Plugins

A green pixel-Ork mascot for DSH Web that masks model thinking and output as Waaaaaaagh! until clicked to reveal, plus a random-length input mask.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

DeepSeek Harness Web 客户端插件：接管 composer 的【模型与推理等级】座位，在「模型」子列表首位插入一个大小写不敏感的连续子串模糊搜索框（div>input），实时过滤已配置模型；弹框宽度锁定防抖动。

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

Editable local and desktop dictation for DeepSeek Harness

Vocabulary flashcards for agent wait time: a spelling card appears in the Web client lower-right after ~18s of agent activity and retreats when the session finishes or needs input; optional shared progress with the local VibeGap desktop app.

Voice input for DeepSeek Harness: hold Space to speak, release to insert. Zero dependencies, Web Speech API. / 语音输入：长按空格说话，松开上屏，零依赖。

Dictate prompts into the DeepSeek Harness Web Client — a microphone in the composer, with swappable transcription: hosted Whisper API, self-hosted server, or a fully offline whisper.cpp binary.

Ghost-text completion for the composer: FIM suggestions stream in inline after a typing pause (SSE, first token rendered immediately), Tab accepts one word at a time and Shift+Tab takes all, in-flight requests are truly cancelled on retyping or Esc. Plus two-layer typo checking: a browser-local dictionary scan (Chinese wrong phrases, English misspellings and proper-noun capitalization, user-defined per-browser entries) with a debounced LLM context pass, underlined in red in the text with per-item navigation and click-to-fix.

One-click silent DSH restart button in the composer input bar. DeepSeek Harness plugin (dsh-plugin).

把长文本渲染成图片发送，利用每图 384 token 封顶压缩 LLM 输入 token，专为DeepSeek Harness设计的插件；Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.

一个输入框增强工具，可以锁住发送按钮、暂存输入框内容

DSH web plugin: desktop notification, chime, and title flash when a session stops — finished output or waiting for human input. Click a notification to jump to that session.

Configure model input capabilities and reasoning efforts for DeepSeek Harness

Per-project LLM token usage and RMB cost in the DSH Web sidebar, split by input (cache miss), cache hit, and output with model price auto-pricing.

DeepSeek Harness 语音输入插件：火山引擎流式 ASR（豆包 Seed ASR），流式回填输入框。Voice input for DSH via Volcengine streaming ASR.

给 DeepSeek Harness（DSH / DeepSeek Hermes）加语音能力的社区插件：输入框语音输入（可配快捷键）+ 回答朗读（微软 Edge 神经网络音色，可换音色、可试听），无需 API Key。

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.

Silence Chrome/iCloud password-manager prompts over DeepSeek Harness API-key inputs: rewrites password-type secret fields into masked text fields so browser password managers never treat DSH API keys as account passwords.

SenseVoice 语音输入插件 for DeepSeek Harness：在对话输入框旁添加麦克风按钮，录音后调用本地 SenseVoice 服务转成文本填入输入框。首次使用自动下载模型并显示进度，后端由插件自动启动。

Voice input for the web UI: a mic button in the composer that transcribes speech into the draft via the Web Speech API, with an optional auto-send toggle.

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Long-lived background terminal jobs for dsh: launch processes in a PTY, write input (including control sequences like Ctrl+C), page through ring-buffered output, and stop jobs gracefully or forcefully.

Desktop (native) control for dsh as a stdio JSON-RPC bridge over a Python core: capture the screen, inject pointer/keyboard input, drive accessibility-tree actions, and gate high-risk operations behind required confirmations.