Merge pull request #200 from Tencent/fix/observation-document-consistency

refactor(observation):  unify cross-frame capture coordination and data ownership | 统一跨 frame 采集协调与数据归属
This commit is contained in:
Hannah Liu
2026-09-09 16:25:52 +08:00
committed by GitHub
14 changed files with 2335 additions and 1589 deletions
File diff suppressed because it is too large Load Diff
@@ -1,10 +1,8 @@
// @vitest-environment node
import { describe, expect, it } from "vitest";
import type { CdpFrame, CdpFrameGraph, CdpTarget } from "@/browser-driver/frame-graph";
import { GeometryContext } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
import { captureViewModel } from "../vom/capture";
import { captureFrameData } from "../vom/frame-capture";
import { captureObservationFacts } from "../vom/capture-coordinator";
type Send = <T = Record<string, unknown>>(
method: string,
@@ -180,14 +178,12 @@ describe.skipIf(!process.env.BSK_GEOMETRY_CHROME)("real DOMSnapshot coordinate c
);
oracles.set(frame.frameId, reply.result.value);
}
const geometry = new GeometryContext(cdp, 1, graph);
const captured = await captureViewModel(cdp, 1, { geometry });
await captureFrameData(cdp, 1, captured, undefined, geometry);
expect(captured.frameGeometryIssues).toEqual([]);
const facts = await captureObservationFacts(cdp, 1);
expect(facts.issues).toEqual([]);
for (const frame of frames) {
const node = captured.frameNodes
?.get(frame.frameId)
?.find((node) => node.attrs.id === "probe");
const node = facts.documents
.find((doc) => doc.frame.frameId === frame.frameId)
?.domNodes.find((node) => node.attrs.id === "probe");
expect(node, `missing probe in ${names.get(frame.frameId) || "root"}`).toBeDefined();
const local = oracles.get(frame.frameId)!.probe;
const top = { ...local };
@@ -206,7 +202,7 @@ describe.skipIf(!process.env.BSK_GEOMETRY_CHROME)("real DOMSnapshot coordinate c
frame: names.get(frame.frameId),
local,
top,
viewport: captured.viewport,
viewport: facts.viewport,
}),
).not.toBeNull();
for (const key of ["x", "y", "w", "h"] as const) {
+26 -227
View File
@@ -1,3 +1,4 @@
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
@@ -35,7 +36,6 @@ 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,
@@ -49,15 +49,9 @@ import {
type ToolEffect,
} from "./shared";
import { resolveSnapshotRef } from "./snapshot-ref";
import {
type CapturedNode,
type CapturedSurfaceProbe,
type CapturedViewModel,
captureViewModel,
collectOverlayExcludedBackendIds,
probeHoverSurfaces,
} from "./vom/capture";
import { type CapturedFrameDocument, captureFrameData } from "./vom/frame-capture";
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 { withOverlayBypass } from "./vom/hover-perception";
import { probeTooltipNames } from "./vom/name-enrichment";
import {
@@ -531,7 +525,7 @@ function buildActiveScopeBlocks(nodes: VomNode[], signals: VomNodeDomSignals): A
function buildConditionalSurfaces(
nodes: VomNode[],
captured: CapturedViewModel,
captured: CapturedSceneInput,
probes: CapturedSurfaceProbe[],
): CondSurface[] {
if (probes.length === 0) return [];
@@ -661,163 +655,9 @@ 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: CapturedViewModel,
captured: CapturedSceneInput,
options: BuildVomSceneOptions = {},
): VomScene {
const scene = buildSemanticVomScene({
@@ -833,7 +673,7 @@ export function buildFrameVomScene(
function attachCapturedSceneAnnotations(
scene: VomScene,
documents: VomFrameDocument[],
captured: CapturedViewModel,
captured: CapturedSceneInput,
surfaceProbes: CapturedSurfaceProbe[],
): VomScene {
const rootDocument = documents.find((document) => document.frameId === scene.rootFrameId);
@@ -983,45 +823,6 @@ 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;
@@ -1054,7 +855,7 @@ const NO_HOVER_PROBES: HoverProbeOutcome = {
async function runHoverProbes(
cdp: CdpRunner,
tabId: number,
captured: CapturedViewModel,
captured: CapturedSceneInput,
documents: VomFrameDocument[],
staticSemantics: ReturnType<typeof resolveSemanticGraph>,
options: CaptureVomObservationOptions,
@@ -1093,21 +894,9 @@ export async function captureVomObservation(
throwIfAborted(options.signal, "observation");
await cdp.ensureAttachedToUrl?.(tabId, url);
throwIfAborted(options.signal, "observation");
const geometry = new GeometryContext(cdp, tabId, undefined, options.signal);
const captured = await captureForVom(cdp, tabId, options, geometry);
const facts = await captureObservationFacts<CdpAxNode>(cdp, tabId, options.signal, url);
const { captured, documents: normalizedDocuments } = semanticCapture(facts);
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,
@@ -1137,19 +926,29 @@ 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 = captured.frameGeometryIssues?.length
? "@warning geometry incomplete: some page or frame content has no top-level coordinates.\n"
: "";
const notices: string[] = [];
if (facts.issues.some((issue) => issue.stage === "geometry"))
notices.push(
"@warning geometry incomplete: some page or frame content has no top-level coordinates.",
);
const incompleteStages = ["dom", "ax", "forms", "ownership"].filter((stage) =>
facts.issues.some((issue) => issue.stage === stage),
);
if (incompleteStages.length)
notices.push(
`@warning observation incomplete: some ${incompleteStages.join(", ")} data is unavailable or omitted.`,
);
const captureNotice = notices.join("\n");
const rendered = renderVom(decoratedScene, {
maxDepth: options.maxDepth,
maxTokens:
!geometryNotice || options.maxTokens === undefined
!captureNotice || options.maxTokens === undefined
? options.maxTokens
: Math.max(0, options.maxTokens - Math.ceil(geometryNotice.length / 4)),
: Math.max(0, options.maxTokens - Math.ceil((captureNotice.length + 1) / 4)),
redactValues: options.redactValues,
activeRegionPolicy: options.activeRegionPolicy,
});
if (geometryNotice) rendered.text += `\n${geometryNotice.trimEnd()}`;
if (captureNotice) rendered.text += `\n${captureNotice}`;
throwIfAborted(options.signal, "observation");
return projectRecordSafeObservation({
rootFrameId: captured.rootFrameId ?? normalizedDocuments[0]?.frameId ?? "root",
File diff suppressed because it is too large Load Diff
@@ -1,7 +1,7 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "../../../lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import { captureViewModel, collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
import { collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
import { captureObservationFacts, semanticCapture } from "../capture-coordinator";
// Minimal but format-accurate captureSnapshot reply: a body with one
// fixed full-screen overlay div carrying a password input.
@@ -27,6 +27,7 @@ function fakeSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 2],
nodeType: [1, 1, 1, 1],
@@ -74,6 +75,7 @@ function hoverTriggerSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeType: [1, 1, 1],
@@ -118,6 +120,7 @@ function twoHoverTriggerSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 1],
nodeType: [1, 1, 1, 1],
@@ -171,6 +174,7 @@ function nestedHoverTriggerSnapshotReply() {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 2, 3],
nodeType: [1, 1, 1, 1, 1],
@@ -248,13 +252,11 @@ function makeCdp(snapshot: unknown) {
};
}
describe("captureViewModel", () => {
describe("snapshot capture and hover", () => {
it("parses nodes, attrs, rects, paint order and styles", async () => {
const { nodes, viewport, iframeNodes } = await captureViewModel(
makeCdp(fakeSnapshotReply()),
4,
);
expect(iframeNodes.size).toBe(0);
const { nodes, viewport } = semanticCapture(
await captureObservationFacts(makeCdp(fakeSnapshotReply()), 4),
).captured;
expect(viewport).toEqual({ width: 1000, height: 800 });
const div = nodes.find((n) => n.backendNodeId === 12);
expect(div).toMatchObject({ tag: "div", position: "fixed", parentBackendNodeId: 11 });
@@ -266,35 +268,11 @@ describe("captureViewModel", () => {
it("never hovers the page while capturing", async () => {
const cdp = makeCdp(fakeSnapshotReply());
await captureViewModel(cdp, 4);
semanticCapture(await captureObservationFacts(cdp, 4)).captured;
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 = {
@@ -336,7 +314,7 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = await captureViewModel(cdp, 4);
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
expect(surfaceProbes).toEqual([
@@ -398,7 +376,7 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = await captureViewModel(cdp, 4);
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
expect(surfaceProbes).toEqual([
@@ -445,7 +423,7 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = await captureViewModel(cdp, 4);
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
await probeHoverSurfaces(cdp, 4, captured.nodes);
expect(hoverMoves).toBe(1);
@@ -477,6 +455,7 @@ describe("captureViewModel", () => {
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")],
@@ -507,7 +486,7 @@ describe("captureViewModel", () => {
],
};
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
const ids = nodes.map((n) => n.backendNodeId);
// Real page nodes survive.
expect(ids).toContain(12);
@@ -538,9 +517,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: "main",
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")],
@@ -571,12 +548,10 @@ describe("captureViewModel", () => {
],
};
const { excludedBackendNodeIds, frameExcludedBackendNodeIds } = await captureViewModel(
makeCdp(snapshot),
4,
);
const { excludedBackendNodeIds } = semanticCapture(
await captureObservationFacts(makeCdp(snapshot), 4),
).captured;
expect(excludedBackendNodeIds).toEqual(new Set([13, 14, 15]));
expect(frameExcludedBackendNodeIds?.get("main")).toEqual(excludedBackendNodeIds);
});
it("excludes overlay host matched by tag name only", async () => {
@@ -596,6 +571,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i(OVERLAY_HOST_NAME)],
@@ -618,7 +594,9 @@ describe("captureViewModel", () => {
],
};
const { nodes, excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
const { nodes, excludedBackendNodeIds } = semanticCapture(
await captureObservationFacts(makeCdp(snapshot), 4),
).captured;
expect(nodes.map((n) => n.backendNodeId)).not.toContain(13);
expect(excludedBackendNodeIds).toEqual(new Set([13]));
});
@@ -641,6 +619,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -663,7 +642,9 @@ describe("captureViewModel", () => {
],
};
const { nodes, excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
const { nodes, excludedBackendNodeIds } = semanticCapture(
await captureObservationFacts(makeCdp(snapshot), 4),
).captured;
expect(nodes.map((n) => n.backendNodeId)).not.toContain(13);
expect(excludedBackendNodeIds).toEqual(new Set([13]));
});
@@ -686,6 +667,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -708,7 +690,7 @@ describe("captureViewModel", () => {
},
],
};
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
expect(nodes.find((n) => n.backendNodeId === 12)?.cursor).toBe("pointer");
expect(nodes.find((n) => n.backendNodeId === 11)?.cursor).toBe("auto");
});
@@ -720,6 +702,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1, 1, 1],
nodeName: [i("html"), i("body"), i("button"), i("button"), i("button")],
@@ -746,7 +729,7 @@ describe("captureViewModel", () => {
],
};
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
expect(nodes.find((node) => node.backendNodeId === 12)?.rendered).toBe(true);
expect(nodes.find((node) => node.backendNodeId === 13)?.rendered).toBe(false);
@@ -768,51 +751,12 @@ describe("captureViewModel", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = await captureViewModel(cdp, 4);
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const div = nodes.find((n) => n.backendNodeId === 12);
expect(div?.localRect?.y).toBe(-200);
expect(div?.rect).toMatchObject({ y: 0, h: 600 });
});
it("normalizes snapshot-owned scroll before using a stale CSS metrics fallback", async () => {
const snapshot = {
strings: ["html", "button"],
documents: [
{
frameId: "root",
scrollOffsetX: 40,
scrollOffsetY: 200,
nodes: {
parentIndex: [-1, 0],
nodeName: [0, 1],
backendNodeId: [10, 11],
attributes: [[], []],
},
layout: { nodeIndex: [1], bounds: [[200, 800, 240, 80]] },
},
],
};
const cdp: CdpRunner = {
send: vi.fn(async (_tab: number, method: string) => {
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics")
return {
visualViewport: { clientWidth: 2000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 999, pageY: 999 },
};
return {};
}) as CdpRunner["send"],
};
const captured = await captureViewModel(cdp, 4);
expect(captured.nodes.find((node) => node.backendNodeId === 11)).toMatchObject({
localRect: { x: 80, y: 300, w: 120, h: 40 },
rect: { x: 80, y: 300, w: 120, h: 40 },
rendered: true,
});
expect(captured.frameGeometryIssues).toEqual([]);
});
it("normalizes raw snapshot bounds before viewport clipping", async () => {
const S = ["html", "body", "div", "position", "fixed", "static", "pointer-events", "auto"];
const i = (s: string) => S.indexOf(s);
@@ -820,6 +764,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -856,7 +801,7 @@ describe("captureViewModel", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = await captureViewModel(cdp, 4);
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
expect(nodes.find((n) => n.backendNodeId === 12)?.rect).toEqual({
x: 0,
y: 0,
@@ -892,6 +837,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
@@ -932,7 +878,7 @@ describe("captureViewModel", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = await captureViewModel(cdp, 4);
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
const btn = nodes.find((n) => n.backendNodeId === 12);
expect(btn?.textContent).toBe("登录");
const link = nodes.find((n) => n.backendNodeId === 14);
@@ -942,7 +888,7 @@ describe("captureViewModel", () => {
expect(body?.textContent).toBeUndefined();
});
it("parses iframe sub-documents and returns iframeNodes keyed by iframe backendNodeId", async () => {
it("retains explicit iframe document ownership and projected nodes", async () => {
const S = [
"html",
"body",
@@ -1030,30 +976,21 @@ describe("captureViewModel", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
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 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 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(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");
expect(facts.rootFrameId).toBe("main-frame");
expect(child.frame.ownerBackendNodeId).toBe(13);
expect(child.frame.parentFrameId).toBe("main-frame");
});
it("projects iframe documents independently of owner snapshot geometry", async () => {
@@ -1074,6 +1011,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
@@ -1091,6 +1029,7 @@ describe("captureViewModel", () => {
},
},
{
frameId: "child",
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
@@ -1129,8 +1068,10 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { iframeNodes } = await captureViewModel(cdp, 4);
const input = iframeNodes.get(13)?.find((n) => n.backendNodeId === 101);
const { documents } = await captureObservationFacts(cdp, 4);
const input = documents
.find((doc) => doc.frame.frameId === "child")
?.domNodes?.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 });
@@ -1154,6 +1095,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("iframe")],
@@ -1177,6 +1119,7 @@ describe("captureViewModel", () => {
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: "child",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("iframe")],
@@ -1200,6 +1143,7 @@ describe("captureViewModel", () => {
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: "nested",
nodes: {
parentIndex: [-1, 0],
nodeName: [i("body"), i("input")],
@@ -1257,9 +1201,13 @@ describe("captureViewModel", () => {
) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
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);
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);
expect(nestedIframe?.localRect).toEqual({ x: 5, y: 6, w: 100, h: 80 });
expect(nestedIframe?.rect).toEqual({ x: 15, y: 26, w: 100, h: 80 });
@@ -1275,6 +1223,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "root",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("div")],
@@ -1311,7 +1260,7 @@ describe("captureViewModel", () => {
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = await captureViewModel(cdp, 4);
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 / 2 - 100);
});
@@ -1337,200 +1286,3 @@ describe("captureViewModel", () => {
expect(excluded).toEqual(new Set([200, 201, 202]));
});
});
// 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[]) => ({
scrollOffsetX: 0,
scrollOffsetY: 0,
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 {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
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 {
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("sibling frame measurement scheduling", () => {
it("batches same-target owner sizes without changing projected results", async () => {
const fixture = siblingCaptureFixture();
const original = fixture.cdp.send;
const methods: string[] = [];
fixture.cdp.send = async (tabId, method, params) => {
methods.push(method);
if (method === "Runtime.evaluate")
return {
result: {
deepSerializedValue: {
type: "array",
value: [100, 101, 102, 103, 104, 105, 200].map((backendNodeId) => ({
type: "array",
value: [
{ type: "node", value: { backendNodeId } },
{ type: "string", value: JSON.stringify({ width: 200, height: 100 }) },
],
})),
},
},
} as never;
return original(tabId, method, params);
};
const captured = await captureViewModel(fixture.cdp, 4);
expect(captured.frameGeometryIssues).toEqual([]);
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
expect(captured.iframeNodes.get(200)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect(methods.filter((method) => method === "DOM.getBoxModel")).toHaveLength(7);
expect(methods.filter((method) => method === "Runtime.evaluate")).toHaveLength(1);
expect(methods.filter((method) => method === "Runtime.releaseObjectGroup")).toHaveLength(1);
expect(methods).not.toContain("DOM.resolveNode");
expect(methods).not.toContain("Runtime.callFunctionOn");
});
it("bounds concurrent reads, fills free slots and preserves depth-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 = captureViewModel(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.frameGeometryIssues).toEqual([]);
expect(fixture.peak()).toBe(4);
expect(fixture.active()).toBe(0);
expect(fixture.measured()).toEqual([100, 101, 102, 103, 104, 105, 200]);
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
expect(captured.iframeNodes.get(200)?.[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 captureViewModel(fixture.cdp, 4);
expect(captured.frameGeometryIssues).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4 }, frameId: "frame-1" },
ownerBackendNodeId: 100,
},
{
status: "blocked",
source: { target: { tabId: 4 }, frameId: "frame-7" },
cause: captured.frameGeometryIssues?.[0],
},
]);
expect(fixture.measured()).not.toContain(200);
expect(captured.iframeNodes.get(200)?.[0]).toMatchObject({
tag: "body",
rect: null,
localRect: { x: 0, y: 0, w: 200, h: 100 },
});
expect(captured.iframeNodes.get(101)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
});
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 = captureViewModel(fixture.cdp, 4, { signal: 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,
);
});
});
@@ -1,289 +0,0 @@
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: [
{
scrollOffsetX: 0,
scrollOffsetY: 0,
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 {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
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 {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
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 {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
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 {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
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: null, rendered: true }),
);
});
});
@@ -1,7 +1,12 @@
import { describe, expect, it } from "vitest";
import { describe, expect, it, vi } from "vitest";
import type { CdpFrameGraph } from "@/browser-driver/frame-graph";
import type { CapturedNode, CapturedViewModel } from "../capture";
import { buildFrameDocuments, type FrameAxBatch, type FrameOwnedAxNode } from "../frame-document";
import type { CapturedNode } from "../capture";
import {
buildFrameDocuments,
type FrameAxBatch,
type FrameDomInput,
type FrameOwnedAxNode,
} from "../frame-document";
function domNode(frameId: string, backendNodeId: number): CapturedNode {
return {
@@ -17,14 +22,11 @@ function domNode(frameId: string, backendNodeId: number): CapturedNode {
};
}
function captured(frameNodes: Map<string, CapturedNode[]>): CapturedViewModel {
function captured(frameNodes: Map<string, CapturedNode[]>): FrameDomInput {
return {
nodes: frameNodes.get("main") ?? [],
viewport: { width: 800, height: 600 },
iframeNodes: new Map(),
frameNodes,
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
}
@@ -157,10 +159,12 @@ 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 } },
frame: {
frameId,
target: { tabId: 4 },
...(frameId === "child" ? { parentFrameId: "left", ownerBackendNodeId: 7 } : {}),
},
nodes: [],
}));
@@ -171,6 +175,23 @@ 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 +1,357 @@
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 {
isAbortError as isCaptureAbort,
throwIfAborted as throwCaptureAborted,
} from "./capture-abort";
import type { CapturedSceneInput } from "./facts";
import { buildDocumentIndex, type CaptureIssue, type ObservationFacts } from "./facts";
import { enrichFormControlStates } from "./form-capture";
import {
buildFrameDocuments,
type FrameAxBatch,
type FrameDocument,
type FrameOwnedAxNode,
} from "./frame-document";
import { type NormalizedFrameDocument, normalizeSnapshot } from "./normalize";
import { describeSnapshotFrames, REQUESTED_STYLES, type SnapshotReply } from "./snapshot";
interface TargetBatch<T extends FrameOwnedAxNode> {
target: CdpTarget;
frames: CdpFrame[];
documents: NormalizedFrameDocument[];
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 collectTasks<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;
const axReady = new Set<TargetBatch<T>>();
await collectTasks(
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.nodes),
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;
}
axReady.add(batch);
},
signal,
);
// Schedule AX by frame across all ready targets, rather than nesting pools.
// Keep result slots in source order even when CDP replies arrive out of order.
const axTasks: { batch: TargetBatch<T>; frame: CdpFrame; result?: FrameAxBatch<T> }[] =
batches.flatMap((batch) =>
axReady.has(batch) ? batch.frames.map((frame) => ({ batch, frame })) : [],
);
await collectTasks(
axTasks,
async (task) => {
const { batch, frame } = task;
try {
throwCaptureAborted(signal);
const result = await cdpRunnerForTarget(cdp, batch.target).send<{ nodes?: T[] }>(
tabId,
"Accessibility.getFullAXTree",
frame.frameId === "root" ? {} : { frameId: frame.frameId },
);
throwCaptureAborted(signal);
task.result = { frame, nodes: result.nodes ?? [] };
} catch (error) {
throwCaptureAborted(signal);
if (isCaptureAbort(error)) throw error;
firstFailure ??= error;
unavailable(batch, "ax", frame.frameId);
}
},
signal,
);
for (const task of axTasks) if (task.result) task.batch.ax.push(task.result);
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;
}
// 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 rootBatch = batches.find((batch) => !batch.target.sessionId);
const rootFrameId =
rootBatch?.rootFrameId ?? graph?.rootFrameId ?? rootBatch?.frames[0]?.frameId ?? "root";
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",
});
}
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.nodes])),
frameExcludedBackendNodeIds: new Map(
[...decoded].map(([id, doc]) => [id, doc.index.excludedBackendNodeIds]),
),
},
signal,
(frame) =>
issues.push({
target: frame.target,
frameId: frame.frameId,
stage: "ownership",
reason: "frame-ownership-unresolved",
}),
);
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,
excludedBackendNodeIds: _excluded,
...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(),
},
};
}
+10 -351
View File
@@ -1,67 +1,18 @@
// 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";
// Browser-side hover probes and overlay exclusion fallback. Static collection
// lives in capture-coordinator; snapshot decoding has no browser dependency.
import { evaluateHoverTrigger } from "@/lib/hover-trigger-policy";
import { OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
import {
type FrameProjectionIssue,
type FrameProjectionState,
snapshotCoordinates,
} from "../geometry/coordinate-types";
import {
GeometryContext,
type LayoutMetrics,
snapshotLayoutScale,
} from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
import { isAbortError, throwIfAborted } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import { enrichFormControlStates } from "./form-capture";
import type { CapturedSurfaceProbe } from "./facts";
export type {
CapturedNode,
CapturedSurfaceProbe,
} from "./facts";
import { isAbortError, throwIfAborted } from "./capture-abort";
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?: {
@@ -492,295 +443,3 @@ export async function collectOverlayExcludedBackendIds(
}
return excluded;
}
interface ParseFrameDocumentsResult {
frameGeometryIssues: FrameProjectionIssue[];
iframeNodes: CapturedIframeNodes;
frameOwnerBackendNodeIds: Map<string, number>;
frameParentIds: Map<string, string>;
frameExcludedBackendNodeIds: Map<string, ReadonlySet<number>>;
excludedBackendNodeIds: Set<number>;
}
async function parseChildFrameDocuments(
documents: SnapshotDocument[],
strings: string[],
parentDocIndex: number,
parentContext: FrameContext,
geometry: GeometryContext,
signal?: AbortSignal,
visited = new Set<number>(),
): Promise<ParseFrameDocumentsResult> {
const frameGeometryIssues: FrameProjectionIssue[] = [];
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);
if (cdi.size === 0) {
return {
iframeNodes,
frameOwnerBackendNodeIds,
frameParentIds,
frameExcludedBackendNodeIds,
excludedBackendNodeIds,
frameGeometryIssues,
};
}
const parentBackendIds = parentDoc?.nodes?.backendNodeId ?? [];
const children = [...cdi].flatMap(([nodeArrayIdx, childDocIndex]) => {
const childDoc = documents[childDocIndex];
const iframeBackendId = parentBackendIds[nodeArrayIdx];
if (visited.has(childDocIndex) || !childDoc || iframeBackendId === undefined) return [];
const source = { target: parentContext.target, frameId: snapshotFrameId(childDoc, strings) };
const coordinates = snapshotCoordinates(childDoc, parentContext.layoutUnitsPerCssPixel);
const parent = parentContext.projection;
const projection: FrameProjectionState =
parent.status === "available"
? coordinates
? { status: "unavailable", source, ownerBackendNodeId: iframeBackendId }
: { status: "unavailable", source, reason: "snapshot-coordinates-unavailable" }
: { status: "blocked", source, cause: parent.status === "blocked" ? parent.cause : parent };
return [
{
childDocIndex,
childDoc,
iframeBackendId,
source,
coordinates,
projection: projection as FrameProjectionState,
},
];
});
const parentProjection =
parentContext.projection.status === "available"
? parentContext.projection.projection.geometry
: null;
if (parentProjection) {
// Measure only direct siblings. Recursion starts after these workers finish,
// so descendants never hold or recursively acquire a measurement slot.
const edge = parentProjection.edges[0];
const clips = edge
? [edge.destinationQuad, ...(edge.destinationClips ?? [])]
: parentProjection.sourceClips;
let cursor = 0;
let failure: unknown;
await Promise.all(
Array.from({ length: Math.min(4, children.length) }, async () => {
while (cursor < children.length && !signal?.aborted && !failure) {
const child = children[cursor++];
if (!child.coordinates) continue;
try {
// Owner quads are target-relative; do not apply the parent transform twice.
child.projection = await geometry.snapshotProjection(
child.source,
child.iframeBackendId,
clips,
parentProjection.topViewport,
);
} catch (error) {
failure ??= error;
}
}
}),
);
// Join all active reads, including object cleanup, before propagating abort.
if (failure) throw failure;
}
throwIfAborted(signal);
// Completion order must not change document traversal or result insertion order.
for (const {
childDocIndex,
childDoc,
iframeBackendId,
source,
projection,
coordinates,
} of children) {
throwIfAborted(signal);
if (projection.status !== "available") frameGeometryIssues.push(projection);
const childContext: FrameContext = {
frameId: source.frameId,
target: source.target,
ownerFrameBackendNodeId: iframeBackendId,
projection,
coordinates,
layoutUnitsPerCssPixel: parentContext.layoutUnitsPerCssPixel,
};
const nextVisited = new Set(visited);
nextVisited.add(childDocIndex);
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.index.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
const nested = await parseChildFrameDocuments(
documents,
strings,
childDocIndex,
childContext,
geometry,
signal,
nextVisited,
);
frameGeometryIssues.push(...nested.frameGeometryIssues);
for (const [nestedFrameId, nestedNodes] of nested.iframeNodes) {
iframeNodes.set(nestedFrameId, nestedNodes);
}
for (const [frameId, ownerBackendNodeId] of nested.frameOwnerBackendNodeIds) {
frameOwnerBackendNodeIds.set(frameId, ownerBackendNodeId);
}
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);
}
return {
iframeNodes,
frameOwnerBackendNodeIds,
frameParentIds,
frameExcludedBackendNodeIds,
excludedBackendNodeIds,
frameGeometryIssues,
};
}
export async function captureViewModel(
cdp: CdpRunner,
tabId: number,
options: CaptureViewModelOptions = {},
): Promise<CapturedViewModel> {
throwIfAborted(options.signal);
const target = options.target ?? { tabId };
const geometry = options.geometry ?? new GeometryContext(cdp, tabId, undefined, options.signal);
let metrics: LayoutMetrics = {};
try {
metrics = await geometry.layoutMetrics(target);
} catch (error) {
if (isAbortError(error)) throw error;
console.debug("[bsk capture] layout metrics unavailable", error);
}
throwIfAborted(options.signal);
const viewport: Viewport = {
width: metrics.cssLayoutViewport?.clientWidth ?? 0,
height: metrics.cssLayoutViewport?.clientHeight ?? 0,
};
const layoutUnitsPerCssPixel = snapshotLayoutScale(metrics);
await cdp.send(tabId, "DOMSnapshot.enable", {});
throwIfAborted(options.signal);
const snap = await cdp.send<SnapshotReply>(tabId, "DOMSnapshot.captureSnapshot", {
computedStyles: REQUESTED_STYLES,
includePaintOrder: true,
includeDOMRects: true,
});
throwIfAborted(options.signal);
const strings = snap.strings ?? [];
const documents = snap.documents ?? [];
const doc0 = documents[0];
if (!doc0?.nodes?.backendNodeId) {
return {
nodes: [],
viewport,
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
};
}
const source = { target, frameId: snapshotFrameId(doc0, strings) };
const coordinates = snapshotCoordinates(doc0, layoutUnitsPerCssPixel, {
x: metrics.cssLayoutViewport?.pageX,
y: metrics.cssLayoutViewport?.pageY,
});
const topContext: FrameContext = {
frameId: snapshotFrameId(doc0, strings),
ownerFrameBackendNodeId: null,
target,
projection:
coordinates &&
[viewport.width, viewport.height].every((size) => Number.isFinite(size) && size > 0)
? {
status: "available",
projection: {
source,
geometry: { sourceClips: [], edges: [], topViewport: viewport },
},
}
: { status: "unavailable", source, reason: "snapshot-coordinates-unavailable" },
coordinates,
layoutUnitsPerCssPixel,
};
const mainParsed = await normalizeDocument(doc0, strings, topContext, options.signal);
const nodes = mainParsed.nodes;
const excludedBackendNodeIds = new Set(mainParsed.index.excludedBackendNodeIds);
const ownerIds = new Set<number>();
for (const document of documents) {
for (const index of document.nodes?.contentDocumentIndex?.index ?? []) {
const id = document.nodes?.backendNodeId?.[index];
if (id !== undefined) ownerIds.add(id);
}
}
geometry.registerSnapshotOwners(target, ownerIds);
const frameParsed = await parseChildFrameDocuments(
documents,
strings,
0,
topContext,
geometry,
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);
}
await enrichFormControlStates(cdp, tabId, [nodes, ...iframeNodes.values()], options.signal);
throwIfAborted(options.signal);
const frameNodes = new Map<string, CapturedNode[]>();
if (topContext.frameId) frameNodes.set(topContext.frameId, nodes);
for (const iframeFrameNodes of iframeNodes.values()) {
const frameId = iframeFrameNodes.find((node) => node.frameId)?.frameId;
if (frameId) frameNodes.set(frameId, iframeFrameNodes);
}
for (const [frameId, ownerBackendNodeId] of frameParsed.frameOwnerBackendNodeIds) {
if (!frameNodes.has(frameId)) {
frameNodes.set(frameId, iframeNodes.get(ownerBackendNodeId) ?? []);
}
}
return {
nodes,
viewport,
iframeNodes,
frameNodes,
frameGeometryIssues: [
...(topContext.projection.status === "available" ? [] : [topContext.projection]),
...frameParsed.frameGeometryIssues,
],
frameOwnerBackendNodeIds: frameParsed.frameOwnerBackendNodeIds,
frameExcludedBackendNodeIds: frameParsed.frameExcludedBackendNodeIds,
frameParentIds: frameParsed.frameParentIds,
...(topContext.frameId ? { rootFrameId: topContext.frameId } : {}),
excludedBackendNodeIds,
};
}
+47
View File
@@ -1,6 +1,10 @@
import type { 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 { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import type { FrameOwnedAxNode } from "./frame-document";
/** Bounds retain their raw snapshot document layout units until normalization. */
export interface SnapshotLayout {
@@ -92,3 +96,46 @@ export async function buildDocumentIndex<T extends DecodedNode>(
}
return { nodes, excludedBackendNodeIds };
}
/** Narrow input shared by the existing semantic scene/hover consumers. */
export interface CapturedSceneInput {
nodes: CapturedNode[];
viewport: Viewport;
rootFrameId?: string;
excludedBackendNodeIds: ReadonlySet<number>;
}
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 interface CapturedSurfaceProbe {
triggerBackendNodeId: number;
triggerPoint?: { x: number; y: number };
triggerAction: "hover" | "focus" | string;
subItems: string[];
confidence?: "high" | "medium" | "low";
}
export type { CapturedNode } from "./capture-types";
@@ -1,183 +0,0 @@
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);
}
+17 -20
View File
@@ -32,8 +32,6 @@ export interface FrameDomInput {
nodes: CapturedNode[];
rootFrameId?: string;
frameNodes?: ReadonlyMap<string, CapturedNode[]>;
frameOwnerBackendNodeIds?: ReadonlyMap<string, number>;
frameParentIds?: ReadonlyMap<string, string>;
frameExcludedBackendNodeIds?: ReadonlyMap<string, ReadonlySet<number>>;
}
@@ -59,27 +57,13 @@ 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);
}
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 } : {}),
};
});
return [...frames.values()];
}
export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
@@ -87,10 +71,11 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
batches: FrameAxBatch<T>[],
captured: FrameDomInput,
signal?: AbortSignal,
unresolved?: (frame: CdpFrame) => void,
): Promise<FrameDocument<T>[]> {
const checkpoint = createCaptureCheckpoint(signal);
let work = 0;
const frames = frameList(graph, batches, captured);
const frames = frameList(graph, batches);
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
const rootFrameId = graph?.rootFrameId ?? captured.rootFrameId ?? frames[0]?.frameId;
const domNodesForFrame = (frameId: string): CapturedNode[] =>
@@ -116,6 +101,7 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
}
nodeById.set(node.nodeId, node);
}
let reported = false;
const ownershipByNodeId = new Map<string, Ownership>();
for (const node of batch.nodes) {
const path: T[] = [];
@@ -134,8 +120,18 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
}
if (visiting.has(current.nodeId)) break;
visiting.add(current.nodeId);
if (current.frameId && frameById.has(current.frameId)) {
ownership = { frameId: current.frameId, strength: 4 };
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 };
ownershipByNodeId.set(current.nodeId, ownership);
break;
}
@@ -160,6 +156,7 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
ownershipByNodeId.set(path[i].nodeId, ownership);
}
if (!ownershipByNodeId.has(node.nodeId)) ownershipByNodeId.set(node.nodeId, ownership);
if (!ownership.frameId) continue;
const key = targetNodeKey(batch.frame.target, node.nodeId);
const existing = candidates.get(key);
if (!existing || ownership.strength > existing.ownership.strength) {
+248 -8
View File
@@ -1,21 +1,38 @@
import type { CdpTarget } from "@/browser-driver/frame-graph";
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 FrameProjectionState,
projectSnapshotRect,
type SnapshotCoordinates,
snapshotCoordinates,
snapshotViewportRect,
} from "../geometry/coordinate-types";
import { createCaptureCheckpoint } from "./capture-abort";
import { buildDocumentIndex, type DocumentIndex, type NodeFacts } from "./facts";
import { decodeDocument, type SnapshotDocument } from "./snapshot";
import {
GeometryContext,
type LayoutMetrics,
snapshotLayoutScale,
} from "../geometry/frame-context";
import {
createCaptureCheckpoint,
isAbortError as isCaptureAbort,
throwIfAborted as throwCaptureAborted,
} from "./capture-abort";
import { buildDocumentIndex, type CaptureIssue, type DocumentIndex, type NodeFacts } from "./facts";
import {
decodeDocument,
type SnapshotDocument,
type SnapshotReply,
snapshotFrameId,
} from "./snapshot";
export interface FrameContext {
frameId?: string;
ownerFrameBackendNodeId: number | null;
projection: FrameProjectionState;
projection: FrameProjectionState | null;
targetProjection?: GeometryProjection | null;
target: CdpTarget;
coordinates: SnapshotCoordinates | null;
layoutUnitsPerCssPixel: number | null;
}
export interface NormalizedDocument {
@@ -46,10 +63,17 @@ export async function normalizeDocument(
context.coordinates,
);
const local = input?.rect;
const rect =
input && context.projection.status === "available"
let rect =
input && context.projection?.status === "available"
? projectSnapshotRect(input, context.projection.projection)
: null;
if (rect && context.targetProjection !== undefined)
rect = context.targetProjection
? projectRectToViewport(
{ x: rect.x, y: rect.y, w: rect.width, h: rect.height },
context.targetProjection,
)
: null;
const visibility = node.layout?.styles.visibility || "visible";
const opacity = node.layout?.styles.opacity || "1";
nodes.push({
@@ -76,3 +100,219 @@ export async function normalizeDocument(
index,
};
}
export interface NormalizedFrameDocument extends NormalizedDocument {
frame: CdpFrame;
}
/** 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[],
signal?: AbortSignal,
rootFrameId?: string,
): Promise<NormalizedFrameDocument[]> {
const strings = snapshot.strings ?? [];
const raw = snapshot.documents ?? [];
const ownerIds = new Set<number>();
for (const document of raw) {
for (const index of document.nodes?.contentDocumentIndex?.index ?? []) {
const id = document.nodes?.backendNodeId?.[index];
if (id !== undefined) ownerIds.add(id);
}
}
geometry.registerSnapshotOwners(target, ownerIds);
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 metrics: LayoutMetrics = {};
try {
metrics = await geometry.layoutMetrics(target);
} catch (error) {
if (isCaptureAbort(error)) throw error;
}
const viewport: Viewport = {
width: metrics.cssLayoutViewport?.clientWidth ?? 0,
height: metrics.cssLayoutViewport?.clientHeight ?? 0,
};
const layoutUnitsPerCssPixel = snapshotLayoutScale(metrics);
const viewportAvailable = [viewport.width, viewport.height].every(
(size) => Number.isFinite(size) && size > 0,
);
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: NormalizedFrameDocument[] = [];
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 checkpoint = createCaptureCheckpoint(signal);
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) {
const pending = checkpoint();
if (pending) await pending;
}
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 coordinates = snapshotCoordinates(
doc,
layoutUnitsPerCssPixel,
frame.frameId === rootFrameId
? { x: metrics.cssLayoutViewport?.pageX, y: metrics.cssLayoutViewport?.pageY }
: undefined,
);
let state: FrameProjectionState | null =
frame.frameId === rootFrameId
? viewportAvailable && coordinates
? {
status: "available",
projection: {
source,
geometry: { sourceClips: [], edges: [], topViewport: viewport },
},
}
: { status: "unavailable", source, reason: "snapshot-coordinates-unavailable" }
: (projections.get(frame.frameId) ?? null);
if (!state && frame.frameId !== rootFrameId)
issues.push({
target,
frameId: frame.frameId,
stage: "ownership",
reason: "frame-ownership-unresolved",
});
if (!coordinates && (!state || state.status === "available"))
state = { status: "unavailable", source, reason: "snapshot-coordinates-unavailable" };
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),
);
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;
}
if (!snapshotCoordinates(sources.get(child.frameId)!, layoutUnitsPerCssPixel)) {
projections.set(child.frameId, {
status: "unavailable",
source: childSource,
reason: "snapshot-coordinates-unavailable",
});
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 normalized = await normalizeDocument(
doc,
strings,
{
frameId: frame.frameId,
ownerFrameBackendNodeId: frame.ownerBackendNodeId ?? null,
projection: state,
target,
...(target.sessionId ? { targetProjection } : {}),
coordinates,
},
signal,
);
result.push({ ...normalized, frame });
}
return result;
}
+67
View File
@@ -1,3 +1,4 @@
import { type CdpFrame, type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
import { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import type { DecodedDocument, DecodedNode } from "./facts";
@@ -23,6 +24,7 @@ interface RareBooleanData {
export interface SnapshotDocument {
frameId?: string | number;
documentURL?: number;
scrollOffsetX?: number;
scrollOffsetY?: number;
nodes?: {
@@ -222,3 +224,68 @@ 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,
};
}