DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

File Attachment — DSH Plugin for DeepSeek Harness
← Plugins

@wszhoho/dsh-file-attachment

File Attachment

File attachments: drag, paste, or upload files (multiple files supported); images and documents are saved uniformly to .dsh-file-attachment and sent using @absolute-path references (works with text models); inline image thumbnail previews and file entries are shown in the input box, while images in

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add @wszhoho/dsh-file-attachment@0.6.4
插件演示可上传类型设置、多模态API设置

Description

File attachments: drag, paste, or upload files (multiple files supported); images and documents are saved uniformly to .dsh-file-attachment and sent using @absolute-path references (works with text models); inline image thumbnail previews and file entries are shown in the input box, while images in the chat area are also rendered as clickable, enlargable thumbnails and files retain a chip style; for non-multimodal models, images automatically invoke a configurable VLM to generate Chinese descriptions and fill them back into the draft; uploadable document/code/configuration file types can be configured in the settings page; supports PC and mobile browsers. File attachment plugin for DeepSeek Harness (DSH) web G

Compatibility and provenance

File Attachment is published as @wszhoho/dsh-file-attachment and currently resolves to version 0.6.4. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
10/16/2026

Versions

0.6.4stable
10/15/2026
0.6.3stable
10/11/2026
0.6.2stable
10/10/2026
Show 21 more versionsCollapse versions
0.6.1stable
10/10/2026
0.6.0stable
10/10/2026
0.5.13stable
9/28/2026
0.5.12stable
9/28/2026
0.5.11stable
9/28/2026
0.5.10stable
9/28/2026
0.5.9stable
9/21/2026
0.5.8stable
9/18/2026
0.5.7stable
9/17/2026
0.5.6stable
9/17/2026
0.5.4stable
9/16/2026
0.5.3stable
9/12/2026
0.5.2stable
9/11/2026
0.5.1stable
9/11/2026
0.5.0stable
9/11/2026
0.4.1stable
9/2/2026
0.4.0stable
8/31/2026
0.3.4stable
8/30/2026
0.3.3stable
8/29/2026
0.2.2stable
8/28/2026
0.2.1stable
8/28/2026

Related plugins

Loading related plugins…

Latest
0.6.4
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
121.2 kB
Files
6
Surface
web
License
MIT
Source
npm
GitHub
★ 2
Weekly downloads
1,225
Security scan
✓ v0.6.4 scan passed
Last push
10/15/2026
View source ↗Project homepage ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in vision-media.

Experimental Voice Input Bundle@deepseek-ai/dsh-experimental-voice-input-bundleExperimental voice input with local SenseVoice; downloads its runtime on first useAb Ocrdsh-ab-ocr--- description: "The out-of-tree ocr tool: recognizes a scanned PDF or image page by page, merges the pages in order only after the last one, and saves one Markdown document with the heading levels the model decided." kind: "package-reference" ---Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLITool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —