The Auto-mode permission classifier has measured pathologies (profiled 2026-07-28 across 25 AWS benchmark attempts, see dossier/followup-tickets-2026-07-28.md in the anvil-checkpoints branch):
- Inherits the session's reasoning effort (tool_loop.rs ~4452): a trivial allow/deny call at xhigh costs ~7s. Force a low effort for classifier calls.
- prefer_json_object output (~4564) at high effort yields a 1.2x empty-completion retry storm. Use strict json_schema.
- Unavailable maps to Reject (~4208-4223): 19% of decisions denied legitimate tool calls and burned a main-loop turn each. Fail open with a visible notice (or prompt).
- No memoization: repeated edits to the same file re-classify from scratch. Cache on (tool, normalized input).
- Retry-attempt and unavailable-response usage bypass session usage accounting (the permission_classifier trace record added in 3d3d492 captures true sums; accounting should too).
Benchmark runs now bypass the classifier entirely via BROKK_ACP_PERMISSION_MODE; these items are for interactive Auto-mode users, who still pay all of the above.
The Auto-mode permission classifier has measured pathologies (profiled 2026-07-28 across 25 AWS benchmark attempts, see dossier/followup-tickets-2026-07-28.md in the anvil-checkpoints branch):
Benchmark runs now bypass the classifier entirely via BROKK_ACP_PERMISSION_MODE; these items are for interactive Auto-mode users, who still pay all of the above.