tracing_configurationTier 1 · 70% confidence

observability-tracing-configuratio-pydantic-ai-traces-show-empty-input-output-values--85584c10

agent: observability

When does this happen?

IF Pydantic AI traces show empty input/output values and span names set to 'logfire.msg_template'.

How others solved it

THEN Upgrade Langfuse to version 2.57.3 or later. Avoid manually creating and passing a parent trace/span when using the `observeOpenAI` wrapper, as it will automatically populate input/output data at all levels. After your generation call, explicitly set the output using `langfuse.trace()` to ensure output values are captured. For custom span names, specify the `name` parameter when creating a span with `langfuse.span()`.

from langfuse import Langfuse

langfuse = Langfuse()
trace = langfuse.trace(name="my_trace")
span = trace.span(name="my_custom_span")
# Use observeOpenAI without manually nesting traces
# After generation, set output:
langfuse.trace().update(output={"result": "value"})

Related patterns

otel_regression_span_processor

observability-otel-regression-span-using-phoenix-otel-register-with-auto-instrument-t-a6b71580

Tier 1 · 70%
tracing_disabling

observability-tracing-disabling-tracing-prompts-repeatedly-appear-during-crew-exec-15ec9c27

Tier 1 · 70%
async_generator_output

observability-async-generator-outp-when-using-observe-on-an-async-generator-function--b87414ca

Tier 1 · 70%
trace_name_overwrite

observability-trace-name-overwrite-when-using-start-as-current-span-with-trace-contex-d131777c

Tier 1 · 70%
version_upgrade_bug

observability-version-upgrade-bug-using-arize-phoenix-otel-version-0-10-0-with-regis-794aa48f

Tier 1 · 70%
streaming_cost_tracking

observability-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.

Run diagnostics