support prompt caching token tracking in langchain #1250
Conversation
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
Extract cache_read and cache_creation from LangChain's nested input_token_details object and map them to Braintrust's standard metric names (prompt_cached_tokens, prompt_cache_creation_tokens). This enables accurate cache token tracking in the UI and correct cost calculations for cached prompts. Fixes Pylon #10400 Co-Authored-By: Claude Opus 4.5 <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
cache_readandcache_creationfrom LangChain's nestedinput_token_detailsobjectprompt_cached_tokens,prompt_cache_creation_tokens)Problem
The LangChain callback handler only extracts top-level fields from
usage_metadata(input_tokens, output_tokens, total_tokens) but not the nestedinput_token_detailscontaining cache metrics. This causes: