dsh-plugin-vision
A DeepSeek Harness vision tool that converts images into text-only OCR, ASCII layout art, and vision-model descriptions.
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.
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.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 6 runtime, 2 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 6 runtime, 2 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
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
- —
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
DeepSeek Harness vision-routing plugin with provider fallback chains and pixel-level image tools.
View plugin →An installable DeepSeek Harness bundle for robotics and embodied-intelligence research workflows.
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 →Adds an OpenAI-compatible vision bridge to DeepSeek Harness, forwarding images to a configured vision model and displaying descriptions in a web panel.
View plugin →