openclaw - 💡(How to fix) Fix [Bug]: embedded run failover decision because of timeout [9 comments, 6 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#59598Fetched 2026-04-08 02:42:47
View on GitHub
Comments
9
Participants
6
Timeline
14
Reactions
0
Author
Timeline (top)
commented ×9cross-referenced ×3labeled ×1subscribed ×1

After upgrated to 2026.4.1, the gateway display the following message after input some message in openclaw webpage:

17:48:38+08:00 [agent/embedded] embedded run failover decision: runId=fa92620f-4ad8-40d4-9855-9f82a5d42ac8 stage=assistant decision=surface_error reason=timeout provider=custom-127-0-0-1-8088/NVIDIA-Nemotron-3-Super-120B-A12B profile=- ...

and then the LLM running is idle, the openclaw stopped working.

Error Message

continue to let the LLM works without timeout error.

Root Cause

as shown above, the openclaw stopped working because of timeout.

RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

After upgrated to 2026.4.1, the gateway display the following message after input some message in openclaw webpage:

17:48:38+08:00 [agent/embedded] embedded run failover decision: runId=fa92620f-4ad8-40d4-9855-9f82a5d42ac8 stage=assistant decision=surface_error reason=timeout provider=custom-127-0-0-1-8088/NVIDIA-Nemotron-3-Super-120B-A12B profile=- ...

and then the LLM running is idle, the openclaw stopped working.

Steps to reproduce

  1. start openclaw 2026.4.1 in Windows 10 64bit, only CPU (the LLM launched by llama-server);
  2. input some message let the openclaw do some work;
  3. after sever miniutes, the above message displayed and then the llama-server displayed slots are idle.

Expected behavior

continue to let the LLM works without timeout error. or is there any settings need to do to increase the timeout value?

Actual behavior

as shown above, the openclaw stopped working because of timeout.

OpenClaw version

2026.4.1

Operating system

Windows 10 64bit

Install method

nmp global

Model

NVIDIA-Nemotron-3-Super-120B-A12B

Provider / routing chain

local

Additional provider/model setup details

the whole openclaw.json: { "models": { "mode": "merge", "providers": { "custom-127-0-0-1-8088": { "baseUrl": "http://127.0.0.1:8088/v1", "apiKey": "tang-local", "api": "openai-completions", "models": [ { "id": "NVIDIA-Nemotron-3-Super-120B-A12B", "name": "NVIDIA-Nemotron-3-Super-120B-A12B (Custom Provider)", "contextWindow": 1048576, "maxTokens": 4194304, "input": [ "text" ], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "reasoning": false } ] } } }, "agents": { "defaults": { "model": { "primary": "custom-127-0-0-1-8088/NVIDIA-Nemotron-3-Super-120B-A12B" }, "models": { "custom-127-0-0-1-8088/NVIDIA-Nemotron-3-Super-120B-A12B": { "alias": "local" } }, "workspace": "C:\Users\local\AppData\Roaming\SPB_Data\.openclaw\workspace", "timeoutSeconds": 360000 } }, "tools": { "profile": "full" }, "session": { "dmScope": "per-channel-peer" }, "gateway": { "port": 18789, "mode": "local", "bind": "loopback", "controlUi": { "allowInsecureAuth": true }, "auth": { "mode": "token", "token": "b570f2eda79ed6e911e4760688db6119263815c0dbf97204" }, "tailscale": { "mode": "off", "resetOnExit": false }, "nodes": { "denyCommands": [ "camera.snap", "camera.clip", "screen.record", "contacts.add", "calendar.add", "reminders.add", "sms.send", "sms.search" ] } }, "hooks": { "internal": { "enabled": true, "entries": { "session-memory": { "enabled": true } } } }, "wizard": { "lastRunAt": "2026-04-02T09:46:03.832Z", "lastRunVersion": "2026.4.1", "lastRunCommand": "doctor", "lastRunMode": "local" }, "meta": { "lastTouchedVersion": "2026.4.1", "lastTouchedAt": "2026-04-02T09:46:03.845Z" } }

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

Increase the timeoutSeconds value in the openclaw.json configuration file to a higher value to prevent timeouts.

Guidance

  • Check the current timeoutSeconds value in the openclaw.json file, which is set to 360000 (100 hours), and consider increasing it to a higher value.
  • Verify that the llama-server is not experiencing any issues or resource constraints that could be causing the timeout.
  • Review the logs and system resources to ensure that there are no other underlying issues that could be contributing to the timeout.
  • Consider adding additional logging or monitoring to help identify the root cause of the timeout.

Example

No code example is provided as the issue is related to configuration and not code.

Notes

The provided openclaw.json file shows a timeoutSeconds value of 360000, which is a relatively high value. However, it's possible that the timeout is still occurring due to other factors such as system resource constraints or network issues.

Recommendation

Apply a workaround by increasing the timeoutSeconds value to a higher value, such as 720000 (200 hours), to prevent timeouts and allow the LLM to continue running without interruption.

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

continue to let the LLM works without timeout error. or is there any settings need to do to increase the timeout value?

Still need to ship something?

×6

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

Back to top recommendations

TRENDING