全部项目

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
星标
13
派生
2

收录依据

DeepSeek Harness 插件在工具结果进入上下文前接入 Jev 判断,涵盖输出精简、注入筛查、技能建议和交付闸门;README 说明失败时放行。

相关项目

  • 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.

    共同主题: 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.

    共同主题: 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.

    共同主题: dsh, dsh-plugin