support prompt caching token tracking in langchain#1250
Merged
Olmo Maldonado (ibolmo) merged 13 commits intomainfrom Jan 24, 2026
Merged
support prompt caching token tracking in langchain#1250Olmo Maldonado (ibolmo) merged 13 commits intomainfrom
Olmo Maldonado (ibolmo) merged 13 commits intomainfrom
Conversation
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 <noreply@anthropic.com>
Contributor
Author
|
Added a focused unit test for cache-token extraction in langchain-py.
Commit: 08205f4 |
Contributor
Caitlin Pinn (cpinn)
left a comment
Caitlin Pinn (cpinn)
left a comment
There was a problem hiding this comment.
This change looks great to me with the added test, was what I was going to take a look into today. Usually for changes like this we also record and save a cassette to have the tests run the tests a little faster.
cc: Olmo Maldonado (@ibolmo) should we add a cassette to the change or should we merge as is and add it later?
… fix/langchain-cache-tokens
Olmo Maldonado (ibolmo)
force-pushed
the
fix/langchain-cache-tokens
branch
from
67e1107 to
8542310
Compare
Olmo Maldonado (ibolmo)
force-pushed
the
fix/langchain-cache-tokens
branch
from
8542310 to
546383a
Compare
|
|
||
| assert "prompt_cache_creation_tokens" in first_metrics | ||
| assert first_metrics["prompt_cache_creation_tokens"] > 0 | ||
| if "prompt_cached_tokens" in first_metrics: |
Contributor
There was a problem hiding this comment.
nit. do we want this if statement in the test because then the assertion may or may not run?
Caitlin Pinn (cpinn)
approved these changes
Jan 22, 2026
Collaborator
|
braintrust-langchain 0.2.1 and @braintrust/langchain-js 0.2.3 are both out. |
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
4 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.
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: