Add cross-judge fatal-objection consensus short-circuit gate

filter rejected GATE reversible: simple 4h proposed 30 May 2026

What is the proposed change?

In argument.js, after both judges (Codex + Gemini) return their objections, check if both independently flagged the same candidate with a fatal-tier objection (severity == 'fatal' and overlapping objection_class). If consensus exists, write status='council_rejected' with kill_reason='fatal_objection_both_confirm_pre_council' and skip the council_verdict move entirely, saving its $0.10/cycle. council_verdict.js becomes a no-op for that candidate. Preserve the move record for audit so Commander can inspect why council was skipped.

Target files

hypothesis_engine/moves/argument.js hypothesis_engine/moves/council_verdict.js

Expected effect

The 2 fatal_objection_both_confirm kills in the current trace would have skipped council, saving $0.20 across those cycles. Council_verdict move cost should drop ~15-25% over a 30-day window without changing the final kept-vs-killed distribution.

Falsifier — what would prove this wrong?

Compare council_verdict outcomes on the 2 historical fatal-both-confirm candidates: if council would have flipped either to kept (i.e. council can override fatal objections), the gate is too aggressive and must be downgraded to a 'fast-track' rather than a skip.

Evidence that triggered the proposal

E — kill_reason_distribution: 2× fatal_objection_both_confirm
E — move_cost: meta_council_verdict $0.10/cycle
D — brain/S176_META_ENGINE_VALIDATION.md (cross-vendor judge agreement principle)

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

Axis	Score
specificity	3
falsifier	3
solo feasible	3
blast radius	1
composability	3
reversibility	3

Disposition

Rejected by filter_score. The proposal did not meet the bar for specificity, falsifiability, or solo-feasibility.

Evaluation history

When	Move
2026-05-30 04:05	meta_filter_score
2026-05-30 04:03	meta_genesis