feat: refactor AlgorithmicEvaluator to stateless, add game engine module and holdem_sim CLI

- Refactor AlgorithmicEvaluator from stateful Arc<Evaluator> wrapper to
  pure stateless evaluator with zero-allocation construction
- Extract shared evaluation logic into pub(crate) methods, eliminating
  ~220 lines of duplicated code from Evaluator
- Add game module: table, hand runner, tournament, bots, config, stats
- Add holdem_sim CLI binary crate for running simulations
- Convert MathEvaluator to thread-safe singleton with Arc<Inner> pattern
- Replace heap-allocated combination generation with const-generics
  stack-based approach in AlgorithmicEvaluator::evaluate_n_card_hand
- Add thiserror 2 dependency for GameError derive
- Update docs: README, ACHIEVEMENTS, ROADMAP

README.md

@@ -282,6 +282,82 @@ Run performance benchmarks:
 cargo test --release hand_eval_integration_test -- --nocapture
 ```
 
+## Simulation Testbed
+
+The `holdem_sim` binary provides a CLI for running poker simulations with configurable bots, game types, and formats. It supports cash games, Sit & Go (SNG) tournaments, and Multi-Table Tournaments (MTT).
+
+### Running Simulations
+
+```bash
+# Run a cash game simulation
+cargo run --bin holdem_sim -- holdem_core/examples/configs/cash_game.toml
+
+# Run with a specific seed for reproducibility
+cargo run --bin holdem_sim -- holdem_core/examples/configs/cash_game.toml --seed 42
+
+# Override the number of hands
+cargo run --bin holdem_sim -- holdem_core/examples/configs/cash_game.toml --hands 5000
+```
+
+### Example Configuration (Cash Game)
+
+```toml
+[game]
+game_type = "Cash"
+num_seats = 6
+small_blind = 10
+big_blind = 20
+ante = 0
+starting_chips = 10000
+num_hands = 1000
+
+[game.bet_limit]
+type = "no_limit"
+min_raise = 20
+
+[[game.bots]]
+bot_type = "call_bot"
+name = "Alice"
+
+[[game.bots]]
+bot_type = "fold_bot"
+name = "Bob"
+
+[[game.bots]]
+bot_type = "random_bot"
+name = "Charlie"
+```
+
+Example configs are available in [`holdem_core/examples/configs/`](holdem_core/examples/configs/):
+
+- [`cash_game.toml`](holdem_core/examples/configs/cash_game.toml) — 6-max NLHE cash game
+- [`sng_tournament.toml`](holdem_core/examples/configs/sng_tournament.toml) — 9-seat Sit & Go
+- [`mtt_tournament.toml`](holdem_core/examples/configs/mtt_tournament.toml) — Multi-table tournament
+
+### Built-in Bots
+
+| Bot | Description |
+|-----|-------------|
+| `call_bot` | Calls every bet, never raises or folds |
+| `fold_bot` | Folds whenever facing a bet, otherwise checks |
+| `raise_bot` | Raises with configurable aggression thresholds |
+| `random_bot` | Takes random legal actions with configurable tendencies |
+
+### Example Output
+
+```
+=== Simulation Results ===
+Hands played: 1000
+
+Player Statistics:
+  Alice (call_bot)
+    Hands: 1000 | VPIP: 100.0% | PFR: 0.0% | Win: $45,230
+  Bob (fold_bot)
+    Hands: 1000 | VPIP: 0.0% | PFR: 0.0% | Win: -$32,100
+  Charlie (random_bot)
+    Hands: 1000 | VPIP: 67.3% | PFR: 22.1% | Win: -$13,130
+```
+
 ## Mathematical Foundation
 
 ### Perfect Hash Algorithm