← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-plugin-image-tools

DeepSeek Harness image tools plugin providing image choice cards, inline chat images, and image intake for text-only models.

UI & ProductivityTerminal & TUIDeveloper Tools
0GitHub Stars1ForksUpdated2026-10-19

Install

$ dsh plugin --profile web add dsh-plugin-image-tools

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-plugin-image-tools provides comprehensive image capabilities for DeepSeek Harness Web GUI across three primary scenarios: interactive visual choice cards (ask_user_choice), inline markdown image rendering with captions (show_images), and safe attachment intake for blind/text-only models (save_received_images). It supports local paths, remote HTTP URLs, and base64 data URIs with zero-token local rendering.

Key Capabilities

  • Interactive image and text-image choice cards rendered in Web GUI with lightbox zoom preview
  • Inline multi-image rendering in chat replies (1-9 images) with captions and hover zoom
  • Blind-model image reception via pre-step placeholder rewriting and workspace saving (save_received_images)
  • Image source normalization supporting local paths, http/https URLs, and base64 data URIs
  • Workspace-isolated image saving preventing directory traversal attacks

Useful For

  • Presenting visual options to users for selecting covers, assets, or design variants
  • Displaying generated graphics, ComfyUI outputs, or fetched visual assets inline inside assistant replies
  • Enabling text-only or blind LLM models to accept user image attachments and inspect saved image files locally

Who It Fits

  • DeepSeek Harness web interface users working with visual content generation and selection
  • Developers using text-only LLM adapters that need to receive and process user image uploads in the workspace

Documented Limitations

  • llmService.resolveModelInfo patching is mutually exclusive with other plugins modifying the same method
  • Maximum single image size is 20 MiB and formats are strictly limited to PNG, JPEG, WebP, and GIF
  • Markdown URLs for inline images are absolute host/port addresses which may break if accessed through changing reverse proxies without cache hit

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 2 development, 1 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
Pasumao/dsh-plugin-image-tools
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
9d08cbc · 2026-10-26

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
0GitHub stars
Forks
1
Open issues
0
Last commit
2026-10-19
Last release
2026-10-19
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app