gugu123a/dsh-tool-see-image4

dsh-tool-see-image

see_image tool for DSH: route image files to a configurable vision model (OpenAI-compatible API) and relay its description back to a text-only model

包名
dsh-tool-see-image
版本
0.1.2
许可证
MIT
最近更新
2026年8月27日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gugu123a/dsh-tool-see-image

Configuration (tool-see-image line in cordis.patch.yml)

KeyDefaultDescription
baseURLhttps://open.bigmodel.cn/api/paas/v4OpenAI-compatible endpoint; the plugin appends /chat/completions
apiKeyEnvZHIPU_API_KEYEnv var name that holds the API key
modelglm-4v-flashVision model id (free on Zhipu)
maxTokens1024Max output tokens. Note: glm-4v-flash caps at 1024 (higher returns 400 max_tokens参数非法; raise it if you switch to a bigger model)
timeoutMs60000Request timeout
maxBytes15728640 (15MB)Per-image size limit
prompt(Chinese detailed-description instruction)Default question; the question argument takes precedence

To use a different vision API, change these three keys, e.g. SiliconFlow:

config:
  baseURL: https://api.siliconflow.cn/v1
  apiKeyEnv: SILICONFLOW_API_KEY
  model: Qwen/Qwen2.5-VL-32B-Instruct