cc-os/plugins/os-orchestration/eval/results/2026-07-08-ws4-baseline-gri...

7.9 KiB

1# WS4 pre-wording baseline grid (ORCHESTRATION.md v2), 2026-07-08.
2# 8 run-set scenarios x {sonnet x3, fable x2} + 4 counted canaries.
3# 15 grid reps were truncated by an account session limit (final message = limit banner,
4# mechanical criterion independent of verdict); they are listed EXCLUDED below and were
5# replaced by fresh reps (rep numbers r4+/r3+ = replacements).
6# canary reps (counted):
7# EXCLUDED (session-limit truncated, replaced above):