feat(vom): vom method bug fix

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

@@ -848,11 +848,7 @@ describe("buildVomScene", () => {
     );
   });
 
-  it("prefers an empty field's placeholder over a label-polluted AX name", () => {
-    // Mirrors xiaohongshu: the <input> is wrapped in a <label> that also holds
-    // a "+86" prefix, so the AX accessible name becomes "+86" and the real
-    // placeholder ("输入手机号") is lost. VOM models perceived state — the empty
-    // field shows its placeholder — so the placeholder wins.
+  it("keeps placeholder separate from the accessible name", () => {
     const axNodes: CdpAxNode[] = [
       {
         nodeId: "1",
@@ -881,7 +877,12 @@ describe("buildVomScene", () => {
     };
 
     expect(buildVomScene(axNodes, captured).nodes[0]).toEqual(
-      expect.objectContaining({ id: 10, role: "textbox", name: "输入手机号" }),
+      expect.objectContaining({
+        id: 10,
+        role: "textbox",
+        name: "+86",
+        placeholder: "输入手机号",
+      }),
     );
   });
 
@@ -979,6 +980,89 @@ describe("buildVomScene", () => {
     );
   });
 
+  it("uses preceding AX static text as a form control label", () => {
+    const axNodes: CdpAxNode[] = [
+      {
+        nodeId: "1",
+        role: { type: "role", value: "RootWebArea" },
+        backendDOMNodeId: 1,
+        childIds: ["2", "3"],
+      },
+      {
+        nodeId: "2",
+        parentId: "1",
+        role: { type: "role", value: "StaticText" },
+        name: { type: "computedString", value: "验证码:" },
+      },
+      {
+        nodeId: "3",
+        parentId: "1",
+        role: { type: "role", value: "textbox" },
+        backendDOMNodeId: 20,
+      },
+    ];
+    const captured: CapturedViewModel = {
+      viewport: { width: 1000, height: 800 },
+      iframeNodes: new Map(),
+      excludedBackendNodeIds: new Set(),
+      nodes: [
+        {
+          backendNodeId: 20,
+          parentBackendNodeId: null,
+          tag: "input",
+          attrs: { type: "text" },
+          rect: { x: 90, y: 0, w: 120, h: 30 },
+          paintOrder: 2,
+          position: "static",
+          pointerEvents: "auto",
+          cursor: "text",
+        },
+      ],
+    };
+
+    expect(buildVomScene(axNodes, captured).nodes.find((node) => node.id === 20)).toEqual(
+      expect.objectContaining({ role: "textbox", name: "验证码", inputState: "empty" }),
+    );
+  });
+
+  it("marks runtime default input values without treating them as ordinary filled input", () => {
+    const scene = buildVomScene(
+      [
+        {
+          nodeId: "1",
+          role: { type: "role", value: "textbox" },
+          backendDOMNodeId: 10,
+        },
+      ],
+      {
+        viewport: { width: 1000, height: 800 },
+        iframeNodes: new Map(),
+        excludedBackendNodeIds: new Set(),
+        nodes: [
+          {
+            backendNodeId: 10,
+            parentBackendNodeId: null,
+            tag: "input",
+            attrs: { type: "text" },
+            formValue: "没有手机号的用编码代替",
+            formDefaultValue: "没有手机号的用编码代替",
+            rect: { x: 0, y: 0, w: 240, h: 48 },
+            paintOrder: 1,
+            position: "static",
+            pointerEvents: "auto",
+          },
+        ],
+      },
+    );
+
+    expect(scene.nodes[0]).toEqual(
+      expect.objectContaining({
+        inputState: "default",
+        value: "没有手机号的用编码代替",
+      }),
+    );
+  });
+
   it("promotes a cursor:pointer icon control to a button named from its <use> sprite", () => {
     // A close button built as <div class=close-button><svg><use href="#close"/></svg></div>
     // — the AX tree exposes it as `generic` with no name, so it would be dropped.

apps/extension/src/tools/observation.ts

@@ -329,6 +329,27 @@ function axPropertyString(axNode: CdpAxNode, name: string): string | undefined {
   return axString(prop?.value);
 }
 
+function axSiblingLabel(axNode: CdpAxNode, axById: Map<string, CdpAxNode>): string | undefined {
+  const parent = axNode.parentId ? axById.get(axNode.parentId) : undefined;
+  const siblings = parent?.childIds ?? [];
+  const index = siblings.indexOf(axNode.nodeId);
+  if (index <= 0) return undefined;
+
+  for (let i = index - 1; i >= Math.max(0, index - 4); i -= 1) {
+    const sibling = axById.get(siblings[i]);
+    if (!sibling) continue;
+    const role = axString(sibling.role)?.toLowerCase() ?? "";
+    if (AX_TEXT_STOP_ROLES.has(role)) break;
+    if (!["statictext", "labeltext", "text", "generic"].includes(role)) continue;
+    const label = cleanAttr(axString(sibling.name) ?? axString(sibling.value))?.replace(
+      /[：:]\s*$/,
+      "",
+    );
+    if (label && label.length <= 40) return label;
+  }
+  return undefined;
+}
+
 function buildAxSignals(axNodes: CdpAxNode[]): Map<string, AxNodeSignals> {
   const axByNodeId = new Map(axNodes.map((node) => [node.nodeId, node]));
   const virtualText = new Map<string, string>();
@@ -619,6 +640,7 @@ function applyCapturedSignals(
   const attrs = capturedNode.attrs;
   const text = cleanAttr(capturedNode.textContent);
   const nearbyText = nearbyTextFor(capturedNode, signals.childrenByParentId);
+  const placeholder = cleanAttr(capturedNode.formPlaceholder) ?? cleanAttr(attrs.placeholder);
   return {
     ...node,
     domParentId: capturedNode.parentBackendNodeId,
@@ -627,6 +649,7 @@ function applyCapturedSignals(
     attrs,
     ...(text ? { text } : {}),
     ...(nearbyText ? { nearbyText } : {}),
+    ...(placeholder ? { placeholder } : {}),
     disabled:
       Object.prototype.hasOwnProperty.call(attrs, "disabled") ||
       (attrs["aria-disabled"] ?? "").toLowerCase() === "true",
@@ -636,6 +659,20 @@ function applyCapturedSignals(
   };
 }
 
+function inputStateFor(
+  capturedNode: CapturedNode | undefined,
+  value: string | undefined,
+): VomNode["inputState"] {
+  if (!capturedNode || !FORM_CONTROL_TAGS.has(normalizeTag(capturedNode.tag))) return undefined;
+  const formValue = capturedNode.formValue;
+  if (formValue !== undefined) {
+    if (formValue === "") return "empty";
+    if (formValue === (capturedNode.formDefaultValue ?? "")) return "default";
+    return "filled";
+  }
+  return value === undefined || value === "" ? "empty" : "filled";
+}
+
 /**
  * Name for a native form control. VOM models the *perceived* viewport
  * (spec §1): an empty field displays its placeholder, so when the field has
@@ -647,19 +684,17 @@ function applyCapturedSignals(
 function formControlName(
   captured: CapturedNode | undefined,
   axName: string | undefined,
-  axValue: string | undefined,
+  axSiblingName: string | undefined,
   signals: VomNodeDomSignals,
 ): string | undefined {
-  const placeholder = cleanAttr(captured?.attrs.placeholder);
   const ariaLabel = cleanAttr(captured?.attrs["aria-label"]);
   const title = cleanAttr(captured?.attrs.title);
+  const placeholder =
+    cleanAttr(captured?.formPlaceholder) ?? cleanAttr(captured?.attrs.placeholder);
   const nearbyLabel = captured
     ? previousSiblingTextFor(captured, signals.childrenByParentId)
     : undefined;
-  const hasValue = axValue !== undefined && axValue !== "";
-  if (nearbyLabel) return nearbyLabel;
-  if (!hasValue && placeholder) return placeholder;
-  return axName ?? ariaLabel ?? placeholder ?? title ?? nearbyLabel;
+  return ariaLabel ?? title ?? axName ?? axSiblingName ?? nearbyLabel ?? placeholder;
 }
 
 function vomNodeFromCaptured(
@@ -668,7 +703,8 @@ function vomNodeFromCaptured(
   signals: VomNodeDomSignals,
 ): VomNode {
   const sensitive = isSensitive(capturedNode);
-  const value = sensitive ? (capturedNode.attrs.value ?? "") : undefined;
+  const value =
+    capturedNode.formValue ?? (sensitive ? (capturedNode.attrs.value ?? "") : undefined);
   const tag = normalizeTag(capturedNode.tag);
   const node = applyCapturedSignals(
     {
@@ -681,6 +717,7 @@ function vomNodeFromCaptured(
       pointerEvents: capturedNode.pointerEvents || "auto",
       modal: isModalSignal(undefined, capturedNode),
       sensitive,
+      inputState: inputStateFor(capturedNode, value),
       ...(value !== undefined ? { value } : {}),
     },
     capturedNode,
@@ -702,10 +739,11 @@ function axVomNode(
   axSignals: Map<string, AxNodeSignals>,
 ): VomNode {
   const role = axString(axNode.role);
-  const value = axValue(axNode.value);
+  const capturedValue = capturedNode?.formValue;
+  const value = capturedValue ?? axValue(axNode.value);
   const signalsForNode = axSignals.get(axNode.nodeId);
   let name = FORM_CONTROL_TAGS.has(normalizeTag(capturedNode?.tag))
-    ? formControlName(capturedNode, axString(axNode.name), value, signals)
+    ? formControlName(capturedNode, axString(axNode.name), axSiblingLabel(axNode, axById), signals)
     : (axString(axNode.name) ?? signalsForNode?.aggregatedText);
   if (name && signalsForNode?.hasPopup) {
     name = signalsForNode.expanded ? `${name} [expanded]` : `${name} [has-submenu]`;
@@ -720,6 +758,7 @@ function axVomNode(
     pointerEvents: capturedNode?.pointerEvents || "auto",
     modal: isModalSignal(axNode, capturedNode),
     sensitive: isSensitive(capturedNode) || signalsForNode?.sensitive === true,
+    inputState: inputStateFor(capturedNode, value),
   };
   if (role) node.role = role;
   if (name) node.name = name;

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

@@ -31,6 +31,9 @@ export interface CapturedNode {
    */
   cursor?: string;
   textContent?: string;
+  formValue?: string;
+  formDefaultValue?: string;
+  formPlaceholder?: string;
 }
 
 export type CapturedIframeNodes = Map<number, CapturedNode[]>;
@@ -95,6 +98,52 @@ interface LayoutMetricsReply {
   layoutViewport?: { clientWidth?: number; clientHeight?: number; pageX?: number; pageY?: number };
 }
 
+function isFormControlTag(tag: string): boolean {
+  return tag === "input" || tag === "textarea" || tag === "select";
+}
+
+async function enrichFormControlState(cdp: CdpRunner, tabId: number, nodes: CapturedNode[]) {
+  for (const node of nodes) {
+    if (!isFormControlTag(node.tag)) continue;
+    let objectId: string | undefined;
+    try {
+      const resolved = await cdp.send<{ object?: { objectId?: string } }>(
+        tabId,
+        "DOM.resolveNode",
+        {
+          backendNodeId: node.backendNodeId,
+        },
+      );
+      objectId = resolved.object?.objectId;
+      if (!objectId) continue;
+      const result = await cdp.send<{
+        result?: { value?: { value?: string; defaultValue?: string; placeholder?: string } };
+      }>(tabId, "Runtime.callFunctionOn", {
+        objectId,
+        returnByValue: true,
+        functionDeclaration: `function(){
+          return {
+            value: typeof this.value === "string" ? this.value : "",
+            defaultValue: typeof this.defaultValue === "string" ? this.defaultValue : "",
+            placeholder: typeof this.placeholder === "string" ? this.placeholder : ""
+          };
+        }`,
+      });
+      const value = result.result?.value;
+      if (!value) continue;
+      node.formValue = value.value ?? "";
+      node.formDefaultValue = value.defaultValue ?? "";
+      node.formPlaceholder = value.placeholder ?? "";
+    } catch {
+      // Best-effort enrichment. DOMSnapshot/AX data still carries the node.
+    } finally {
+      if (objectId) {
+        await cdp.send(tabId, "Runtime.releaseObject", { objectId }).catch(() => {});
+      }
+    }
+  }
+}
+
 interface RuntimeEvaluateReply {
   result?: {
     value?: unknown;
@@ -533,6 +582,11 @@ export async function captureViewModel(cdp: CdpRunner, tabId: number): Promise<C
     }
   }
 
+  await enrichFormControlState(cdp, tabId, nodes);
+  for (const subNodes of iframeNodes.values()) {
+    await enrichFormControlState(cdp, tabId, subNodes);
+  }
+
   const surfaceProbes = await probeHoverSurfaces(cdp, tabId);
 
   return { nodes, viewport, iframeNodes, surfaceProbes, excludedBackendNodeIds };

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

@@ -450,65 +450,90 @@ describe("renderVom single-layer page", () => {
     expect(out.text).not.toContain('StaticText "13311030827"');
   });
 
-  it("adds semantic collection summaries for repeated item containers", () => {
+  it("renders placeholder separately from input value and state", () => {
     const out = renderVom(
       scene([
-        node({ id: 1, role: "RootWebArea", name: "Forum" }),
-        node({ id: 2, parentId: 1, role: "main", name: "Posts" }),
-        node({ id: 3, parentId: 2, role: "searchbox", name: "Search posts", tag: "input" }),
-        node({ id: 10, parentId: 2, role: "article" }),
-        node({ id: 11, parentId: 10, role: "heading", name: "First post" }),
-        node({ id: 12, parentId: 10, role: "link", name: "First post", tag: "a" }),
-        node({ id: 13, parentId: 10, role: "button", name: "Upvote", tag: "button" }),
-        node({ id: 20, parentId: 2, role: "article" }),
-        node({ id: 21, parentId: 20, role: "heading", name: "Second post" }),
-        node({ id: 22, parentId: 20, role: "link", name: "Second post", tag: "a" }),
-        node({ id: 23, parentId: 20, role: "button", name: "Upvote", tag: "button" }),
+        node({ id: 1, role: "RootWebArea", name: "Doc" }),
+        node({
+          id: 2,
+          parentId: 1,
+          role: "textbox",
+          name: "手机号",
+          value: "没有手机号的用编码代替",
+          placeholder: "手机号",
+          inputState: "default",
+          tag: "input",
+        }),
       ]),
-      { semanticCollections: true },
     );
 
-    expect(out.text).toContain("@collections");
     expect(out.text).toContain(
-      'collection c1 role=main item_role=article label="First post" items=2',
+      '@e1 textbox "手机号" [default] placeholder="手机号" ="没有手机号的用编码代替"',
     );
-    expect(out.text).toContain('controls: search=@e1 "Search posts"');
-    expect(out.text).toContain('title="First post" title_handle=@e2');
-    expect(out.text).toContain('actions=[@e3 "Upvote"]');
   });
 
-  it("does not summarize login forms as semantic collections", () => {
+  it("keeps only local context for duplicate labels", () => {
     const out = renderVom(
       scene([
         node({ id: 1, role: "RootWebArea", name: "北京市小客车指标调控管理信息系统" }),
-        node({ id: 2, parentId: 1, role: "list" }),
-        node({ id: 3, parentId: 2, role: "listitem", name: "用户登录" }),
-        node({ id: 4, parentId: 2, role: "listitem", name: "手机号：" }),
-        node({
-          id: 5,
-          parentId: 4,
-          role: "textbox",
-          value: "13311030827",
-          tag: "input",
-        }),
-        node({ id: 6, parentId: 2, role: "listitem", name: "密 码：" }),
-        node({
-          id: 7,
-          parentId: 6,
-          role: "textbox",
-          value: "secret",
-          tag: "input",
-          sensitive: true,
-        }),
-        node({ id: 8, parentId: 2, role: "listitem", name: "验证码：" }),
-        node({ id: 9, parentId: 8, role: "textbox", value: "h8Mh", tag: "input" }),
-        node({ id: 10, parentId: 2, role: "listitem" }),
-        node({ id: 11, parentId: 10, role: "button", name: "登录", tag: "button" }),
+        node({ id: 2, parentId: 1, role: "section" }),
+        node({ id: 3, parentId: 2, role: "StaticText", name: "账号" }),
+        node({ id: 4, parentId: 2, role: "link", name: "操作说明", tag: "a" }),
+        node({ id: 5, parentId: 1, role: "section" }),
+        node({ id: 6, parentId: 5, role: "StaticText", name: "配置指标" }),
+        node({ id: 7, parentId: 5, role: "link", name: "操作说明", tag: "a" }),
       ]),
     );
 
-    expect(out.text).not.toContain("@collections");
-    expect(out.text).toContain('@e2 textbox [filled] ="•••"');
+    expect(out.text).toContain('@e1 link "操作说明" [ctx: 账号]');
+    expect(out.text).toContain('@e2 link "操作说明" [ctx: 配置指标]');
+    expect(out.text).not.toContain("北京市小客车指标调控管理信息系统]");
+  });
+
+  it("does not add low-value root context to duplicated brand links", () => {
+    const out = renderVom(
+      scene([
+        node({ id: 1, role: "RootWebArea", name: "北京市小客车指标调控管理信息系统" }),
+        node({ id: 2, parentId: 1, role: "link", name: "北京市交通委员会", tag: "a" }),
+        node({ id: 3, parentId: 1, role: "link", name: "北京市交通委员会", tag: "a" }),
+      ]),
+    );
+
+    expect(out.text).toContain('@e1 link "北京市交通委员会"');
+    expect(out.text).toContain('@e2 link "北京市交通委员会"');
+    expect(out.text).not.toContain("[ctx:");
+  });
+
+  it("does not render redundant table cell descendants when the cell name covers them", () => {
+    const out = renderVom(
+      scene([
+        node({ id: 1, role: "RootWebArea", name: "Doc" }),
+        node({ id: 2, parentId: 1, role: "table" }),
+        node({ id: 3, parentId: 2, role: "row" }),
+        node({ id: 4, parentId: 3, role: "cell", name: "申请人姓名：刘珺瑶" }),
+        node({ id: 5, parentId: 4, role: "StaticText", name: "申请人姓名：" }),
+        node({ id: 6, parentId: 4, role: "StaticText", name: "刘珺瑶" }),
+      ]),
+    );
+
+    expect(out.text).toContain('cell "申请人姓名：刘珺瑶"');
+    expect(out.text).not.toContain('StaticText "申请人姓名："');
+    expect(out.text).not.toContain('StaticText "刘珺瑶"');
+  });
+
+  it("keeps interactive descendants inside table cells", () => {
+    const out = renderVom(
+      scene([
+        node({ id: 1, role: "RootWebArea", name: "Doc" }),
+        node({ id: 2, parentId: 1, role: "table" }),
+        node({ id: 3, parentId: 2, role: "row" }),
+        node({ id: 4, parentId: 3, role: "cell", name: "操作：下载" }),
+        node({ id: 5, parentId: 4, role: "link", name: "下载", tag: "a" }),
+      ]),
+    );
+
+    expect(out.text).toContain('cell "操作：下载"');
+    expect(out.text).toContain('@e1 link "下载"');
   });
 });
 

packages/vom/src/render.ts

@@ -83,12 +83,6 @@ const MAX_RECOVERABLE_SINGLE_INTENT_AREA = 360_000;
 const MAX_HANDLE_CONTEXT_ITEMS = 3;
 const MAX_SURFACE_ITEMS = 12;
 const MAX_SCOPE_LINES = 40;
-const MAX_SEMANTIC_COLLECTIONS = 3;
-const MAX_SEMANTIC_ITEMS = 20;
-const MAX_SEMANTIC_CONTROLS = 8;
-const MAX_SEMANTIC_ACTIONS = 6;
-const MAX_SEMANTIC_FIELD_CHARS = 120;
-
 const RECOVERY_HANDLER_ATTRS = ["onclick", "onmousedown", "onkeydown", "onkeyup", "onkeypress"];
 const NATIVE_TAGS = new Set(["button", "input", "select", "textarea"]);
 const GRAPHIC_ONLY_TAGS = new Set(["svg", "use", "path", "g", "symbol"]);
@@ -157,6 +151,17 @@ function cleanSemanticText(value: string | undefined): string | undefined {
   return clean;
 }
 
+function isLowValueContext(value: string): boolean {
+  const clean = value.trim();
+  const key = clean.toLowerCase();
+  if (clean === "欢迎") return true;
+  if (key.includes("icp") || key.includes("备案")) return true;
+  if (clean.includes("联系方式") || clean.includes("政府网站标识")) return true;
+  if (/^\d{5,}$/.test(clean)) return true;
+  if (/北京市小客车指标调控管理信息系统|beijing municipal commission/i.test(clean)) return true;
+  return false;
+}
+
 function normalizedRole(node: VomNode): string {
   return node.role?.toLowerCase() ?? "";
 }
@@ -431,6 +436,7 @@ function weakContextText(label: string | undefined, targetName: string): string
   const key = normalizeContextKey(clean);
   if (
     !key ||
+    isLowValueContext(clean) ||
     key === normalizeContextKey(targetName) ||
     key.startsWith("ctx_") ||
     key === "section" ||
@@ -450,7 +456,7 @@ interface ContextCandidate {
 }
 
 function contextSourceRank(source: ContextSource): number {
-  return source === "owned" ? 0 : source === "same" ? 1 : 2;
+  return source === "same" ? 0 : source === "owned" ? 1 : 2;
 }
 
 function contextCategory(key: string): string {
@@ -482,7 +488,7 @@ function dedupeContexts(contexts: ContextCandidate[]): string[] {
     seen.add(key);
     seenCategories.add(category);
     unique.push(clean);
-    if (unique.length >= MAX_HANDLE_CONTEXT_ITEMS) break;
+    if (unique.length >= 1) break;
   }
   return unique;
 }
@@ -611,9 +617,12 @@ function renderNodeLine(
 
   const rawValue = cleaned(node.value);
   const role = normalizedRole(node);
-  if (["textbox", "searchbox"].includes(role)) {
-    line += rawValue === undefined ? " [empty]" : " [filled]";
+  const fillable = ["textbox", "searchbox"].includes(role);
+  if (fillable) {
+    line += ` [${node.inputState ?? (rawValue === undefined ? "empty" : "filled")}]`;
   }
+  const placeholder = cleaned(node.placeholder);
+  if (placeholder) line += ` placeholder=${JSON.stringify(placeholder)}`;
   const value = node.sensitive
     ? rawValue !== undefined
       ? SENSITIVE_MASK
@@ -644,6 +653,29 @@ function shouldSkipRedundantRefChildren(node: VomNode): boolean {
   );
 }
 
+function descendantTextCoveredByName(node: VomNode, state: RenderState): boolean {
+  const name = cleaned(node.name);
+  if (!name) return false;
+  const stack = [...(state.children.get(node.id) ?? [])];
+  const texts: string[] = [];
+  while (stack.length > 0) {
+    const child = stack.pop() as VomNode;
+    if (shouldReference(child)) return false;
+    const text = cleaned(child.name) ?? cleaned(child.text) ?? cleaned(child.value);
+    if (text) texts.push(text);
+    stack.push(...(state.children.get(child.id) ?? []));
+  }
+  return texts.length > 0 && texts.every((text) => name.includes(text));
+}
+
+function shouldSkipRedundantChildren(node: VomNode, state: RenderState): boolean {
+  const role = normalizedRole(node);
+  if (["cell", "gridcell", "columnheader", "rowheader"].includes(role)) {
+    return descendantTextCoveredByName(node, state);
+  }
+  return false;
+}
+
 interface RenderState {
   lines: string[];
   refs: Array<{ ref: string; backendNodeId: number }>;
@@ -733,7 +765,9 @@ function renderTree(
     const scope = state.scopeMap.get(node.id);
     if (scope) emitActiveScopeBlock(scope, depth + 1, state);
 
-    if (ref && shouldSkipRedundantRefChildren(node)) continue;
+    if ((ref && shouldSkipRedundantRefChildren(node)) || shouldSkipRedundantChildren(node, state)) {
+      continue;
+    }
     renderTree(children, node.id, depth + 1, state);
   }
 }
@@ -910,386 +944,6 @@ function countRenderable(nodes: VomNode[]): number {
   return nodes.filter(shouldRender).length;
 }
 
-interface SemanticControl {
-  kind: string;
-  handle?: string;
-  label: string;
-}
-
-interface SemanticAction {
-  handle: string;
-  label: string;
-}
-
-interface SemanticItem {
-  title?: string;
-  titleHandle?: string;
-  author?: string;
-  time?: string;
-  score?: string;
-  comments?: string;
-  commentsHandle?: string;
-  actions: SemanticAction[];
-}
-
-interface SemanticCollection {
-  role: string;
-  itemRole: string;
-  label?: string;
-  controls: SemanticControl[];
-  items: SemanticItem[];
-}
-
-function truncateField(value: string): string {
-  if ([...value].length <= MAX_SEMANTIC_FIELD_CHARS) return value;
-  return `${[...value].slice(0, MAX_SEMANTIC_FIELD_CHARS - 1).join("")}…`;
-}
-
-function quoteField(value: string): string {
-  return JSON.stringify(truncateField(value));
-}
-
-function roleIsCollectionItem(role: string): boolean {
-  return role === "article" || role === "row" || role === "listitem";
-}
-
-function roleIsCollectionContainer(role: string): boolean {
-  return ["main", "feed", "list", "table", "grid", "rowgroup", "region", "section"].includes(role);
-}
-
-function textForSemantics(node: VomNode): string | undefined {
-  return (
-    cleanSemanticText(node.name) ??
-    cleanSemanticText(node.value) ??
-    cleanSemanticText(node.text) ??
-    cleanSemanticText(node.nearbyText)
-  );
-}
-
-function buildRefLookup(refs: Array<{ ref: string; backendNodeId: number }>): Map<number, string> {
-  return new Map(
-    refs.map((entry) => [
-      entry.backendNodeId,
-      entry.ref.startsWith("@") ? entry.ref : `@${entry.ref}`,
-    ]),
-  );
-}
-
-function collectDescendantNodes(
-  children: Map<number | null, VomNode[]>,
-  rootId: number,
-  nodesById: Map<number, VomNode>,
-): VomNode[] {
-  const out: VomNode[] = [];
-  const stack = [rootId];
-  const seen = new Set<number>();
-  while (stack.length > 0) {
-    const id = stack.pop() as number;
-    if (!seen.add(id)) continue;
-    const node = nodesById.get(id);
-    if (node) out.push(node);
-    for (const child of [...(children.get(id) ?? [])].reverse()) {
-      stack.push(child.id);
-    }
-  }
-  return out;
-}
-
-function collectDescendantIdSet(
-  children: Map<number | null, VomNode[]>,
-  rootId: number,
-): Set<number> {
-  const out = new Set<number>();
-  const stack = [rootId];
-  while (stack.length > 0) {
-    const id = stack.pop() as number;
-    if (!out.add(id)) continue;
-    for (const child of [...(children.get(id) ?? [])].reverse()) stack.push(child.id);
-  }
-  return out;
-}
-
-function collectionLabel(
-  node: VomNode,
-  children: Map<number | null, VomNode[]>,
-  nodesById: Map<number, VomNode>,
-): string | undefined {
-  return (
-    contextLabel(node, "") ??
-    collectDescendantNodes(children, node.id, nodesById).find(
-      (candidate) => normalizedRole(candidate) === "heading" && textForSemantics(candidate),
-    )?.name
-  );
-}
-
-function classifyControl(label: string, role: string): string | undefined {
-  const key = label.toLowerCase();
-  if (role === "searchbox" || key.includes("search")) return "search";
-  if (key.includes("sort") || key.includes("order")) return "sort";
-  if (key.includes("filter")) return "filter";
-  if (role === "tab") return "tab";
-  if (key === "next" || key.includes("next page")) return "pagination";
-  if (key === "previous" || key.includes("previous page")) return "pagination";
-  return undefined;
-}
-
-function collectCollectionControls(
-  container: VomNode,
-  items: VomNode[],
-  children: Map<number | null, VomNode[]>,
-  nodesById: Map<number, VomNode>,
-  refLookup: Map<number, string>,
-): SemanticControl[] {
-  const itemIds = new Set(items.flatMap((item) => [...collectDescendantIdSet(children, item.id)]));
-  const controls: SemanticControl[] = [];
-  for (const node of collectDescendantNodes(children, container.id, nodesById)) {
-    if (itemIds.has(node.id)) continue;
-    const role = normalizedRole(node);
-    if (!["button", "combobox", "searchbox", "tab", "link"].includes(role)) continue;
-    const label = textForSemantics(node);
-    if (!label) continue;
-    const kind = classifyControl(label, role);
-    if (!kind) continue;
-    controls.push({ kind, handle: refLookup.get(node.id), label });
-    if (controls.length >= MAX_SEMANTIC_CONTROLS) break;
-  }
-  return controls;
-}
-
-function isFormLikeCollection(
-  container: VomNode,
-  items: VomNode[],
-  children: Map<number | null, VomNode[]>,
-  nodesById: Map<number, VomNode>,
-): boolean {
-  const descendants = collectDescendantNodes(children, container.id, nodesById);
-  const interactive = descendants.filter((node) => shouldReference(node));
-  const textboxCount = interactive.filter((node) =>
-    ["textbox", "searchbox"].includes(normalizedRole(node)),
-  ).length;
-  const sensitiveCount = descendants.filter((node) => node.sensitive).length;
-  const labels = descendants
-    .map((node) => textForSemantics(node))
-    .filter((label): label is string => label !== undefined)
-    .join(" ")
-    .toLowerCase();
-  const hasLoginSignals =
-    /(用户登录|登录|验证码|密码|忘记密码|手机号|证书口令|captcha|password|sign in|log in)/i.test(
-      labels,
-    );
-
-  return (
-    (textboxCount >= 2 && hasLoginSignals) ||
-    (sensitiveCount > 0 && hasLoginSignals) ||
-    (items.length <= 8 && textboxCount > 0 && interactive.length >= 3 && hasLoginSignals)
-  );
-}
-
-function isCommentLabel(label: string): boolean {
-  const key = label.toLowerCase();
-  return key.includes("comment") || key === "no comments";
-}
-
-function parseScoreBetweenVoteButtons(
-  item: VomNode,
-  children: Map<number | null, VomNode[]>,
-): string | undefined {
-  for (const descendantId of collectDescendantIdSet(children, item.id)) {
-    const siblings = children.get(descendantId) ?? [];
-    for (let index = 0; index + 2 < siblings.length; index += 1) {
-      const prev = textForSemantics(siblings[index])?.toLowerCase() ?? "";
-      const score = textForSemantics(siblings[index + 1]);
-      const next = textForSemantics(siblings[index + 2])?.toLowerCase() ?? "";
-      if (
-        prev.includes("upvote") &&
-        next.includes("downvote") &&
-        score !== undefined &&
-        /^-?\d+$/.test(score.replaceAll(",", ""))
-      ) {
-        return score;
-      }
-    }
-  }
-  return undefined;
-}
-
-function extractAuthor(descendants: VomNode[]): string | undefined {
-  for (let index = 0; index < descendants.length; index += 1) {
-    const label = textForSemantics(descendants[index]);
-    if (!label) continue;
-    const key = label.toLowerCase();
-    if (key === "submitted by" || key === "by" || key.endsWith(" by")) {
-      for (const candidate of descendants.slice(index + 1, index + 9)) {
-        if (normalizedRole(candidate) === "link") return textForSemantics(candidate);
-      }
-    }
-  }
-  return undefined;
-}
-
-function extractSemanticItem(
-  item: VomNode,
-  children: Map<number | null, VomNode[]>,
-  nodesById: Map<number, VomNode>,
-  refLookup: Map<number, string>,
-): SemanticItem {
-  const descendants = collectDescendantNodes(children, item.id, nodesById);
-  let title: string | undefined;
-  let titleHandle: string | undefined;
-  for (const role of ["heading", "link"]) {
-    const node = descendants.find(
-      (candidate) => normalizedRole(candidate) === role && textForSemantics(candidate),
-    );
-    if (!node) continue;
-    title = textForSemantics(node);
-    titleHandle = refLookup.get(node.id);
-    if (!titleHandle && title) {
-      const matchingLink = descendants.find(
-        (candidate) =>
-          normalizedRole(candidate) === "link" && textForSemantics(candidate) === title,
-      );
-      if (matchingLink) titleHandle = refLookup.get(matchingLink.id);
-    }
-    break;
-  }
-  if (!title) {
-    title = textForSemantics(item);
-    titleHandle = refLookup.get(item.id);
-  }
-
-  let time: string | undefined;
-  let comments: string | undefined;
-  let commentsHandle: string | undefined;
-  const actions: SemanticAction[] = [];
-  for (const node of descendants) {
-    const role = normalizedRole(node);
-    const label = textForSemantics(node);
-    if (!time && role === "time") time = label;
-    if (!comments && label && isCommentLabel(label)) {
-      comments = label;
-      commentsHandle = refLookup.get(node.id);
-    }
-    if (
-      actions.length < MAX_SEMANTIC_ACTIONS &&
-      shouldReference(node) &&
-      !["link", "textbox", "searchbox"].includes(role)
-    ) {
-      const handle = refLookup.get(node.id);
-      if (handle && label) actions.push({ handle, label });
-    }
-  }
-
-  return {
-    title,
-    titleHandle,
-    author: extractAuthor(descendants),
-    time,
-    score: parseScoreBetweenVoteButtons(item, children),
-    comments,
-    commentsHandle,
-    actions,
-  };
-}
-
-function detectSemanticCollections(
-  nodes: VomNode[],
-  refs: Array<{ ref: string; backendNodeId: number }>,
-): SemanticCollection[] {
-  const children = buildChildren(nodes);
-  const nodesById = new Map(nodes.map((node) => [node.id, node]));
-  const refLookup = buildRefLookup(refs);
-  const collections: SemanticCollection[] = [];
-  const coveredItems = new Set<number>();
-
-  for (const container of nodes) {
-    if (collections.length >= MAX_SEMANTIC_COLLECTIONS) break;
-    const role = normalizedRole(container);
-    if (!roleIsCollectionContainer(role)) continue;
-    const childList = children.get(container.id) ?? [];
-    const counts = new Map<string, number>();
-    for (const child of childList) {
-      const childRole = normalizedRole(child);
-      if (roleIsCollectionItem(childRole)) counts.set(childRole, (counts.get(childRole) ?? 0) + 1);
-    }
-    const best = [...counts].filter(([, count]) => count >= 2).sort((a, b) => b[1] - a[1])[0];
-    if (!best) continue;
-    const [itemRole] = best;
-    const items = childList.filter(
-      (child) => normalizedRole(child) === itemRole && !coveredItems.has(child.id),
-    );
-    if (items.length < 2) continue;
-    if (isFormLikeCollection(container, items, children, nodesById)) continue;
-    for (const item of items) coveredItems.add(item.id);
-    collections.push({
-      role,
-      itemRole,
-      label: collectionLabel(container, children, nodesById),
-      controls: collectCollectionControls(container, items, children, nodesById, refLookup),
-      items: items
-        .slice(0, MAX_SEMANTIC_ITEMS)
-        .map((item) => extractSemanticItem(item, children, nodesById, refLookup)),
-    });
-  }
-  return collections;
-}
-
-function renderSemanticCollections(collections: SemanticCollection[]): string[] {
-  if (collections.length === 0) return [];
-  const lines = ["@collections"];
-  for (const [index, collection] of collections.entries()) {
-    const label = collection.label ? ` label=${quoteField(collection.label)}` : "";
-    lines.push(
-      `collection c${index + 1} role=${collection.role} item_role=${collection.itemRole}${label} items=${collection.items.length}`,
-    );
-    if (collection.controls.length > 0) {
-      const rendered = collection.controls
-        .map(
-          (control) =>
-            `${control.kind}=${control.handle ? `${control.handle} ` : ""}${quoteField(control.label)}`,
-        )
-        .join("; ");
-      lines.push(`  controls: ${rendered}`);
-    }
-    lines.push(
-      "  columns: index title title_handle author time score comments comments_handle actions",
-    );
-    collection.items.forEach((item, itemIndex) => {
-      const parts = [`${itemIndex + 1}. `];
-      if (item.title) parts.push(`title=${quoteField(item.title)}`);
-      if (item.titleHandle) parts.push(`title_handle=${item.titleHandle}`);
-      if (item.author) parts.push(`author=${quoteField(item.author)}`);
-      if (item.time) parts.push(`time=${quoteField(item.time)}`);
-      if (item.score) parts.push(`score=${quoteField(item.score)}`);
-      if (item.comments) parts.push(`comments=${quoteField(item.comments)}`);
-      if (item.commentsHandle) parts.push(`comments_handle=${item.commentsHandle}`);
-      if (item.actions.length > 0) {
-        parts.push(
-          `actions=[${item.actions.map((action) => `${action.handle} ${quoteField(action.label)}`).join(", ")}]`,
-        );
-      }
-      lines.push(`  ${parts.join(" ")}`);
-    });
-  }
-  return lines;
-}
-
-function insertAfterHeader(text: string, insertLines: string[]): string {
-  if (insertLines.length === 0) return text;
-  const lines = text.split("\n");
-  const l1Index = lines.findIndex((line) => line.startsWith("L1 "));
-  const insertAt = l1Index >= 0 ? l1Index + 1 : Math.min(lines.length, 3);
-  lines.splice(insertAt, 0, ...insertLines);
-  return lines.join("\n");
-}
-
-function augmentVomResult(result: VomResult, nodes: VomNode[], options: VomOptions): VomResult {
-  if (!options.semanticCollections) return result;
-  const semanticLines = renderSemanticCollections(detectSemanticCollections(nodes, result.refs));
-  return semanticLines.length === 0
-    ? result
-    : { ...result, text: insertAfterHeader(result.text, semanticLines) };
-}
-
 function renderDoubleLayer(scene: VomScene, layer: BlockingLayer, options: VomOptions): VomResult {
   const included = collectDescendantsOfMembers(scene.nodes, layer.members);
   const visibleNodes = scene.nodes.filter((node) => included.has(node.id));
@@ -1303,15 +957,11 @@ function renderDoubleLayer(scene: VomScene, layer: BlockingLayer, options: VomOp
   const state = renderNodes(visibleNodes, options, header, scene.surfaces, scene.activeScopeBlocks);
   state.lines.push(renderPageOcclusionLine(hiddenCount));
 
-  return augmentVomResult(
-    {
-      text: state.lines.join("\n"),
-      refs: state.refs,
-      truncated: state.truncated,
-    },
-    visibleNodes,
-    options,
-  );
+  return {
+    text: state.lines.join("\n"),
+    refs: state.refs,
+    truncated: state.truncated,
+  };
 }
 
 export function renderVom(scene: VomScene, options: VomOptions = {}): VomResult {
@@ -1334,13 +984,9 @@ export function renderVom(scene: VomScene, options: VomOptions = {}): VomResult
     scene.activeScopeBlocks,
   );
 
-  return augmentVomResult(
-    {
-      text: state.lines.join("\n"),
-      refs: state.refs,
-      truncated: state.truncated,
-    },
-    visibleNodes,
-    options,
-  );
+  return {
+    text: state.lines.join("\n"),
+    refs: state.refs,
+    truncated: state.truncated,
+  };
 }

packages/vom/src/types.ts

@@ -25,6 +25,8 @@ export interface VomNode {
   role?: string;
   name?: string;
   value?: string;
+  placeholder?: string;
+  inputState?: "empty" | "filled" | "default" | "unknown";
   href?: string; // hostname of external link target; omitted for same-origin links
   text?: string;
   nearbyText?: string;
@@ -63,12 +65,6 @@ export interface VomOptions {
    * public layer header format.
    */
   activeRegionPolicy?: boolean;
-  /**
-   * Experimental: emit semantic summaries for repeated collection-like
-   * containers. Disabled by default because false positives in menus/forms are
-   * still noisy.
-   */
-  semanticCollections?: boolean;
 }
 
 export interface CondSurface {