fix(vom): bug fix

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

@@ -36,6 +36,14 @@ function fakeAgentWindow(ids: number[]) {
 const TINY_PNG =
   "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR4nGNgYGBgAAAABQABh6FO1AAAAABJRU5ErkJggg==";
 
+function pngWithIhdrDimensions(width: number, height: number): string {
+  const bytes = Uint8Array.from(atob(TINY_PNG), (character) => character.charCodeAt(0));
+  const view = new DataView(bytes.buffer);
+  view.setUint32(16, width);
+  view.setUint32(20, height);
+  return btoa(String.fromCharCode(...bytes));
+}
+
 function makeScreenshotDeps(
   opts: {
     cdp?: CdpRunner;
@@ -86,6 +94,7 @@ describe("stripDataUrlPrefix", () => {
 describe("parsePngDimensions", () => {
   it("parses width/height from the IHDR chunk", () => {
     expect(parsePngDimensions(TINY_PNG)).toEqual({ width: 1, height: 1 });
+    expect(parsePngDimensions(pngWithIhdrDimensions(100, 80))).toEqual({ width: 100, height: 80 });
   });
   it("returns null on non-PNG input", () => {
     expect(parsePngDimensions("not-a-png-payload-just-random-base64-text-zzzzzzzzz")).toBeNull();
@@ -120,6 +129,20 @@ describe("handleScreenshot", () => {
     expect(get).not.toHaveBeenCalled();
   });
 
+  it("fails closed when a full-tab capture is not a valid PNG", async () => {
+    const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
+    await sm.start("aa11");
+    const res = await handleScreenshot(
+      sm,
+      { session_id: "aa11" },
+      makeScreenshotDeps({
+        captureVisibleTab: vi.fn(async () => "data:image/png;base64,bm90LWEtcG5n"),
+      }),
+    );
+
+    expect(res).toMatchObject({ code: "cdp_failed", message: /invalid PNG data/ });
+  });
+
   it("returns not_found when Agent Window has no active tab", async () => {
     const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
     await sm.start("aa11");
@@ -349,7 +372,7 @@ describe("handleScreenshot", () => {
         cssLayoutViewport: { clientWidth: 800, clientHeight: 600 },
       }),
       "DOM.getContentQuads": () => ({ quads: [[0, 0, 200, 0, 200, 100, 0, 100]] }),
-      "Page.captureScreenshot": () => ({ data: TINY_PNG }),
+      "Page.captureScreenshot": () => ({ data: pngWithIhdrDimensions(100, 80) }),
     });
 
     const res = await handleScreenshot(
@@ -368,6 +391,95 @@ describe("handleScreenshot", () => {
       clip?: { x: number; y: number; width: number; height: number };
     };
     expect(clip.clip).toMatchObject({ x: 25, y: 30, width: 50, height: 40 });
+    expect(res).toMatchObject({ width: 100, height: 80 });
+  });
+
+  it("routes OOPIF surface geometry through its child session and captures top coordinates", async () => {
+    const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
+    const ctx = await sm.start("aa11");
+    ctx.refStore.set("e5", 999, {
+      tabId: 7,
+      frameId: "child-frame",
+      cdpSessionId: "child-session",
+      kind: "surface",
+      visibleRect: { x: 224, y: 346, w: 200, h: 80 },
+    });
+    const { cdp, sent } = makeFakeCdp({
+      "DOM.getBoxModel": () => ({
+        model: { content: [204, 306, 604, 306, 604, 506, 204, 506] },
+      }),
+      "Page.getLayoutMetrics": () => ({
+        cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
+      }),
+      "Page.captureScreenshot": () => ({ data: TINY_PNG }),
+    });
+    cdp.getFrameGraph = vi.fn(async () => ({
+      rootFrameId: "main",
+      frames: [
+        { frameId: "main", target: { tabId: 7 } },
+        {
+          frameId: "child-frame",
+          parentFrameId: "main",
+          ownerBackendNodeId: 99,
+          target: { tabId: 7, sessionId: "child-session" },
+        },
+      ],
+    }));
+    const targetCalls: Array<{ sessionId?: string; method: string }> = [];
+    cdp.sendToTarget = vi.fn(async (target, method) => {
+      targetCalls.push({ sessionId: target.sessionId, method });
+      if (method === "DOM.getContentQuads") {
+        return { quads: [[10, 20, 110, 20, 110, 60, 10, 60]] };
+      }
+      if (method === "Page.getLayoutMetrics") {
+        return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
+      }
+      throw new Error(`unexpected child CDP call ${method}`);
+    }) as CdpRunner["sendToTarget"];
+
+    const res = await handleScreenshot(
+      sm,
+      { session_id: "aa11", ref: "@e5", tab_id: 7 },
+      makeScreenshotDeps({
+        cdp,
+        get: vi.fn(async () => ({ id: 7, windowId: 100, active: false }) as chrome.tabs.Tab),
+        query: vi.fn(),
+        captureVisibleTab: vi.fn(),
+      }),
+    );
+
+    if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
+    expect(targetCalls).toEqual([
+      { sessionId: "child-session", method: "DOM.getContentQuads" },
+      { sessionId: "child-session", method: "Page.getLayoutMetrics" },
+    ]);
+    const clip = sent.find((call) => call.method === "Page.captureScreenshot")?.params as {
+      clip?: { x: number; y: number; width: number; height: number };
+    };
+    expect(clip.clip).toMatchObject({ x: 224, y: 346, width: 200, height: 80 });
+  });
+
+  it("fails closed when a ref capture is not a valid PNG", async () => {
+    const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
+    const ctx = await sm.start("aa11");
+    ctx.refStore.set("e5", 999, { tabId: 7, kind: "surface" });
+    const { cdp } = makeFakeCdp({
+      "DOM.getContentQuads": () => ({ quads: [[0, 0, 50, 0, 50, 50, 0, 50]] }),
+      "Page.captureScreenshot": () => ({ data: "bm90LWEtcG5n" }),
+    });
+
+    const res = await handleScreenshot(
+      sm,
+      { session_id: "aa11", ref: "@e5", tab_id: 7 },
+      makeScreenshotDeps({
+        cdp,
+        get: vi.fn(async () => ({ id: 7, windowId: 100, active: false }) as chrome.tabs.Tab),
+        query: vi.fn(),
+        captureVisibleTab: vi.fn(),
+      }),
+    );
+
+    expect(res).toMatchObject({ code: "cdp_failed", message: /invalid PNG data/ });
   });
 
   it("returns not_found for unknown ref", async () => {

apps/extension/src/tools/observation.ts

@@ -116,8 +116,8 @@ export function stripDataUrlPrefix(dataUrl: string): string {
 
 /**
  * Parse a PNG's IHDR chunk and return `(width, height)`. Returns
- * `null` on any malformed input so callers fall back to `0/0` instead
- * of throwing.
+ * `null` on malformed input so callers can reject dimensions that are
+ * not authoritative instead of guessing from a CSS-space rectangle.
  *
  * PNG layout: 8-byte signature, then a 4-byte length, 4-byte type
  * ("IHDR"), then the chunk data — width is bytes 16-19 BE, height is
@@ -129,9 +129,9 @@ export function parsePngDimensions(base64: string): { width: number; height: num
     const head = base64.length > 64 ? base64.slice(0, 64) : base64;
     const bin = atob(head);
     if (bin.length < 24) return null;
-    if (bin.charCodeAt(0) !== 0x89 || bin.charCodeAt(1) !== 0x50 || bin.charCodeAt(2) !== 0x4e) {
-      return null;
-    }
+    const expectedSignature = [0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a];
+    if (expectedSignature.some((byte, index) => bin.charCodeAt(index) !== byte)) return null;
+    if (bin.slice(12, 16) !== "IHDR") return null;
     const u32 = (off: number) =>
       (bin.charCodeAt(off) << 24) |
       (bin.charCodeAt(off + 1) << 16) |
@@ -250,10 +250,10 @@ async function captureElementScreenshot(
     if (!image_base64) {
       return { code: "cdp_failed", message: "Page.captureScreenshot returned no data" };
     }
-    const dims = parsePngDimensions(image_base64) ?? {
-      width: Math.round(rect.width),
-      height: Math.round(rect.height),
-    };
+    const dims = parsePngDimensions(image_base64);
+    if (!dims) {
+      return { code: "cdp_failed", message: "Page.captureScreenshot returned invalid PNG data" };
+    }
     return { image_base64, width: dims.width, height: dims.height };
   } catch (err) {
     return {
@@ -402,7 +402,10 @@ export async function handleScreenshot(
   if (isRpcError(captured)) return captured;
   if (signal?.aborted) return cancelled("screenshot");
   const image_base64 = captured;
-  const dims = parsePngDimensions(image_base64) ?? { width: 0, height: 0 };
+  const dims = parsePngDimensions(image_base64);
+  if (!dims) {
+    return { code: "cdp_failed", message: "screenshot capture returned invalid PNG data" };
+  }
   return withShotDialogs({
     image_base64,
     width: dims.width,

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

@@ -1,6 +1,7 @@
 import { describe, expect, it, vi } from "vitest";
 import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "../../../lib/overlay-bridge";
 import { captureViewModel, collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
+import { discoverRenderedSurfaces } from "../rendered-surfaces";
 
 // Minimal but format-accurate captureSnapshot reply: a body with one
 // fixed full-screen overlay div carrying a password input.
@@ -1188,6 +1189,97 @@ describe("captureViewModel", () => {
     expect(input?.rect).toEqual({ x: 16, y: 28, w: 40, h: 20 });
   });
 
+  it("keeps same-origin iframe canvas discovery in top-level CSS coordinates at dpr 1 and 2", async () => {
+    const captureAtDpr = async (dpr: number) => {
+      const S = ["html", "body", "iframe", "canvas", "static", "auto"];
+      const i = (s: string) => S.indexOf(s);
+      const scale = (values: number[]) => values.map((value) => value * dpr);
+      const snapshot = {
+        strings: S,
+        documents: [
+          {
+            frameId: "main",
+            nodes: {
+              parentIndex: [-1, 0, 1],
+              nodeName: [i("html"), i("body"), i("iframe")],
+              backendNodeId: [10, 11, 13],
+              attributes: [[], [], []],
+              contentDocumentIndex: { index: [2], value: [1] },
+            },
+            layout: {
+              nodeIndex: [1, 2],
+              styles: [
+                [i("static"), i("auto")],
+                [i("static"), i("auto")],
+              ],
+              bounds: [scale([0, 0, 1000, 800]), scale([100, 150, 300, 200])],
+              paintOrders: [0, 1],
+            },
+          },
+          {
+            frameId: "child",
+            nodes: {
+              parentIndex: [-1, 0],
+              nodeName: [i("body"), i("canvas")],
+              backendNodeId: [20, 21],
+              attributes: [[], []],
+            },
+            layout: {
+              nodeIndex: [0, 1],
+              styles: [
+                [i("static"), i("auto")],
+                [i("static"), i("auto")],
+              ],
+              bounds: [scale([0, 0, 300, 200]), scale([20, 30, 120, 60])],
+              paintOrders: [0, 1],
+            },
+          },
+        ],
+      };
+      const cdp = {
+        send: vi.fn(async (_tabId: number, method: string) => {
+          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 },
+              layoutViewport: { clientWidth: 1000 * dpr, clientHeight: 800 * dpr },
+            };
+          }
+          throw new Error(method);
+        }) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
+      };
+      const captured = await captureViewModel(cdp, 4);
+      const childNodes = captured.frameNodes?.get("child") ?? [];
+      return discoverRenderedSurfaces(
+        [
+          {
+            frameId: "child",
+            contextScopeId: "child",
+            parentFrameId: "main",
+            ownerBackendNodeId: 13,
+            target: { tabId: 4 },
+            domNodes: childNodes,
+            axNodes: [],
+          },
+        ],
+        captured.viewport,
+      );
+    };
+
+    const atDpr1 = await captureAtDpr(1);
+    const atDpr2 = await captureAtDpr(2);
+
+    expect(atDpr1).toEqual([
+      expect.objectContaining({
+        backendNodeId: 21,
+        frameId: "child",
+        visibleRect: { x: 120, y: 180, w: 120, h: 60 },
+      }),
+    ]);
+    expect(atDpr2).toEqual(atDpr1);
+  });
+
   it("normalizes bounds then subtracts CSS scroll at dpr>1", async () => {
     const S = ["html", "body", "div", "position", "fixed", "static", "pointer-events", "auto"];
     const i = (s: string) => S.indexOf(s);

packages/vom/src/__tests__/render.test.ts

@@ -47,8 +47,9 @@ describe("renderVom single-layer page", () => {
     ];
     const out = renderVom(input);
 
+    expect(out.text).toContain("[visual surfaces]");
     expect(out.text).toContain(
-      '@e1 surface "Data grid" [rendering=canvas; layers=2; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
+      '@e1 surface "Data grid" [bounds=10,20,800,500; rendering=canvas; layers=2; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
     );
     expect(out.refs).toContainEqual(
       expect.objectContaining({
@@ -77,7 +78,7 @@ describe("renderVom single-layer page", () => {
     const out = renderVom(input);
 
     expect(out.text).toContain(
-      '@e1 surface "canvas visual surface" [rendering=canvas; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
+      '@e1 surface "canvas visual surface" [bounds=10,20,800,500; rendering=canvas; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
     );
     expect(out.refs).toContainEqual(
       expect.objectContaining({
@@ -89,6 +90,78 @@ describe("renderVom single-layer page", () => {
     );
   });
 
+  it("appends visual refs after DOM refs so canvas density cannot renumber controls", () => {
+    const input = scene([
+      node({ id: 1, role: "RootWebArea", frameId: "main" }),
+      node({ id: 2, parentId: 1, role: "button", name: "Submit", tag: "button" }),
+    ]);
+    input.visualSurfaces = [
+      {
+        parentId: 1,
+        backendNodeId: 99,
+        frameId: "main",
+        renderingKind: "canvas",
+        visibleRect: { x: 10, y: 20, w: 80, h: 50 },
+        memberCount: 1,
+      },
+    ];
+
+    const withoutVisuals = renderVom({ ...input, visualSurfaces: [] });
+    const withVisuals = renderVom(input);
+
+    expect(withoutVisuals.refs[0]).toMatchObject({ ref: "e1", backendNodeId: 2, kind: "dom" });
+    expect(withVisuals.refs[0]).toMatchObject({ ref: "e1", backendNodeId: 2, kind: "dom" });
+    expect(withVisuals.refs[1]).toMatchObject({ ref: "e2", backendNodeId: 99, kind: "surface" });
+    expect(withVisuals.text.indexOf('@e1 button "Submit"')).toBeLessThan(
+      withVisuals.text.indexOf("[visual surfaces]"),
+    );
+  });
+
+  it("bounds visual output and prefers explicitly labeled surfaces", () => {
+    const input = scene([node({ id: 1, role: "RootWebArea", frameId: "main" })]);
+    input.visualSurfaces = Array.from({ length: 12 }, (_, index) => ({
+      parentId: 1,
+      backendNodeId: 100 + index,
+      frameId: "main",
+      renderingKind: "canvas" as const,
+      visibleRect: { x: index * 10, y: 20, w: 8, h: 8 },
+      ...(index === 11 ? { label: "Important status" } : {}),
+      memberCount: 1,
+    }));
+
+    const out = renderVom(input);
+    const surfaceRefs = out.refs.filter((ref) => ref.kind === "surface");
+
+    expect(surfaceRefs).toHaveLength(8);
+    expect(surfaceRefs[0]).toMatchObject({ backendNodeId: 111, name: "Important status" });
+    expect(out.text).toContain("… 4 additional visual surfaces omitted");
+    expect(out.truncated).toBe(true);
+  });
+
+  it("does not let a visual surface exhaust the budget before later DOM content", () => {
+    const input = scene([
+      node({ id: 1, role: "RootWebArea", name: "Doc", frameId: "main" }),
+      node({ id: 2, parentId: 1, role: "button", name: "First", tag: "button" }),
+      node({ id: 3, parentId: 1, role: "button", name: "Later", tag: "button" }),
+    ]);
+    input.visualSurfaces = [
+      {
+        parentId: 1,
+        backendNodeId: 99,
+        frameId: "main",
+        renderingKind: "canvas",
+        visibleRect: { x: 10, y: 20, w: 800, h: 500 },
+        memberCount: 1,
+      },
+    ];
+
+    const out = renderVom(input, { maxTokens: 30 });
+
+    expect(out.text).toContain('@e2 button "Later"');
+    expect(out.refs.filter((ref) => ref.kind === "surface")).toHaveLength(0);
+    expect(out.truncated).toBe(true);
+  });
+
   it("does not derive handle context across frame scopes", () => {
     const out = renderVom(
       scene([

packages/vom/src/render.ts

@@ -88,6 +88,7 @@ const MAX_CUSTOM_RECOVERY_AREA = 180_000;
 const MAX_RECOVERABLE_SINGLE_INTENT_AREA = 360_000;
 const MAX_HANDLE_CONTEXT_ITEMS = 3;
 const MAX_SURFACE_ITEMS = 12;
+const MAX_VISUAL_SURFACES = 8;
 const MAX_SCOPE_LINES = 40;
 const RECOVERY_HANDLER_ATTRS = ["onclick", "onmousedown", "onkeydown", "onkeyup", "onkeypress"];
 const NATIVE_TAGS = new Set(["button", "input", "select", "textarea"]);
@@ -794,40 +795,81 @@ interface RenderState {
   duplicateRefNames: Set<string>;
   surfaceMap: Map<number, CondSurface>;
   scopeMap: Map<number, ActiveScopeBlock>;
-  visualSurfaces: Map<number | null, VomVisualSurface[]>;
+  visualSurfaces: VomVisualSurface[];
 }
 
-function groupedByParent<T extends { parentId: number | null }>(
-  items: T[],
-): Map<number | null, T[]> {
-  const grouped = new Map<number | null, T[]>();
-  for (const item of items) {
-    const siblings = grouped.get(item.parentId) ?? [];
-    siblings.push(item);
-    grouped.set(item.parentId, siblings);
-  }
-  return grouped;
+function visualSurfaceArea(surface: VomVisualSurface): number {
+  return Math.max(0, surface.visibleRect.w) * Math.max(0, surface.visibleRect.h);
 }
 
-function emitVisualEntries(parentId: number | null, depth: number, state: RenderState): void {
-  if (state.stopped) return;
-  for (const surface of state.visualSurfaces.get(parentId) ?? []) {
-    if (depth > state.maxDepth) {
-      state.truncated = true;
+function compareVisualSurfaces(a: VomVisualSurface, b: VomVisualSurface): number {
+  const aLabeled = cleaned(a.label) !== undefined;
+  const bLabeled = cleaned(b.label) !== undefined;
+  return (
+    Number(bLabeled) - Number(aLabeled) ||
+    visualSurfaceArea(b) - visualSurfaceArea(a) ||
+    a.frameId.localeCompare(b.frameId) ||
+    a.visibleRect.y - b.visibleRect.y ||
+    a.visibleRect.x - b.visibleRect.x ||
+    a.backendNodeId - b.backendNodeId
+  );
+}
+
+function visualSurfaceLine(surface: VomVisualSurface, ref: string): string {
+  const label = cleaned(surface.label) ?? `${surface.renderingKind} visual surface`;
+  const layers = surface.memberCount > 1 ? `; layers=${surface.memberCount}` : "";
+  const { x, y, w, h } = surface.visibleRect;
+  const bounds = [x, y, w, h].map(Math.round).join(",");
+  return `  @${ref} surface ${JSON.stringify(label)} [bounds=${bounds}; rendering=${surface.renderingKind}${layers}; visual-only; requires=image-understanding; use: bsk screenshot --ref @${ref}]`;
+}
+
+function selectVisualSurfaces(
+  surfaces: readonly VomVisualSurface[],
+  nodesById: ReadonlyMap<number, VomNode>,
+): { selected: VomVisualSurface[]; eligibleCount: number } {
+  const selected: VomVisualSurface[] = [];
+  let eligibleCount = 0;
+
+  for (const surface of surfaces) {
+    if (surface.parentId !== null && !nodesById.has(surface.parentId)) continue;
+    eligibleCount += 1;
+
+    const insertionIndex = selected.findIndex(
+      (candidate) => compareVisualSurfaces(surface, candidate) < 0,
+    );
+    if (insertionIndex < 0) {
+      if (selected.length < MAX_VISUAL_SURFACES) selected.push(surface);
       continue;
     }
+    selected.splice(insertionIndex, 0, surface);
+    if (selected.length > MAX_VISUAL_SURFACES) selected.pop();
+  }
+
+  return { selected, eligibleCount };
+}
+
+function emitVisualAppendix(state: RenderState): void {
+  if (state.stopped) return;
+  const { selected, eligibleCount } = selectVisualSurfaces(state.visualSurfaces, state.nodesById);
+  if (eligibleCount === 0) return;
+
+  const header = "[visual surfaces]";
+  let headerEmitted = false;
+  let emitted = 0;
+  for (const surface of selected) {
     const ref = `e${state.nextRef}`;
-    const label = cleaned(surface.label) ?? `${surface.renderingKind} visual surface`;
-    const layers = surface.memberCount > 1 ? `; layers=${surface.memberCount}` : "";
-    const line = `${"  ".repeat(depth)}@${ref} surface ${JSON.stringify(label)} [rendering=${surface.renderingKind}${layers}; visual-only; requires=image-understanding; use: bsk screenshot --ref @${ref}]`;
-    const nextTokens = state.tokens + estimateTokens(line);
-    if (nextTokens > state.maxTokens) {
-      state.truncated = true;
-      state.stopped = true;
-      return;
+    const line = visualSurfaceLine(surface, ref);
+    const nextTokens =
+      state.tokens + estimateTokens(line) + (headerEmitted ? 0 : estimateTokens(header));
+    if (nextTokens > state.maxTokens) break;
+    if (!headerEmitted) {
+      state.lines.push(header);
+      state.tokens += estimateTokens(header);
+      headerEmitted = true;
     }
     state.lines.push(line);
-    state.tokens = nextTokens;
+    state.tokens += estimateTokens(line);
+    const label = cleaned(surface.label) ?? `${surface.renderingKind} visual surface`;
     state.refs.push({
       ref,
       backendNodeId: surface.backendNodeId,
@@ -840,6 +882,20 @@ function emitVisualEntries(parentId: number | null, depth: number, state: Render
       line: state.lines.length - 1,
     });
     state.nextRef += 1;
+    emitted += 1;
+  }
+
+  const omitted = eligibleCount - emitted;
+  if (omitted > 0) {
+    state.truncated = true;
+    if (headerEmitted) {
+      const summary = `  … ${omitted} additional visual surfaces omitted`;
+      const nextTokens = state.tokens + estimateTokens(summary);
+      if (nextTokens <= state.maxTokens) {
+        state.lines.push(summary);
+        state.tokens = nextTokens;
+      }
+    }
   }
 }
 
@@ -872,34 +928,24 @@ function emitActiveScopeBlock(scope: ActiveScopeBlock, depth: number, state: Ren
   }
 }
 
-type RenderTask =
-  | { kind: "node"; node: VomNode; depth: number }
-  | { kind: "visual"; parentId: number | null; depth: number };
-
 function pushRenderChildren(
-  stack: RenderTask[],
+  stack: Array<{ node: VomNode; depth: number }>,
   children: readonly VomNode[],
   depth: number,
 ): void {
   for (let index = children.length - 1; index >= 0; index -= 1) {
-    stack.push({ kind: "node", node: children[index], depth });
+    stack.push({ node: children[index], depth });
   }
 }
 
 function renderTree(children: Map<number | null, VomNode[]>, state: RenderState): void {
-  const stack: RenderTask[] = [{ kind: "visual", parentId: null, depth: 1 }];
+  const stack: Array<{ node: VomNode; depth: number }> = [];
   pushRenderChildren(stack, children.get(null) ?? [], 1);
 
   while (stack.length > 0 && !state.stopped) {
-    const task = stack.pop() as RenderTask;
-    if (task.kind === "visual") {
-      emitVisualEntries(task.parentId, task.depth, state);
-      continue;
-    }
-    const { node, depth } = task;
+    const { node, depth } = stack.pop() as { node: VomNode; depth: number };
 
     if (!shouldRender(node)) {
-      stack.push({ kind: "visual", parentId: node.id, depth });
       pushRenderChildren(stack, children.get(node.id) ?? [], depth);
       continue;
     }
@@ -942,10 +988,8 @@ function renderTree(children: Map<number | null, VomNode[]>, state: RenderState)
     if (scope) emitActiveScopeBlock(scope, depth + 1, state);
 
     if ((ref && shouldSkipRedundantRefChildren(node)) || shouldSkipRedundantChildren(node, state)) {
-      emitVisualEntries(node.id, depth + 1, state);
       continue;
     }
-    stack.push({ kind: "visual", parentId: node.id, depth: depth + 1 });
     pushRenderChildren(stack, children.get(node.id) ?? [], depth + 1);
   }
 }
@@ -976,7 +1020,7 @@ function renderNodes(
     duplicateRefNames: duplicateReferenceNames(nodes),
     surfaceMap: new Map(surfaces.map((surface) => [surface.triggerId, surface])),
     scopeMap: new Map(activeScopeBlocks.map((scope) => [scope.triggerId, scope])),
-    visualSurfaces: groupedByParent(visualSurfaces),
+    visualSurfaces,
   };
 
   renderTree(children, state);
@@ -1198,7 +1242,10 @@ function renderDoubleLayer(scene: VomScene, layer: BlockingLayer, options: VomOp
     scene.activeScopeBlocks,
     scene.visualSurfaces?.filter((surface) => visibleSurface(surface.parentId)),
   );
-  state.lines.push(renderPageOcclusionLine(hiddenCount));
+  const occlusionLine = renderPageOcclusionLine(hiddenCount);
+  state.lines.push(occlusionLine);
+  state.tokens += estimateTokens(occlusionLine);
+  emitVisualAppendix(state);
 
   return {
     text: state.lines.join("\n"),
@@ -1227,6 +1274,7 @@ export function renderVom(scene: VomScene, options: VomOptions = {}): VomResult
     scene.activeScopeBlocks,
     scene.visualSurfaces,
   );
+  emitVisualAppendix(state);
 
   return {
     text: state.lines.join("\n"),