deepseekplugins

DeepSeek Harness plugin

dsh-effort

DeepSeek Harness 插件：在 Web GUI 中选择模型的推理程度（reasoning effort）。按当前模型的适配器目录展示可选档位（如 Off / High / Max），一键写入会话的模型选择。

Memory
Jump to install

Source facts

Repository
AI-Galaxy-GPU/dsh-effort
Latest update
Aug 15, 2026
Category
Memory
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/AI-Galaxy-GPU/dsh-effort
Plugin: dsh-effort
Author: AI-Galaxy-GPU

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer2 files
README.mdSource · read only

dsh-effort

!License: MIT !Version !Platform: Web GUI

> DeepSeek Harness 插件:在 Web GUI 中为会话选择模型的推理程度(reasoning effort)。

About

DeepSeek Harness 的模型请求链路已原生支持 reasoningEffort(GenerateOptions.reasoningEffort、会话的 ModelSelection.reasoningEffort),但 Web GUI 目前没有任何入口可以设置它——本插件补上这个缺口:在模型下拉的「推理」行下方放一个星光推理选择器,松手即写入会话的模型选择,下一轮请求生效。

演示

<video src="https://github.com/user-attachments/assets/2fbc5ab2-3430-415f-9b18-b0e344b647b0" controls></video>

源文件: [docs/demo.mp4](docs/demo.mp4)

特性

  • ✨ 星光轨选择器:低档是深色胶囊 + 圆点刻度;往右拖,紫色像素星空逐渐点亮
  • 🎚️ 档位与适配器对齐:Off(目录里有则置最左)→「默认」(交给适配器 / 提供方)→ 其余档位(如 High / Max,按适配器显示顺序)
  • 🧠 共用事实源:通过 sessions.selectModel 写回,与内置模型选择器共用同一个 host 状态
  • 🎛️ 总开关:设置 → General 新增「推理程度选择器」开关(localStorage 持久化)
  • 🔌 零侵入:纯客户端注入,不修改 DeepSeek Harness 核心代码

安装(本地开发)

cd <本仓库目录>
dsh plugin --profile web add .

重启 dsh web,打开模型下拉,在「推理」那一行下面即可看到星光推理选择器。

使用

  • 星光轨:从左到右为 Off(若当前模型目录含 Off)→「默认」(清除自定义选择,恢复适配器 / 提供方默认)→ 其余档位(名称由适配器提供,如 High / Max,按适配器显示顺序)。拖动预览、松手(pointer-up / 键盘 key-up / 失焦)提交。
  • 模型不暴露推理程度目录时选择器不显示。
  • 设置 → General:新增「推理程度选择器」总开关(localStorage 持久化)。

架构

双半身插件包(与 dsh-answer-sound / dsh-sound 同构):

半身文件职责
Hostlib/index.jsCordis 加载入口(当前为 no-op,扩展点见文件头注释)
Clientlib/client.js浏览器 bundle:挂到模型下拉「推理」行下方的星光轨 + settings.general.item 设置行
  • 注入服务:slots(注册 UI)、connection(RPC:sessions.models / sessions.selectModel)、sessions(快照订阅)。
  • 数据流:滑块挂载时拉取 sessions.models;之后订阅会话快照并每秒静默对账(拖动预览时不抢位置)。选择通过 sessions.selectModel 写回,与内置模型选择器共用同一个 host 事实源。
  • 档位顺序:Off 固定最左,「默认」随后,其余档位按适配器目录显示顺序。

License

MIT

Back to searchOpen GitHub repository

More related plugins

View category