Plugins

A full-screen terminal workbench for DeepSeek Harness with a durable assistant, workspace-grouped project sessions, transcript-only scrolling, and structured thinking, tool, diff, plan, and subagent views.

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.

DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.

One-click collapse of every expanded section (Think rows, tool cards) with a live-count pill and a customizable hotkey.

JetBrains Junie CLI as a one-shot DeepSeek Harness subagent provider over the Agent Client Protocol, with a settings page for model and thinking depth.

Reads local txt novels inside the chat dialog: chapters are detected automatically, the novel text is paginated in the assistant thinking block, a next-chapter button continues in the same reply, progress is remembered, and visible replies are fixed summaries.

Reasoning-effort slider that replaces the composer model seat: one rail over the levels the current model declares (off/low/high/max on DeepSeek), with a 241-frame portrait that evolves frame by frame as you drag and a per-model choice that survives restarts. Uninstall restores the shipped picker.

Skill that switches the displayed reasoning to Simplified Chinese: it enables the built-in experimental reasoning translation, pins provider bing and target language zh, then verifies and troubleshoots the result. The same repository also ships an optional one-install preset plugin for users who want the same setup without running the steps. Requires the DSH 0.2.1 line with the experimental reasoning-translation bundle and a Web or Desktop GUI; the default provider is bing, so expanded reasoning text is sent to Bing.

Renders a Live2D Cubism 4 model as the DSH web UI background: a transparent click-through canvas that covers the window without blocking any control. Eyes, head and body follow the pointer; expressions track the agent state (thinking, running a tool, turn finished, error, waiting) and the conversation (message arrives, reply ends, question asked); after an idle delay the character shows speech bubbles and plays motions and expressions drawn at random from pools you tick. Settings list the models under ~/.dsh/live2d-stage/models, expose position, scale, opacity, gaze strength and every interval and probability, and open a resizable live preview of the same canvas. Expressions and motions a model3.json omits are detected from the model folder; one sample model is included.

Judges the right reasoning level locally from the current draft and recent turns and switches it in one click; warns when the context grows long and tells apart "new topic" from "same unfinished task" — less overthinking on simple tasks, enough reasoning on hard ones.

System Duo for DeepSeek Harness. Make your agent think fast and slow: System One decision models triage, guard, shield, mask and check your agent loop beside System Two (vllm-sr/auto), with a free app.vllm-sr.ai key.

Whole-PDF paper translation for DSH on top of a BabelDOC installation you provide (Python CLI, with an OpenAI-compatible API key in its config.toml): bilingual dual-page output, a token cost estimate before running, a per-domain glossary reused across papers, and the server-side thinking overhead disabled for translation.

DeepSeek Harness (DSH) plugin: edit a finalized assistant reply and its reasoning/thinking chain right in the conversation. A pencil action opens a single-message editor; edits become a plugin message projection, so the model and the UI only ever see your

Session board orb: live thinking and tool progress per session, task duration, context usage and 12h/30d usage stats; click through to any session.

Prompt enhancement for the DSH Web GUI composer: pick a style before generating (logic-only, structured, or concise), or supply or clear a custom system prompt in settings; a sparkle button or Shift+Tab rewrites the current draft through the harness model, streams the result into an inline preview (original vs enhanced) with a live thinking timer, fills it back with one click, keeps an undo bar, and offers settings for model route, temperature, length limits, context awareness, undo-bar behavior and shortcuts.

DeepSeek 官方思考链完整复刻：思考内容跟随用户语言，并以自绘的 assistant-step 渲染器对齐官方思考面板（思考中多行滚动预览、展开看完整推理、左侧竖线、深度思考标题与耗时）。 Full DeepSeek thinking-chain parity: reasoning language follows the user, and a self-owned assistant-step renderer reproduces the official thinking panel.

Adds a tier bar to the DSH composer with three thinking tiers (normal, strict, max), an exclusive loop mode whose three levels run 3, 5 or 8 self-review rounds, and a counter-review toggle that stacks on either; the model reads the current tier through the clarify_tier and forge_level tools.

A 44x44 always-on-top desktop ball for DSH that reflects what the agent is actually doing (thinking, searching, web fetch, error, waiting for input) and shows an exclamation or question-mark badge when a task finishes or needs an answer while you are away. Windows only; it downloads its own Electron runtime on first use.

A separate narrow-screen web surface for DeepSeek Harness rather than the desktop GUI scaled down: it serves its own session list and chat stream behind a random access token over LAN, a tunnel (cloudflared, localtunnel or localhost.run) or an SSH reverse forward through a server you own. On the phone it streams assistant text, thinking, tool calls and results, sends prompts, stops the running turn, answers blocking questions and tool approvals (including ones waiting in other sessions), switches model, thinking level and permission preset, sends up to four photos compressed on the device, and keeps the computer awake.

Registers system-prompt sections that make the model reason in Simplified or Traditional Chinese, with strict/prefer modes and an optional reply-language policy. Adds a /thinking-zh command for per-session switching. Zero runtime dependencies.

Generative background music while the model streams, plus completion, approval and attention chimes: hear whether the agent is thinking, still working, or waiting for you without watching the screen.

Brings the models of the SCNet (超算互联网) Computing Service desktop client into DSH by reusing the API key that client already wrote, with a 30-model catalog and a per-model default thinking level.

Expands the assistant reasoning block while it streams and folds it back when done, animated in both directions; the sidebar switch only controls whether that happens automatically.

Time-based model routing: a settings panel defines weekday peak and off-peak windows and the provider/model each one uses, the choices are read from the harness registry (API keys and subscription logins alike), and a global switch decides whether that policy sets the model and reasoning effort of every request. The switch is independent per session, each session row carries a light showing its own state, and the settings panel names the model in force right now and why. A day no window matches — every weekend and holiday — uses the primary model of the first plan; the advanced thinking model is a separate axis, used only when a session itself asks for max reasoning.