Warning: This build has drifted.
The coverage report for this pull request build may be inaccurate because its base commit is no longer the HEAD of its target branch.
This means it includes changes from outside the original pull request, including, potentially, unrelated coverage changes.

    • Learn more: For more information on this, see Tracking coverage changes for pull request builds.
    • Fix now: For a quick fix, rebase this PR at GitHub. Your next report should be accurate.
    • Prevent going forward: To avoid this issue with future PRs, see these Recommended CI Configurations.

Enhance Google provider usage extraction and token handling

- Updated the `extract_usage/2` function in the Google provider to include cached content token handling, improving the accuracy of usage metrics.
- Introduced a new private function, `add_cached_tokens/1`, to manage the addition of cached tokens to the usage data.
- Refactored the `ReqLLM.Step.Usage` module to streamline cached token retrieval and clamping logic, ensuring consistent behavior across different scenarios.
- Added comprehensive tests for cached token scenarios in both the Google provider and usage handling, ensuring robust validation of new functionality.

These changes enhance the overall functionality and reliability of the usage calculation features within the ReqLLM library, providing better support for diverse provider interactions.