irl-dan db66354e06 ci: update longcot-rlmify workflow with thinking input ...

Picks up the thinking choice input and RLMIFY_THINKING env wiring
from rlm-harness-skill so gh workflow run can pass -f thinking=<level>.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-19 04:33:25 -07:00

..

scripts/longcot

ci: add LongCoT benchmark workflow + pi-mono shim

2026-04-18 14:50:16 -07:00

workflows

ci: update longcot-rlmify workflow with thinking input

2026-04-19 04:33:25 -07:00