test(geometry): identify the regression browser attachment

apps/extension/src/tools/__tests__/geometry-context.test.ts

@@ -5,9 +5,10 @@ import { rectPolygon } from "../geometry";
 import {
   projectSnapshotRect,
   screenshotPageRect,
+  snapshotCoordinates,
   snapshotViewportRect,
 } from "../geometry/coordinate-types";
-import { GeometryContext } from "../geometry/frame-context";
+import { GeometryContext, snapshotLayoutScale } from "../geometry/frame-context";
 import type { CdpRunner } from "../shared";
 
 const target = { tabId: 4 };
@@ -22,7 +23,11 @@ const graph: CdpFrameGraph = {
 function driver() {
   const send = vi.fn(async (_tab: number, method: string): Promise<object> => {
     if (method === "Page.getLayoutMetrics")
-      return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 1000 } };
+      return {
+        visualViewport: { clientWidth: 1000 },
+        cssVisualViewport: { clientWidth: 1000 },
+        cssLayoutViewport: { clientWidth: 1000, clientHeight: 1000 },
+      };
     if (method === "DOM.getBoxModel")
       return { model: { content: [52.5, 612.5, 427.5, 612.5, 427.5, 862.5, 52.5, 862.5] } };
     if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
@@ -35,6 +40,63 @@ function driver() {
 }
 
 describe("measurement geometry context", () => {
+  it.each([0.8, 1, 1.25, 2])("normalizes snapshot layout units at scale %s", (scale) => {
+    const measured = snapshotLayoutScale({
+      visualViewport: { clientWidth: 997.25, zoom: 1.1 },
+      cssVisualViewport: { clientWidth: 997.25 / scale, zoom: 1.1 },
+      // Rounded layout dimensions must not supply the scale.
+      layoutViewport: { clientWidth: 997 },
+      cssLayoutViewport: { clientWidth: Math.floor(997.25 / scale) },
+    });
+    expect(measured).toBeCloseTo(scale, 12);
+    const coordinates = snapshotCoordinates(
+      { scrollOffsetX: 80 * scale, scrollOffsetY: 200 * scale },
+      measured,
+      { x: 999, y: 999 },
+    );
+    expect(
+      snapshotViewportRect(
+        [160 * scale, 320 * scale, 120 * scale, 40 * scale],
+        { target },
+        coordinates,
+      )?.rect,
+    ).toEqual({ x: 80, y: 120, width: 120, height: 40 });
+  });
+
+  it("uses CSS root scroll only for missing snapshot offsets, without scaling it twice", () => {
+    const coordinates = snapshotCoordinates({ scrollOffsetX: 80 }, 2, { x: 999, y: 100 });
+    expect(snapshotViewportRect([200, 800, 240, 80], { target }, coordinates)?.rect).toEqual({
+      x: 60,
+      y: 300,
+      width: 120,
+      height: 40,
+    });
+    expect(snapshotCoordinates({ scrollOffsetX: 0 }, 2)).toBeNull();
+    expect(
+      snapshotCoordinates({ scrollOffsetX: NaN, scrollOffsetY: 0 }, 2, { x: 0, y: 0 }),
+    ).toBeNull();
+  });
+
+  it("does not infer snapshot units from missing, invalid, or CSS-only metrics", () => {
+    expect(snapshotLayoutScale({ cssLayoutViewport: { clientWidth: 800 } })).toBeNull();
+    for (const raw of [0, -1, NaN, Infinity]) {
+      expect(
+        snapshotLayoutScale({
+          visualViewport: { clientWidth: raw },
+          cssVisualViewport: { clientWidth: 800 },
+        }),
+      ).toBeNull();
+    }
+    expect(
+      snapshotLayoutScale({
+        visualViewport: { clientWidth: 0, clientHeight: 600 },
+        cssVisualViewport: { clientWidth: 0, clientHeight: 300 },
+      }),
+    ).toBe(2);
+    expect(snapshotCoordinates({ scrollOffsetX: 0, scrollOffsetY: 0 }, null)).toBeNull();
+    expect(snapshotViewportRect([10, 20, 120, 40], { target }, null)).toBeNull();
+  });
+
   it("shares in-flight frame measurements, but never shares them with the next context", async () => {
     const cdp = driver();
     const context = new GeometryContext(cdp, 4);
@@ -61,14 +123,20 @@ describe("measurement geometry context", () => {
       height: 1000,
     });
     if (projection.status !== "available") throw new Error("expected available projection");
-    const input = snapshotViewportRect([17, 23, 120, 40], source, { x: 0, y: 0 });
+    const input = snapshotViewportRect([17, 23, 120, 40], source, {
+      layoutUnitsPerCssPixel: 1,
+      scrollCss: { x: 0, y: 0 },
+    });
     expect(projectSnapshotRect(input!, projection.projection)).toEqual({
       x: 73.75,
       y: 641.25,
       width: 150,
       height: 50,
     });
-    const scrolled = snapshotViewportRect([17, 23, 120, 40], source, { x: 0, y: 10 });
+    const scrolled = snapshotViewportRect([17, 23, 120, 40], source, {
+      layoutUnitsPerCssPixel: 1,
+      scrollCss: { x: 0, y: 10 },
+    });
     expect(projectSnapshotRect(scrolled!, projection.projection)?.y).toBe(628.75);
     await context.snapshotProjection(source, 10, [], { width: 1000, height: 1000 });
     expect(cdp.calls.mock.calls.filter(([, method]) => method === "DOM.resolveNode")).toHaveLength(
@@ -173,7 +241,7 @@ describe("measurement geometry context", () => {
     const input = snapshotViewportRect(
       [30, 50, 120, 40],
       { target, frameId: "main" },
-      { x: 10, y: 20 },
+      { layoutUnitsPerCssPixel: 1, scrollCss: { x: 10, y: 20 } },
     )!;
     const projection = {
       source: { target, frameId: "main" },
@@ -194,8 +262,20 @@ describe("measurement geometry context", () => {
         source: { target: { tabId: 5 }, frameId: "main" },
       }),
     ).toBeNull();
-    expect(snapshotViewportRect([0, 0, NaN, 40], { target }, { x: 0, y: 0 })).toBeNull();
-    expect(snapshotViewportRect([0, 0, 10, 40], { target }, { x: Infinity, y: 0 })).toBeNull();
+    expect(
+      snapshotViewportRect(
+        [0, 0, NaN, 40],
+        { target },
+        { layoutUnitsPerCssPixel: 1, scrollCss: { x: 0, y: 0 } },
+      ),
+    ).toBeNull();
+    expect(
+      snapshotViewportRect(
+        [0, 0, 10, 40],
+        { target },
+        { layoutUnitsPerCssPixel: 1, scrollCss: { x: Infinity, y: 0 } },
+      ),
+    ).toBeNull();
   });
 
   it("does not turn a border quad or a failed owner read into a content projection", async () => {
@@ -228,7 +308,7 @@ describe("measurement geometry context", () => {
     const input = snapshotViewportRect(
       [0, 0, 300, 200],
       { target, frameId: "nested" },
-      { x: 0, y: 0 },
+      { layoutUnitsPerCssPixel: 1, scrollCss: { x: 0, y: 0 } },
     );
     expect(projectSnapshotRect(input!, projection.projection)).toEqual({
       x: 60,
@@ -278,7 +358,11 @@ describe("measurement geometry context", () => {
       peak = Math.max(peak, active);
       await new Promise<void>((resolve) => release.push(resolve));
       active--;
-      return { cssLayoutViewport: { clientWidth: 100, clientHeight: 100 } };
+      return {
+        visualViewport: { clientWidth: 1000 },
+        cssVisualViewport: { clientWidth: 1000 },
+        cssLayoutViewport: { clientWidth: 100, clientHeight: 100 },
+      };
     });
     const controller = new AbortController();
     const context = new GeometryContext(

apps/extension/src/tools/__tests__/observation.test.ts

@@ -93,7 +93,11 @@ function makeFakeCdp(handlers: Record<string, (params?: object) => unknown>) {
     sent.push({ method, params });
     const handler = handlers[method];
     if (!handler && method === "Page.getLayoutMetrics") {
-      return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
+      return {
+        visualViewport: { clientWidth: 1000 },
+        cssVisualViewport: { clientWidth: 1000 },
+        cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 },
+      };
     }
     if (!handler) throw new Error(`unexpected CDP call ${method}`);
     return handler(params);
@@ -2583,7 +2587,11 @@ describe("handleSnapshot", () => {
       if (method === "Accessibility.enable") return {};
       if (method === "Accessibility.getFullAXTree") return { nodes };
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
+        };
       }
       if (method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot") throw new Error("snapshot unsupported");
@@ -2670,7 +2678,11 @@ describe("handleSnapshot", () => {
       if (method === "Accessibility.enable") return {};
       if (method === "Accessibility.getFullAXTree") return { nodes: [root, button] };
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
+        };
       }
       if (method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot") {
@@ -2678,6 +2690,8 @@ describe("handleSnapshot", () => {
           strings,
           documents: [
             {
+              scrollOffsetX: 0,
+              scrollOffsetY: 0,
               frameId: "root",
               nodes: {
                 parentIndex: [-1, 0],
@@ -2762,7 +2776,11 @@ describe("handleSnapshot", () => {
       if (method === "Accessibility.enable") return {};
       if (method === "Accessibility.getFullAXTree") return { nodes: [root, button] };
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
+        };
       }
       if (method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot") {
@@ -2770,6 +2788,8 @@ describe("handleSnapshot", () => {
           strings,
           documents: [
             {
+              scrollOffsetX: 0,
+              scrollOffsetY: 0,
               frameId: "root",
               nodes: {
                 parentIndex: [-1, 0],
@@ -2857,7 +2877,11 @@ describe("handleSnapshot", () => {
       if (method === "Accessibility.enable") return {};
       if (method === "Accessibility.getFullAXTree") return { nodes: [root, button] };
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
+        };
       }
       if (method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot") {
@@ -2865,6 +2889,8 @@ describe("handleSnapshot", () => {
           strings,
           documents: [
             {
+              scrollOffsetX: 0,
+              scrollOffsetY: 0,
               frameId: "root",
               nodes: {
                 parentIndex: [-1, 0],
@@ -3023,7 +3049,11 @@ describe("handleSnapshot", () => {
         };
       }
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
+        };
       }
       if (method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot") {
@@ -3130,6 +3160,8 @@ describe("handleSnapshot", () => {
       strings: S,
       documents: [
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "root",
           nodes: {
             parentIndex: [-1, 0, 1, 2],
@@ -3188,6 +3220,8 @@ describe("handleSnapshot", () => {
       strings: S,
       documents: [
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "root",
           nodes: {
             parentIndex: [-1, 0, 1, 1, 1, 1],
@@ -3238,6 +3272,8 @@ describe("handleSnapshot", () => {
   }
 
   const VP_METRICS = {
+    visualViewport: { clientWidth: 1000 },
+    cssVisualViewport: { clientWidth: 1000 },
     cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
   };
 
@@ -3251,6 +3287,8 @@ describe("handleSnapshot", () => {
       strings,
       documents: [
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "main",
           nodes: {
             parentIndex: [-1, 0, 1],
@@ -3271,6 +3309,8 @@ describe("handleSnapshot", () => {
           },
         },
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "child",
           nodes: {
             parentIndex: [-1, 0, 1],
@@ -3341,7 +3381,11 @@ describe("handleSnapshot", () => {
     });
     const sendToTarget = vi.fn(async (_target, method: string) => {
       if (method === "Page.getLayoutMetrics" && ownerGeometry !== "unavailable")
-        return { cssLayoutViewport: { clientWidth: 400, clientHeight: 300 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 400, clientHeight: 300 },
+        };
       if (method === "Accessibility.enable" || method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot")
         return { ...snapshot, documents: [snapshot.documents[1]] };
@@ -3384,6 +3428,8 @@ describe("handleSnapshot", () => {
       strings: ["body", "a", "href", "//outside.test/docs", "https://page.test/start"],
       documents: [
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "main",
           ...(hasSnapshotUrl ? { documentURL: 4 } : {}),
           nodes: {
@@ -3505,6 +3551,8 @@ describe("handleSnapshot", () => {
       strings,
       documents: [
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "root",
           nodes: {
             parentIndex: [-1, 0, 1, 1, 3],
@@ -3649,14 +3697,14 @@ describe("handleSnapshot", () => {
     });
     expect(result.text.match(/@warning/g)).toHaveLength(2);
     expect(result.text).toContain("document identity unverified");
-    expect(result.text).toContain("iframe geometry incomplete");
+    expect(result.text).toContain("geometry incomplete");
     expect(result.text.startsWith("@vom 1\n")).toBe(true);
     if (maxTokens === undefined) {
       expect(result.truncated).toBe(false);
       expect(result.text).toContain("Frame action");
       expect(result.matchNodes.find((node) => node.backendNodeId === 22)).toMatchObject({
         rect: null,
-        localRect: { x: 20, y: 30, w: 120, h: 40 },
+        localRect: null,
       });
     }
     if (maxTokens === 100) expect(Math.ceil(result.text.length / 4)).toBeLessThanOrEqual(maxTokens);
@@ -3747,7 +3795,7 @@ describe("handleSnapshot", () => {
     expect(result.matchNodes.find((node) => node.backendNodeId === 22)).toMatchObject({
       frameId: "child",
       tag: "button",
-      localRect: { x: 20, y: 30, w: 120, h: 40 },
+      localRect: null,
     });
     expect(result.refs.find((ref) => ref.backendNodeId === 22)).toMatchObject({
       frameId: "child",
@@ -4091,6 +4139,8 @@ describe("handleSnapshot", () => {
       strings: S,
       documents: [
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "root",
           nodes: {
             parentIndex: [-1, 0, 1, 0, 3, 4, 5],

apps/extension/src/tools/__tests__/snapshot-coordinates.browser.test.ts

@@ -0,0 +1,234 @@
+// @vitest-environment node
+import { describe, expect, it } from "vitest";
+import type { CdpFrame, CdpFrameGraph, CdpTarget } from "@/browser-driver/frame-graph";
+import type { CdpRunner } from "../shared";
+import { captureObservationFacts } from "../vom/capture-coordinator";
+
+type Send = <T = Record<string, unknown>>(
+  method: string,
+  params?: object,
+  sessionId?: string,
+) => Promise<T>;
+type Tree = { frame: { id: string; parentId?: string; name?: string }; childFrames?: Tree[] };
+type Rect = { x: number; y: number; w: number; h: number };
+type Oracle = { probe: Rect; owners: Record<string, { x: number; y: number; scale: number }> };
+
+// The independent oracle uses DOM border boxes and this fixture's axis-aligned
+// iframe transforms. No production snapshot conversion/projection builds expectations.
+const oracleExpression = `(() => {
+  const box = document.querySelector('#probe').getBoundingClientRect();
+  const owners = {};
+  for (const frame of document.querySelectorAll('iframe')) {
+    const rect = frame.getBoundingClientRect();
+    const style = getComputedStyle(frame);
+    const scale = rect.width / frame.offsetWidth;
+    owners[frame.name] = {
+      x: rect.x + (frame.clientLeft + parseFloat(style.paddingLeft)) * scale,
+      y: rect.y + (frame.clientTop + parseFloat(style.paddingTop)) * scale,
+      scale,
+    };
+  }
+  return { probe: { x: box.x, y: box.y, w: box.width, h: box.height }, owners };
+})()`;
+
+describe.skipIf(!process.env.BSK_GEOMETRY_CHROME)("real DOMSnapshot coordinate contract", () => {
+  it.each([
+    { deviceScale: 1, zoom: 1 },
+    { deviceScale: 0.8, zoom: 1 },
+    { deviceScale: 1, zoom: 1.25 },
+    { deviceScale: 2, zoom: 1 },
+    { deviceScale: 2, zoom: 0.8 },
+  ])("matches DOM geometry at device scale $deviceScale and zoom $zoom", async (configuration) => {
+    const evalRoot = new URL("../../../../../evals/browser/", import.meta.url);
+    const { createEvalServer } = await import(new URL("lib/server.mjs", evalRoot).href);
+    const { withChrome } = await import(
+      new URL("cases/regression/snapshot-coordinates/chrome.mjs", evalRoot).href
+    );
+    const server = createEvalServer();
+    const { baseUrl } = await server.start();
+    try {
+      await withChrome(
+        { executable: process.env.BSK_GEOMETRY_CHROME, ...configuration },
+        async (send: Send) => {
+          const { targetId } = await send<{ targetId: string }>("Target.createTarget", {
+            url: "about:blank",
+          });
+          const { sessionId: rootSession } = await send<{ sessionId: string }>(
+            "Target.attachToTarget",
+            { targetId, flatten: true },
+          );
+          await send(
+            "Page.navigate",
+            { url: `${baseUrl}/snapshot-coordinates?run=coordinates` },
+            rootSession,
+          );
+          await expect
+            .poll(
+              () =>
+                server
+                  .snapshot("coordinates")
+                  .events.some(
+                    (event: { type: string; data: { root?: boolean } }) =>
+                      event.type === "geometry.ready" && event.data.root,
+                  ),
+              { timeout: 10_000 },
+            )
+            .toBe(true);
+
+          const targets = await send<{ targetInfos: { targetId: string; type: string }[] }>(
+            "Target.getTargets",
+          );
+          const sessions = [rootSession];
+          for (const target of targets.targetInfos.filter((target) => target.type === "iframe")) {
+            const { sessionId } = await send<{ sessionId: string }>("Target.attachToTarget", {
+              targetId: target.targetId,
+              flatten: true,
+            });
+            sessions.push(sessionId);
+          }
+          expect(sessions.length).toBe(2); // The cross-site fixture must actually be an OOPIF.
+          const frames: CdpFrame[] = [];
+          const names = new Map<string, string>();
+          const sessionFor = (target: CdpTarget) => target.sessionId ?? rootSession;
+          for (const sessionId of sessions) {
+            const { frameTree } = await send<{ frameTree: Tree }>(
+              "Page.getFrameTree",
+              {},
+              sessionId,
+            );
+            const target: CdpTarget = {
+              tabId: 1,
+              ...(sessionId === rootSession ? {} : { sessionId }),
+            };
+            const visit = (tree: Tree, parentFrameId = tree.frame.parentId) => {
+              frames.push({ frameId: tree.frame.id, parentFrameId, target });
+              names.set(tree.frame.id, tree.frame.name ?? "");
+              for (const child of tree.childFrames ?? []) visit(child, tree.frame.id);
+            };
+            visit(frameTree);
+          }
+          expect(frames).toHaveLength(5);
+          for (const frame of frames) {
+            if (!frame.parentFrameId) continue;
+            const parent = frames.find((item) => item.frameId === frame.parentFrameId)!;
+            const owner = await send<{ backendNodeId: number }>(
+              "DOM.getFrameOwner",
+              { frameId: frame.frameId },
+              sessionFor(parent.target),
+            );
+            frame.ownerBackendNodeId = owner.backendNodeId;
+          }
+          const graph: CdpFrameGraph = { rootFrameId: frames[0].frameId, frames };
+          const calls: string[] = [];
+          const cdp: CdpRunner = {
+            send: (tabId, method, params) => {
+              calls.push(`${tabId}:${method}`);
+              return send(method, params, rootSession);
+            },
+            sendToTarget: (target, method, params) => {
+              calls.push(`${target.sessionId ?? target.tabId}:${method}`);
+              return send(method, params, sessionFor(target));
+            },
+            getFrameGraph: async () => graph,
+            getAttachmentId: () => rootSession,
+          };
+          const oracles = new Map<string, Oracle>();
+          for (const frame of frames) {
+            const session = sessionFor(frame.target);
+            const { executionContextId } = await send<{ executionContextId: number }>(
+              "Page.createIsolatedWorld",
+              { frameId: frame.frameId, worldName: "coordinate-oracle" },
+              session,
+            );
+            await expect
+              .poll(
+                async () => {
+                  const ready = await send<{ result: { value: boolean } }>(
+                    "Runtime.evaluate",
+                    {
+                      expression: 'document.documentElement.dataset.geometryReady === "true"',
+                      contextId: executionContextId,
+                      returnByValue: true,
+                    },
+                    session,
+                  );
+                  return ready.result.value;
+                },
+                { timeout: 5_000 },
+              )
+              .toBe(true);
+            // Establish scroll after cross-process target creation/layout settles.
+            const scroll = frame.parentFrameId
+              ? names.get(frame.frameId) === "nested"
+                ? [10, 20]
+                : [40, 100]
+              : [80, 240];
+            await send(
+              "Runtime.evaluate",
+              {
+                expression: `(async () => { scrollTo(${scroll.join(",")}); await new Promise(resolve => requestAnimationFrame(() => requestAnimationFrame(resolve))); })()`,
+                contextId: executionContextId,
+                awaitPromise: true,
+              },
+              session,
+            );
+            const reply = await send<{ result: { value: Oracle } }>(
+              "Runtime.evaluate",
+              { expression: oracleExpression, contextId: executionContextId, returnByValue: true },
+              session,
+            );
+            oracles.set(frame.frameId, reply.result.value);
+          }
+          const facts = await captureObservationFacts(cdp, 1);
+          expect(facts.issues).toEqual([]);
+          for (const frame of frames) {
+            const node = facts.documents
+              .find((doc) => doc.frame.frameId === frame.frameId)
+              ?.domNodes.find((node) => node.attrs.id === "probe");
+            expect(node, `missing probe in ${names.get(frame.frameId) || "root"}`).toBeDefined();
+            const local = oracles.get(frame.frameId)!.probe;
+            const top = { ...local };
+            let current = frame;
+            while (current.parentFrameId) {
+              const owner = oracles.get(current.parentFrameId)!.owners[names.get(current.frameId)!];
+              top.x = owner.x + top.x * owner.scale;
+              top.y = owner.y + top.y * owner.scale;
+              top.w *= owner.scale;
+              top.h *= owner.scale;
+              current = frames.find((item) => item.frameId === current.parentFrameId)!;
+            }
+            expect(
+              node!.rect,
+              JSON.stringify({
+                frame: names.get(frame.frameId),
+                local,
+                top,
+                viewport: facts.viewport,
+              }),
+            ).not.toBeNull();
+            for (const key of ["x", "y", "w", "h"] as const) {
+              expect(
+                Math.abs(node!.localRect![key] - local[key]),
+                `${names.get(frame.frameId)} local ${key}`,
+              ).toBeLessThan(2);
+              expect(
+                Math.abs(node!.rect![key] - top[key]),
+                `${names.get(frame.frameId)} top ${key}`,
+              ).toBeLessThan(2);
+            }
+          }
+          expect(calls.filter((call) => call.endsWith(":Page.getLayoutMetrics"))).toHaveLength(
+            sessions.length,
+          );
+          const metrics = await send<{
+            cssVisualViewport: { zoom: number };
+            visualViewport: { clientWidth: number };
+          }>("Page.getLayoutMetrics", {}, rootSession);
+          expect(metrics.cssVisualViewport.zoom).toBeCloseTo(configuration.zoom, 4);
+        },
+      );
+    } finally {
+      await server.stop();
+    }
+  }, 30_000);
+});

apps/extension/src/tools/geometry/coordinate-types.ts

@@ -25,6 +25,12 @@ export interface UnavailableFrameProjection {
   ownerBackendNodeId: number;
 }
 
+export interface UnavailableSnapshotCoordinates {
+  status: "unavailable";
+  source: CoordinateOwner;
+  reason: "snapshot-coordinates-unavailable";
+}
+
 export type SnapshotProjectionResult =
   | { status: "available"; projection: SnapshotProjection }
   | UnavailableFrameProjection;
@@ -32,25 +38,74 @@ export type SnapshotProjectionResult =
 /** Descendants inherit the failed boundary without attempting another owner read. */
 export type FrameProjectionIssue =
   | UnavailableFrameProjection
-  | { status: "blocked"; source: CoordinateOwner; cause: UnavailableFrameProjection };
+  | UnavailableSnapshotCoordinates
+  | {
+      status: "blocked";
+      source: CoordinateOwner;
+      cause: UnavailableFrameProjection | UnavailableSnapshotCoordinates;
+    };
 
 export type FrameProjectionState = SnapshotProjectionResult | FrameProjectionIssue;
 
-/** DOMSnapshot bounds are document-relative CSS pixels, independent of raster DPR. */
+export interface SnapshotCoordinates {
+  layoutUnitsPerCssPixel: number;
+  scrollCss: { x: number; y: number };
+}
+
+/** Snapshot scroll offsets share the raw layout units of its bounds. Only a
+ * target's root document may fall back to that target's CSS layout viewport. */
+export function snapshotCoordinates(
+  document: { scrollOffsetX?: number; scrollOffsetY?: number },
+  layoutUnitsPerCssPixel: number | null,
+  rootScrollCss?: { x?: number; y?: number },
+): SnapshotCoordinates | null {
+  if (
+    layoutUnitsPerCssPixel === null ||
+    !Number.isFinite(layoutUnitsPerCssPixel) ||
+    layoutUnitsPerCssPixel <= 0
+  )
+    return null;
+  const x =
+    document.scrollOffsetX === undefined
+      ? rootScrollCss?.x
+      : document.scrollOffsetX / layoutUnitsPerCssPixel;
+  const y =
+    document.scrollOffsetY === undefined
+      ? rootScrollCss?.y
+      : document.scrollOffsetY / layoutUnitsPerCssPixel;
+  if (x === undefined || y === undefined || !Number.isFinite(x) || !Number.isFinite(y)) return null;
+  return { layoutUnitsPerCssPixel, scrollCss: { x, y } };
+}
+
+/** Convert raw document-relative Blink layout units exactly once, before any
+ * CSS viewport clipping or frame projection. This scale is not screenshot zoom. */
 export function snapshotViewportRect(
   bounds: number[],
   owner: CoordinateOwner,
-  scroll: { x: number; y: number },
+  coordinates: SnapshotCoordinates | null,
 ): FrameViewportRect | null {
-  if (bounds.length < 4 || !bounds.slice(0, 4).every(Number.isFinite)) return null;
+  if (!coordinates || bounds.length < 4 || !bounds.slice(0, 4).every(Number.isFinite)) return null;
+  const { layoutUnitsPerCssPixel: scale, scrollCss: scroll } = coordinates;
   const [x, y, width, height] = bounds;
-  if (width <= 0 || height <= 0 || !Number.isFinite(scroll.x) || !Number.isFinite(scroll.y)) {
+  if (
+    !Number.isFinite(scale) ||
+    scale <= 0 ||
+    width <= 0 ||
+    height <= 0 ||
+    !Number.isFinite(scroll.x) ||
+    !Number.isFinite(scroll.y)
+  ) {
     return null;
   }
   return {
     space: "frame-viewport-css",
     owner,
-    rect: { x: x - scroll.x, y: y - scroll.y, width, height },
+    rect: {
+      x: x / scale - scroll.x,
+      y: y / scale - scroll.y,
+      width: width / scale,
+      height: height / scale,
+    },
   };
 }
 

apps/extension/src/tools/geometry/frame-context.ts

@@ -18,8 +18,8 @@ import type { CoordinateOwner, CssViewport, SnapshotProjectionResult } from "./c
 import { readSnapshotOwnerSizes } from "./snapshot-owner-sizes";
 
 export interface LayoutMetrics {
-  cssVisualViewport?: { zoom?: number };
-  visualViewport?: { zoom?: number };
+  cssVisualViewport?: { zoom?: number; clientWidth?: number; clientHeight?: number };
+  visualViewport?: { zoom?: number; clientWidth?: number; clientHeight?: number };
   cssLayoutViewport?: {
     clientWidth?: number;
     clientHeight?: number;
@@ -29,6 +29,29 @@ export interface LayoutMetrics {
   layoutViewport?: { clientWidth?: number; clientHeight?: number; pageX?: number; pageY?: number };
 }
 
+/** Chromium emits these paired floating-point dimensions before/after dividing
+ * by LayoutZoomFactor. Integer layout viewport dimensions lose precision at
+ * fractional zoom. Neither visualViewport.scale nor .zoom is this conversion.
+ * See InspectorPageAgent::getLayoutMetrics in Chromium. */
+export function snapshotLayoutScale(metrics: LayoutMetrics): number | null {
+  for (const dimension of ["clientWidth", "clientHeight"] as const) {
+    const raw = metrics.visualViewport?.[dimension];
+    const css = metrics.cssVisualViewport?.[dimension];
+    if (
+      raw !== undefined &&
+      css !== undefined &&
+      Number.isFinite(raw) &&
+      Number.isFinite(css) &&
+      raw > 0 &&
+      css > 0
+    ) {
+      const scale = raw / css;
+      if (Number.isFinite(scale) && scale > 0) return scale;
+    }
+  }
+  return null;
+}
+
 /** The legacy field is a compatibility fallback, never a source of raster DPR. */
 export function cssViewport(metrics: LayoutMetrics): CssViewport {
   const value = metrics.cssLayoutViewport ?? metrics.layoutViewport;

apps/extension/src/tools/observation.ts

@@ -929,7 +929,7 @@ export async function captureVomObservation(
   const notices: string[] = [];
   if (facts.issues.some((issue) => issue.stage === "geometry"))
     notices.push(
-      "@warning iframe geometry incomplete: some frame content has no top-level coordinates.",
+      "@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),

apps/extension/src/tools/vom/__tests__/capture-coordinator.test.ts

@@ -6,7 +6,7 @@ import { captureVomObservation } from "../../observation";
 import type { CdpRunner } from "../../shared";
 import { captureObservationFacts, semanticCapture } from "../capture-coordinator";
 import { buildSemanticGraph } from "../semantic-graph/build";
-import { REQUESTED_STYLES } from "../snapshot";
+import { REQUESTED_STYLES, type SnapshotReply } from "../snapshot";
 
 function fixture(
   options: {
@@ -76,7 +76,11 @@ function fixture(
               };
       }
       if (method === "Page.getLayoutMetrics")
-        result = { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
+        result = {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
+        };
       if (method === "DOMSnapshot.captureSnapshot") {
         snapshots++;
         expect((params as { computedStyles: unknown }).computedStyles).toEqual(REQUESTED_STYLES);
@@ -108,6 +112,8 @@ function fixture(
               const children = localFrames.filter((f) => f.parentFrameId === frame.frameId);
 
               return {
+                scrollOffsetX: 0,
+                scrollOffsetY: 0,
                 frameId: frame.frameId,
                 nodes: {
                   backendNodeId: [
@@ -180,6 +186,35 @@ function fixture(
 }
 
 describe("captureObservationFacts", () => {
+  it("normalizes snapshot-owned root scroll instead of mixing in stale CSS scroll", async () => {
+    const { cdp } = fixture({ frames: [{ frameId: "main", target: { tabId: 4 } }] });
+    const original = cdp.sendToTarget!;
+    cdp.sendToTarget = async (target, method, params) => {
+      if (method === "Page.getLayoutMetrics")
+        return {
+          visualViewport: { clientWidth: 2000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 999, pageY: 999 },
+        } as never;
+      const reply = await original(target, method, params);
+      if (method === "DOMSnapshot.captureSnapshot") {
+        const doc = (reply as SnapshotReply).documents![0];
+        doc.scrollOffsetX = 40;
+        doc.scrollOffsetY = 200;
+        doc.layout!.bounds![1] = [200, 800, 240, 80];
+      }
+      return reply as never;
+    };
+    cdp.send = (tabId, method, params) => cdp.sendToTarget!({ tabId }, method, params);
+    const facts = await captureObservationFacts(cdp, 4);
+    expect(facts.documents[0].domNodes.find((node) => node.backendNodeId === 2)).toMatchObject({
+      localRect: { x: 80, y: 300, w: 120, h: 40 },
+      rect: { x: 80, y: 300, w: 120, h: 40 },
+      rendered: true,
+    });
+    expect(facts.issues).toEqual([]);
+  });
+
   it("collects each target once and scopes equal backend IDs", async () => {
     const { cdp, logs } = fixture();
     const facts = await captureObservationFacts(cdp, 4);
@@ -591,6 +626,8 @@ function childSnapshot(frameId: string, backendNodeId: number) {
     strings,
     documents: [
       {
+        scrollOffsetX: 0,
+        scrollOffsetY: 0,
         frameId,
         nodes: {
           parentIndex: [-1, 0],
@@ -619,7 +656,11 @@ describe("OOPIF capture", () => {
   it("captures and positions multiple OOPIF documents missing from the root snapshot", async () => {
     const sendToTarget = vi.fn(async (target, method) => {
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200, pageX: 0, pageY: 0 } };
+        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") {
@@ -641,7 +682,11 @@ describe("OOPIF capture", () => {
           return { model: { content: [x, 100, x + 300, 100, x + 300, 300, x, 300] } };
         }
         if (method === "Page.getLayoutMetrics") {
-          return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
+          return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
+            cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
+          };
         }
         throw new Error(`unexpected root ${method}`);
       }) as CdpRunner["send"],
@@ -719,7 +764,11 @@ describe("OOPIF capture", () => {
     };
     const reply = async (_target: unknown, method: string) => {
       if (method === "Page.getLayoutMetrics")
-        return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 300, clientHeight: 200 },
+        };
       if (method === "DOMSnapshot.captureSnapshot")
         return typeof _target === "number" ? childSnapshot("main", 11) : snapshot;
       if (method === "DOM.getBoxModel")
@@ -777,7 +826,11 @@ describe("OOPIF capture", () => {
         if (method === "Accessibility.getFullAXTree") return { nodes: [] };
         if (method === "DOM.getBoxModel") throw new Error("owner geometry unavailable");
         if (method === "Page.getLayoutMetrics") {
-          return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
+          return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
+            cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
+          };
         }
         throw new Error(`unexpected root ${method}`);
       }) as CdpRunner["send"],
@@ -820,7 +873,7 @@ describe("OOPIF capture", () => {
       expect.objectContaining({ backendDOMNodeId: 101, frameId: "child" }),
     ]);
     expect(childDocument?.domNodes.find((node) => node.backendNodeId === 101)).toEqual(
-      expect.objectContaining({ rect: null, localRect: { x: 10, y: 20, w: 100, h: 40 } }),
+      expect.objectContaining({ rect: null, localRect: null, rendered: true }),
     );
   });
 });
@@ -830,6 +883,8 @@ function siblingCaptureFixture(
   beforeReply: (method: string, params: Record<string, unknown>) => Promise<void> = async () => {},
 ) {
   const document = (id: number, owners: number[], childIndexes: number[]) => ({
+    scrollOffsetX: 0,
+    scrollOffsetY: 0,
     frameId: `frame-${id}`,
     nodes: {
       parentIndex: [-1, ...owners.map(() => 0)],
@@ -861,7 +916,11 @@ function siblingCaptureFixture(
       await beforeReply(method, args);
       if (method === "DOMSnapshot.captureSnapshot") return snapshot;
       if (method === "Page.getLayoutMetrics")
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
+        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) } };
@@ -1065,7 +1124,11 @@ describe("snapshot document provenance", () => {
         (method === "DOMSnapshot.captureSnapshot"
           ? { ...f.snapshot, documents: [f.snapshot.documents[1]] }
           : method === "Page.getLayoutMetrics"
-            ? { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } }
+            ? {
+                visualViewport: { clientWidth: 1000 },
+                cssVisualViewport: { clientWidth: 1000 },
+                cssLayoutViewport: { clientWidth: 200, clientHeight: 100 },
+              }
             : {}) as T,
     };
     const facts = await captureObservationFacts(cdp, 4);

apps/extension/src/tools/vom/__tests__/capture.test.ts

@@ -215,7 +215,11 @@ function makeCdp(snapshot: unknown) {
       if (method === "DOMSnapshot.enable") return {};
       if (method === "DOMSnapshot.captureSnapshot") return snapshot;
       if (method === "Page.getLayoutMetrics") {
-        return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
+        return {
+          visualViewport: { clientWidth: 1000 },
+          cssVisualViewport: { clientWidth: 1000 },
+          cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
+        };
       }
       if (method === "Runtime.evaluate") {
         return {
@@ -277,6 +281,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return hoverTriggerSnapshotReply();
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
           };
         }
@@ -340,6 +346,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return twoHoverTriggerSnapshotReply();
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
           };
         }
@@ -388,6 +396,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return nestedHoverTriggerSnapshotReply();
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
           };
         }
@@ -733,6 +743,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return fakeSnapshotReply();
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 200 },
           };
         }
@@ -745,7 +757,7 @@ describe("snapshot capture and hover", () => {
     expect(div?.rect).toMatchObject({ y: 0, h: 600 });
   });
 
-  it("keeps CSS snapshot bounds independent of legacy metrics ratio", async () => {
+  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);
     const snapshot = {
@@ -780,6 +792,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return snapshot;
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 2000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
             layoutViewport: { clientWidth: 2000, clientHeight: 1600 },
           };
@@ -797,8 +811,8 @@ describe("snapshot capture and hover", () => {
     expect(nodes.find((n) => n.backendNodeId === 12)?.localRect).toEqual({
       x: 0,
       y: 0,
-      w: 2000,
-      h: 1600,
+      w: 1000,
+      h: 800,
     });
   });
 
@@ -856,6 +870,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return snapshot;
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
           };
         }
@@ -946,6 +962,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return snapshot;
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
           };
         }
@@ -1035,6 +1053,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return snapshot;
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 1000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
           };
         }
@@ -1097,6 +1117,8 @@ describe("snapshot capture and hover", () => {
           },
         },
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "child",
           nodes: {
             parentIndex: [-1, 0, 1],
@@ -1119,6 +1141,8 @@ describe("snapshot capture and hover", () => {
           },
         },
         {
+          scrollOffsetX: 0,
+          scrollOffsetY: 0,
           frameId: "nested",
           nodes: {
             parentIndex: [-1, 0],
@@ -1146,6 +1170,8 @@ describe("snapshot capture and hover", () => {
           if (method === "DOMSnapshot.captureSnapshot") return snapshot;
           if (method === "Page.getLayoutMetrics") {
             return {
+              visualViewport: { clientWidth: 1000 },
+              cssVisualViewport: { clientWidth: 1000 },
               cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
             };
           }
@@ -1225,6 +1251,8 @@ describe("snapshot capture and hover", () => {
         if (method === "DOMSnapshot.captureSnapshot") return snapshot;
         if (method === "Page.getLayoutMetrics") {
           return {
+            visualViewport: { clientWidth: 2000 },
+            cssVisualViewport: { clientWidth: 1000 },
             cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 100 },
             layoutViewport: { clientWidth: 2000, clientHeight: 1600 },
           };
@@ -1233,7 +1261,7 @@ describe("snapshot capture and hover", () => {
       }) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
     };
     const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
-    expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 - 100);
+    expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 / 2 - 100);
   });
 
   it("collectOverlayExcludedBackendIds walks the pierced overlay host subtree", async () => {

apps/extension/src/tools/vom/__tests__/facts.test.ts

@@ -77,7 +77,7 @@ describe("document facts", () => {
     );
     expect(nodes[0].attrs).toEqual({ "aria-hidden": "true", inert: "" });
     expect(nodes[0].layout).toEqual({
-      boundsSpace: "snapshot-document-css",
+      boundsSpace: "snapshot-document-layout",
       bounds: [10, 20, 120, 40],
       styles: {
         position: "static",

apps/extension/src/tools/vom/facts.ts

@@ -6,9 +6,9 @@ import { createCaptureCheckpoint } from "./capture-abort";
 import type { CapturedNode } from "./capture-types";
 import type { FrameOwnedAxNode } from "./frame-document";
 
-/** Bounds retain their snapshot document CSS units until normalization. */
+/** Bounds retain their raw snapshot document layout units until normalization. */
 export interface SnapshotLayout {
-  readonly boundsSpace: "snapshot-document-css";
+  readonly boundsSpace: "snapshot-document-layout";
   bounds?: number[];
   styles: Readonly<Record<string, string>>;
 }

apps/extension/src/tools/vom/normalize.ts

@@ -4,9 +4,15 @@ import { type GeometryProjection, projectRectToViewport } from "../geometry";
 import {
   type FrameProjectionState,
   projectSnapshotRect,
+  type SnapshotCoordinates,
+  snapshotCoordinates,
   snapshotViewportRect,
 } from "../geometry/coordinate-types";
-import { cssViewport, GeometryContext } from "../geometry/frame-context";
+import {
+  GeometryContext,
+  type LayoutMetrics,
+  snapshotLayoutScale,
+} from "../geometry/frame-context";
 import {
   createCaptureCheckpoint,
   isAbortError as isCaptureAbort,
@@ -26,8 +32,7 @@ export interface FrameContext {
   projection: FrameProjectionState | null;
   targetProjection?: GeometryProjection | null;
   target: CdpTarget;
-  scrollX: number;
-  scrollY: number;
+  coordinates: SnapshotCoordinates | null;
 }
 
 export interface NormalizedDocument {
@@ -52,10 +57,11 @@ export async function normalizeDocument(
       if (pending) await pending;
     }
     const node = decoded.nodes[i];
+    const bounds = node.layout?.bounds ?? [];
     const input = snapshotViewportRect(
-      node.layout?.bounds ?? [],
+      bounds,
       { target: context.target, frameId: context.frameId },
-      { x: context.scrollX, y: context.scrollY },
+      context.coordinates,
     );
     const local = input?.rect;
     let rect =
@@ -78,7 +84,10 @@ export async function normalizeDocument(
       localRect: local ? { x: local.x, y: local.y, w: local.width, h: local.height } : null,
       rect: rect ? { x: rect.x, y: rect.y, w: rect.width, h: rect.height } : null,
       rendered:
-        !!local &&
+        bounds.length >= 4 &&
+        bounds.slice(0, 4).every(Number.isFinite) &&
+        bounds[2] > 0 &&
+        bounds[3] > 0 &&
         visibility !== "hidden" &&
         visibility !== "collapse" &&
         (Number.parseFloat(opacity) || 0) > 0,
@@ -139,17 +148,20 @@ export async function normalizeSnapshot(
     }
     sources.set(id, doc);
   }
-  let viewport: Viewport = { width: 0, height: 0 };
-  let scrollX = 0,
-    scrollY = 0;
+  let metrics: LayoutMetrics = {};
   try {
-    const measured = cssViewport(await geometry.layoutMetrics(target));
-    viewport = { width: measured.width, height: measured.height };
-    scrollX = measured.scrollX;
-    scrollY = measured.scrollY;
+    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[] = [];
@@ -195,12 +207,24 @@ export async function normalizeSnapshot(
     const doc = sources.get(frame.frameId);
     if (!doc) continue;
     const source = { target, frameId: frame.frameId };
-    const state: FrameProjectionState | null =
+    const coordinates = snapshotCoordinates(
+      doc,
+      layoutUnitsPerCssPixel,
       frame.frameId === rootFrameId
-        ? {
-            status: "available",
-            projection: { source, geometry: { sourceClips: [], edges: [], topViewport: viewport } },
-          }
+        ? { 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({
@@ -209,6 +233,8 @@ export async function normalizeSnapshot(
         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))
@@ -253,6 +279,14 @@ export async function normalizeSnapshot(
             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,
@@ -281,8 +315,7 @@ export async function normalizeSnapshot(
         projection: state,
         target,
         ...(target.sessionId ? { targetProjection } : {}),
-        scrollX: doc.scrollOffsetX ?? (frame.frameId === rootFrameId ? scrollX : 0),
-        scrollY: doc.scrollOffsetY ?? (frame.frameId === rootFrameId ? scrollY : 0),
+        coordinates,
       },
       signal,
     );

apps/extension/src/tools/vom/snapshot.ts

@@ -175,7 +175,7 @@ export async function decodeDocument(
       li === undefined
         ? undefined
         : {
-            boundsSpace: "snapshot-document-css" as const,
+            boundsSpace: "snapshot-document-layout" as const,
             bounds: dl?.bounds?.[li],
             styles,
           };

evals/browser/cases/regression/snapshot-coordinates/README.md

@@ -0,0 +1,44 @@
+# DOMSnapshot layout-unit regression (#195)
+
+Source: https://github.com/Tencent/BrowserSkill/pull/195
+
+DOMSnapshot bounds and document scroll offsets retain Blink layout units. Treating them as CSS
+pixels changes both positions and sizes under device scaling/browser zoom, before iframe
+projection or viewport clipping even starts.
+
+The fixture contains a scrolled root, a scrolled same-process iframe, an OOPIF served from the
+other loopback hostname, and a nested iframe in each. Owners have borders, padding and CSS
+transforms. The geometry test compares the production capture's local and top-level rectangles
+against independent DOM border boxes, with at most 2 CSS pixels of layout rounding. It also
+checks that each target reads layout metrics only once. No credentials or personal tabs are used.
+
+Run the geometric assertions with Node 22+ and a local Chrome executable:
+
+```sh
+BSK_GEOMETRY_CHROME=/path/to/chrome pnpm --filter @browser-skill/extension exec vitest run \
+  src/tools/__tests__/snapshot-coordinates.browser.test.ts
+```
+
+The test launches and cleans up its own headless Chrome profiles. It explicitly verifies the
+requested browser zoom and OOPIF topology, so unsupported setups fail rather than silently
+testing a different configuration. It is skipped in ordinary unit runs unless the executable
+is specified. No browser download or new package dependency is required.
+
+The corpus smoke case checks fixture readiness and observable semantics through the real CLI:
+
+```sh
+BSK_AUTO_UPDATE=off pnpm eval:browser smoke --case snapshot-coordinates --bsk ./target/debug/bsk
+```
+
+Smoke alone does **not** certify coordinate accuracy; CLI observations do not expose raw boxes.
+Use the geometric test above for the regression's numeric assertions.
+
+## Separate existing boundary
+
+The OOPIF root uses non-occupying scrollbars in the unit-conversion regression. Root and
+same-process frames retain normal scrollbars. Append `&classic-scrollbars` to the fixture URL
+to reproduce the separate existing OOPIF projection issue: `targetProjection()` maps the CSS
+layout viewport (which excludes occupying scrollbars) onto the entire owner content quad.
+This inflates the projected coordinates when scrollbars occupy space. Main already has that
+mapping; fixing it also changes shared live geometry and is outside this snapshot-unit fix.
+The test does not relax its numeric tolerance to absorb that error.

evals/browser/cases/regression/snapshot-coordinates/chrome.mjs

@@ -0,0 +1,99 @@
+import { spawn } from "node:child_process";
+import { once } from "node:events";
+import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+
+// This regression owns its browser/profile. It never attaches to a user's Chrome.
+export async function withChrome({ executable, deviceScale, zoom }, run) {
+  const profile = await mkdtemp(join(tmpdir(), "bsk-snapshot-coordinates-"));
+  let chrome;
+  let socket;
+  const pending = new Map();
+  try {
+    await mkdir(join(profile, "Default"));
+    await writeFile(
+      join(profile, "Default", "Preferences"),
+      JSON.stringify({
+        partition: { default_zoom_level: { x: Math.log(zoom) / Math.log(1.2) } },
+      }),
+    );
+    chrome = spawn(
+      executable,
+      [
+        "--headless=new",
+        "--no-first-run",
+        "--no-default-browser-check",
+        "--disable-extensions",
+        "--site-per-process",
+        "--remote-debugging-port=0",
+        "--window-size=1600,1200",
+        `--force-device-scale-factor=${deviceScale}`,
+        `--user-data-dir=${profile}`,
+        "about:blank",
+      ],
+      { stdio: ["ignore", "ignore", "pipe"] },
+    );
+    const endpoint = await new Promise((resolve, reject) => {
+      let output = "";
+      const timeout = setTimeout(
+        () => reject(new Error(`Chrome startup timed out: ${output}`)),
+        15_000,
+      );
+      const fail = (error) => {
+        clearTimeout(timeout);
+        reject(error);
+      };
+      chrome.once("error", fail);
+      chrome.once("exit", (code) => fail(new Error(`Chrome exited (${code}): ${output}`)));
+      chrome.stderr.on("data", (chunk) => {
+        output += chunk;
+        const match = output.match(/DevTools listening on (ws:\/\/\S+)/);
+        if (match) {
+          clearTimeout(timeout);
+          resolve(match[1]);
+        }
+      });
+    });
+    socket = new WebSocket(endpoint);
+    await new Promise((resolve, reject) => {
+      socket.addEventListener("open", resolve, { once: true });
+      socket.addEventListener("error", reject, { once: true });
+    });
+    socket.addEventListener("message", ({ data }) => {
+      const reply = JSON.parse(data);
+      const request = pending.get(reply.id);
+      if (!request) return;
+      clearTimeout(request.timeout);
+      pending.delete(reply.id);
+      if (reply.error) request.reject(new Error(JSON.stringify(reply.error)));
+      else request.resolve(reply.result);
+    });
+    let sequence = 0;
+    const send = (method, params = {}, sessionId) =>
+      new Promise((resolve, reject) => {
+        const id = ++sequence;
+        const timeout = setTimeout(() => {
+          pending.delete(id);
+          reject(new Error(`CDP timed out: ${method}`));
+        }, 10_000);
+        pending.set(id, { resolve, reject, timeout });
+        socket.send(JSON.stringify({ id, method, params, sessionId }));
+      });
+    await run(send);
+  } finally {
+    for (const request of pending.values()) {
+      clearTimeout(request.timeout);
+      request.reject(new Error("regression browser closed"));
+    }
+    socket?.close();
+    if (chrome && chrome.exitCode === null && chrome.signalCode === null) {
+      const exited = once(chrome, "exit");
+      const timeout = setTimeout(() => chrome.kill("SIGKILL"), 5_000);
+      chrome.kill();
+      await exited;
+      clearTimeout(timeout);
+    }
+    await rm(profile, { recursive: true, force: true });
+  }
+}

evals/browser/cases/regression/snapshot-coordinates/snapshot-coordinates.case.json

@@ -0,0 +1,33 @@
+{
+  "$schema": "../../../schemas/case.schema.json",
+  "schemaVersion": 1,
+  "id": "snapshot-coordinates",
+  "title": "Scrolled and nested frame coordinate fixture",
+  "suite": "regression",
+  "tags": ["geometry", "iframe", "scroll"],
+  "fixture": { "startPath": "/snapshot-coordinates" },
+  "prompts": {
+    "en": "Open {url}, observe the page and its frames, report the GEOMETRY marker, then close the session.",
+    "zh-CN": "打开 {url}，观察页面及其 iframe，报告 GEOMETRY 标记，然后关闭会话。"
+  },
+  "coverage": ["session.start", "session.stop", "page.navigate", "inspect.observe"],
+  "assertions": {
+    "site": [
+      {
+        "label": "root fixture scrolled and settled",
+        "type": "geometry.ready",
+        "where": { "data.root": true },
+        "minCount": 1
+      }
+    ],
+    "response": [{ "label": "observed the fixture marker", "includes": "GEOMETRY-195" }],
+    "adapter": [{ "label": "browser session was closed", "key": "sessionStopped" }]
+  },
+  "smoke": {
+    "steps": [
+      { "action": "navigate" },
+      { "action": "wait-site-event", "type": "geometry.ready", "where": { "root": true } },
+      { "action": "observe" }
+    ]
+  }
+}

evals/browser/cases/regression/snapshot-coordinates/snapshot-coordinates.fixture.mjs

@@ -0,0 +1,52 @@
+import { page, withRun } from "../../../lib/fixtures.mjs";
+
+export default {
+  id: "snapshot-coordinates",
+  routes: ["/snapshot-coordinates", "/snapshot-coordinates/frame", "/snapshot-coordinates/nested"],
+  render({ pathname, runId, query }) {
+    const root = pathname === "/snapshot-coordinates";
+    const nested = pathname.endsWith("/nested");
+    return page({
+      title: "Snapshot coordinate regression",
+      body: `
+        <style>
+          main { margin: 0; width: auto; }
+          body { width: 2000px; height: 2400px; }
+          html { overflow-anchor: none; }
+          ${query.get("scrollbars") === "none" ? "html { scrollbar-width: none; }" : ""}
+          button { position: absolute; box-sizing: border-box; padding: 0; border: 2px solid black; border-radius: 0; }
+          #probe { left: ${root ? 180 : 100}px; top: ${root ? 360 : 160}px; width: 120px; height: 40px; }
+          iframe { position: absolute; box-sizing: content-box; width: 320px; height: 220px;
+            border: 6px solid black; padding: 8px; transform: scale(1.25); transform-origin: 0 0; }
+          #same { left: 340px; top: 400px; }
+          #cross { left: 820px; top: 400px; }
+          #nested { left: 150px; top: 210px; width: 130px; height: 70px; border-width: 2px; padding: 4px; transform: scale(0.8); }
+          ${nested ? "#probe { left: 30px; top: 40px; width: 60px; height: 20px; }" : ""}
+        </style>
+        <button id="probe" data-geometry-probe>GEOMETRY-195</button>
+        ${root ? `<iframe id="same" name="same" title="same-process frame" src="${withRun("/snapshot-coordinates/frame", runId)}"></iframe><iframe id="cross" name="cross" title="cross-site frame"></iframe>` : ""}
+        ${!root && !nested ? `<iframe id="nested" name="nested" title="nested frame" src="${withRun("/snapshot-coordinates/nested", runId)}"></iframe>` : ""}
+      `,
+      script: `
+        history.scrollRestoration = "manual";
+        const cross = document.querySelector("#cross");
+        if (cross) {
+          const url = new URL(${JSON.stringify(withRun("/snapshot-coordinates/frame", runId))}, location.href);
+          url.hostname = location.hostname === "127.0.0.1" ? "localhost" : "127.0.0.1";
+          // Isolate unit conversion from the pre-existing OOPIF scrollbar-width
+          // projection issue. ?classic-scrollbars retains that separate reproduction.
+          if (!new URLSearchParams(location.search).has("classic-scrollbars")) url.searchParams.set("scrollbars", "none");
+          cross.src = url.href;
+        }
+        window.addEventListener("load", () => {
+          scrollTo(${root ? "80, 240" : nested ? "10, 20" : "40, 100"});
+          requestAnimationFrame(() => requestAnimationFrame(() => {
+            window.geometryReady = true;
+            document.documentElement.dataset.geometryReady = "true";
+            browserEval.send("geometry.ready", { root: ${root} });
+          }));
+        });
+      `,
+    });
+  },
+};

evals/browser/tests/eval.test.mjs

@@ -41,17 +41,22 @@ test("case manifests are discovered, ordered, and grouped into suites", () => {
       "diagnostics",
       "mobile-emulation",
       "generated-form",
+      "snapshot-coordinates",
     ],
   );
-  assert.deepEqual(repositorySummary(cases, fixtureRegistry).suites, { core: 6, matrix: 1 });
+  assert.deepEqual(repositorySummary(cases, fixtureRegistry).suites, {
+    core: 6,
+    matrix: 1,
+    regression: 1,
+  });
 });
 
 test("repository validation links every case to a fixture and valid workflow evidence", () => {
   assert.deepEqual(validateRepositoryCases(cases, fixtureRegistry), []);
   const summary = repositorySummary(cases, fixtureRegistry);
-  assert.equal(summary.cases, 7);
-  assert.equal(summary.fixtureModules, 8);
-  assert.equal(summary.fixtureRoutes, 12);
+  assert.equal(summary.cases, 8);
+  assert.equal(summary.fixtureModules, 9);
+  assert.equal(summary.fixtureRoutes, 15);
 });
 
 test("manifest validation rejects unknown operations and incomplete workflow steps", () => {