issue) => issue.projectionIssue),
).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4 }, frameId: "frame-1" },
ownerBackendNodeId: 100,
},
{
status: "blocked",
source: { target: { tabId: 4 }, frameId: "frame-7" },
cause: captured.issues.find((issue) => issue.frameId === "frame-1")?.projectionIssue,
},
]);
expect(fixture.measured()).not.toContain(200);
expect(
captured.documents.find((doc) => doc.frame.frameId === "frame-7")?.domNodes[0],
).toMatchObject({
tag: "body",
rect: null,
localRect: { x: 0, y: 0, w: 200, h: 100 },
});
expect(
captured.documents.find((doc) => doc.frame.frameId === "frame-2")?.domNodes[0].rect,
).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect(captured.documents.map((doc) => doc.frame.frameId)).toEqual(
Array.from({ length: 8 }, (_, i) => `frame-${i}`),
);
});
it("stops scheduling on cancellation and waits for resolved objects to be released", async () => {
const controller = new AbortController();
const resolutions = new Map<string, () => void>();
const releases = new Map<string, () => void>();
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.resolveNode")
await new Promise<void>((resolve) =>
resolutions.set(String(params.backendNodeId), resolve),
);
if (method === "Runtime.releaseObject")
await new Promise<void>((resolve) => releases.set(String(params.objectId), resolve));
});
let settled = false;
const capture = captureObservationFacts(fixture.cdp, 4, controller.signal);
const rejected = expect(capture).rejects.toMatchObject({ name: "AbortError" });
void capture.then(
() => {
settled = true;
},
() => {
settled = true;
},
);
await vi.waitFor(() => expect(resolutions.size).toBe(4));
controller.abort();
for (const resolve of resolutions.values()) resolve();
await vi.waitFor(() => expect(releases.size).toBe(4));
expect(settled).toBe(false);
expect(fixture.measured()).toEqual([100, 101, 102, 103]);
for (const release of releases.values()) release();
await rejected;
expect(fixture.active()).toBe(0);
expect(fixture.send.mock.calls.some(([, method]) => method === "Runtime.callFunctionOn")).toBe(
false,
);
});
});
@@ -1,7 +1,7 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "../../../lib/overlay-bridge";
import { collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
import { captureObservationFacts, semanticCapture } from "../capture-coordinator";
import type { CdpRunner } from "../../shared";
import { captureViewModel, collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
// Minimal but format-accurate captureSnapshot reply: a body with one
// fixed full-screen overlay div carrying a password input.
@@ -27,7 +27,6 @@ function fakeSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 2],
nodeType: [1, 1, 1, 1],
@@ -75,7 +74,6 @@ function hoverTriggerSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeType: [1, 1, 1],
@@ -120,7 +118,6 @@ function twoHoverTriggerSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 1],
nodeType: [1, 1, 1, 1],
@@ -174,7 +171,6 @@ function nestedHoverTriggerSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 2, 3],
nodeType: [1, 1, 1, 1, 1],
@@ -248,11 +244,13 @@ function makeCdp(snapshot: unknown) {
};
}
describe("snapshot capture and hover", () => {
describe("captureViewModel", () => {
it("parses nodes, attrs, rects, paint order and styles", async () => {
const { nodes, viewport } = semanticCapture(
await captureObservationFacts(makeCdp(fakeSnapshotReply()), 4),
).captured;
const { nodes, viewport, iframeNodes } = await captureViewModel(
makeCdp(fakeSnapshotReply()),
4,
);
expect(iframeNodes.size).toBe(0);
expect(viewport).toEqual({ width: 1000, height: 800 });
const div = nodes.find((n) => n.backendNodeId === 12);
expect(div).toMatchObject({ tag: "div", position: "fixed", parentBackendNodeId: 11 });
@@ -264,11 +262,35 @@ describe("snapshot capture and hover", () => {
it("never hovers the page while capturing", async () => {
const cdp = makeCdp(fakeSnapshotReply());
semanticCapture(await captureObservationFacts(cdp, 4)).captured;
await captureViewModel(cdp, 4);
expect(cdp.send).not.toHaveBeenCalledWith(4, "Input.dispatchMouseEvent", expect.anything());
});
it("batch-enriches form controls without per-node object resolution", async () => {
const cdp = makeCdp(fakeSnapshotReply());
const result = await captureViewModel(cdp, 4);
const input = result.nodes.find((node) => node.backendNodeId === 13);
expect(input).toMatchObject({
formState: "filled",
formPlaceholder: "secret",
attrs: { type: "password" },
});
expect(input?.formValue).toBeUndefined();
expect(input?.formDefaultValue).toBeUndefined();
expect(cdp.send).toHaveBeenCalledWith(
4,
"Runtime.evaluate",
expect.objectContaining({
serializationOptions: expect.objectContaining({ serialization: "deep" }),
}),
);
expect(cdp.send).toHaveBeenCalledWith(4, "Runtime.releaseObjectGroup", expect.anything());
expect(cdp.send).not.toHaveBeenCalledWith(4, "DOM.resolveNode", expect.anything());
expect(cdp.send).not.toHaveBeenCalledWith(4, "Runtime.callFunctionOn", expect.anything());
});
it("runs hover surface probes when explicitly enabled", async () => {
let hoverStateCalls = 0;
const cdp = {
@@ -308,7 +330,7 @@ describe("snapshot capture and hover", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const captured = await captureViewModel(cdp, 4);
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
expect(surfaceProbes).toEqual([
@@ -368,7 +390,7 @@ describe("snapshot capture and hover", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const captured = await captureViewModel(cdp, 4);
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
expect(surfaceProbes).toEqual([
@@ -413,7 +435,7 @@ describe("snapshot capture and hover", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const captured = await captureViewModel(cdp, 4);
await probeHoverSurfaces(cdp, 4, captured.nodes);
expect(hoverMoves).toBe(1);
@@ -445,7 +467,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 0, 3, 4],
nodeName: [i("html"), i("body"), i("div"), i(OVERLAY_HOST_NAME), i("div"), i("button")],
@@ -476,7 +497,7 @@ describe("snapshot capture and hover", () => {
],
};
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
const ids = nodes.map((n) => n.backendNodeId);
// Real page nodes survive.
expect(ids).toContain(12);
@@ -507,7 +528,7 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
frameId: "main",
nodes: {
parentIndex: [-1, 0, 1, 0, 3, 4],
nodeName: [i("html"), i("body"), i("div"), i(OVERLAY_HOST_NAME), i("div"), i("button")],
@@ -538,10 +559,12 @@ describe("snapshot capture and hover", () => {
],
};
const { excludedBackendNodeIds } = semanticCapture(
await captureObservationFacts(makeCdp(snapshot), 4),
).captured;
const { excludedBackendNodeIds, frameExcludedBackendNodeIds } = await captureViewModel(
makeCdp(snapshot),
4,
);
expect(excludedBackendNodeIds).toEqual(new Set([13, 14, 15]));
expect(frameExcludedBackendNodeIds?.get("main")).toEqual(excludedBackendNodeIds);
});
it("excludes overlay host matched by tag name only", async () => {
@@ -561,7 +584,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i(OVERLAY_HOST_NAME)],
@@ -584,9 +606,7 @@ describe("snapshot capture and hover", () => {
],
};
const { nodes, excludedBackendNodeIds } = semanticCapture(
await captureObservationFacts(makeCdp(snapshot), 4),
).captured;
const { nodes, excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
expect(nodes.map((n) => n.backendNodeId)).not.toContain(13);
expect(excludedBackendNodeIds).toEqual(new Set([13]));
});
@@ -609,7 +629,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -632,9 +651,7 @@ describe("snapshot capture and hover", () => {
],
};
const { nodes, excludedBackendNodeIds } = semanticCapture(
await captureObservationFacts(makeCdp(snapshot), 4),
).captured;
const { nodes, excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
expect(nodes.map((n) => n.backendNodeId)).not.toContain(13);
expect(excludedBackendNodeIds).toEqual(new Set([13]));
});
@@ -657,7 +674,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -680,7 +696,7 @@ describe("snapshot capture and hover", () => {
},
],
};
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
expect(nodes.find((n) => n.backendNodeId === 12)?.cursor).toBe("pointer");
expect(nodes.find((n) => n.backendNodeId === 11)?.cursor).toBe("auto");
});
@@ -692,7 +708,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 1, 1],
nodeName: [i("html"), i("body"), i("button"), i("button"), i("button")],
@@ -719,7 +734,7 @@ describe("snapshot capture and hover", () => {
],
};
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
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);
@@ -739,7 +754,7 @@ describe("snapshot capture and hover", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const { nodes } = await captureViewModel(cdp, 4);
const div = nodes.find((n) => n.backendNodeId === 12);
expect(div?.localRect?.y).toBe(-200);
expect(div?.rect).toMatchObject({ y: 0, h: 600 });
@@ -752,7 +767,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -787,7 +801,7 @@ describe("snapshot capture and hover", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const { nodes } = await captureViewModel(cdp, 4);
expect(nodes.find((n) => n.backendNodeId === 12)?.rect).toEqual({
x: 0,
y: 0,
@@ -823,7 +837,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
@@ -862,7 +875,7 @@ describe("snapshot capture and hover", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const { nodes } = await captureViewModel(cdp, 4);
const btn = nodes.find((n) => n.backendNodeId === 12);
expect(btn?.textContent).toBe("登录");
const link = nodes.find((n) => n.backendNodeId === 14);
@@ -872,7 +885,7 @@ describe("snapshot capture and hover", () => {
expect(body?.textContent).toBeUndefined();
});
it("retains explicit iframe document ownership and projected nodes", async () => {
it("parses iframe sub-documents and returns iframeNodes keyed by iframe backendNodeId", async () => {
const S = [
"html",
"body",
@@ -958,21 +971,30 @@ describe("snapshot capture and hover", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const facts = await captureObservationFacts(cdp, 4);
const root = facts.documents.find((doc) => doc.frame.frameId === "main-frame")!;
const child = facts.documents.find((doc) => doc.frame.frameId === "child-frame")!;
expect(facts.documents).toHaveLength(2);
expect(root.domNodes.find((n) => n.backendNodeId === 13)?.tag).toBe("iframe");
const subNodes = child.domNodes;
const {
nodes,
iframeNodes,
frameNodes,
frameOwnerBackendNodeIds,
frameParentIds,
rootFrameId,
} = await captureViewModel(cdp, 4);
// Main frame has 4 nodes; iframe is included
expect(nodes.find((n) => n.backendNodeId === 13)?.tag).toBe("iframe");
// iframeNodes keyed by the <iframe> element's backendNodeId=13
expect(iframeNodes.size).toBe(1);
expect(iframeNodes.has(13)).toBe(true);
const subNodes = iframeNodes.get(13)!;
const input = subNodes.find((n) => n.backendNodeId === 101);
expect(input?.tag).toBe("input");
expect(input?.attrs.type).toBe("text");
expect(input?.ownerFrameBackendNodeId).toBe(13);
expect(input?.localRect).toEqual({ x: 0, y: 0, w: 200, h: 40 });
expect(input?.rect).toEqual({ x: 100, y: 300, w: 200, h: 40 });
expect(facts.rootFrameId).toBe("main-frame");
expect(child.frame.ownerBackendNodeId).toBe(13);
expect(child.frame.parentFrameId).toBe("main-frame");
expect(rootFrameId).toBe("main-frame");
expect(frameNodes?.get("child-frame")).toBe(subNodes);
expect(frameOwnerBackendNodeIds?.get("child-frame")).toBe(13);
expect(frameParentIds?.get("child-frame")).toBe("main-frame");
});
it("projects iframe documents independently of owner snapshot geometry", async () => {
@@ -993,7 +1015,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
@@ -1011,7 +1032,6 @@ describe("snapshot capture and hover", () => {
},
},
{
frameId: "child",
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
@@ -1048,10 +1068,8 @@ describe("snapshot capture and hover", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { documents } = await captureObservationFacts(cdp, 4);
const input = documents
.find((doc) => doc.frame.frameId === "child")
?.domNodes?.find((n) => n.backendNodeId === 101);
const { iframeNodes } = await captureViewModel(cdp, 4);
const input = iframeNodes.get(13)?.find((n) => n.backendNodeId === 101);
expect(input?.localRect).toEqual({ x: 20, y: 20, w: 120, h: 60 });
expect(input?.rect).toEqual({ x: 120, y: 320, w: 120, h: 60 });
@@ -1075,7 +1093,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("iframe")],
@@ -1097,7 +1114,6 @@ describe("snapshot capture and hover", () => {
},
},
{
frameId: "child",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("iframe")],
@@ -1119,7 +1135,6 @@ describe("snapshot capture and hover", () => {
},
},
{
frameId: "nested",
nodes: {
parentIndex: [-1, 0],
nodeName: [i("body"), i("input")],
@@ -1175,13 +1190,9 @@ describe("snapshot capture and hover", () => {
) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { documents } = await captureObservationFacts(cdp, 4);
const nestedIframe = documents
.find((doc) => doc.frame.frameId === "child")
?.domNodes?.find((n) => n.backendNodeId === 23);
const input = documents
.find((doc) => doc.frame.frameId === "nested")
?.domNodes?.find((n) => n.backendNodeId === 31);
const { iframeNodes } = await captureViewModel(cdp, 4);
const nestedIframe = iframeNodes.get(13)?.find((n) => n.backendNodeId === 23);
const input = iframeNodes.get(23)?.find((n) => n.backendNodeId === 31);
expect(nestedIframe?.localRect).toEqual({ x: 5, y: 6, w: 100, h: 80 });
expect(nestedIframe?.rect).toEqual({ x: 15, y: 26, w: 100, h: 80 });
@@ -1197,7 +1208,6 @@ describe("snapshot capture and hover", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -1232,7 +1242,7 @@ describe("snapshot capture and hover", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const { nodes } = await captureViewModel(cdp, 4);
expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 - 100);
});
@@ -1,6 +1,7 @@
import { describe, expect, it, vi } from "vitest";
import { type CdpRunner, cdpRunnerForTarget } from "../../shared";
import { captureObservationFacts } from "../capture-coordinator";
import { enrichFormControlStates } from "../form-capture";
import { decodeDocument } from "../snapshot";
interface Control {
id: number;
@@ -77,21 +78,32 @@ function reply(entries: Array<[number, unknown]>) {
};
}
function fakeCdp(groups: Control[][], evaluate: (params: Record<string, unknown>) => unknown) {
async function fakeCdp(
groups: Control[][],
evaluate: (params: Record<string, unknown>) => unknown,
) {
const snap = snapshot(groups);
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
if (method === "DOMSnapshot.captureSnapshot") return snap;
if (method === "Runtime.evaluate") return evaluate(params as Record<string, unknown>);
return {};
});
return { send, cdp: { send: send as CdpRunner["send"] } };
const nodes = await decodeControls(snap);
return { send, cdp: { send: send as CdpRunner["send"] }, nodes };
}
async function decodeControls(snap: ReturnType<typeof snapshot>) {
return Promise.all(
snap.documents.map(async (doc) =>
(await decodeDocument(doc, snap.strings)).nodes.map((node) => ({ ...node, rect: null })),
),
);
}
describe("form state identity", () => {
it("matches reordered controls by identity and preserves controls missing from the batch", async () => {
// The snapshot includes a shadow input. The runtime query skips it,
// encounters a new input, and sees the remaining inputs in a new order.
const { cdp } = fakeCdp(
const { cdp, nodes } = await fakeCdp(
[
[
{ id: 10, value: "" },
@@ -106,23 +118,21 @@ describe("form state identity", () => {
[11, state("alice@example.com")],
]),
);
const captured = await captureObservationFacts(cdp, 7);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 10)).toMatchObject({
await enrichFormControlStates(cdp, 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 10)).toMatchObject({
formValue: "",
formState: "empty",
formPlaceholder: "snapshot placeholder",
});
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 11)).toMatchObject({
expect(nodes[0].find((n) => n.backendNodeId === 11)).toMatchObject({
formValue: "alice@example.com",
});
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 12)).toMatchObject({
formValue: "上海",
});
expect(captured.documents[0].domNodes.some((n) => n.backendNodeId === 99)).toBe(false);
expect(nodes[0].find((n) => n.backendNodeId === 12)).toMatchObject({ formValue: "上海" });
expect(nodes[0].some((n) => n.backendNodeId === 99)).toBe(false);
});
it("does not shift state between frames when one frame is absent from the runtime batch", async () => {
const { cdp } = fakeCdp(
const { cdp, nodes } = await fakeCdp(
[
[],
[{ id: 11, value: "inaccessible frame" }],
@@ -135,10 +145,8 @@ describe("form state identity", () => {
[21, state("second frame")],
]),
);
const captured = await captureObservationFacts(cdp, 7);
const controls = captured.documents
.filter((doc) => doc.frame.parentFrameId)
.flatMap((doc) => doc.domNodes);
await enrichFormControlStates(cdp, 7, nodes);
const controls = nodes.slice(1).flat();
expect(controls.find((n) => n.backendNodeId === 11)?.formValue).toBe("inaccessible frame");
expect(controls.find((n) => n.backendNodeId === 21)?.formValue).toBe("second frame");
expect(controls.find((n) => n.backendNodeId === 31)?.formValue).toBe("third frame");
@@ -146,7 +154,6 @@ describe("form state identity", () => {
it("keeps identical backend ids in different OOPIF targets separate", async () => {
const sendToTarget = vi.fn(async (target, method) => {
if (method === "DOMSnapshot.captureSnapshot") return snapshot([[{ id: 11, value: "old" }]]);
if (method === "Runtime.evaluate") return reply([[11, state(target.sessionId)]]);
return {};
});
@@ -155,13 +162,9 @@ describe("form state identity", () => {
});
const cdp = { send, sendToTarget } as unknown as CdpRunner;
for (const sessionId of ["left-frame", "right-frame"]) {
const captured = await captureObservationFacts(
cdpRunnerForTarget(cdp, { tabId: 7, sessionId }),
7,
);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 11)?.formValue).toBe(
sessionId,
);
const nodes = await decodeControls(snapshot([[{ id: 11, value: "old" }]]));
await enrichFormControlStates(cdpRunnerForTarget(cdp, { tabId: 7, sessionId }), 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 11)?.formValue).toBe(sessionId);
expect(sendToTarget).toHaveBeenCalledWith(
{ tabId: 7, sessionId },
"Runtime.releaseObjectGroup",
@@ -177,7 +180,7 @@ describe("form state identity", () => {
"malformed",
"invalid-state",
])("preserves snapshot data when enrichment is %s", async (mode) => {
const { cdp, send } = fakeCdp([[{ id: 11, value: "snapshot value" }]], () => {
const { cdp, send, nodes } = await fakeCdp([[{ id: 11, value: "snapshot value" }]], () => {
if (mode === "unsupported") throw new Error("serialization unsupported");
if (mode === "legacy") return { result: { value: { controls: [state("wrong value")] } } };
const result = reply([
@@ -187,8 +190,8 @@ describe("form state identity", () => {
result.result.deepSerializedValue.value[0].value[1].value = "not json";
return result;
});
const captured = await captureObservationFacts(cdp, 7);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 11)).toMatchObject({
expect(await enrichFormControlStates(cdp, 7, nodes)).toBe(mode !== "unsupported");
expect(nodes[0].find((n) => n.backendNodeId === 11)).toMatchObject({
formValue: "snapshot value",
formPlaceholder: "snapshot placeholder",
});
@@ -197,18 +200,34 @@ describe("form state identity", () => {
it("releases the batch's remote objects when capture is cancelled", async () => {
const controller = new AbortController();
const { cdp, send } = fakeCdp([[{ id: 11, value: "old" }]], () => {
const { cdp, send, nodes } = await fakeCdp([[{ id: 11, value: "old" }]], () => {
controller.abort();
return reply([[11, state("new")]]);
});
await expect(captureObservationFacts(cdp, 7, controller.signal)).rejects.toMatchObject({
await expect(enrichFormControlStates(cdp, 7, nodes, controller.signal)).rejects.toMatchObject({
name: "AbortError",
});
expect(send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
});
it("does not report success when cancelled during object cleanup", async () => {
const controller = new AbortController();
const nodes = await decodeControls(snapshot([[{ id: 11, value: "old" }]]));
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "Runtime.evaluate") return reply([[11, state("new")]]);
if (method === "Runtime.releaseObjectGroup") controller.abort();
return {};
}) as CdpRunner["send"],
};
await expect(enrichFormControlStates(cdp, 7, nodes, controller.signal)).rejects.toMatchObject({
name: "AbortError",
});
expect(cdp.send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
});
it("skips entries without node identity while still applying valid entries", async () => {
const { cdp } = fakeCdp(
const { cdp, nodes } = await fakeCdp(
[
[
{ id: 11, value: "snapshot value" },
@@ -225,24 +244,20 @@ describe("form state identity", () => {
return result;
},
);
const captured = await captureObservationFacts(cdp, 7);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 11)?.formValue).toBe(
"snapshot value",
);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 12)?.formValue).toBe(
"live value",
);
await enrichFormControlStates(cdp, 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 11)?.formValue).toBe("snapshot value");
expect(nodes[0].find((n) => n.backendNodeId === 12)?.formValue).toBe("live value");
});
it.each([
"password",
"text",
])("redacts a sensitive %s control after identity matching", async (type) => {
const { cdp } = fakeCdp([[{ id: 11, value: "secret", type }]], () =>
const { cdp, nodes } = await fakeCdp([[{ id: 11, value: "secret", type }]], () =>
reply([[11, { ...state("secret"), sensitive: true }]]),
);
const captured = await captureObservationFacts(cdp, 7);
const control = captured.documents[0].domNodes.find((n) => n.backendNodeId === 11);
await enrichFormControlStates(cdp, 7, nodes);
const control = nodes[0].find((n) => n.backendNodeId === 11);
expect(control?.formState).toBe("filled");
expect(control?.formValue).toBeUndefined();
expect(control?.formDefaultValue).toBeUndefined();
@@ -259,7 +274,7 @@ describe("form state identity", () => {
defaultValue: "",
placeholder: "",
}));
const { cdp, send } = fakeCdp([controls], (params) => {
const { cdp, send, nodes } = await fakeCdp([controls], (params) => {
const doc = {
querySelectorAll: (selector: string) =>
selector === "input,textarea,select" ? elements : [],
@@ -270,13 +285,9 @@ describe("form state identity", () => {
expect(entries).toHaveLength(250);
return reply(entries.map(([element, json]) => [element.backendNodeId, JSON.parse(json)]));
});
const captured = await captureObservationFacts(cdp, 7);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 250)?.formValue).toBe(
"live 250",
);
expect(captured.documents[0].domNodes.find((n) => n.backendNodeId === 251)?.formValue).toBe(
"old",
);
await enrichFormControlStates(cdp, 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 250)?.formValue).toBe("live 250");
expect(nodes[0].find((n) => n.backendNodeId === 251)?.formValue).toBe("old");
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(1);
expect(
send.mock.calls.filter(([, method]) => method === "Runtime.releaseObjectGroup"),
@@ -0,0 +1,271 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import type { CapturedNode, CapturedViewModel } from "../capture";
import { captureFrameData } from "../frame-capture";
function ownerNode(backendNodeId: number, x: number): CapturedNode {
return {
backendNodeId,
parentBackendNodeId: 1,
frameId: "main",
ownerFrameBackendNodeId: null,
tag: "iframe",
attrs: {},
rect: { x, y: 100, w: 300, h: 200 },
localRect: { x, y: 100, w: 300, h: 200 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
};
}
function childSnapshot(frameId: string, backendNodeId: number) {
const strings = [frameId, "body", "button", "static", "auto", "pointer"];
return {
strings,
documents: [
{
frameId,
nodes: {
parentIndex: [-1, 0],
nodeName: [1, 2],
backendNodeId: [backendNodeId - 1, backendNodeId],
attributes: [[], []] as number[][],
},
layout: {
nodeIndex: [0, 1],
styles: [
[3, 4, 4],
[3, 4, 5],
],
bounds: [
[0, 0, 300, 200],
[10, 20, 100, 40],
],
paintOrders: [0, 1],
},
},
],
};
}
describe("captureFrameData", () => {
it("retains nested owner failures when merging a captured OOPIF", async () => {
const owner = ownerNode(10, 50);
const captured: CapturedViewModel = {
nodes: [owner],
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
frameNodes: new Map([["main", [owner]]]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const child = childSnapshot("child", 101);
const nested = childSnapshot("nested", 201);
const document = child.documents[0];
const snapshot = {
strings: child.strings,
documents: [
{
...document,
nodes: { ...document.nodes, contentDocumentIndex: { index: [1], value: [1] } },
},
nested.documents[0],
],
};
const reply = async (_target: unknown, method: string) => {
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200 } };
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "DOM.getBoxModel")
return { model: { content: [50, 100, 350, 100, 350, 300, 50, 300] } };
if (method === "DOM.resolveNode") throw new Error("nested owner replaced");
return {};
};
const cdp: CdpRunner = {
send: vi.fn(reply) as CdpRunner["send"],
sendToTarget: vi.fn(reply) 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" },
},
],
})),
};
await captureFrameData(cdp, 4, captured);
expect(captured.frameGeometryIssues).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4, sessionId: "child-session" }, frameId: "nested" },
ownerBackendNodeId: 101,
},
]);
expect(captured.frameNodes?.get("nested")?.[1]).toMatchObject({
rect: null,
localRect: { x: 10, y: 20, w: 100, h: 40 },
});
});
it("captures and positions multiple OOPIF documents missing from the root snapshot", async () => {
const leftOwner = ownerNode(10, 50);
const rightOwner = ownerNode(20, 500);
const captured: CapturedViewModel = {
nodes: [leftOwner, rightOwner],
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
frameNodes: new Map([["main", [leftOwner, rightOwner]]]),
frameOwnerBackendNodeIds: new Map(),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const sendToTarget = vi.fn(async (target, method) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200, pageX: 0, pageY: 0 } };
}
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
if (target.sessionId !== "left-session") return childSnapshot("right", 201);
const snapshot = childSnapshot("left", 101);
const marker = snapshot.strings.push(OVERLAY_HOST_MARKER_ATTR) - 1;
const nodes = snapshot.documents[0].nodes;
nodes.backendNodeId.push(201); // Same id as a real button in the other target.
nodes.parentIndex.push(0);
nodes.nodeName.push(2);
nodes.attributes.push([marker, -1]);
return snapshot;
}
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
throw new Error(`unexpected ${method}`);
});
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method, params) => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
if (method === "DOM.getBoxModel") {
const backendNodeId = (params as { backendNodeId?: number })?.backendNodeId;
const x = backendNodeId === 10 ? 50 : 500;
return { model: { content: [x, 100, x + 300, 100, x + 300, 300, x, 300] } };
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
throw new Error(`unexpected root ${method}`);
}) as CdpRunner["send"],
sendToTarget: sendToTarget as unknown as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "left",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4, sessionId: "left-session" },
},
{
frameId: "right",
parentFrameId: "main",
ownerBackendNodeId: 20,
target: { tabId: 4, sessionId: "right-session" },
},
],
})),
};
const trees = await captureFrameData(cdp, 4, captured);
expect(trees.find((tree) => tree.frameId === "left")?.excludedBackendNodeIds).toEqual(
new Set([201]),
);
expect(trees.find((tree) => tree.frameId === "right")?.excludedBackendNodeIds?.size).toBe(0);
expect(trees.map((tree) => tree.frameId)).toEqual(["main", "left", "right"]);
expect(
captured.frameNodes?.get("left")?.find((node) => node.backendNodeId === 101)?.rect,
).toEqual({ x: 60, y: 120, w: 100, h: 40 });
expect(
captured.frameNodes?.get("right")?.find((node) => node.backendNodeId === 201)?.rect,
).toEqual({ x: 510, y: 120, w: 100, h: 40 });
expect(captured.frameOwnerBackendNodeIds).toEqual(
new Map([
["left", 10],
["right", 20],
]),
);
expect(captured.frameParentIds).toEqual(
new Map([
["left", "main"],
["right", "main"],
]),
);
});
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 } }),
);
});
});
@@ -1,12 +1,7 @@
import { describe, expect, it, vi } from "vitest";
import { describe, expect, it } from "vitest";
import type { CdpFrameGraph } from "@/browser-driver/frame-graph";
import type { CapturedNode } from "../capture";
import {
buildFrameDocuments,
type FrameAxBatch,
type FrameDomInput,
type FrameOwnedAxNode,
} from "../frame-document";
import type { CapturedNode, CapturedViewModel } from "../capture";
import { buildFrameDocuments, type FrameAxBatch, type FrameOwnedAxNode } from "../frame-document";
function domNode(frameId: string, backendNodeId: number): CapturedNode {
return {
@@ -22,11 +17,14 @@ function domNode(frameId: string, backendNodeId: number): CapturedNode {
};
}
function captured(frameNodes: Map<string, CapturedNode[]>): FrameDomInput {
function captured(frameNodes: Map<string, CapturedNode[]>): CapturedViewModel {
return {
nodes: frameNodes.get("main") ?? [],
viewport: { width: 800, height: 600 },
iframeNodes: new Map(),
frameNodes,
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
}
@@ -159,12 +157,10 @@ describe("buildFrameDocuments", () => {
["child", [domNode("child", 9)]],
]);
const capture = captured(frameNodes);
capture.frameOwnerBackendNodeIds = new Map([["child", 7]]);
capture.frameParentIds = new Map([["child", "left"]]);
const frames = ["main", "left", "right", "child"].map((frameId) => ({
frame: {
frameId,
target: { tabId: 4 },
...(frameId === "child" ? { parentFrameId: "left", ownerBackendNodeId: 7 } : {}),
},
frame: { frameId, target: { tabId: 4 } },
nodes: [],
}));
@@ -175,23 +171,6 @@ describe("buildFrameDocuments", () => {
ownerBackendNodeId: 7,
});
});
it("rejects explicit AX frame ownership in a different target", async () => {
const frames = [
{ frameId: "main", target: { tabId: 4 } },
{ frameId: "remote", target: { tabId: 4, sessionId: "remote" } },
];
const unresolved = vi.fn();
const documents = await buildFrameDocuments(
{ rootFrameId: "main", frames },
[{ frame: frames[0], nodes: [{ nodeId: "wrong", frameId: "remote" }] }],
captured(new Map()),
undefined,
unresolved,
);
expect(documents.every((doc) => doc.axNodes.length === 0)).toBe(true);
expect(unresolved).toHaveBeenCalledOnce();
});
it("resolves a reverse-ordered deep AX parent chain without recursion", async () => {
const frame = { frameId: "main", target: { tabId: 4 } };
const nodes: FrameOwnedAxNode[] = Array.from({ length: 10000 }, (_, i) => ({
@@ -0,0 +1,32 @@
function captureAbortError(): Error {
const error = new Error("observation aborted");
error.name = "AbortError";
return error;
}
export function isAbortError(error: unknown): boolean {
return (
typeof error === "object" &&
error !== null &&
(error as { name?: string }).name === "AbortError"
);
}
export function throwIfAborted(signal: AbortSignal | undefined): void {
if (signal?.aborted) throw captureAbortError();
}
/** Called only at bounded block boundaries, not once per node. */
export async function captureCheckpoint(signal?: AbortSignal): Promise<void> {
throwIfAborted(signal);
await new Promise<void>((resolve) => {
const channel = new MessageChannel();
channel.port1.onmessage = () => {
channel.port1.close();
channel.port2.close();
resolve();
};
channel.port2.postMessage(null);
});
throwIfAborted(signal);
}
@@ -1,334 +0,0 @@
import {
type CdpFrame,
type CdpFrameGraph,
type CdpTarget,
cdpTargetKey,
} from "@/browser-driver/frame-graph";
import { cssViewport, GeometryContext } from "../geometry/frame-context";
import { type CdpRunner, cdpRunnerForTarget } from "../shared";
import { collectOverlayExcludedBackendIds } from "./capture";
import type { CapturedSceneInput } from "./facts";
import {
buildDocumentIndex,
type CaptureIssue,
isCaptureAbort,
type ObservationFacts,
throwCaptureAborted,
} from "./facts";
import { enrichFormControlStates } from "./form-capture";
import {
buildFrameDocuments,
type FrameAxBatch,
type FrameDocument,
type FrameOwnedAxNode,
} from "./frame-document";
import { type NormalizedDocument, normalizeSnapshot } from "./normalize";
import { describeSnapshotFrames, REQUESTED_STYLES, type SnapshotReply } from "./snapshot";
interface TargetBatch<T extends FrameOwnedAxNode> {
target: CdpTarget;
frames: CdpFrame[];
documents: NormalizedDocument[];
ax: FrameAxBatch<T>[];
fallbackExcluded: Set<number>;
snapshotFrameIds?: Set<string>;
rootFrameId?: string;
}
/** A fixed worker pool scoped to one capture; each worker issues at most one
* collection request at a time. Geometry has its own measurement-phase bound. */
async function collectTargets<T>(
items: readonly T[],
collect: (item: T) => Promise<void>,
signal?: AbortSignal,
): Promise<void> {
let cursor = 0;
let failed = false;
let failure: unknown;
await Promise.all(
Array.from({ length: Math.min(4, items.length) }, async () => {
try {
while (cursor < items.length && !failed && !signal?.aborted) {
const item = items[cursor++];
await collect(item);
}
} catch (error) {
if (!failed) failure = error;
failed = true;
}
}),
);
// A worker's rejection must not let the capture outlive its own task scope.
// In-flight reads and their finally blocks settle before cancellation/failure.
throwCaptureAborted(signal);
if (failed) throw failure;
}
export async function captureObservationFacts<T extends FrameOwnedAxNode>(
cdp: CdpRunner,
tabId: number,
signal?: AbortSignal,
pageUrl?: string,
): Promise<ObservationFacts<T>> {
const startedAt = Date.now();
throwCaptureAborted(signal);
let graph: CdpFrameGraph | undefined;
try {
graph = await cdp.getFrameGraph?.(tabId);
} catch (error) {
if (isCaptureAbort(error)) throw error;
}
throwCaptureAborted(signal);
const geometry = new GeometryContext(cdp, tabId, graph, signal);
const issues: CaptureIssue[] = [];
const graphFrames = new Map(graph?.frames.map((frame) => [frame.frameId, frame]) ?? []);
const groups = new Map<string, TargetBatch<T>>();
for (const frame of graph?.frames ?? []) {
const key = cdpTargetKey(frame.target);
let group = groups.get(key);
if (!group) {
group = {
target: frame.target,
frames: [],
documents: [],
ax: [],
fallbackExcluded: new Set(),
};
groups.set(key, group);
}
group.frames.push(
!frame.target.sessionId && frame.frameId === graph?.rootFrameId && !frame.url && pageUrl
? { ...frame, url: pageUrl }
: frame,
);
}
if (!groups.has(cdpTargetKey({ tabId })))
groups.set(cdpTargetKey({ tabId }), {
target: { tabId },
frames: [],
documents: [],
ax: [],
fallbackExcluded: new Set(),
});
const batches = [...groups.values()];
const unavailable = (batch: TargetBatch<T>, stage: CaptureIssue["stage"], frameId?: string) =>
issues.push({ target: batch.target, frameId, stage, reason: "capture-unavailable" });
let firstFailure: unknown;
await collectTargets(
batches,
async (batch) => {
const scoped = cdpRunnerForTarget(cdp, batch.target);
try {
throwCaptureAborted(signal);
await scoped.send(tabId, "DOMSnapshot.enable", {});
throwCaptureAborted(signal);
const snapshot = await scoped.send<SnapshotReply>(tabId, "DOMSnapshot.captureSnapshot", {
computedStyles: REQUESTED_STYLES,
includePaintOrder: true,
includeDOMRects: true,
});
throwCaptureAborted(signal);
const observed = describeSnapshotFrames(snapshot, batch.target, graphFrames, pageUrl);
batch.snapshotFrameIds = observed.ids;
batch.rootFrameId = observed.rootFrameId;
// Keep graph-only frames for AX fallback, never in preference to observed membership.
batch.frames = [
...observed.frames,
...batch.frames.filter((frame) => !observed.ids.has(frame.frameId)),
];
batch.documents = await normalizeSnapshot(
snapshot,
batch.target,
batch.frames.filter((frame) => observed.ids.has(frame.frameId)),
geometry,
issues,
signal,
observed.rootFrameId,
);
const formsAvailable = await enrichFormControlStates(
scoped,
tabId,
batch.documents.map((doc) => doc.domNodes),
signal,
);
throwCaptureAborted(signal);
if (!formsAvailable) unavailable(batch, "forms");
const present = new Set(batch.documents.map((doc) => doc.frame.frameId));
for (const frame of batch.frames)
if (!present.has(frame.frameId)) unavailable(batch, "dom", frame.frameId);
} catch (error) {
throwCaptureAborted(signal);
if (isCaptureAbort(error)) throw error;
firstFailure ??= error;
unavailable(batch, "dom");
batch.fallbackExcluded = await collectOverlayExcludedBackendIds(scoped, tabId, signal);
}
if (!batch.frames.length && !graph)
batch.frames = [
{
frameId: "root",
target: batch.target,
...(!batch.target.sessionId && pageUrl ? { url: pageUrl } : {}),
},
];
try {
throwCaptureAborted(signal);
await scoped.send(tabId, "Accessibility.enable", {});
} catch (error) {
throwCaptureAborted(signal);
if (isCaptureAbort(error)) throw error;
firstFailure ??= error;
unavailable(batch, "ax");
return;
}
for (const frame of batch.frames) {
try {
throwCaptureAborted(signal);
const result = await scoped.send<{ nodes?: T[] }>(
tabId,
"Accessibility.getFullAXTree",
frame.frameId === "root" ? {} : { frameId: frame.frameId },
);
throwCaptureAborted(signal);
batch.ax.push({ frame, nodes: result.nodes ?? [] });
} catch (error) {
throwCaptureAborted(signal);
if (isCaptureAbort(error)) throw error;
firstFailure ??= error;
unavailable(batch, "ax", frame.frameId);
}
}
},
signal,
);
// A snapshot claim outranks an old graph hint. Conflicting actual claims
// cannot be resolved by completion order or by overwriting a frameId map.
const claims = new Map<string, string>();
const invalid = new Set<string>();
for (const batch of batches) {
const targetKey = cdpTargetKey(batch.target);
for (const id of batch.snapshotFrameIds ?? []) {
const previous = claims.get(id);
if (previous !== undefined && previous !== targetKey) invalid.add(id);
claims.set(id, targetKey);
}
const accepted = new Set(batch.frames.map((frame) => frame.frameId));
for (const id of batch.snapshotFrameIds ?? []) if (!accepted.has(id)) invalid.add(id);
}
const currentFrames = batches.flatMap((batch) =>
batch.frames.filter(
(frame) =>
!claims.has(frame.frameId) || claims.get(frame.frameId) === cdpTargetKey(batch.target),
),
);
const children = new Map<string, string[]>();
for (const frame of currentFrames) {
if (!frame.parentFrameId) continue;
const siblings = children.get(frame.parentFrameId);
if (siblings) siblings.push(frame.frameId);
else children.set(frame.parentFrameId, [frame.frameId]);
}
const blocked = [...invalid];
for (let i = 0; i < blocked.length; i++) {
for (const child of children.get(blocked[i]) ?? []) {
if (!invalid.has(child)) {
invalid.add(child);
blocked.push(child);
}
}
}
for (const frame of currentFrames) {
if (invalid.has(frame.frameId))
issues.push({
target: frame.target,
frameId: frame.frameId,
stage: "ownership",
reason: "frame-ownership-unresolved",
});
}
const rootBatch = batches.find((batch) => !batch.target.sessionId);
const rootFrameId =
rootBatch?.rootFrameId ?? graph?.rootFrameId ?? rootBatch?.frames[0]?.frameId ?? "root";
if (invalid.has(rootFrameId)) throw new Error("observation root document ownership is ambiguous");
const frames = currentFrames.filter((frame) => !invalid.has(frame.frameId));
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
const belongs = (frame: CdpFrame) => {
const current = frameById.get(frame.frameId);
return current && cdpTargetKey(current.target) === cdpTargetKey(frame.target);
};
const decoded = new Map(
batches
.flatMap((batch) => batch.documents)
.filter((doc) => belongs(doc.frame))
.map((doc) => [doc.frame.frameId, doc]),
);
const ax = batches.flatMap((batch) => batch.ax).filter((batch) => belongs(batch.frame));
const documents = await buildFrameDocuments(
{ rootFrameId, frames },
ax,
{
nodes: [],
rootFrameId,
frameNodes: new Map([...decoded].map(([id, doc]) => [id, doc.domNodes])),
},
signal,
(frame) =>
issues.push({
target: frame.target,
frameId: frame.frameId,
stage: "ownership",
reason: "frame-ownership-unresolved",
}),
);
let viewport = { width: 0, height: 0 };
try {
const measured = cssViewport(await geometry.layoutMetrics({ tabId }));
viewport = { width: measured.width, height: measured.height };
} catch (error) {
if (isCaptureAbort(error)) throw error;
}
const facts: ObservationFacts<T>["documents"][number][] = [];
for (const document of documents) {
const doc = decoded.get(document.frameId);
const index = doc?.index ?? (await buildDocumentIndex([], signal));
const fallback = groups.get(cdpTargetKey(document.target))?.fallbackExcluded;
const { domNodes, axNodes, contextScopeId: _scope, ...frame } = document;
facts.push({
frame,
index: fallback?.size ? { ...index, excludedBackendNodeIds: fallback } : index,
domNodes,
axNodes,
});
}
throwCaptureAborted(signal);
if (firstFailure && facts.every((doc) => !doc.domNodes.length && !doc.axNodes.length))
throw firstFailure;
return { rootFrameId, viewport, documents: facts, issues, startedAt, finishedAt: Date.now() };
}
/** Existing semantic consumers get a narrow view; no raw snapshot
* data can leak through recording's allowlisted output DTO. */
export function semanticCapture<T extends FrameOwnedAxNode>(
facts: ObservationFacts<T>,
): { captured: CapturedSceneInput; documents: FrameDocument<T>[] } {
const documents = facts.documents.map((doc) => ({
...doc.frame,
contextScopeId: doc.frame.frameId,
domNodes: doc.domNodes.filter(
(node) => !doc.index.excludedBackendNodeIds.has(node.backendNodeId),
),
axNodes: doc.axNodes,
excludedBackendNodeIds: doc.index.excludedBackendNodeIds,
}));
const root = documents.find((doc) => doc.frameId === facts.rootFrameId);
return {
documents,
captured: {
nodes: root?.domNodes ?? [],
viewport: facts.viewport,
rootFrameId: facts.rootFrameId,
excludedBackendNodeIds: root?.excludedBackendNodeIds ?? new Set(),
},
};
}
@@ -0,0 +1,37 @@
import type { Rect } from "@browser-skill/vom";
export interface CapturedNode {
backendNodeId: number;
parentBackendNodeId: number | null;
frameId?: string;
/** Owning iframe backend node id; `null` for the top-level document. */
ownerFrameBackendNodeId?: number | null;
tag: string;
attrs: Record<string, string>;
/** Top-level viewport-relative CSS px, clipped to the owning frame viewport. */
rect: Rect | null;
/** Frame-local viewport-relative CSS px before top-level projection. */
localRect?: Rect | null;
paintOrder: number;
position: string;
pointerEvents: string;
/**
* computed `cursor`. `cursor: pointer` is the strongest CDP-free signal
* that a non-semantic element (a `<div>`/`<span>` with a click handler)
* is actually an interactive control — used by the adapter to surface
* custom buttons/checkboxes the AX tree drops as `generic`. Optional like
* `textContent`: the live parser always sets it, hand-built fixtures may not.
*/
cursor?: string;
/**
* 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;
formDefaultValue?: string;
formPlaceholder?: string;
}
+69 -197
View File
@@ -1,17 +1,59 @@
// Browser-side hover probes and overlay exclusion fallback. Static collection
// lives in capture-coordinator; snapshot decoding has no browser dependency.
// Coordinate DOMSnapshot acquisition, frame geometry and hover probes.
// Snapshot decoding and form enrichment live in their own modules.
import type { Viewport } from "@browser-skill/vom";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import { evaluateHoverTrigger } from "@/lib/hover-trigger-policy";
import { OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
import { type FrameProjectionIssue, type FrameProjectionState } from "../geometry/coordinate-types";
import { cssViewport, GeometryContext, type LayoutMetrics } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
import type { CapturedNode, CapturedSurfaceProbe } from "./facts";
export type {
CapturedNode,
CapturedSurfaceProbe,
} from "./facts";
import { isCaptureAbort as isAbortError, throwCaptureAborted as throwIfAborted } from "./facts";
import { isAbortError, throwIfAborted } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import { enrichFormControlStates } from "./form-capture";
import { clearHover, ProbeBudget, waitForHover } from "./hover-perception";
import { type FrameContext, normalizeDocument } from "./normalize";
import {
REQUESTED_STYLES,
type SnapshotDocument,
type SnapshotReply,
snapshotFrameId,
sparseIndexMap,
} from "./snapshot";
export type { CapturedNode } from "./capture-types";
export type CapturedIframeNodes = Map<number, CapturedNode[]>;
export interface CapturedSurfaceProbe {
triggerBackendNodeId: number;
triggerPoint?: { x: number; y: number };
triggerAction: "hover" | "focus" | string;
subItems: string[];
confidence?: "high" | "medium" | "low";
}
export interface CapturedViewModel {
nodes: CapturedNode[];
viewport: Viewport;
iframeNodes: CapturedIframeNodes;
frameNodes?: Map<string, CapturedNode[]>;
frameExcludedBackendNodeIds?: Map<string, ReadonlySet<number>>;
frameOwnerBackendNodeIds?: Map<string, number>;
/** Explicit DOMSnapshot frame ancestry; never inferred from backend node ids. */
frameParentIds?: Map<string, string>;
rootFrameId?: string;
/** Failed boundaries and descendants blocked by them; clipping is not a failure. */
frameGeometryIssues?: FrameProjectionIssue[];
/** Backend node ids belonging to the agent overlay host + its shadow subtree. */
excludedBackendNodeIds: Set<number>;
}
export interface CaptureViewModelOptions {
signal?: AbortSignal;
geometry?: GeometryContext;
target?: CdpTarget;
}
interface RuntimeEvaluateReply {
result?: {
@@ -443,194 +485,12 @@ export async function collectOverlayExcludedBackendIds(
return excluded;
}
/**
* Parse one DOMSnapshot document into CapturedNode[].
*
* @param doc - the raw DOMSnapshot document object
* @param strings - the shared string table for the whole snapshot
* @param context - frame coordinate context; output rects are top viewport-relative
*/
function parseDocumentNodes(
doc: SnapshotDocument,
strings: string[],
context: FrameContext,
): ParseDocumentResult {
const dn = doc.nodes;
const dl = doc.layout;
if (!dn?.backendNodeId) {
return { nodes: [], excludedBackendNodeIds: new Set() };
}
const count = dn.backendNodeId.length;
const layoutByNode = new Map<number, number>();
(dl?.nodeIndex ?? []).forEach((nodeIdx, layoutIdx) => layoutByNode.set(nodeIdx, layoutIdx));
// The agent's own overlay (WXT shadow host, marked with OVERLAY_HOST_MARKER_ATTR)
// is injected into the page and its open shadow root
// is inlined by DOMSnapshot as descendants of the host. Its fixed
// full-viewport click-blocker would otherwise dominate occlusion detection
// and hide the real page, so mark the host + its whole subtree excluded.
// parentIndex always references an earlier node, so one forward pass suffices.
const excluded = new Array<boolean>(count).fill(false);
const excludedBackendNodeIds = new Set<number>();
for (let n = 0; n < count; n++) {
const parentIdx = dn.parentIndex?.[n] ?? -1;
const inherited = parentIdx >= 0 && excluded[parentIdx];
let isOverlayHost = inherited;
if (!isOverlayHost) {
const pairs = dn.attributes?.[n] ?? [];
const attrNames: string[] = [];
for (let a = 0; a + 1 < pairs.length; a += 2) {
attrNames.push(str(strings, pairs[a]));
}
isOverlayHost = isOverlayHostNode(str(strings, dn.nodeName?.[n]), attrNames);
}
if (!isOverlayHost) continue;
excluded[n] = true;
const backendNodeId = dn.backendNodeId[n];
if (backendNodeId !== undefined) {
excludedBackendNodeIds.add(backendNodeId);
}
}
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 inputValues = sparseIndexMap(dn.inputValue);
const textValues = sparseIndexMap(dn.textValue);
const checkedInputs = new Set(dn.inputChecked?.index ?? []);
const selectedOptions = new Set(dn.optionSelected?.index ?? []);
// Collect visible text from #text child nodes so element CapturedNodes
// carry a textContent value usable as a button/link label fallback.
// nodeValue is a parallel array: string index for text nodes, -1 otherwise.
const nodeTextContent = new Map<number, string>();
if (dn.nodeValue) {
for (let n = 0; n < count; n++) {
const nvIdx = dn.nodeValue[n] ?? -1;
if (nvIdx < 0) continue;
const text = str(strings, nvIdx).trim();
if (!text) continue;
const parentIdx = dn.parentIndex?.[n] ?? -1;
if (parentIdx >= 0) {
const existing = nodeTextContent.get(parentIdx);
nodeTextContent.set(parentIdx, existing ? `${existing} ${text}` : text);
}
}
}
// Build CapturedNodes.
const nodes: CapturedNode[] = [];
for (let n = 0; n < count; n++) {
if (excluded[n]) continue;
const backendNodeId = dn.backendNodeId[n];
const parentIdx = dn.parentIndex?.[n] ?? -1;
const parentBackendNodeId = parentIdx >= 0 ? (dn.backendNodeId[parentIdx] ?? null) : null;
const tag = str(strings, dn.nodeName?.[n]).toLowerCase();
const attrs: Record<string, string> = {};
const pairs = dn.attributes?.[n] ?? [];
for (let a = 0; a + 1 < pairs.length; a += 2) {
attrs[str(strings, pairs[a]).toLowerCase()] = str(strings, pairs[a + 1]);
}
let rect: Rect | null = null;
let localRect: Rect | null = null;
let paintOrder = 0;
let position = "static";
let pointerEvents = "auto";
let cursor = "auto";
let rendered = false;
const li = layoutByNode.get(n);
if (li !== undefined) {
const b = dl?.bounds?.[li];
if (b && b.length >= 4 && b[2] > 0 && b[3] > 0) {
const input = snapshotViewportRect(
b,
{ target: context.target, frameId: context.frameId },
{ x: context.scrollX, y: context.scrollY },
);
if (input) {
const { x, y, width: w, height: h } = input.rect;
localRect = { x, y, w, h };
}
const bounds =
input && context.projection.status === "available"
? projectSnapshotRect(input, context.projection.projection)
: null;
rect = bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
}
paintOrder = dl?.paintOrders?.[li] ?? 0;
const styleRow = dl?.styles?.[li] ?? [];
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";
rendered =
localRect !== null &&
visibility !== "hidden" &&
visibility !== "collapse" &&
(Number.parseFloat(opacity) || 0) > 0;
}
// Skip non-element nodes (#text, #cdata-section, etc.) — they carry no
// geometry and are never queried by callers.
if (tag.startsWith("#")) continue;
const textContent = nodeTextContent.get(n);
const rawFormValueIndex = tag === "textarea" ? textValues.get(n) : inputValues.get(n);
const rawFormValue =
rawFormValueIndex !== undefined ? str(strings, rawFormValueIndex) : undefined;
const sensitive = isSensitiveFormControl({ tag, attrs });
const formDefaultValue = attrs.value ?? "";
const formValue = sensitive ? undefined : rawFormValue;
const formState = snapshotFormState(
rawFormValue,
formDefaultValue,
Object.prototype.hasOwnProperty.call(attrs, "value"),
sensitive,
);
if (sensitive) delete attrs.value;
nodes.push({
backendNodeId,
parentBackendNodeId,
...(context.frameId ? { frameId: context.frameId } : {}),
ownerFrameBackendNodeId: context.ownerFrameBackendNodeId,
tag,
attrs,
rect,
localRect,
paintOrder,
position,
pointerEvents,
cursor,
rendered,
textContent,
...(formValue !== undefined ? { formValue } : {}),
...(tag === "input" || tag === "textarea"
? {
formPlaceholder: attrs.placeholder ?? "",
...(!sensitive ? { formDefaultValue } : {}),
...(formState ? { formState } : {}),
}
: {}),
...(checkedInputs.has(n) ? { formValue: "true", formState: "filled" } : {}),
...(selectedOptions.has(n) ? { formValue: attrs.value ?? textContent ?? "" } : {}),
});
}
return { nodes, excludedBackendNodeIds };
}
interface ParseFrameDocumentsResult {
frameGeometryIssues: FrameProjectionIssue[];
iframeNodes: CapturedIframeNodes;
frameOwnerBackendNodeIds: Map<string, number>;
frameParentIds: Map<string, string>;
frameExcludedBackendNodeIds: Map<string, ReadonlySet<number>>;
excludedBackendNodeIds: Set<number>;
}
@@ -647,6 +507,7 @@ async function parseChildFrameDocuments(
const iframeNodes: CapturedIframeNodes = new Map();
const frameOwnerBackendNodeIds = new Map<string, number>();
const frameParentIds = new Map<string, string>();
const frameExcludedBackendNodeIds = new Map<string, ReadonlySet<number>>();
const excludedBackendNodeIds = new Set<number>();
const parentDoc = documents[parentDocIndex];
const cdi = sparseIndexMap(parentDoc?.nodes?.contentDocumentIndex);
@@ -655,6 +516,7 @@ async function parseChildFrameDocuments(
iframeNodes,
frameOwnerBackendNodeIds,
frameParentIds,
frameExcludedBackendNodeIds,
excludedBackendNodeIds,
frameGeometryIssues,
};
@@ -732,13 +594,14 @@ async function parseChildFrameDocuments(
};
const nextVisited = new Set(visited);
nextVisited.add(childDocIndex);
const parsed = parseDocumentNodes(childDoc, strings, childContext);
const parsed = await normalizeDocument(childDoc, strings, childContext, signal);
iframeNodes.set(iframeBackendId, parsed.nodes);
if (childContext.frameId) {
frameOwnerBackendNodeIds.set(childContext.frameId, iframeBackendId);
frameExcludedBackendNodeIds.set(childContext.frameId, parsed.index.excludedBackendNodeIds);
if (parentContext.frameId) frameParentIds.set(childContext.frameId, parentContext.frameId);
}
for (const id of parsed.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
for (const id of parsed.index.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
const nested = await parseChildFrameDocuments(
documents,
@@ -759,6 +622,8 @@ async function parseChildFrameDocuments(
for (const [frameId, parentFrameId] of nested.frameParentIds) {
frameParentIds.set(frameId, parentFrameId);
}
for (const [frameId, excluded] of nested.frameExcludedBackendNodeIds)
frameExcludedBackendNodeIds.set(frameId, excluded);
for (const id of nested.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
}
@@ -766,6 +631,7 @@ async function parseChildFrameDocuments(
iframeNodes,
frameOwnerBackendNodeIds,
frameParentIds,
frameExcludedBackendNodeIds,
excludedBackendNodeIds,
frameGeometryIssues,
};
@@ -827,9 +693,9 @@ export async function captureViewModel(
scrollX,
scrollY,
};
const mainParsed = parseDocumentNodes(doc0, strings, topContext);
const mainParsed = await normalizeDocument(doc0, strings, topContext, options.signal);
const nodes = mainParsed.nodes;
const excludedBackendNodeIds = new Set(mainParsed.excludedBackendNodeIds);
const excludedBackendNodeIds = new Set(mainParsed.index.excludedBackendNodeIds);
const ownerIds = new Set<number>();
for (const document of documents) {
@@ -848,6 +714,11 @@ export async function captureViewModel(
options.signal,
);
const iframeNodes = frameParsed.iframeNodes;
if (topContext.frameId)
frameParsed.frameExcludedBackendNodeIds.set(
topContext.frameId,
mainParsed.index.excludedBackendNodeIds,
);
for (const id of frameParsed.excludedBackendNodeIds) {
excludedBackendNodeIds.add(id);
}
@@ -874,6 +745,7 @@ export async function captureViewModel(
frameNodes,
frameGeometryIssues: frameParsed.frameGeometryIssues,
frameOwnerBackendNodeIds: frameParsed.frameOwnerBackendNodeIds,
frameExcludedBackendNodeIds: frameParsed.frameExcludedBackendNodeIds,
frameParentIds: frameParsed.frameParentIds,
...(topContext.frameId ? { rootFrameId: topContext.frameId } : {}),
excludedBackendNodeIds,
+2 -104
View File
@@ -1,60 +1,6 @@
import type { Rect, Viewport } from "@browser-skill/vom";
import type { CdpFrame, CdpTarget } from "@/browser-driver/frame-graph";
import { isOverlayHostNode } from "@/lib/overlay-bridge";
import type { FrameProjectionIssue } from "../geometry/coordinate-types";
import type { FrameOwnedAxNode } from "./frame-document";
export interface CapturedNode {
backendNodeId: number;
parentBackendNodeId: number | null;
frameId?: string;
/** Owning iframe backend node id; `null` for the top-level document. */
ownerFrameBackendNodeId?: number | null;
tag: string;
attrs: Record<string, string>;
/** Top-level viewport-relative CSS px, clipped to the owning frame viewport. */
rect: Rect | null;
/** Frame-local viewport-relative CSS px before top-level projection. */
localRect?: Rect | null;
paintOrder: number;
position: string;
pointerEvents: string;
/**
* computed `cursor`. `cursor: pointer` is the strongest CDP-free signal
* that a non-semantic element (a `<div>`/`<span>` with a click handler)
* is actually an interactive control — used by the adapter to surface
* custom buttons/checkboxes the AX tree drops as `generic`. Optional like
* `textContent`: the live parser always sets it, hand-built fixtures may not.
*/
cursor?: string;
/**
* 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;
formDefaultValue?: string;
formPlaceholder?: string;
}
export interface CapturedSurfaceProbe {
triggerBackendNodeId: number;
triggerPoint?: { x: number; y: number };
triggerAction: "hover" | "focus" | string;
subItems: string[];
confidence?: "high" | "medium" | "low";
}
/** Narrow input shared by the existing semantic scene/hover consumers. */
export interface CapturedSceneInput {
nodes: CapturedNode[];
viewport: Viewport;
rootFrameId?: string;
excludedBackendNodeIds: ReadonlySet<number>;
}
import { captureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
/** Bounds retain their snapshot document CSS units until normalization. */
export interface SnapshotLayout {
@@ -82,54 +28,6 @@ export interface DecodedDocument {
nodes: DecodedNode[];
}
export interface CaptureIssue {
/** Owner failure or inherited blockage; absent for other geometry failures. */
projectionIssue?: FrameProjectionIssue;
target: CdpTarget;
frameId?: string;
stage: "dom" | "ax" | "ownership" | "geometry" | "forms";
reason: "capture-unavailable" | "frame-ownership-unresolved" | "geometry-unavailable";
}
export interface DocumentFacts<T extends FrameOwnedAxNode> {
readonly frame: CdpFrame;
readonly index: DocumentIndex;
readonly domNodes: CapturedNode[];
readonly axNodes: T[];
}
export interface ObservationFacts<T extends FrameOwnedAxNode> {
readonly rootFrameId: string;
readonly viewport: Viewport;
readonly documents: readonly DocumentFacts<T>[];
readonly issues: readonly CaptureIssue[];
readonly startedAt: number;
readonly finishedAt: number;
}
export function throwCaptureAborted(signal?: AbortSignal): void {
if (signal?.aborted) throw new DOMException("observation aborted", "AbortError");
}
export function isCaptureAbort(error: unknown): boolean {
return error instanceof Error && error.name === "AbortError";
}
/** Called only at bounded block boundaries, not once per node. */
export async function captureCheckpoint(signal?: AbortSignal): Promise<void> {
throwCaptureAborted(signal);
await new Promise<void>((resolve) => {
const channel = new MessageChannel();
channel.port1.onmessage = () => {
channel.port1.close();
channel.port2.close();
resolve();
};
channel.port2.postMessage(null);
});
throwCaptureAborted(signal);
}
/** All snapshot nodes participate, including document and shadow roots. This
* preserves overlay propagation when the semantic adapter omits those nodes. */
export async function buildDocumentIndex<T extends DecodedNode>(
+2 -2
View File
@@ -1,6 +1,6 @@
import type { CdpRunner } from "../shared";
import type { CapturedNode } from "./facts";
import { isCaptureAbort as isAbortError, throwCaptureAborted as throwIfAborted } from "./facts";
import { isAbortError, throwIfAborted } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
interface RuntimeEvaluateReply {
result?: { deepSerializedValue?: DeepSerializedValue };
@@ -0,0 +1,183 @@
import type { CdpFrame, CdpFrameGraph } from "@/browser-driver/frame-graph";
import { type GeometryProjection, projectRectToViewport } from "../geometry";
import { GeometryContext } from "../geometry/frame-context";
import { type CdpRunner, cdpRunnerForTarget, sendToCdpTarget } from "../shared";
import { type CapturedNode, type CapturedViewModel, captureViewModel } from "./capture";
import {
buildFrameDocuments,
type FrameAxBatch,
type FrameDocument,
type FrameOwnedAxNode,
} from "./frame-document";
export type FrameAxNode = FrameOwnedAxNode;
export type CapturedFrameDocument<T extends FrameAxNode> = FrameDocument<T>;
function throwIfAborted(signal?: AbortSignal): void {
if (signal?.aborted) throw new DOMException("observation aborted", "AbortError");
}
function isAbortError(err: unknown): boolean {
return err instanceof Error && err.name === "AbortError";
}
function transformFrameNodes(
nodes: CapturedNode[],
projection: GeometryProjection | null,
): CapturedNode[] {
return nodes.map((node) => ({
...node,
rect: projection
? (() => {
const bounds = projectRectToViewport(node.rect, projection);
return bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
})()
: null,
}));
}
async function captureMissingFrameDocuments(
cdp: CdpRunner,
tabId: number,
graph: CdpFrameGraph,
captured: CapturedViewModel,
geometry: GeometryContext,
signal?: AbortSignal,
): Promise<void> {
if (!captured.frameNodes) captured.frameNodes = new Map();
if (!captured.frameOwnerBackendNodeIds) captured.frameOwnerBackendNodeIds = new Map();
if (!captured.frameParentIds) captured.frameParentIds = new Map();
for (const frame of graph.frames) {
if (!frame.target.sessionId || captured.frameNodes.has(frame.frameId)) continue;
try {
const child = await captureViewModel(cdpRunnerForTarget(cdp, frame.target), tabId, {
signal,
geometry,
target: frame.target,
});
if (child.frameExcludedBackendNodeIds?.size) {
captured.frameExcludedBackendNodeIds ??= new Map();
for (const [id, excluded] of child.frameExcludedBackendNodeIds)
captured.frameExcludedBackendNodeIds.set(id, excluded);
}
if (child.frameGeometryIssues?.length) {
(captured.frameGeometryIssues ??= []).push(...child.frameGeometryIssues);
}
let projection: GeometryProjection | null = null;
try {
projection = await geometry.targetProjection(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);
if (rootFrameId !== frame.frameId && !childFrames.has(frame.frameId)) {
childFrames.set(
frame.frameId,
child.nodes.map((node) => ({ ...node, frameId: frame.frameId })),
);
}
for (const [childFrameId, nodes] of childFrames) {
captured.frameNodes.set(childFrameId, transformFrameNodes(nodes, projection));
}
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);
}
for (const [childFrameId, parentFrameId] of child.frameParentIds ?? []) {
captured.frameParentIds.set(childFrameId, parentFrameId);
}
} catch (err) {
if (isAbortError(err)) throw err;
console.debug("[bsk observation] child frame DOM capture failed", {
frameId: frame.frameId,
err,
});
}
}
}
async function captureAxTrees<T extends FrameAxNode>(
cdp: CdpRunner,
tabId: number,
discoveredFrames: CdpFrame[],
captured: CapturedViewModel,
signal?: AbortSignal,
): Promise<FrameAxBatch<T>[]> {
let frames = [...discoveredFrames];
const capturedFrameIds = [...(captured.frameNodes?.keys() ?? [])];
if (frames.length === 0) {
const rootFrameId = captured.rootFrameId ?? capturedFrameIds[0] ?? "root";
frames = [{ frameId: rootFrameId, target: { tabId } }];
}
for (const frameId of capturedFrameIds) {
if (!frames.some((frame) => frame.frameId === frameId)) {
frames.push({ frameId, target: { tabId } });
}
}
let firstFailure: unknown;
const trees = await Promise.all(
frames.map(async (frame): Promise<FrameAxBatch<T>> => {
try {
throwIfAborted(signal);
await sendToCdpTarget(cdp, frame.target, "Accessibility.enable", {});
const result = await sendToCdpTarget<{ nodes?: T[] }>(
cdp,
frame.target,
"Accessibility.getFullAXTree",
frame.frameId === "root" ? {} : { frameId: frame.frameId },
);
throwIfAborted(signal);
return {
frame,
nodes: result.nodes ?? [],
};
} catch (err) {
if (isAbortError(err)) throw err;
firstFailure ??= err;
console.debug("[bsk observation] frame AX capture failed", {
frameId: frame.frameId,
err,
});
return { frame, nodes: [] };
}
}),
);
const capturedNodeCount = [...captured.iframeNodes.values()].reduce(
(count, nodes) => count + nodes.length,
captured.nodes.length,
);
if (firstFailure && capturedNodeCount === 0 && trees.every((tree) => tree.nodes.length === 0)) {
throw firstFailure;
}
return trees;
}
export async function captureFrameData<T extends FrameAxNode>(
cdp: CdpRunner,
tabId: number,
captured: CapturedViewModel,
signal?: AbortSignal,
geometry = new GeometryContext(cdp, tabId, undefined, signal),
): Promise<CapturedFrameDocument<T>[]> {
const graph = await geometry.graph();
const frames = graph?.frames ?? [];
if (graph) await captureMissingFrameDocuments(cdp, tabId, graph, captured, geometry, signal);
throwIfAborted(signal);
const batches = await captureAxTrees<T>(cdp, tabId, frames, captured, signal);
return buildFrameDocuments(graph, batches, captured, signal);
}
+24 -19
View File
@@ -4,8 +4,8 @@ import {
type CdpTarget,
cdpTargetKey,
} from "@/browser-driver/frame-graph";
import type { CapturedNode } from "./facts";
import { captureCheckpoint } from "./facts";
import { captureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
export interface FrameOwnedAxNode {
nodeId: string;
@@ -32,6 +32,9 @@ export interface FrameDomInput {
nodes: CapturedNode[];
rootFrameId?: string;
frameNodes?: ReadonlyMap<string, CapturedNode[]>;
frameOwnerBackendNodeIds?: ReadonlyMap<string, number>;
frameParentIds?: ReadonlyMap<string, string>;
frameExcludedBackendNodeIds?: ReadonlyMap<string, ReadonlySet<number>>;
}
interface Ownership {
@@ -56,13 +59,27 @@ function targetBackendKey(target: CdpTarget, backendNodeId: number): string {
function frameList<T extends FrameOwnedAxNode>(
graph: CdpFrameGraph | null,
batches: FrameAxBatch<T>[],
captured: FrameDomInput,
): CdpFrame[] {
const frames = new Map<string, CdpFrame>();
for (const frame of graph?.frames ?? []) frames.set(frame.frameId, frame);
for (const batch of batches) {
if (!frames.has(batch.frame.frameId)) frames.set(batch.frame.frameId, batch.frame);
}
return [...frames.values()];
for (const frameId of captured.frameNodes?.keys() ?? []) {
if (!frames.has(frameId))
frames.set(frameId, { frameId, target: { tabId: batches[0]?.frame.target.tabId ?? 0 } });
}
return [...frames.values()].map((frame) => {
const ownerBackendNodeId =
frame.ownerBackendNodeId ?? captured.frameOwnerBackendNodeIds?.get(frame.frameId);
const parentFrameId = frame.parentFrameId ?? captured.frameParentIds?.get(frame.frameId);
return {
...frame,
...(ownerBackendNodeId !== undefined ? { ownerBackendNodeId } : {}),
...(parentFrameId ? { parentFrameId } : {}),
};
});
}
export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
@@ -70,10 +87,9 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
batches: FrameAxBatch<T>[],
captured: FrameDomInput,
signal?: AbortSignal,
unresolved?: (frame: CdpFrame) => void,
): Promise<FrameDocument<T>[]> {
let work = 0;
const frames = frameList(graph, batches);
const frames = frameList(graph, batches, captured);
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
const rootFrameId = graph?.rootFrameId ?? captured.rootFrameId ?? frames[0]?.frameId;
const domNodesForFrame = (frameId: string): CapturedNode[] =>
@@ -93,7 +109,6 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
if (work++ % 256 === 0) await captureCheckpoint(signal);
nodeById.set(node.nodeId, node);
}
let reported = false;
const ownershipByNodeId = new Map<string, Ownership>();
const resolveOwnership = async (node: T): Promise<Ownership> => {
const path: T[] = [];
@@ -109,18 +124,8 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
}
if (visiting.has(current.nodeId)) break;
visiting.add(current.nodeId);
if (current.frameId) {
const frame = frameById.get(current.frameId);
// An explicit contradiction must not fall through to a guessed owner.
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(batch.frame.target)) {
if (!reported) {
unresolved?.(batch.frame);
reported = true;
}
ownership = { frameId: "", strength: 0 };
break;
}
ownership = { frameId: frame.frameId, strength: 4 };
if (current.frameId && frameById.has(current.frameId)) {
ownership = { frameId: current.frameId, strength: 4 };
ownershipByNodeId.set(current.nodeId, ownership);
break;
}
@@ -148,7 +153,6 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
for (const node of batch.nodes) {
if (work++ % 256 === 0) await captureCheckpoint(signal);
const ownership = await resolveOwnership(node);
if (!ownership.frameId) continue;
const key = targetNodeKey(batch.frame.target, node.nodeId);
const existing = candidates.get(key);
if (!existing || ownership.strength > existing.ownership.strength) {
@@ -188,5 +192,6 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
contextScopeId: frame.frameId,
axNodes: axNodesByFrame.get(frame.frameId) ?? [],
domNodes: domNodesForFrame(frame.frameId),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(frame.frameId),
}));
}
+54 -218
View File
@@ -1,233 +1,69 @@
import type { Viewport } from "@browser-skill/vom";
import { type CdpFrame, type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
import { type GeometryProjection, projectRectToViewport } from "../geometry";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import {
type FrameProjectionState,
projectSnapshotRect,
snapshotViewportRect,
} from "../geometry/coordinate-types";
import { cssViewport, GeometryContext } from "../geometry/frame-context";
import type { CapturedNode } from "./facts";
import {
buildDocumentIndex,
type CaptureIssue,
captureCheckpoint,
type DocumentIndex,
isCaptureAbort,
type NodeFacts,
throwCaptureAborted,
} from "./facts";
import {
decodeDocument,
type SnapshotDocument,
type SnapshotReply,
snapshotFrameId,
} from "./snapshot";
import { captureCheckpoint } from "./capture-abort";
import { buildDocumentIndex, type DocumentIndex, type NodeFacts } from "./facts";
import { decodeDocument, type SnapshotDocument } from "./snapshot";
export interface FrameContext {
frameId?: string;
ownerFrameBackendNodeId: number | null;
projection: FrameProjectionState;
target: CdpTarget;
scrollX: number;
scrollY: number;
}
export interface NormalizedDocument {
nodes: NodeFacts[];
index: DocumentIndex;
frame: CdpFrame;
domNodes: CapturedNode[];
}
/** One target's snapshot. Source ownership is checked before interpreting any
* coordinates. Snapshot and live quad coordinates are deliberately not conflated. */
export async function normalizeSnapshot(
snapshot: SnapshotReply,
target: CdpTarget,
frames: readonly CdpFrame[],
geometry: GeometryContext,
issues: CaptureIssue[],
/** Interpret one document using a supplied projection. No live reads or frame scheduling. */
export async function normalizeDocument(
doc: SnapshotDocument,
strings: string[],
context: FrameContext,
signal?: AbortSignal,
rootFrameId?: string,
): Promise<NormalizedDocument[]> {
const strings = snapshot.strings ?? [];
const raw = snapshot.documents ?? [];
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
const sources = new Map<string, SnapshotDocument>();
for (const doc of raw) {
const id = snapshotFrameId(doc, strings);
if (!id || !frameById.has(id) || sources.has(id)) {
issues.push({
target,
frameId: id,
stage: "ownership",
reason: "frame-ownership-unresolved",
});
continue;
}
sources.set(id, doc);
}
let viewport: Viewport = { width: 0, height: 0 };
let scrollX = 0,
scrollY = 0;
try {
const measured = cssViewport(await geometry.layoutMetrics(target));
viewport = { width: measured.width, height: measured.height };
scrollX = measured.scrollX;
scrollY = measured.scrollY;
} catch (error) {
if (isCaptureAbort(error)) throw error;
}
const children = new Map<string, CdpFrame[]>();
const pending: CdpFrame[] = [];
for (const frame of frames) {
if (!frame.parentFrameId || !frameById.has(frame.parentFrameId)) pending.push(frame);
else {
const siblings = children.get(frame.parentFrameId);
if (siblings) siblings.push(frame);
else children.set(frame.parentFrameId, [frame]);
}
}
const projections = new Map<string, FrameProjectionState | null>();
const result: NormalizedDocument[] = [];
let targetProjection: GeometryProjection | null = null;
const targetRoot = rootFrameId ? frameById.get(rootFrameId) : undefined;
if (target.sessionId && targetRoot) {
try {
const known = await geometry.frame(targetRoot.frameId);
if (known && cdpTargetKey(known.target) === cdpTargetKey(target))
targetProjection = await geometry.targetProjection(targetRoot.frameId);
} catch (error) {
if (isCaptureAbort(error)) throw error;
}
}
const visited = new Set<string>();
const remaining = frames[Symbol.iterator]();
for (let cursor = 0; visited.size < frames.length; cursor++) {
if (cursor >= pending.length) {
let next = remaining.next();
while (!next.done && visited.has(next.value.frameId)) next = remaining.next();
if (next.done) break;
pending.push(next.value);
}
if (cursor % 256 === 0) await captureCheckpoint(signal);
const frame = pending[cursor];
if (visited.has(frame.frameId)) continue;
visited.add(frame.frameId);
for (const child of children.get(frame.frameId) ?? []) pending.push(child);
const doc = sources.get(frame.frameId);
if (!doc) continue;
const source = { target, frameId: frame.frameId };
const state: FrameProjectionState | null =
frame.frameId === rootFrameId
? {
status: "available",
projection: { source, geometry: { sourceClips: [], edges: [], topViewport: viewport } },
}
: (projections.get(frame.frameId) ?? null);
if (!state && frame.frameId !== rootFrameId)
issues.push({
target,
frameId: frame.frameId,
stage: "ownership",
reason: "frame-ownership-unresolved",
});
projections.set(frame.frameId, state);
const projection = state?.status === "available" ? state.projection : null;
if (!projection || (target.sessionId && !targetProjection))
issues.push({
target,
frameId: frame.frameId,
stage: "geometry",
reason: "geometry-unavailable",
...(state && state.status !== "available" ? { projectionIssue: state } : {}),
});
// Only direct siblings share this pool. Keep normalization in its existing
// breadth-first order, independent of owner read completion order.
const siblings = (children.get(frame.frameId) ?? []).filter((child) =>
sources.has(child.frameId),
): Promise<NormalizedDocument> {
const decoded = await decodeDocument(doc, strings, signal);
const nodes: NodeFacts[] = [];
for (let i = 0; i < decoded.nodes.length; i++) {
if (i % 256 === 0) await captureCheckpoint(signal);
const node = decoded.nodes[i];
const input = snapshotViewportRect(
node.layout?.bounds ?? [],
{ target: context.target, frameId: context.frameId },
{ x: context.scrollX, y: context.scrollY },
);
const edge = projection?.geometry.edges[0];
const clips = edge
? [edge.destinationQuad, ...(edge.destinationClips ?? [])]
: (projection?.geometry.sourceClips ?? []);
let next = 0;
let failure: unknown;
await Promise.all(
Array.from({ length: Math.min(4, siblings.length) }, async () => {
while (next < siblings.length && !signal?.aborted && !failure) {
const child = siblings[next++];
const childSource = { target, frameId: child.frameId };
if (!projection) {
projections.set(
child.frameId,
state && state.status !== "available"
? {
status: "blocked",
source: childSource,
cause: state.status === "blocked" ? state.cause : state,
}
: null,
);
continue;
}
if (child.ownerBackendNodeId === undefined) {
projections.set(child.frameId, null);
continue;
}
try {
projections.set(
child.frameId,
await geometry.snapshotProjection(
childSource,
child.ownerBackendNodeId,
clips,
viewport,
),
);
} catch (error) {
failure ??= error;
}
}
}),
);
// Join active reads and their cleanup before returning cancellation.
if (failure) throw failure;
throwCaptureAborted(signal);
const decoded = await decodeDocument(doc, strings, signal);
const nodes: NodeFacts[] = [];
for (let i = 0; i < decoded.nodes.length; i++) {
if (i % 256 === 0) await captureCheckpoint(signal);
const node = decoded.nodes[i];
const input = snapshotViewportRect(node.layout?.bounds ?? [], source, {
x: doc.scrollOffsetX ?? (frame.frameId === rootFrameId ? scrollX : 0),
y: doc.scrollOffsetY ?? (frame.frameId === rootFrameId ? scrollY : 0),
});
const local = input?.rect;
let rect = input && projection ? projectSnapshotRect(input, projection) : null;
if (rect && target.sessionId)
rect = targetProjection
? projectRectToViewport(
{ x: rect.x, y: rect.y, w: rect.width, h: rect.height },
targetProjection,
)
: null;
const styles = node.layout?.styles;
const visibility = styles?.visibility || "visible";
const opacity = styles?.opacity || "1";
nodes.push({
...node,
frameId: frame.frameId,
ownerFrameBackendNodeId: frame.ownerBackendNodeId ?? null,
localRect: local ? { x: local.x, y: local.y, w: local.width, h: local.height } : null,
rect: rect ? { x: rect.x, y: rect.y, w: rect.width, h: rect.height } : null,
rendered:
!!local &&
visibility !== "hidden" &&
visibility !== "collapse" &&
(Number.parseFloat(opacity) || 0) > 0,
});
}
const index = await buildDocumentIndex(nodes, signal);
const domNodes = nodes.filter((node) => !node.tag.startsWith("#"));
result.push({
index,
frame,
domNodes,
const local = input?.rect;
const rect =
input && context.projection.status === "available"
? projectSnapshotRect(input, context.projection.projection)
: null;
const visibility = node.layout?.styles.visibility || "visible";
const opacity = node.layout?.styles.opacity || "1";
nodes.push({
...node,
...(context.frameId ? { frameId: context.frameId } : {}),
ownerFrameBackendNodeId: context.ownerFrameBackendNodeId,
localRect: local ? { x: local.x, y: local.y, w: local.width, h: local.height } : null,
rect: rect ? { x: rect.x, y: rect.y, w: rect.width, h: rect.height } : null,
rendered:
!!local &&
visibility !== "hidden" &&
visibility !== "collapse" &&
(Number.parseFloat(opacity) || 0) > 0,
});
}
return result;
const index = await buildDocumentIndex(nodes, signal);
return {
nodes: nodes.filter(
(node) => !node.tag.startsWith("#") && !index.excludedBackendNodeIds.has(node.backendNodeId),
),
index,
};
}
+4 -70
View File
@@ -1,6 +1,6 @@
import { type CdpFrame, type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
import type { CapturedNode } from "./facts";
import { captureCheckpoint, type DecodedDocument, type DecodedNode } from "./facts";
import { captureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import type { DecodedDocument, DecodedNode } from "./facts";
export const REQUESTED_STYLES = [
"position",
"pointer-events",
@@ -23,7 +23,6 @@ interface RareBooleanData {
export interface SnapshotDocument {
frameId?: string | number;
documentURL?: number;
scrollOffsetX?: number;
scrollOffsetY?: number;
nodes?: {
@@ -87,7 +86,7 @@ function str(strings: string[], idx: number | undefined): string {
return strings[idx] ?? "";
}
function sparseIndexMap(sparse: SparseArray | undefined): Map<number, number> {
export function sparseIndexMap(sparse: SparseArray | undefined): Map<number, number> {
const out = new Map<number, number>();
if (!sparse?.index || !sparse.value) return out;
for (let i = 0; i < sparse.index.length; i++) {
@@ -213,68 +212,3 @@ export async function decodeDocument(
}
return { nodes };
}
/** Snapshot membership and same-target edges are current response evidence.
* The earlier graph only supplies compatible metadata and cross-target edges. */
export function describeSnapshotFrames(
snapshot: SnapshotReply,
target: CdpTarget,
hintById: ReadonlyMap<string, CdpFrame>,
pageUrl?: string,
): { frames: CdpFrame[]; ids: Set<string>; rootFrameId?: string } {
const raw = snapshot.documents ?? [];
const strings = snapshot.strings ?? [];
const ids = new Set<string>();
const invalid = new Set<string>();
const frames = raw.map((doc) => {
const frameId = snapshotFrameId(doc, strings);
if (!frameId) return undefined;
if (ids.has(frameId)) invalid.add(frameId);
ids.add(frameId);
const hint = hintById.get(frameId);
const compatible =
hint && cdpTargetKey(hint.target) === cdpTargetKey(target) ? hint : undefined;
const url =
(doc.documentURL === undefined ? undefined : strings[doc.documentURL]) || compatible?.url;
return { frameId, target, ...(url ? { url } : {}) } as CdpFrame;
});
const root = frames[0];
if (root) {
const hint = hintById.get(root.frameId);
const parent = hint?.parentFrameId ? hintById.get(hint.parentFrameId) : undefined;
if (
target.sessionId &&
hint &&
cdpTargetKey(hint.target) === cdpTargetKey(target) &&
parent &&
cdpTargetKey(parent.target) !== cdpTargetKey(target)
) {
root.parentFrameId = parent.frameId;
root.ownerBackendNodeId = hint.ownerBackendNodeId;
}
if (!target.sessionId && !root.url && pageUrl) root.url = pageUrl;
}
const owned = new Set<string>();
for (let i = 0; i < raw.length; i++) {
const edges = raw[i].nodes?.contentDocumentIndex;
const parent = frames[i];
if (!parent || !edges) continue;
for (let e = 0; e < edges.index.length; e++) {
const child = frames[edges.value[e]];
const owner = raw[i].nodes?.backendNodeId?.[edges.index[e]];
if (!child || owner === undefined) continue;
if (child === root || child === parent || owned.has(child.frameId)) {
invalid.add(child.frameId);
continue;
}
owned.add(child.frameId);
child.parentFrameId = parent.frameId;
child.ownerBackendNodeId = owner;
}
}
return {
frames: frames.filter((frame): frame is CdpFrame => !!frame && !invalid.has(frame.frameId)),
ids,
rootFrameId: root?.frameId,
};
}