플러그인

ChatGPT-style side chat for the DSH Web GUI: ask small questions about the current topic in a floating side panel, answered by an independent lightweight session over the official /api RPC — the main conversation is never touched. Streaming text, collapsible reasoning, tool chips, stop button, agent-preset selector, and an automatic context snapshot from the visible main chat.

Select text in any Windows app to explain or translate it with the Harness agent, answered in a native always-on-top overlay.

Teaching board view: agent-generated self-contained HTML is projected into a sandboxed iframe as a board, annotated by hand (brush, four colours, eraser, undo), extended in place across several tool calls, and screenshotted back into the conversation as a real user message.

Replace the dsh-whale-widget mascot with your own image through a built-in cutout pipeline, plus a session-header restart button, a browser heartbeat, and an opt-in patch self-heal that is off by default.

flykit for DeepSeek Harness — status line, file explorer with editor and live watch, and Claude Code / Pi / Codex terminals in the web GUI. Fly your agents.

Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.

The dsh grep and glob tools executed in-process by the dsh-rs addon, with the packaged-ripgrep spawn as the fallback

Persistent, conversation-decoupled multi-shell terminal panel for DeepSeek Harness (DSH): real tmux TTYs, 11 model tools, draggable floating panel

Fail-closed runtime tool-call loop guard for DeepSeek Harness.

Zhihu (知乎) for DeepSeek Harness: wraps the local pyzhihu-cli as 18 zhihu_* tools — 14 read-only (search, hot list, question, answer, user, feed, topic, notifications, collections) plus 4 publishing tools that are not registered until readOnly is turned off — with a web panel in the sidebar for login, config and lookups.

Read-only bridge that surfaces Claude Code's existing project memory in DSH — git-root-aware resolution, credential redaction before injection, and an on-demand recall tool. Zero runtime dependencies.

MCP server management panel in Settings: add, edit, enable/disable and delete servers across user and workspace scopes with form or JSON editing, and auto-register discovered MCP tools as native conversation tools.

Five web UI tools in one plugin: a provider + model two-button selector with reasoning-level control, collapse/expand-all for sidebar workspace groups, a session tab listing the files the session changed (needs kernel 0.1.2-alpha.1+, silently absent on older kernels), a workspace badge next to the session title, and a settings page that toggles them.

Three tools for DeepSeek Harness: typeset LaTeX formulas into images, draw mathematical figures from a declarative spec, and convert a formula or SVG into an image ready to embed in a document.

Peer communication between conversations in one DeepSeek Harness process: list the conversations the workspace shows, link one under a nickname, message it without waiting for its turn to end, read its progress without waking it, and declare rules for your own tool calls.

Adds a Long text button to the composer tool row: write or paste the body in an editor overlay, and on save it is written to <workspace>/.dsh-longtext/<timestamp>_<title>.md and an @ path reference to that file is appended to the composer, leaving the conversation free of the long text itself.

Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.

Applies per-workspace default Agent and permission presets to new root sessions automatically (Settings - Workspace defaults), using only official extension points.

In-app local notification center for DSH: a sidebar Notifications entry with unread badge, full-screen center with level color coding (info/success/warn/error), time/source filters, sorting, title/content search, read/unread, delete, detail popup with one-click copy, and pagination; written by the notify_add agent tool or the dsh-localnotify CLI (with auto-cleanup retention), page refreshes live, UI follows dsh web language (zh/en).

Keeps notes as local Markdown files grouped by directory under a root folder you choose, with a sidebar page, AGENTS-style rule files surfaced as writing context, and six agent tools.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Minimal DSH Web transcript toggle: hide thinking, tool-call, and turn-process rows from the session header while preserving assistant answer text.

DSH plugin: persistent SQLite tools for the agent (sqlite_query / sqlite_exec / sqlite_tables / sqlite_export / sqlite_import), a read-only table browser settings page, and a persistence-usage prompt rule — zero runtime deps beyond Node 22 node:sqlite.

会话注入门控：给 DeepSeek Harness (dsh) 加一个会话级上下文裁剪闸门，按会话取消/恢复插件贡献的 skill、tool、系统提示词段落——3 条影子通道、5 条本地路由、零依赖零配置。Per-session injection gate for DeepSeek Harness (dsh): trim skills, tools and prompt sections per session. Zero-config, zero dependencies.