shareAI-lab / shareAI-lab/learn-claude-code
s16 将 Inbox 消费改为运行时自动驱动
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 77.2k
- Forks
- 12.4k
- Avg merge
- 2d 5h
- Merged PRs (30d)
- 6
Description
当前 s16 的 Inbox 消费不够可靠：
check_inbox依赖模型主动调用，无法保证调用时机。- 主循环中的
consume_lead_inbox()只有在整轮agent_loop()结束后才执行。 - 当 Lead 连续进行模型或工具调用时，协议响应和队友消息无法被及时处理。
建议在 Agent Loop 的安全点自动消费 Inbox，例如每次模型调用前后或工具执行后，而不是主要依赖模型主动调用。
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
Trace the Agent Loop and the existing check_inbox, consume_lead_inbox(), and agent_loop() entry points. Identify the safe points around model and tool calls where Inbox consumption can run without disrupting the loop. Done means protocol responses and teammate messages are processed during long sequences of model or tool calls, rather than only after the full loop ends.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai-infra-agents
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100