DeepSeek HarnessHub
Submit plugin

ManoloRemiddi/dsh-adaptive-reasoning ↗★ 0

dsh-adaptive-reasoning

Conservative per-request reasoning selection for DeepSeek Harness, with no classifier model calls 适合需要优化推理成本和速度的用户，在无需分类器模型的情况下动态控制思考强度。

Other extensions
Package
dsh-adaptive-reasoning
Compatibility
Unverified
Harness peer range
0.1.5-rc.1
Cordis peer range
4.0.2
Version
0.2.3
License
MIT
Last updated
Sep 23, 2026

Other repositories with this package name

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ManoloRemiddi/dsh-adaptive-reasoning

README

Read the full README ↗

Configuration

  • enabled: boolean, default true.
  • textOnly: boolean, default true.
  • presets: exact preset allowlist; empty means inactive.
  • routes: exact provider/model pairs with an efforts mapping for off, low, medium, high. The existing Qwen maps high to xhigh.

Automatic mode owns per-request effort on allowlisted routes. Explicit requests to think deeply remain high. Unsupported effort strings fail DSH's adapter validation before inference. Unrecognised languages retain high reasoning.