DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-image-read

DeepSeek Harness native plugin providing structured image analysis, OCR, provider failover, and caching via the read_image_mimo tool.

VisionUI & ProductivityDeveloper Tools
0GitHub Stars0ForksUpdated2026-08-23

Install

No clear install command was found in the current repository evidence.

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-image-read is a DeepSeek Harness plugin that provides a tool (read_image_mimo) allowing any model to analyze images via multimodal APIs. It returns structured JSON evidence covering OCR text, layout regions, and uncertainty notes, with built-in multi-provider failover, content-hash caching, cross-platform downscaling, SSRF protection, and a Web UI settings card.

Key Capabilities

  • Provides the read_image_mimo tool for OCR, general image understanding, and multi-image comparison
  • Outputs structured JSON containing summary, full OCR lines, layout regions, and uncertainty analysis
  • Supports multi-provider failover with automatic fallback to secondary vision endpoints
  • Implements content-hash result caching for both local and remote images with failure cooldown
  • Includes cross-platform preprocessing (downscaling, EXIF orientation, format conversion) using sharp or sips
  • Enforces SSRF protection, cumulative payload budget limits, and API key redaction in error messages
  • Provides a Web UI configuration card integrated with DSH client settings

Useful For

  • Extracting structured OCR and layout data from screenshots and documents
  • Enabling non-vision models within DeepSeek Harness to query and inspect visual content
  • Routing image analysis tasks across fallback vision providers to ensure high availability

Who It Fits

  • DeepSeek Harness users needing structured OCR and multimodal image analysis
  • Developers building workflows requiring failover across external vision APIs

Documented Limitations

  • Supports up to 8 images per multi-image comparison request
  • Requires external multimodal API credentials (such as Xiaomi MiMo or DashScope) to process images
  • Full preprocessing optimization relies on optional dependency sharp (falls back to sips on macOS or passthrough)

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 2 runtime, 1 development, 0 peer, and 1 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Not Declared

GitHub did not report an SPDX license for this repository snapshot.

low
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
Triple3h/dsh-image-read
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
e1e4212 · 2026-08-24

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
0
Open issues
0
Last commit
2026-08-23
Last release
No release detected
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