Showing the last saved plugin snapshot.

← Leaderboard / Models / Plugin
Last repository activity November 11, 2026 · Created November 10, 2026

subeichen1/dsh-auto-effort

“Per-turn reasoning-effort routing that keeps the current provider/model.”

Star rank
#13922
declared plugin rank
In Models
#1673
category rank
Stars
0
GitHub repository
Forks
0
GitHub repository
Watchers
0
GitHub subscribers
Open on GitHub ↗
TL;DR

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

30 days of GitHub stars
+0 stars
+0% observed change
Oct 14Oct 28Nov 12