Skip to content

support prompt caching token tracking in langchain #1250

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
colinbennettbrain wants to merge 1 commit into
base: main
Choose a base branch
from
+12 −0
Open

support prompt caching token tracking in langchain #1250

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions integrations/langchain-py/src/braintrust_langchain/callbacks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -633,6 +633,18 @@ def _get_metrics_from_response(response: LLMResult):
)
)

# Extract cache tokens from nested input_token_details (LangChain format)
# Maps to Braintrust's standard cache token metric names
input_token_details = usage_metadata.get("input_token_details")
if input_token_details and isinstance(input_token_details, dict):
cache_read = input_token_details.get("cache_read")
cache_creation = input_token_details.get("cache_creation")

if cache_read is not None:
metrics["prompt_cached_tokens"] = cache_read
if cache_creation is not None:
metrics["prompt_cache_creation_tokens"] = cache_creation

if not metrics or not any(metrics.values()):
llm_output: dict[str, Any] = response.llm_output or {}
metrics = llm_output.get("token_usage") or llm_output.get("estimatedTokens") or {}
Expand Down
Loading