feat: upgrade paper trading to $100k moderate tier

Paper money has no downside — bigger capital exposes more model
behavior: position sizing, diversification, sector exposure,
correlation checks, circuit breakers, reserve pool siphoning,
and risk tier auto-adjustment all become meaningful.

- risk_tier: conservative → moderate (min_confidence 0.55)
- absolute_position_cap: $25 → $10,000
- max_open_positions: 5 → 10
- initial portfolio value: $500 → $100,000
- Updated migration 019, Helm values, and engine default

services/trading/engine.py

@@ -552,10 +552,12 @@ class TradingEngine:
             logger.debug("Could not load circuit breaker state — using inactive")
 
         # Build portfolio state with defaults
+        # Default initial capital for paper trading — overridden by broker sync
+        initial_capital = 100000.0
         self.portfolio_state = PortfolioState(
             reserve_pool=reserve_balance,
-            active_pool=max(0.0, 500.0 - reserve_balance),
-            total_value=500.0,
+            active_pool=max(0.0, initial_capital - reserve_balance),
+            total_value=initial_capital,
         )
 
     async def _decision_loop(self) -> None: