플러그인

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

Sticker/emoji expression for assistants: emotion-driven auto-matching, library management, AI image tagging, dialects, style mimicry, and chat-based tag refinement.

DeepSeek Harness (dsh) plugin: /refine command + settings panel for the dsh-continual-harness self-refinement engine — entry browsing, refinement history timeline, one-click rollback, auto-gate audit; engine optional at runtime.

Two-phase session captioning: instant keyword titles while the conversation is busy, then cheapest-budget-model refinement plus a one-line summary once it goes idle.