dsh-auto-chat-titles
Run the following command in DeepSeek Harness:
dsh plugin install leonardoxr/dsh-auto-chat-titles
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install leonardoxr/dsh-auto-chat-titles in DeepSeek Harness to install; source at https://github.com/leonardoxr/dsh-auto-chat-titles .
About this plugin
By default, DeepSeek Harness derives session titles by truncating the first few words, which rarely captures the actual topic of a multi-turn or multilingual conversation. dsh-auto-chat-titles replaces that fallback with semantic LLM-generated titles, giving every session a meaningful name and removing the need for constant manual renaming.
The plugin layers on top of DSH's existing durable title service, preserving cancellation, normalization, pinning, provenance, and projection behavior. It adds a dedicated title-model selector, separate CJK and non-CJK word-count targets, a regeneration-context slider, and fine-grained limits on input bytes, output tokens, and timeout. A one-click Regenerate button in the conversation header calls the same service using the configured number of recent human messages.
Designed for DSH users who maintain many long sessions, mix Chinese and English content, or simply want more searchable and recognizable conversation titles without modifying the core harness.
Use Cases
- Quickly tell conversations apart after long multi-turn discussions
- Generate topic-accurate titles across mixed Chinese and English sessions
- Cut down manual renaming when managing many DSH sessions
Best For
- Developers running many concurrent DSH sessions
- Teams working in mixed Chinese-English workflows who want meaningful names
- Users who want better titles while keeping DSH's native session service intact
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.