Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix 4.27 Regression: Feishu response delay from 8s to 30s, resolved by downgrading to 4.23 [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#74911•Fetched 2026-05-01 05:40:01
View on GitHub
Comments
2
Participants
3
Timeline
7
Reactions
2
Author
sslnv88sslnv88
Participants
clawsweeper[bot]clawsweeper[bot]porly1985porly1985sslnv88sslnv88
Timeline (top)
commented ×2mentioned ×2subscribed ×2cross-referenced ×1

After upgrading to 2026.4.27, Feishu channel response latency increased from ~8 seconds to ~30 seconds per message. Downgrading back to 2026.4.23 immediately restored ~8 second responses.

Error Message

  • Gateway CPU usage normal, no obvious error logs

Root Cause

The delay is not in model inference itself, but in the Gateway processing layer. Possible root causes:

  1. Model catalog / Provider discovery — ensureOpenClawModelsJson() cold start path is expensive
  2. Plugin runtime dependencies — Each message triggers repeated filesystem/cache/materialization work
  3. Event loop blocking — Synchronous file reads + heavy computation blocking the main thread

Consistent with issues #74135 and #74240.

Fix Action

Workaround

Downgrade to 2026.4.23:

npm install -g [email protected]
openclaw gateway restart

Code Example

npm install -g openclaw@2026.4.23
openclaw gateway restart
RAW_BUFFERClick to expand / collapse

Summary

After upgrading to 2026.4.27, Feishu channel response latency increased from ~8 seconds to ~30 seconds per message. Downgrading back to 2026.4.23 immediately restored ~8 second responses.

Environment

  • OpenClaw: 2026.4.23 (working) / 2026.4.27 (broken)
  • OS: Linux 6.17.0-22-generic (x64)
  • Node: v22.22.2
  • Channel: Feishu (Lark)
  • Model: mimo/mimo-v2.5 (1000k ctx)
  • Plugins: openclaw-lark, memory-core, browser, duckduckgo, qqbot

Symptoms

2026.4.27

  • Every conversation response takes ~30 seconds
  • Gateway CPU usage normal, no obvious error logs
  • Feishu messages send fine, but replies are clearly slower
  • Bootstrap files total only ~5570 chars (~1400 tokens) — not a context loading issue

2026.4.23 (after downgrade)

  • Every conversation response takes ~8 seconds
  • All features working normally

Analysis

The delay is not in model inference itself, but in the Gateway processing layer. Possible root causes:

  1. Model catalog / Provider discovery — ensureOpenClawModelsJson() cold start path is expensive
  2. Plugin runtime dependencies — Each message triggers repeated filesystem/cache/materialization work
  3. Event loop blocking — Synchronous file reads + heavy computation blocking the main thread

Consistent with issues #74135 and #74240.

Workaround

Downgrade to 2026.4.23:

npm install -g [email protected]
openclaw gateway restart

Additional Context

  • Enabled truncateAfterCompaction: true and maxActiveTranscriptBytes: "3mb" for transcript optimization
  • Same hardware environment — only difference between 4.23 and 4.27 is the version number

extent analysis

TL;DR

Downgrade to OpenClaw version 2026.4.23 to immediately restore the ~8 second response time.

Guidance

  • Verify that the issue is indeed caused by the Gateway processing layer by checking CPU usage and error logs, as the model inference itself does not seem to be the cause of the delay.
  • Investigate the ensureOpenClawModelsJson() cold start path as a potential root cause, as it is an expensive operation that could be contributing to the increased latency.
  • Consider optimizing plugin runtime dependencies to reduce repeated filesystem/cache/materialization work triggered by each message.
  • Check for event loop blocking caused by synchronous file reads and heavy computation, which could be blocking the main thread and contributing to the delay.

Example

No code snippet is provided as the issue is more related to versioning and configuration rather than a specific code problem.

Notes

The provided workaround of downgrading to 2026.4.23 has been confirmed to restore the ~8 second response time, but it is essential to investigate the root cause to ensure a long-term solution.

Recommendation

Apply the workaround by downgrading to OpenClaw version 2026.4.23, as it has been confirmed to resolve the issue immediately. This will allow for further investigation into the root cause while maintaining a functional system.

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…
#api#installation#tensor shape#autograd error#optimization

Still need to ship something?

×6

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

Back to top recommendations

TRENDING