DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-plugin-vision

A DeepSeek Harness vision tool that converts images into text-only OCR, ASCII layout art, and vision-model descriptions.

VisionUI & ProductivityDeveloper Tools

Install

Awaiting GitHub sync

Repository Intelligence

AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.

source-grounded
This installable DSH profile bundle registers a `see` tool for image analysis. It combines macOS Vision OCR with coordinates, Python/PIL ASCII layout output, and an OpenAI-compatible gateway for structured visual descriptions, allowing text-only routed models to analyze images.

Key Capabilities

  • Registers the `see` tool in DeepSeek Harness.
  • Returns offline OCR text with normalized bounding-box positions.
  • Generates grayscale ASCII layout art for text-based layout inspection.
  • Requests structured semantic descriptions through an OpenAI-compatible vision-model gateway.
  • Supports configurable default and fallback models, gateway URL, image preprocessing, output limits, and timeouts.
  • Can read credentials from the DSH credentials service or a configured YAML credential file.
  • Provides a live settings namespace for selecting the default vision model.

Useful For

  • Let text-only DSH models inspect image files without using `read_image`.
  • Extract positioned Chinese and English text from images on macOS.
  • Review UI layouts or charts through ASCII representations.
  • Produce structured text, layout, UI, style, and notes descriptions of images.
  • Analyze images in DSH web profiles or other compatible Cordis compositions.

Who It Fits

  • DeepSeek Harness users running web profiles or compatible compositions.
  • Users of text-only models who need image analysis results as text.
  • Developers building DSH agents and presets that need an image-analysis tool.

Documented Limitations

  • OCR requires macOS and the Vision framework.
  • ASCII, preprocessing, and VLM-related paths require `python3` and PIL.
  • V1 does not provide screenshot capture mode.
  • The vision-description channel depends on an OpenAI-compatible gateway and configured credentials.
  • Swift OCR has an initial compilation cost; the README estimates approximately 1–2 seconds on first use.
  • Individual channels can fail independently, returning channel-level errors rather than failing the entire analysis.

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

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
Package Manifest Available

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

info
License Declared

GitHub reports the repository license as MIT.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info
Dependency Counts

package.json declares 6 runtime, 2 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
Package Manifest Available

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

info
License Declared

GitHub reports the repository license as MIT.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Traceable source and registry metadata for this entry, kept separate from runtime verification.

Source repository
qizhen2021/dsh-plugin-vision
Registry source
Public GitHub repository
Source snapshot
1865251d3478
Artifact type
plugin
AI enrichment
gpt-5.6-terra · 2026-08-14
Prompt version
dsh-plugin-enrichment-v3

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
0
Forks
0
Open issues
0
Last commit
2026-08-14
Last release