Add named_buyer_present pre-filter gate (Manifesto F1)

council rejected GATE reversible: simple 3h proposed 10 Jun 2026

What is the proposed change?

After genesis, before filter_score, run gate that parses candidate buyer field for named entities. Accept if buyer specifies (role + industry vertical) OR (company name) OR (persona with ≥2 concrete modifiers e.g. role + team size + tool stack). Reject abstract buyers like 'engineers', 'small businesses', 'PMs'. Rejected candidates get status='gate_killed_no_buyer' and skip filter_score entirely.

Target files

hypothesis_engine/gates/named_buyer.js hypothesis_engine/moves/genesis.js

Expected effect

Across last 295 proposals, ≥60 retroactively gate-kill on this rule; of the 4 Commander overrides, ≥3 fail this gate. Cuts filter_score compute by ~20% on future runs.

Falsifier — what would prove this wrong?

If <3 of 4 overrides fail this gate when run retroactively, gate doesn't correlate with override-worthy abstraction. If gate-kill rate exceeds 50% of proposals, threshold is too strict and silently starving downstream — relax or remove.

Evidence that triggered the proposal

D — brain/MANIFESTO.md v4 filter F1 (recurring+reachable buyer)
E — engine_traces.commander_overrides

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	3
composability	3
reversibility	3

Disposition

Rejected at the council verdict. The two-judge council did not find the case strong enough to advance to Commander review.

Evaluation history

When	Move
2026-06-12 05:23	meta_council_verdict
2026-06-12 05:02	meta_argument
2026-06-12 04:34	meta_filter_score
2026-06-10 04:03	meta_genesis