🧪TDD Challenge·advanced·⏱️ 30–40m·⭐ 200 XP
M-076Build an OpenTelemetry LLM Exporter
Description
Nebula Corp wants vendor-neutral observability. Build a lightweight OpenTelemetry-compatible span exporter for LLM calls. The exporter should capture LLM-specific semantic conventions (gen_ai.* attributes), batch spans for efficient export, and format them as OTLP-compatible JSON. This lets them send traces to any backend — Langfuse, Jaeger, Grafana Tempo — without changing application code.
Test Cases (3)
Creates valid span
Should create span with trace ID
Input:createLLMSpan('test', {'gen_ai.system': 'openai'})
Expected:CONTAINS:traceId
Ends span with OK
Should end span with OK status
Input:endSpan(createLLMSpan('test'), {})
Expected:CONTAINS:OK
Ends span with error
Should set ERROR status when error present
Input:endSpan(createLLMSpan('err'), {error: 'timeout'})
Expected:CONTAINS:ERROR
Related Lessons
Click Run / Check to validate your solution