wtagent 0.1.0 → 0.2.0

package/README.md

@@ -1,26 +1,20 @@
 # WTAgent
 
-Use GPT Web as a local CLI agent.
+Use your web AI account as a local CLI agent.
 
-把 GPT 网页聊天变成可读写本地文件、运行本地命令的 CLI Agent。
+WTAgent connects ChatGPT, Claude, DeepSeek, Gemini, Kimi, or GLM Web to your local project: the model reasons in the browser while WTAgent reads and writes local files and runs commands on your machine.
 
-[中文](#中文) · [English](#english)
+[中文](#中文)
 
-## 中文
-
-WTAgent 把 GPT Web 连接到你的本地项目，提供类似 Codex 的命令行体验：GPT 在网页中思考，WTAgent 在本机读写文件、编译代码并运行测试。
-
-当前支持 ChatGPT Web。无需 OpenAI API Key，也不要求 ChatGPT Pro；使用的是你自己的网页账号、可用模型和额度。
-
-### 开始使用
+## Quick start
 
-需要 Node.js 20.17+ 和 Chrome/Chromium；支持 macOS、Linux 和原生 Windows，暂不支持 WSL。
+Requires Node.js 20.17+ and Chrome/Chromium. WTAgent supports macOS, Linux, and native Windows. WSL is not currently supported.
 
 ```bash
 npm install -g wtagent
 ```
 
-进入要工作的目录并启动：
+Open a working directory and start WTAgent:
 
 ```bash
 mkdir wtagent-demo
@@ -28,41 +22,50 @@ cd wtagent-demo
 wtagent
 ```
 
-启动后选择 `Pro` 或 `Current`，然后直接输入任务。如果尚未登录 ChatGPT，WTAgent 会打开专用 Chrome 并提示你登录；登录成功后任务会自动继续。
-
-例如，启动后直接在终端输入：
+ChatGPT asks you to choose `Pro` or `Current`; other providers keep or silently select their configured default. Then type a task:
 
 ```text
 $ wtagent
-you › 创建 qsort.c，实现整数快速排序。使用系统可用的 C 编译器开启警告编译，并运行测试，覆盖普通输入、重复值和空输入。
-you › 再增加一组包含负数的测试
+you › Create hello.js that writes "Hello from WTAgent" to hello.txt. Run it with Node.js and verify the result.
 ```
 
-WTAgent 会在当前目录创建代码、调用本地编译器并运行测试。任务完成后可以继续在同一个终端中对话。
+WTAgent creates the files in the current directory, runs the script locally, and checks its output. You can continue chatting in the same terminal after the task finishes.
 
-也可以在启动时直接附带任务：
+Choose a provider with `--model` (ChatGPT is the default). Supported values are `chatgpt`, `claude`, `deepseek`, `gemini`, `kimi`, and `glm`:
 
 ```bash
-wtagent "创建 qsort.c，编译并测试"
+wtagent --model claude "inspect this project and summarize its architecture"
+wtagent --model gemini "inspect this project and summarize its architecture"
 ```
 
-支持多行粘贴和 `↑` / `↓` 输入历史。使用 `Ctrl+C` 或 `Ctrl+D` 退出。
+Claude keeps the model selected by claude.ai in its browser profile; WTAgent does not override it.
+Gemini likewise keeps the model selected in its browser profile.
+
+If the provider is not signed in, WTAgent opens its dedicated Chrome profile and asks you to sign in. Each provider has an independent profile, and your task continues automatically after login.
+
+WTAgent itself does not require an API key. It uses your own web account, available models, and quota.
+
+You can also provide the first task directly:
+
+```bash
+wtagent "create hello.js, run it, and verify the output"
+```
 
-## English
+Multiline paste and `↑` / `↓` input history are supported. Press `Ctrl+C` or `Ctrl+D` to exit.
 
-WTAgent connects GPT Web to your local project and provides a Codex-like CLI experience: GPT reasons in the browser while WTAgent reads and writes files, compiles code, and runs tests on your machine.
+## 中文
 
-The current adapter supports ChatGPT Web. No OpenAI API key or ChatGPT Pro subscription is required; WTAgent uses your own web account, available models, and quota.
+WTAgent 将 ChatGPT、Claude、DeepSeek、Gemini、Kimi 或 GLM 网页聊天连接到本地项目：模型在浏览器中思考，WTAgent 在你的电脑上读写本地文件并运行命令。
 
-### Get started
+### 快速开始
 
-Requires Node.js 20.17+ and Chrome/Chromium. macOS, Linux, and native Windows are supported; WSL is not currently supported.
+需要 Node.js 20.17+ 和 Chrome/Chromium。支持 macOS、Linux 和原生 Windows，暂不支持 WSL。
 
 ```bash
 npm install -g wtagent
 ```
 
-Open a working directory and start WTAgent:
+进入工作目录并启动：
 
 ```bash
 mkdir wtagent-demo
@@ -70,25 +73,36 @@ cd wtagent-demo
 wtagent
 ```
 
-Choose `Pro` or `Current`, then type a task. If ChatGPT is not signed in, WTAgent opens its dedicated Chrome profile and asks you to sign in. The task continues automatically after login.
-
-For example, start it and type directly in the terminal:
+ChatGPT 会让你选择 `Pro` 或 `Current`；其他 provider 会保持或自动选择配置的默认模式。然后直接输入任务：
 
 ```text
 $ wtagent
-you › Create qsort.c with an integer quicksort. Compile it with warnings using an available C compiler, then test normal input, duplicate values, and empty input.
-you › Add another test containing negative numbers.
+you › 创建 hello.js，将“Hello from WTAgent”写入 hello.txt。用 Node.js 运行并验证结果。
 ```
 
-WTAgent creates the code in the current directory, invokes the local compiler, and runs the tests. Keep chatting in the same terminal after the task finishes.
+WTAgent 会在当前目录创建文件、运行本地脚本并检查输出。任务完成后，可以继续在同一个终端中对话。
 
-You can also provide the first task directly:
+通过 `--model` 选择 provider（默认是 ChatGPT）。可选值包括 `chatgpt`、`claude`、`deepseek`、`gemini`、`kimi` 和 `glm`：
 
 ```bash
-wtagent "create qsort.c, compile it, and test it"
+wtagent --model claude "分析这个项目并总结架构"
+wtagent --model gemini "分析这个项目并总结架构"
 ```
 
-Multiline paste and `↑` / `↓` input history are supported. Press `Ctrl+C` or `Ctrl+D` to exit.
+Claude 会沿用 claude.ai 在该浏览器 Profile 中选择的模型，WTAgent 不会自动切换模型。
+Gemini 同样沿用其浏览器 Profile 当前选择的模型。
+
+如果尚未登录对应 provider，WTAgent 会打开它的独立专用 Chrome Profile 并提示登录；登录成功后任务会自动继续。
+
+WTAgent 本身无需 API Key，而是使用你自己的网页账号、可用模型和额度。
+
+也可以在启动时直接附带第一个任务：
+
+```bash
+wtagent "创建 hello.js，运行并验证输出"
+```
+
+支持多行粘贴和 `↑` / `↓` 输入历史。使用 `Ctrl+C` 或 `Ctrl+D` 退出。
 
 ## License
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wtagent",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "Turn your own web AI session into a local tool-using agent.",
   "repository": {
     "type": "git",
@@ -30,7 +30,7 @@
   ],
   "scripts": {
     "test": "node --test",
-    "test:unit": "node --test test/protocol.test.js test/policy.test.js test/tools.test.js test/prompt-builder.test.js test/session-export.test.js test/platform.test.js test/cli.test.js test/at-files.test.js",
+    "test:unit": "node --test test/protocol.test.js test/policy.test.js test/tools.test.js test/prompt-builder.test.js test/session-export.test.js test/platform.test.js test/cli.test.js test/at-files.test.js test/self-update.test.js test/startup-notices.test.js test/provider-registry.test.js test/claude-adapter.test.js test/deepseek-adapter.test.js test/gemini-adapter.test.js test/kimi-adapter.test.js test/glm-adapter.test.js",
     "test:integration": "node --test test/runtime.test.js",
     "test:windows": "node --test test/windows-command-launcher.test.js test/windows-diagnostics.test.js test/windows-search-path.test.js test/atomic-write.test.js test/process-utils.test.js test/cdp-state.test.js test/windows-fixtures.test.js test/windows-package-smoke.test.js",
     "check": "node scripts/check-syntax.js",