fix: remove failed user content from history to prevent cascading 400 errors

[jackwotherspoon]

Summary

• Fix issue where a 400 invalid API error would corrupt the conversation history, causing all subsequent prompts to fail with the same error
• Remove bad content from history when API requests fail, preventing invalid content from persisting

Note: This PR does not fix the cause of the 400 errors, just makes them recoverable. Previously if they happened the session was toast and would need a /clear or full close.

Previous

Now

Problem

We save user content to history, even corrupt content such as when API returns a 400 error. Previously, this invalid content remained in the conversation history, causing every subsequent request to include it and fail with the same 400 error.

Solution

Call history.pop() to remove the failed user content when an error occurs, in both:

1. Connection-phase errors (immediate API failures like 400)
2. Streaming-phase errors (after retries are exhausted)

This ensures invalid content doesn't persist in history and break the session.

Related Issues

How to Validate

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed)
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • MacOS
    • npm run
    • npx
    • Docker
    • Podman
    • Seatbelt
  • Windows
    • npm run
    • npx
    • Docker
  • Linux
    • npm run
    • npx
    • Docker

[gemini-cli]

Hi @jackwotherspoon, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this.

We're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: Improving Our Contribution Process & Introducing New Guidelines.

Key Update: Starting January 26, 2026, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed.

Thank you for your understanding and for being a part of our community!

[gemini-code-assist]

Summary of Changes

Hello @jackwotherspoon, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical bug where API 400 errors would lead to a corrupted conversation history, causing all subsequent interactions to fail. The change ensures that any user content associated with a failed API request is immediately removed from the history. This proactive removal prevents the invalid state from persisting, thereby making the conversation recoverable and eliminating the need to clear the session or restart the application after an API error.

Highlights

• Error Recovery: Fixes an issue where 400 invalid API errors would corrupt conversation history, making sessions unrecoverable and requiring a full clear or restart.
• History Management: Removes user content from the conversation history when API requests fail, preventing invalid content from persisting and breaking subsequent requests.
• Cascading Error Prevention: Stops cascading 400 errors, allowing subsequent prompts to function correctly after an initial API failure by ensuring the history remains clean.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[github-actions]

Size Change: +642 B (0%)

Total Size: 23.2 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	23.2 MB	+642 B (0%)
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB	0 B
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-closed.sb	3.29 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B

_{compressed-size-action}

[gemini-code-assist]

Code Review

This pull request aims to fix an issue where failed API requests would corrupt the conversation history, leading to subsequent errors. The approach of removing the user's content from history upon failure is correct. However, the implementation for connection-phase errors has a critical flaw: it unconditionally removes the content and throws the error, which prevents the retry mechanism from engaging for recoverable errors like 5xx server issues. My review includes a critical comment with a suggested fix to ensure that retries can still happen for recoverable connection-phase errors, and the history is only popped for non-retryable failures or after all retries are exhausted.

[gemini-cli]

Hi there! Thank you for your contribution to Gemini CLI. We really appreciate the time and effort you've put into this pull request.

To keep our backlog manageable and ensure we're focusing on current priorities, we are closing pull requests that haven't seen maintainer activity for 30 days. Currently, the team is prioritizing work associated with 🔒 maintainer only or help wanted issues.

If you believe this change is still critical, please feel free to comment with updated details. Otherwise, we encourage contributors to focus on open issues labeled as help wanted. Thank you for your understanding!