dsh-model-memory
Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.
为自定义 API 模型提供推理强度分级管理与跨会话偏好记忆：在「设置 → 模型」中内联切换 low/medium/high/max，配置写入为原子操作。
How to install
dsh plugin add dsh-model-memory About
🧠 dsh-model-memory --- **dsh-model-memory** 是专为 DeepSeek Harness (DSH) 打造的自定义 API 模型思考等级管理与偏好持久记忆插件。 --- 🌟 核心功能 1. 🧠 自定义模型思考等级一键配置 **直接嵌入官方设置**：在 DSH 官方「设置 -> 模型」中，展开自定义 API 模型时，自动挂载极简思考等级配置栏。 **思考档位自由勾选**：支持为模型一键开启 supportsReasoningEffort 并勾选档位（low / medium / high / max）。 **即时生效与持久化**：点击保存原子化写入 ~/.dsh/settings.yaml，即时热重载。 2. ⚡ 跨会话模型与思考强度偏好记忆 **分渠道精准记忆**：跨会话精准记录每个渠道最后选用的模型及其配置的思考强度（如 max 强度）。 **新建会话自动回填**：切换渠道或新建会话时自动保持历史偏好，不再自动回退到默认基本强度。 3. 🛡️ 纯净轻量 & 升级防抹除 **零界面冗余**：彻底移除多余按钮，主界面 100% 保持原生清爽。 **升级免疫**：基于独立本地工程与 DSH Profile 软链接机制，升级 DSH 全局脚手架永不丢失插件与配置。 --- 🚀 安装与挂载 方式一：从 NPM 安装（推荐） bash dsh…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- 1.7K
- Last push
- 2026-09-02
- Created
- 2026-08-21
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
- Topics
- cordis, deepseek, deepseek-harness, dsh, dsh-plugin, model-memory, reasoning-effort, session-memory, thinking-level
Related plugins
dsh-plugin-subscriptions
V1ki/dsh-plugin-subscriptions
Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.
dsh-workbuddy-connect
corrinehu/dsh-workbuddy-connect
Brings the models in the WorkBuddy desktop app straight into DeepSeek Harness — zero configuration in the DSH chat.
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-thinking-effort
hytime/dsh-thinking-effort
Configure reasoning-effort levels and sub-agent defaults for custom DSH models.