feat(aidd-orchestrator): run tdd analysis and cycle in isolated contexts

未关闭
#1,264 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
48/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
typescript

调研方向

Read the implementation in aidd-orchestrator and the related work in epic #1259 to identify how the existing generic agents are dispatched and how acceptance criteria are tracked. Then trace the current TDD analysis and cycle flow; done means analysis and each autonomous cycle run use fresh contexts, pass the test list between runs, and repeat until all acceptance criteria hold.

由索引模型根据 Issue 内容生成。

描述

Epic: #1259

Story

As a team delivering through the orchestrator
I want the TDD analysis and the TDD cycle dispatched as two isolated runs
So that whoever decides the tests never writes the code

Acceptance

  • The orchestrator runs analyze in one fresh context and cycle in another, passing the test list between them.
  • The cycle runs autonomously, without asking the user.
  • One cycle run covers one small iteration; the orchestrator loops, each run in a fresh context, until every acceptance criterion holds.
  • No new agent is created; the existing generic agents are reused.
  • The change lives in aidd-orchestrator.
主要语言
TypeScript
星标
481
派生
45
平均合并
1 天 13 小时
30 天内合并 PR
91

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

ai-driven-dev/framework 的其他 Issue

查看 ai-driven-dev/framework 的全部 Issue

相似的 Issue

更多 TypeScript Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。