dsh-image-read
DeepSeek Harness native plugin providing structured image analysis, OCR, provider failover, and caching via the read_image_mimo tool.
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.
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.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 2 runtime, 1 development, 0 peer, and 1 optional dependencies.
package.json declares DSH bundle metadata.
GitHub did not report an SPDX license for this repository snapshot.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
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
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →DeepSeek Harness plugin integrating ego-lite Chromium browser with 32 structured automation tools and live interactive screencast panel.
View plugin →A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.
View plugin →