dsh-tool-ralph 使用指南

本文由本站基于该插件已收录的字段自动派生（wiki / faq / compatibility_json / readme），非 AI 即时创作。每节末尾标源字段。

快速上手

运行固定工作流，将不可变目标依次分配给多个fresh子代理完成，用于模型需要多轮子代理协作处理复杂任务的场景

— 源: plugins.ai_summary

安装与验证

dsh plugin --profile web add npm:@deepseek-ai/dsh-tool-ralph

复制以上命令在 DSH Web Profile 内运行。安装完成后在「插件列表」启用即可。

— 源: plugins.install

关键要点

• Foreground only — there is no job id, background collection, process-resume checkpoint, scheduler, or wall-clock start policy.
• The workspace is the only cross-round long-term memory — one bounded report is the explicit handoff, and uncommitted conversational reasoning disappears with each child.
• One round is one fresh child — there is no within-round fan-out, model/provider switching, fork context, or model-call-selected provider.
• Only round count bounds aggregate effort — token, price, and elapsed-time budgets are deferred.

— 源: plugin_wiki.readme_zh (fallback readme_raw)

踩坑提醒

安装前请审阅上游仓库；本指南基于已收录字段自动派生，可能滞后于最新版本。如发现与官方文档冲突，请以上游为准。

— 来源：通用规则