Issue Station
Sign In
Tools hereToolbox

gemini-cli - 💡(How to fix) Fix [Bug] Fatal Crash on Keystroke at 100% API Quota (Inline Completion Error) + Severe Model Performance [1 comments, 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#26089•Fetched 2026-04-29 06:36:12
View on GitHub
Comments
1
Participants
1
Timeline
2
Reactions
0
Author
jyongchuljyongchul
Participants
jyongchuljyongchul
Timeline (top)
commented ×1labeled ×1

Error Message

This appears to be caused by the background enablePromptCompletion and inlineThinkingMode features triggering an API request on keystroke. When the API returns a 429 Quota Exceeded error, the CLI fails to handle the exception gracefully and terminates the session entirely without displaying an error message. The CLI should smoothly handle the 429 error from inline completion without crashing the terminal session. It should display a "Quota Reached" warning or simply disable autocomplete, allowing the user to continue interacting with menus.

Root Cause

1. CLI Fatal Crash on Keystroke (Inline Completion Bug) Even when not actively using the CLI to generate any prompts, the Model Usage quota occasionally shows 100% exhausted across all models (Flash, Flash Lite, Pro) due to background tasks or strict preview model limits. The critical bug is that when the quota is at 100%, simply typing any character into the CLI causes the entire application to instantly crash and bounce out to the terminal prompt. This appears to be caused by the background enablePromptCompletion and inlineThinkingMode features triggering an API request on keystroke. When the API returns a 429 Quota Exceeded error, the CLI fails to handle the exception gracefully and terminates the session entirely without displaying an error message.

RAW_BUFFERClick to expand / collapse

1. CLI Fatal Crash on Keystroke (Inline Completion Bug) Even when not actively using the CLI to generate any prompts, the Model Usage quota occasionally shows 100% exhausted across all models (Flash, Flash Lite, Pro) due to background tasks or strict preview model limits. The critical bug is that when the quota is at 100%, simply typing any character into the CLI causes the entire application to instantly crash and bounce out to the terminal prompt. This appears to be caused by the background enablePromptCompletion and inlineThinkingMode features triggering an API request on keystroke. When the API returns a 429 Quota Exceeded error, the CLI fails to handle the exception gracefully and terminates the session entirely without displaying an error message.

Steps to Reproduce:

  1. Reach 100% quota limit on the connected Google One AI Ultra account.
  2. Launch gemini --yolo.
  3. Type any character in the prompt area.
  4. The CLI immediately crashes/exits to the standard bash prompt.

Expected Behavior: The CLI should smoothly handle the 429 error from inline completion without crashing the terminal session. It should display a "Quota Reached" warning or simply disable autocomplete, allowing the user to continue interacting with menus.

2. Appalling Performance of gemini-3.1-pro-preview on Windows/WSL I must also strongly report that the gemini-3.1-pro-preview model is currently severely underperforming to the point where it is fundamentally impossible to work effectively in a Windows/WSL environment. The model frequently misunderstands basic file system structures and outputs "stupid" context assumptions, causing critical workflow bottlenecks.

Environment:

  • OS: Windows 11 / WSL Ubuntu
  • CLI Version: v0.39.1
  • Plan: Google One AI Ultra

extent analysis

TL;DR

Modify the CLI to handle the 429 Quota Exceeded error from the API without crashing the session.

Guidance

  • Investigate the enablePromptCompletion and inlineThinkingMode features to determine how they can be modified to handle quota limits without triggering a crash.
  • Consider implementing a try-catch block to catch the 429 Quota Exceeded error and display a "Quota Reached" warning or disable autocomplete instead of crashing.
  • Review the error handling mechanisms in the CLI to ensure that exceptions are handled gracefully and do not terminate the session.
  • Evaluate the performance of the gemini-3.1-pro-preview model in the Windows/WSL environment to identify potential bottlenecks and areas for improvement.

Example

try:
    # API request for inline completion
    response = api_request()
    if response.status_code == 429:
        # Handle quota exceeded error
        print("Quota Reached")
        # Disable autocomplete or display warning
except Exception as e:
    # Handle other exceptions
    print(f"Error: {e}")

Notes

The provided guidance is based on the assumption that the CLI is written in a language that supports try-catch blocks and error handling mechanisms. The example code snippet is a simplified illustration and may need to be adapted to the actual implementation.

Recommendation

Apply workaround: Modify the CLI to handle the 429 Quota Exceeded error without crashing the session, as this will provide a more stable and user-friendly experience.

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#pipeline error#runtime error#dependency conflict#environment setup

Still need to ship something?

×6

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

Back to top recommendations

TRENDING