Session inspection was coupling quick status and usage rendering to live context control requests, so a slow get_context_usage path could leave the desktop inspector stuck on a loading state. The desktop panel now loads basic inspection data first, renders a transcript-based context estimate immediately, and only asks for live context details as a background refinement. The translation hook now returns a stable function per locale so effects that depend on translation do not reset and re-fetch after every render. Constraint: Third-party provider sessions may not expose reliable live context capabilities through the control request path. Rejected: Keep waiting on live get_context_usage for the context tab | it recreates the user-visible loading stall. Rejected: Hardcode provider-specific context windows | provider capabilities are not always known from the desktop session record. Confidence: high Scope-risk: moderate Directive: Do not make the inspector first render depend on live CLI control requests without a transcript or cached fallback. Tested: bun test src/server/__tests__/conversations.test.ts -t "structured session inspection|Sonnet 4.6 transcript usage" Tested: cd desktop && bun run test -- --run src/i18n/index.test.tsx Tested: cd desktop && bun run build Tested: git diff --check Tested: agent-browser verified /context renders transcript estimate without Loading context data Not-tested: Provider-specific true context-window discovery for every third-party vendor
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.
















