桌面端的工作区文件面板现在可以把文件或局部评论加入聊天,发送给 CLI 的内容保持为原生 @文件路径引用,聊天界面则保留用户可读的文件 chip。为了让本轮变更卡片和 checkpoint 回滚继续可靠,UI 消息会同时保存用于展示的内容和实际发给模型的 modelContent;历史转录里的 @文件路径也会在重载时还原成附件 chip。 Constraint: CLI 侧最稳定的文件上下文入口仍是原生 @文件路径 Constraint: 聊天 UI 不能把绝对路径裸露成用户消息正文 Rejected: 只发送隐藏提示文本 | CLI 对 @文件路径已有稳定读取行为 Rejected: 只依赖前端展示内容做回滚校验 | 会和真实转录内容不一致 Confidence: high Scope-risk: moderate Directive: 修改附件展示或回滚校验时必须同时验证 modelContent 与 UI content 的分离 Tested: cd desktop && bun run test -- src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx src/stores/workspaceChatContextStore.test.ts src/components/workspace/WorkspacePanel.test.tsx Tested: cd desktop && bun run lint Tested: cd desktop && bun run build Tested: SKIP_INSTALL=1 ./desktop/scripts/build-macos-arm64.sh Tested: codesign --verify --deep --strict --verbose=2 desktop/build-artifacts/macos-arm64/Claude\ Code\ Haha.app Tested: hdiutil verify desktop/build-artifacts/macos-arm64/Claude\ Code\ Haha_0.1.8_aarch64.dmg Tested: Computer Use macOS run with /private/tmp/cc-haha-computer-use-e2e verified file chip, @path model input, model sentinel response, workspace preview interactions Not-tested: Deep unloaded-folder fuzzy search in all-files view
Claude Code Haha
A locally runnable version repaired from the leaked Claude Code source, with support for any Anthropic-compatible API endpoint (MiniMax, OpenRouter, etc.). Beyond the full TUI, we've also completed Computer Use (macOS / Windows), built a GUI desktop app, and enabled full remote control via Telegram / Feishu.
Features · Desktop · Architecture · Quick Start · Env Vars · FAQ · Global Usage · More Docs
Features
- Full Ink TUI experience (matching the official Claude Code interface)
--printheadless mode for scripts and CI- MCP server, plugin, and Skills support
- Custom API endpoint and model support (Third-Party Models Guide)
- Memory System (cross-session persistent memory) — Usage Guide
- Multi-Agent System (agent orchestration, parallel tasks, Teams collaboration) — Usage Guide | Implementation
- Skills System (extensible capability plugins, custom workflows) — Usage Guide | Implementation
- Channel System (remote Agent control via Telegram/Feishu/Discord IM platforms) — Architecture
- Computer Use desktop control — Guide | Architecture
- Desktop App (Tauri 2 + React GUI client, multi-tab multi-session) — Docs
- Fallback Recovery CLI mode (
CLAUDE_CODE_FORCE_RECOVERY_CLI=1 ./bin/claude-haha)
Architecture Overview
![]() Overall architecture |
![]() Request lifecycle |
![]() Tool system |
![]() Multi-agent architecture |
![]() Terminal UI |
![]() Permissions and security |
![]() Services layer |
![]() State and data flow |
Desktop Preview
![]() Main Interface |
![]() Code Editing & Diff View |
![]() Permission Control & AI Questions |
![]() Multi-Provider Management |
![]() Scheduled Tasks |
![]() IM Adapters (Telegram / Feishu) |
Quick Start
1. Install Bun
# macOS / Linux
curl -fsSL https://bun.sh/install | bash
# macOS (Homebrew)
brew install bun
# Windows (PowerShell)
powershell -c "irm bun.sh/install.ps1 | iex"
On minimal Linux images, if you see
unzip is required, runapt update && apt install -y unzipfirst.
2. Install Dependencies and Configure
bun install
cp .env.example .env
# Edit .env with your API key — see docs/en/guide/env-vars.md for details
3. Start
macOS / Linux
./bin/claude-haha # Interactive TUI mode
./bin/claude-haha -p "your prompt here" # Headless mode
./bin/claude-haha --help # Show all options
Windows
Prerequisite: Git for Windows must be installed.
# PowerShell / cmd — call Bun directly
bun --env-file=.env ./src/entrypoints/cli.tsx
# Or run inside Git Bash
./bin/claude-haha
4. Global Usage (Optional)
Add bin/ to your PATH to run from any directory. See Global Usage Guide:
export PATH="$HOME/path/to/claude-code-haha/bin:$PATH"
5. Desktop Development
If you are developing or testing the desktop/ frontend, start both the API server and the desktop frontend.
5.1 Start the API server
cd /Users/nanmi/workspace/myself_code/claude-code-haha
SERVER_PORT=3456 bun run src/server/index.ts
Optional health check:
curl http://127.0.0.1:3456/health
5.2 Start the desktop frontend
cd /Users/nanmi/workspace/myself_code/claude-code-haha/desktop
bun run dev --host 127.0.0.1 --port 2024
Then open:
http://127.0.0.1:2024
5.3 Notes
- If port
3456is already occupied by an old server process, runlsof -nP -iTCP:3456 -sTCP:LISTEN, find the PID, thenkill <PID>. - For chat testing, create a fresh session and re-select a real working directory.
- If an old session points to a deleted directory, the server will return
Working directory does not exist. That is separate from whether the API server is running.
Tech Stack
| Category | Technology |
|---|---|
| Runtime | Bun |
| Language | TypeScript |
| Terminal UI | React + Ink |
| CLI parsing | Commander.js |
| API | Anthropic SDK |
| Protocols | MCP, LSP |
More Documentation
| Document | Description |
|---|---|
| Environment Variables | Full env var reference and configuration methods |
| Third-Party Models | Using OpenAI / DeepSeek / Ollama and other non-Anthropic models |
| Memory System | Cross-session persistent memory usage and implementation |
| Multi-Agent System | Agent orchestration, parallel tasks and Teams collaboration |
| Skills System | Extensible capability plugins, custom workflows and conditional activation |
| Channel System | Remote Agent control via Telegram/Feishu/Discord IM platforms |
| Computer Use | Desktop control (screenshots, mouse, keyboard) — Architecture |
| Desktop App | Tauri 2 + React GUI client — Quick Start | Architecture | Installation |
| Global Usage | Run claude-haha from any directory |
| FAQ | Common error troubleshooting |
| Source Fixes | Fixes compared with the original leaked source |
| Project Structure | Code directory structure |
Sponsorship & Partnership
This project is maintained in the author's spare time. Corporate or individual sponsorships are welcome to support ongoing development. Custom features, integrations, and business partnerships are also open for discussion.
| Sponsor | Description |
|---|---|
|
接口AI |
Thanks to JieKou AI for sponsoring this project. JieKou AI provides official model resources with stable, high-performance API access. Subscription bundles are priced at 20% off the official rate; new users who register through this link and bind GitHub can claim a $3 coupon. |
|
|
Thanks to ShengSuanYun for sponsoring this project. ShengSuanYun is an industrial-grade AI task parallel execution platform for AI Native Teams, aggregating Claude, ChatGPT, Gemini, and other LLM, image, and video model capacity through direct, non-reverse-engineered access. Its platform SLA reaches 99.7%, with service status available online. It also supports dedicated enterprise gateways, cost and permission controls, smart routing, security protection, BYOK, usage-based billing, upcoming tokens plans, and invoicing. New users registering through this link can receive 10 yuan in model credits plus a 10% first top-up bonus. |
📧 Contact: relakkes@gmail.com
☕ Buy Me a Coffee
If this project helps you, consider buying me a coffee — every bit of support keeps this project going ❤️
![]() WeChat Pay |
![]() Alipay |
Buy Me a Coffee |
Thanks
Thanks to the following open-source projects and community practices for reference and inspiration:
- React: frontend engineering and component-based UI ecosystem.
- Tauri: cross-platform desktop app capabilities and engineering practices.
- cc-switch: reference for model provider configuration.
Disclaimer
This repository is based on the Claude Code source leaked from the Anthropic npm registry on 2026-03-31. All original source code copyrights belong to Anthropic. It is provided for learning and research purposes only.
















