openclacky 1.1.2 → 1.1.3

data/docs/HOW-TO-USE.md

@@ -1,94 +0,0 @@
-# How to Use OpenClacky
-
-## Installation
-
-```bash
-gem install openclacky
-```
-
-**Requirements:** Ruby >= 3.1
-
-## Quick Start
-
-### 1. Start Clacky
-
-```bash
-clacky
-```
-
-### 2. Configure API Key (First Time)
-
-In the chat interface, type:
-
-```
-/config
-```
-
-Then follow the prompts to set your API key:
-- **OpenAI**: Get key from https://platform.openai.com/api-keys
-- **Anthropic**: Get key from https://console.anthropic.com/
-
-### 3. Start Chatting
-
-Just type your questions or requests in the chat:
-
-```
-Help me write a Ruby script to parse CSV files
-```
-
-```
-Create a web scraper for extracting article titles
-```
-
-## Key Features
-
-### 🎯 Autonomous Agent Mode
-Clacky can automatically execute complex tasks using built-in tools:
-- **File Operations**: Read, write, edit, search files
-- **Web Access**: Browse and search the web
-- **Code Execution**: Run shell commands and test code
-- **Project Management**: Git operations, testing, deployment
-
-### 🔌 Skill System
-Use powerful skills with simple shorthand commands:
-
-```
-/commit          # Smart git commit helper
-/gem-release     # Automated gem publishing
-```
-
-Create your own skills in `.clacky/skills/` directory!
-
-### 💬 Smart Memory Management
-- **Automatic compression** for long conversations
-- **Context preservation** while reducing token costs
-- **Intelligent summarization** of conversation history
-
-### ⚙️ Easy Configuration
-- Interactive setup wizard
-- Support for multiple API providers
-- Cost tracking and usage limits
-- Smart defaults for common use cases
-
-## Common Commands in Chat
-
-```
-/config          # Configure API settings
-/help            # Show available commands
-/skills          # List available skills
-```
-
-## Why Choose OpenClacky?
-
-✅ **Simple Setup** - Just `gem install` and start chatting  
-✅ **Powerful Agent** - Executes complex tasks autonomously  
-✅ **Extensible** - Create custom skills for your workflows  
-✅ **Cost-Effective** - Smart memory compression saves tokens  
-✅ **Multi-Provider** - Works with OpenAI and Anthropic  
-✅ **Well-Tested** - 367+ passing tests ensure reliability  
-
-## Learn More
-
-- GitHub: https://github.com/clacky-ai/openclacky
-- Report Issues: https://github.com/clacky-ai/openclacky/issues
-- Version: 0.7.0

data/docs/browser-cdp-native-design.md

@@ -1,195 +0,0 @@
-# Browser Tool: Native CDP Integration Design
-
-## 背景与目标
-
-现有的 browser tool 依赖 `agent-browser`（Rust 二进制，通过 npm 分发），每次使用都启动一个独立的 Chrome 实例，存在以下问题：
-
-- 用户登录态、Cookie 无法复用
-- 需要额外安装 npm / agent-browser
-- 每次任务弹出新 Chrome 窗口，体验差
-- 依赖链长：npm → agent-browser binary → Chrome for Testing
-
-**核心目标**：Clacky 直接复用用户已打开的 Chrome，继承所有登录态和 Cookie，零额外依赖。
-
----
-
-## Chrome 146 的关键变化
-
-### 时间线
-
-| Chrome 版本 | 行为 |
-|------------|------|
-| ≤ 135 | `--remote-debugging-port` 可连接 default profile（不推荐但能用）|
-| 136 ~ 145 | Default profile 被封锁，必须用 `--user-data-dir` 开隔离 profile（空的，无登录态）|
-| **146+** | 新增 **autoConnect toggle**，一次开关，直接连真实浏览器，Consent-based ✅ |
-
-### 用户操作（一次性）
-
-1. 打开 `chrome://inspect/#remote-debugging`
-2. 勾选 **"Allow remote debugging for this browser instance"**
-3. Chrome 在 `127.0.0.1:9222` 启动 CDP server
-
-之后每次 Clacky 连接时，Chrome 会弹一次 **"Allow remote debugging?"** 权限确认框，用户点 Allow 即可。
-
----
-
-## 技术方案：纯 Ruby CDP Client
-
-### 核心发现
-
-Chrome 146 的 autoConnect 模式**不暴露标准 `/json` HTTP endpoint**（返回 404），而是通过一个文件告知连接信息：
-
-```
-~/Library/Application Support/Google/Chrome/DevToolsActivePort
-```
-
-文件内容格式：
-```
-9222
-/devtools/browser/98823857-17b3-48ec-8f24-5805e3012a05
-```
-
-第一行是端口，第二行是 WebSocket path，直接拼成：
-
-```
-ws://127.0.0.1:9222/devtools/browser/98823857-17b3-48ec-8f24-5805e3012a05
-```
-
-### 连接流程
-
-```
-1. 读 DevToolsActivePort 文件
-        ↓
-2. WebSocket 连接 Browser endpoint
-        ↓
-3. Target.getTargets → 列出所有真实 tab
-        ↓
-4. Target.attachToTarget(targetId, flatten: true) → 获得 sessionId
-        ↓
-5. 通过 sessionId 发送 CDP 命令操作指定 tab
-```
-
-### 依赖
-
-**零新依赖**，只用已有的：
-- `websocket-driver`（已在 gemspec）
-- `socket`（Ruby 标准库）
-- `net/http`（Ruby 标准库）
-- `json`（Ruby 标准库）
-
-### 已验证能力
-
-实测（2026-03-20）通过脚本验证：
-
-- ✅ 读取 DevToolsActivePort，发现 9222 端口
-- ✅ WebSocket 连接 Browser endpoint
-- ✅ `Target.getTargets` 列出用户所有真实 tab（含标题、URL）
-- ✅ `Target.attachToTarget` attach 到指定 tab
-- ✅ `Runtime.evaluate` 执行 JS（获取 URL、title 等）
-- ✅ `Page.captureScreenshot` 截图
-- ✅ `Target.createTarget` 开新 tab 并导航
-- ✅ 复用用户登录态（访问 yafeilee.com/admin 直接进后台，无需重新登录）
-
----
-
-## 实施方案
-
-### 第一层：Discovery（发现层）
-
-```ruby
-# 检测 Chrome 是否开启了 remote debugging
-def discover_chrome_cdp
-  port_file = File.expand_path(
-    "~/Library/Application Support/Google/Chrome/DevToolsActivePort"
-  )
-  return nil unless File.exist?(port_file)
-
-  lines = File.read(port_file).strip.split("\n")
-  port = lines[0].to_i
-  path = lines[1]
-
-  # 验证端口确实在监听
-  TCPSocket.new("127.0.0.1", port).close
-  { port: port, path: path, ws_url: "ws://127.0.0.1:#{port}#{path}" }
-rescue Errno::ECONNREFUSED
-  nil
-end
-```
-
-**没有发现时的引导**：
-
-> "请在 Chrome 地址栏打开 `chrome://inspect/#remote-debugging`，
-> 勾选 'Allow remote debugging for this browser instance'，只需一次。"
-
-### 第二层：CDP Client（通信层）
-
-新建 `lib/clacky/tools/cdp_client.rb`，实现：
-
-- WebSocket 连接管理
-- 命令发送（带 id）/ 响应匹配
-- Session 管理（Browser-level vs Tab-level）
-- 事件监听（Page.loadEventFired 等）
-
-### 第三层：Browser Tool 改造
-
-`lib/clacky/tools/browser.rb` 改造策略：
-
-```
-优先级 1: 检测 DevToolsActivePort → 用户真实 Chrome（Native CDP）
-优先级 2: Fallback → 现有 agent-browser（向后兼容）
-```
-
-### macOS 路径（其他平台待补充）
-
-| 平台 | DevToolsActivePort 路径 |
-|------|------------------------|
-| macOS | `~/Library/Application Support/Google/Chrome/DevToolsActivePort` |
-| Linux | `~/.config/google-chrome/DevToolsActivePort` |
-| Windows | `%LOCALAPPDATA%\Google\Chrome\User Data\DevToolsActivePort` |
-
----
-
-## 关键问题与结论
-
-### Q: `/json` endpoint 返回 404，怎么办？
-
-Chrome 146 autoConnect 模式不走 HTTP `/json`，改用 `DevToolsActivePort` 文件 + 直接 WebSocket 连接。
-
-### Q: ferrum gem 是否适用？
-
-**不适用**。`Ferrum::Browser.new(url: "http://localhost:9222")` 虽然能连接到已有 Chrome，但会创建新的 incognito browser context，不复用用户的 tab 和登录态。需要绕过 ferrum，直接操作原始 CDP。
-
-### Q: 每次连接都要点 Allow？
-
-是的，Chrome 146 每次新的 WebSocket 连接都会弹确认框。这是 Chrome 的安全 consent 机制，无法绕过，但体验上是可以接受的（用户清楚地知道浏览器被控制了）。
-
-### Q: agent-browser 是否彻底废弃？
-
-建议渐进迁移：先并行运行，Native CDP 作为优先路径，agent-browser 作为 fallback，稳定后再移除。
-
----
-
-## 参考资料
-
-- [Chrome 146 autoConnect 介绍 - DEV Community](https://dev.to/minatoplanb/chrome-146-finally-lets-ai-control-your-real-browser-google-oauth-included-28b7)
-- [One Toggle That Changed Browser Automation - LinkedIn](https://www.linkedin.com/posts/surajadsul_one-toggle-that-changed-the-browser-automation-activity-7439161929664864257-0v8z)
-- [Chrome DevTools MCP 连接模式详解](https://www.heyuan110.com/posts/ai/2026-03-17-chrome-devtools-mcp-guide/)
-- [agent-browser #412: Support --auto-connect](https://github.com/vercel-labs/agent-browser/issues/412)
-- [Chrome DevTools Protocol 官方文档](https://chromedevtools.github.io/devtools-protocol/)
-- [DevToolsActivePort WebSocket path 说明](https://deepwiki.com/ChromeDevTools/chrome-devtools-mcp/2.3-connection-modes)
-- [ferrum issue #320: Connect to existing Chrome](https://github.com/rubycdp/ferrum/issues/320)
-- [Chrome remote-debugging security changes](https://developer.chrome.com/blog/remote-debugging-port)
-
----
-
-## 测试脚本
-
-原型验证脚本位于：`tmp/cdp_test.rb`
-
-运行前提：
-1. Chrome 已开启 remote debugging（`chrome://inspect/#remote-debugging`）
-2. 点击 Allow 弹框
-
-```bash
-bundle exec ruby tmp/cdp_test.rb
-```

data/docs/c-end-user-positioning.md

@@ -1,64 +0,0 @@
-# C-End User Positioning
-
-> Date: 2026-03-30
-
----
-
-## Market Context
-
-The "OpenClaw ecosystem" has exploded in 2026. Key players:
-
-- **OpenClaw** — open-source, self-hosted, community Skills. Designed for technical users who configure everything themselves.
-- **QClaw** — Tencent's fork. Bundled Kimi model, WeChat binding. Mass-market but Tencent-ecosystem only.
-- **Others** (Wukong, etc.) — same lane.
-
-OpenClaw has 5,700+ Skills, but almost all are open-source, free, and easily copied. The ecosystem lacks **expertise-backed, production-grade Skills worth paying for**.
-
----
-
-## Who openclacky Is For
-
-**Ordinary users, not technical geeks.**
-
-The target user knows OpenClaw exists, has heard about "raising a lobster", but can't or doesn't want to:
-- configure Docker / environment / webhooks
-- manage their own API keys without knowing what they'll spend
-- troubleshoot when a long task breaks halfway
-
-They want to use a lobster built by an expert (a lawyer, a trader, an SEO specialist) — not build one themselves.
-
-> Core insight: **OpenClaw is built for people who create Skills. openclacky is built for people who use them.**
-
----
-
-## Why openclacky Over OpenClaw: 3 Core Reasons
-
-### 1. Zero-friction IM setup — the strongest differentiator
-
-OpenClaw requires users to manually configure webhooks, tokens, and config files to connect WeChat / Feishu / WeCom. High technical barrier, most ordinary users give up.
-
-openclacky uses **AI-automated channel setup**: one sentence, and the AI configures the IM connection for you — no plugins, no docs, no engineering knowledge required. This is a genuine technical moat.
-
-### 2. Built for China, natively
-
-- No VPN required, no overseas credit card
-- WeChat / Feishu / WeCom are the primary daily tools for Chinese users — openclacky treats them as first-class citizens
-- Supports domestic models (DeepSeek, Kimi, etc.) out of the box
-- QClaw is domestic too, but locked to Tencent's ecosystem and model choices
-
-### 3. Cost transparency and long-task reliability
-
-- Real-time token cost tracking — users always know what they're spending
-- Automatic compression (up to 90% savings via Insert-then-Compress + Prompt Caching)
-- Long tasks don't break: sub-agent isolation + Time Machine architecture keeps context intact
-
----
-
-## The User Progression
-
-```
-Can use it  →  Dare to use it  →  Keep using it
-(zero setup)   (cost clarity)     (tasks don't break)
-```
-
-Each of the 3 reasons maps directly to one stage of this progression.

data/docs/config.example.yml

@@ -1,27 +0,0 @@
-# Clacky Configuration File
-# This is a top-level array of model configurations
-# The first model in the array is used as the default
-
-# Claude Sonnet 4 (default - first in array)
-- model: "claude-sonnet-4"
-  api_key: "your-api-key-here"
-  base_url: "https://api.anthropic.com"
-  anthropic_format: true
-
-# Claude Opus 4
-- model: "claude-opus-4"
-  api_key: "your-api-key-here"
-  base_url: "https://api.anthropic.com"
-  anthropic_format: true
-
-# OpenAI GPT-4
-- model: "gpt-4"
-  api_key: "your-openai-api-key-here"
-  base_url: "https://api.openai.com/v1"
-  anthropic_format: false
-
-# Custom model (e.g., local or third-party)
-- model: "custom-model"
-  api_key: "your-custom-api-key"
-  base_url: "https://your-api-endpoint.com"
-  anthropic_format: false