zhiyuchen1101/codewhale-dsh

Name: zhiyuchen1101/codewhale-dsh
Author: zhiyuchen1101

插件Plugin ⭐ 2 MIT cat_label.agent-interopcat_label.agent-interop cat_label.codewhalecat_label.codewhale cat_label.mcpcat_label.mcp

DSH says everything is a plugin — so DSH itself can be one too. Run DeepSeek Harness as a codewhale sub-agent / 把 DeepSeek Harness 作为 codewhale 的子 agent（MCP bridge + 黑板 + headless → ACP）

项目介绍Project Overview

由知微Agent(zhiwei)编辑Edited by Zhiwei Agent (zhiwei)

codewhale-dsh 是把 DSH 作为独立智能体接入 codewhale 的 MCP 桥接插件。它通过 FastMCP 暴露 dsh_init、dsh_status、dsh_read、dsh_respond、dsh_cancel，可在 codewhale 会话中派发任务、轮询进度、读取结果、响应权限请求并取消；任务板为单一事实源，DSH 进程独立运行并使用自身插件生态。适合需要在 codewhale 内并行调用完整 DSH 引擎时使用。注意桥接层只做协议转换，不含智能体决策，且忙碌时拒绝新任务。

codewhale-dsh is an MCP bridge plugin that runs DSH as a standalone agent inside codewhale. It exposes dsh_init, dsh_status, dsh_read, dsh_respond, and dsh_cancel for dispatching tasks, polling progress, collecting results, answering permission requests, and canceling work. The task board is the single source of truth, while the DSH process runs with its own engine and plugin ecosystem. Use it when codewhale needs a full DSH agent alongside it. The bridge only translates protocols and rejects new tasks while busy.

在 GitHub 查看View on GitHub

发给你的 DSH 安装Send to your DSH

请帮我了解并安装插件：【codewhale-dsh】【https://github.com/zhiyuchen1101/codewhale-dsh】

把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.

或使用命令行安装（适合开发者）Or use CLI install (for developers)

命令行安装CLI Install

dsh plugin --profile web add github:zhiyuchen1101/codewhale-dsh

把 zhiyuchen1101/codewhale-dsh 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

5.0 KB · 缓存于 2026-08-27 05:41:41 · 5.0 KB

English · 简体中文

codewhale-dsh

DeepSeek Harness says: everything is a plugin. So DSH itself can be one too.

It doesn't leave its own waters. Inside codewhale, DSH swims in as another whale — its own engine, its own plugin ecosystem (358+ community plugins), its own temperament, sharing the same terminal and the same ledger.

Dispatch work, watch progress, collect results, answer its calls for help — one ledger, all inside your codewhale session.

Why

DSH ecosystem bridges all point one way (tool → DSH). This project points the other way:

DSH → codewhale. Not a guest UI, not a borrowed toolset — a full agent with its own plugin tree, running alongside yours.

How it works

┌────────────────────────────────────────────────────┐
│ codewhale TUI        your daily · your ledger       │
│        │ MCP (mcp.json)                            │
│        ▼                                           │
│ dsh-bridge            FastMCP thin shell           │
│   tools: dsh_init · dsh_status                     │
│          dsh_read  · dsh_cancel                    │
│   board: task_board.json  (single-writer machine)  │
│        │ spawn                                     │
│        ▼                                           │
│ DSH headless          its own engine & plugins     │
└────────────────────────────────────────────────────┘

The bridge translates protocols only — no agent logic, no decisions. The board is the single source of truth; the DSH process is the only worker.

Tools

Tool	What it does
`dsh_init(task, workspace)`	Dispatch a task. Rejects while busy; resets after `done`/`error`
`dsh_status()`	Poll status; auto-settles `done`/`error` when the process exits
`dsh_read()`	Read the full result
`dsh_respond(allow)`	Answer a permission/help request (`blocked` state)
`dsh_cancel()`	Graceful ACP cancel; kill fallback

Quick start

git clone https://github.com/zhiyuchen1101/codewhale-dsh && cd codewhale-dsh
make install

{
  "mcpServers": {
    "dsh": {
      "command": "/Users/<you>/codewhale-dsh/.venv/bin/python",
      "args": ["/Users/<you>/codewhale-dsh/src/dsh_bridge.py"]
    }
  }
}

Then in a codewhale session: "use dsh_init to dispatch a task: ..."

Roadmap

Status	Item
✅	Minimal loop — `dsh_init` → headless works → `dsh_read` collects
✅	ACP streaming — official ACP server (`packages/acp`): live chunks, permission relay (`blocked` + `dsh_respond`), graceful cancel
🚧	Help requests L2/L3 — richer blocking reasons and escalation tiers (L1 done: permission relay)
✅	Token accounting — per-task usage from DSH session log (`input/output/cache/reasoning`)
⬜	Task queue — multiple tasks, isolated workspace/session each
⬜	npm package — ship `dsh-bridge` as an installable binary

Design rules

Thin shell — the bridge translates protocols only: no agent logic, no decisions
Single writer — the board has exactly one writer
TDD — RED before GREEN (make test)
Task isolation — fresh workspace and DSH session per task
Summaries out, judgment stays — with you, or codewhale's verifier role

Contributing

Pick an open Roadmap item, open an issue first, then send a PR. Tests must pass (make test). First contributions welcome — the maintainers harvest what works and credit every author.

Architecture decisions

ADR-001 · ADR-002 · ADR-003 · ADR-004 · ADR-005 · ADR-006

License

MIT — an independent community project, not affiliated with DeepSeek or any model provider.

渲染基于仓库 zhiyuchen1101/codewhale-dsh 的 README.md。在 GitHub 查看原文 →

命令行安装CLI Install 复制安装命令Copy Install