binsarjr/dsh-codex-media

Name: binsarjr/dsh-codex-media
Author: binsarjr

插件 ⭐ 0 MIT visual

DeepSeek Harness 的图像与文档分析工具，由本地 OpenAI Codex CLI 驱动（零依赖，3 种传输方式，与 dsh-drop-to-path 搭配使用）

catalog 简介：Image & document analysis tools for DeepSeek Harness, powered by a local OpenAI Codex CLI (zero deps, 3 transports, pairs with dsh-drop-to-path)

↗ 在 GitHub 查看 📄 阅读完整 README

安装

# 1. Generate the two sample fixtures (no dependencies needed)
npm run fixtures

# 2. Offline wire-shape tests for the HTTP transports (no credentials)
npm test

# 3. Smoke-test the engine directly (uses your local Codex CLI)
npm run smoke:image      # "Describe this chart in two sentences."
npm run smoke:document   # "What is the invoice number and the total amount?"

# 3b. ...or through a direct API transport
CODEX_ANALYSIS_TRANSPORT=api-compatible \
CODEX_ANALYSIS_API_KEY=$OPENAI_API_KEY \
CODEX_ANALYSIS_DOCUMENT_MODELS=gpt-5.2-codex \
  npm run smoke:document

# 4. Start the MCP server over stdio
npm run mcp

把 binsarjr/dsh-codex-media 加入你的 DSH 配置（web profile）即可启用。

README

10.2 KB · 缓存于 2026-08-18 17:11:39 · 10.2 KB

展开完整 README 收起

README 内容为空。

渲染基于仓库 binsarjr/dsh-codex-media 的 README.md。在 GitHub 查看原文 →

安装

README

相关插件