Plugins

Adds a take screenshot tool plus two optional automatic capture points, putting the screen into the conversation as an image block; requires an image-capable model.

Provides the see_image tool for DSH: send an image file to a configurable OpenAI-compatible vision model and relay its description back to a text-only model.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.

Adds selectable animated skins to the "Deep diving..." status row, with configurable size and optional status-text replacement.

File explorer for the dock workbench: tree browsing of the session workspace with create/rename/copy-paste/delete, drag-and-drop import and paste of local files and clipboard images.

Version management for dsh: inspect the installed version against every npm channel or version line, install or downgrade in one click, stream the install log live (rollback-snapshot copy progress, npm extraction progress, elapsed time), roll back instantly from local snapshots, and automate the cycle with a policy engine (silent auto-update, execution windows, daily checks). Never stops npm mid-install — a wedged run is only stopped after an hour, and a half-committed global tree is detected and repaired from the pre-install snapshot automatically. Confirms before installing a found update, auto-restarts the host after install, and falls back to a mirror when the primary registry is unreachable.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Local OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR 插件：图片转文字，PP-OCRv5 + ONNX Runtime，完全离线，支持 TUI 与 Web。

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

A lightweight, general-purpose attachment Dock for DSH: paste, drop, or choose images, PDFs, documents, archives, code, and other files, review and manage them before sending, then pass them to the Agent as local paths. It gives non-image files a consistent attachment entry point.

DSH Web background settings: upload a local image or pick a preset ambiance, with live preview and persistent settings.

DeepSeek account balance and current-session spend estimate in a top-bar chip and settings card, with pause-aware auto-refresh, an editable official price table, a `deepseek_balance` model tool, and a bilingual UI.

Session cost estimate in a status bar at the bottom of the conversation (per-model token pricing, CNY) plus the live DeepSeek account balance via the official balance API.

A DeepSeek Harness plugin for real-time token tracking and highly accurate session cost estimation, featuring dynamic peak/off-peak pricing support.

QQ Bot text and image channel plugin for DeepSeek Harness

Render local image paths from assistant replies inline in the message body (9 formats, click-to-zoom lightbox, adjustable size).

Activity heatmap in the DSH Web sidebar: GitHub-style grid of daily commits, token usage, and estimated spend, with a today stats line for all-session token totals, cache hit rate, and per-model auto-priced cost.

DeepSeek API balance and 24-hour usage dashboard in Settings, with estimated spend, token counts, request counts, and an hourly timeline.

DSH plugin: drive PhotoCraft (raster image editing) headlessly through its own CLI and MCP server.

GitHub-style activity heatmap in the sidebar, one cell per day over 30/90/365-day ranges, with token usage and estimated cost per model and editable per-model prices.

SAO (Sword Art Online) theme for DeepSeek Harness: a Link Start startup animation rendered ahead of the app shell, with Kirito/Asuna voice lines, plus theme and surface colours, liquid or frosted glass, per-component transparency, nine built-in or uploaded wallpapers, and a model-intensity slider.

Deploys the qq-bridge engine to a remote host over SSH and wires it into DeepSeek Harness: environment check, config generation that keeps credentials out of the repo, systemd units for the bridge plus daily-archive, today-sync and watchdog timers, and four tools to check, configure, deploy and inspect the install. Adds a lite reply mode that calls the DeepSeek chat completions API directly, switchable persona cards, image and video understanding, and keyword search over archived group chats.