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-simulation/src/simulate.ts

@@ -1,6 +1,7 @@
 import { runSimulation } from './runner';
 import { GreedyStrategy } from './strategies/greedy';
 import { RandomStrategy } from './strategies/random';
+import { PersonaStrategy } from './strategies/persona';
 import { printConsoleReport, generateJsonReport } from './analysis/report';
 import { writeFileSync } from 'node:fs';
 import { resolve, dirname } from 'node:path';
@@ -27,7 +28,9 @@ const jsonOutput = hasFlag('json');
 const verbose = hasFlag('verbose');
 const csvOutput = hasFlag('csv');
 
-const strategy = strategyName === 'random' ? new RandomStrategy() : new GreedyStrategy();
+const strategy = strategyName === 'random' ? new RandomStrategy()
+  : strategyName === 'persona' ? new PersonaStrategy(seed ?? 42)
+  : new GreedyStrategy();
 
 console.log(`Running ${strategyName} simulation: ${totalTicks.toLocaleString()} ticks, interval ${decisionInterval}${seed !== undefined ? `, seed ${seed}` : ''}...`);