dsh-think-ultra
Reasoning layer for the official DeepSeek Harness: every request stays on native max effort, with isolated Flash/Vision/Pro depth controls, stability axes and reasoning toolboxes built above it. Delivered build only; commercial use open, reverse/modify/extract closed.
官方 DeepSeek Harness 的推理层：所有请求保持原生最大努力模式，并在其之上构建隔离的 Flash/Vision/Pro 深度控制、稳定性轴和推理工具箱。仅提供构建版本；允许商业用途，禁止逆向/修改/提取。
How to install
dsh plugin add github:YUEYUEXYS/dsh-think-ultra About
dsh-think-ultra A reasoning layer for DeepSeek Harness (DSH). Current build is 0.10.0-experimental-preview. It runs only inside an official, unmodified DSH, and this repository ships the delivered build — the readable source is not published, and the licence does not grant reverse analysis, modification or extraction (see LICENSE). What "Ultra" actually is DeepSeek's API exposes four reasoning efforts: off, low, high, max. There is no fifth one. Send reasoning_effort="ultra" and the provider rejects the request outright (... does not support reasoning effort "ultra"). This plugin never makes t…
Recommendation signals
Meta
- License
- NOASSERTION
- Language
- –
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-31
- Created
- 2026-08-30
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:0xsline/awesome-deepseek-harness
- Topics
- ai, deepseek, deepseek-harness, dsh, dsh-plugin, harness-plugin, llm, max, plugin, reasoning, ultra
Related plugins
dsh-commandcode-provider
Mars-Sea/dsh-commandcode-provider
Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.
claude-code-router
musistudio/claude-code-router
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
dsh-llm-fallbacks
btspoony/dsh-llm-fallbacks
Role-based LLM retry & fallback strategies.