fix(record): rebase and dto policy

apps/extension/src/lib/__tests__/recording-observation.test.ts

@@ -18,22 +18,13 @@ function sessionWithInput(redactValues = false): RecordingObservationSession {
     rootFrameId: "root",
     index: new ObservationNodeIndex({
       rootFrameId: "root",
-      frameDocuments: [
+      matchNodes: [
         {
           frameId: "root",
-          domNodes: [
-            {
-              backendNodeId: 42,
-              parentBackendNodeId: null,
-              frameId: "root",
-              tag: "input",
-              attrs: {},
-              rect: { x: 20, y: 40, w: 200, h: 30 },
-              paintOrder: 1,
-              position: "static",
-              pointerEvents: "auto",
-            },
-          ],
+          backendNodeId: 42,
+          tag: "input",
+          rect: { x: 20, y: 40, w: 200, h: 30 },
+          localRect: { x: 20, y: 40, w: 200, h: 30 },
         },
       ],
       refs: [{ ref: "e1", backendNodeId: 42, role: "textbox", name: "Password", line: 1 }],

apps/extension/src/lib/__tests__/settle-controller.test.ts

@@ -8,7 +8,7 @@ import type { RecordingDraftStep } from "../recording/types";
 const OBSERVATION: RegisteredObservation = {
   stateId: "s-next",
   rootFrameId: "root",
-  index: new ObservationNodeIndex({ rootFrameId: "root", frameDocuments: [], refs: [] }),
+  index: new ObservationNodeIndex({ rootFrameId: "root", matchNodes: [], refs: [] }),
   url: "https://example.com/next",
 };
 

apps/extension/src/lib/__tests__/target-matcher.test.ts

@@ -1,40 +1,50 @@
 import type { RenderedRef } from "@browser-skill/vom";
 import { describe, expect, it } from "vitest";
-import type { CapturedNode } from "@/tools/vom/capture";
+import type { CaptureVomMatchNode } from "@/tools/capture-vom-observation";
 import { ObservationNodeIndex, type RegisteredObservation } from "../recording/observation-capture";
 import { matchObservationTarget } from "../recording/target-matcher";
 
-function node(backendNodeId: number, frameId: string, x = 10): CapturedNode {
+function node(backendNodeId: number, frameId: string, x = 10): CaptureVomMatchNode {
   return {
     backendNodeId,
-    parentBackendNodeId: null,
     frameId,
     tag: "button",
-    attrs: {},
     rect: { x, y: 20, w: 100, h: 30 },
-    paintOrder: 1,
-    position: "static",
-    pointerEvents: "auto",
+    localRect: { x, y: 20, w: 100, h: 30 },
   };
 }
 
 function observation(
-  documents: Array<{ frameId: string; domNodes: CapturedNode[] }>,
+  matchNodes: CaptureVomMatchNode[],
   refs: RenderedRef[],
 ): RegisteredObservation {
   return {
     stateId: "s1",
     rootFrameId: "root",
-    index: new ObservationNodeIndex({ rootFrameId: "root", frameDocuments: documents, refs }),
+    index: new ObservationNodeIndex({ rootFrameId: "root", matchNodes, refs }),
     url: "https://example.com",
   };
 }
 
 describe("matchObservationTarget", () => {
+  it("indexes the safe geometry DTO without discarding frame-local geometry", () => {
+    const geometry = node(42, "child");
+    geometry.localRect = { x: 5, y: 6, w: 100, h: 30 };
+    const ref: RenderedRef = {
+      ref: "e1",
+      backendNodeId: 42,
+      frameId: "child",
+      line: 1,
+    };
+    const candidate = observation([geometry], [ref]).index.candidates("child", "button")[0];
+
+    expect(candidate).toEqual({ frameId: "child", geometry, ref });
+  });
+
   it("matches a unique node using canonical top-level viewport geometry", () => {
     const target = matchObservationTarget({
       observation: observation(
-        [{ frameId: "root", domNodes: [node(42, "root")] }],
+        [node(42, "root")],
         [{ ref: "e1", backendNodeId: 42, role: "button", name: "发布", line: 1 }],
       ),
       hint: { geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" } },
@@ -45,10 +55,7 @@ describe("matchObservationTarget", () => {
   it("uses frame id with backend node id so sibling frames cannot collide", () => {
     const target = matchObservationTarget({
       observation: observation(
-        [
-          { frameId: "left", domNodes: [node(42, "left")] },
-          { frameId: "right", domNodes: [node(42, "right")] },
-        ],
+        [node(42, "left"), node(42, "right")],
         [
           { ref: "e1", backendNodeId: 42, frameId: "left", line: 1 },
           { ref: "e2", backendNodeId: 42, frameId: "right", line: 2 },
@@ -65,10 +72,7 @@ describe("matchObservationTarget", () => {
   it("restricts a missing frame hint to the root frame", () => {
     const target = matchObservationTarget({
       observation: observation(
-        [
-          { frameId: "root", domNodes: [] },
-          { frameId: "child", domNodes: [node(42, "child")] },
-        ],
+        [node(42, "child")],
         [{ ref: "e1", backendNodeId: 42, frameId: "child", line: 1 }],
       ),
       hint: { geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" } },
@@ -80,7 +84,7 @@ describe("matchObservationTarget", () => {
   it("returns unmatched for ambiguous geometry", () => {
     const target = matchObservationTarget({
       observation: observation(
-        [{ frameId: "root", domNodes: [node(42, "root"), node(43, "root")] }],
+        [node(42, "root"), node(43, "root")],
         [
           { ref: "e1", backendNodeId: 42, line: 1 },
           { ref: "e2", backendNodeId: 43, line: 2 },
@@ -94,10 +98,7 @@ describe("matchObservationTarget", () => {
   it("uses semantics when geometry is unavailable without crossing frame boundaries", () => {
     const target = matchObservationTarget({
       observation: observation(
-        [
-          { frameId: "root", domNodes: [node(41, "root")] },
-          { frameId: "child", domNodes: [node(42, "child")] },
-        ],
+        [node(41, "root"), node(42, "child")],
         [
           { ref: "e1", backendNodeId: 41, role: "button", name: "保存", line: 1 },
           { ref: "e2", backendNodeId: 42, frameId: "child", role: "button", name: "保存", line: 2 },
@@ -112,7 +113,7 @@ describe("matchObservationTarget", () => {
   it("uses semantics to disambiguate equal geometry in one frame", () => {
     const target = matchObservationTarget({
       observation: observation(
-        [{ frameId: "root", domNodes: [node(42, "root"), node(43, "root")] }],
+        [node(42, "root"), node(43, "root")],
         [
           { ref: "e1", backendNodeId: 42, role: "button", name: "保存", line: 1 },
           { ref: "e2", backendNodeId: 43, role: "button", name: "取消", line: 2 },

apps/extension/src/lib/recording/observation-capture.ts

@@ -1,11 +1,14 @@
 import type { RenderedRef } from "@browser-skill/vom";
-import { captureVomObservation } from "@/tools/capture-vom-observation";
+import {
+  type CaptureVomMatchNode,
+  type CaptureVomObservationResult,
+  captureVomObservation,
+} from "@/tools/capture-vom-observation";
 import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
-import type { CapturedNode } from "@/tools/vom/capture";
 
 export interface IndexedObservationNode {
   frameId: string;
-  node: CapturedNode;
+  geometry: CaptureVomMatchNode;
   ref?: RenderedRef;
 }
 
@@ -38,11 +41,7 @@ export class ObservationNodeIndex {
   readonly #refById = new Map<string, RenderedRef>();
   readonly #refsByFrame = new Map<string, RenderedRef[]>();
 
-  constructor(input: {
-    rootFrameId: string;
-    frameDocuments: Array<{ frameId: string; domNodes: CapturedNode[] }>;
-    refs: RenderedRef[];
-  }) {
+  constructor(input: Pick<CaptureVomObservationResult, "rootFrameId" | "matchNodes" | "refs">) {
     const refByNode = new Map<string, RenderedRef>();
     for (const ref of input.refs) {
       const frameId = ref.frameId ?? input.rootFrameId;
@@ -52,15 +51,17 @@ export class ObservationNodeIndex {
       frameRefs.push(ref);
       this.#refsByFrame.set(frameId, frameRefs);
     }
-    for (const document of input.frameDocuments) {
-      for (const node of document.domNodes) {
-        const frameId = node.frameId ?? document.frameId;
-        const entry = { frameId, node, ref: refByNode.get(nodeKey(frameId, node.backendNodeId)) };
-        const key = frameTagKey(frameId, node.tag);
-        const bucket = this.#nodesByFrameTag.get(key) ?? [];
-        bucket.push(entry);
-        this.#nodesByFrameTag.set(key, bucket);
-      }
+    for (const geometry of input.matchNodes) {
+      const { frameId } = geometry;
+      const entry = {
+        frameId,
+        geometry,
+        ref: refByNode.get(nodeKey(frameId, geometry.backendNodeId)),
+      };
+      const key = frameTagKey(frameId, geometry.tag);
+      const bucket = this.#nodesByFrameTag.get(key) ?? [];
+      bucket.push(entry);
+      this.#nodesByFrameTag.set(key, bucket);
     }
   }
 

apps/extension/src/lib/recording/target-matcher.ts

@@ -15,7 +15,7 @@ function rectMatches(a: TargetGeometry["rect"], b: TargetGeometry["rect"]): bool
 }
 
 function candidateMatches(candidate: IndexedObservationNode, geometry: TargetGeometry): boolean {
-  return candidate.node.rect !== null && rectMatches(geometry.rect, candidate.node.rect);
+  return candidate.geometry.rect !== null && rectMatches(geometry.rect, candidate.geometry.rect);
 }
 
 export function unmatchedTarget(fallback?: CaptureTargetDescriptor): TargetDescriptorV3 {