openclaw - 💡(How to fix) Fix [Bug]: fallover loop [2 comments, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#62047Fetched 2026-04-08 03:09:45
View on GitHub
Comments
2
Participants
1
Timeline
4
Reactions
0
Author
Participants
Timeline (top)
commented ×2labeled ×2

I testing gemma4:26b on my OC. I have OC continuously fallover to another model and it starts to loop around the models. Also it starts from the last one that is a qwen3.5:4b on the fallover list.

These are the messages I am getting in the logs:

7:31:35 PM error diagnostic lane task error: lane=main durationMs=61140 error="FailoverError: LLM request timed out."

lane task error: lane=session:agent:developeragent:discord:channel:1234567890 durationMs=61141 error="FailoverError: LLM request timed out."

Embedded agent failed before reply: All models failed (4): ollama/qwen3.5:4b: LLM request timed out. (timeout) | ollama/qwen3.5:35b: LLM request timed out. (timeout) | ollama/qwen3.5:27b: LLM request timed out. (timeout) | ollama/qwen3.5:9b: LLM request timed out. (timeout)

everything was working fine until 2/3 OC releases ago.

Error Message

7:31:35 PM error diagnostic lane task error: lane=main durationMs=61140 error="FailoverError: LLM request timed out."

lane task error: lane=session:agent:developeragent:discord:channel:1234567890 durationMs=61141 error="FailoverError: LLM request timed out."

Embedded agent failed before reply: All models failed (4): ollama/qwen3.5:4b: LLM request timed out. (timeout) | ollama/qwen3.5:35b: LLM request timed out. (timeout) | ollama/qwen3.5:27b: LLM request timed out. (timeout) | ollama/qwen3.5:9b: LLM request timed out. (timeout)

Root Cause

I testing gemma4:26b on my OC. I have OC continuously fallover to another model and it starts to loop around the models. Also it starts from the last one that is a qwen3.5:4b on the fallover list.

These are the messages I am getting in the logs:

7:31:35 PM error diagnostic lane task error: lane=main durationMs=61140 error="FailoverError: LLM request timed out."

lane task error: lane=session:agent:developeragent:discord:channel:1234567890 durationMs=61141 error="FailoverError: LLM request timed out."

Embedded agent failed before reply: All models failed (4): ollama/qwen3.5:4b: LLM request timed out. (timeout) | ollama/qwen3.5:35b: LLM request timed out. (timeout) | ollama/qwen3.5:27b: LLM request timed out. (timeout) | ollama/qwen3.5:9b: LLM request timed out. (timeout)

everything was working fine until 2/3 OC releases ago.

Code Example

7:31:35 PM error diagnostic lane task error: lane=main durationMs=61140 error="FailoverError: LLM request timed out."

lane task error: lane=session:agent:developeragent:discord:channel:1234567890 durationMs=61141 error="FailoverError: LLM request timed out."

Embedded agent failed before reply: All models failed (4): ollama/qwen3.5:4b: LLM request timed out. (timeout) | ollama/qwen3.5:35b: LLM request timed out. (timeout) | ollama/qwen3.5:27b: LLM request timed out. (timeout) | ollama/qwen3.5:9b: LLM request timed out. (timeout)

---
RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

I testing gemma4:26b on my OC. I have OC continuously fallover to another model and it starts to loop around the models. Also it starts from the last one that is a qwen3.5:4b on the fallover list.

These are the messages I am getting in the logs:

7:31:35 PM error diagnostic lane task error: lane=main durationMs=61140 error="FailoverError: LLM request timed out."

lane task error: lane=session:agent:developeragent:discord:channel:1234567890 durationMs=61141 error="FailoverError: LLM request timed out."

Embedded agent failed before reply: All models failed (4): ollama/qwen3.5:4b: LLM request timed out. (timeout) | ollama/qwen3.5:35b: LLM request timed out. (timeout) | ollama/qwen3.5:27b: LLM request timed out. (timeout) | ollama/qwen3.5:9b: LLM request timed out. (timeout)

everything was working fine until 2/3 OC releases ago.

Steps to reproduce

No sure since I do not know if it's my configuration or something else.

Expected behavior

Use the first model of the list: gemma4:26b

Actual behavior

fallover to the other LLMs until it stops and nothing work anymore until I restart the gateway.

OpenClaw version

2026.4.5

Operating system

ubuntu 24

Install method

No response

Model

openclaw update

Provider / routing chain

ollama/gemma4:26b, ollama/qwen3.5:35b, ollama/qwen3.5:27b, ollama/qwen3.5:9b, ollama/qwen3.5:4b

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

The issue can be mitigated by investigating and addressing the "LLM request timed out" errors for the models in the fallover list, starting with the first model, gemma4:26b.

Guidance

  • Investigate the "LLM request timed out" errors for each model in the fallover list to identify the root cause of the timeouts.
  • Verify the configuration and setup of the models, especially gemma4:26b, to ensure they are correctly set up and functioning as expected.
  • Check the network connectivity and latency between the OC and the LLM models to rule out any external factors contributing to the timeouts.
  • Consider increasing the timeout duration for the LLM requests to see if it resolves the issue, but this should be done cautiously to avoid masking underlying problems.

Example

No code snippet is provided as the issue does not contain sufficient information to create a relevant example.

Notes

The issue seems to have started after a recent OC release, suggesting a potential regression. However, without more information on the configuration, setup, and changes made, it's challenging to provide a definitive solution. The guidance provided aims to help the user troubleshoot and potentially mitigate the issue.

Recommendation

Apply workaround: Investigate and address the "LLM request timed out" errors, as this approach allows for a more targeted troubleshooting effort without waiting for a potential fix in a future release.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

Use the first model of the list: gemma4:26b

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING