[Feature] 方向：教导模型 转向 能力上界
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- TypeScript
- Stars
- 119
- Forks
- 19
- PR merge metrics
- No merged PRs in 30d
Description
Problem
一开始 FrontAgent 存在是为了解决我当时在美团做前端时遇到模型因为幻觉问题而不遵守组件库限制等等的缺陷
但是现在模型能力提升、上下文窗口变长
我认为有必要进行重构，从“劝导”模型 -> 让模型有更多能力，更自如地做事情，例如
- 并发任务
- 工具调用的异步处理、回调处理
- Agent 集群
Proposed Behavior
- 并发任务
- 工具调用的异步处理、回调处理
- Agent 集群
Affected Area
CLI
Alternatives Considered
No response
Acceptance Criteria
约束减少，能力上界提高
（甚至 SDD 可能直接在重构中可以删除？转而用 skills 进行自由搭配）
Contribution
- I am willing to submit a PR for this feature.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. Start by identifying the CLI boundaries for SDD, skills, tool calls, and agent orchestration, then define concrete behavior for concurrent tasks, asynchronous callbacks, and agent clusters. Done requires agreed acceptance criteria showing how these capabilities raise the capability ceiling while reducing constraints.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, cli
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100