From a3afbb96cf85d55dac242489520db5e290730031 Mon Sep 17 00:00:00 2001 From: dtoro Date: Wed, 15 Jul 2026 14:05:33 +0200 Subject: [PATCH] fix(eval): raise iteration-followup run cap to 25 The agent legitimately runs 20+ diagnostic commands for a config_mutation task (reset service, re-run backup, verify, check logs). Cap of 8 was too strict. --- evals/iteration-followup.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/evals/iteration-followup.yaml b/evals/iteration-followup.yaml index 8a989ad..954e42d 100644 --- a/evals/iteration-followup.yaml +++ b/evals/iteration-followup.yaml @@ -15,4 +15,4 @@ - kind: proposes_plan - kind: writes_back - kind: max_run_calls - value: 8 + value: 25