Langfuse showed $0.00 cost on every trace even after tracing was wired up:
provider.bedrock_converse.* spans carried only latency, no content or usage.
Converse's own response already includes token usage -- it just wasn't being
read. Captured on the adapter (last_usage, no interface change) and attached
to the span using Langfuse's own OTel attribute convention
(langfuse.observation.*), which its docs say takes precedence over generic
GenAI attributes. Verified live: a fresh trace now shows real prompt/completion
tokens and Langfuse computes real cost once given the model's actual per-token
price.
Weight-based dosing and multi-drug comparison both measured live and
confirmed absent. Fixtures carry the exact query, measured behavior,
and code pointer so the gap can be re-checked later instead of taken
on faith.
VuQuangBao