Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Monthly Maximum GenerateAssistantResponse #6184

Open
adrianstephens opened this issue Dec 9, 2024 · 2 comments
Open

Monthly Maximum GenerateAssistantResponse #6184

adrianstephens opened this issue Dec 9, 2024 · 2 comments
Labels
amazon-q codewhisperer guidance General information and guidance, answers to FAQs, or recommended best practices/resources.

Comments

@adrianstephens
Copy link

System details (run AWS: About and/or Amazon Q: About)

  • OS: Windows 11
  • Visual Studio Code version: 1.95.3
  • Amazon Q version: 1.39.0 2024-12-03

Question

Around the 20th of every month since I started using Q I get:
"An error occurred while processing your request.
This error is reported to the team automatically. We will attempt to fix it as soon as possible.
Details: Maximum com.amazon.aws.codewhisperer.streaming.GenerateAssistantResponse reached for this month."

I understand that you might need to limit usage, and I'm not complaining, but:

  1. Is this typical? Do most people get this after ~20 days or am I being excessive?
  2. Is this expected? Was the limit chosen with the expectation that it'd run out 3 weeks in, or was it intended to last the whole month?
  3. Is there a way to get 30 days' worth?
  4. Is there some way to keep track of usage?
  5. Is this limit likely to be increased or decreased? This month I got the error 12 days in; was the limit reduced?

When I regained access at the beginning of this month something had changed. Context retention seemed much worse. When I replied to Q's questions I'd very often get 'I apologize, but your request seems to be outside my domain of expertise'. I resorted to copying out the whole question and modifying it (e.g. 'Would you like to...' => 'Yes, I would like to...'). I'm wondering if all this extra typing is part of why I hit the limit earlier?

Adrian Stephens

@adrianstephens adrianstephens added the guidance General information and guidance, answers to FAQs, or recommended best practices/resources. label Dec 9, 2024
@justinmk3
Copy link
Contributor

To get a personalized answer on this, I recommend sharing some request-ids with customer support, so they can inspect the logs for the requests and gives a more specific answer.

@adrianstephens
Copy link
Author

I can certainly add request-ids for the 'Maximum com.amazon.aws.codewhisperer.streaming.GenerateAssistantResponse reached for this month' errors. Here's one I just generated:

Request ID: 1886318b-5279-4a3b-875d-45fcd1047da9

Though I suppose I assumed in this case the title says it all.

I'll make a point of noting request-ids for the context-losing responses once I regain access in January, but it's hard to know when exactly it's acting outside of expected behavior.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
amazon-q codewhisperer guidance General information and guidance, answers to FAQs, or recommended best practices/resources.
Projects
None yet
Development

No branches or pull requests

3 participants