Problem Statement
Hi, we have instrumentation for Anthropic.SDK configured according to https://docs.sentry.io/platforms/dotnet/tracing/instrumentation/ai-agents-module/
It works nicely! One thing we’re missing currently though, are the thinking messages. Only the assistant messages seem to get captured in the output. Without the thinking messages, when an LLM fails to do something because it took a wrong approach, we don’t know why it took the route it took. So having the thinking messages captured and displayed in the UI would be really useful in such cases.
Solution Brainstorm
No response
Problem Statement
Hi, we have instrumentation for Anthropic.SDK configured according to https://docs.sentry.io/platforms/dotnet/tracing/instrumentation/ai-agents-module/
It works nicely! One thing we’re missing currently though, are the thinking messages. Only the assistant messages seem to get captured in the output. Without the thinking messages, when an LLM fails to do something because it took a wrong approach, we don’t know why it took the route it took. So having the thinking messages captured and displayed in the UI would be really useful in such cases.
Solution Brainstorm
No response