refactor(lotto): Phase 1 코드리뷰 반영 (로컬 RNG·write-once·가드·테스트 보강)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lotto/app/backtest.py

@@ -1,10 +1,10 @@
 """로또 자가학습 백테스트 — 순수 연산 (FastAPI 의존성 0, Windows 이전 대비)."""
+import logging
 import random
 from typing import Any, Dict, List, Optional, Tuple
 
 from .analyzer import build_analysis_cache, build_number_weights, score_combination
 from .utils import weighted_sample_6
-from .weight_evolver import count_match
 
 
 def grade_tickets(tickets: List[List[int]], winning6: List[int], bonus: int) -> Dict[str, Any]:
@@ -45,8 +45,7 @@ def prize_counts(hist: Dict[str, Any]) -> Dict[str, int]:
 def generate_pool(cache, number_weights, n: int = 20000,
                   seed: Optional[int] = None) -> List[List[int]]:
     """가중 샘플링으로 distinct 후보 풀 생성."""
-    if seed is not None:
-        random.seed(seed)
+    rng = random.Random(seed)
     seen, pool = set(), []
     attempts, cap = 0, n * 4
     while len(pool) < n and attempts < cap:
@@ -56,22 +55,29 @@ def generate_pool(cache, number_weights, n: int = 20000,
             continue
         seen.add(nums)
         pool.append(list(nums))
+    if len(pool) < n:
+        logging.getLogger(__name__).warning(
+            "generate_pool: requested %d, got %d", n, len(pool)
+        )
     return pool
 
 
 def purchase_tickets(pool, cache, W: List[float], k: int) -> List[List[int]]:
     """풀을 score_combination(·, W)로 랭킹 → 상위 k장 distinct."""
+    if k > len(pool):
+        raise ValueError(f"k={k} exceeds pool size {len(pool)}")
     ranked = sorted(pool, key=lambda t: -score_combination(t, cache, W)["score_total"])
     return ranked[:k]
 
 
 def random_null_tickets(k: int, seed: Optional[int] = None) -> List[List[int]]:
     """무작위 distinct 티켓 k장 (null-model 대조군)."""
-    if seed is not None:
-        random.seed(seed)
+    rng = random.Random(seed)
     seen, out = set(), []
-    while len(out) < k:
-        nums = tuple(sorted(random.sample(range(1, 46), 6)))
+    guard = 0
+    while len(out) < k and guard < k * 200:
+        guard += 1
+        nums = tuple(sorted(rng.sample(range(1, 46), 6)))
         if nums in seen:
             continue
         seen.add(nums)
@@ -82,18 +88,17 @@ def random_null_tickets(k: int, seed: Optional[int] = None) -> List[List[int]]:
 def coverage_tickets(k: int, seed: Optional[int] = None) -> List[List[int]]:
     """greedy 커버리지 — 아직 덜 쓰인 번호를 우선 배치해 번호를 넓게 분산.
     (휠링/보장설계는 향후. 현재는 distinct + 번호 사용 균등화)"""
-    if seed is not None:
-        random.seed(seed)
+    rng = random.Random(seed)
     usage = {n: 0 for n in range(1, 46)}
     seen, out = set(), []
     guard = 0
     while len(out) < k and guard < k * 50:
         guard += 1
-        ranked = sorted(range(1, 46), key=lambda n: (usage[n], random.random()))
+        ranked = sorted(range(1, 46), key=lambda n: (usage[n], rng.random()))
         nums = tuple(sorted(ranked[:6]))
         if nums in seen:
-            # 동점 흔들기: 약간 더 깊은 풀에서 샘플
-            nums = tuple(sorted(random.sample(ranked[:12], 6)))
+            # 동점 흔들기: top-6과 disjoint한 영역에서 샘플
+            nums = tuple(sorted(rng.sample(ranked[6:12], 6)))
             if nums in seen:
                 continue
         seen.add(nums)

lotto/app/db.py

@@ -1501,10 +1501,10 @@ def save_backtest_run(draw_no, strategy, weight_label, weight_json, trial_id,
               weight_json=excluded.weight_json, trial_id=excluded.trial_id,
               n_tickets=excluded.n_tickets, m3=excluded.m3, m4=excluded.m4,
               m5=excluded.m5, m6=excluded.m6, bonus_hits=excluded.bonus_hits,
-              best_match=excluded.best_match, avg_meta_score=excluded.avg_meta_score,
-              created_at=datetime('now')
+              best_match=excluded.best_match, avg_meta_score=excluded.avg_meta_score
             """,
             (draw_no, strategy, weight_label,
+             # weight_json must be a dict/list (not a pre-serialized string) to avoid double-encoding
              json.dumps(weight_json) if weight_json is not None else None,
              trial_id, n_tickets,
              hist.get("m3",0), hist.get("m4",0), hist.get("m5",0), hist.get("m6",0),
@@ -1536,8 +1536,7 @@ def save_winner_calibration(draw_no, winning, scores, percentile,
               score_frequency=excluded.score_frequency, score_fingerprint=excluded.score_fingerprint,
               score_gap=excluded.score_gap, score_cooccur=excluded.score_cooccur,
               score_diversity=excluded.score_diversity, percentile=excluded.percentile,
-              my_pick_avg=excluded.my_pick_avg, cache_draws=excluded.cache_draws,
-              created_at=datetime('now')
+              my_pick_avg=excluded.my_pick_avg, cache_draws=excluded.cache_draws
             """,
             (draw_no, json.dumps(winning), scores["score_total"], scores["score_frequency"],
              scores["score_fingerprint"], scores["score_gap"], scores["score_cooccur"],
@@ -1557,7 +1556,7 @@ def get_calibration_history(limit: int = 52) -> List[Dict[str, Any]]:
             (limit,)).fetchall()
     return [dict(r) for r in rows]
 
-def get_calibrated_draw_nos() -> set:
+def get_calibrated_draw_nos() -> set[int]:
     with _conn() as conn:
         return {r["draw_no"] for r in
                 conn.execute("SELECT draw_no FROM winner_calibration").fetchall()}