dtoro 3d7fa99560 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).

2026-07-15 10:48:21 +02:00

630 B

Raw Blame History

View Raw