dsh-union
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-union
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-union in DeepSeek Harness to install this plugin; source code is available at https://github.com/uckkk/dsh-union
About this plugin
In model-inference sessions, you often need to merge multiple sets into a deduplicated union, combining candidate tags, keywords, or option lists from different sources. dsh-union delivers a lightweight, offline set-union tool that lets you complete this step directly within the conversation, without any network calls or external services.
Built as pure Node with zero network dependencies, the plugin registers as a session tool right after installation. It is a good fit for developers who want to quickly merge sets in their inference pipeline without adding extra runtime complexity.
Use Cases
- Merging candidate tags from multiple sources into a deduplicated list
- Combining keyword sets produced by different reasoning steps
- Deduplicating option lists accumulated across dialogue turns
Best For
- Model-inference developers who need lightweight set operations
- Offline-first engineers who want to avoid network dependencies
- App developers merging multiple sets in their dialogue toolchain
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.