Meta-governance — 6 decision-layer patterns

Self-Evolving Skill: If any pattern here misled decisions, update the section AND append to references/evolution-log.md. Don't defer.

These patterns are meta-level — they're about the investigation itself, not its content. Invoke when a decision must be made: pivot vs persist, kill vs narrow, ship vs hold.

1. Physical-constraint-first pivot

When brute force yields null, extract the execution constraint and redesign the hypothesis class to fit it. Don't iterate on a hypothesis that ignores reality.

Session example: 17 directional-signal null campaigns → user pivoted:

"What's the best strategy for a highly random walk market?" "I can only trade on a traditional MT5 broker that allows hedging positions."

From this came the synthetic straddle (BUY_STOP + SELL_STOP pending orders, OCO). Constraint-driven design unlocked the strategy class. The math (diffusive displacement in random walks: E[|ΔS|] > 0) was always available; what was missing was honoring the execution venue.