dsh-reasoning-settings

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Star

5+2

7-day growth

Contributors

Language

JavaScript

Updated

2026-08-15

Install

Derived from package metadata

dsh plugin --profile web add github:JuneLearn/dsh-reasoning-settings

The author hasn't published to npm, so this command installs from git source. pnpm ≥ 10 refuses to run a git dependency's prepare script until you grant it, so your first install needs an allowBuilds entry in that profile's pnpm-workspace.yaml — which means letting this package's code run on your machine. Pin a #commit while you're at it.

The name after --profile is a profile name you choose yourself — swap in whichever one you use.

Share card

Drop it into your README — it links back to this page.

Badge (inline)

[![dshfind](https://dshfind.com/api/badge/JuneLearn/dsh-reasoning-settings)](https://dshfind.com/en/plugins/JuneLearn/dsh-reasoning-settings?ref=badge)

Card (440×200)

[![dshfind](https://dshfind.com/api/card/JuneLearn/dsh-reasoning-settings)](https://dshfind.com/en/plugins/JuneLearn/dsh-reasoning-settings?ref=badge)

#model-provider #openai-compatible #reasoning-effort #web-ui