config: stop the churn — hold for big moves, wide TP/SL, low leverage

Live decomposition of the losing streak: 23% win rate with avg win +$1.23 /
avg loss -$1.04 on ~0.3-0.5% price moves, where the ~0.14% round-trip fee ate
30-50% of every tiny winner. Death by small-move grinding. The AI was closing
positions on ±0.5% noise after the 60m min-hold, capping winners at ~0.86%.

Redesign to 'few big positions, held for big moves':
- Throttle: min hold 60m->4h, noise-close window 90m->8h, reentry 30m->3h,
  opens/hour 30->3, opens/cycle 6->2. Noise band widened -1%..+2% -> -4%..+6%
  so small moves can no longer trigger a close.
- Exits: stop bypass -2.5% -> -5%, take-profit bypass +5% -> +12% (wide,
  asymmetric — let winners run, cut losers only on a real move).
- Leverage 20x -> 5x: a -5% stop at 20x is instant liquidation; at 5x it is
  -25% of margin, survivable. 2 positions x 2.5x = 5x total (full margin,
  ~20% cushion) instead of 4x5x=20x.
- Prompt now instructs the AI to set wide stops (~-5%) and distant targets
  (~+10-12%), hold multi-hour, and never scalp 0.5% moves.

Live strategy updated (maxPos=2, lev=5, ratio=2.5).

kernel/engine_prompt_test.go

@@ -29,8 +29,8 @@ func TestBuildSystemPromptUsesVergexClaw402Prompt(t *testing.T) {
 	if !strings.Contains(prompt, "Direction must be data-driven") {
 		t.Fatalf("prompt should explain that direction is data-driven, not long-only:\n%s", prompt)
 	}
-	if !strings.Contains(prompt, "every open position must use exactly 20x") {
-		t.Fatalf("prompt should force 20x leverage for Claw402 opens:\n%s", prompt)
+	if !strings.Contains(prompt, "every open position must use exactly 5x") {
+		t.Fatalf("prompt should force 5x leverage for Claw402 opens:\n%s", prompt)
 	}
 	if !strings.Contains(prompt, "use the full max notional per position") {
 		t.Fatalf("prompt should force full-size Claw402 opens:\n%s", prompt)