Harness-native agent components for Codex and Pi: a DeepSeek V4 Flash subagent and a DSH Minimal mimic for V4 Pro.
dsh-reasoning-effort
β FeaturedBrings Codex-style model and reasoning-effort controls into DeepSeek Harness, letting you switch models and dial the thinking intensity with a slider instead of editing config.
Plugin facts
Screenshots
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:HanaAyane/dsh-reasoning-effort β οΈ Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety β
Related guides
Learn how to choose, install, and use models & providers plugins.
About this plugin: dsh-reasoning-effort
What is dsh-reasoning-effort?
dsh-reasoning-effort is a models & providers plugin maintained by HanaAyane. Brings Codex-style model and reasoning-effort controls into DeepSeek Harness, letting you switch models and dial the thinking intensity with a slider instead of editing config.
How do I install dsh-reasoning-effort?
Run dsh plugin add github:HanaAyane/dsh-reasoning-effort in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:HanaAyane/dsh-reasoning-effort#commit.
Is dsh-reasoning-effort free?
dsh-reasoning-effort is a community open-source project released under the MIT license. You can inspect its source and install it for free.
Related plugins
Liang-Saint-Slider
β 85The Liang Saint Slider β a model and thinking-effort selector for DeepSeek Harness.
dsh-commandcode-provider
β 53An unofficial LLM provider plugin that lets Command Code use DeepSeek Harness models, with a live model catalog, reasoning-effort support, and a card on the Models page. Ported from pi-commandcode-provider under the MIT license.