Skip to content

feat: add cached token metrics support for Amazon Bedrock #641

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

poshinchen
Copy link
Contributor

Description

Add cached token metrics support for Amazon Bedrock to track cache read/write input tokens.

Taking over the pr with tests and some refinements

Related Issues

#529

Documentation PR

N/A

Type of Change

Update

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

  • I ran hatch run prepare

Checklist

  • I have read the CONTRIBUTING document
  • I have added any necessary tests that prove my fix is effective or my feature works
  • I have updated the documentation accordingly
  • I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
  • My changes generate no new warnings
  • Any dependent changes have been merged and published

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

@poshinchen poshinchen requested a review from a team August 8, 2025 19:01
@poshinchen poshinchen marked this pull request as ready for review August 8, 2025 19:01
@poshinchen poshinchen self-assigned this Aug 8, 2025
Copy link
Member

@Unshure Unshure left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@dbschmigelski
Copy link
Member

In the referenced PR we have " Maintainers are allowed to edit this pull request." I think we should try to make edits there for one to keep everything in one place, but also to avoid community members feeling that they aren't given credit or the opportunity to contribute themselves.

At the very least lets make sure oaltagar-aws gets some credit as a co-author

outputTokens: Number of tokens that the model generated for the request.
totalTokens: Total number of tokens (input + output).
cacheReadInputTokens: Number of tokens read from cache (optional).
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you explain your thinking of making this optional vs it just staying at 0 if cache isn't being used?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants