fix(langchain): avoid double-counting cached input tokens#445
Merged
Abhijeet Prasad (AbhiPrasad) merged 1 commit intoMay 20, 2026
Merged
Conversation
Only fold cache tokens into prompt and total metrics when LangChain reports cache tokens separately from input tokens. This preserves Anthropic-style cache normalization while avoiding double-counting for OpenAI-style responses where cached tokens are already included in input_tokens. Adds regression coverage for OpenAI cached token metrics.
Luca Forstner (lforst)
approved these changes
May 20, 2026
Abhijeet Prasad (AbhiPrasad)
deleted the
abhi-fix-bt-5310-langchain-cache-tokens
branch
Abhijeet Prasad (AbhiPrasad)
added a commit
that referenced
this pull request
May 20, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Only fold cache tokens into prompt and total metrics when LangChain reports cache tokens separately from input tokens. This preserves Anthropic-style cache normalization while avoiding double-counting for OpenAI-style responses where cached tokens are already included in input_tokens.
Adds regression coverage for OpenAI cached token metrics.
resolves https://linear.app/braintrustdata/issue/BT-5310/langchain-callback-double-counts-cache-tokens-for-openai-after-pr-411