Topic
Instrument it, learn to query it, then point it at something that thinks.
If you distribute a Claude Code agent to a marketplace, every developer who runs it spends your reasoning budget and yours to answer for. Here is how I wired Claude Code's built-in OpenTelemetry into a Grafana/LGTM stack to watch cost, tokens and tool decisions — per run.
TraceQL has a tiny surface area but a few sharp edges. Here is the mental model — span scopes, the spanset, aggregates, and structural operators — that makes it click and stops the silent zero-result queries.
Wiring OpenTelemetry into Spring Boot 4 — the annotation way and the manual Tracer way — plus the context model that ties them together and the gotchas that cost me time (a silent @WithSpan, http/protobuf vs gRPC, and Docker's 'is a directory').
Posts that touch this subject but live under another topic.
Building agents on the JVM with Embabel · Part 5
I pointed my Embabel agents at a local Grafana LGTM stack and saw nothing. Three configuration gotchas later, every GOAP planning step, LLM call and tool loop shows up as a span in Tempo. Here is the full walkthrough, with screenshots.