协同模式长时间使用后 Lead→Worker 通道失效(send_to_worker 401 Session instance mismatch),无法向 Worker 回执
- Dominant language
- TypeScript
- Stars
- 2.7k
- Forks
- 395
- Avg merge
- 21h 48m
- Merged PRs (30d)
- 776
Description
**提交人**: 用户9200
**客户端版本**: 0.1.33
---
## 现象
在协同(Orca)模式下,长时间使用后出现单向通道失效:Worker→Lead 方向正常(Worker 消息仍能送达 Lead 会话),但 Lead→Worker 方向不可用,Lead 调用 `send_to_worker`、`get_workspace_info`、`list_workers` 等 Orca 工具全部返回 `HTTP 401: Session instance mismatch`,无法向 Worker 回执或派发新任务。该问题已多次复现。
## 复现步骤
1. 长时间使用协同(Orca)模式(数小时量级),期间主会话可能经历连接重连/恢复(日志可见 `Reconnecting...` 与 `thread resume`);
2. 之后 Lead 调用 `send_to_worker`、`get_workspace_info`、`list_workers` 等工具,即全部返回 `401 Session instance mismatch`;
3. Worker→Lead 方向仍正常,形成单向失效。
## 期望行为
Lead→Worker 方向应随主会话重连/恢复自动重建 MCP 会话绑定并恢复可用;若无法自动恢复,应给出明确的重连提示或提供手动重连入口,而不是静默失效。
## 实际行为
MCP 会话句柄未随主会话重建,导致 Lead→Worker 方向持续 401,需人工重启会话/应用才能恢复。
---
**版本区域**: CN
**OS**: win32 x64 (10.0.26100)
**界面语言**: zh-CN
Contributor guide
Research direction
Start by tracing the send_to_worker, get_workspace_info, and list_workers entry points alongside the Reconnecting and thread resume flow. Inspect how the MCP session handle is bound and rebuilt after the main session reconnects. Done means Lead→Worker calls no longer return 401 after recovery, with a clear reconnect path if automatic recovery fails.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- authentication, backend-api-design, distributed-systems
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100