dsh-model-auto-hot-switch

Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.

AI Analysis

核心用途是实现多模态任务的自动模型分流，无需手动切换。适合经常在 DSH 中混合处理文本和图像任务的用户。无需额外配置，开箱即用。

Vision

Package: dsh-model-auto-hot-switch
Version: 0.1.0
License: MIT
Last updated: Aug 28, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SHUJILAI/dsh-model-auto-hot-switch

README

Read the full README ↗

Configuration

None. The single toggle is the whole surface:

Field	Meaning
`enabled` (in `config.json`)	`true` routes image tasks to the vision model; `false` leaves every request on the default model

The preferred vision model id is deepseek-v4-flash-vision-exp; if absent, the first discovered image-capable model wins.