@DoctorxPriestess

A DSH plugin that manages local llama.cpp GGUF model lifecycles, automatically loading and unloading models on demand through an OpenAI-compatible gateway.

A DeepSeek Harness (DSH) plugin that keeps tool results cache-prefix safe: truncate a result before it first enters the session surface, and never rewrite a tool result a provider request has already delivered.

A Windows system-tray indicator that monitors and controls a local DeepSeek Harness (DSH) web instance — the process started by dsh web