Feature hasn't been suggested before
Describe the enhancement you want to request
The TUI status bar currently shows context usage (e.g. "1.2K (12%)" ) and cost in the prompt footer, subagent footer, and sidebar context plugin. It would be useful to also show the average output tokens per second (TPS) for the last completed assistant message, placed before the context info — e.g. "42 t/s · 1.2K (12%) · $0.05".
TPS is calculated from existing data already available on AssistantMessage: tokens.output / ((time.completed - time.created) / 1000). It only appears after a response completes (since time.completed is required), giving a rough throughput metric for the last turn.
Feature hasn't been suggested before
Describe the enhancement you want to request
The TUI status bar currently shows context usage (e.g. "1.2K (12%)" ) and cost in the prompt footer, subagent footer, and sidebar context plugin. It would be useful to also show the average output tokens per second (TPS) for the last completed assistant message, placed before the context info — e.g. "42 t/s · 1.2K (12%) · $0.05".
TPS is calculated from existing data already available on
AssistantMessage:tokens.output / ((time.completed - time.created) / 1000). It only appears after a response completes (sincetime.completedis required), giving a rough throughput metric for the last turn.