Plugins

A six-stop reasoning-effort slider for DeepSeek Harness, with a pixel-texture Ultracode mode that sweeps in from right to left and adapts to light and dark themes.

Adapts the DSH Web GUI for mobile screens and adds a workspace file browser with previews and downloads.

Scratchpad panel for DeepSeek Harness: tagged notes, image/file attachments, Markdown task lists, send-to-chat, a wake-up shortcut, JSON export/import, and Agent tools.

Redraw the left-hand workspace sidebar to add color highlighting, sorting, status indicators, and system notifications. You can also switch back to the original sidebar, which likewise implements some of these features.

DSH text-to-image/image-to-image plugin: compatible with OpenAI-style image generation APIs, with 多米API as the default; standard OpenAI endpoints may require protocol, image-to-image mode and size adjustments; text-to-image and URL reference images do not use COS, while local reference images can be compressed and stored in COS; custom prompt suffixes are supported.

Read-only GitHub research tools for the agent - repository search, repo health check (stars, license, last push, size, archived), dependency manifests, and single-file reads over the raw channel - plus an oss-reuse skill that makes the agent search GitHub and check real dependencies before writing code, so features are assembled from existing open-source projects instead of rewritten; nothing is cloned and no disk space is used.

Configures forward proxies per enabled provider in Settings (HTTP/HTTPS/SOCKS5), keeping unconfigured providers and other traffic direct.

DeepSeek Harness (`dsh`) 可视化本地游戏汉化插件 — 支持 Unity、RPG Maker、Ren'Py、Godot、WOLF、TyranoScript 六大引擎，提供原生玻璃窗口、双栏对照审校、多模型子 Agent 派发与 100% 读回安全写回。Visual game localization plugin for DeepSeek Harness.

Douyin (抖音) automation for DeepSeek Harness: watch private messages and wake the agent event-driven, plus 10 tools (read DM, send DM, comment, @ mention, reply, delete comment, read notice, share video card, pick feed candidates, cookie backup/restore) —

Deletes any DSH session from its sidebar row, in bulk, or through a settings panel — into a recoverable trash, with ghost entries pruned automatically.

Feishu/Lark bridge for DeepSeek Harness (dsh): one Feishu topic = one dsh session, in-card approvals and questions, streaming cards, model and permission switching, Web settings page, long connection with no public endpoint.

Read local EPUB, TXT and Markdown novels below selected native DSH chat regions on explicit expansion, preserving real reasoning and tool output without sending novel text to the model. Requires DSH >=0.2.1-rc.2 <0.3.0-0.

Reads one Genshin Impact account (characters, talents, weapons, artifacts, wish history) into a single snapshot, then exposes it as six agent tools and a six-tab panel. Artifact substats come from the public in-game character showcase; scoring ships both CV and per-character weight models with six grade tiers; wish analysis covers pity, luck tiers and per-pool progress. Needs a Miyoushe QR login to read characters, weapons and wish history; showcase data is public by UID.

Session-level autonomy gears for DSH: a rail on the edge of the conversation area switches P/R/NT/NC/NE/M-/M+/D/A and injects the active gear's behavioral prompt into every request; the model's set_gear tool can only downshift, and handbrake H blocks all tool calls. The set_gear tool can downshift on its own; upshifts need user approval.

WeChat Mini Program dev loop for DeepSeek-Harness: check IDE status, launch the DevTools project, trigger preview and get the QR code straight into the conversation, parse compile errors into file/line/column, and watch it all from a sidebar panel. Six agent tools over the official DevTools CLI — honest about needing a one-time scan-login, never fakes a preview. Requires the Windows WeChat DevTools CLI and a one-time QR login.

Lists the skills in the shared skills directory with their source and version, installs and updates them from a GitHub repo, removes them to a recycle bin kept for 7 days, and controls which agents can see each skill and whether the model may invoke it.

Adds a Chat/Work switch in the DSH Desktop titlebar: Chat embeds the DeepSeek web chat (chat.deepseek.com) in a native webview with no DSH API calls from the plugin and is the default on first launch, Work keeps the native agent UI, the page stays mounted across switches, and a confirm-first dialog can copy chat text into a work-mode draft without sending it.

Drives the sidebar browser already open on the right: same cookies and same sign-in, a pointer you can watch, no second window.

Black-box GUI testing for DeepSeek Harness: an AI tester drives a real Windows virtual machine using only screenshots and mouse/keyboard, so its verdicts rest on pixels instead of logs or source code. Ships the dsh-vm-tester plugin with twelve vm_* tools (status, UI tree, screenshot, click, type, type-secret, key, basic key, wait, snapshot, upload, download), a reverse-tunnel guest agent for Windows, and run verification scripts. Needs Windows, VirtualBox 7 and a Windows guest VM with the bundled agent before any vm tool works.

Records DeepSeek Harness runtime errors and coding retrospectives as an interactive GPU graph, and feeds the recorded lessons back into the model's context.

Use Jev to adjust main-chat reasoning effort without switching its model, independently select and apply fresh sub-agent capability and effort, and inspect decisions with per-reply allocation feedback.

Set the provider, model and reasoning effort delegated subagents run with, from one chip beside the composer: a per-conversation override and a profile-wide default share the same two controls, and the chip always shows the effective route. Applied when each in-process child is created (agent/created + agent.model.select()); no settings page, no preset edits, no model-facing tool parameters.

Named subagent presets bound to model-route allowlists, where an out-of-list child model is refused before a delegation starts and each child conversation shows the model its last request actually used.

Project-level usage hub for DSH: per-project token, time and cost, with half-hour swimlanes, 26-week activity heatmaps and provider balance alerts; unpriceable usage is flagged rather than estimated.