gemini-cli - 💡(How to fix) Fix Inaccurate and excessive usage of token [1 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
google-gemini/gemini-cli#26077Fetched 2026-04-28 06:49:46
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Participants
Timeline (top)
labeled ×1
RAW_BUFFERClick to expand / collapse

What happened?

It seems with the new update token limits are reaching much faster as compared to last week or week before for my user. Previously for my user, i have never hit the capacity even while working for weeks together. I have also observed memory crashes more frequently, just today it crashed twice, and with memory crash, even a bug cant be created as the session ends.

What did you expect to happen?

To get a clear usage stats of how tokens are being use for each of the prompt or query that I am asking gemini to work on.

Client information

  • CLI Version: 0.34.0
  • Git Commit: 49a86

Login information

google account CLI.

Anything else we need to know?

No response

extent analysis

TL;DR

The issue may be resolved by optimizing token usage or increasing the token limit, although the exact solution depends on the specifics of the Gemini API and the user's workflow.

Guidance

  • Review the Gemini API documentation to understand how token limits are calculated and what factors contribute to reaching the limit more quickly.
  • Investigate the recent update (CLI Version 0.34.0) to see if there are any changes in token usage or allocation that could be causing the issue.
  • Consider reaching out to the Gemini support team to request more detailed usage statistics, as the user is currently unable to access this information.
  • Look into optimizing the user's workflow to reduce token usage, such as batching queries or using more efficient prompts.

Notes

The issue lacks specific details about the Gemini API and the user's workflow, making it difficult to provide a more targeted solution. Additionally, the memory crashes may be a separate issue that needs to be addressed independently.

Recommendation

Apply workaround: Optimize token usage and investigate the recent update to identify potential causes of the issue, as there is no clear indication of a fixed version that resolves the problem.

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

gemini-cli - 💡(How to fix) Fix Inaccurate and excessive usage of token [1 participants]