feat(langchain): Support cache/reasoning token metrics based on Langchain UsageMetadata#6840
Open
flippingbitss wants to merge 1 commit into
Conversation
…hain UsageMetadata Cache read/Cache write tokens and output reasoning tokens weren't being picked up by Langchain integration. We now include those and normalize the usages to Langchain's provider-agnostic UsageMetadata shape. Fixes getsentryGH-6799 Fixes PY-2606
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Cache read/Cache write tokens and output reasoning tokens weren't being picked up by the Langchain integration.
scripts/generate-test-files.shto update Langchain version as the olderlatestversion wasn't returningcache_writemetric.Description
As described by my initial approach here, this PR adds a few new token usage metrics
cache_read/cache_creation/reasoning/audioand populates the following additional span tags.gen_ai.usage.input_tokens.cachedgen_ai.usage.input_tokens.cache_writegen_ai.usage.output_tokens.reasoningTesting
Add new asserts in Langchain v1+ only tests (
test_langchain_create_agent,test_tool_execution_span) as suggested by @alexander-alderman-webbRan unit tests with
TESTPATH=tests/integrations/langchain/test_langchain.py uv run tox -e <ENV>for following envs:py3.14-langchain-base-v0.1.20py3.14-langchain-base-latestIssues
Fixes #6799
Fixes PY-2606
Related
OTel's Langchain Integration's set_chat_response_usage impl
Test Evidence
py3.14-langchain-base-v0.1.20py3.14-langchain-base-latest