dsh-visionary

Give text-only DeepSeek models eyes — a DeepSeek Harness plugin that transparently converts chat images into OCR text + vision-model descriptions before they reach the LLM. Configure vision backends (GLM-4V, Qwen-VL, Gemini, Ollama…) right in the Models settings page; multi-backend fallback chain, double-layer caching, no config files.

PluginAI ModelsVisionVision / OCR

Verification

L2 · Structured

Security

Pending

Health

Active

Trust

Bronze

What it does

Installation

dsh plugin --profile web add github:zhuiyueya/dsh-visionary

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

Compatibility

DSH Version	Status
not stated	Declared — not tested

Requirements

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

Security Report

Automated static scan, not manual review.

DSH.SONOT SCANNEDSCAN— FILES

------

Security reviewAutomated review · daily

NOT SCANNED

No security scan record for this plugin yet. Newly indexed plugins are scanned by the daily pipeline.

0 critical·0 warning·0 info·— files scanned

Version binding

plugin version—

scanned commit—

latest commitf7c654f9f5b7

The scan result is only valid for the scanned commit. If the latest commit differs, the badge shows outdated until the daily pipeline rescans.

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

• Static heuristic scan: pending

• Dependency vulnerabilities: —

• Hardcoded secrets: —

• Supply chain risks: —

⚠ Static scan not run yet — results will appear here.

Activity

Last commit 2026-08-14 · activity: Active

• Repo created: 2026-08-18

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/zhuiyueya/dsh-visionary