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>

.gitea/workflows/balance-check.yml

@@ -54,7 +54,7 @@ jobs:
         run: pnpm install --frozen-lockfile
 
       - name: Run multi-simulation (5 runs)
-        run: pnpm --filter @ai-tycoon/game-simulation multirun -- --runs 5 --parallel 2 --strategy greedy --ticks 28800 --no-timeseries
+        run: pnpm --filter @ai-tycoon/game-simulation multirun -- --runs 5 --parallel 2 --strategy persona --ticks 28800 --no-timeseries
 
       - name: Interpret results
         if: always()