fix(patch): cherry-pick 2139b12 to release/v0.55.0-preview.1-pr-28716 to patch version v0.55.0-preview.1 and create version 0.55.0-preview.2 - #28719
Conversation
Summary of ChangesHello, 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 updates the model fallback mechanism to improve resilience when encountering capacity exhaustion. By reclassifying specific quota errors as terminal, the system can now trigger an immediate fallback to an alternative model rather than attempting redundant retries on an exhausted resource. This change ensures a more efficient and responsive user experience during high-load scenarios. Highlights
Using Gemini Code AssistThe 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
Customization To customize the 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 Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. 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. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request updates the error classification logic for Google API errors to treat model capacity exhaustion as a terminal error (TerminalQuotaError) rather than a retryable one, enabling immediate model fallback. It also updates the experimental agent-to-agent server task fallback handler to activate fallback mode and stop execution instead of retrying. Feedback was provided to pass delaySeconds to the TerminalQuotaError constructor when capacity exhaustion is detected via the error message to preserve any server-specified retry delay.
|
Size Change: +638 B (0%) Total Size: 35.2 MB
ℹ️ View Unchanged
|
|
📊 PR Size: size/M
|
b39816c
into
release/v0.55.0-preview.1-pr-28716
This PR automatically cherry-picks commit 2139b12 to patch version v0.55.0-preview.1 in the preview release to create version 0.55.0-preview.2.