Per-model reasoning-effort and input-modality configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.
- GitHub stars
- 1
- Version
- v0.3.1
- License
- MIT
- Added
- 2026-08-23
GitHub info
- GitHub stars
- 1
- License
- MIT
- Primary language
- TypeScript
- Last push
- Aug 21, 2026, 6:13 PM
- Maintainer
- HaoyueQin
- Added
- 2026-08-23
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
Install
dsh plugin --profile web add dsh-better-reasoning-effortTags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/HaoyueQin/dsh-better-reasoning-effort)Related plugins
Models & Providersbetter-model-provider
★ 11Settings page for per-model capabilities: reasoning-effort levels with their wire spellings, input modalities, and token capacities, written as declarations or sparse catalog overrides.
dsh-reasoning-slider
★ 2Adds a model-aware reasoning effort slider with native and animated modes, light and dark palettes, and shared or per-model colors.
dsh-plugin-subscriptions
★ 297Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.