Skip to main content
Applies to:
  • Plan - Any
  • Deployment - Any

​
Summary

Braintrust maps OTel span attributes to structured fields such as input, output, and metrics. Attribute stripping removes the parsed attributes from metadata to avoid storing duplicate payloads.
  • Braintrust-hosted: this option is enabled. Parsed OTel attributes no longer appear in metadata.
  • Self-hosted: the option is off by default. There is no change to your data until you opt in.
  • Per-span escape hatch: set the braintrust.otel.preserve_attributes attribute to true on any span where you need the raw attributes preserved on metadata for forensics or debugging.
This mapping and stripping behavior applies to trace spans. OTLP log records keep record attributes in metadata without GenAI field mapping, so braintrust.otel.preserve_attributes does not control their storage.

​
What changes for Braintrust-hosted customers

For spans ingested via OTel, attribute keys that Braintrust successfully parses into structured fields are removed from metadata. The data is not lost. It is available on the parsed field (input, output, metrics, scores, expected, tags, span_attributes, or origin). Examples of attributes that are parsed and therefore stripped:
  • Vercel AI SDK: ai.prompt, ai.prompt.messages, ai.prompt.format, ai.response.text
  • GenAI: gen_ai.input.messages, gen_ai.output.messages
  • OpenInference, including LlamaIndex: parsed message, input, output, token usage, and score attributes. See OpenInference mappings.
  • Traceloop, CrewAI, Pydantic AI, LiveKit, and other supported integrations: their parsed attributes are stripped as well.
Unparsed attributes remain in metadata. For OpenInference feedback, this includes names, labels, explanations, and scores that fail validation.

​
Escape hatch: preserve raw attributes per span

If you need the raw OTel attributes on metadata for a specific code path, for example to compare what an upstream library actually emitted against what Braintrust parsed, set the attribute braintrust.otel.preserve_attributes to true on that span. The override is evaluated per-span, so you can scope it to one suspect call without changing the rest of your tracing. Both the boolean true and the string "true" are accepted.
When this attribute is set, Braintrust skips the strip step for that span and writes all raw attributes to metadata exactly as before.

​
Self-hosted: enabling the feature

Self-hosted deployments default to the prior behavior (raw attributes are kept on metadata). To opt in, set STRIP_OTEL_ATTRIBUTES_FROM_METADATA=true on the api-ts service through your deployment configuration. The per-span braintrust.otel.preserve_attributes escape hatch works the same way once the env var is enabled.

​
Verifying the behavior

  1. Send a known OTel span (for example, a Vercel AI SDK call producing ai.prompt) to Braintrust.
  2. Open the resulting log row. The parsed payload should appear in input / output, and the corresponding attribute keys should be absent from metadata.
  3. Re-run the same call after setting the braintrust.otel.preserve_attributes attribute to true on the span. The raw attribute keys should reappear in metadata while still being parsed into input / output.