The problem
A single LLM call is easy to reason about. You send a prompt, you get tokens back, you log the latency and you move on.
A swarm is not that. Four or five agents run, some in parallel, each with its own model. One of them times out and quietly falls back to a cheaper model. A critic agent reads the output and sends work back for another round. When the whole thing takes 40 seconds instead of 12, or costs three times what you budgeted, you have no idea which agent did it. Your logs are a flat stream of interleaved lines from concurrent tasks, with no parent-child structure and no way to ask "which role burned the tokens".
Traces solve this exactly. The catch is that hand-wiring OpenTelemetry across every role, every provider call and every retry path is boring work that nobody wants to do twice, and if you skip a level the trace tree lies to you.
So I extracted the instrumentation out of DevSwarm (a multi-agent code generator I built for this hackathon) into a standalone MIT library: otel-swarm.
