icekale/dsh-provider-auto

README excerpt

dsh-provider-auto Automatically adds reasoning-effort controls to compatible custom provider models in DeepSeek Harness. 中文说明 What it does @deepseek-ai/dsh-llm-pi-ai only shows a reasoning selector when a model declares reasoningEfforts . Custom OpenAI-compatible gateways often return model ids but no capability metadata. This plugin watches the llm-pi-ai settings section and fills the missing declaration for recognized reasoning models. Defaults: - Protocols: openai-completions , openai-responses - Models: gpt-5 , o1 , o3 , o4 , other o , and codex - Levels: off , low , medium , high - Exclusions: image, audio, embedding, moderation, and reranking models - Existing reasoningEfforts declarations are never overwritten The plugin updates the persisted llm-pi-ai section, so DSH's native model picker and request path remain authoritative. Install Install directly from GitHub into the Web profile: Restart dsh web once after installation. Later provider/model changes are handled live through the settings service. To remove it: Provider configuration Add providers from the DSH Models page, or edit /.dsh/settings.yaml : The plugin adds this only to gpt-5.6-sol : Plugin configuration Overri…

Category