openclaw - 💡(How to fix) Fix [Bug]: FailoverError — CLI timeout after 600s with no output, failover never triggers, TUI/webchat unresponsive [1 participants]

TL;DR

The issue can be mitigated by adjusting the timeout configuration or investigating the unreachable primary model, minimax/MiniMax-M2.5, to ensure failover to the fallback model, kimi-coding/k2p5, occurs as expected.

Guidance

• Investigate the primary model, minimax/MiniMax-M2.5, to determine why it became unreachable after the 2026.4.1 update, as this is the root cause of the failover issue.
• Review the configuration for the failover mechanism to ensure it is correctly set up to switch to the fallback model, kimi-coding/k2p5, when the primary model times out or fails.
• Consider temporarily reducing the 600s timeout to a lower value to reduce the wait time for users before the session is considered dead and potentially allow for quicker failover attempts.
• Examine the related issues (#57437, #58881, #58885, #59003, #59006, #59008, #59010, #59014, #59017, #59018) for any insights or fixes that might apply to this problem.

Example

No specific code snippet can be provided without more details on the configuration or codebase, but checking the model's connection settings and the failover logic would be a good starting point.

Notes

The exact solution depends on the specifics of the model integration and the failover mechanism's implementation, which are not fully detailed in the issue. The primary model's unreachability after the update suggests a compatibility or configuration issue that needs addressing.

Recommendation

Apply a workaround by adjusting the timeout and investigating the primary model's unreachability, as upgrading to a fixed version is not explicitly mentioned as an option in the provided context.