Oscar-Williams/dsh-deepcanary
Oscar-Williams
为 DeepSeek Harness 提供本地注意力监督,优先呈现关键证据,静默通知并汇总可操作事项,帮你专注重要信息。
jiezeng2004-design81更新于 1 个月前
在长任务执行前对齐关键决策,防止 Agent 悄悄改需求、扩范围、换架构。
实用分
78 / 100
配置门槛
开箱即用
协议
MIT
语言
TypeScript
复制命令,或者把整个安装任务交给你的 Harness 智能体。
git clone https://github.com/jiezeng2004-design/dsh-requirements-alignment.git请帮我安装 DeepSeek Harness 插件「dsh-requirements-alignment」: - GitHub 仓库:jiezeng2004-design/dsh-requirements-alignment(https://github.com/jiezeng2004-design/dsh-requirements-alignment) - 类型:cordis 插件(装到 DSH profile) - 注意:该插件声明 DSH 版本要求 0.1.7-rc.2,安装前请先确认我的版本是否满足。 -…
来自项目自身文档的清洗摘录。
dsh-requirements-alignment Stop long-running agents from quietly changing what you asked for. 让 DSH Agent 自己做工程决策,但别让它在长任务里悄悄改需求、扩范围、换架构。 dsh-requirements-alignment is a lightweight runtime drift guard for DeepSeek Harness (DSH) . It turns the user's intent into a durable requirement baseline, stays out of the way while the agent works, and only interrupts when the next step would materially change the direction. You decide the direction. The agent decides the engineering. Current release candidate: v0.5.0-rc.1 , targeting DeepSeek Harness 0.1.7-rc.2 . Requires Node.js =22.18.0 . See the compatibility report for verified behavior and limits. The problem Long-running coding agents are good at keeping momentum. That is also how they can drift. A task may start as: Later the agent discovers that a cleaner solution would require backend changes. Without an explicit guardrail, it may simply expand the scope and continue. Requirements Alignment changes that behavior:…
在 GitHub 打开来自同一生态方向的相似工具。
Oscar-Williams
为 DeepSeek Harness 提供本地注意力监督,优先呈现关键证据,静默通知并汇总可操作事项,帮你专注重要信息。
MichengAI
让 AI 助手别轻易放弃,换个思路再试,并在收工前自己检查一遍结果。
ItQianChen
在 DSH 里直接用 gh 打通本地 Git 和 GitHub,PR、Issue、CI 诊断、代码审查一站搞定。