Files
portal/tools
Дмитрий da6263c235 fix(enforce): hole 1 — remove self-override via assistant text
Brain-retro #5 candidate C, hole 1: enforce-classifier-match.mjs allowed
the agent to bypass the rule by writing 'override: <reason>' in its own
response (self-override = no enforcement). The user-vocabulary override
phrases in enforce-override-vocab.json remain the only legitimate path.

Added regression test asserting block on assistantText override when user
prompt has no override phrase.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 11:07:03 +03:00
..