DeepSeek Harness 插件

dsh-thinking-effort

为 DSH 自定义模型配置思考档位和子 agent 默认思考强度。

跳到安装方式

来源信息

GitHub 仓库
hytime/dsh-thinking-effort
最近更新
2026年8月20日
分类
模型与服务商
GitHub stars
0

安装

默认先复制一段 Prompt,让 Agent 读页面和仓库;需要自己装时再切到命令。

复制这段 Prompt,发给 DSH、Codex 或其他 Agent,让它先读页面和仓库。

请先不要安装。阅读这个 DeepSeek Harness 插件,说明它解决什么问题、会访问哪些文件、网络或密钥,以及如何安装和卸载。

插件页面:https://deepseekplugins.org/zh/plugins/hytime/dsh-thinking-effort
GitHub:https://github.com/hytime/dsh-thinking-effort
插件名:dsh-thinking-effort
作者:hytime
安装命令:dsh plugin --profile web add github:hytime/dsh-thinking-effort

确认前不要执行安装命令。

检查来源文件

安装前先看这个插件目录里的 README 和其他文件。

文件资源管理器3 个文件
README.md来源说明 · 只读预览

dsh-thinking-effort

A DSH (DeepSeek Harness) plugin that adds configurable reasoning effort levels to hand-declared llm-pi-ai models and sets a default reasoning effort for subagents.

![npm version](https://www.npmjs.com/package/@hytime/dsh-thinking-effort) ![npm downloads](https://www.npmjs.com/package/@hytime/dsh-thinking-effort) ![GitHub license](https://github.com/hytime/dsh-thinking-effort/blob/main/LICENSE)

  • [中文 README](./README.zh.md)
  • [日本語 README](./README.ja.md)
  • [한국어 README](./README.ko.md)
  • [Installation guide](./INSTALL.md)
  • [中文安装指南](./INSTALL.zh.md)
  • [日本語インストールガイド](./INSTALL.ja.md)
  • [한국어 설치 안내](./INSTALL.ko.md)
  • [Changelog](./CHANGELOG.md)
  • [日本語 changelog](./CHANGELOG.ja.md)
  • [한국어 changelog](./CHANGELOG.ko.md)

Why use it?

The llm-pi-ai adapter supports hand-declared third-party models, but those entries often do not declare reasoningEfforts. As a result, Composer does not show a reasoning effort selector, and gateway-specific values such as ultra cannot be mapped to DSH's standard levels.

This plugin provides the configuration layer needed to:

  • Add default off, high, and max options to models without a declaration;
  • Configure reasoning levels per model from the DSH settings page;
  • Map a DSH level such as high to a gateway value such as ultra;
  • Set a default reasoning effort for subagents while preserving explicit request values;
  • Keep existing user-defined model declarations unchanged.

The plugin is usually unnecessary when you only use built-in DSH models and their reasoning controls already work.

Identifiers

These identifiers have different responsibilities:

IdentifierPurpose
@hytime/dsh-thinking-effortnpm package, browser bundle path, loader ID, and host/client runtime ID
thinking-effortCordis composition entry ID and settings Slot ID

Features

FeatureDescription
Default levelsAdds off, high, and max without overwriting custom values
Per-model editorSelect levels and configure their gateway values from Settings
Gateway mappingSend ultra when the user selects DSH high
Subagent defaultApply a default effort only when a subagent request has no explicit value
Multilingual settingsSwitch the plugin settings page between Chinese, English, Japanese, and Korean
Version watermarkShow the installed plugin version in the bottom-right corner

Install, upgrade, and remove

Use the official DSH CLI to manage the plugin profile. A plain npm install does not register a DSH profile bundle.

# Install the latest version
dsh plugin --profile <profile> add @hytime/dsh-thinking-effort

# Install a specific version
dsh plugin --profile <profile> add @hytime/dsh-thinking-effort@0.1.7

# Upgrade
dsh plugin --profile <profile> update @hytime/dsh-thinking-effort

# Remove
dsh plugin --profile <profile> remove @hytime/dsh-thinking-effort
rm -f "${DSH_HOME:-$HOME/.dsh}/thinking-effort-loaded.json"

See [INSTALL.md](./INSTALL.md) for profile discovery, migration, validation, and troubleshooting.

Quick use

1. Open DSH Settings → Reasoning effort. 2. Use the Page language selector at the top to choose 中文, English, 日本語, or 한국어. DSH uses the persisted locale first, then the browser language, then Chinese as the fallback. The selection is persisted by DSH and survives refreshes and restarts. 3. Choose a subagent default from the Subagent reasoning effort card, then click Apply. 4. Apply a preset to all models, or expand one model for detailed configuration. 5. Select a level and enter the exact gateway value. For example:

DSH levelGateway value
------
offLeave empty to omit the parameter
highultra
maxmax

6. Return to Composer and select the model to use its reasoning selector.

The settings page shows the installed version as a small watermark such as v0.1.7 in the bottom-right corner.

How it works

  • Host: Scans llm-pi-ai models and modelOverrides on startup and settings changes, adding defaults only where reasoningEfforts is missing.
  • Client: Registers a settings page through the standard DSH settings API and the official DSH locale service. Chinese, English, Japanese, and Korean dictionaries are maintained separately in src/locales/zh.json, src/locales/en.json, src/locales/ja.json, and src/locales/ko.json, then generated into the client bundle before publishing.
  • Subagents: Stores the default in the llm-pi-ai user layer as subagentEffort. The agent/request waterfall only fills requests that do not already specify an effort.
  • No configured default: The plugin does not automatically choose off, high, or max; the request omits reasoning and the gateway decides its own default behavior.

Limitations

  • llm-pi-ai exposes seven standard levels: off, minimal, low, medium, high, xhigh, and max.
  • Non-off levels require a gateway value. An empty off value means that the parameter is omitted.
  • The selected subagent level must be supported by the target model, or the gateway may return UNSUPPORTED_REASONING_EFFORT.
  • off and an unset effort may both omit reasoning; whether this disables thinking depends on the gateway protocol.
  • Host changes require a DSH restart. Settings and locale changes are applied in the browser, with a refresh available when needed.

License

[MIT](./LICENSE)