dsh-zh-output
Run the following command in DeepSeek Harness:
dsh plugin install YKennen/dsh-zh-output
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, you can install this plugin by running the command "dsh plugin install YKennen/dsh-zh-output", with the full source code available at https://github.com/YKennen/dsh-zh-output.
About this plugin
When using DeepSeek Harness for model inference, the default English mode may not meet the needs of Chinese users, especially as the context compression feature automatically uses English summaries, breaking the continuity of Chinese output. The dsh-zh-output plugin is designed to solve this issue by injecting Chinese presets and language rules, forcing the model to think and output entirely in Chinese, with only non-natural language elements like code kept as-is. Its core capabilities include providing various Chinese modes (such as standard, PTC, minimal, and cordis) and featuring a dedicated Chinese compression engine that ensures summaries during context compression are also in Chinese, maintaining consistency in Chinese constraints. This plugin is ideal for Chinese developers, researchers, or anyone relying on DeepSeek Harness for Chinese interactions, helping them achieve a more natural and seamless experience in localized environments, thereby enhancing productivity and conversation fluency.
Use Cases
- When performing model inference tasks requiring full Chinese conversation.
- Using DeepSeek Harness for Chinese content creation or research.
- Wanting automatic summaries to maintain Chinese consistency during context compression.
Best For
- Chinese developers or researchers.
- Users deploying DeepSeek Harness in localized environments.
- Practitioners in natural language processing tasks requiring forced Chinese output.
Related Plugins
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.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.