@anionex/dsh-vision-toolkit
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
176 results
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
Install the full dsh-mnemon integration from the Mnemon repository.
DSH Web selection-annotation plugin: select assistant text, annotate (optional), and press Enter to send the annotation block with your message — the model replies to each annotation by number, with hoverable chips in the reply.
DSH Web selection-annotation plugin: select assistant text, annotate (optional), and press Enter to send the annotation block with your message — the model replies to each annotation by number, with hoverable chips in the reply.
DSH web plugin: select conversation text -> ask in a right-side panel -> a dedicated follow-up session (❓<topic>) in the same workspace, without interrupting the main conversation. Thin consumer of dsh-better-sidebar.
Configurable running-turn status text for dsh Web: General Settings row plus the conversationStatus provider for the chat view
DSH 专属语音输入插件:点按或按住 Alt 说话、松开/再点按转文字,支持热词替换表(hot.txt)、自定义润色提示词、录音电平指示。默认本地离线识别(SenseVoice,零配置零 key、音频不出本机),自动回退浏览器 Web Speech,可选云端 ASR 与润色(复用 DSH 模型)。Voice input for DeepSeek Harness: tap or hold Alt to talk, get text in the composer — local SenseVoice by default, zero config, zero API key.
DSH diff-viewer plugin: PiUI-style visual diff surface (split/unified, change bars, real file line numbers, word-level marks, collapsed context, windowed rendering) replacing the stock DiffBlock for write/edit tool calls. Registers into the ui-tool keyed toolview slots.
Composer draft polisher for DeepSeek Harness: a ✨ button in the composer tool row rewrites the current draft with a zero-prefix flash call and fills the polished text straight back into the input box.
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
OpenViking retrieval, resource management, auto-recall and session memory for DeepSeek Harness.
DeepSeek Harness plugin: paragraph-batched streaming reveals with 8 designed animations, smooth scroll-follow and a settings panel.
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
DSH peer link — point-to-point messaging between dsh agents and other local agent sessions (e.g. Claude Code) over unix sockets. Independent plugin: register as a peer, receive messages into agent context, reply with peer_send, list peers with peer_list.
Session folders for the DSH web sidebar: one-level named folders per workspace to group sessions, drag-and-drop or context menu to move them, server-side persistence. Status badges mirror the built-in session browser.
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, live per-task cost, prices and context windows.
Real-time token consumption HUD for DeepSeek Harness: a sleek tech-style panel showing live token usage, context pressure and cost estimates across sessions
Third-party DSH WebUI enhancement plugin: custom backgrounds, theme colors, prompt presets, token visibility, and manual context compaction.
Brings open-mcp-apps into DeepSeek Harness (dsh): an Apps section in the sidebar, one container per app with its own workspace and conversation, an agent-presence strip under the app, and inline app rendering for MCP tool calls.
Local OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR 插件:图片转文字,PP-OCRv5 + ONNX Runtime,完全离线,支持 TUI 与 Web。
ChatGPT-style text selection helper for DeepSeek Harness: select text in a conversation and a floating 「询问 DeepSeek」 button appears; click it to quote the selection into the composer.
Composer expand toggle for DeepSeek Harness: a ⬆/⬇ button in the composer tool row toggles the input between the default capped height and a tall 70vh writing view, so long drafts stay readable.