genai: retry_delay is not used to guide retry interval #945
Description
For my agent workflow, I often send a burst of requests thus exceeding the free tier from time to time.
It seems that the retry logic does not take the retry_delay from the 429 ResourceExhausted Error returned by Gemini
google.api_core.exceptions.ResourceExhausted: 429 You exceeded your current quota. Please migrate to Gemini 2.0 Flash Preview (Image Generation) (models/gemini-2.0-flash-preview-image-generation) for high
er quota limits. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. [violations {
}
, links { description: "Learn more about Gemini API quotas"
url: "https://ai.google.dev/gemini-api/docs/rate-limits"
}
, retry_delay {
seconds: 41
}
]