All projects

dsh-jev-tools

HorusJiang/dsh-jev-tools

Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside DeepSeek Harness.

TypeScript
Stars
13
Forks
2

Why it is listed

A DeepSeek Harness plugin inserts Jev judgments before tool results enter context; README describes output trimming, injection screening, skill suggestions, and delivery gates, with fail-open behavior.

Related projects

  • dsh-plugin-jev-effort-selector

    DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

    Shared topics: deepseek-harness, dsh, dsh-plugin

  • dsh-jev-advisor

    Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev builds a structured Jev request and floats the recommendation, probability spread and confidence beside the options - one click to adopt. API key lives in Settings. No prompt changes.

    Shared topics: dsh, dsh-plugin

  • dsh-jev-grep

    Search-flood adjudication plugin for DeepSeek Harness: ripgrep + TypeSafe Jev typed judgments (noul/choice) so the agent reads ~30 calibrated rows instead of hundreds. Configurable provider (OpenCode Zen free tier / TypeSafe / OpenRouter), degrades to raw grep when offline. Zero deps, cross-platform.

    Shared topics: dsh, dsh-plugin