dtoro a9b3f844b2 fix(eval): raise iteration-followup run cap to 40 (maxIterations) ...

The agent's run count varies (21-30+) for a real config_mutation task
involving diagnostics. 40 is the natural upper bound (maxIterations).

2026-07-15 14:16:46 +02:00

..

golden.yaml

chore(eval): consolidate evals into single evals/ folder

2026-07-15 09:50:26 +02:00

iteration-followup.yaml

fix(eval): raise iteration-followup run cap to 40 (maxIterations)

2026-07-15 14:16:46 +02:00

iteration-readonly.yaml

fix(eval): fix manifests to require live inspection + approval followup

2026-07-15 10:02:46 +02:00

no-plan-no-run.yaml

feat(agent): plan-first gate, iterative follow-ups, reasoning persistence

2026-07-15 09:36:27 +02:00

plan-always-readonly.yaml

fix(eval): preserve plan generations across iterations

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