pub fn system_mutation_decision(
prefix_before: u64,
system_before: &Value,
system_after: &Value,
reuse: u32,
cost: &ModelCost,
) -> MutationDecisionExpand description
Priced gate for compressing the system prompt while the client caches a
message prefix (#1912). The system block sits in front of every cached
message, so rewriting it busts the whole prefix: the bust is priced on
prefix_before (system + cached messages, see prefix_tokens) and the
saving on the measured shrink of the system block alone.