wechat-devtools

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Wechat DevTools MCP Skill (v0.9.5)

前置条件

Prerequisites

Step 0：安装与配置

Step 0: Installation and Configuration

bash

pip install uv   # 如未安装 uv
uv tool install wechat-devtools-mcp --force  # 通过uv安装wechat-devtools-mcp

编辑器配置：

json

{
  "mcpServers": {
    "wechat-devtools": {
      "command": "uvx",
      "args": ["wechat-devtools-mcp"],
      "env": {
        "WECHAT_DEVTOOLS_CLI": "C:\\Program Files (x86)\\Tencent\\微信web开发者工具\\cli.bat",
        "WECHAT_PROJECT_PATH": "D:\\Your\\Project\\Path"
      }
    }
  }
}

主流编辑器配置见 README.md

[!IMPORTANT] 必须手动开启开发者工具的服务端口：
设置
→
安全设置
→
服务端口
→
开启
。未开启将导致所有 CLI 操作报
CLI_TIMEOUT
。

bash

pip install uv   # Install uv if not present
uv tool install wechat-devtools-mcp --force  # Install wechat-devtools-mcp via uv

Editor Configuration:

json

{
  "mcpServers": {
    "wechat-devtools": {
      "command": "uvx",
      "args": ["wechat-devtools-mcp"],
      "env": {
        "WECHAT_DEVTOOLS_CLI": "C:\\Program Files (x86)\\Tencent\\微信web开发者工具\\cli.bat",
        "WECHAT_PROJECT_PATH": "D:\\Your\\Project\\Path"
      }
    }
  }
}

See README.md for mainstream editor configurations

[!IMPORTANT] You must manually enable the service port of the developer tools:
Settings
→
Security Settings
→
Service Port
→
Enable
. Failure to enable will cause all CLI operations to report
CLI_TIMEOUT
.

Step 1：运行时环境检查

Step 1: Runtime Environment Check

首先调用
wechat_ide(action='status')
一次性确认所有前置条件。

检查项	偏好命令	失败时操作
CLI 已安装	`status` → `cli_exists: true`	安装工具并配置 `WECHAT_DEVTOOLS_CLI`
项目路径已配置	`status` → `project_exists: true`	配置 `WECHAT_PROJECT_PATH`
已登录	`is_login` → `logged_in: true`	`login(qr_format='terminal')` 扫码
Node.js 可用	`status` → `node_available: true`	安装 Node.js ≥ 8.0

First call
wechat_ide(action='status')
to verify all prerequisites at once.

Check Item	Preferred Command	Action on Failure
CLI Installed	`status` → `cli_exists: true`	Install the tool and configure `WECHAT_DEVTOOLS_CLI`
Project Path Configured	`status` → `project_exists: true`	Configure `WECHAT_PROJECT_PATH`
Logged In	`is_login` → `logged_in: true`	`login(qr_format='terminal')` to scan QR code
Node.js Available	`status` → `node_available: true`	Install Node.js ≥ 8.0

Efficiency Principles

IDE 只在会话开始时 open 一次，compile 只在代码变更后执行，页面跳转优先用 evaluate 而非 navigate。

场景	正确做法	错误做法
没改代码，换页面测试	`evaluate(expression="wx.reLaunch({url:'/pages/xxx/index'}); 'ok'")` → `page_data`	重新 open → compile
改了代码	`compile` → `page_data` 验证（compile 自动重连 automator）	重新 open → compile
连接断开	先快速恢复（仅 `start` ）	直接走完整恢复

The IDE is opened only once at the start of the session, compile is executed only after code changes, and page navigation uses evaluate preferentially over navigate.

Scenario	Correct Practice	Incorrect Practice
Testing different pages without code changes	`evaluate(expression="wx.reLaunch({url:'/pages/xxx/index'}); 'ok'")` → `page_data`	Re-open → compile
Code changed	`compile` → `page_data` verification (compile automatically reconnects automator)	Re-open → compile
Connection disconnected	Quick recovery first (only `start` )	Directly perform full recovery

API 速查表

API Cheat Sheet

wechat_ide

— IDE 生命周期

wechat_ide

— IDE Lifecycle

action	功能	关键参数
`open`	打开 IDE/项目（cdp_enabled 时自动做启动健康检查）	`cdp_enabled=true` （开启 CDP 9222 端口，自动采集 5s CDP 日志检测启动错误）
`login`	扫码登录	`qr_format="terminal"`
`is_login`	检查登录状态	—
`close` / `quit`	关闭项目 / 退出 IDE	—
`status`	环境诊断	—

action	Function	Key Parameters
`open`	Open IDE/project (automatically performs startup health check when cdp_enabled)	`cdp_enabled=true` (Enable CDP port 9222, automatically collect 5s CDP logs to detect startup errors)
`login`	QR code login	`qr_format="terminal"`
`is_login`	Check login status	—
`close` / `quit`	Close project / Exit IDE	—
`status`	Environment diagnosis	—

wechat_build

— 构建与发布

wechat_build

— Building and Publishing

action	功能	关键参数
`compile`	编译检查（捕获错误/警告，成功后自动重连 automator）	—

注意：compile_condition 对 tabBar 页面可能无效（app 路由守卫覆盖），用 evaluate + wx.reLaunch 跳转更可靠

preview

| 生成预览二维码 |

qr_format="terminal"

| |

upload

| 上传到微信后台 | version
（必填）,

desc?

| |

build_npm

| 构建 NPM 依赖（upload 前必做） | — | |

cache_clean

| 清除缓存 |

clean_type="compile"

action	Function	Key Parameters
`compile`	Compilation check (captures errors/warnings, automatically reconnects automator after success)	—

Note: compile_condition may be invalid for tabBar pages (overridden by app route guards), using evaluate + wx.reLaunch for navigation is more reliable

preview

| Generate preview QR code |

qr_format="terminal"

| |

upload

| Upload to WeChat backend | version
(required),

desc?

| |

build_npm

| Build NPM dependencies (mandatory before upload) | — | |

cache_clean

| Clear cache |

clean_type="compile"

wechat_automator

— 自动化交互

wechat_automator

— Automated Interaction

前提：先调用
start
开启自动化端口（整个会话仅需一次）。

action	功能	必填参数
`start`	开启自动化端口	—
`tap`	点击元素	`selector`
`input`	输入文本	`selector` , `value`
`element_info`	获取元素详情（文本/尺寸/WXML）	`selector`
`set_data`	热更新页面 data（无需重编译）	`data_json`
`call_method`	调用页面方法	`method` , `args_json?`
`call_wx`	调用 wx API	`method`
`mock_wx`	Mock wx API 返回值	`method` , `result_json`
`evaluate`	执行 JS 表达式（逻辑层万能钥匙）	`expression`

注意：v0.7.0 起支持声明语句（const/let/var）
v0.9.2：compile 后自动 invalidate 旧缓存连接再重连，daemon 健康检查 3s 超时保护，navigate currentPage 轮询 2s 独立超时
v0.9.0：底层改为持久化 Node daemon（NDJSON 协议），WS 连接按端口缓存复用，工具调用延迟 ~3ms

page_stack

| 获取页面栈 | — | |

page_data

| 获取当前页面 data |

expected_path?

（轮询验证页面路径） | |

system_info

| 获取运行时系统信息 | — | |

storage

| 读取本地缓存 |

key?

（空=列出全部） |

Prerequisite: Call
start
first to enable the automation port (only required once per session).

action	Function	Required Parameters
`start`	Enable automation port	—
`tap`	Click element	`selector`
`input`	Input text	`selector` , `value`
`element_info`	Get element details (text/size/WXML)	`selector`
`set_data`	Hot update page data (no recompilation needed)	`data_json`
`call_method`	Call page method	`method` , `args_json?`
`call_wx`	Call wx API	`method`
`mock_wx`	Mock wx API return value	`method` , `result_json`
`evaluate`	Execute JS expression (universal key for logic layer)	`expression`

Note: Declaration statements (const/let/var) are supported since v0.7.0
v0.9.2: Automatically invalidates old cache connections and reconnects after compile, adds 3s timeout protection for daemon health check, and 2s independent timeout for navigate currentPage polling
v0.9.0:底层改为持久化 Node daemon（NDJSON 协议），WS 连接按端口缓存复用，工具调用延迟 ~3ms

page_stack

| Get page stack | — | |

page_data

| Get current page data |

expected_path?

(poll to verify page path) | |

system_info

| Get runtime system information | — | |

storage

| Read local cache |

key?

(empty = list all) |

wechat_inspector

— 日志采集

wechat_inspector

— Log Collection

action	功能	关键参数
`console`	采集 console 日志和 JS 异常	`duration=10` , `log_type="all"`
`cdp`	CDP 协议采集底层日志（WXML/渲染层）	`duration=10` , `detail_level="concise"` , `max_logs=50`

cdp 前提：以
cdp_enabled=true
打开项目，确保端口 9222 可用。

action	Function	Key Parameters
`console`	Collect console logs and JS exceptions	`duration=10` , `log_type="all"`
`cdp`	Collect underlying logs via CDP protocol (WXML/rendering layer)	`duration=10` , `detail_level="concise"` , `max_logs=50`

CDP Prerequisite: Open the project with
cdp_enabled=true
and ensure port 9222 is available.

wechat_screenshot

— 截图

wechat_screenshot

— Screenshot

```
output_path
```
（可选）：截图保存路径。留空则自动保存到项目目录下
```
screenshots/
```
文件夹
```
full_page
```
（默认
```
true
```
）：设为
```
false
```
只截当前视口
```
scroll_top
```
（可选）：截图前滚动到的位置（逻辑像素），配合
```
full_page=false
```
使用
```
page_path
```
（可选）：确保截图前在指定页面上，若当前页面不匹配则自动跳转
前提：先调用
```
wechat_automator(action='start')
```
注意：不要主动截图，仅在用户明确要求或排查异常需要视觉确认时才调用
限制：使用
```
scroll-view
```
组件滚动的页面无法长图拼接（automator SDK 限制），仅截取当前视口
限制：截图可能无法捕获 fixed/absolute overlay（弹窗、蒙层），以 page_data 为准
路径规约：推荐
```
<project>/screenshots/
```
或显式绝对路径。避免写入
.claude/image-cache/
— 这是 Claude Code 的用户发图缓存目录，MCP 截图混入会互相污染

```
output_path
```
(optional): Screenshot save path. Leave blank to automatically save to the
```
screenshots/
```
folder under the project directory
```
full_page
```
(default
```
true
```
): Set to
```
false
```
to capture only the current viewport
```
scroll_top
```
(optional): Position to scroll to before taking the screenshot (logical pixels), use with
```
full_page=false
```
```
page_path
```
(optional): Ensure being on the specified page before taking the screenshot, automatically navigate if current page does not match
Prerequisite: Call
```
wechat_automator(action='start')
```
first
Note: Do not take screenshots actively, only call when explicitly requested by the user or visual confirmation is needed for troubleshooting
Limitation: Pages using
```
scroll-view
```
component cannot be stitched into long screenshots (automator SDK limitation), only the current viewport is captured
Limitation: Screenshots may not capture fixed/absolute overlays (pop-ups, masks), rely on
```
page_data
```
instead
Path Convention: Recommended to use
```
<project>/screenshots/
```
or explicit absolute path. Avoid writing to
.claude/image-cache/
— this is the user image cache directory for Claude Code, mixing MCP screenshots will cause mutual contamination

wechat_navigate

— 跳转并采集日志

wechat_navigate

— Navigate and Collect Logs

```
page_path
```
（必填）：如
```
pages/index/index
```
```
wait_ms
```
：等待毫秒，建议 3000
```
clear_logs
```
：是否过滤历史 CDP 日志，默认
```
true
```
```
check_data
```
：跳转后是否检查 page_data 空值，默认
```
true
```
```
detail_level
```
：
```
concise
```
（仅 errors+warnings）或
```
full
```
v0.8.0 新增：自动检测 TabBar 页面并使用
```
switchTab
```
替代
```
reLaunch
```
，返回
```
navigation_method
```
字段
前提：需
```
automator start
```
+
```
cdp_enabled=true
```

```
page_path
```
(required): e.g.
```
pages/index/index
```
```
wait_ms
```
: Wait time in milliseconds, recommended 3000
```
clear_logs
```
: Whether to filter historical CDP logs, default
```
true
```
```
check_data
```
: Whether to check for empty page_data after navigation, default
```
true
```
```
detail_level
```
:
```
concise
```
(only errors+warnings) or
```
full
```
Added in v0.8.0: Automatically detects TabBar pages and uses
```
switchTab
```
instead of
```
reLaunch
```
, returns
```
navigation_method
```
field
Prerequisite: Requires
```
automator start
```
+
```
cdp_enabled=true
```

wechat_file

— 文件读取

wechat_file

— File Reading

action	功能	必填参数
`project_info`	项目完整信息（app.json + 目录结构）	—
`list_pages`	所有页面列表（含文件完整性检查）	—
`read_page`	读取页面源码（wxml/wxss/js/json）	`page_path`
`read_file`	读取任意单文件（最多 800 行）	`file_path`

云函数与云数据库管理：本 MCP 自 v0.9.5 起不再提供
wechat_cloud
工具。请改用 CloudBase MCP（
manageFunctions
/
readNoSqlDatabaseContent
/
writeNoSqlDatabaseContent
等），无 IDE 依赖且覆盖更完整。

action	Function	Required Parameters
`project_info`	Get complete project information (app.json + directory structure)	—
`list_pages`	Get all page list (including file integrity check)	—
`read_page`	Read page source code (wxml/wxss/js/json)	`page_path`
`read_file`	Read any single file (max 800 lines)	`file_path`

Cloud Function and Cloud Database Management: This MCP no longer provides
wechat_cloud
tools since v0.9.5. Please use CloudBase MCP instead (with
manageFunctions
/
readNoSqlDatabaseContent
/
writeNoSqlDatabaseContent
etc.), which has no IDE dependency and covers more features.

SOP 标准操作流程

SOP Standard Operating Procedures

SOP A：初始化（新环境必做）

SOP A: Initialization (Mandatory for New Environments)

wechat_ide(action='status')                         # 诊断环境
wechat_ide(action='is_login')                       # 检查登录
  ↳ 未登录: wechat_ide(action='login', qr_format='terminal')
wechat_ide(action='open', cdp_enabled=True)         # 开启 IDE + CDP 9222 + 自动健康检查
  ↳ 返回 success=false + startup_errors → 小程序启动阶段有致命错误，必须先修复再继续
  ↳ 返回 success=true → 启动正常，继续后续步骤
  ↳ IDE 冷启动可能出现瞬态错误（simulator not found / subPackages of undefined），属正常现象，忽略并继续执行 compile 即可刷新
wechat_automator(action='start')                    # 启动 daemon + 开启自动化 9420
wechat_file(action='project_info')                  # [可选] 确认项目结构
wechat_build(action='cache_clean', clean_type='all')     # 清除全部缓存
wechat_build(action='compile')                            # 编译建立干净 CDP 基线（自动重连 automator）
wechat_automator(action='page_data')                # 验证连接可用
  ↳ ⚠ 检查输出中 AppID 是否为 undefined
  ↳ 如果 undefined → project_path 可能指向了子目录而非项目根目录
  ↳ 云开发项目根目录包含 project.config.json、miniprogram/ 和 cloudfunctions/
  ↳ 正确: project_path="D:/MyProject"  错误: project_path="D:/MyProject/miniprogram"

project_path 规则：必须指向包含
project.config.json
的根目录。云开发项目的
miniprogram/
是子目录，不能作为 project_path。

wechat_ide(action='status')                         # Diagnose environment
wechat_ide(action='is_login')                       # Check login status
  ↳ Not logged in: wechat_ide(action='login', qr_format='terminal')
wechat_ide(action='open', cdp_enabled=True)         # Launch IDE + CDP 9222 + automatic health check
  ↳ Returns success=false + startup_errors → Fatal error during mini program startup, must fix before proceeding
  ↳ Returns success=true → Startup normal, proceed to next steps
  ↳ Transient errors may occur during IDE cold start (simulator not found / subPackages of undefined), which is normal, ignore and continue to execute compile to refresh
wechat_automator(action='start')                    # Launch daemon + enable automation port 9420
wechat_file(action='project_info')                  # [Optional] Confirm project structure
wechat_build(action='cache_clean', clean_type='all')     # Clear all cache
wechat_build(action='compile')                            # Compile to establish clean CDP baseline (automatically reconnects automator)
wechat_automator(action='page_data')                # Verify connection availability
  ↳ ⚠ Check if AppID is undefined in the output
  ↳ If undefined → project_path may point to a subdirectory instead of the project root
  ↳ Cloud development project root directory contains project.config.json, miniprogram/ and cloudfunctions/
  ↳ Correct: project_path="D:/MyProject"  Wrong: project_path="D:/MyProject/miniprogram"

project_path Rule: Must point to the root directory containing
project.config.json
. For cloud development projects,
miniprogram/
is a subdirectory and cannot be used as project_path.

SOP A-2：代码变更后重编译（无需重新 open）

SOP A-2: Recompile After Code Changes (No Need to Re-open IDE)

wechat_build(action='compile')                      # 编译（自动重连 automator）
wechat_automator(action='page_data')                # 验证连接可用

不需要重新 open IDE、不需要 cache_clean。仅在修改了小程序源码后执行。

wechat_build(action='compile')                      # Compile (automatically reconnects automator)
wechat_automator(action='page_data')                # Verify connection availability

No need to re-open IDE or perform cache_clean. Only execute after modifying mini program source code.

页面跳转标准方法

Standard Page Navigation Methods

场景	方式
普通页面	`evaluate(expression="wx.navigateTo({url:'<path>'}); 'ok'")`
tabBar 页面	`wechat_navigate(page_path='<tabBar路径>')` 自动走 switchTab
强制重置	`evaluate(expression="wx.reLaunch({url:'<path>'}); 'ok'")`
跳转后	`page_data` 校验 `path` 匹配预期

Scenario	Method
Normal page	`evaluate(expression="wx.navigateTo({url:'<path>'}); 'ok'")`
TabBar page	`wechat_navigate(page_path='<tabBar path>')` automatically uses switchTab
Force reset	`evaluate(expression="wx.reLaunch({url:'<path>'}); 'ok'")`
After navigation	Verify `path` matches expectation via `page_data`

SOP B：UI 调试（数据/布局问题）

SOP B: UI Debugging (Data/Layout Issues)

wechat_file(action='list_pages')                           # ⓪ 首次导航前，获取有效页面路径列表
  ↳ tabBar 页面路径通常是 pages/xxx/index（非 pages/xxx/xxx）
wechat_navigate(page_path='pages/xxx/index', wait_ms=3000) # ① 跳转 + CDP 日志
wechat_automator(action='page_data')                       # ② 查看 data 状态
  ↳ ⚠ 必须校验 data.path === 预期的 page_path
  ↳ 如不匹配 → 页面跳转失败或被重定向（见 page_data 注意事项）
  ↳ 数据异常: set_data(data_json='{"key":"val"}')  热更新验证
  ↳ 确认元素: element_info(selector='.target')
  ↳ 仅在用户要求或需要视觉确认时: wechat_screenshot()  # 默认保存到项目 screenshots/

wechat_file(action='list_pages')                           # ⓪ Before first navigation, get list of valid page paths
  ↳ TabBar page paths are usually pages/xxx/index (not pages/xxx/xxx)
wechat_navigate(page_path='pages/xxx/index', wait_ms=3000) # ① Navigate + CDP logs
wechat_automator(action='page_data')                       # ② Check data status
  ↳ ⚠ Must verify that data.path === expected page_path
  ↳ If not matching → Page navigation failed or redirected (see page_data notes)
  ↳ Data exception: set_data(data_json='{"key":"val"}') to hot update and verify
  ↳ Confirm element: element_info(selector='.target')
  ↳ Only when requested by user or visual confirmation is needed: wechat_screenshot()  # Default saves to project screenshots/

SOP C：异常排查（报错/白屏/JS 异常）

SOP C: Troubleshooting (Errors/White Screen/JS Exceptions)

wechat_automator(action='page_data')                       # ① 首选：直接检查页面数据
  ↳ 关键字段为 null/空 → 数据未加载或参数错误
  ↳ 数据正常 → 跳到步骤 ④ 确认非数据问题
wechat_automator(action='evaluate', expression='wx.cloud.callFunction({name:"xxx",data:{...}})')
                                                            # ② 直接调 API 获取完整返回值
  ↳ 遇到 [object Object] 时必用此步骤，可拿到完整 JSON
wechat_inspector(action='cdp', duration=5, detail_level='concise')
                                                            # ③ CDP 辅助参考
  ⚠ CDP 错误计数可能包含历史缓存，以 page_data 为准
wechat_build(action='compile')                              # ④ 捕获编译错误
  ↳ 检查 wxml_errors 字段；⚠ 中文引号 "" 等编译错误工具无法捕获

wechat_automator(action='page_data')                       # ① Preferred: Directly check page data
  ↳ Key fields are null/empty → Data not loaded or parameter error
  ↳ Data normal → Proceed to step ④ to confirm it's not a data issue
wechat_automator(action='evaluate', expression='wx.cloud.callFunction({name:"xxx",data:{...}})')
                                                            # ② Directly call API to get complete return value
  ↳ Must use this step when encountering [object Object] to get complete JSON
wechat_inspector(action='cdp', duration=5, detail_level='concise')
                                                            # ③ CDP auxiliary reference
  ⚠ CDP error count may include historical cache, rely on page_data instead
wechat_build(action='compile')                              # ④ Capture compilation errors
  ↳ Check wxml_errors field; ⚠ Compilation errors like Chinese quotes "" cannot be captured by the tool

SOP D：全页面巡检（回归/发布前验收）

SOP D: Full Page Inspection (Regression/Pre-release Acceptance)

wechat_build(action='cache_clean', clean_type='all')    # 建立干净 CDP 基线
wechat_build(action='compile')
  ↳ ⚠ 检查 AppID 是否为 undefined
wechat_file(action='list_pages')                        # 获取页面列表，确认有效路径

wechat_build(action='cache_clean', clean_type='all')    # Establish clean CDP baseline
wechat_build(action='compile')
  ↳ ⚠ Check if AppID is undefined
wechat_file(action='list_pages')                        # Get page list, confirm valid paths

对每个 page 顺序执行（禁止并行）：

Execute sequentially for each page (parallel execution is prohibited):

wechat_navigate(page_path=page, wait_ms=3000) # 跳转 + CDP 日志 wechat_automator(action='page_data') # 核心验证：关键字段非 null/空 ↳ ⚠ 必须校验 data.path === 预期的 page_path ↳ 如不匹配 → 页面跳转失败或被重定向，标记异常 ↳ 字段正常且 path 匹配 → ✅ 页面通过 ↳ 字段为空 → ⚠ 标记异常，用 evaluate 进一步诊断 ↳ 仅在 page_data 异常时补充截图

wechat_navigate(page_path=page, wait_ms=3000) # Navigate + CDP logs wechat_automator(action='page_data') # Core verification: Key fields are not null/empty ↳ ⚠ Must verify that data.path === expected page_path ↳ If not matching → Page navigation failed or redirected, mark as exception ↳ Fields normal and path matching → ✅ Page passed ↳ Fields empty → ⚠ Mark as exception, use evaluate for further diagnosis ↳ Only take supplementary screenshots when page_data is abnormal

汇总：按 page_data 结果排序输出报告

Summary: Output report sorted by page_data results

undefined

undefined

SOP E：Mock 集成测试（支付/权限/设备）

SOP E: Mock Integration Testing (Payment/Permissions/Devices)

wechat_automator(action='mock_wx', method='requestPayment', result_json='{"errMsg":"requestPayment:ok"}')
wechat_automator(action='mock_wx', method='getUserProfile',  result_json='{"userInfo":{"nickName":"测试用户"}}')
wechat_automator(action='mock_wx', method='getLocation',     result_json='{"latitude":23.099,"longitude":113.324}')
wechat_automator(action='tap', selector='.pay-btn')         # 触发交互
wechat_automator(action='page_data')                        # 验证 data 变化

Mock 仅当前会话有效，重启 IDE 后需重新设置。

wechat_automator(action='mock_wx', method='requestPayment', result_json='{"errMsg":"requestPayment:ok"}')
wechat_automator(action='mock_wx', method='getUserProfile',  result_json='{"userInfo":{"nickName":"Test User"}}')
wechat_automator(action='mock_wx', method='getLocation',     result_json='{"latitude":23.099,"longitude":113.324}')
wechat_automator(action='tap', selector='.pay-btn')         # Trigger interaction
wechat_automator(action='page_data')                        # Verify data changes

Mock is only valid for the current session, needs to be reset after restarting IDE.

SOP F：网络调试与 UI 适配

SOP F: Network Debugging and UI Adaptation

① 网络与 API 调试

undefined

① Network and API Debugging

undefined

拦截请求（逻辑层注入）

Intercept requests (logic layer injection)

evaluate(expression='var o=wx.request; wx.request=function(p){console.log(p.url);return o.apply(wx,arguments)}')

模拟超时

Simulate timeout

mock_wx(method='request', result_json='{"errMsg":"request:fail timeout"}')


**② UI 适配测试**

mock_wx(method='getSystemInfo', result_json='{"theme":"dark"}') # 暗黑模式适配 mock_wx(method='getSystemInfo', result_json='{"platform":"mac","windowWidth":1024}') # iPad/PC 适配 system_info() # 记录 windowWidth/Height

undefined

mock_wx(method='request', result_json='{"errMsg":"request:fail timeout"}')


**② UI Adaptation Testing**

mock_wx(method='getSystemInfo', result_json='{"theme":"dark"}') # Dark mode adaptation mock_wx(method='getSystemInfo', result_json='{"platform":"mac","windowWidth":1024}') # iPad/PC adaptation system_info() # Record windowWidth/Height

undefined

SOP G：子页面测试（需 query 参数的页面）

SOP G: Subpage Testing (Pages Requiring Query Parameters)

wechat_file(action='read_page', page_path='pages/xxx/xxx')  # ① 查看 onLoad 方法
  ↳ 从 options 参数中确认 query 参数名（如 id / matchId）
wechat_navigate(page_path='pages/xxx/xxx?正确参数名=值', wait_ms=3000)  # ② 跳转
wechat_automator(action='page_data')                          # ③ 验证数据
  ↳ 关键字段非空 → ✅
  ↳ 大部分为 null → 参数名可能有误，回到 ①

wechat_file(action='read_page', page_path='pages/xxx/xxx')  # ① Check onLoad method
  ↳ Confirm query parameter names (such as id / matchId) from options parameter
wechat_navigate(page_path='pages/xxx/xxx?correct_param_name=value', wait_ms=3000)  # ② Navigate
wechat_automator(action='page_data')                          # ③ Verify data
  ↳ Key fields not empty → ✅
  ↳ Most fields are null → Parameter name may be incorrect, go back to ①

SOP I：跨页面数据一致性校验

SOP I: Cross-page Data Consistency Verification

适用场景：验证同一数据在不同页面的展示是否一致（如积分、用户状态、等级等）

wechat_file(action='list_pages')                         # ① 获取页面列表

Applicable scenario: Verify whether the same data is displayed consistently across different pages (such as points, user status, level, etc.)

wechat_file(action='list_pages')                         # ① Get page list

定义需要校验的公共字段（如 points, phone_bound, level）

Define common fields to verify (such as points, phone_bound, level)

② 逐页面采集数据（顺序执行，禁止并行）：

② Collect data page by page (execute sequentially, parallel execution is prohibited):

wechat_navigate(page_path=page, wait_ms=3000) wechat_automator(action='page_data') ↳ 校验 data.path === 预期页面（跳转失败则标记并跳过） ↳ 提取公共字段值，记录到比对表

wechat_navigate(page_path=page, wait_ms=3000) wechat_automator(action='page_data') ↳ Verify that data.path === expected page (mark and skip if navigation failed) ↳ Extract values of common fields, record to comparison table

③ 比对各页面的同名字段值

③ Compare values of fields with the same name across pages

↳ 值一致 → ✅ 字段通过 ↳ 值不一致 → ⚠ 标记异常，用 evaluate 直接调 API 对比返回值 ↳ 子页面数据异常时，检查是否使用了独立的数据获取链路

undefined

↳ Values consistent → ✅ Field passed ↳ Values inconsistent → ⚠ Mark as exception, use evaluate to directly call API for comparison ↳ When subpage data is abnormal, check if independent data acquisition link is used

undefined

SOP J：小程序 + 管理后台并行数据比对

SOP J: Parallel Data Comparison Between Mini Program and Management Backend

适用场景：验证小程序前端数据与管理后台数据的一致性

undefined

Applicable scenario: Verify consistency between mini program frontend data and management backend data

undefined

架构：

Architecture:

管理后台 → Playwright MCP（浏览器端口）

Management Backend → Playwright MCP (browser port)

小程序 → WeChat DevTools MCP（automator 9420 端口）

Mini Program → WeChat DevTools MCP (automator port 9420)

两者使用不同端口，可以并行运行

They use different ports and can run in parallel

① 分别从两端提取数据（可并行）

① Extract data from both ends respectively (can be parallel)

Agent A: Playwright 操作管理后台，提取数据

Agent A: Operate management backend via Playwright, extract data

Agent B: WeChat MCP 操作小程序，提取 page_data

Agent B: Operate mini program via WeChat MCP, extract page_data

② 在主进程中做数据比对（串行）

② Perform data comparison in main process (serial)


> **端口独占规则**：automator 9420 端口是独占的，同一时刻只能有一个 Agent 操作 WeChat MCP。Playwright 和 WeChat MCP 可同时使用（不同端口）。

---


> **Port Exclusivity Rule**: The automator port 9420 is exclusive, only one Agent can operate WeChat MCP at the same time. Playwright and WeChat MCP can be used simultaneously (different ports).

---

CDP 日志策略

CDP Log Strategy

concise → 仅 errors + warnings（节省 Token，优先使用）
  ↓ summary.errors > 0 时
full    → 完整日志 + source 定位 → wechat_file(action='read_file', file_path=source)

场景	推荐参数
快速诊断	`duration=5, detail_level='concise', max_logs=20`
深度排查	`duration=10, detail_level='full', max_logs=100`
页面巡检	`duration=3, detail_level='concise', max_logs=30`

重要：CDP 错误计数可能包含跨页面累积的历史日志。v0.4.0 的
clear_logs=true
（默认）会基于时间戳过滤历史日志，但仍建议以
page_data
作为最终验证标准。

concise → Only errors + warnings (saves tokens, preferred)
  ↓ When summary.errors > 0
full    → Complete logs + source location → wechat_file(action='read_file', file_path=source)

Scenario	Recommended Parameters
Quick diagnosis	`duration=5, detail_level='concise', max_logs=20`
In-depth troubleshooting	`duration=10, detail_level='full', max_logs=100`
Page inspection	`duration=3, detail_level='concise', max_logs=30`

Important: CDP error count may include accumulated historical logs across pages.
clear_logs=true
(default) in v0.4.0 filters historical logs based on timestamp, but it is still recommended to use
page_data
as the final verification standard.

CDP 日志噪音过滤

CDP Log Noise Filtering

以下日志来源属于开发工具内部噪音，不代表应用错误，应在判断时排除：

source 前缀	说明	处理
`devtools://devtools/`	开发者工具自身的断言/警告	忽略
`ide:///extensions/`	IDE 扩展注入的提醒	区分对待

以下 message 模式属于框架级提醒，非应用错误：

message 模式	说明
`console.assert`	devtools 内部断言
`SharedArrayBufferIssue`	浏览器引擎警告
`getSystemInfo API 提示`	废弃 API 迁移提醒
`wx.saveFile 即将废弃` / `wx.removeSavedFile 即将废弃`	框架 API 废弃预警
`[Component] property "xxx" received type-uncompatible value`	组件属性类型不匹配警告

判断原则：CDP 的 errors/warnings 计数可能被上述噪音抬高，导致误判。始终以
page_data
返回的实际数据作为最终验证标准。

The following log sources are internal noise of the developer tools and do not represent application errors, should be excluded when judging:

source Prefix	Description	Handling
`devtools://devtools/`	Assertions/warnings from the developer tool itself	Ignore
`ide:///extensions/`	Reminders injected by IDE extensions	Treat differently

The following message patterns are framework-level reminders, not application errors:

message Pattern	Description
`console.assert`	Internal assertions of devtools
`SharedArrayBufferIssue`	Browser engine warning
`getSystemInfo API prompt`	Deprecated API migration reminder
`wx.saveFile will be deprecated` / `wx.removeSavedFile will be deprecated`	Framework API deprecation warning
`[Component] property "xxx" received type-uncompatible value`	Component property type mismatch warning

Judgment Principle: The errors/warnings count in CDP may be inflated by the above noise, leading to misjudgment. Always use the actual data returned by
page_data
as the final verification standard.

page_data 使用注意事项

page_data Notes

必须校验 path 字段：返回的
```
data.path
```
表示当前实际页面，如果与导航目标不一致，说明页面跳转失败或被重定向。
常见不一致原因：
- 用户未登录，页面拦截跳转到登录/欢迎页
- 云函数调用失败（AppID undefined），页面 fallback 到首页
- page_path 拼写错误，navigate 静默失败（返回 success: true）
- 页面 onLoad 中有条件跳转逻辑

推荐模式：

wechat_navigate(page_path='pages/xxx/index', wait_ms=3000)
wechat_automator(action='page_data')
  ↳ data.path !== 'pages/xxx/index' → 页面未正确加载
  ↳ 用 page_stack 查看完整页面栈，定位重定向原因

Must verify the path field: The returned
```
data.path
```
represents the current actual page. If it does not match the navigation target, it means the page navigation failed or was redirected.
Common reasons for inconsistency:
- User not logged in, page intercepts and redirects to login/welcome page
- Cloud function call failed (AppID undefined), page falls back to homepage
- page_path spelling error, navigate fails silently (returns success: true)
- Conditional navigation logic exists in page onLoad

Recommended Pattern:

wechat_navigate(page_path='pages/xxx/index', wait_ms=3000)
wechat_automator(action='page_data')
  ↳ data.path !== 'pages/xxx/index' → Page not loaded correctly
  ↳ Use page_stack to view complete page stack, locate redirection reason

返回值格式

Return Value Format

json

{"success": true,  "data": {...}, "message": "操作描述"}
{"success": false, "error_code": "CLI_TIMEOUT", "message": "...", "hint": "修复提示"}
{"success": false, "error_code": "UNKNOWN_ERROR", "message": "小程序启动阶段检测到 N 个错误...", "hint": "...", "startup_errors": [...], "cdp_summary": {...}}

error_code	含义	处理
`PARAM_MISSING`	必填参数缺失	查看 hint 字段
`CLI_NOT_FOUND`	找不到 CLI	检查 `WECHAT_DEVTOOLS_CLI`
`PROJECT_PATH_MISSING`	项目路径未配置	检查 `WECHAT_PROJECT_PATH`
`NODE_NOT_FOUND`	Node.js 未安装	安装 Node.js ≥ 8.0
`CLI_TIMEOUT`	CLI 执行超时	开启服务端口；重启 IDE

json

{"success": true,  "data": {...}, "message": "Operation description"}
{"success": false, "error_code": "CLI_TIMEOUT", "message": "...", "hint": "Fix hint"}
{"success": false, "error_code": "UNKNOWN_ERROR", "message": "N errors detected during mini program startup...", "hint": "...", "startup_errors": [...], "cdp_summary": {...}}

error_code	Meaning	Handling
`PARAM_MISSING`	Required parameter missing	Check hint field
`CLI_NOT_FOUND`	CLI not found	Check `WECHAT_DEVTOOLS_CLI`
`PROJECT_PATH_MISSING`	Project path not configured	Check `WECHAT_PROJECT_PATH`
`NODE_NOT_FOUND`	Node.js not installed	Install Node.js ≥ 8.0
`CLI_TIMEOUT`	CLI execution timeout	Enable service port; restart IDE

Connection Recovery Tiers

Quick Recovery (try first):

wechat_automator(action='start')                    # 仅重连
wechat_automator(action='page_data')                # 验证

Full Recovery (when quick fails):

wechat_ide(action='open', cdp_enabled=True)         # 重新打开
wechat_automator(action='start')                    # 重连
wechat_build(action='compile')                      # 重编译（自动重连 automator）
wechat_automator(action='page_data')                # 验证

Quick Recovery (try first):

wechat_automator(action='start')                    # Only reconnect
wechat_automator(action='page_data')                # Verify

Full Recovery (when quick fails):

wechat_ide(action='open', cdp_enabled=True)         # Re-open
wechat_automator(action='start')                    # Reconnect
wechat_build(action='compile')                      # Recompile (automatically reconnects automator)
wechat_automator(action='page_data')                # Verify

故障速查

Troubleshooting Quick Reference

症状	原因	解决
CDP 采集失败（9222 无响应）	IDE 未用 cdp_enabled 启动	`wechat_ide(action='open', cdp_enabled=True)` 重启
截图空白 / 尺寸 0	automator 未启动或页面未渲染	确认 `start` 已调用；增加 `wait_ms=3000`
`Page is not found`	page_path 拼写错 / 未注册	`wechat_file(action='list_pages')` 核查
`Element is obfuscated`	元素被遮挡或在 shadow-root 外	检查 WXML 结构，尝试父节点
`Cannot find context`	逻辑层崩溃 / 正在重载	等待 3s 后重试
`CLI_TIMEOUT`	服务端口未开启 / IDE 未运行	开启服务端口； `wechat_ide(action='open')`
元素未找到	不在当前页面或 selector 错	`page_stack` 确认页面； `element_info` 验证 selector
`Using AppID: undefined`	project_path 指向子目录而非项目根目录	改为包含 `project.config.json` 的目录
`appid missing` 云函数失败	AppID 未配置或未登录	检查 project_path + 登录状态
`Connection closed` 截图/操作失败	automator WS 连接断开（v0.9.0 daemon 架构下极少出现）	先快速恢复（仅 `start` → `page_data` ）；失败再完整恢复（见 Recovery Tiers）
`Failed connecting to ws://localhost:9420`	automator 未启动或已断开	同上
navigate 返回 success 但页面未跳转	page_path 不存在或拼写错误	`list_pages` 确认路径；用 `page_stack` 验证
page_data.path 与 navigate 目标不一致	页面被重定向（未登录/参数错/云函数失败）	检查 AppID、登录状态、页面 onLoad 逻辑
CDP errors 计数含 console.assert	devtools 内部噪音	过滤 `devtools://` 来源，以 page_data 为准
子页面数据与主页面不一致	子页面使用独立数据获取链路	用 `evaluate` 直接调用 API 对比返回值
长图截图底部导航栏重复出现	固定区域检测失败（已在 v0.5.0 修复）	升级到最新版本；如仍复现请反馈
`open` 返回 startup_errors	小程序启动阶段有致命错误（页面无法显示）	根据 `startup_errors` 中的错误详情修复代码，修复后重新 `open`
`simulator not found` / `subPackages of undefined`	IDE 冷启动瞬态错误，运行时尚未就绪	忽略，继续执行 compile 刷新即可
compile 成功但 IDE 显示红色 WXML 错误	WXML 编译错误走 IDE 内部通道	检查中文引号 `""` 、未关闭标签；查看 `wxml_errors` 字段
`currentPageTimeout is not defined`	wechat_navigate 内部变量作用域 bug（v0.7.0 已修复）	升级到 v0.7.0；或改用 evaluate + wx.reLaunch
compile_condition 入口页被覆盖	app 路由守卫覆盖编译入口	编译默认页，evaluate(wx.reLaunch) 跳转
switchTab ok 但未切换	switchTab 异步未完成	增加 wait_ms；v0.8.0 navigate 已自动处理 TabBar 页面
evaluate 报 `Unexpected token 'const'`	v0.6.0 仅支持表达式（v0.7.0 已修复）	升级到 v0.7.0；或用 IIFE 包裹
截图看不到弹窗/蒙层	fixed/absolute overlay 不在同一渲染层	以 page_data 为准
call_method 报 `page.xxx not exists` 且无页面信息	v0.6.0 未返回路径（v0.7.0 已修复）	升级到 v0.7.0；或先 page_data 确认 path
navigate TabBar 页面无效	TabBar 页面不支持 reLaunch/navigateTo	v0.8.0 自动检测并使用 switchTab；或手动 `evaluate(wx.switchTab)`
截图显示错误页面	screenshot connect 后页面被重置	使用 `page_path` 参数确保截图前在正确页面
scroll-view 页面长图只有一屏	automator SDK 无法捕获 scroll-view 内部滚动	已知限制，返回 `isScrollViewPage: true` ；改用页面级滚动或 canvas 截图

Symptom	Cause	Solution
CDP collection failed (port 9222 unresponsive)	IDE not started with cdp_enabled	Restart with `wechat_ide(action='open', cdp_enabled=True)`
Blank screenshot / size 0	automator not started or page not rendered	Confirm `start` has been called; increase `wait_ms=3000`
`Page is not found`	page_path spelled incorrectly / not registered	Verify with `wechat_file(action='list_pages')`
`Element is obfuscated`	Element blocked or outside shadow-root	Check WXML structure, try parent node
`Cannot find context`	Logic layer crashed / reloading	Retry after waiting 3s
`CLI_TIMEOUT`	Service port not enabled / IDE not running	Enable service port; `wechat_ide(action='open')`
Element not found	Not on current page or selector wrong	Confirm page with `page_stack` ; verify selector with `element_info`
`Using AppID: undefined`	project_path points to subdirectory instead of project root	Change to directory containing `project.config.json`
`appid missing` cloud function failed	AppID not configured or not logged in	Check project_path + login status
`Connection closed` screenshot/operation failed	automator WS connection disconnected (rare under v0.9.0 daemon architecture)	First perform quick recovery (only `start` → `page_data` ); if failed, perform full recovery (see Recovery Tiers)
`Failed connecting to ws://localhost:9420`	automator not started or disconnected	Same as above
navigate returns success but page not navigated	page_path does not exist or spelled incorrectly	Confirm path with `list_pages` ; verify with `page_stack`
page_data.path does not match navigate target	Page redirected (not logged in/parameter error/cloud function failed)	Check AppID, login status, page onLoad logic
CDP errors count includes console.assert	devtools internal noise	Filter `devtools://` sources, rely on page_data
Subpage data inconsistent with main page	Subpage uses independent data acquisition link	Use `evaluate` to directly call API for comparison
Bottom navigation bar repeated in long screenshot	Fixed area detection failed (fixed in v0.5.0)	Upgrade to latest version; feedback if still reproducible
`open` returns startup_errors	Fatal error during mini program startup (page cannot be displayed)	Fix code according to error details in `startup_errors` , re-open after fix
`simulator not found` / `subPackages of undefined`	Transient error during IDE cold start, not ready yet	Ignore, continue to execute compile to refresh
compile succeeds but IDE shows red WXML error	WXML compilation errors go through IDE internal channel	Check Chinese quotes `""` , unclosed tags; check `wxml_errors` field
`currentPageTimeout is not defined`	Internal variable scope bug in wechat_navigate (fixed in v0.7.0)	Upgrade to v0.7.0; or use evaluate + wx.reLaunch
compile_condition entry page overridden	App route guard overrides compilation entry	Compile default page, navigate with evaluate(wx.reLaunch)
switchTab ok but not switched	switchTab not completed asynchronously	Increase wait_ms; v0.8.0 navigate automatically handles TabBar pages
evaluate reports `Unexpected token 'const'`	v0.6.0 only supports expressions (fixed in v0.7.0)	Upgrade to v0.7.0; or wrap with IIFE
Pop-ups/masks not visible in screenshot	fixed/absolute overlay not in same rendering layer	Rely on page_data
call_method reports `page.xxx not exists` and no page info	v0.6.0 does not return path (fixed in v0.7.0)	Upgrade to v0.7.0; or confirm path with page_data first
navigate to TabBar page ineffective	TabBar pages do not support reLaunch/navigateTo	v0.8.0 automatically detects and uses switchTab; or manually `evaluate(wx.switchTab)`
Screenshot shows wrong page	Page reset after screenshot connection	Use `page_path` parameter to ensure being on correct page before screenshot
Long screenshot of scroll-view page only shows one screen	automator SDK cannot capture internal scroll of scroll-view	Known limitation, returns `isScrollViewPage: true` ; use page-level scrolling or canvas screenshot instead

连接断开恢复流程

Connection Disconnection Recovery Process

当截图或自动化操作报

Connection closed

或

ws://localhost:9420

连接失败时，执行以下标准恢复流程：

wechat_ide(action='open', project_path='...', cdp_enabled=true)   # ① 重新打开项目
wechat_automator(action='start', project_path='...')               # ② 重启 automator
wechat_build(action='compile', project_path='...')                 # ③ 重新编译

When screenshot or automation operation reports

Connection closed

ws://localhost:9420

connection failure, execute the following standard recovery process:

wechat_ide(action='open', project_path='...', cdp_enabled=true)   # ① Re-open project
wechat_automator(action='start', project_path='...')               # ② Restart automator
wechat_build(action='compile', project_path='...')                 # ③ Recompile

④ 重试失败的操作

④ Retry the failed operation

---

---

绝对红线

Absolute Red Lines

❌
```
open
```
返回
```
startup_errors
```
后仍继续执行后续测试操作（必须先修复错误）
❌ 未确认
```
is_login: true
```
时调用
```
preview
```
/
```
upload
```
❌ 对生产项目调用
```
cache_clean(clean_type='all')
```
❌ 在
```
evaluate
```
中执行
```
eval()
```
或不安全代码
❌ 脑补运行状态——必须以 MCP 接口返回的实际数据为准
❌ 同一失败操作重试超过 3 次（应转为诊断根因）
❌ 自动化测试中使用
```
sleep
```
硬等待（用
```
wait_ms
```
或轮询
```
page_data
```
）
❌ 在 SOP 流程中主动调用截图——仅在用户明确要求或异常排查需要视觉确认时才截图
❌ 连接断开时直接走完整恢复（应先快速恢复：仅
```
start
```
→
```
page_data
```
）
❌ 没改代码就 compile（浪费时间，直接 evaluate 跳转）
❌ compile 后不验证 automator 连接（v0.8.0 自动重连，但需
```
page_data
```
确认）
❌ 使用
```
miniprogram/
```
子目录作为云开发项目的 project_path
❌ navigate 后不校验
```
page_data.path
```
是否匹配预期页面
❌ 将 CDP 日志中
```
devtools://
```
来源的
```
console.assert
```
视为应用错误
❌ 在多个并行 Agent 中同时使用
```
wechat_automator
```
（9420 端口独占）
✅
```
wechat_screenshot
```
的
```
output_path
```
可选，留空自动保存到项目
```
screenshots/
```
目录
✅ 使用任何自动化/截图功能前必须先调用
```
automator(action='start')
```
✅ 执行
```
tap
```
/
```
input
```
前先用
```
element_info
```
确认元素存在
✅
```
upload
```
前确认版本号已递增，
```
build_npm
```
已执行
✅ 关注 CDP 日志中的
```
[Violation]
```
标记（渲染阻塞/性能问题）
✅
```
compile
```
后检查 AppID 是否为 undefined
❌ WXML 属性值中使用中文引号
```
""
```
或未转义双引号（编译错误且工具无法检测）
✅ 截图/操作失败后执行
```
open
```
→
```
start
```
→
```
compile
```
恢复连接
✅ navigate 后必须通过
```
page_data
```
或
```
page_stack
```
校验当前页面路径
✅ 在跨页面测试中比对同名字段的一致性

❌ Continue executing subsequent test operations after
```
open
```
returns
```
startup_errors
```
(must fix errors first)
❌ Call
```
preview
```
/
```
upload
```
without confirming
```
is_login: true
```
❌ Call
```
cache_clean(clean_type='all')
```
on production projects
❌ Execute
```
eval()
```
or unsafe code in
```
evaluate
```
❌ Assume running status — must rely on actual data returned by MCP interfaces
❌ Retry the same failed operation more than 3 times (should switch to diagnosing root cause)
❌ Use
```
sleep
```
hard wait in automated testing (use
```
wait_ms
```
or poll
```
page_data
```
)
❌ Actively call screenshot in SOP process — only take screenshots when explicitly requested by user or visual confirmation is needed for troubleshooting
❌ Directly perform full recovery when connection is disconnected (should first perform quick recovery: only
```
start
```
→
```
page_data
```
)
❌ Compile without code changes (wastes time, directly navigate with evaluate)
❌ Do not verify automator connection after compile (v0.8.0 automatically reconnects, but need
```
page_data
```
confirmation)
❌ Use
```
miniprogram/
```
subdirectory as project_path for cloud development projects
❌ Do not verify if
```
page_data.path
```
matches expected page after navigate
❌ Treat
```
console.assert
```
from
```
devtools://
```
source in CDP logs as application errors
❌ Use
```
wechat_automator
```
in multiple parallel Agents (port 9420 is exclusive)
✅
```
output_path
```
of
```
wechat_screenshot
```
is optional, leave blank to automatically save to project
```
screenshots/
```
directory
✅ Must call
```
automator(action='start')
```
before using any automation/screenshot features
✅ Use
```
element_info
```
to confirm element exists before executing
```
tap
```
/
```
input
```
✅ Confirm version number has been incremented and
```
build_npm
```
has been executed before
```
upload
```
✅ Pay attention to
```
[Violation]
```
marks in CDP logs (render blocking/performance issues)
✅ Check if AppID is undefined after
```
compile
```
❌ Use Chinese quotes
```
""
```
or unescaped double quotes in WXML attribute values (compilation error that cannot be detected by tools)
✅ Execute
```
open
```
→
```
start
```
→
```
compile
```
to restore connection after screenshot/operation failure
✅ Must verify current page path via
```
page_data
```
or
```
page_stack
```
after navigate
✅ Compare consistency of fields with the same name in cross-page testing