Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: LLM request timeout still present

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…

Following up on #46049 I configure

openclaw config get agents.defaults.timeoutSeconds
300

As opposed to what is descibed in #46049, agents.defaults.llm.idleTimeoutSeconds is not accepted anymore.

node@f8f71cc900d4:/app$ openclaw config set agents.defaults.llm.idleTimeoutSeconds 300
Error: Config validation failed: agents.defaults: Unrecognized key: "llm"

Error Message

node@f8f71cc900d4:/app$ openclaw config set agents.defaults.llm.idleTimeoutSeconds 300 Error: Config validation failed: agents.defaults: Unrecognized key: "llm"

Root Cause

Following up on #46049 I configure

openclaw config get agents.defaults.timeoutSeconds
300

As opposed to what is descibed in #46049, agents.defaults.llm.idleTimeoutSeconds is not accepted anymore.

node@f8f71cc900d4:/app$ openclaw config set agents.defaults.llm.idleTimeoutSeconds 300
Error: Config validation failed: agents.defaults: Unrecognized key: "llm"

Code Example

openclaw config get agents.defaults.timeoutSeconds
300

---

node@f8f71cc900d4:/app$ openclaw config set agents.defaults.llm.idleTimeoutSeconds 300
Error: Config validation failed: agents.defaults: Unrecognized key: "llm"

---

08:39:15+00:00 warn agent/embedded {"subsystem":"agent/embedded"} Profile google:default timed out. Trying next account...
08:39:15+00:00 warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_failover_decision","tags":["error_handling","failover","assistant","fallback_model"],"runId":"1ce11eec-71e5-4860-b5df-c458eeabad01","stage":"assistant","decision":"fallback_model","failoverReason":"timeout","profileFailureReason":"timeout","provider":"google","model":"gemini-3.1-flash-lite-preview","sourceProvider":"google","sourceModel":"gemini-3.1-flash-lite-preview","profileId":"sha256:a94403a4f9d0","fallbackConfigured":true,"timedOut":true,"aborted":true,"status":408} embedded run failover decision
08:39:15+00:00 error diagnostic {"subsystem":"diagnostic"} lane task error: lane=main durationMs=124825 error="FailoverError: LLM request timed out."
08:39:15+00:00 error diagnostic {"subsystem":"diagnostic"} lane task error: lane=session:agent:main:tui-8d0853e2-3659-4eba-bf52-632061daad7f durationMs=124826 error="FailoverError: LLM request timed out."
08:39:15+00:00 warn diagnostic {"subsystem":"diagnostic"} lane wait exceeded: lane=session:agent:main:tui-8d0853e2-3659-4eba-bf52-632061daad7f waitedMs=28755 queueAhead=0
08:39:15+00:00 warn model-fallback/decision {"subsystem":"model-fallback/decision"} {"event":"model_fallback_decision","tags":["error_handling","model_fallback","candidate_failed"],"runId":"1ce11eec-71e5-4860-b5df-c458eeabad01","decision":"candidate_failed","requestedProvider":"google","requestedModel":"gemini-3.1-pro-preview","candidateProvider":"google","candidateModel":"gemini-3.1-pro-preview","attempt":1,"total":1,"reason":"timeout","status":408,"errorPreview":"LLM request timed out.","errorHash":"sha256:321034bb3121","fallbackStepType":"fallback_step","fallbackStepFromModel":"google/gemini-3.1-pro-preview","fallbackStepFromFailureReason":"timeout","fallbackStepFromFailureDetail":"LLM request timed out.","fallbackStepChainPosition":1,"fallbackStepFinalOutcome":"chain_exhausted","isPrimary":true,"requestedModelMatched":true,"fallbackConfigured":false} model fallback decision
RAW_BUFFERClick to expand / collapse

Bug type

Behavior bug (incorrect output/state without crash)

Beta release blocker

No

Summary

Following up on #46049 I configure

openclaw config get agents.defaults.timeoutSeconds
300

As opposed to what is descibed in #46049, agents.defaults.llm.idleTimeoutSeconds is not accepted anymore.

node@f8f71cc900d4:/app$ openclaw config set agents.defaults.llm.idleTimeoutSeconds 300
Error: Config validation failed: agents.defaults: Unrecognized key: "llm"

Steps to reproduce

Start a dockerized environment, standard config. Run a simple on-line prompt.

Expected behavior

Even if the model takes a bit longer, the call should not be aborted before the timeout was hit.

Actual behavior

I still get the LLM request timed out. for almost every prompt. The timeout happens earlier than configured (durationMs=124826?).

OpenClaw version

2026.5.7

Operating system

Linux

Install method

docker

Model

gemini-3.1-flash-lite-preview / gemini-3.1-pro-preview

Provider / routing chain

openclaw -> Gemini

Additional provider/model setup details

No response

Logs, screenshots, and evidence

08:39:15+00:00 warn agent/embedded {"subsystem":"agent/embedded"} Profile google:default timed out. Trying next account...
08:39:15+00:00 warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_failover_decision","tags":["error_handling","failover","assistant","fallback_model"],"runId":"1ce11eec-71e5-4860-b5df-c458eeabad01","stage":"assistant","decision":"fallback_model","failoverReason":"timeout","profileFailureReason":"timeout","provider":"google","model":"gemini-3.1-flash-lite-preview","sourceProvider":"google","sourceModel":"gemini-3.1-flash-lite-preview","profileId":"sha256:a94403a4f9d0","fallbackConfigured":true,"timedOut":true,"aborted":true,"status":408} embedded run failover decision
08:39:15+00:00 error diagnostic {"subsystem":"diagnostic"} lane task error: lane=main durationMs=124825 error="FailoverError: LLM request timed out."
08:39:15+00:00 error diagnostic {"subsystem":"diagnostic"} lane task error: lane=session:agent:main:tui-8d0853e2-3659-4eba-bf52-632061daad7f durationMs=124826 error="FailoverError: LLM request timed out."
08:39:15+00:00 warn diagnostic {"subsystem":"diagnostic"} lane wait exceeded: lane=session:agent:main:tui-8d0853e2-3659-4eba-bf52-632061daad7f waitedMs=28755 queueAhead=0
08:39:15+00:00 warn model-fallback/decision {"subsystem":"model-fallback/decision"} {"event":"model_fallback_decision","tags":["error_handling","model_fallback","candidate_failed"],"runId":"1ce11eec-71e5-4860-b5df-c458eeabad01","decision":"candidate_failed","requestedProvider":"google","requestedModel":"gemini-3.1-pro-preview","candidateProvider":"google","candidateModel":"gemini-3.1-pro-preview","attempt":1,"total":1,"reason":"timeout","status":408,"errorPreview":"LLM request timed out.","errorHash":"sha256:321034bb3121","fallbackStepType":"fallback_step","fallbackStepFromModel":"google/gemini-3.1-pro-preview","fallbackStepFromFailureReason":"timeout","fallbackStepFromFailureDetail":"LLM request timed out.","fallbackStepChainPosition":1,"fallbackStepFinalOutcome":"chain_exhausted","isPrimary":true,"requestedModelMatched":true,"fallbackConfigured":false} model fallback decision

Impact and severity

Almost every prompt times out. Only very small contexts with a fast and simple model work seldomly.

Additional information

No response

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

Even if the model takes a bit longer, the call should not be aborted before the timeout was hit.

#agent setup#task chaining#parallel task#integration issue#index setup

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: LLM request timeout still present