Add research money costs, longer research times, era-scaled talent costs, and persona strategy

Research now costs money (drained per-tick) with ~2.5-3.5x longer durations by category.
Early-game talent budget costs reduced via era multiplier (startup 0.2x → bigtech 1.0x).
New seed-driven PersonaStrategy with 8 axes of variation for meaningful multi-run testing.
CI multi-run switched from greedy to persona strategy.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

packages/game-engine/src/systems/economySystem.ts

@@ -1,5 +1,6 @@
 import type { GameState, EconomyState, InfrastructureState } from '@ai-tycoon/shared';
 import { FINANCIAL_SNAPSHOT_INTERVAL, MAX_FINANCIAL_HISTORY, REGULATION_COMPLIANCE_PER_CAPABILITY } from '@ai-tycoon/shared';
+import { TECH_TREE } from '../data/techTree';
 import type { MarketTickResult } from './marketSystem';
 
 export function processEconomy(
@@ -27,7 +28,16 @@ export function processEconomy(
   const complianceCost = bestCapability > 30 ? bestCapability * REGULATION_COMPLIANCE_PER_CAPABILITY * (1 + eraIdx * 0.5) / 100 : 0;
 
   const devRelExpenses = state.market.developerEcosystem.devRelSpending;
-  const expenses = infraExpenses + talentExpenses + dataExpenses + complianceCost + devRelExpenses + extraCosts;
+
+  let researchExpenses = 0;
+  if (state.research.activeResearch) {
+    const node = TECH_TREE.find(n => n.id === state.research.activeResearch!.researchId);
+    if (node) {
+      researchExpenses = node.cost.money / node.cost.ticks;
+    }
+  }
+
+  const expenses = infraExpenses + talentExpenses + dataExpenses + complianceCost + devRelExpenses + researchExpenses + extraCosts;
 
   const money = state.economy.money + revenue - expenses;