mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-13 03:59:12 +00:00
c5ac1845b0
* fix(langfuse): log token usage for /v1/responses calls ResponseAPIUsage exposes input_tokens/output_tokens, so the Langfuse generation logger read prompt_tokens/completion_tokens as 0 while cost was still correct. Normalize the usage with ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage before extracting usage_details. Resolves LIT-8238 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(langfuse): adapt responses-api usage regression test to langfuse v4 spans The v4 migration exports usage_details as an OTEL span attribute via an in-memory exporter instead of a mocked generation() call. Assert on the exported span's langfuse.observation.usage_details with the same token counts. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(langfuse): log token usage for streamed /v1/responses calls An assembled /v1/responses stream reaches the logger with its usage stored as a plain dict of chat fields, which the attribute reads saw as zero. Route both ResponseAPIUsage and that dict through one normalizer. * fix(langfuse): keep generations whose usage dict fails validation; cover streaming in the e2e A usage dict whose token counts are not integers falls back to the raw object, so the generation is still logged with zero usage instead of being dropped. The live e2e now runs streamed and non-streamed /v1/responses. * ci: re-run the e2e gate * test(langfuse): run the real prompt helper and label the responses usage e2e cases Drop the _add_prompt_to_generation_params pass-through patch from the Responses usage unit tests so the real helper runs with the empty metadata they already pass. Declare a Subject on both e2e parametrizations (observability, /v1/responses, openai, stream and nonstream). --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| conftest.py | ||
| datadog_reader.py | ||
| gcs_reader.py | ||
| logging_client.py | ||
| s3_reader.py | ||
| test_datadog_log_e2e.py | ||
| test_gcs_log_e2e.py | ||
| test_langsmith_batch_serialization_e2e.py | ||
| test_otel_trace_e2e.py | ||
| test_otel_v2_langfuse_generation_output_e2e.py | ||
| test_prometheus_cardinality_e2e.py | ||
| test_prometheus_queue_time_e2e.py | ||
| test_responses_langfuse_usage_e2e.py | ||
| test_s3_log_e2e.py | ||
| test_team_langfuse_callback_e2e.py | ||
| test_weave_log_e2e.py | ||
| weave_reader.py | ||