DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to let text-only DSH agents describe images through a vision fallback with DSH Crew

Use the multimodal bridge so DSH workers can describe images by calling DeepSeek's vision model or an installed CLI.

Short answer: Install and start the plugin: dsh plugin --profile web add @zseven-w/dsh-crew@latest, then dsh web; then open Settings → DSH Crew and review the multimodal bridge and custom provider settings; add an OpenAI-compatible endpoint (Base URL, API key, models) under Custom Providers if you want one, then run its connectivity test. All steps.

Credentials. A DeepSeek key or a custom provider API key is needed for the vision path, so store keys carefully and do not paste them into prompts.

Who it is forA developer whose DSH workers need to read screenshots or diagrams, but whose DSH models are text-only.

The problemDSH's models cannot read images, so a worker given a screenshot or diagram has no way to understand it.

The outcomeThe worker calls describe_image, which uses DeepSeek's VL model when a key is available or falls back to a CLI or OpenAI-compatible API, and returns a text description.

What you need first

  • A DeepSeek Harness (DSH) instance to install the plugin into, or a DeepSeek API key for the standalone fallback
  • npm and node available on the machine, since the install commands use them
  • Claude Code or Codex installed as the orchestrating host

Steps

  1. Install and start the plugin: dsh plugin --profile web add @zseven-w/dsh-crew@latest, then dsh web
  2. Open Settings → DSH Crew and review the multimodal bridge and custom provider settings
  3. Add an OpenAI-compatible endpoint (Base URL, API key, models) under Custom Providers if you want one, then run its connectivity test
  4. Dispatch a worker with an image path and ask it to call describe_image on that image
  5. Check that the returned text description matches the image content

Prompt for your agent

Using the dsh-crew repo (ZSeven-W/dsh-crew), dispatch a worker that calls describe_image on <image-path>. Expected output: a text description of the image. Verify the connectivity test for the configured provider passed before relying on the result.

Caveat. describe_image prefers DeepSeek's VL model when a key is available, so the behavior depends on which keys and CLIs you have configured.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for ZSeven-W/dsh-crew and "Let text-only DSH agents describe images through a vision fallback"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer