Showing the last saved plugin snapshot.

← Leaderboard / Models / Plugin
Last repository activity November 11, 2026 · Created August 18, 2026

drscrewdriver/dsh-thinking-levels

“Per-round thinking-level (reasoning_effort) control for DeepSeek Harness.”

Star rank
#1007
declared plugin rank
In Models
#116
category rank
Stars
17
GitHub repository
Forks
0
GitHub repository
Watchers
1
GitHub subscribers
Open on GitHub ↗
TL;DR

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM.

30 days of GitHub stars
+7 stars
+70% observed change
Oct 14Oct 28Nov 12