Plugins

One-click backup, export, import and migration of a whole DSH config: settings, plugins, MCP, skills and workspaces. Secrets are excluded by default and, if you opt in, are AES-256-GCM encrypted rather than written in the clear; imports preview first and auto-backup with rollback, profiles hold multiple setups, and remote sync pushes portable config through a private Git repo with secrets excluded.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Curated MCP server bundle: one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, plus a connectivity verifier tool and CI checks.

Upload local images and files to your image host through PicGo's existing configuration (PicGo Cloud, GitHub, S3, COS, Qiniu, or any installed uploader plugin), via a `picgo_upload` tool and a `/picgo` command.

Load Wallpaper Engine .mpkg files as the DSH web background: embedded video, time-of-day switching, unified frosted blur, local wallpaper library & rotation.

PDF toolbox for DeepSeek Harness: extract text, metadata, and page ranges from PDF files (local parsing, no API key).

Safe delete plugin for DeepSeek Harness (DSH): move files to trash / staging area instead of permanent removal, with restore and purge support.

Export the current session to portable, schema-versioned Markdown and JSON files via the `session_export` tool and slash commands, with cross-platform-safe filenames.

Sidebar file tree for DeepSeek Harness: a files panel with a lazy, per-extension-icon tree, copy-path and send-to-agent actions

Migrate Codex CLI conversations, MCP servers, memories and project files into DeepSeek Harness sessions, workspaces and MCP registrations. 把 Codex CLI 的对话、MCP、记忆与项目文件迁移为 DSH 会话、工作区与 MCP 注册。

Skill Manager page in the DSH settings panel: browse system / user / workspace / preset skills, expand a skill to its file tree, view and edit files, import skills from a zip, and export or delete them (system skills read-only).

Automatic type-check diagnostics: after the model edits or creates TS files, runs `tsc --noEmit` in the background (debounced per project) and reports errors via the `code_check` tool — grouped by file with line/column, severity and TS error codes, closing the "edit → check → fix" loop.

Review Changes panel above the web composer with a VS Code sidebar bridge: send editor selections, drag files/folders as tags, and batch accept/reject every listed file.

Git hygiene checker: read-only scan of merged and stale branches, oversized tracked files, untracked files and uncommitted work, with cleanup suggestions (it never deletes anything).

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

In-chat preview for produced files: click a produced-file chip to render Markdown (server-side markdown-it + highlight.js), images, or plain text right in the conversation; system-app open and reveal-in-folder stay one click away.

Give agents access to files on the machine where the browser runs: user authorizes a local directory via File System Access, tool calls relay over the plugin's own WebSocket; read-only compat mode for mobile/insecure contexts.

Adds a path-backed attachment dock for images, documents, archives, code, and other files, leaving file reading to the Agent's available tools.

DSH Web right-side output dock that collects session artifacts, previews user-facing files, and preserves tab state per session.

Incremental file mounting with read dedupe: mounted line ranges are never re-sent to the model, on-disk changes invalidate and remount, with a Mounted Files tab and token-savings accounting.

Right-side developer panel for DeepSeek Harness: files, session history, and git version control

Render Markdown to a standalone, self-contained HTML page: an `md_html_render` tool that works in a headless profile, plus a web drawer to browse, preview, edit and export local `.md` files; both share one renderer, with no runtime dependencies.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

A 轨迹解读 (trajectory interpretation) tab that summarizes each user round — what was wanted, how the assistant thought and executed, files/commands/errors — via a rules engine plus optional LLM narrative; user messages stay verbatim.