JuneLearn/dsh-reasoning-settings

Name: JuneLearn/dsh-reasoning-settings
Author: JuneLearn

Plugin插件 Native原生 ⭐ 5 MIT Subagents & Orchestration子代理与编排 Clients & Launchers客户端与启动器

为DeepSeek Harness的第三方API添加低、中、高等推理强度支持，并可为每次子Agent调用选择模型。

Project Overview项目介绍

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

This is a native web settings plugin built exclusively for DeepSeek Harness (DSH). It adds a standalone reasoning effort configuration page for custom OpenAI-compatible LLM providers, since the official DSH UI only exposes this setting for first-party DeepSeek models. The plugin automatically pulls existing custom provider and model data from the official DSH Models page, and lets users set per-model reasoning effort levels ranging from off to max, plus a provider-wide default that applies to all models under that provider. It modifies settings only via DSH's official settings.mutate API and never touches user-stored API keys.

The plugin fixes common inheritance issues for in-process DSH subagents. By default, subagents inherit the model set when the parent agent was created, even if the parent switches to a third-party provider mid-session. This plugin updates that behavior to let child subagents inherit the parent's current live provider, model, and reasoning effort settings. It also adds three optional parameters to the existing subagent and subagent_fork tools, letting users explicitly set provider, model, and reasoning effort per call without breaking original tool functionality.

To install the plugin, you first need to have Node.js 22.19.x or newer, Git, and pnpm installed on your system. Regular users can install via the recommended npx method, which does not require cloning the full DeepSeek Harness source code. Developers who have already cloned the DSH source can install it via pnpm in the DSH root directory. The plugin is released under the open-source MIT license, and is built against DSH version 0.1.0-rc.5, which is still in active developer preview.

这是一款专为 DeepSeek Harness (DSH) 开发的原生网页设置插件，为自定义的 OpenAI 兼容大语言模型提供商新增了独立的推理强度（思考深度）配置页面。官方 DSH 界面仅为官方 DeepSeek 模型开放推理强度选择功能，本插件让该功能也可用于第三方 API 和中转服务。它会自动读取用户已在官方模型页面添加的自定义提供商和模型，支持按模型和提供商配置默认推理强度。

本插件修正了多子代理场景下的模型和推理强度继承问题，原本子代理会默认继承创建代理时的官方模型设置，本插件让子代理可以继承父代理当前使用的第三方模型和推理强度配置。它还为原有的 subagent 和 subagent_fork 工具新增了可选的提供商、模型和推理强度参数字段，不改动原有工具的核心逻辑和生命周期。适用于需要使用第三方 OpenAI 兼容 API 自定义大模型推理强度的 DSH 用户。

安装需要预先配置 Node.js 22.19+ 或 24+ 版本、Git 和 pnpm，推荐普通用户使用 npx 命令一键安装，无需克隆 DSH 源码。插件遵循 MIT 许可开源，不绑定任何特定的第三方 API 服务商，仅在 README 中推荐了中转服务并附带推荐链接。当前适配 DSH 0.1.0-rc.5 版本的接口，DSH 仍在开发者预览阶段，升级后可能需要适配调整。

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-reasoning-settings（JuneLearn/dsh-reasoning-settings）
仓库：https://github.com/JuneLearn/dsh-reasoning-settings
本站详情页：https://www.yhbd.top/plugins/junelearn-dsh-reasoning-settings/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 5 · 最近提交 2026-08-16 · 主语言 JavaScript

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 1 warning1 项注意

Only 5 stars - very few users, little community feedback星标只有 5，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:JuneLearn/dsh-reasoning-settings

把 JuneLearn/dsh-reasoning-settings 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

9.7 KB · 缓存于 2026-08-23 03:41:36 · 9.7 KB

DSH Reasoning Settings

A DeepSeek Harness Web settings plugin that adds an independent reasoning effort (thinking intensity) page for custom llm-pi-ai providers. The official UI only exposes effort selection for first-party DeepSeek models; this plugin makes it work for third-party / relay APIs too.

中文说明

Third-party service recommendation (referral link)

If you are looking for an OpenAI-compatible API relay, you can take a look at WPIronman API. This is my referral link, and I may receive a referral benefit if you register through it; any promotion or benefit is subject to the provider's current terms. This plugin is independent of that service and does not require any particular relay. Evaluate pricing, reliability, and privacy terms before choosing a provider.

New users can redeem the gift quota with code 99F509ABC6C38F77.

Features

Auto-reads the custom providers and models you already added on the official Models page.
Declares a per-model effort level from off / minimal / low / medium / high / xhigh / max.
Customizes the actual wire value sent to the API for each level.
Sets a provider-wide default effort, restricted to the levels supported by every model in that provider.
Configures the reasoning wire format for openai-completions providers.
Writes back to llm-pi-ai.providers.* through the official settings.mutate API — API keys are never touched.
Fixes in-process subagents inheriting the Agent's create-time official model instead of the parent's live third-party provider/model selection.
Makes subagents inherit an explicit parent reasoning effort, or fall back to the target provider's configured default effort.
Resolves model-only child overrides such as grok-4.5 against user-configured third-party providers instead of an unrelated official provider.
Extends the ordinary subagent and subagent_fork tools with per-call provider, model, and reasoning_effort fields, without replacing their official lifecycle, background, or result behavior.

Live demo

Reasoning effort settings page

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 JuneLearn/dsh-reasoning-settings 的 README.md。在 GitHub 查看原文 →