openclaw - 💡(How to fix) Fix [Bug] core-plugin-tools ~3.5s overhead on every embedded run persists after #75520 fix — Windows + Node 24 + isolated cron jobs [2 comments, 2 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#80416Fetched 2026-05-11 03:14:54
View on GitHub
Comments
2
Participants
2
Timeline
2
Reactions
2
Timeline (top)
commented ×2

Despite the fixes in #75520 and #77029 being shipped in v2026.5.7, core-plugin-tools still takes ~3.4-4.2s on every embedded agent run. With frequent cron jobs, this creates a domino effect where the event loop saturates and Ollama cloud requests timeout.

Root Cause

Despite the fixes in #75520 and #77029 being shipped in v2026.5.7, core-plugin-tools still takes ~3.4-4.2s on every embedded agent run. With frequent cron jobs, this creates a domino effect where the event loop saturates and Ollama cloud requests timeout.

RAW_BUFFERClick to expand / collapse

Summary

Despite the fixes in #75520 and #77029 being shipped in v2026.5.7, core-plugin-tools still takes ~3.4-4.2s on every embedded agent run. With frequent cron jobs, this creates a domino effect where the event loop saturates and Ollama cloud requests timeout.

Environment

  • OpenClaw: v2026.5.7 (eeef486) — latest stable
  • Node: v24.15.0
  • OS: Windows 11 (22000) x64
  • CPU: Intel i7-12700K (12 cores)
  • RAM: 48GB
  • Model provider: Ollama (local install, but models are cloud-hosted, not local)
  • Primary model: ollama/deepseek-v4-pro:cloud

Active plugins (minimal)

Only 3 plugins active after pruning everything unused:

  • rowser
  • memory-core (dreaming disabled)
  • ollama

(Previously removed: feishu, acpx, telegram, slack, and others)

Symptom

Every isolated cron job run and every direct message shows the same overhead:

core-plugin-tools: 3441ms, 3453ms, 3534ms, 3567ms, 3554ms, 3611ms, 3621ms, 3642ms, 4248ms bundle-tools: 5810ms - 6166ms stream-setup: 4972ms - 5345ms TOTAL prep: 15279ms - 16036ms

This repeats on every single run — not just cold starts. Even consecutive runs for the same agent show the same overhead.

Effect

With a cron job running every 10 minutes (

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…

Still need to ship something?

×6

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

Back to top recommendations

TRENDING