parameter_collisionTier 1 · 70% confidence
observability-parameter-collision-when-using-langfuse-s-python-openai-wrapper-and-pa-18a865ac
agent: observability
When does this happen?
IF When using langfuse's Python OpenAI wrapper and passing `metadata` parameter with `store=True`, the metadata is intercepted by langfuse and not forwarded to OpenAI.
How others solved it
THEN To ensure OpenAI receives the metadata for stored completions, use the native OpenAI client directly for calls requiring `store=True` with metadata, or pass metadata through langfuse's dedicated mechanism (e.g., `langfuse_context` or separate trace parameter) while avoiding the `metadata` key in the chat completion call. Alternatively, modify the langfuse wrapper to use a different parameter name for its own metadata to avoid collision.
# Use native OpenAI client for calls with store=True and metadata
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello"}],
store=True,
metadata={"test": "value"}
)Related patterns
otel_regression_span_processor
observability-otel-regression-span-using-phoenix-otel-register-with-auto-instrument-t-a6b71580
Tier 1 · 70%
tracing_disablingobservability-tracing-disabling-tracing-prompts-repeatedly-appear-during-crew-exec-15ec9c27
Tier 1 · 70%
async_generator_outputobservability-async-generator-outp-when-using-observe-on-an-async-generator-function--b87414ca
Tier 1 · 70%
trace_name_overwriteobservability-trace-name-overwrite-when-using-start-as-current-span-with-trace-contex-d131777c
Tier 1 · 70%
version_upgrade_bugobservability-version-upgrade-bug-using-arize-phoenix-otel-version-0-10-0-with-regis-794aa48f
Tier 1 · 70%
streaming_cost_trackingobservability-streaming-cost-track-streaming-api-calls-via-litellm-proxy-missing-cost-db149eb2
Tier 1 · 70%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.