@Ansonfishing

Per-model capability profiling for DSH: turns local session history into tool-usage and error-rate dashboards with time-range filters

Clean Architecture reference library for DSH: 8 pinned reference repos with FTS5 search, assertion rules, and a review ledger for architecture reviews

Manage local LLM inference servers in DSH: GPU registry, parameter profiles, VRAM validation, and tok/s benchmarks for llama.cpp, SGLang, and vLLM