binsarjr/dsh-codex-media
Image & document analysis tools for DeepSeek Harness, powered by a local OpenAI Codex CLI (zero deps, 3 transports, pairs with dsh-drop-to-path)
Install
# 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
Add binsarjr/dsh-codex-media to your DSH config (web profile) to enable.
README
Expand full README Collapse
README is empty.
tt-a1i/archify
strukto-ai/mirage
liustack/modlens
omdsh-dev/DSH-better-sidebar
GanyuanRan/Aegis
dsh-market/dsh-market
toby-bridges/api-relay-audit
ysr666/dsh-vision-router