The brace-bounded grep truncated at the first nested "}" in the usage
object, so the token segment silently rendered empty. Parse each
transcript JSONL line as JSON instead, summing input + cache_read +
cache_creation to match /context's window-occupancy figure.
Show it as "X.Xk/<limit> tokens (Y%)" with the limit auto-sized to the
model's context window (1m vs 200k), and color the segment red once
context reaches 200k.
Keysat