Skip to content
PluginNeeds setup

dsh-better-reasoning-effort

HaoyueQin673Updated 24d ago

Open on GitHub

Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.

Practical score

79 / 100

Setup

Needs setup

License

MIT

Language

TypeScript

Install

Quick start

Copy the command, or hand the whole task to your harness agent.

git clone https://github.com/HaoyueQin/dsh-better-reasoning-effort.git
DSH versionDSH ≥ 0.2.1-alpha.1Setup required
Install with your agent

Please install the DeepSeek Harness plugin "dsh-better-reasoning-effort" for me. - GitHub repository: HaoyueQin/dsh-better-reasoning-effort (https://github.com/HaoyueQin/dsh-better-reasoning-effort) - Type: a Cordis plugin (installed into a DSH profile) - The…

From the README

A cleaned excerpt from the project's own documentation.

DSH Better Reasoning Effort English 中文 Reasoning-effort and input-modality editing for third-party models in DeepSeek Harness, edited right inside the official Models page card — plus a quick reasoning-effort slider inside the official composer model menu (adapted from HanaAyane's dsh-reasoning-effort, see Acknowledgements).…

Open on GitHub

Project details

by
HaoyueQin
License
MIT
stars
67
Forks
3
Updated
Oct 18, 2026
Created
Aug 19, 2026
Language
TypeScript
Indexed from
topic
Visit homepage

Related entries

Similar tools from the same corner of the ecosystem.

View all
Plugin

dsh-workbuddy-bridge

dsh-plugin-lab

DSH 插件:把 WorkBuddy 桌面 App 里的模型接入 DeepSeek Harness,零配置直接用。(原生嵌入"插件-插件配置页")

agent-harnessaiai-agent
37Ready to use
86/100
Plugin

dsh-lowtide

KelaoHu

Time-shifting task delegation for DeepSeek Harness (dsh): plan tasks at leisure, they run unattended off-peak, come back to a report. Human-adjudicated, desktop + web.

ai-agentautomationbatch-processing
178Needs setup
82/100
Plugin

dsh-smooth-stream

Laplace-bit

Silky streaming reveal for the Web UI: text appears at the model's arrival rate, new lines glide in, no flicker; follow stays with the user and respects prefers-reduced-motion.

ai-chatchat-uicordis
95Ready to use
90/100