Plugins

DSH plugin: keep the running turn's work visible — process groups, reasoning and tool results expand automatically and fold once the group ends, leaving history untouched.

Drive DSH's own built-in browser (the right-hand Sidebar's Browser tab) from the agent: list tabs, open, navigate, read the page, run JavaScript, click, fill forms, log in, and look at pictures or the pane itself with vision. No second Chromium process.

DSH Square: An all-in-one sidebar for managing plugins / experts / skills / connectors / (compatible with both web and desktop). DSH Square（广场）：侧边栏一体化管理插件 / 专家 / 技能 / 连接器 / （Web 端与桌面端通用）

DeepSeek Harness Web UI cleanup: a direct Settings launcher instead of the sidebar 更多 menu, no unusable official DeepSeek provider card, and the official-model Session-log upload pinned off. · DSH 界面官方入口清理

Refuses Git inside a Jujutsu workspace and hands the model the jj command instead. Eleven jj tools, prompt teaching, and a jj-hunk bridge for the DeepSeek Harness.

Multi-root workspaces for DeepSeek Harness: attach other repositories to a workspace, writable under workspace-write, listed in the model context with their AGENTS.md, and editable from the composer or /roots

Action cards: the agent proposes a concrete action (create a file, edit a value, run a command), you edit it and apply it in one click, and the Host executes it and reports back.

给小朋友的编程学习启蒙插件：一个包 = 一张 🐵「小教室·跑代码」卡片（真跑 Python/海龟画图）+ 五个模型工具（kid_run / kid_explain / kid_practice / kid_review / kid_steps），零第三方依赖、无构建步骤。

Natural, human-sounding voice for the dsh harness: server-proxied neural TTS read-aloud and agent speech tools over OpenAI-compatible endpoints, browser-native or Whisper speech input, and a Voice settings section

Use a GitHub Codespace directly as a DSH workspace: the agent reads, writes and runs commands inside the cloud Codespace.

DeepSeek Harness 插件：把 shimo-mcp / lanhu-design-mcp / codesign-prd-mcp 三个 MCP Server 一键接入 DSH（MCP 代码零改动，纯配置 bundle）

DeepSeek Harness sandbox provider backed by MXC (Microsoft eXecution Containers): wraps ctx.sandbox.confine() argv as `wxc-exec --config-base64 <policy> -- <command>` on the BaseContainer backend. One runtime dependency (@microsoft/mxc-sdk, for the wxc-ex

Runs a fixed set of agent benchmark cases in isolated sandboxes, scores each case with deterministic assertions, and diffs two runs to show which cases regressed after a model, prompt or DSH upgrade.

Adds a Restart card to the harness settings: one click hands the restart to the DeepSeek Harness launcher (`Launch-DeepSeekHarness.ps1`), which replaces the running web process, and the page reconnects itself once the new instance answers. Windows only; without that launcher the button reports an error instead of restarting.

Records the files and folders an AI agent creates, modifies, deletes, renames or moves, shows them in a draggable floating panel with unread counts, and persists the records as per-workspace JSONL logs.

Jujutsu (jj) version-control panel in the DSH web GUI: a Jujutsu tab renders the jj log change graph with change details, changed files and file diffs, a revset input, and jj-native history edits (drag-to-rebase, split by file, describe, squash, abandon, undo, push); it reads jj directly rather than through git, and every command runs as an argv array through a whitelisted host service with confirmations, timeouts and output caps.

Git tab in the DSH web UI right sidebar for the current session repository — switches branches from a dropdown of local and remote branches (with ahead/behind counts), stages files in staged/unstaged/untracked/conflicted groups, commits, fetches, pulls and pushes with automatic upstream setup, drafts a Conventional Commits message from the staged diff with the default model and falls back to a plain chore message when none is available, and renders git log --graph with per-branch colors plus a word-level highlighted diff.

Personal project assistant for bounded project context and memory, explicit task handoffs through an existing WeChat bridge, reminders, and source-linked summaries. The WeChat path needs the separate pan17/dsh-wechat bridge and your own scan-code binding.

The DSH app also doubles as a desktop pet: wake it with your voice, talk out loud, and give orders by speaking. Reach the DeepSeek Harness running on your own computer over LAN, your own domain, or a relay server — and chat with the little whale working in your project to put it to work. Travelling without your laptop is no longer a problem.

Generate images and videos, edit images, remove backgrounds, upscale images, upload reference media, and check Fotor credits.

A 护航 panel in the session header that switches the local dsh-guard watchdog on or off and shows whether scanning is enabled, whether the guard is alive and when it last scanned; the Python watchdog that does the watching is deployed separately and found through the DSH_GUARD_ROOT environment variable. The watchdog defaults to a Windows checkout (D:\AI\Projects\dsh-guard); set DSH_GUARD_ROOT to point at another directory.

Runs the model's bash commands in a local shell chosen in Settings (Niubash, Git Bash, MSYS2, Cygwin, or any bash.exe on PATH) instead of rewriting them for PowerShell, and hides the pwsh tool on Windows.

Bilibili autopilot run by a local Ollama model: it picks videos within per-topic quota, reads subtitles, hot comments and keyframes, decides whether a reply is warranted, then writes and posts one comment through a five-level safety gate. Triggered by dsh-schedule; write tools are not registered while commenting is disabled. v1.1 hardens the write path: revoking write access is a runtime state checked before every send, publishing is atomic, risk-control errors persist as a pause, and the final post re-checks persona style. Needs Python 3.10+ with the repo's requirements.txt installed.

One header button stops running turns, goals and background jobs and writes the plan to disk; after a restart the same button picks the work up again.