dsh-plugin-reasoning-efforts: Adding Reasoning Level Selection for DSH Third-Party Relay Models

The DeepSeek Harness (DSH) plugin is designed to address the issue where third-party relayed models cannot use the “reasoning level” selector. By monitoring the `llm-pi-ai` configuration section, the plugin automatically completes the `reasoning.efforts` capability declaration and provides six default levels. Users can customize dialects and levels by model family in `~/.dsh/settings.yaml`. After installation, restart `dsh web` to independently select the reasoning intensity for each session in the chat box. The plugin supports multiple dialect formats, including OpenAI and DeepSeek, and intelligently handles route-level default values.