← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-reasoning-effort

Interactive reasoning-effort slider and runner visual integration for DeepSeek Harness model selectors.

UI & ProductivityTerminal & TUIDeveloper ToolsSecurity & Policy
247GitHub Stars16ForksUpdated2026-10-23

Install

$ dsh plugin --profile web add @ayanehana/[email protected]

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-reasoning-effort is a DeepSeek Harness UI plugin that integrates a stepped slider into the native model selector to adjust model reasoning effort levels. It dynamically adapts to model-supported effort tiers, provides an animated runner thumb, syncs state with the /model command, and includes configuration guidance for custom provider endpoints.

Key Capabilities

  • Integrates a stepped slider directly into the native DSH model selector and reasoning effort view
  • Dynamically adjusts slider intervals and labels based on model catalog reasoning.efforts metadata
  • Provides an animated sprite runner control with reduced-motion and standard button fallbacks
  • Synchronizes effort selections bidirectionally with the native /model command and session state
  • Offers UI guidance and YAML templates to configure reasoning tiers for custom provider models
  • Adapts automatically to DSH dark and light visual themes and active language settings

Useful For

  • Quickly switching reasoning levels (e.g., low, medium, high) without manually typing session commands
  • Visualizing reasoning step configurations across multiple models in DSH Web and Desktop profiles
  • Setting up and troubleshooting reasoning parameters for custom OpenAI-compatible endpoints

Who It Fits

  • DeepSeek Harness Web and Desktop users working with reasoning-capable models
  • Developers integrating custom model endpoints requiring reasoning effort parameters

Documented Limitations

  • Requires models to expose at least two reasoning effort tiers in catalog metadata to display the slider
  • Targeted specifically at DSH 0.2.1-rc.2+; does not support unmaintained alpha releases
  • Host or desktop app restart and page reload are required after installation or configuration changes
  • Does not alter endpoint inference logic; model backend must support requested reasoning parameters

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 1 runtime, 20 development, 13 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
HanaAyane/dsh-reasoning-effort
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
49bea3b · 2026-10-23

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
247GitHub stars
Forks
16
Open issues
6
Last commit
2026-10-23
Last release
2026-10-19
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app