feat(browser-event): support drag event (#321)

zhoushaw · web-flow · commit 839dc6c799c2 · 2025-01-26T12:00:55.000+08:00
diff --git a/packages/midscene/src/ai-model/ui-tars-planning.ts b/packages/midscene/src/ai-model/ui-tars-planning.ts
@@ -8,7 +8,14 @@ import {
 } from './prompt/ui-tars-planning';
 import { call } from './service-caller';
 
-type ActionType = 'click' | 'type' | 'hotkey' | 'finished' | 'scroll' | 'wait';
+type ActionType =
+  | 'click'
+  | 'drag'
+  | 'type'
+  | 'hotkey'
+  | 'finished'
+  | 'scroll'
+  | 'wait';
 
 function capitalize(str: string) {
   return str.charAt(0).toUpperCase() + str.slice(1);
@@ -60,6 +67,18 @@ export async function vlmPlanning(options: {
         },
         param: action.thought || '',
       });
+    } else if (action.action_type === 'drag') {
+      const startPoint = getPoint(action.action_inputs.start_box, size);
+      const endPoint = getPoint(action.action_inputs.end_box, size);
+      transformActions.push({
+        type: 'Drag',
+        param: {
+          start_box: { x: startPoint[0], y: startPoint[1] },
+          end_box: { x: endPoint[0], y: endPoint[1] },
+        },
+        locate: null,
+        thought: action.thought || '',
+      });
     } else if (action.action_type === 'type') {
       transformActions.push({
         type: 'Input',
@@ -140,6 +159,14 @@ interface ClickAction extends BaseAction {
   };
 }
 
+interface DragAction extends BaseAction {
+  action_type: 'drag';
+  action_inputs: {
+    start_box: string; // JSON string of [x, y] coordinates
+    end_box: string; // JSON string of [x, y] coordinates
+  };
+}
+
 interface WaitAction extends BaseAction {
   action_type: 'wait';
   action_inputs: {
@@ -175,6 +202,7 @@ interface FinishedAction extends BaseAction {
 
 export type Action =
   | ClickAction
+  | DragAction
   | TypeAction
   | HotkeyAction
   | ScrollAction
diff --git a/packages/midscene/src/types.ts b/packages/midscene/src/types.ts
@@ -221,6 +221,7 @@ export interface PlanningAction<ParamType = any> {
   type:
     | 'Locate'
     | 'Tap'
+    | 'Drag'
     | 'Hover'
     | 'Input'
     | 'KeyboardPress'
diff --git a/packages/web-integration/package.json b/packages/web-integration/package.json
@@ -107,7 +107,8 @@
     "test": "vitest --run",
     "test:u": "vitest --run -u",
     "test:ai": "AI_TEST_TYPE=web npm run test",
-    "test:ai:bridge": "BRIDGE_MODE=true npm run test --inspect packages/web-integration/tests/ai/bridge/agent.test.ts",
+    "test:ai:temp": "AI_TEST_TYPE=web vitest --run tests/ai/bridge/temp.test.ts",
+    "test:ai:bridge": "BRIDGE_MODE=true npm run test --inspect tests/ai/bridge/agent.test.ts",
     "test:ai:cache": "MIDSCENE_CACHE=true AI_TEST_TYPE=web npm run test",
     "test:ai:all": "npm run test:ai:web && npm run test:ai:native",
     "test:ai:native": "MIDSCENE_CACHE=true AI_TEST_TYPE=native npm run test",
diff --git a/packages/web-integration/src/appium/page.ts b/packages/web-integration/src/appium/page.ts
@@ -63,6 +63,8 @@ export class Page implements AbstractPage {
       wheel: (deltaX: number, deltaY: number) =>
         this.mouseWheel(deltaX, deltaY),
       move: (x: number, y: number) => this.mouseMove(x, y),
+      drag: (from: { x: number; y: number }, to: { x: number; y: number }) =>
+        this.mouseDrag(from, to),
     };
   }
 
@@ -249,6 +251,25 @@ export class Page implements AbstractPage {
     ]);
   }
 
+  private async mouseDrag(
+    from: { x: number; y: number },
+    to: { x: number; y: number },
+  ): Promise<void> {
+    await this.browser.performActions([
+      {
+        type: 'pointer',
+        id: 'mouse',
+        parameters: { pointerType: 'mouse' },
+        actions: [
+          { type: 'pointerMove', duration: 0, x: from.x, y: from.y },
+          { type: 'pointerDown', button: 0 },
+          { type: 'pointerMove', duration: 500, x: to.x, y: to.y },
+          { type: 'pointerUp', button: 0 },
+        ],
+      },
+    ]);
+  }
+
   private async mouseWheel(
     deltaX: number,
     deltaY: number,
diff --git a/packages/web-integration/src/bridge-mode/agent-cli-side.ts b/packages/web-integration/src/bridge-mode/agent-cli-side.ts
@@ -63,6 +63,7 @@ export const getBridgePageInCliSide = (): ChromeExtensionPageCliSide => {
           click: bridgeCaller(MouseEvent.Click),
           wheel: bridgeCaller(MouseEvent.Wheel),
           move: bridgeCaller(MouseEvent.Move),
+          drag: bridgeCaller(MouseEvent.Drag),
         };
         return mouse;
       }
diff --git a/packages/web-integration/src/bridge-mode/common.ts b/packages/web-integration/src/bridge-mode/common.ts
@@ -26,6 +26,7 @@ export enum MouseEvent {
   Click = 'mouse.click',
   Wheel = 'mouse.wheel',
   Move = 'mouse.move',
+  Drag = 'mouse.drag',
 }
 
 export enum KeyboardEvent {
diff --git a/packages/web-integration/src/bridge-mode/page-browser-side.ts b/packages/web-integration/src/bridge-mode/page-browser-side.ts
@@ -55,6 +55,9 @@ export class ChromeExtensionPageBrowserSide extends ChromeExtensionProxyPage {
 
         if (method.startsWith(MouseEvent.PREFIX)) {
           const actionName = method.split('.')[1] as keyof MouseAction;
+          if (actionName === 'drag') {
+            return this.mouse[actionName].apply(this.mouse, args as any);
+          }
           return this.mouse[actionName].apply(this.mouse, args as any);
         }
 
diff --git a/packages/web-integration/src/chrome-extension/page.ts b/packages/web-integration/src/chrome-extension/page.ts
@@ -425,6 +425,27 @@ export default class ChromeExtensionProxyPage implements AbstractPage {
         y,
       });
     },
+    drag: async (
+      from: { x: number; y: number },
+      to: { x: number; y: number },
+    ) => {
+      await this.mouse.move(from.x, from.y);
+      await this.sendCommandToDebugger('Input.dispatchMouseEvent', {
+        type: 'mousePressed',
+        x: from.x,
+        y: from.y,
+        button: 'left',
+        clickCount: 1,
+      });
+      await this.mouse.move(to.x, to.y);
+      await this.sendCommandToDebugger('Input.dispatchMouseEvent', {
+        type: 'mouseReleased',
+        x: to.x,
+        y: to.y,
+        button: 'left',
+        clickCount: 1,
+      });
+    },
   };
 
   keyboard = {
diff --git a/packages/web-integration/src/common/tasks.ts b/packages/web-integration/src/common/tasks.ts
@@ -311,6 +311,25 @@ export class PageTaskExecutor {
             },
           };
         tasks.push(taskActionTap);
+      } else if (plan.type === 'Drag') {
+        const taskActionDrag: ExecutionTaskActionApply<{
+          start_box: { x: number; y: number };
+          end_box: { x: number; y: number };
+        }> = {
+          type: 'Action',
+          subType: 'Drag',
+          param: plan.param,
+          thought: plan.thought,
+          locate: plan.locate,
+          executor: async (taskParam) => {
+            assert(
+              taskParam?.start_box && taskParam?.end_box,
+              'No start_box or end_box to drag',
+            );
+            await this.page.mouse.drag(taskParam.start_box, taskParam.end_box);
+          },
+        };
+        tasks.push(taskActionDrag);
       } else if (plan.type === 'Hover') {
         const taskActionHover: ExecutionTaskActionApply<PlanningActionParamHover> =
           {
diff --git a/packages/web-integration/src/page.ts b/packages/web-integration/src/page.ts
@@ -13,6 +13,10 @@ export interface MouseAction {
   ) => Promise<void>;
   wheel: (deltaX: number, deltaY: number) => Promise<void>;
   move: (x: number, y: number) => Promise<void>;
+  drag: (
+    from: { x: number; y: number },
+    to: { x: number; y: number },
+  ) => Promise<void>;
 }
 
 export interface KeyboardAction {
@@ -36,6 +40,10 @@ export abstract class AbstractPage {
       ) => {},
       wheel: async (deltaX: number, deltaY: number) => {},
       move: async (x: number, y: number) => {},
+      drag: async (
+        from: { x: number; y: number },
+        to: { x: number; y: number },
+      ) => {},
     };
   }
 
diff --git a/packages/web-integration/src/playground/static-page.ts b/packages/web-integration/src/playground/static-page.ts
@@ -80,6 +80,7 @@ export default class StaticPage implements AbstractPage {
     click: ThrowNotImplemented.bind(null, 'mouse.click'),
     wheel: ThrowNotImplemented.bind(null, 'mouse.wheel'),
     move: ThrowNotImplemented.bind(null, 'mouse.move'),
+    drag: ThrowNotImplemented.bind(null, 'mouse.drag'),
   };
 
   keyboard = {
diff --git a/packages/web-integration/src/puppeteer/base-page.ts b/packages/web-integration/src/puppeteer/base-page.ts
@@ -96,6 +96,32 @@ export class Page<
       },
       move: async (x: number, y: number) =>
         this.underlyingPage.mouse.move(x, y),
+      drag: async (
+        from: { x: number; y: number },
+        to: { x: number; y: number },
+      ) => {
+        if (this.pageType === 'puppeteer') {
+          await (this.underlyingPage as PuppeteerPage).mouse.drag(
+            {
+              x: from.x,
+              y: from.y,
+            },
+            {
+              x: to.x,
+              y: to.y,
+            },
+          );
+        } else if (this.pageType === 'playwright') {
+          // Playwright doesn't have a drag method, so we need to simulate it
+          await (this.underlyingPage as PlaywrightPage).mouse.move(
+            from.x,
+            from.y,
+          );
+          await (this.underlyingPage as PlaywrightPage).mouse.down();
+          await (this.underlyingPage as PlaywrightPage).mouse.move(to.x, to.y);
+          await (this.underlyingPage as PlaywrightPage).mouse.up();
+        }
+      },
     };
   }
 
diff --git a/packages/web-integration/tests/ai/bridge/temp.test.ts b/packages/web-integration/tests/ai/bridge/temp.test.ts
@@ -0,0 +1,19 @@
+import {
+  AgentOverChromeBridge,
+  getBridgePageInCliSide,
+} from '@/bridge-mode/agent-cli-side';
+import { describe, expect, it, vi } from 'vitest';
+
+vi.setConfig({
+  testTimeout: 260 * 1000,
+});
+
+describe.skipIf(!process.env.BRIDGE_MODE)('drag event', () => {
+  it('agent in cli side, current tab', async () => {
+    const agent = new AgentOverChromeBridge();
+    await agent.connectCurrentTab();
+    await agent.ai('Finish dragging the slider');
+
+    await agent.destroy();
+  });
+});

Original file line number	Diff line number	Diff line change
`@@ -63,6 +63,7 @@ export const getBridgePageInCliSide = (): ChromeExtensionPageCliSide => {`
`63`	`63`	`click: bridgeCaller(MouseEvent.Click),`
`64`	`64`	`wheel: bridgeCaller(MouseEvent.Wheel),`
`65`	`65`	`move: bridgeCaller(MouseEvent.Move),`
	`66`	`+ drag: bridgeCaller(MouseEvent.Drag),`
`66`	`67`	`};`
`67`	`68`	`return mouse;`
`68`	`69`	`}`
Original file line number	Diff line number	Diff line change
`@@ -26,6 +26,7 @@ export enum MouseEvent {`
`26`	`26`	`Click = 'mouse.click',`
`27`	`27`	`Wheel = 'mouse.wheel',`
`28`	`28`	`Move = 'mouse.move',`
	`29`	`+ Drag = 'mouse.drag',`
`29`	`30`	`}`
`30`	`31`
`31`	`32`	`export enum KeyboardEvent {`
Original file line number	Diff line number	Diff line change
`@@ -55,6 +55,9 @@ export class ChromeExtensionPageBrowserSide extends ChromeExtensionProxyPage {`
`55`	`55`
`56`	`56`	`if (method.startsWith(MouseEvent.PREFIX)) {`
`57`	`57`	`const actionName = method.split('.')[1] as keyof MouseAction;`
	`58`	`+ if (actionName === 'drag') {`
	`59`	`+ return this.mouse[actionName].apply(this.mouse, args as any);`
	`60`	`+ }`
`58`	`61`	`return this.mouse[actionName].apply(this.mouse, args as any);`
`59`	`62`	`}`
`60`	`63`