fix(litellm): populate cacheWriteInputTokens from cache_creation_input_token not cache_creation_tokens

[dbschmigelski]

Description

We were previously reading from LiteLLM's PromptTokensDetailsWrapper using the cache_creation_tokens property.

Something, either on the Bedrock, Anthropic, or LiteLLM side, appears to not be populating that. Which was breaking the test_cache_read_tokens_multi_turn integration test for writes.

We had thought that this was possibly the result of cache being set earlier, or tests being executed by someone concurrently. But even when we set a uuid, which should be done anyway, the cacheWriteInputTokens were not appearing.

This switches to reading from the documented cache_creation_input_token instead.

Type of Change

Bug fix

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.

[codecov]

Codecov Report

❌ Patch coverage is 50.00000% with 1 line in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/strands/models/litellm.py	50.00%	0 Missing and 1 partial ⚠️

📢 Thoughts on this report? Let us know!