Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Delay in provider/transport path [2 comments, 3 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#74192•Fetched 2026-04-30 06:27:39
View on GitHub
Comments
2
Participants
3
Timeline
12
Reactions
2
Author
karlis0karlis0
Participants
clawsweeper[bot]clawsweeper[bot]karlis0karlis0porly1985porly1985
Timeline (top)
subscribed ×4mentioned ×3commented ×2labeled ×2

After updating to 2026.4.24 there was a huge delay introduced from the moment the message is sent till the moment the actual reply from the agent shows up. I have tried to reinstall OpenClaw before wiping all the files (clean and fresh start), but still getting the same delay.

For reference, on Hermes are not experiencing similar issue.

Root Cause

After updating to 2026.4.24 there was a huge delay introduced from the moment the message is sent till the moment the actual reply from the agent shows up. I have tried to reinstall OpenClaw before wiping all the files (clean and fresh start), but still getting the same delay.

For reference, on Hermes are not experiencing similar issue.

RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

After updating to 2026.4.24 there was a huge delay introduced from the moment the message is sent till the moment the actual reply from the agent shows up. I have tried to reinstall OpenClaw before wiping all the files (clean and fresh start), but still getting the same delay.

For reference, on Hermes are not experiencing similar issue.

Steps to reproduce

Baseline: hermes chat -q 'Reply pong only.' -m gpt-5.5 --provider openai-codex -Q -> pong in ~4.16s

OpenClaw local infer: /usr/bin/time -f 'ELAPSED=%e' openclaw infer model run --model openai-codex/gpt-5.5 --prompt 'Reply pong only.' --json -> transport=local, pong, ELAPSED ~105–113s

OpenClaw gateway infer: /usr/bin/time -f 'ELAPSED=%e' openclaw infer model run --gateway --model openai-codex/gpt-5.5 --prompt 'Reply pong only.' --json -> transport=gateway, pong, ELAPSED ~46s

OpenClaw agent: sid="debug-$(date +%s)" /usr/bin/time -f 'ELAPSED=%e' openclaw agent --session-id "$sid" --message 'Reply pong only.' --thinking off --json -> pong, ELAPSED ~31–42s, promptTokens ~13.7k

Actual:

Expected behavior

OpenClaw openai-codex/gpt-5.5 should be in the same rough latency class as Hermes using the same provider/model.

Actual behavior

OpenClaw local infer is ~25x slower than Hermes, gateway/agent paths are still ~8–11x slower.

OpenClaw version

2026.4.26 (be8c246)

Operating system

Ubuntu 25.10

Install method

npm global

Model

openai-codex/gpt-5.5

Provider / routing chain

gateway

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

Downgrade OpenClaw to a version prior to 2026.4.24 to potentially resolve the significant delay introduced in the latest update.

Guidance

  • Verify the delay is consistent across different models and providers to isolate if the issue is specific to openai-codex/gpt-5.5 or a broader problem.
  • Compare the performance of OpenClaw local infer, gateway infer, and agent to identify if the bottleneck is in a specific part of the pipeline.
  • Test the same workflow on a different operating system or environment to check if the issue is Ubuntu 25.10 specific.
  • Consider reaching out to the OpenClaw community or support for further assistance, as the delay is substantial and not seen in Hermes.

Example

No specific code snippet can be provided without more context on the changes made in the 2026.4.24 update.

Notes

The delay seems to have been introduced in the 2026.4.24 update of OpenClaw, and downgrading might be a temporary workaround. However, without more information on the changes made in this update, it's difficult to provide a more targeted fix.

Recommendation

Apply workaround: Downgrade OpenClaw to a version before 2026.4.24, as this seems to be when the delay was introduced, and there's no clear indication of how to fix it in the current version.

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

OpenClaw openai-codex/gpt-5.5 should be in the same rough latency class as Hermes using the same provider/model.

#inference speed#output truncation#response parsing#generation error#database connection

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]: Delay in provider/transport path [2 comments, 3 participants]