Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Upgrading from Before: 2026.3.24 After: 2026.5.19 => significant increase in llm token usage when inactive [1 pull requests]

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…

After upgrading from 2026.3.24 to 2026.5.19, and even though my openclaw is just idling with no requested activity, my chosen model's token usage jumped from where it had often been as low as ~10k tokens per day, to averaging over a million for the duration since I upgraded it last night:

I have a few chat gateways installed, but 'openclaw status' indicates they haven't been active since upgrading.

It says my 'main' session has "82k/205k (40%) · 🗄️ 52% cached" tokens (though I tried /new in the tui)... and there is a '30m heartbeat'.

In stopping the gateway, my llm's token usage has fallen to ~0 aga

<img width="809" height="626" alt="Image" src="https://github.com/user-attachments/assets/ed9f755c-19b6-46b2-bd2d-0dc465a02dea" />

Root Cause

After upgrading from 2026.3.24 to 2026.5.19, and even though my openclaw is just idling with no requested activity, my chosen model's token usage jumped from where it had often been as low as ~10k tokens per day, to averaging over a million for the duration since I upgraded it last night:

I have a few chat gateways installed, but 'openclaw status' indicates they haven't been active since upgrading.

It says my 'main' session has "82k/205k (40%) · 🗄️ 52% cached" tokens (though I tried /new in the tui)... and there is a '30m heartbeat'.

In stopping the gateway, my llm's token usage has fallen to ~0 aga

<img width="809" height="626" alt="Image" src="https://github.com/user-attachments/assets/ed9f755c-19b6-46b2-bd2d-0dc465a02dea" />

Fix Action

Fixed

RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

After upgrading from 2026.3.24 to 2026.5.19, and even though my openclaw is just idling with no requested activity, my chosen model's token usage jumped from where it had often been as low as ~10k tokens per day, to averaging over a million for the duration since I upgraded it last night:

I have a few chat gateways installed, but 'openclaw status' indicates they haven't been active since upgrading.

It says my 'main' session has "82k/205k (40%) · 🗄️ 52% cached" tokens (though I tried /new in the tui)... and there is a '30m heartbeat'.

In stopping the gateway, my llm's token usage has fallen to ~0 aga

<img width="809" height="626" alt="Image" src="https://github.com/user-attachments/assets/ed9f755c-19b6-46b2-bd2d-0dc465a02dea" />

Steps to reproduce

I would try installing 2026.3.24 + discord, telegram gateways & then upgrade it to 2026.5.19

Expected behavior

I do not think upgrading should result in significantly increased token usage.

Actual behavior

Significantly increased token usage.

OpenClaw version

2026.5.19

Operating system

MacOS Sequoyah 15.6.1 (24G90)

Install method

No response

Model

glm-5.1

Provider / routing chain

z.ai

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

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

I do not think upgrading should result in significantly increased token usage.

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]: Upgrading from Before: 2026.3.24 After: 2026.5.19 => significant increase in llm token usage when inactive [1 pull requests]