dsh-dictation
Editable local and desktop dictation for DeepSeek Harness
197 results
Editable local and desktop dictation for DeepSeek Harness
Offline content-addressed proof that a recorded build stayed within declared inputs and outputs
Web agent-heartbeat sonification for DeepSeek Harness: a calm lub-dub hum while agents work, ticks on streaming output, chime when a session awaits your input
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
DeepSeek Harness plugin: a Git commit-graph view with lanes, refs, and worktree management, beside the chat input
DeepSeek Harness web plugin: a Model Capabilities settings page for declaring model input modalities, context window, output cap and image budgets without hand-editing settings.yaml.
A faithful Windows 98 skin for the DeepSeek Harness web GUI: teal desktop, silver beveled panels, navy accents, pixelated MS Sans Serif, beveled buttons, sunken inputs and checkerboard scrollbars — derived from the classic 98.css design system.
DSH web plugin: play a chime when a turn completes or your input (approval / question / plan review) is needed — foreground or background.
DSH 模型视觉开关:设置页「模型视觉」行,为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态(settings.mutate 官方通道,热生效)。
DeepSeek Harness Web 插件:「光污染」RGB 光效皮肤 —— 输入框/侧栏等 RGB 流光光效(独立皮肤,不修改任何原皮肤)。
DSH Prompt Optimization plugin: one-click prompt optimization in the composer input, with an optional dedicated optimizer model in Settings
Zero-token offline math input for DeepSeek Harness: handwriting recognition, screenshot OCR, LaTeX editor, and inline LaTeX rendering.
Real-time token usage dashboard for DeepSeek Harness — live totals (input/output/cache/reasoning), filters by model, day, month and project, and a smooth trend chart. · 实时 Token 用量仪表盘:总量/输入/输出/缓存命中按模型、按天、按月、按项目随选,附趋势曲线。
Sage GUI Toolkit — Windows desktop control tools (screen layout / annotated screenshot / click / type / key / scroll / wait / window / UIA structured query) via PowerShell + SendInput + UIAutomation, DPI-aware and multi-monitor safe
Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.
Wake-word voice input for DeepSeek Harness: an always-on, low-power keyword spotter wakes the agent, then local ASR turns what you say next into a submitted message. No API key, no cloud, no typing.
DSH 输入历史导航插件(纯 client 双面):对话输入框中按 ↑/↓ 方向键遍历当前会话发送过的消息(shell history 式交互),浏览中编辑或发送即退出。
DSH Input Translator: 输入框悬浮快捷翻译与历史找回挂件 (支持当前会话模型 / 智谱 GLM-4-Flash / 自定义 OpenAI 兼容端点)
Voice control for DSH web: speech-to-text into the composer (with auto-send) and spoken playback of assistant replies via the Web Speech API
Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run server). Bilingual UI (zh/en)
Filter input for the composer model menu: case-insensitive list filtering with combobox keyboard navigation, rendered with the shipped menu design
DSH plugin exposing adb-based tools that let the model operate an Android phone (screenshot, UI dump, tap, swipe, input text, press keys, open apps). | 让模型通过 adb 操作安卓手机的 DSH 插件(截图、UI 树、点击、滑动、输入文本、按键、打开应用)。
Per-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
DeepSeek Harness plugin to audit and correct llm-pi-ai model capability declarations by probing the endpoint itself: out-of-range maxTokens, contextWindow, reasoning levels, image input.