dsh-ellipsis
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-ellipsis
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-ellipsis in your terminal to install the plugin; the full source repository is available at https://github.com/uckkk/dsh-ellipsis .
About this plugin
In long-form model inference outputs, middle sections often need to be elided or abbreviated to keep responses concise and readable. dsh-ellipsis is purpose-built for exactly that: it packages ellipsis and abbreviation logic into a plug-and-play inference tool that the model can invoke on demand, eliminating the need for separate post-processing scripts.
Under the hood the plugin is written in pure Node.js with zero network dependencies and no third-party services. Once installed it registers itself as a tool in the current session, ready to be called at any point during generation. This self-contained design means it runs reliably in offline environments, sandboxes, or resource-constrained runtimes.
It suits developers who need lightweight text elision or abbreviation in their inference pipeline but want to avoid introducing network calls or extra middleware for such a small step. Licensed under MIT, it can be dropped into any DeepSeek Harness workflow without restriction.
Use Cases
- Eliding middle sections in long inference outputs on demand
- Running text abbreviation in offline or sandboxed environments
- Building lightweight inference workflows with zero external services
Best For
- Inference developers needing lightweight text elision
- Architects who want to avoid network calls for small features
- Engineers deploying DeepSeek Harness in controlled environments
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.