feat: 视觉能力去 Electron 化，经 HostBridge.screen 注入（迁移阶段1-A9）

- HostBridge 新增可选 screen 服务（listDisplays/primaryDisplay/dipToScreenPoint/
  displayMatching/captureDisplay），vision 3 处、cv-vision 2 处动态 import(electron)
  全部改为 requireScreenService()；未注入时抛稳定的 host_unavailable
- demo 宿主 src/main/index.ts 用 desktopCapturer/screen 实现 screen 服务
- check-deps.mjs 升级：新增动态 import()/require() 扫描（旧正则实测 0 命中的盲区），
  合成用例验证命中，升级后真实源码 0 违规
- 包依赖闭包：补声明 @cantoo/pdf-lib、@napi-rs/canvas、pdfjs-dist
- cv-vision 测试从 vi.mock(electron) 改为宿主桥注入，11/11 通过

packages/rpa-core/src/capabilities/cv-vision.test.ts

@@ -10,30 +10,50 @@ const detectMock = vi.hoisted(() => vi.fn(async () => ({
     { text: "确认", box: [[100, 200], [130, 200], [130, 210], [100, 210]] }
   ]
 })));
-// desktopCapturer 模拟: 默认无画面(走 GDI 回退), 多屏用例按请求宽度提供对应显示器画面
+// 屏幕服务模拟: 默认无画面(走 GDI 回退), 多屏用例按显示器 id/请求宽度提供对应画面
 const electronState = vi.hoisted(() => ({ sources: [] as Array<{ display_id: string; thumbnail: any }> }));
 
 vi.mock("../driver/windows/powershell", () => ({ powershell: powershellMock }));
 vi.mock("@gutenye/ocr-node", () => ({
   default: { create: vi.fn(async () => ({ detect: detectMock })) }
 }));
-vi.mock("electron", () => ({
-  desktopCapturer: {
-    getSources: vi.fn(async (opts: { thumbnailSize: { width: number } }) =>
-      electronState.sources.filter(s => s.thumbnail.getSize().width === opts.thumbnailSize.width))
-  },
-  screen: {
-    getAllDisplays: vi.fn(() => [
-      { id: 1, bounds: { x: 0, y: 0, width: 1920, height: 1080 }, scaleFactor: 1 },
-      { id: 2, bounds: { x: 1920, y: 0, width: 1280, height: 720 }, scaleFactor: 2 }
-    ]),
-    dipToScreenPoint: vi.fn((p: { x: number; y: number }) => ({ x: p.x, y: p.y }))
-  }
-}));
 
 import { getHandler } from "../engine/registry";
+import { setHostBridge, type HostDisplay } from "../engine/host-bridge";
 import "./cv-vision";
 
+const displayOf = (id: string, x: number, width: number, height: number, scaleFactor: number): HostDisplay => ({
+  id,
+  bounds: { x, y: 0, width, height },
+  scaleFactor
+});
+const displays: HostDisplay[] = [
+  displayOf("1", 0, 1920, 1080, 1),
+  displayOf("2", 1920, 1280, 720, 2)
+];
+
+setHostBridge({
+  createFormWindow: () => { throw new Error("not used in cv-vision tests"); },
+  dipToScreenPoint: (point) => ({ x: point.x, y: point.y }),
+  screenToDipPoint: (point) => ({ x: point.x, y: point.y }),
+  loadAiConfig: () => ({ baseUrl: "", apiKey: "", model: "", visionModel: "" }),
+  screen: {
+    listDisplays: () => displays,
+    primaryDisplay: () => displays[0],
+    dipToScreenPoint: (point) => ({ x: point.x, y: point.y }),
+    displayMatching: () => displays[0],
+    captureDisplay: async (displayId: string, wantWidth: number, wantHeight: number) => {
+      // 模拟真实 captureDisplay 的对位规则，但不做 sources[0] 兜底：
+      // 保持"主屏无画面 → 跳过该屏"的旧多屏语义
+      const source = electronState.sources.find((item) => item.display_id === displayId && item.thumbnail.getSize().width === wantWidth)
+        || electronState.sources.find((item) => item.thumbnail.getSize().width === wantWidth);
+      if (!source || source.thumbnail.isEmpty()) throw new Error(`无法获取显示器 ${displayId} 的屏幕截图`);
+      void wantHeight;
+      return source.thumbnail.toPNG();
+    }
+  }
+});
+
 describe("CV vision capabilities", () => {
   beforeEach(() => {
     powershellMock.mockClear();

packages/rpa-core/src/capabilities/cv-vision.ts

@@ -1,5 +1,6 @@
 import { register } from "../engine/registry";
 import { RuntimeError, type CapabilityHandler } from "../engine/types";
+import { requireScreenService } from "../engine/host-bridge";
 import { powershell } from "../driver/windows/powershell";
 import fs from "node:fs";
 import os from "node:os";
@@ -44,30 +45,27 @@ async function gdiGrabScreen(imagePath: string): Promise<void> {
 /** 一次屏幕截图: 图片左上角在虚拟桌面上的绝对 DIP 坐标 + 物理/DIP 缩放比 */
 interface ScreenShot { imagePath: string; dipX: number; dipY: number; scale: number }
 
-/** desktopCapturer 逐显示器截屏(每屏原生分辨率), 不可用时回退 GDI 全虚拟桌面单图 */
+/** 宿主屏幕服务逐显示器截屏(每屏原生分辨率), 不可用时回退 GDI 全虚拟桌面单图 */
 async function grabScreenAll(baseDir: string): Promise<ScreenShot[]> {
   fs.mkdirSync(baseDir, { recursive: true });
   try {
-    const { desktopCapturer, screen } = await import("electron");
-    if (desktopCapturer && screen?.getAllDisplays) {
-      const shots: ScreenShot[] = [];
-      const displays = screen.getAllDisplays();
-      for (const display of displays) {
-        const scale = display.scaleFactor || 1;
-        const sources = await desktopCapturer.getSources({
-          types: ["screen"],
-          thumbnailSize: { width: Math.round(display.bounds.width * scale), height: Math.round(display.bounds.height * scale) }
-        });
-        const source = sources.find(item => item.display_id === String(display.id))
-          || sources.find(item => item.thumbnail.getSize().width === Math.round(display.bounds.width * scale))
-          || sources[0];
-        if (!source || source.thumbnail.isEmpty()) continue;
+    const screenHost = requireScreenService();
+    const shots: ScreenShot[] = [];
+    for (const display of screenHost.listDisplays()) {
+      const scale = display.scaleFactor || 1;
+      try {
+        const pngBytes = await screenHost.captureDisplay(
+          display.id,
+          Math.round(display.bounds.width * scale),
+          Math.round(display.bounds.height * scale)
+        );
+        if (!pngBytes?.length) continue;
         const imagePath = path.join(baseDir, `rpa-cv-screen-${display.id}-${Date.now()}.png`);
-        fs.writeFileSync(imagePath, source.thumbnail.toPNG());
+        fs.writeFileSync(imagePath, Buffer.from(pngBytes));
         shots.push({ imagePath, dipX: display.bounds.x, dipY: display.bounds.y, scale });
-      }
-      if (shots.length) return shots;
+      } catch {}
     }
+    if (shots.length) return shots;
   } catch {}
   const imagePath = path.join(baseDir, `rpa-cv-screen-${Date.now()}.png`);
   await gdiGrabScreen(imagePath);
@@ -207,14 +205,11 @@ function coordinateScript(x: number, y: number, action: "hover" | "click" | "dou
   return lines.join("\n");
 }
 
-/** DIP → 物理像素(SetCursorPos 在 DPI 感知进程里用物理坐标); 无 Electron API 时按原值(缩放 100% 等价) */
+/** DIP → 物理像素(SetCursorPos 在 DPI 感知进程里用物理坐标); 无宿主屏幕服务时按原值(缩放 100% 等价) */
 async function toPhysical(x: number, y: number): Promise<{ x: number; y: number }> {
   try {
-    const { screen } = await import("electron");
-    if (screen && typeof screen.dipToScreenPoint === "function") {
-      const p = screen.dipToScreenPoint({ x: Math.round(x), y: Math.round(y) });
-      return { x: p.x, y: p.y };
-    }
+    const point = requireScreenService().dipToScreenPoint({ x: Math.round(x), y: Math.round(y) });
+    return { x: point.x, y: point.y };
   } catch {}
   return { x: Math.round(x), y: Math.round(y) };
 }

packages/rpa-core/src/capabilities/vision.ts

@@ -3,6 +3,7 @@ import { promises as fs } from "node:fs";
 import { PNG } from "pngjs";
 import { register } from "../engine/registry";
 import { RuntimeError } from "../engine/types";
+import { requireScreenService, type HostDisplay } from "../engine/host-bridge";
 import { powershell, psString } from "../driver/windows/powershell";
 
 function text(args: Record<string, unknown>, keys: string[], fallback = ""): string {
@@ -15,28 +16,20 @@ function text(args: Record<string, unknown>, keys: string[], fallback = ""): str
  * 逐屏截图后按各自物理原点拼到一张画布上——目标在副屏也能搜到。
  * 返回 originX/originY = 拼接画布左上角对应的屏幕物理坐标（副屏在主屏左侧时为负），用于结果坐标平移。 */
 async function captureVirtualScreenPng(): Promise<{ png: PNG; originX: number; originY: number }> {
-  const { desktopCapturer, screen } = await import("electron");
-  const displays = screen.getAllDisplays();
+  const screenHost = requireScreenService();
+  const displays = screenHost.listDisplays();
   if (displays.length === 0) throw new RuntimeError("desktop_error", "无法获取屏幕信息");
-  // 每屏按自己的物理分辨率截图（display_id 匹配 → 缩略图尺寸匹配 → 按物理原点排序对位）
-  const captures: { display: Electron.Display; origin: { x: number; y: number }; png: PNG }[] = [];
+  // 每屏按自己的物理分辨率截图（宿主按 displayId 对位 → 按物理原点排序对位）
+  const captures: { display: HostDisplay; origin: { x: number; y: number }; png: PNG }[] = [];
   for (const display of displays) {
     const scale = display.scaleFactor || 1;
     const wantW = Math.round(display.bounds.width * scale);
     const wantH = Math.round(display.bounds.height * scale);
-    const sources = await desktopCapturer.getSources({
-      types: ["screen"],
-      thumbnailSize: { width: wantW, height: wantH }
-    });
-    const source = sources.find(item => item.display_id === String(display.id))
-      || sources.find(item => item.thumbnail.getSize().width === wantW)
-      || sources[0];
-    if (!source || source.thumbnail.isEmpty()) {
-      throw new RuntimeError("desktop_error", "无法获取屏幕截图");
-    }
+    const pngBytes = await screenHost.captureDisplay(display.id, wantW, wantH);
+    if (!pngBytes?.length) throw new RuntimeError("desktop_error", "无法获取屏幕截图");
     // 显示器 DIP 原点的物理坐标 = 该屏物理原点（屏内线性映射: 物理 = (DIP-原点)*缩放 + 物理原点）
-    const origin = screen.dipToScreenPoint({ x: display.bounds.x, y: display.bounds.y });
-    captures.push({ display, origin, png: PNG.sync.read(source.thumbnail.toPNG()) });
+    const origin = screenHost.dipToScreenPoint({ x: display.bounds.x, y: display.bounds.y });
+    captures.push({ display, origin, png: PNG.sync.read(Buffer.from(pngBytes)) });
   }
   const originX = Math.min(...captures.map(c => c.origin.x));
   const originY = Math.min(...captures.map(c => c.origin.y));
@@ -63,9 +56,9 @@ async function captureVirtualScreenPng(): Promise<{ png: PNG; originX: number; o
 
 /** DIP 区域 → 物理像素区域：左上角经 dipToScreenPoint 换算（天然支持副屏/负坐标），宽高乘所在屏缩放比 */
 async function dipRegionToPhysical(region: { x: number; y: number; width: number; height: number }): Promise<{ x: number; y: number; width: number; height: number }> {
-  const { screen } = await import("electron");
-  const topLeft = screen.dipToScreenPoint({ x: Math.round(region.x), y: Math.round(region.y) });
-  const display = screen.getDisplayMatching({
+  const screenHost = requireScreenService();
+  const topLeft = screenHost.dipToScreenPoint({ x: Math.round(region.x), y: Math.round(region.y) });
+  const display = screenHost.displayMatching({
     x: region.x, y: region.y,
     width: Math.max(1, Math.round(region.width)), height: Math.max(1, Math.round(region.height))
   });
@@ -429,7 +422,7 @@ async function locate(args: Record<string, unknown>, evidenceDir: string, nodeId
   const rawAccuracy = Number(text(args, ["accuracy"], "0.8"));
   const similarity = Math.max(0.05, Math.min(1, Number.isFinite(rawAccuracy) && rawAccuracy > 0 ? rawAccuracy : 0.8));
   // 原生 1:1 匹配失败时, 按缩放比对模板放大/缩小重试——兼容旧版 DIP 截图存的模板与任意来源的图片
-  const scale = (await import("electron")).screen.getPrimaryDisplay().scaleFactor || 1;
+  const scale = requireScreenService().primaryDisplay().scaleFactor || 1;
   const result = await findImage(template, screenshot, 1 - similarity, scale !== 1 ? [scale, 1 / scale] : []);
   if (!result) throw new RuntimeError("not_found", `屏幕中未找到目标图像（要求相似度 ${(similarity * 100).toFixed(0)}%，未达到阈值）`, { nodeId, recommendation: "重新框选模板（框小一点、只框目标图案），或适当调低相似度（如 0.8）；目标在副屏时确认其清晰可见" });
   return { ...result, x: result.x + offsetX, y: result.y + offsetY };