程序员阿江(Relakkes) 6e5dd94dad Stop bearer providers from inheriting local API keys
Desktop Anthropic-compatible relay providers use ANTHROPIC_AUTH_TOKEN for
Authorization, but the CLI process can still load a stale ANTHROPIC_API_KEY
from inherited env, original settings, keychain-backed config, or the SDK
constructor fallback. That made Provider Test pass while real sessions sent
both Authorization and x-api-key to relays such as Packy and Shengsuanyun,
which then rejected the request as an invalid token/key.

The client now avoids falling back to a local API key when bearer-token
provider auth is active. Provider-managed auth_token env also writes an empty
ANTHROPIC_API_KEY so cc-haha settings explicitly override stale original
settings during desktop/sidecar startup. Regression tests pin both the SDK
client behavior and the desktop child-env behavior.

Constraint: Anthropic-compatible relay providers can reject mixed Authorization plus x-api-key headers even when direct provider tests pass
Rejected: Treat this as a provider/model-name issue | local proxy captures showed the failing request shape before provider handling
Rejected: Rely only on client.ts fallback suppression | settings/env layering can leave ANTHROPIC_API_KEY populated before the client is constructed
Confidence: high
Scope-risk: moderate
Directive: Bearer-token provider sessions must keep Authorization without inheriting or reintroducing x-api-key from user/global settings
Tested: bun test src/services/api/client.test.ts
Tested: bun test src/server/__tests__/providers.test.ts src/server/__tests__/providers-real.test.ts src/server/__tests__/conversation-service.test.ts
Tested: bun run check:server
Tested: Source and packaged sidecar proxy captures with stale original ANTHROPIC_API_KEY showed Authorization=true and x-api-key=false after the fix
Tested: desktop/scripts/build-macos-arm64.sh
Tested: PackyCodex2ccCustom and 胜算云 packaged-sidecar live calls returned ok
Not-tested: Full manual UI click-through in the rebuilt macOS app window
2026-05-08 15:20:45 +08:00
2026-04-01 10:30:17 +08:00

Claude Code Haha

Claude Code Haha

GitHub Stars GitHub Forks GitHub Issues GitHub Pull Requests License 中文 English Docs

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 / WeChat / DingTalk.

Desktop · Features · Architecture · Quick Start · Env Vars · FAQ · Global Usage · More Docs


Desktop Preview

The Claude Code Haha desktop app brings sessions, multi-project navigation, code diffs, permission review, provider setup, scheduled tasks, and IM adapters into one graphical workspace for daily development flows beyond the terminal.

Download Desktop   Install Guide

Main UI
Main Interface
Code Editing
Code Editing & Diff View
Permission Control
Permission Control & AI Questions
Provider Settings
Multi-Provider Management
Scheduled Tasks
Scheduled Tasks
IM Adapters
IM Adapters (Telegram / Feishu / WeChat / DingTalk)

Features

  • Full Ink TUI experience (matching the official Claude Code interface)
  • --print headless 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
  • IM Integration (remote chat, project switching, and permission approval via Telegram / Feishu / WeChat / DingTalk) — Guide
  • Computer Use desktop controlGuide | 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
Overall architecture
Request lifecycle
Request lifecycle
Tool system
Tool system
Multi-agent architecture
Multi-agent architecture
Terminal UI
Terminal UI
Permissions and security
Permissions and security
Services layer
Services layer
State and data flow
State and data flow

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, run apt update && apt install -y unzip first.

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 3456 is already occupied by an old server process, run lsof -nP -iTCP:3456 -sTCP:LISTEN, find the PID, then kill <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.

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
JieKou AI
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.
ShengSuanYun 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
WeChat Pay
Alipay
Alipay
Buy Me a Coffee
Buy Me a Coffee

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
Contributing Local tests, live model baselines, PR gates, and release gates
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
IM Integration Remote chat, project switching, and permission approval via Telegram / Feishu / WeChat / DingTalk
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

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.

Star History

If this project helps you, please support it with a Star so more people can discover Claude Code Haha.

Star History Chart

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.

Description
Claude Code 本地可运行版本 - mirror from GitHub
Readme 519 MiB
Languages
TypeScript 99.1%
Rust 0.2%
Shell 0.2%
Python 0.2%
PowerShell 0.1%
Other 0.1%