sanshanya/better-model-provider

README 摘要

better-model-provider Better custom-provider model onboarding for DeepSeek Harness (dsh), with per-model declaration of native vision input and reasoning-effort levels. English 中文 Why you may need it The official Models page manages providers and model rows, but two per-model capability fields stayed YAML-only: reasoningEfforts (which reasoning levels the model accepts, plus each level's wire spelling) and input (which request modalities the model admits). Until they are declared: - the composer's model picker shows no reasoning-effort control for your model; - image sessions refuse to switch to it ( Model ... does not accept image input ), because a hand-declared model defaults to text-only. Install Restart dsh web , hard-refresh the browser, and the settings sidebar gains Model capabilities . Uninstall: Use 1. Configure the provider on the official Models page first (that's where the API key lives; this page never touches credentials). 2. Open Settings → Model capabilities . 3. Expand a model row: pick Custom under reasoning effort and check the levels; for vision models check image under input modalities. 4. Apply. The picker immediately offers exactly the declared levels, and t…

分类