Cost estimates now pick the cache lifetime that actually applied, so numbers match reality.
What's wrong with this entry?
Cost estimation now chooses a one-hour cache lifetime when a longer-TTL override is configured or the request comes from the interactive session's main thread, and five minutes otherwise, so estimates match the cache tier actually used.
return nM("repl_main_thread") ? "1h" : "5m";
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.239
Cost is computed as a multiplied token subtotal plus web search
Both mention cost tracking
-
v2.1.246
Resuming a session restores its accumulated cost
Both mention cost tracking
-
v2.1.246
Cost is stored per session rather than only for the most recent one
Both mention cost tracking