CodeWhale Bot d1990cca47 tui: delete AppMode::Auto and its CommandMode mirror
Audit slice: dead/pretender mode abstractions (item 1).

AppMode::Auto had no user spelling: parse() maps "auto" to Agent and the
variant was never in the Tab cycle (crates/config/src/app_mode.rs). Only
tests constructed it directly. Delete the variant and drop the defensive
Auto arms from every exhaustive match in codewhale-tui, plus the init
comment that explained the ghost (crates/tui/src/tui/app/init.rs).

command-contract's CommandMode::Auto existed only as the adapter mirror
of the dead variant (crates/tui/src/commands/contract.rs); remove the
mirror and its adapter arms. CommandMode has no consumers outside the
tui adapter, so the boundary shape stays otherwise untouched.

Tests updated (not weakened): the Auto assertions in app_mode helper and
base_policy_for_mode tests, the cycle_mode_reverse Auto leg, the
protocol_parity mode-label round trip, the command-contract boundary
mapping test, and the engine mode-invariant matrix "auto-compat" case
(behavior identical to the remaining "agent" case).

Gates: cargo fmt --check; nextest codewhale-tui 11909 passed;
codewhale-config 639 passed; codewhale-command-contract 29 passed;
dead-code budget PASS 425; vocabulary gate exit 0.
2026-09-02 11:43:05 -07:00

Codewhale

Codewhale is an open source coding agent for your terminal, built in Rust and improved in public with the people who use it.

Codewhale

简体中文 · 日本語 · Tiếng Việt · Bahasa Indonesia · 한국어 · Español · Português · Русский · Українська · Français · Deutsch · 繁體中文 · हिन्दी · Türkçe · Italiano · Polski · العربية · Català

CI crates.io npm Discord

A Codewhale terminal session

Install

npm install -g codewhale
codewhale

The first run helps you connect a provider or stay offline. Codewhale also supports Cargo, Docker, Nix, Scoop, prebuilt archives, Android/Termux, and a CNB mirror. See the installation guide.

Tab completion is one command per shell — codewhale completion bash|zsh|fish|powershell|elvish. See shell completions.

Use

Talk to Codewhale the same way you would talk to a teammate:

Fix the failing tests and explain what changed.

Or run a task without opening the TUI:

codewhale exec "fix the failing tests and explain what changed"

Codewhale can read your repository, edit files, run commands, inspect results, and keep working toward a goal. You decide how much access it has.

Why Codewhale

  • Use the model you want. Connect hosted providers or local models through Ollama, vLLM, or SGLang. Switch provider and model with /model.
  • Stay in control. Plan is read-only. Ask, Auto-Review, and Full Access make approval behavior visible. /undo reverts the last turn and /restore returns the workspace to an earlier snapshot.
  • Keep long work organized. Save sessions, set a durable /goal, review workflows before they run, and coordinate agents without turning their internal instructions into your transcript.
  • Extend the agent you already have. Connect MCP servers and skills, configure hooks, and keep agent roles as readable files in your project or personal settings.

Run /help in the TUI for commands and keyboard shortcuts.

Safety

Codewhale runs on your machine with the access you grant it. Approval modes and repository rules limit what the agent may do; optional OS sandboxing adds a stronger execution boundary where supported. Unknown model prices stay unknown instead of being reported as free.

Read authorization order for the exact policy stack and configuration for local settings.

Documentation

Join the community

Codewhale gets better when people use it, report what feels wrong, and help fix it. If a provider is missing, a workflow is awkward, or the terminal UI gets in your way, open an issue. If you know how to improve it, open a pull request. First contributions are welcome, and contributors keep credit for the work that lands.

Join the Discord, or add Hunter on WeChat (hunterbown) and ask to join the Whale Brothers group.

Project history

Codewhale began as deepseek-tui and still preserves that configuration and session compatibility. It is now provider-neutral and independently maintained; it is not affiliated with any model provider.

Thanks to every contributor and to the open source communities that helped the project grow. See the contributor record.

License

MIT. Portions adapted from other open-source projects are recorded in third-party notices.

Description
面向 DeepSeek V4 的终端原生编程智能体:100 万 token 上下文、思考模式流式推理、前缀缓存感知。自包含 Rust 二进制发布——开箱即带 MCP 客户端、沙箱和持久化任务队列
Readme MIT 378 MiB
Languages
Rust 92.9%
TypeScript 3.2%
JavaScript 1.7%
Python 1%
Shell 0.7%
Other 0.3%