dsh-model-info-hint
Show a hover hint with a model's full configuration (input types, context window, max tokens, protocol, base URL, credential env, …) over each model in the DeepSeek Harness web model picker, read from ~/.dsh/settings.yaml.
225 results
Show a hover hint with a model's full configuration (input types, context window, max tokens, protocol, base URL, credential env, …) over each model in the DeepSeek Harness web model picker, read from ~/.dsh/settings.yaml.
Reasoning effort slider for DeepSeek Harness — a client (web) bundle that injects a per-session slider into the conversation input, shown when the selected model declares reasoning effort levels. Works with any provider that has reasoning efforts (Bailian, DeepSeek official, OpenAI o-series, etc.)
RainbowSpeak (虹语) — rainbow marquee border for the DeepSeek Harness chat composer: a continuously flowing conic-gradient ring traced along the input card boundary.
DeepSeek Harness (dsh) plugin: an IDE-style Git panel in the Web GUI — branch/history overview, uncommitted changes with commit & amend, diff stats, and a zsh-style branch marker in the input bar.
Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图:连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口
DSH WebUI 插件:把聊天输入框变成代码编辑器一样的输入风格(CodeMirror 6 接管 conversation.composer.bar)。
Screenshot/file paste board for the DSH Web GUI: paste, drag or browse to save files locally, show reference chips above the input, and auto-append file paths when sending a message.
DeepSeek Harness (dsh) rules, commands & skills manager: /rules slash command, settings panel with visual rule editing, command list, user-defined custom commands (with {input} argument support, disable/enable), skill management (view/disable/enable/delet
Voice chat for DSH Web: speech-to-text input (Web Speech) + auto/manual read-aloud of assistant replies (TTS) with voice/rate/pitch settings. Pure client UI, minimal Node entry.
Voice input plugin for DeepSeek Harness web: a mic button in the composer that recognizes speech (Web Speech API) and fills the draft, with optional auto-send.
Real-time DeepSeek account balance and per-session token usage for the DeepSeek Harness web UI: per-currency quota card with availability badge and refresh, plus current-session input/output/cache token breakdown, as an installable Settings section.
DSH web plugin: plays opencode sound effects on task completion/failure/input-request with a native Settings panel (45-sound pack, per-event picker + on/off switch, preview, volume).
Composer auto-hide on scroll for the dsh web GUI: the input bar follows the message flow off-screen when you scroll up to read context, and slides back in when you return to the latest message.
Speech suite for DeepSeek Harness: free edge-tts page announce, speech-to-text voice input (Bailian paraformer-realtime-v2) with Alt+Q hotkey, tap/hold modes, auto-send, and stop-playback-on-record
Codex OAuth provider with native compaction and image input support for DeepSeek Harness.
DSH Web GUI layout fix: composer (input bar + bottom status bar) leaves the scroll region — message scrolling stops above the input bar, the scrollbar no longer covers the input area
图片转文字输入插件:给无视觉能力的纯文本 LLM(DeepSeek 等)提供图片输入接管。输入框粘贴/拖拽图片后一键转为结构化文字描述;视觉 API 配置在设置页填写,支持任意 OpenAI 兼容视觉模型(qwen-vl / gpt-4o / glm-4v 等)。多模态模型下自动让位,不劫持原生图片通道。
Dual-face (host + client) plugin: independent text-output ocr_image tool + tools/execute read_image capability dispatch + ctx.ocr seam, with a conversation.input.left OCR toggle button.
DSH web focus mode plugin: ?focus=conversation.composer shows only the input area, ?focus=conversation.session shows only the message flow, both hiding the DSH main sidebar; auto-resumes the most recent non-blank session when none is current.
Offline Parakeet voice input for DeepSeek Harness
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。
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
Configure model input capabilities and reasoning efforts for DeepSeek Harness
DSH web composer resizer: drag the handle on the top edge of the input card — up to grow, down to shrink — with bottom-anchored scrolling for long drafts.