生産性ツール · DeepSeek Harness プラグイン — 140 ページ

DSH native scheduling: run a saved prompt in a brand-new session when the clock says so, with a persisted task table, run history and a restrained management UI.

Left-sidebar file switch: hover a workspace row, click the folder icon, and its session list becomes a lazy file tree.

Zen Mode view tab + foreground time tracker for DeepSeek Harness: a calm minimal surface (status message, latest user message, live activity hints, markdown AI reply, one-line turn stats) while the agent works, with screen-watching time tracking, daily/weekly Zen scores, a chat-hide toggle, auto enter/exit and an Alt+Z shortcut — pure client-side, no network. dsh-zen 禅模式插件：智能体后台运行时提供极简的 Zen 视图标签页（状态文案、用户消息、动态提示、Markdown 最终回复、单行轮次统计），并统计前台盯屏时长、给出每日/每周禅值，支持隐藏中间过程、自动进出禅与 Alt+Z 快捷键——纯前端、无网络请求。

Workspace file browser with agent-change review (accept/reject + undo), full user editing (undo/redo, save, auto-save), diff view and rendered markdown, plus an integrated terminal view with auto-detected project run targets (static host+client plugin)

Paper digest plugin: every day at a configured time, collect quality papers on your topics (Chinese + English), rank them with transparent quality signals, and write a Markdown report into the workspace. Configured from its own page in DSH Settings.

View and edit the current session's system prompt (in-memory, session-local override) for the DeepSeek Harness

让 AI 真正操作浏览器完成任务。支持打开网页、点击、输入、翻页、读取内容和下载文件等操作，可用于网页测试、信息采集和自动化流程，并提供域名限制等安全控制。

让 AI 真正操作浏览器完成任务。支持打开网页、点击、输入、翻页、读取内容和下载文件等操作，可用于网页测试、信息采集和自动化流程，并提供域名限制等安全控制。

让 AI 项目可以在无人监管下持续推进。Orbit 会自动规划任务、分工执行、逐步检查并继续完成后续工作；不同环节可以使用不同模型，让低成本模型承担执行任务、强模型负责规划和审核，从而降低整体 AI 使用成本。Watchdog 还会监控运行异常，在任务卡死或中断时协助恢复。

让 AI 项目可以在无人监管下持续推进。Orbit 会自动规划任务、分工执行、逐步检查并继续完成后续工作；不同环节可以使用不同模型，让低成本模型承担执行任务、强模型负责规划和审核，从而降低整体 AI 使用成本。Watchdog 还会监控运行异常，在任务卡死或中断时协助恢复。

Agent-loop change review for the DeepSeek Harness web GUI: after every agent loop it snapshots the workspace, detects file/code changes, and offers one-click revert plus a right-sidebar diff review panel. 官方双面 dsh 插件（host + client），零依赖。

Family bundle 会话工具箱: message-tools, message-timeline, session-title-edit, quote, inline-html-render, context-guard and taskpilot in one install. Thin meta package: a patch carrying the members' canonical rows, npm dependencies on the members, locale card metadata — no runtime code, no client half.

Session title editing in the web GUI chat header: an edit control beside the title that renames the current session through the official session.rename RPC (the user-sourced title pins against automatic regeneration)

Shared client-side content-preview kernel for community file surfaces: the kind-union content pane (markdown / JSON / CSV / image / code, plus the Tier0/Tier1 sandboxed HTML render with its capability bridge), rendered-content search, and the per-file host-open chrome. Consumed at the SOURCE plane — each surface's tsdown client bundle inlines it — never mounted as a plugin row.

Generic versioned dataset storage over git repositories: layered items, commit-pinned reads, managed sparse-checkout worktree views, per-session bindings with layer whitelists, and a web session tab over a Typert Remote data face

The session-granted dataset model tools, companion to @khorsheed/dsh-datasets: a tool-only row (provides no service) that agent presets compose to grant the datasets_* tools (`tools`: all / read / authoring / none) per session, plus their tool-guidance prompt section. Deliberately NOT self-mounting — installing it as a dependency only makes the module resolvable; an agent preset's agent.cordis.yml references the row by name.

The session-granted eval tools, companion to @khorsheed/dsh-eval: a tool-only row (provides no service) that agent presets compose to grant eval_conditions / eval_plan_validate / eval_plan_draft / eval_run_status / eval_cells (`tools`: all / none) per session, plus their tool-guidance prompt section. Four reads and one draft — eval_plan_draft writes a plan and its new conditions into the bound repository working copy and validates them, which starts nothing. Deliberately NOT self-mounting — installing it as a dependency only makes the module resolvable; an agent preset's agent.cordis.yml references the row by name.

Session products preview, host+client in one: the read-only file-preview Remote service (the files a session wrote or edited, current content, per-change diffs) plus the right-sidebar 会话产物 tab, per-turn change cards, and the file detail view

Claude Code harness for dsh-local-agent: scoped CLAUDE_CONFIG_DIR, one-shot claude -p delegation visible in the 子代理 surface, project-file session records

Codex harness for dsh-local-agent: scoped CODEX_HOME, one-shot codex exec delegation visible in the 子代理 surface, rollout-file session records

dsh harness for dsh-local-agent: delegate to dsh itself as a local CLI — scoped DSH_HOME under the shared homes root, one-shot sub-dsh runs visible in the 子代理 surface, caller-supplied session ids, resume across rounds, DeepSeek toggle in settings

Sub-dsh headless bundle for the local-agent-dsh harness: a direct Agent/Session runner over dsh-base — one-shot (caller-supplied --session-id/--resume, prints the final assistant text, exits) or resident (--serve) driving turns over the family stdio wire

Kimi Code harness for dsh-local-agent: scoped KIMI_CODE_HOME, one-shot kimi -p delegation visible in the 子代理 surface, session records and preset wiring

Family-owned subagent delegation tool over the ctx.subagents seam with optional one-shot resume: the model may pass the dsh child session id returned by the first delegation to continue the same CLI conversation in a later round