311 results
Per-conversation persona / master prompt for DeepSeek Harness: a small box beside the mode controls in the composer lets you create, switch and manage the highest-priority persona of the current conversation (subagents inherit, new conversations inherit the last-used persona).
AI 输入框粘贴大段文本自动缩略为 [Paste #N +M lines] 小序号标签(编号不可改);👁 点击预览全文(点外关闭)、✎ 编辑名称、↺ 恢复纯原文;无删除按钮,删输入框标签文本即消失;发送时自动展开原文并加固定方括号纯标识块分隔(编号与输入框一致);slash 命令参数展开不加装饰;代理可用 myds_read_captured 工具按编号读取标签对应文本。
Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. DSH plugin host; Python stdlib + Markdown core. Zero database / vector service / external service dependencies.
低成本视频理解工具：B站链接/BV/本地视频 → 信息层（ASR+场景+对象轨迹+YOLO）→ 摘要+问答。问题驱动动态路由分层（L0/L1/L2）、语义层复用、预算上限。采用 Python 引擎：核心层需 faster-whisper / opencv / yt-dlp（约 200-300MB），可选语义层另需约 2GB 的 torch / transformers / ultralytics，内置 doctor --fix 一键建 venv 并装齐两者。
Out-of-tree dsh provider plugin: a DeepSeek gateway route that claims image input and transparently describes pasted images through a configured vision-language model (e.g. Qwen-VL) before the text-only DeepSeek wire sees them.
基于deepseek harness的短剧/动画画布工作室：会话「画布」视图页 + ComfyUI 生成服务（图片 FLUX / 视频 MiniMax H3 音视频，带声音/参考绑定/原生字幕/fast·balanced·quality 三档）+ Agent 画布工具 + 自带 skill。双面 DSH 插件。
DeepSeek Harness plugin: 千星沙箱知识库（节点/指南/教程/FAQ）查询工具与技能
DeepSeek Harness (DSH) 插件：任务完成 / 等待审批 / 等待回答时发送 Windows 系统桌面通知
DSH 插件：对话完成时播放提示音 + Windows 通知，WebUI 铃铛按钮可调开关/音量/音效
dsh plugin (Windows): desktop shortcut that launches dsh web silently (hidden console) and auto-opens the browser; port-aware reconnect; settings UI section; tray with native toast notifications and close-to-exit semantics.
Tensorlake sandbox execution providers for DeepSeek Harness
DeepSeek Harness pet companion — Codex Pets style floating pet with notification broadcasting and a pet_say tool
Unified native desktop and webhook notifications for DeepSeek Harness.
Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness
Task-completion reminder for DeepSeek Harness: in-page toast, OS notification, and sound when an agent turn or background job finishes
DSH Web plugin that lets text-only models see images: paste images in the chat and send without file paths; the model discovers its own vision tools. Multimodal models pass through natively.
Local OCR fallback for DeepSeek Harness (Web): when the routed model cannot accept image input, a pasted image is saved locally and its text read by PP-OCRv5 + ONNX Runtime — fully offline, no vision model required. / DeepSeek Harness 本地 OCR 兜底插件（Web）：当接入的模型不支持图片输入时，自动把图片存到本地并用 PP-OCRv5 读出文字，完全离线。
任务完成时播放提示音并弹出小通知（页面内 toast + 后台时系统通知），按结果状态着色（完成/阻塞等待反馈/中断/失败），支持按操作系统选择音效预设、三状态独立音效，附带一句话小结（recap）与运行统计（时长/tokens/步骤）。纯浏览器方案，零系统依赖，跨 Windows/macOS/Linux。
拖入/粘贴文件：输入框上方文件栏（chips）+ @文件名 光标内联插入 + 随消息发送（含绝对路径）+ 气泡文件卡片。Drag/paste files into the DeepSeek Harness web GUI and send them with your message (absolute paths included).
DSH web plugin: edit the last user message back into the composer after stopping a turn
Custom background image plugin for the DeepSeek Harness web GUI: upload a local picture or paste an image URL, and render it behind the whole app surface with adjustable opacity, scrim, panel transparency and frosted-glass blur.
A universal path-backed attachment dock for DeepSeek Harness.
DeepSeek Lens: Deep AST code graph, symbol call hierarchies, and refactoring impact analysis tool plugin for DeepSeek Harness
DSH web plugin: roll back to before any of your questions, or edit the last one and resubmit, restoring the workspace files the discarded turns produced.