[viliamgonda]

What does this PR do?

Fixes langfuse/langfuse#19452

In CallbackHandler._parse_usage_model, Anthropic prompt caching reports cache-write breakdown under cache_creation (ephemeral_5m_input_tokens, ephemeral_1h_input_tokens) alongside the aggregate cache_creation_input_tokens.

Previously, _parse_usage_model flattened the nested dict into cache_creation_ephemeral_* and also set/kept cache_creation_input_tokens. Because both the aggregate count and TTL tiers describe the same tokens, downstream bucket summation counted prompt cache creation twice.

This change:

1. Maps Anthropic's TTL breakdown tiers to canonical Langfuse keys (input_cache_creation_5m, input_cache_creation_1h), matching server model pricing.
2. Deducts attributed TTL tokens from aggregate counters (cache_creation_input_tokens, input_cache_creation), retaining only unattributed remainder tokens.
3. Adds regression tests verifying proper de-duplication and remainder handling.

Type of change

• Bug fix
• New feature
• Breaking change
• Refactor
• Documentation update
• Tooling, CI, or repo maintenance

Verification

List the main commands you ran:

uv run --frozen pytest tests/unit/test_parse_usage_model.py
LANGFUSE_PUBLIC_KEY=pk-lf-test LANGFUSE_SECRET_KEY=sk-lf-test uv run --frozen pytest -n auto --dist worksteal tests/unit
uv run --frozen ruff check .
uv run --frozen ruff format --check .
uv run --frozen mypy langfuse --no-error-summary

Checklist

• I self-reviewed the diff using code_review.md.
• I added or updated tests for behavior changes.
• I updated docs, examples, or .env.template if needed.
• I did not hand-edit generated files; if generated files changed, I used the upstream regeneration path.
• I did not commit secrets or credentials.

Confidence Score: 5/5

The PR appears safe to merge.

Summary

Fixes double counting of Anthropic cache creation tokens in _parse_usage_model.

• LangChain usage parsing records Anthropic cache tiers without repeating their counts.

No actionable issues were found. Tests were reviewed but not run.

_{Reviews (1) · Last reviewed commit: "fix(langchain): avoid double counting An..." · Reviewed by Greptile}

[claude]

Claude Code Review

This pull request is from a fork — automated review is disabled. A repository maintainer can comment @claude review to run a one-time review.

[CLAassistant]

All committers have signed the CLA.