dsh-history-edit：在 DSH 对话里撤回、回退与编辑历史
dsh-history-edit 是 MathieuPortmann 维护的 DSH 客户端插件，在 Web 聊天页提供 Recall、Go back here、Edit reply 等操作，通过 surfaceOp 替换实现改问重答与分叉，不删除 session log。安装命令为 dsh plugin --profile web add github:MathieuPortmann/dsh-history-edit，需 Node ^22.19.0 或 >=24 与 DSH >=0.2.0-rc.2 <0.3.0，无配置项，MIT 0.1.0。
Read Moredsh-session-recall：DeepSeek Harness 的会话史书与上游历史工具开关
dsh-session-recall 为 DeepSeek Harness 提供一份有界、零模型的会话史书，并支持按当前 harness 精确版本打开上游那 5 个只读会话历史工具。史书对会话事件日志进行纯函数投影，不落盘、不建索引、不跑后台任务，硬性渲染预算 6,000 字符；上游工具通过脚本安装并挂载，版本与 dsh-base 完全相等。
Read Moredsh-history-viewer：在 DSH Web 里本地浏览、检索并导出会话历史
dsh-history-viewer 是 xiao0xueAI 维护的 DSH Web 插件，直接读取本机 ~/.dsh/sessions 下的 zstd 会话日志与工作区配置，在侧栏提供按项目过滤、全文检索、Markdown 渲染阅读及一键导出。安装命令为 dsh plugin --profile web add dsh-history-viewer，装后需重启 dsh web。适合在 0.2.x 等环境下替代不适配的历史类插件，数据不上传，索引缓存在 ~/.dsh/dsh-history-viewer/。使用前请自行审阅 MIT 源码与进程权限。
Read Moreshl-session-history: Mini Slider for Session History Requests
`shl-session-history` is a DeepSeek Harness (DSH) plugin designed to address the pain point of locating early requests in long conversations. It provides a mini slider rail on the left side of the chat area, allowing users to view summaries by hovering and jump to specific conversations by clicking, while automatically handling pagination loading. It features highly customizable styling, real-time updates, smart filtering, and automatic hiding. Version 1.1.5 refactors the positioning mechanism, ensuring precise jumps via direct links using unique keys. Users can install it with a terminal command and adjust its appearance and size in the settings.
Read Moredsh-recall: Adding session history original text retrieval for DeepSeek Harness
dsh-recall is a DeepSeek Harness (DSH) plugin maintained by Relistencode, designed to address the difficulty of locating original information after context accumulation and compression in long sessions. This tool transforms "searching chat history" into a recall mechanism callable by an agent. Version 0.2.2, based on the MIT license, requires a Node >= 22 environment and runs completely offline. Its core functions include a three-layer hybrid retrieval that merges literal, fuzzy, and semantic results, and automatically degrades when semantic coverage is insufficient. It adopts a progressive disclosure strategy, returning lightweight coarse recall first and expanding the original text window as needed. It aggregates multiple mentions of the same topic into complete events. It supports the agent to actively recall defaults when the context is compressed or missing.
Read More