dsh-pseudo-vision

仓库内包含的插件

• dsh-pseudo-visionv0.5.3✓

  Adds opt-in image-capable sibling routes for text-only providers and converts image blocks into budgeted, locally enhanced OCR, color-statistics, pixel-scan, and metadata evidence before delegation.

  package.json

  package.json

  dsh.bundle.patch

  cordis.patch.yml

  官方核心包 (9)

  • @deepseek-ai/cordis4.0.1共享
  • @deepseek-ai/dsh-anonymous-user-id0.1.1-rc.2共享
  • @deepseek-ai/dsh-attachment0.1.1-rc.2共享
  • @deepseek-ai/dsh-credentials0.1.1-rc.2共享
  • @deepseek-ai/dsh-launch-environment0.1.1-rc.2共享
  • @deepseek-ai/dsh-llm0.1.1-rc.2共享
  • @deepseek-ai/dsh-llm-deepseek0.1.1-rc.2共享
  • @deepseek-ai/dsh-settings0.1.1-rc.2共享
  • @deepseek-ai/schemastery3.18.1私有副本

路径固定于提交 4e280e405f1c

概览

Local OCR, color-statistics, pixel-scan, and metadata bridge for text-only DeepSeek Harness models; no external vision API.