dsh-vision-helper

DeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案

PluginVisionVision / OCR
Verification
L2 · Structured
Security
Pending
Health
Active
Trust
Bronze

What it doesAI

Persistent vision plugin for DeepSeek Harness that registers a vision analyze tool to describe images, OCR, screenshots, and charts via configurable multimodal models.

  • Registers vision analyze tool for local paths and data URIs
  • Configurable multimodal model via settings page or JSON
  • Robust: strips invisible Unicode, resizes images, streams text

AI-generated from the repo README — for reference only.

Installation

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

Install method: npm · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated scan, not manual review.

• Dependency vulnerabilities: — (pending)

• Suspicious permissions: — (pending)

• Hardcoded secrets: — (pending)

• Supply chain risks: — (pending)

⚠ Security audit scheduled — results will appear here after the next scan.

Activity

Last commit 2026-08-14 · activity: active

6 mo

Source

GitHub: github.com/Yuuz12/dsh-vision-helper