9 RESULTS · “npu”
v1.6.8 · MIT
DSH web plugin for the composer: shell-style prompt history (Up/Down with prefix search, Ctrl+R reverse search), Codex-style history completion and next-prompt prediction ghosted in the empty input (Tab or → to accept), a selection toolbar (copy / quote /
v0.5.4 · MIT
Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models
v1.17.0 · MIT
DSH 桌面消息提醒插件 / desktop notification and message alerts for DeepSeek Harness web:需要你操作(可操作提醒)与回复完成提醒,系统通知+提示音+标签页标题,设置页开关 + 中英通知语言
v0.29.2 · MIT
DSH Web 输入体验增强插件:可配置发送/换行键位 + 自定义输入框右键菜单 + 面板尺寸记忆 + 快捷指令(分类 / 跨分类移动 / 关·每次·仅首次三种插入模式 / 存 ~/.dsh/quick-prompts.json)+ 提示词优化(0.11.1 起工具行有独立「优化」按钮、带秒表与斜杠命令保护、写回前比对草稿) + OpenCode 会话请求头 + Windows 默认终端切换(把模型的 PowerShell 工具换成 Git Bash)+ 官方持久终端六件套(terminal_open/r
v0.16.2 · MIT
Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support.
v6.1.1 · MIT
All-in-one AI desktop app: one-click install for Claude Code, Codex CLI, DeepSeek and more, manage AI accounts and quotas, smart model routing with auto-failover, voice input, and run local LLMs. Bonus: a Token Pet that grows as you use AI.
v0.9.46 · MIT
Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).
v0.3.7 · MIT
为 DeepSeek Harness 提供电脑控制插件:新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入(目前支持macos)|Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.
v0.20.1 · MIT
Git status badges for DeepSeek Harness: an input-row chip and a sidebar session-row action glyph, on every install — no patch and no manual step. Event-driven freshness over SSE.