dsh-zh-labels
Run the following command in DeepSeek Harness:
dsh plugin install Xingkong42/dsh-zh-labels
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Xingkong42/dsh-zh-labels in DeepSeek Harness to install; the source code is available at https://github.com/Xingkong42/dsh-zh-labels.
About this plugin
In the DeepSeek Harness Web UI, tool row titles, think-collapse headers, trajectory panel labels, and sidebar branding are all hardcoded as English strings inside the client module. Many users have tried to hack node_modules by hand to localize the interface, only to lose every change the moment DSH ships an update.
dsh-zh-labels turns that one-off patch into a self-healing routine. Once mounted, the plugin runs on every DSH startup: it scans the deployed client files across npm global, profile shared, and profile web installation roots, then applies 316 built-in replacement rules to swap known English strings for their Chinese counterparts. Rules are idempotent and fault-tolerant: already-patched files are skipped, and a single unmatched rule simply passes while the rest proceed. After a DSH upgrade overwrites the files, the next startup restores every Chinese label automatically with zero manual steps.
Built for users who rely on the DSH Web interface daily, want a consistent Chinese UI, and would rather not repeat hand-edits after every release.
Use Cases
- Chinese labels vanish after a DSH upgrade and must auto-recover on next start
- Localize the Web UI without hand-editing files inside node_modules
- Unify the Web UI language to Chinese across multiple DSH deployment roots
Best For
- Developers who use the DSH Web UI daily and prefer a Chinese interface
- Users who upgrade DSH often and want to skip repeated manual localization
- Teams running DSH across multiple environments that need a consistent UI language
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.