@dsh-extension/dsh-vision-bridge

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model 适合纯文本会话中偶尔需要看图描述的用户，需配置兼容视觉模型

パッケージ

@dsh-extension/dsh-vision-bridge

互換性

未検証

Harness ピア範囲

>=0.0.1-rc.1 <0.2.0

Cordis ピア範囲

>=4.0.0-rc.7 <5.0.0

バージョン

1.0.0

ライセンス

MIT

最終更新

2026/08/16

Configuration

Configure it in Settings → Vision Bridge (DSH Web), or edit ~/.dsh/vision-bridge.json:

{
  "enabled": true,
  "baseUrl": "https://api.openai.com/v1",
  "apiKey": "sk-xxxx",
  "apiKeyEnv": "",
  "model": "gpt-5.6-terra"
}

baseUrl accepts an API root, a .../v1 base, or a full .../chat/completions URL (the plugin normalizes it).
apiKey and apiKeyEnv are mutually exclusive. A directly entered key is synced to the DSH credential store and referenced as DSH_VISION_BRIDGE_API_KEY.
The plugin maintains exactly one vision-bridge route inside DSH's llm-pi-ai.providers and never touches other providers.
enabled: false disables the whole chain: no tool registration, no image rewriting, no admission bypass (native behavior restored).

Precedence (highest wins): Settings page (with schema defaults) → environment variables → config file.

Environment overrides: DSH_VISION_BRIDGE_BASE_URL, DSH_VISION_BRIDGE_API_KEY, DSH_VISION_BRIDGE_API_KEY_ENV, DSH_VISION_BRIDGE_MODEL, DSH_VISION_BRIDGE_ENABLED.

@dsh-extension/dsh-vision-bridge

インストール

ドキュメント

Configuration