dsh-thinking-effort

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.

• 中文 README
• 日本語 README
• 한국어 README
• Installation guide
• 中文安装指南
• 日本語インストールガイド
• 한국어 설치 안내
• Changelog
• 日本語 changelog
• 한국어 changelog

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:

Features

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 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 level	Gateway value
   off	Leave empty to omit the parameter
   high	ultra
   max	max

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