dsh-vision-plugin

Name: dsh-vision-plugin
Author: Zhangbo-cn

PluginConfirmed pluginCommunity

Zhangbo-cn/dsh-vision-plugin · updated 17 days ago

View source ↗

Installation

dsh plugin --profile web add dsh-vision-plugin

dsh plugin --profile web add github:Zhangbo-cn/dsh-vision-plugin

Plugins in this repository

dsh-vision-pluginv0.1.0
Vision capability seam for DeepSeek Harness: service, OpenAI-compatible provider, and view_image tool.
package.json
package.json
dsh.bundle.patch
—
@zhangbo-cn/dsh-tool-visionv0.1.0
Model-facing view_image tool over the DeepSeek Harness vision seam (ctx.vision): reads an image file, commits its bytes durably, and returns a text description from an external vision provider.
package.json
packages/tool-vision/package.json
dsh.bundle.patch
—
Official core packages (7)
- @deepseek-ai/cordis^4.0.1shared
- @deepseek-ai/dsh-attachment>=0.1.0-rc.6shared
- @deepseek-ai/dsh-fs>=0.1.0-rc.6shared
- @deepseek-ai/dsh-invariants>=0.1.0-rc.6shared
- @deepseek-ai/dsh-system-prompt>=0.1.0-rc.6shared
- @deepseek-ai/dsh-tools>=0.1.0-rc.6shared
- @deepseek-ai/schemastery^3.18.1private copy
@zhangbo-cn/dsh-vision-openai-compatiblev0.1.0
OpenAI-compatible chat-completions vision provider for the DeepSeek Harness vision seam (ctx.vision).
package.json
packages/vision-openai-compatible/package.json
dsh.bundle.patch
—
Official core packages (4)
- @deepseek-ai/cordis^4.0.1shared
- @deepseek-ai/dsh-attachment>=0.1.0-rc.6shared
- @deepseek-ai/dsh-invariants>=0.1.0-rc.6shared
- @deepseek-ai/schemastery^3.18.1private copy
@zhangbo-cn/dsh-visionv0.1.0
Vision capability seam for DeepSeek Harness: a provider registry with auto-selecting describe() execution, letting a text-only model 'understand' an image.
package.json
packages/vision/package.json
dsh.bundle.patch
—
Official core packages (3)
- @deepseek-ai/cordis^4.0.1shared
- @deepseek-ai/dsh-attachment>=0.1.0-rc.6shared
- @deepseek-ai/dsh-invariants>=0.1.0-rc.6shared

Paths are pinned to commit 8da9a9b940fa

Overview

Vision capability for DeepSeek Harness: lets a text-only model "understand" an image by routing to an external OpenAI-compatible multimodal API. Built as a standalone dsh-plugin from the official vision capability seam proposal.

Repository check result

Results are bound to the listed commit and cover only static checks run by this registry. The Evidence Score measures reviewable information; it is not a compatibility percentage or a security guarantee.

Static repository check

Sep 1, 2026, 5:54 AM

High risk

Checked commit: 8da9a9b940fa
Evidence Score: 50/100
Static risk: High risk
Files scanned: 4
Findings: 5

Evidence breakdown

Source provenance25/25

Install documentation8/25

Maintenance12/20

Compatibility evidence0/20

Security signals10/10

Compatibility confidence: Unknown

Findings (5)

Highinstall.script
packages/tool-vision/package.jsoninstall-time
```
"prepack": "npm run build"
```
Highinstall.script
packages/vision-openai-compatible/package.jsoninstall-time
```
"prepack": "npm run build"
```
Highinstall.script
packages/vision/package.jsoninstall-time
```
"prepack": "npm run build"
```
Mediumdeps.core-package-installed
packages/tool-vision/package.jsondependencies
```
"@deepseek-ai/schemastery": "^3.18.1"
```
Mediumdeps.core-package-installed
packages/vision-openai-compatible/package.jsondependencies
```
"@deepseek-ai/schemastery": "^3.18.1"
```

Not run

Dependency advisory database scan
Installation execution test
Runtime behavior verification

Scanner 1.0.0 · Scorer 1.0.0