fix(eval): preserve plan generations across iterations

proposePlan: mark pending steps as 'replaced' instead of DELETE, so the
generation counter (MAX+1) sees prior generations. Without this, a first
plan that was proposed but never executed would be wiped, resetting the
counter — a follow-up's plan would look like generation 1 instead of 2.

plan-always-readonly: raise max_run_calls from 3 to 6 (agent inspects
thoroughly).

evals/plan-always-readonly.yaml

@@ -11,4 +11,4 @@
       value: run
     - kind: writes_back
     - kind: max_run_calls
-      value: 3
+      value: 6