Cost attribution gets even worse when you factor in the bad decisions. Retries, abandoned tool calls, and cascading failures that still hit your bill but never show up in traces.
I’m building an OTel-based SDK that wraps the billable edges (entrypoint, LLM/tool clients, async publish/consume) and emits both traces for debugging and a lightweight event ledger for run/attempt lifecycle and call boundaries. I define the workflow + possible outcomes up front, then attribute all runs and attempts to the final outcome event to get the cost per outcome
deborahjacob|1 month ago