PineKings/deepseek-harness-desktop--packages-bundle-image-recognition ↗★ 0
@deepseek-ai/dsh-image-recognition-bundle
Opt-in image-recognition bundle for the DeepSeek Harness: mounts the image-recognition capability seam, a configurable HTTP vision provider, and the model-facing recognition tool + skill with deterministic image-task injection 适合需让模型识别图片的用户，需自行配置接口、密钥与模型。
インストール
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PineKings/deepseek-harness-desktop#9855358304c06ba41ef328c12f266c2903550b42&path:packages/bundle/image-recognitionドキュメント
README 全文を読む ↗@deepseek-ai/dsh-image-recognition-bundle
Opt-in image-recognition bundle for a profile. Its cordis.patch.yml mounts the
capability seam (@deepseek-ai/dsh-image-recognition), the configurable HTTP
provider (@deepseek-ai/dsh-image-recognition-http), and the model-facing
consumer (@deepseek-ai/dsh-tool-image-recognition).
The web profile template mounts this bundle by default. A non-web profile opts
in by adding this package to its dsh.profile.bundles (or
dsh plugin --profile add @deepseek-ai/dsh-image-recognition-bundle).
Then configure the endpoint, key, and model in the Plugins settings page
(image-recognition card).
Known Limitations and Deferred Work
- Requires the user to supply a vision provider endpoint and key; recognition is unavailable until both are configured.