dsh-cot-flow：流式场景下展开思考链的增量渲染
dsh-cot-flow 是 DeepSeek Harness 客户端插件，针对展开 reasoning 时官方每帧整段 Markdown 重解析导致的卡顿，按围栏外空行切段、已定稿段落只解析一次，每帧仅处理尾部，并走官方 conversation.chat.reasoning.content Factory。安装需在 profile 目录执行 pnpm add github:yutaosheng004-bit/dsh-cot-flow 并写入 dsh.profile.bundles。控制台 __dshCotFlow 可验证；失败静默降级。MIT 0.1.0，维护者 yutaosheng004-bit。
Read Moredsh-think-command：在聊天里用 /think 切换思考等级
dsh-think-command 是 rootAyaka 维护的 DSH 客户端插件，通过 /think 在 Web 指令适配器与 QQ 机器人通道查看、切换当前会话的思考（reasoning）等级。切换从下一轮回复生效，写入 model/selection，不占用模型轮次。安装目标为 github:rootAyaka/dsh-think-command，支持 bundle 自动 patch profile。QQ 端桥接 dsh-qqbot，回复含可点击的等级指令条。
Read Moredsh-thinking-summary：在 DSH 原生思考披露里做 Codex 式逐步推理摘要
dsh-thinking-summary 是 HUSTforever 维护的 DSH 客户端插件，在 Harness 自带 thinking disclosure 中按模型步骤生成 Codex 风格摘要：短 action 标题替换原始预览，过程卡片展示 1–2 句说明，并可切回原始 reasoning。0.3 起支持 tarball 或 Git tag 安装，需辅助模型请求；本文基于官方 README 说明行为、安装 spec、设置路径与配置项，并提醒延迟、权限与社区目录性质。
Read Moredsh-cot-summerization: DeepSeek Harness Chain of Thought Summarization Plugin
Developed by MeowLynxSea, the DSH plugin `dsh-cot-summation` is designed to optimize reasoning display. Instead of directly displaying the raw Chain of Thought, it intercepts raw incremental data at the `llm/stream` layer and generates thumbnail summaries via a small model, which then flow into the UI as Reasoning blocks. This design ensures a clean interface while preserving the raw Chain of Thought within the model's visible history, avoiding interference with the Agent's multi-round reasoning. Core capabilities include streaming segmented summarization, dynamic chunking, near-duplicate elimination, and support for the Nekomimi boundary protocol. The plugin offers various error handling strategies and allows for the configuration of an independent small model channel. After installation, users can configure the enable status, summary style, and length limits via the Web Client. Although this incurs an additional cost for a small model call and requires the raw data to pass through the configured LLM channel, users can point to this...
Read More