Skip to main content

How to use dsh-reasoning-settings

Adds low, medium, and high reasoning levels to third-party APIs and selects models for subagent calls.

This article is auto-derived from indexed fields (wiki / faq / compatibility_json), not freshly AI-generated.

This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.

Quick start

Adds low, medium, and high reasoning levels to third-party APIs and selects models for subagent calls.

— source: plugins.ai_summary

Install & verify

dsh plugin --profile web add github:JuneLearn/dsh-reasoning-settings

Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.

— source: plugins.install

Key points

  • Auto-reads the custom providers and models you already added on the official Models page.
  • Declares a per-model effort level from off / minimal / low / medium / high / xhigh / max.
  • Customizes the actual wire value sent to the API for each level.
  • Sets a provider-wide default effort, restricted to the levels supported by every model in that provider.
  • Configures the reasoning wire format for openai-completions providers.

— source: plugin_wiki.readme_en (fallback readme_raw)

Pitfalls

Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.

— source: general rule