plug
A DeepSeek Harness plugin that converts pasted, dropped, or imported images into text through an external vision model before sending the result to a text-only model.
Install
$ dsh plugin --profile <name> add github:qing9835/plug#<commit>Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Installs through the DSH CLI as a persistent bundle plugin.
- Captures pasted, dropped, and imported images in the chat input.
- Provides image preview and configuration controls in the input UI.
- Calls external OpenAI-compatible vision endpoints to describe, inspect, or OCR images.
- Supports image validation, optional cropping, resizing, JPEG conversion, and base64 encoding.
- Supports retry handling for selected transient errors and configured backup models.
- Includes a separate Python stdio MCP bridge for compatible MCP clients.
Useful For
- Letting a text-only DSH model work from screenshots or local images via textual descriptions.
- Extracting text from images before sending it to a chat model.
- Inspecting images with a configured external vision model.
- Adding image-input translation to a DSH conversation workflow.
Who It Fits
- DeepSeek Harness users running text-only models.
- Users with access to an OpenAI-compatible vision endpoint.
- Developers who want to use the included MCP bridge with DSH or another MCP client.
Documented Limitations
- Requires setup of the bundled Python bridge environment and configuration of a vision model endpoint.
- Vision analysis depends on an external OpenAI-compatible endpoint, model, and potentially an API key.
- The MCP bridge cannot process an image that has already been rejected by the host chat message gate; the UI interception plugin addresses that input path.
- The dynamic-plugin variant is session-scoped and must be defined again after a process restart; the bundle variant is the persistent option.
- The README cautions that vision conclusions about layout issues should be cross-checked with OCR and source code.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 3 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- qing9835/plug
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- d104d24 · 2026-08-15
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-15
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Real-time market research cockpit and MCP bundle for DeepSeek Harness financial and macro data.
View plugin →Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →Preview, create, and edit spreadsheets, docs, slides, and canvases in DeepSeek Harness powered by Univer.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →