Plugins

Read-only DSH Web plugin for inspecting and searching Milvus or Zilliz Cloud collections from chat, including scalar, BM25, dense, and hybrid queries.

Visual goal lifecycle for the DSH web UI: a composer dock to create, multiline-edit, pause, resume, complete and clear session goals with live round progress, plus a phase-dot composer entry and a settings-page goal overview.

Codex-style temporary side conversations for DeepSeek Harness.

Manages archived DSH sessions in the native sidebar with conversation search, restore, and confirmed safe permanent deletion.

Chat column width and alignment control, numbered question history with keyboard navigation and auto-load of older questions, and markdown outline rails for both the conversation and the file preview.

OpenAI Codex provider for DeepSeek Harness with ChatGPT OAuth, native settings, and account usage.

Adds a red permanent-delete action with a confirmation dialog to the native session menu.

Adds a non-uniform conversation density map(chat history markers) to the right of the DSH chat area: one tick per turn, with tick length and spacing reflecting message size, clickable to jump to a turn and expanding on hover when crowded.

Vertical message pointer rail on the left edge of the chat: one dash per user message, click to scroll to that message, hover for a preview bubble.

Web chat entry for DeepSeek Harness: a sidebar button opening chat.deepseek.com in a dedicated desktop window under dsh-desktop, with in-webview fallback for plain web environments.

Unified messaging gateway for DeepSeek Harness: 27 IM platforms (Telegram, QQ, WeChat, Discord, WhatsApp, Feishu and more) in one plugin, with QR scan-to-authorize, per-platform workspaces, slash commands, and a web setup dialog.

Adds a "Work Roles" tab and a pixel-art office overlay to the DeepSeek Harness Web UI: 508 built-in role cards (The Agency 255 + agency-agents-zh 253) with search, EN/ZH toggle and department filter; draggable Canvas 2D pixel characters that stand, type and pace, with idle chat that can plug into AI. One-command npm install, no dsh source changes.

Full local-first issue board embedded in the DSH web GUI: Kanban / list / Gantt / workflow / dashboard views, AI chat per task, attachments and labels, auto-claim of todo tasks driven by dsh-routines — data lives in local SQLite (dsh plugin add @ttmouse/dsh-taskboard).

Multi-channel IM gateway plugin for DeepSeek Harness (dsh): DingTalk / QQ / WeChat(iLink) with QR-scan binding, streaming replies, and a unified ctx.imGateway service. 为 DeepSeek Harness 提供钉钉/QQ/个人微信多 IM 通道接入。

Multi-platform IM gateway for DSH: Feishu (Lark) WebSocket long connection (no public URL), WeCom AES-encrypted callbacks, and Telegram long polling — per-chat agent sessions, whitelist access, and a visual settings card in the web GUI.

WeChat automation for DSH: push task progress to WeChat, listen for messages with keyword auto-reply, and a WeChat ↔ DSH two-way bridge controllable from the settings page, built on wxauto4.

WeChat Official Account content studio: anti-homogenization rotation writing, low-creativity remediation playbook, blessing-image visual baseline, gpt-image pipeline with OCR acceptance, and the measured xiaolvshu draft web API.

Preview Mermaid diagrams as images via local rendering in DSH Web when the chat message contains a Mermaid fenced code block, and also allow integration with external rendering servers.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.

聊天流中悬挂皮鞭，甩动鞭梢（>2.0 px/ms）即向 agent 发送 go work 消息 | A whip hanging in the chat stream; flick the tip (>2.0 px/ms) to send the agent a "go work!" message

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Runs the built-in web_search tool server-side on an OpenRouter-compatible gateway, so search uses the same endpoint and key as the chat models: three request protocols, every citation shape parsed (including snippets recovered from the cited span), and a settings card with a live connection test.