dsh-vision-analysis

Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.

AI 分析

核心用途是为 DSH 引入强大的多模态图像分析与 OCR 能力。适合需要对本地或网络图片进行深度结构化分析的任务。必要条件是配置兼容的视觉 API（如 SiliconFlow 等）。

パッケージ

dsh-vision-analysis

バージョン

0.1.0-rc.8

ライセンス

MIT

最終更新

2026/08/21

⚙️ Configuration

- id: vision-analysis
  name: dsh-vision-analysis
  config:
    apiFormat: openai          # openai | anthropic
    baseURL: https://api.siliconflow.cn/v1
    apiKey: ''                # empty → UNIVERSAL_VISION_API_KEY → local model
    model: Qwen/Qwen2.5-VL-72B-Instruct
    defaultMode: describe
    maxImages: 2              # 1-4
    maxBytes: 10485760        # per-image cap (10 MB)
    timeoutMs: 120000
    maxTokens: 4096
    temperature: 0.7
    modes:                    # per-mode overrides
      ocr:
        temperature: 0.0

All fields are editable live from Settings → 插件配置 (API key field is masked).

dsh-vision-analysis

AI 分析

インストール

ドキュメント

⚙️ Configuration