better-dsh-codex-effort-slider：DSH 输入区的 Codex 风格推理等级滑条
eloimovo 维护的 DSH 客户端插件 better-dsh-codex-effort-slider（v1.3.10）将输入区模型席改为 Codex 风格连续滑条：拖动改档、蓝紫渐变与星尘粒子、自建 provider/模型两级面板，fail-open 不破坏官方 UI。文章说明安装（面板、install.cmd、非 desktop 的 dsh plugin 命令）、用法、编译期配置与 DSH 0.2.0-rc.2 兼容性，并提醒完全重启宿主与插件同进程权限。
Read Moredsh-aurora-effort-slider：把推理等级换成可拖动的星河滑轨
dsh-aurora-effort-slider 由 Jimmyliweihao 维护，将 DSH Desktop 模型菜单中的「推理等级」行替换为可拖动的星河滑轨，读写走 modelDirectories 官方数据面，失败时静默退回原界面。支持键盘、MAX 曲速动效与深色主题，尊重 prefers-reduced-motion。须在 DSH Desktop 插件面板用本地绝对路径安装 desktop profile，不可命令行安装。使用前请审阅 MIT 源码与权限边界。
Read Moredsh-effort-slider-chaunye：在 Web Composer 里用滑条改推理等级
dsh-effort-slider-chaunye 是 chaunye 维护的 DSH 客户端插件，在 Web Composer 模型选择器旁提供胶囊与整宽渐变滑条，通过 session.selectModel 与官方模型目录共用 per-session 状态。支持键盘操作、无网络与额外权限，需 DSH ≥ 0.2.0-rc.1。文章说明安装命令、用法及 README 中的档位效果实测限制与 Ultra 展示层说明。
Read Moredsh-reasoning-slider: Replacing the DSH Reasoning Level Selector with Slider Cards
`dsh-reasoning-slider` is a DeepSeek Harness web plugin designed to optimize the inference level selection experience. By injecting code, it replaces cumbersome submenu interactions with an intuitive card-based slider that supports drag-and-drop, click, and keyboard shortcut switching, and provides one-click reset and automatic light/dark theme adaptation. It is compatible with DSH 0.2.0-rc.2; a page refresh is required after installation, and uninstalling restores the official style.
Read Moredsh-effort-slider: DeepSeek Harness Inference Effort Slider
The `dsh-effort-slider` plugin transforms DSH's model inference level selector into a sci-fi-style slider with drag support. It adds an **Ultra tier** (locks the MAX level), a **Lightning mode** (the parent agent only handles orchestration, greatly increasing token consumption), and real-time display of child agents’ token output rate. The plugin also includes companion Skills and detailed technical documentation, and requires DSH Desktop 2.0.9 or later.
Read Moredsh-plugin-reasoning-efforts: Adding Reasoning Level Selection for DSH Third-Party Relay Models
The DeepSeek Harness (DSH) plugin is designed to address the issue where third-party relayed models cannot use the “reasoning level” selector. By monitoring the `llm-pi-ai` configuration section, the plugin automatically completes the `reasoning.efforts` capability declaration and provides six default levels. Users can customize dialects and levels by model family in `~/.dsh/settings.yaml`. After installation, restart `dsh web` to independently select the reasoning intensity for each session in the chat box. The plugin supports multiple dialect formats, including OpenAI and DeepSeek, and intelligently handles route-level default values.
Read Moredsh-plugin-model-switcher: Switch models and reasoning levels in DSH using keyboard shortcuts
# Introduction During agent development, frequent comparison between different models is often required: running a task with the current model and then switching models to compare results, or adjusting reasoning levels based on task complexity. Manually opening the model selector, selecting a model, and adjusting levels repeatedly is quite tedious. DSH's philosophy is "everything is a plugin," making high-frequency, small operations ideal for plugins. The `dsh-plugin-model-switcher` introduced below is exactly that: it adds two sets of keyboard shortcuts to the DSH web client—one for switching models and one for switching reasoning levels—accompanied by toast notifications to confirm each action. # What is this `dsh-plugin-model-switcher` by Mrlilil
Read MoreDSH Custom Provider Reasoning: Completing Reasoning Levels for DSH Custom Providers
dsh-custom-provider-reasoning is a DSH host plugin designed to solve the problem where custom provider models cannot select thinking intensity in the interface due to missing reasoning metadata. This plugin automatically injects `reasoningEfforts` (with default levels ranging from off to max), fills in missing `maxTokens` and `contextWindow`, and intelligently manages route-level `compat` configurations under different protocols, ensuring that reasoning level selections are actually sent to the online service. During installation, you need to add the GitHub dependency in the web profile and run `pnpm install`, and the plugin will automatically write the configuration into `settings.yaml`. Users can use `cordis
Read More