DeepSeek Harness Plugin: dsh-local-llm

`dsh-local-llm` is a community plugin for DeepSeek Harness designed to run GGUF-format models locally. It provides model downloading, management, and an OpenAI-compatible inference interface launched via `llama-server`. The plugin supports downloading models from Hugging Face, SSE streaming, automatic context-size detection, and secure path handling. Users need Node.js 18+ and can start the service with the specified configuration to call local models directly within Harness, achieving low-latency, privacy-preserving inference.