mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-09 03:18:44 +00:00
OpenInferenceMapper spelled every captured prompt and response message out as two indexed attributes with no bound. A few dozen turns overran the OTel SDK's 128-attribute span limit, which evicts oldest first, so the gen_ai.* model, provider, usage, cost and finish reason written before it were what got dropped. Both directions now share one MAX_MESSAGE_ATTRS_PER_SPAN ceiling, the response keeps at least half of it, and input.value / output.value still carry the complete conversation Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| test_db_endpoint.py | ||
| test_langfuse_logger.py | ||
| test_otel_v2_baggage.py | ||
| test_otel_v2_components.py | ||
| test_otel_v2_config_baggage_parenting_guardrails.py | ||
| test_otel_v2_destinations.py | ||
| test_otel_v2_dynamic.py | ||
| test_otel_v2_emitter.py | ||
| test_otel_v2_logger.py | ||
| test_otel_v2_metrics.py | ||
| test_otel_v2_mount.py | ||
| test_otel_v2_multibackend.py | ||
| test_otel_v2_presets.py | ||
| test_otel_v2_sources_of_truth.py | ||
| test_otel_v2_vendor_mappers.py | ||
| test_runtime.py | ||