原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复
Go to file
Dosion 9d17597e58
feat(autofix-pr): 完整完成回流机制 (latent bug fix + completionChecker + 内容回流) (#1240)
* fix(autofix-pr): 修复 taskId 不一致导致 monitor lock dangling

问题:createAutofixTeammate 生成 teammate UUID 作为 monitor lock 的 key,
但 registerRemoteAgentTask 内部生成的 framework taskId 是另一个 UUID。
CCR session 自然完成时框架调 clearActiveMonitor(frameworkTaskId)
guard 失败,lock 永不释放,导致后续 /autofix-pr 报 "already monitoring"。

修复(Phase 1 of remote-agent completion loop):
- monitorState 新增 updateActiveMonitor(partial) 原子更新
- callAutofixPr 在 register 后 swap lock 的 taskId 到 framework 分配的 id
- RemoteAgentTask 引入 registerCompletionHook 注册式 API(参考已有的
  registerCompletionChecker 模式),在 5 个完成路径调 runCompletionHook
- autofix-pr 命令模块自己注册 cleanup hook,避免 framework 反向依赖
  command 模块

测试:
- monitorState 新增 4 个测试(updateActiveMonitor 行为 + bug 复现/修复)
- launchAutofixPr 新增 3 个端到端回归测试(taskId swap + hook 触发 +
  subsequent launch 不报 already monitoring)

完整分析与 Phase 2/3 改造方案见
docs/features/remote-agent-completion-analysis.md。

* feat(autofix-pr): 注册 completionChecker 用 gh CLI 探测 PR 完成

Phase 2 of remote-agent completion loop。Phase 1 修了 monitor lock
dangling,但完成信号仍然只能等 CCR session 自然 archive(timing 不可
预测,且不知道 PR 究竟有没有被修好)。Phase 2 加上主动完成探测。

实现:
- 新增 prOutcomeCheck.ts(纯决策矩阵):summariseAutofixOutcome 给定
  PR 快照 + 基线 SHA 返回 completed/summary。8 个决策分支单元测试。
- 新增 prFetch.ts(spawn 层):runGhPrView 调 gh CLI,fetchPrHeadSha
  在 launch 时捕获基线 SHA,checkPrAutofixOutcome 组合两者。
- AutofixPrRemoteTaskMetadata 加 initialHeadSha?: string 字段,survive
  --resume。
- launchAutofixPr.ts 模块顶部 registerCompletionChecker('autofix-pr',
  ...),5s throttle 防 gh CLI 调用爆。callAutofixPr 启动时调
  fetchPrHeadSha 传入 metadata。

决策矩阵:
  MERGED                  → done(merged)
  CLOSED 未 merge          → done(closed without fix)
  OPEN 无 baseline        → 继续轮询
  OPEN head 未变           → 继续轮询(agent 还没 push)
  OPEN head 变 + CI pending → 继续轮询
  OPEN head 变 + CI failure → done(surface red,user 决定 retry)
  OPEN head 变 + CI success → done(clean fix)

设计:
- gh CLI 而非 Octokit:复用用户已有 auth,不引入 token 管理
- 决策与 spawn 分文件:prOutcomeCheck 纯函数易测,prFetch 单独 mock
  避免 Bun mock.module 进程级污染(已在 launchAutofixPr.test 注释说明)
- 5s throttle:framework 每 1s 轮询,gh CLI subprocess 太重不能跟上
- 失败兜底:fetchPrHeadSha/checkPrAutofixOutcome 失败均不抛,returns
  null/false,framework 继续走原路径

测试:
- prOutcomeCheck 9 个单测覆盖决策矩阵
- launchAutofixPr 5 个新测试:checker 注册 / fetchPrHeadSha 调用 /
  initialHeadSha 传 metadata / SHA 失败仍能 launch / SHA null 处理

完整方案见 docs/features/remote-agent-completion-analysis.md。

* feat(autofix-pr): 内容回流让本地模型读到 PR 修复结果

Phase 3 of remote-agent completion loop。Phase 2 注册了 completionChecker
让框架能在 PR 合并/关闭/有 push+CI 绿时主动完成 task,但 task-notification
仍然只携带 generic 文本(""${owner}/${repo}#42 merged"")。Phase 3 让本地
模型读到远端 agent 自己产出的结构化结果(commits 列表、files 列表、CI
状态、人类可读 summary)。

实现:
- 新增 extractAutofixResultFromLog (src/commands/autofix-pr/
  extractAutofixResult.ts):从 SDKMessage[] 中扫 <autofix-result> tag,
  优先 hook stdout 后 fallback assistant text,latest-wins。10 个单测。
- RemoteAgentTask 新增 registerContentExtractor 注册式 API + 私有
  enqueueRichRemoteNotification(参考 enqueueRemoteReviewNotification),
  在 3 个 generic 完成路径(archived / completionChecker / result-driven)
  先尝试 tryExtractRichContent,有内容用 rich 变体,没有走 generic。
  isRemoteReview 路径不变(它走自己的 enqueueRemoteReviewNotification)。
- launchAutofixPr.ts 模块顶部 registerContentExtractor('autofix-pr',
  extractAutofixResultFromLog)。initialMessage 加 <autofix-result> 输出
  指令(pr-number / commits-pushed / files-changed / ci-status / summary)。

设计:
- 注册式 API(同 Phase 1 hook + Phase 2 checker):framework 不反向依赖
  命令模块,所有 PR-specific 逻辑在 autofix-pr/
- latest-wins:agent 重试时只取最新 tag,旧 tag 不会污染
- truncated tag → null:开 tag 无对应闭 tag 视为不完整,走 generic
  fallback
- 跨 message 不拼接:开 tag 和闭 tag 在不同 message 视为不完整(避免
  误拼字符串)
- 字符串 content 不解析:assistant.message.content 为 string(非 block
  array)的少见路径直接 skip,不 crash

测试:
- extractAutofixResultFromLog 10 个单测(空 log / 无 tag / hook stdout /
  assistant text / hook_response subtype / 多 tag latest-wins / 截断 /
  hook 后于 assistant 的优先级 / 跨 message 不拼接 / 字符串 content
  graceful)
- launchAutofixPr 3 个新测试(extractor 注册 / initialMessage 含 tag
  schema / extractor 真实行为)

完整方案见 docs/features/remote-agent-completion-analysis.md 第 5.3 节。

* fix(autofix-pr): extractBetween 支持 latest tag 截断时回溯到更早完整对

如果远端 agent 重试时写了完整 <autofix-result> 后又开了一个被截断的
第二个 tag, 旧实现只看 lastIndexOf(open) 然后找不到 close 就返回 null,
导致前面那个完整结果被丢弃。改为从尾向首遍历所有 open tag, 返回第一个
能配对的 open/close 对。

附带:
- docs/features/remote-agent-completion-analysis.md: 9 处裸 fenced block
  补 language tag (text/http), 修复 markdownlint MD040 警告
- 同文件: 两处"三选项" → "三个选项" 符合中文量词习惯

* test(autofix-pr): 补齐 completionChecker / 边界 CI 检查覆盖率

针对 codecov patch coverage gap, 补足三块此前未走到的代码路径:

prOutcomeCheck.ts (原 96.92%, 2 lines missing):
- statusCheckRollup === undefined 路径 (与空数组分支不同, GitHub 在无
  checks 配置的 PR 上直接省略字段)
- COMPLETED 状态但 conclusion 为 null/空 的 in-flight 检查归为 pending

launchAutofixPr.ts (原 58.33%, 15 lines missing):
- registerCompletionChecker arrow body: metadata 缺失早返回 / 节流窗口内
  返回 null / completed=false 返回 null / completed=true 返回 summary /
  initialHeadSha 透传到 checkPrAutofixOutcome
- registerCompletionHook 的 if(meta) 短路两侧: 有 metadata 时清空节流条目,
  无 metadata 时仍释放 active monitor lock

所有新测试沿用现有 mock.module 与 registerXxxMock.mock.calls 拉取注册
回调的模式, 无新增依赖。prOutcomeCheck 11/11 本地通过。

* style: biome check --fix 整形 launchAutofixPr.test 新增段

---------

Co-authored-by: unraid <local@unraid.local>
Co-authored-by: Claude <noreply@anthropic.com>
2026-05-22 21:06:26 +08:00
.claude fix: 修复 anthropic 煞笔的四个 bug (#352) 2026-04-24 20:07:18 +08:00
.github chore: 复原原始的 package.json 2026-05-20 10:14:40 +08:00
.husky fix: 尝试修复 OTEL 的问题 2026-05-04 23:53:28 +08:00
.vscode chore: 添加 VSCode 推荐扩展列表并固定 Bun 运行时版本 2026-05-01 22:28:34 +08:00
docs perf: Vite 构建启用 code splitting,Bun RSS 从 966MB 降至 35MB 2026-05-21 16:36:27 +08:00
packages fix: 明确告知 agent SearchExtraTools/ExecuteExtraTool 是核心工具,已在工具列表中 2026-05-19 23:03:46 +08:00
scripts perf: Vite 构建启用 code splitting,Bun RSS 从 966MB 降至 35MB 2026-05-21 16:36:27 +08:00
spec Revert "feat: 添加 GBK 编码自动检测支持,文件读写工具透明处理非 UTF-8 文件" 2026-05-10 22:57:30 +08:00
src feat(autofix-pr): 完整完成回流机制 (latent bug fix + completionChecker + 内容回流) (#1240) 2026-05-22 21:06:26 +08:00
teach-me Fix mintlify validate errors (#367) 2026-04-26 11:07:20 +08:00
tests fix: 修复 Bun mock.module 跨文件污染导致 87 个测试失败 2026-05-11 08:50:03 +08:00
vendor style: 完成所有文件的lint 2026-05-01 21:39:30 +08:00
.dockerignore feat: 支持自托管的 remote-control-server (#214) 2026-04-09 17:40:50 +08:00
.editorconfig style: 完成所有文件的lint 2026-05-01 21:39:30 +08:00
.gitignore chore: 添加 CI 配置、codecov 和测试 mock 基础设施 2026-05-09 23:04:04 +08:00
.impeccable.md feat: ACP 协议版本 remote control (#293) 2026-04-18 21:54:22 +08:00
.mintignore fix: 修复 mintlify ignore, 修复侧边栏 2026-04-10 18:14:07 +08:00
.npmrc build: 更改构建逻辑 2026-04-19 08:45:06 +08:00
.tool-versions chore: 添加 VSCode 推荐扩展列表并固定 Bun 运行时版本 2026-05-01 22:28:34 +08:00
AGENTS.md chore: 清理仓库审计问题——修正 CLAUDE.md、删除冗余 yoga-layout、清除 621 个未使用的类型 stub (#354) 2026-04-25 08:54:18 +08:00
biome.json style: 修复所有 lint 错误,覆盖 @ant forked 代码 2026-05-01 21:49:21 +08:00
build.ts fix: 修复条件式 hook 调用导致的 "Rendered fewer hooks than expected" 错误 2026-05-08 13:17:25 +08:00
bun.lock style: 完成所有文件的lint 2026-05-01 21:39:30 +08:00
bunfig.toml feat: 搭建单元测试基础设施 — Bun test runner + 示例测试 2026-04-01 02:08:38 +08:00
CLAUDE.md perf: Vite 构建启用 code splitting,Bun RSS 从 966MB 降至 35MB 2026-05-21 16:36:27 +08:00
codecov.yml chore: 添加 CI 配置、codecov 和测试 mock 基础设施 2026-05-09 23:04:04 +08:00
contributors.svg docs: update contributors 2026-05-18 00:20:32 +00:00
DEV-LOG.md feat: 远程群控 (#243) 2026-04-11 23:22:55 +08:00
docs.json style: 完成所有文件的lint 2026-05-01 21:39:30 +08:00
Friends.md docs: 新增留影文档 2026-04-06 11:04:13 +08:00
knip.json style: 完成所有文件的lint 2026-05-01 21:39:30 +08:00
mint.json feat: 恢复 --channels 能力 (#297) 2026-04-19 10:24:34 +08:00
package.json chore: 2.6.5 2026-05-22 21:05:06 +08:00
progress.md fix: 优化压缩错误消息和自动压缩提示的可理解性 2026-05-05 07:19:19 +08:00
README_EN.md Fix mintlify validate errors (#367) 2026-04-26 11:07:20 +08:00
README.md Fix formatting in README.md links section 2026-04-28 11:53:30 +08:00
SECURITY.md Create SECURITY.md 2026-04-01 08:54:08 +08:00
tsconfig.base.json feat: 重构供应商层次 (#286) 2026-04-17 09:33:14 +08:00
tsconfig.json style: 完成所有文件的lint 2026-05-01 21:39:30 +08:00
vite.config.ts perf: Vite 构建启用 code splitting,Bun RSS 从 966MB 降至 35MB 2026-05-21 16:36:27 +08:00

Claude Code Best V5 (CCB)

GitHub Stars GitHub Contributors GitHub Issues GitHub License Last Commit Bun

Which Claude do you like? The open source one is the best.

A reverse-engineered / decompiled source restoration of Anthropic's official Claude Code CLI tool. The goal is to reproduce most of Claude Code's functionality and engineering capabilities. It's abbreviated as CCB.

Documentation (Chinese) — PR contributions welcome.

Sponsor placeholder.

  • v1: Basic runability and type checking pass
  • V2: Complete engineering infrastructure
    • Biome formatting may not be implemented first to avoid code conflicts
    • Build pipeline complete, output runnable on both Node.js and Bun
  • V3: Extensive documentation and documentation site improvements
  • V4: Large-scale test suite for improved stability
    • Buddy pet feature restored Docs
    • Auto Mode restored Docs
    • All features now configurable via environment variables instead of bun --feature
  • V5: Enterprise-grade monitoring/reporting, missing tools补全, restrictions removed
    • Removed anti-distillation code
    • Web search capability (using Bing) Docs
    • Debug mode support Docs
    • Disabled auto-updates
    • Custom Sentry error reporting support Docs
    • Custom GrowthBook support (GB is open source — configure your own feature flag platform) Docs
    • Custom login mode — configure Claude models your way
  • V6: Large-scale refactoring, full modular packaging
    • V6 will be a new branch; main branch will be archived as a historical version

I don't know how long this project will survive. Star + Fork + git clone + .zip is the safest bet.

This project updates rapidly — Opus continuously optimizes in the background, with new changes almost every few hours.

Claude has burned over $1000, out of budget, switching to GLM to continue; @zai-org GLM 5.1 is quite capable.

Quick Start

Prerequisites

Make sure you're on the latest version of Bun, otherwise you'll run into all sorts of weird bugs. Run bun upgrade!

  • Bun >= 1.3.11

Install Bun:

# Linux and macOS
curl -fsSL https://bun.sh/install | bash

# Windows (PowerShell)
powershell -c "irm bun.sh/install.ps1 | iex"

Post-installation steps:

  1. Make bun available in the current terminal

    The installer adds ~/.bun/bin to the matching shell configuration file. On macOS with the default zsh shell, you may see:

    Added "~/.bun/bin" to $PATH in "~/.zshrc"
    

    Restart the current shell as the installer suggests:

    exec /bin/zsh
    

    If you use bash, reload the bash configuration:

    source ~/.bashrc
    

    Windows PowerShell users can close and reopen PowerShell.

  2. Verify that Bun is available:

    bun --help
    bun --version
    
  3. Update to latest version (if already installed):

    bun upgrade
    
  • Standard Claude Code configuration — each provider has its own setup method

Command Execution Location

  • Bun installation and checking commands can be run from any directory: curl -fsSL https://bun.sh/install | bash, bun --help, bun --version, bun upgrade
  • Project dependency installation, development mode, and builds must be run from this repository root, the directory containing package.json.

Install

cd /path/to/claude-code
bun install

Run

# Dev mode — if you see version 888, it's working
bun run dev

# Build
bun run build

The build uses code splitting (build.ts), outputting to dist/ (entry dist/cli.js + ~450 chunk files).

The build output runs on both Bun and Node.js — you can publish to a private registry and run directly.

If you encounter a bug, please open an issue — we'll prioritize it.

First-time Setup /login

After the first run, enter /login in the REPL to access the login configuration screen. Select Anthropic Compatible to connect to third-party API-compatible services (no Anthropic account required).

Fields to fill in:

Field Description Example
Base URL API service URL https://api.example.com/v1
API Key Authentication key sk-xxx
Haiku Model Fast model ID claude-haiku-4-5-20251001
Sonnet Model Balanced model ID claude-sonnet-4-6
Opus Model High-performance model ID claude-opus-4-6
  • Tab / Shift+Tab to switch fields, Enter to confirm and move to the next, press Enter on the last field to save
  • Model fields auto-fill from current environment variables
  • Configuration saves to ~/.claude/settings.json under the env key, effective immediately

You can also edit ~/.claude/settings.json directly:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.example.com/v1",
    "ANTHROPIC_AUTH_TOKEN": "sk-xxx",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-haiku-4-5-20251001",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-4-6",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "claude-opus-4-6"
  }
}

Supports all Anthropic API-compatible services (e.g., OpenRouter, AWS Bedrock proxies, etc.) as long as the interface is compatible with the Messages API.

Feature Flags

All feature toggles are enabled via FEATURE_<FLAG_NAME>=1 environment variables, for example:

FEATURE_BUDDY=1 FEATURE_FORK_SUBAGENT=1 bun run dev

See docs/features/ for detailed descriptions of each feature. Contributions welcome.

VS Code Debugging

The TUI (REPL) mode requires a real terminal and cannot be launched directly via VS Code's launch config. Use attach mode:

Steps

  1. Start inspect server in terminal:

    bun run dev:inspect
    

    This outputs an address like ws://localhost:8888/xxxxxxxx.

  2. Attach debugger from VS Code:

    • Set breakpoints in src/ files
    • Press F5 → select "Attach to Bun (TUI debug)"

Contributors

Star History

Star History Chart

License

This project is for educational and research purposes only. All rights to Claude Code belong to Anthropic.