@dsh-external/dsh-drop-to-path
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
600 results
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
Real-time DeepSeek API account balance readout for the DeepSeek Harness web GUI (dsh web).
Generate and display images inline in the DSH chat via API channels or local CLIs (mmx / codex / agy), and read images into structured JSON evidence (OCR / layout / semantics) on any model — with backend probing and a bundled recovery skill.
MiniMax multimodal bridge for DeepSeek Harness (DSH). One mmx_bridge tool covers describe/image/video/speech/music/cover/search/quota; optional web_search/read_image takeover; built-in client enhancement renders inline players/previews plus a settings-page management card in the Web GUI.
DuckDuckGo web search and fetch tools for DeepSeek Harness. Zero Python dependency — search is pure Node, fetch uses @mozilla/readability with optional trafilatura fallback for better extraction.
DSH Web GUI font engine + settings page: runtime discovery of every client plugin's styles, declaration-point pick-to-tune selector (design tokens / per-rule px), configurable hotkeys (picker / font size ±1), system font enumeration via sfnt name-table parsing, DSH settings.yaml persistence (with localStorage fallback for older installs and offline reads), manual refresh (no polling).
DeepSeek Harness (dsh) browser companion: a Chrome side panel that embeds the full dsh web UI and lets the dsh agent read the current page, capture HTTP traffic, and drive the browser.
AI-for-Science research workflow skill bundle for DeepSeek Harness: multi-angle literature review with per-angle files, anchored experiment design with a caveat list, figures, paper reading; cross-verification briefs.
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。
DeepSeek Harness-native publicity toolkit: turn any long-form source into a source-grounded, platform-native promotion matrix.
DSH session health checker: frame-level diagnostics over multi-frame zstd session logs (torn/corrupt/empty detection), zero-dependency read-only scanner
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.
DSH Web 客户端插件:把会话里非正文的工具卡片(read/think/bash/...)合并折叠为输入框上方一个可展开的 "Deep Sleeping..." 小列表,前端不再显示一堆工具卡片。
本地插件管理器:分类折叠(必要程度×来源)、更新源一键更新(npm/GitHub/插件超市)、浏览器下载优先、下载目录自动安装、插件市场(dshfind 精选目录)、README 简介提取、救砖与启动前自检;事务化卸载(备份→删除→校验→回滚)、操作历史一键撤销、场景方案、来源人工修正、依赖关系感知;独立救砖工具链(3081 rescue-daemon / open-boot 浏览器触发自启 / dsh-boot 启动序列);跨平台(Windows/macOS/Linux)
Give DeepSeek Harness agents live control of your ComfyUI canvas (local or cloud): embed it as a split-screen tab, then read/edit/run workflows, debug errors, fetch output images, and batch-sweep parameters straight from the chat. Ships the ComfyUI-side bridge node.
Display images read by the read_image tool inside the DeepSeek Harness Web GUI: a dedicated Read image row with a default-expanded message-style image card (PS-style transparency checkerboard), merged read-N-images rows with side-by-side frames for multi-image requests, and an in-page full-resolution lightbox (zoom buttons, mouse wheel, 1:1 original size). 在 Web GUI 对话流中展示 read_image 读到的图片:默认展开的消息图片卡(透明棋盘格)+ 多图合并并排行(读取了 N 张图片)+ 页面内全精度放大层。
OpenCode Go subscription usage readout for the dsh web GUI: rolling (5h), weekly, and monthly usage windows with reset countdowns in the composer dock.
Drive Origin scientific plotting from DeepSeek Harness AI chat via MCP - 35 tools: file import (CSV/TXT/XLSX, CJK-safe), plan-confirm flow, domain templates (stacked spectra/XRD/dual-Y/forest/multi-panel), editable OPJU delivery, deterministic readback verification, inline image preview, statistics batch (t/ANOVA/PCA/survival), version capability handshake, stable error codes. Market-safe bundle: self-locating server path, fail-open startup, sync stdio transport.
DeepSeek Harness vision enhancer: raises image limits to the official DeepSeek values, raises the per-model request image budget for DeepSeek-V4.1-Flash, and provides high-resolution tiled image reading via a dedicated tool.
DeepSeek Harness plugin that turns a 3D idea into a shootable scene brief and publish-ready showcase copy.
A live peak/off-peak pricing readout for the DeepSeek Harness Web GUI: one status pill under the composer, with the effective prices on hover. · DeepSeek Harness 错峰计价浮标
Self-contained Trellis workflow trigger for DeepSeek Harness: per-turn breadcrumb injection via agent/pre-step, a bundled skill provider, and DSH-native task/phase state resolution. No Trellis AGPL code is vendored; workflow semantics are rewritten and licensed MIT.
DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件:设置页输入人设卡名称和内容即可,文件由插件自动管理;可按工作区指定人设、聊天框可给会话单独切人设;AI 可自行演化人设与记忆(soul_read/soul_update/memory_*)。
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.