多Agent模式下其中一个SubAgent的internal错误灰导致后续其它SubAgent的CheckPont保存序列化失败
Open
C-bug
D-adk
- Dominant language
- Go
- Stars
- 13k
- Forks
- 1.1k
- Avg merge
- 4h 6m
- Merged PRs (30d)
- 41
Description
**Describe the bug**
一个supervisor agent调用SubAgentA, SubAgentA抛出innternalNodeError(比如exceed max iteration),SubAgentA transfer to MainAgent, MainAgent调用SubAgentB,SubAgentB事InterruptableAgent,获取user response后回因为SubAgentA的internal错误导致checkpoint保存gob序列化compose.InternalErr没有注册错误
**Version:**
0.7.30
Contributor guide
Research direction
Start by reproducing the described supervisor/SubAgentA/SubAgentB flow on version 0.7.30, including the internal error and subsequent user response. Trace the checkpoint save and gob serialization path; the work is done when a checkpoint can be saved successfully after the earlier SubAgent error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- go
- Domain
- ai, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100