AtropinolTT/dsh-guide-dog
DSH导盲犬 — MiniMax多模态插件:图像/视频/音乐/语音生成与视觉工具、语音模式、语音输入。已实现实时通话模式:流式语音对话、统一悬浮界面、自适应提示、中英文国际化。无障碍功能计划测试并推出。已收录于dsh-recommend插件库。
Project Overview项目介绍
Guide Dog is a native Cordis plugin built exclusively for DeepSeek Harness (DSH) that adds full multimodal capabilities to DSH via the MiniMax mmx CLI. It enables non-vision-native LLMs like base DeepSeek to process visual content including frontend designs, screenshots, figures, and generated images via MiniMax's visual language model. It also supports generating images, video, speech, music, and text through MiniMax APIs, and adds integrated web search functionality. To install the plugin, you only need to run the standard DSH plugin install command targeting this GitHub repository, no npm publish is required.
The plugin includes an automatic invocation rule that triggers the visual inspection tool automatically any time a task requires visual analysis and the active model cannot process images natively. All generated media files are hosted on the same origin as DSH's web UI, and are rendered inline directly in the conversation tool cards. There is also a dedicated settings page for the plugin where you can check your authentication status and test text-to-speech output. If you already have an existing speech conversation skill pipeline set up in DSH, Guide Dog can reuse that pipeline for voice interactions.
Guide Dog is released under the permissive MIT open source license. As of the latest release, Phase 1 visual and generation features and Phase 2 hands-free real-time voice call mode are fully implemented, with support for push-to-talk, streaming TTS, and a bilingual zh/en UI. Phase 3 accessibility mode is currently planned, and configuration placeholders are reserved in the codebase. If you experience issues after installation, verify that the plugin bundle is registered correctly in your DSH web profile, and restart DSH after any plugin updates or changes.
导盲犬(Guide Dog)是专为 DeepSeek Harness(DSH)开发的原生 Cordis 插件,基于 MiniMax 的 mmx CLI 为 DSH 赋予多模态超级能力。它为不支持原生视觉输入的大模型提供图像描述能力,能让 DeepSeek 这类模型处理前端设计、截图、图表和生成图像,同时还支持图像、视频、语音、音乐和文本生成,以及联网搜索。用户可以通过标准 DSH 插件命令直接从本仓库安装,无需额外发布到 npm,安装后重启 DSH 即可启用全部功能。
插件自带自动调用规则,会在任务需要视觉检查且当前模型无法处理图像时自动触发图像描述工具。生成的所有媒体文件都会在同域名下提供访问,直接渲染在对话的工具卡片中,还内置了设置页面,可以查看授权状态、测试语音合成。对于已有语音对话技能管线的用户,还可以复用现有管线实现语音对话功能。它适合需要让 DSH 处理多模态内容但当前模型不支持原生多模态的用户。
该插件采用 MIT 许可证开源,目前已经上线了第一阶段的视觉和生成功能,以及第二阶段的实时语音通话模式,支持免提实时对话、流式 TTS 和中英双语界面。第三阶段的无障碍模式还在规划中,代码库保留了相关配置占位。安装后如果遇到功能不生效的问题,需要检查是否在正确的 web 配置文件中注册了插件包,修改代码后需要重新部署并重启 DSH。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-guide-dog(AtropinolTT/dsh-guide-dog)
仓库:https://github.com/AtropinolTT/dsh-guide-dog
本站详情页:https://www.yhbd.top/plugins/atropinoltt-dsh-guide-dog/
本站登记:类型 collection · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 5 · 最近提交 2026-08-17 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 5 stars - very few users, little community feedback星标只有 5,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add github:AtropinolTT/dsh-guide-dog
把 AtropinolTT/dsh-guide-dog 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
Guide Dog for DSH, powered by MiniMax
English | 简体中文
A dynamic Cordis plugin that gives DeepSeek Harness multimodal superpowers through the mmx CLI (MiniMax):
- Eyes for DeepSeek — MiniMax VLM (
guide_dog_vision/guide_dog_inspect) describes images, so a model with no native vision input (e.g. DeepSeek) can still review frontend designs, figures, screenshots, and generated images. - Hands for generation — images (
image-01), video (MiniMax-H3/ Hailuo), speech (MiniMax TTS), music (music-3.0), text (MiniMax-M3), and web search. - Web UI preview & playback — every generated file is served same-origin at
/guide-dog/media/<file>and rendered inline in the conversation tool cards (<img>,<audio controls>,<video controls>), plus a Guide Dog settings page with auth status and a speak tester. - Skill integration —
guide_dog_speakreuses your existingaudio-conversationandspeech-mmxskill pipelines (text transform, CJK auto-detect, per-language voices, host playback), and falls back to rawmmx speech synthesizewhen the skill scripts are absent. - Automatic invocation — a mounted system-prompt section
(
guide-dog-vision, order 110) tells the agent to auto-invoke the inspection tools for any job needing visual checks, especially when the active model cannot see images. - Call mode (Phase 2, shipped) — hands-free, real-time voice conversation in the web UI: VAD / push-to-talk turn-taking, streaming sentence-level TTS with barge-in, consensus-first protection for write commands, progress announcements, and a unified floating dual-pill UI at the composer with zh/en i18n (details in "Phase 2 — call mode" below).
- Accessibility mode (Phase 3, planned) — an
a11yconfig block is reserved (auto-narration, vision-cloud, summary-first); accessibility features are next on the roadmap and will be tested and rolled out after the call-mode shakeout.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
freestylefly/awesome-gpt-image-2
LAN-TINA-WS/dsh-gui-customization
yu-wenchao/deepseek-harness-desktop-Install
XHR666/dsh-mpkg-wallpaper