← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-plugin-jev-effort-selector

Dynamic reasoning effort selector for DeepSeek Harness using Jev System One classification per message.

Terminal & TUIDeveloper ToolsRemote Execution
8GitHub Stars1ForksUpdated2026-10-01

Install

$ dsh plugin --profile web add github:justhalfbit/dsh-plugin-jev-effort-selector

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-plugin-jev-effort-selector automatically evaluates and sets the reasoning effort for each user message in DeepSeek Harness. By querying a lightweight Jev System One classification model with a fixed context envelope from session history, it dynamically selects appropriate reasoning tiers (e.g., off, medium, high) according to model-advertised capabilities, while supporting manual overrides, session-level toggles, and silent fallbacks.

Key Capabilities

  • Automatic reasoning effort tier derivation based on per-model advertised support
  • Lightweight context envelope construction from session logs without transmitting full conversation history
  • Dual classification per message evaluating both tier requirement and continuation status
  • Upward tie-breaking on low confidence scores and uncompleted task continuations
  • Silent non-blocking fallback to default effort levels upon network or API errors
  • Web GUI status chip reflecting real-time Jev decisions and reasoning states
  • Per-session toggle and full manual effort override respect

Useful For

  • Saving reasoning tokens and latency on trivial chat messages and queries
  • Automatically elevating reasoning effort for complex engineering and architecture prompts
  • Preserving contextual depth and high reasoning effort during follow-up task iterations

Who It Fits

  • DeepSeek Harness users seeking automated reasoning effort management
  • Developers looking to optimize token costs and response times across mixed complexity conversations

Documented Limitations

  • Requires a configured Jev System One API endpoint and credentials
  • Visual status chips are supported only in the Web GUI profile, not in TUI or headless modes
  • Cannot override gateway-level adaptive thinking configurations such as compat.forceAdaptiveThinking

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 2 runtime, 0 development, 0 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
justhalfbit/dsh-plugin-jev-effort-selector
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
9b8ac7d · 2026-10-20

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
8GitHub stars
Forks
1
Open issues
1
Last commit
2026-10-01
Last release
No release detected
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