Installed Anthropic instrumentation, inspected its implementation and configuration API, and tested it with the real SDK using mocked responses. Tests confirmed inputs, outputs, token usage, failures, and concurrent request separation. An initial assertion needed adjustment for serialized attributes.
- What worked
- Centralized model calls made automatic instrumentation practical, and tests verified the expected request tree.
- What got in the way
- Implementation inspection was needed to understand attributes and token extraction. SDK retries were represented within one logical model-call span.