Electricitysheep/dsh-tool-turbo

Name: Electricitysheep/dsh-tool-turbo
Author: Electricitysheep

Plugin插件 Native原生 ⭐ 9 Productivity & Tasks效率与任务 Runtime & Injection运行时与注入

DeepSeek Harness（dsh）的逐轮推理努力优化器：自动降低简单工具链中工具调用推理的强度，并在面对繁重任务时自动提升。减少工具调用之间的思考时间。

Project Overview项目介绍

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

This is a native plugin built exclusively for DeepSeek Harness (DSH) that cuts tool-call latency by automatically adjusting DeepSeek API's reasoning_effort parameter based on recent tool calls. Multi-step agent workflows spend most of their total wall-clock time on reasoning between tool calls, and this plugin keeps lightweight reasoning rounds cheap while preserving full reasoning power for harder steps. It taps into DSH's agent/request config waterfall to inject its automatically calculated reasoning effort before each model call, based on a simple, tested decision policy.

The plugin follows a clear, deterministic policy for setting reasoning effort that has passed all six available unit tests. If there are no recent tool calls, it keeps the user's baseline reasoning effort as configured. If 75% or more of recent tools are simple, deterministic tools like read, write or grep with small payloads and downgrading is allowed, it sets effort to low. Mixed or heavy tool calls get set to high effort, and very heavy payloads can get set to max effort if upgrading is enabled.

To install the plugin, you first clone the repository from GitHub, run npm install to install dependencies, and build the package. Next, you add the plugin as a linked dependency to your existing DSH profile, update the Cordis patch config to register the plugin, and run pnpm install before restarting your DSH instance. The project is licensed under MIT, all core logic is verified to work in live DSH instances, and additional features like a settings UI are currently on the development roadmap.

这是一个专为 DeepSeek Harness (DSH) 开发的原生插件，核心功能是通过自动调整模型的 reasoning_effort 参数，降低多步骤工具调用流程中的总推理延迟。DSH 在每一轮模型请求前开放配置修改瀑布流，该插件会监听当前步骤最近的工具调用记录，根据工具类型和 payload 大小自动决定下一轮的推理强度，再将决策注入到下一步的模型请求配置中。

DSH 用户在处理多步骤代理任务时，工具调用之间的推理耗时往往占总耗时的大部分，50步的任务可能要花费数分钟在推理上。该插件会让简单工具调用轮次保持低推理强度，需要深度思考的轮次则维持或升高推理强度，既不影响任务完成质量，又能显著减少整体耗时，适合经常运行长步骤工具链的 DSH 开发者使用。

该插件使用 TypeScript 开发，依赖 npm 和 Node.js 环境，安装需要手动克隆仓库构建，然后在本地 DSH 配置文件中添加依赖和插件注册，重启 DSH 即可生效。目前所有核心功能都已通过单元测试，代码可以通过 tsc 编译检测，使用 MIT 许可证开源，设置面板功能仍在开发路线中。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-tool-turbo（Electricitysheep/dsh-tool-turbo）
仓库：https://github.com/Electricitysheep/dsh-tool-turbo
本站详情页：https://www.yhbd.top/plugins/electricitysheep-dsh-tool-turbo/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证未声明 · ⭐ 9 · 最近提交 2026-08-17 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 项注意

No license declared - all rights reserved by default; ask the author before commercial use or redistribution未声明开源许可证 —— 默认「保留所有权利」，商用或再分发前先问作者
Only 9 stars - very few users, little community feedback星标只有 9，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

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

CLI Install命令行安装

dsh plugin --profile web add github:Electricitysheep/dsh-tool-turbo

把 Electricitysheep/dsh-tool-turbo 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.2 KB · 缓存于 2026-08-23 03:41:35 · 3.2 KB

dsh-tool-turbo

Cut tool-call latency in DeepSeek Harness (dsh) by auto-adjusting reasoning_effort per tool round.

中文文档 · English

In a multi-step tool chain, the model re-thinks before every tool call — and that thinking dominates the wall-clock time (a 50-step agent task can spend minutes in reasoning between tools). dsh-tool-turbo watches the recent tool calls of a step and injects the lowest sensible reasoning effort into the next model request, then lifts it again the moment the work gets heavy.

How it works

DeepSeek's API exposes reasoning_effort in three steps (low / high / max, shipped 2026-08-13). dsh re-resolves the request config for every step through an agent/request waterfall (see packages/core/agent-loop/src/agent.ts — "plugins propose the next request config"). dsh-tool-turbo plugs into that waterfall:

Watch the step's recent tool/call records from the session.
Decide: simple, deterministic tools (write, read, grep, glob, bash, fs_*, …) with small payloads → low; mixed/heavy work → high; very heavy payloads → max (opt-in).
Inject the decision into the agent/request config for the next model call of that step.

Long tool chains keep the cheap rounds cheap, and never starve the hard rounds of reasoning.

Install

# 1. clone + build the plugin
git clone https://github.com/Electricitysheep/dsh-tool-turbo.git
cd dsh-tool-turbo && npm install

# 2. register into your dsh profile (web shown; any profile works)
#    ~/.dsh/profiles/web/package.json dependencies:
#      "dsh-tool-turbo": "link:<absolute path to dsh-tool-turbo>"
#    ~/.dsh/profiles/web/cordis.patch.yml:
#      - insert:
#          - id: tool-turbo
#            name: dsh-tool-turbo
cd ~/.dsh/profiles/web && pnpm install

# 3. restart dsh web
dsh web

Verified

Injector works in a live dsh instance (log lines from a real run):

[tool-turbo] agent/request: baseline=high calls=[]                    => reasoningEffort=high
[tool-turbo] agent/request: baseline=high calls=[{"name":"write",…}] => reasoningEffort=low

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 Electricitysheep/dsh-tool-turbo 的 README.md。在 GitHub 查看原文 →