208 results
Codex-style text annotation for DeepSeek Harness conversations: select text, add a quote with your comment, inject it into the composer, and expand sent annotations as a pill. / Codex 风格对话文字批注：选中原文加注释、引用进对话、发送后以「N 条注释」胶囊展开。
QuickLook-style space-key large preview for dsh-better-sidebar: press Space on the active file tab for an instant image / PDF / text overlay
Declutter the DeepSeek Harness chat: hide agent execution-log rows (Think / context injection / tool calls), tighten message spacing and font sizes, wrap messages in rounded-corner bubbles, and inject an editable "reply concisely" instruction into the system prompt.
Overlay reader for agent output files: Markdown/GFM rendering, in-panel PDF preview, DOCX/XLSX/PPTX text extraction, reply-end file chips. Pure JS, zero dependencies, no persistent UI.
Conversation full-width by default + pretext text measurement (DSH plugin)
Model-facing describe_image + extract_text tools for the DeepSeek Harness web GUI: gives a text-only model reliable image understanding and OCR through an OpenAI-compatible vision endpoint, with critical-inspection prompts, auto-preprocessing, retries, and a persistent answer cache.
DeepSeek Harness bundle that exposes Model Context Protocol (MCP) servers — stdio, streamable HTTP and legacy SSE — as native Harness tools, with a settings UI, live status, auto-reconnect, and backup/restore via local files or WebDAV.
Per-session Node REPL terminal in the DSH web UI: a session-local floating terminal (ghostty-web) bridged over WebSocket to an in-process node:repl that has the live agent Cordis Context (agent.ctx) in scope.
DSH plugin: convert user-sent non-text files (PDF/DOCX/XLSX/PPTX/HTML/CSV/EPUB/…) into LLM-friendly Markdown with Microsoft MarkItDown — composer file button + model-facing markitdown tool + send-time auto-convert.
A resizable right-side document rail for the DeepSeek Harness web GUI: shows Markdown / plain-text files beside your conversation with light and deep-navy themes, drag-to-resize, recent-file history, and auto-sync while the file changes on disk.
Run every DeepSeek Harness task directly in the FlowText Agent UI
Fix the DeepSeek Harness Web GUI over plain HTTP on a LAN: injects a crypto.randomUUID polyfill (getRandomValues-backed) before dsh bundle code runs. No official source changes needed.
VS Code-style minimap (text thumbnail + draggable viewport) overlay for the dsh web GUI's side file viewer
Auto-fold context/system messages in DSH conversation — hide the large system prompt / instructions by default, click to expand.
The see tool for the DeepSeek Harness: offline OCR with positions (macOS Vision) + ASCII layout art (PIL) + vision-model semantic description (mimo-v2.5 via the opencode-go gateway). Works with any model, including text-only ones.
A canvas the agent draws on and then sees: eyes_render draws text/shapes in the Web GUI, stores the PNG locally, and hands the result back to the model. Windows-only: eyes_ocr reads text via the built-in Windows OCR engine (Windows.Media.Ocr).
In-session full-text search for the DeepSeek Harness web GUI: kind filters, multi-term AND matching, keyboard navigation, copy-to-clipboard, and jump-to-message.
Session ID footer for DeepSeek Harness: shows the current session id in small text under the composer, click to copy.
替换侧边栏左上角的品牌名与构建徽标文案（默认 DSH Local Build + commit hash），经 WebUI 插件配置页卡片实时配置。 | Replace the sidebar's top-left brand name and build-revision badge text (defaults to DSH Local Build + commit hash) via a live settings card in the Plugin Config page.
DeepSeek Harness plugin: capture the provider model fingerprint (system_fingerprint) of every LLM call and show it as a hover-revealed plain-text suffix on each assistant message's metrics row in the Web UI.
DSH (DeepSeek Harness) file preview & editor plugin: in-browser workspace file tree, multi-format preview (code, Markdown, PDF, image, Office, HTML), online editing with version history, and full-text search. DSH 文件预览插件：工作区文件树浏览、代码/Markdown/PDF/图片/Office/HTML 多格式预览、在线编辑与版本回滚、全文搜索。
Web selection-add feature: float an 'Add to conversation' button over a text selection in the conversation body and prefill the composer draft
Input assistant for DeepSeek Harness Web UI: inline AI completion (FIM ghost suggestion, Tab to accept) and Chinese-friendly typo checking with click-to-fix.
会话地图 for DeepSeek Harness — turn the conversation waterfall into a navigable map: one complete turn per card, branchable DAG, live growth, docked turn inspector. Pure map, no context-graph extras.