feat: cross-market date fix and strategic context selector (issue #88)

KR planner now reads US scorecard from previous day (timezone-aware),
and generate_playbook uses STRATEGIC context selection.

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

docs/requirements-log.md

@@ -64,3 +64,25 @@
 **참고:** Realtime 모드 전용. Daily 모드는 배치 효율성을 위해 정적 watchlist 사용.
 
 **이슈/PR:** #76, #77
+
+---
+
+## 2026-02-10
+
+### 코드 리뷰 시 플랜-구현 일치 검증 규칙
+
+**배경:**
+- 코드 리뷰 시 플랜(EnterPlanMode에서 승인된 계획)과 실제 구현이 일치하는지 확인하는 절차가 없었음
+- 플랜과 다른 구현이 리뷰 없이 통과될 위험
+
+**요구사항:**
+1. 모든 PR 리뷰에서 플랜-구현 일치 여부를 필수 체크
+2. 플랜에 없는 변경은 정당한 사유 필요
+3. 플랜 항목이 누락되면 PR 설명에 사유 기록
+4. 스코프가 플랜과 일치하는지 확인
+
+**구현 결과:**
+- `docs/workflow.md`에 Code Review Checklist 섹션 추가
+  - Plan Consistency (필수), Safety & Constraints, Quality, Workflow 4개 카테고리
+
+**이슈/PR:** #114

docs/workflow.md

@@ -74,3 +74,37 @@ task_tool(
 ```
 
 Use `run_in_background=True` for independent tasks that don't block subsequent work.
+
+## Code Review Checklist
+
+**CRITICAL: Every PR review MUST verify plan-implementation consistency.**
+
+Before approving any PR, the reviewer (human or agent) must check ALL of the following:
+
+### 1. Plan Consistency (MANDATORY)
+
+- [ ] **Implementation matches the approved plan** — Compare the actual code changes against the plan created during `EnterPlanMode`. Every item in the plan must be addressed.
+- [ ] **No unplanned changes** — If the implementation includes changes not in the plan, they must be explicitly justified.
+- [ ] **No plan items omitted** — If any planned item was skipped, the reason must be documented in the PR description.
+- [ ] **Scope matches** — The PR does not exceed or fall short of the planned scope.
+
+### 2. Safety & Constraints
+
+- [ ] `src/core/risk_manager.py` is unchanged (READ-ONLY)
+- [ ] Circuit breaker threshold not weakened (only stricter allowed)
+- [ ] Fat-finger protection (30% max order) still enforced
+- [ ] Confidence < 80 still forces HOLD
+- [ ] No hardcoded API keys or secrets
+
+### 3. Quality
+
+- [ ] All new/modified code has corresponding tests
+- [ ] Test coverage >= 80%
+- [ ] `ruff check src/ tests/` passes (no lint errors)
+- [ ] No `assert` statements removed from tests
+
+### 4. Workflow
+
+- [ ] PR references the Gitea issue number
+- [ ] Feature branch follows naming convention (`feature/issue-N-description`)
+- [ ] Commit messages are clear and descriptive

src/analysis/scanner.py

@@ -108,7 +108,7 @@ class MarketScanner:
             self.context_store.set_context(
                 ContextLayer.L7_REALTIME,
                 timeframe,
-                f"{market.code}_{stock_code}_volatility",
+                f"volatility_{market.code}_{stock_code}",
                 {
                     "price": metrics.current_price,
                     "atr": metrics.atr,
@@ -179,7 +179,7 @@ class MarketScanner:
         self.context_store.set_context(
             ContextLayer.L7_REALTIME,
             timeframe,
-            f"{market.code}_scan_result",
+            f"scan_result_{market.code}",
             {
                 "total_scanned": len(valid_metrics),
                 "top_movers": [m.stock_code for m in top_movers],

src/context/__init__.py

@@ -5,6 +5,7 @@ The context tree implements Pillar 2: hierarchical memory management across
 """
 
 from src.context.layer import ContextLayer
+from src.context.scheduler import ContextScheduler
 from src.context.store import ContextStore
 
-__all__ = ["ContextLayer", "ContextStore"]
+__all__ = ["ContextLayer", "ContextScheduler", "ContextStore"]

src/context/aggregator.py

@@ -18,16 +18,33 @@ class ContextAggregator:
         self.conn = conn
         self.store = ContextStore(conn)
 
-    def aggregate_daily_from_trades(self, date: str | None = None) -> None:
+    def aggregate_daily_from_trades(
+        self, date: str | None = None, market: str | None = None
+    ) -> None:
         """Aggregate L6 (daily) context from trades table.
 
         Args:
             date: Date in YYYY-MM-DD format. If None, uses today.
+            market: Market code filter (e.g., "KR", "US"). If None, aggregates all markets.
         """
         if date is None:
             date = datetime.now(UTC).date().isoformat()
 
-        # Calculate daily metrics from trades
+        if market is None:
+            cursor = self.conn.execute(
+                """
+                SELECT DISTINCT market
+                FROM trades
+                WHERE DATE(timestamp) = ?
+                """,
+                (date,),
+            )
+            markets = [row[0] for row in cursor.fetchall() if row[0]]
+        else:
+            markets = [market]
+
+        for market_code in markets:
+            # Calculate daily metrics from trades for the market
             cursor = self.conn.execute(
                 """
                 SELECT
@@ -41,29 +58,43 @@ class ContextAggregator:
                     SUM(CASE WHEN pnl > 0 THEN 1 ELSE 0 END) as wins,
                     SUM(CASE WHEN pnl < 0 THEN 1 ELSE 0 END) as losses
                 FROM trades
-            WHERE DATE(timestamp) = ?
+                WHERE DATE(timestamp) = ? AND market = ?
                 """,
-            (date,),
+                (date, market_code),
             )
             row = cursor.fetchone()
 
             if row and row[0] > 0:  # At least one trade
                 trade_count, buys, sells, holds, avg_conf, total_pnl, stocks, wins, losses = row
 
-            # Store daily metrics in L6
+                key_suffix = f"_{market_code}"
-            self.store.set_context(ContextLayer.L6_DAILY, date, "trade_count", trade_count)
+
-            self.store.set_context(ContextLayer.L6_DAILY, date, "buys", buys)
+                # Store daily metrics in L6 with market suffix
-            self.store.set_context(ContextLayer.L6_DAILY, date, "sells", sells)
-            self.store.set_context(ContextLayer.L6_DAILY, date, "holds", holds)
                 self.store.set_context(
-                ContextLayer.L6_DAILY, date, "avg_confidence", round(avg_conf, 2)
+                    ContextLayer.L6_DAILY, date, f"trade_count{key_suffix}", trade_count
+                )
+                self.store.set_context(ContextLayer.L6_DAILY, date, f"buys{key_suffix}", buys)
+                self.store.set_context(ContextLayer.L6_DAILY, date, f"sells{key_suffix}", sells)
+                self.store.set_context(ContextLayer.L6_DAILY, date, f"holds{key_suffix}", holds)
+                self.store.set_context(
+                    ContextLayer.L6_DAILY,
+                    date,
+                    f"avg_confidence{key_suffix}",
+                    round(avg_conf, 2),
                 )
                 self.store.set_context(
-                ContextLayer.L6_DAILY, date, "total_pnl", round(total_pnl, 2)
+                    ContextLayer.L6_DAILY,
+                    date,
+                    f"total_pnl{key_suffix}",
+                    round(total_pnl, 2),
+                )
+                self.store.set_context(
+                    ContextLayer.L6_DAILY, date, f"unique_stocks{key_suffix}", stocks
                 )
-            self.store.set_context(ContextLayer.L6_DAILY, date, "unique_stocks", stocks)
                 win_rate = round(wins / max(wins + losses, 1) * 100, 2)
-            self.store.set_context(ContextLayer.L6_DAILY, date, "win_rate", win_rate)
+                self.store.set_context(
+                    ContextLayer.L6_DAILY, date, f"win_rate{key_suffix}", win_rate
+                )
 
     def aggregate_weekly_from_daily(self, week: str | None = None) -> None:
         """Aggregate L5 (weekly) context from L6 (daily).
@@ -92,14 +123,25 @@ class ContextAggregator:
             daily_data[row[0]].append(json.loads(row[1]))
 
         if daily_data:
-            # Sum all PnL values
+            # Sum all PnL values (market-specific if suffixed)
             if "total_pnl" in daily_data:
                 total_pnl = sum(daily_data["total_pnl"])
                 self.store.set_context(
                     ContextLayer.L5_WEEKLY, week, "weekly_pnl", round(total_pnl, 2)
                 )
 
-            # Average all confidence values
+            for key, values in daily_data.items():
+                if key.startswith("total_pnl_"):
+                    market_code = key.split("total_pnl_", 1)[1]
+                    total_pnl = sum(values)
+                    self.store.set_context(
+                        ContextLayer.L5_WEEKLY,
+                        week,
+                        f"weekly_pnl_{market_code}",
+                        round(total_pnl, 2),
+                    )
+
+            # Average all confidence values (market-specific if suffixed)
             if "avg_confidence" in daily_data:
                 conf_values = daily_data["avg_confidence"]
                 avg_conf = sum(conf_values) / len(conf_values)
@@ -107,6 +149,17 @@ class ContextAggregator:
                     ContextLayer.L5_WEEKLY, week, "avg_confidence", round(avg_conf, 2)
                 )
 
+            for key, values in daily_data.items():
+                if key.startswith("avg_confidence_"):
+                    market_code = key.split("avg_confidence_", 1)[1]
+                    avg_conf = sum(values) / len(values)
+                    self.store.set_context(
+                        ContextLayer.L5_WEEKLY,
+                        week,
+                        f"avg_confidence_{market_code}",
+                        round(avg_conf, 2),
+                    )
+
     def aggregate_monthly_from_weekly(self, month: str | None = None) -> None:
         """Aggregate L4 (monthly) context from L5 (weekly).
 
@@ -135,8 +188,16 @@ class ContextAggregator:
 
         if weekly_data:
             # Sum all weekly PnL values
+            total_pnl_values: list[float] = []
             if "weekly_pnl" in weekly_data:
-                total_pnl = sum(weekly_data["weekly_pnl"])
+                total_pnl_values.extend(weekly_data["weekly_pnl"])
+
+            for key, values in weekly_data.items():
+                if key.startswith("weekly_pnl_"):
+                    total_pnl_values.extend(values)
+
+            if total_pnl_values:
+                total_pnl = sum(total_pnl_values)
                 self.store.set_context(
                     ContextLayer.L4_MONTHLY, month, "monthly_pnl", round(total_pnl, 2)
                 )
@@ -230,21 +291,44 @@ class ContextAggregator:
             )
 
     def run_all_aggregations(self) -> None:
-        """Run all aggregations from L7 to L1 (bottom-up)."""
+        """Run all aggregations from L7 to L1 (bottom-up).
+
+        All timeframes are derived from the latest trade timestamp so that
+        past data re-aggregation produces consistent results across layers.
+        """
+        cursor = self.conn.execute("SELECT MAX(timestamp) FROM trades")
+        row = cursor.fetchone()
+        if not row or row[0] is None:
+            return
+
+        ts_raw = row[0]
+        if ts_raw.endswith("Z"):
+            ts_raw = ts_raw.replace("Z", "+00:00")
+        latest_ts = datetime.fromisoformat(ts_raw)
+        trade_date = latest_ts.date()
+        date_str = trade_date.isoformat()
+
+        iso_year, iso_week, _ = trade_date.isocalendar()
+        week_str = f"{iso_year}-W{iso_week:02d}"
+        month_str = f"{trade_date.year}-{trade_date.month:02d}"
+        quarter = (trade_date.month - 1) // 3 + 1
+        quarter_str = f"{trade_date.year}-Q{quarter}"
+        year_str = str(trade_date.year)
+
         # L7 (trades) → L6 (daily)
-        self.aggregate_daily_from_trades()
+        self.aggregate_daily_from_trades(date_str)
 
         # L6 (daily) → L5 (weekly)
-        self.aggregate_weekly_from_daily()
+        self.aggregate_weekly_from_daily(week_str)
 
         # L5 (weekly) → L4 (monthly)
-        self.aggregate_monthly_from_weekly()
+        self.aggregate_monthly_from_weekly(month_str)
 
         # L4 (monthly) → L3 (quarterly)
-        self.aggregate_quarterly_from_monthly()
+        self.aggregate_quarterly_from_monthly(quarter_str)
 
         # L3 (quarterly) → L2 (annual)
-        self.aggregate_annual_from_quarterly()
+        self.aggregate_annual_from_quarterly(year_str)
 
         # L2 (annual) → L1 (legacy)
         self.aggregate_legacy_from_annual()

src/context/scheduler.py

@@ -0,0 +1,135 @@
+"""Context aggregation scheduler for periodic rollups and cleanup."""
+
+from __future__ import annotations
+
+import sqlite3
+from calendar import monthrange
+from dataclasses import dataclass
+from datetime import UTC, datetime
+
+from src.context.aggregator import ContextAggregator
+from src.context.store import ContextStore
+
+
+@dataclass(frozen=True)
+class ScheduleResult:
+    """Represents which scheduled tasks ran."""
+
+    weekly: bool = False
+    monthly: bool = False
+    quarterly: bool = False
+    annual: bool = False
+    legacy: bool = False
+    cleanup: bool = False
+
+
+class ContextScheduler:
+    """Run periodic context aggregations and cleanup when due."""
+
+    def __init__(
+        self,
+        conn: sqlite3.Connection | None = None,
+        aggregator: ContextAggregator | None = None,
+        store: ContextStore | None = None,
+    ) -> None:
+        if aggregator is None:
+            if conn is None:
+                raise ValueError("conn is required when aggregator is not provided")
+            aggregator = ContextAggregator(conn)
+        self.aggregator = aggregator
+
+        if store is None:
+            store = getattr(aggregator, "store", None)
+        if store is None:
+            if conn is None:
+                raise ValueError("conn is required when store is not provided")
+            store = ContextStore(conn)
+        self.store = store
+
+        self._last_run: dict[str, str] = {}
+
+    def run_if_due(self, now: datetime | None = None) -> ScheduleResult:
+        """Run scheduled aggregations if their schedule is due.
+
+        Args:
+            now: Current datetime (UTC). If None, uses current time.
+
+        Returns:
+            ScheduleResult indicating which tasks ran.
+        """
+        if now is None:
+            now = datetime.now(UTC)
+
+        today = now.date().isoformat()
+        result = ScheduleResult()
+
+        if self._should_run("cleanup", today):
+            self.store.cleanup_expired_contexts()
+            result = self._with(result, cleanup=True)
+
+        if self._is_sunday(now) and self._should_run("weekly", today):
+            week = now.strftime("%Y-W%V")
+            self.aggregator.aggregate_weekly_from_daily(week)
+            result = self._with(result, weekly=True)
+
+        if self._is_last_day_of_month(now) and self._should_run("monthly", today):
+            month = now.strftime("%Y-%m")
+            self.aggregator.aggregate_monthly_from_weekly(month)
+            result = self._with(result, monthly=True)
+
+        if self._is_last_day_of_quarter(now) and self._should_run("quarterly", today):
+            quarter = self._current_quarter(now)
+            self.aggregator.aggregate_quarterly_from_monthly(quarter)
+            result = self._with(result, quarterly=True)
+
+        if self._is_last_day_of_year(now) and self._should_run("annual", today):
+            year = str(now.year)
+            self.aggregator.aggregate_annual_from_quarterly(year)
+            result = self._with(result, annual=True)
+
+            # Legacy rollup runs after annual aggregation.
+            self.aggregator.aggregate_legacy_from_annual()
+            result = self._with(result, legacy=True)
+
+        return result
+
+    def _should_run(self, key: str, date_str: str) -> bool:
+        if self._last_run.get(key) == date_str:
+            return False
+        self._last_run[key] = date_str
+        return True
+
+    @staticmethod
+    def _is_sunday(now: datetime) -> bool:
+        return now.weekday() == 6
+
+    @staticmethod
+    def _is_last_day_of_month(now: datetime) -> bool:
+        last_day = monthrange(now.year, now.month)[1]
+        return now.day == last_day
+
+    @classmethod
+    def _is_last_day_of_quarter(cls, now: datetime) -> bool:
+        if now.month not in (3, 6, 9, 12):
+            return False
+        return cls._is_last_day_of_month(now)
+
+    @staticmethod
+    def _is_last_day_of_year(now: datetime) -> bool:
+        return now.month == 12 and now.day == 31
+
+    @staticmethod
+    def _current_quarter(now: datetime) -> str:
+        quarter = (now.month - 1) // 3 + 1
+        return f"{now.year}-Q{quarter}"
+
+    @staticmethod
+    def _with(result: ScheduleResult, **kwargs: bool) -> ScheduleResult:
+        return ScheduleResult(
+            weekly=kwargs.get("weekly", result.weekly),
+            monthly=kwargs.get("monthly", result.monthly),
+            quarterly=kwargs.get("quarterly", result.quarterly),
+            annual=kwargs.get("annual", result.annual),
+            legacy=kwargs.get("legacy", result.legacy),
+            cleanup=kwargs.get("cleanup", result.cleanup),
+        )

src/db.py

@@ -6,6 +6,7 @@ import json
 import sqlite3
 from datetime import UTC, datetime
 from pathlib import Path
+from typing import Any
 
 
 def init_db(db_path: str) -> sqlite3.Connection:
@@ -26,7 +27,8 @@ def init_db(db_path: str) -> sqlite3.Connection:
             price REAL,
             pnl REAL DEFAULT 0.0,
             market TEXT DEFAULT 'KR',
-            exchange_code TEXT DEFAULT 'KRX'
+            exchange_code TEXT DEFAULT 'KRX',
+            decision_id TEXT
         )
         """
     )
@@ -41,6 +43,8 @@ def init_db(db_path: str) -> sqlite3.Connection:
         conn.execute("ALTER TABLE trades ADD COLUMN exchange_code TEXT DEFAULT 'KRX'")
     if "selection_context" not in columns:
         conn.execute("ALTER TABLE trades ADD COLUMN selection_context TEXT")
+    if "decision_id" not in columns:
+        conn.execute("ALTER TABLE trades ADD COLUMN decision_id TEXT")
 
     # Context tree tables for multi-layered memory management
     conn.execute(
@@ -143,6 +147,7 @@ def log_trade(
     market: str = "KR",
     exchange_code: str = "KRX",
     selection_context: dict[str, any] | None = None,
+    decision_id: str | None = None,
 ) -> None:
     """Insert a trade record into the database.
 
@@ -166,9 +171,9 @@ def log_trade(
         """
         INSERT INTO trades (
             timestamp, stock_code, action, confidence, rationale,
-            quantity, price, pnl, market, exchange_code, selection_context
+            quantity, price, pnl, market, exchange_code, selection_context, decision_id
         )
-        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
         """,
         (
             datetime.now(UTC).isoformat(),
@@ -182,6 +187,30 @@ def log_trade(
             market,
             exchange_code,
             context_json,
+            decision_id,
         ),
     )
     conn.commit()
+
+
+def get_latest_buy_trade(
+    conn: sqlite3.Connection, stock_code: str, market: str
+) -> dict[str, Any] | None:
+    """Fetch the most recent BUY trade for a stock and market."""
+    cursor = conn.execute(
+        """
+        SELECT decision_id, price, quantity
+        FROM trades
+        WHERE stock_code = ?
+          AND market = ?
+          AND action = 'BUY'
+          AND decision_id IS NOT NULL
+        ORDER BY timestamp DESC
+        LIMIT 1
+        """,
+        (stock_code, market),
+    )
+    row = cursor.fetchone()
+    if not row:
+        return None
+    return {"decision_id": row[0], "price": row[1], "quantity": row[2]}

src/evolution/__init__.py

@@ -1,12 +1,14 @@
 """Evolution engine for self-improving trading strategies."""
 
 from src.evolution.ab_test import ABTester, ABTestResult, StrategyPerformance
+from src.evolution.daily_review import DailyReviewer
 from src.evolution.optimizer import EvolutionOptimizer
 from src.evolution.performance_tracker import (
     PerformanceDashboard,
     PerformanceTracker,
     StrategyMetrics,
 )
+from src.evolution.scorecard import DailyScorecard
 
 __all__ = [
     "EvolutionOptimizer",
@@ -16,4 +18,6 @@ __all__ = [
     "PerformanceTracker",
     "PerformanceDashboard",
     "StrategyMetrics",
+    "DailyScorecard",
+    "DailyReviewer",
 ]

src/evolution/daily_review.py

@@ -0,0 +1,196 @@
+"""Daily review generator for market-scoped end-of-day scorecards."""
+
+from __future__ import annotations
+
+import json
+import logging
+import re
+import sqlite3
+from dataclasses import asdict
+
+from src.brain.gemini_client import GeminiClient
+from src.context.layer import ContextLayer
+from src.context.store import ContextStore
+from src.evolution.scorecard import DailyScorecard
+
+logger = logging.getLogger(__name__)
+
+
+class DailyReviewer:
+    """Builds daily scorecards and optional AI-generated lessons."""
+
+    def __init__(
+        self,
+        conn: sqlite3.Connection,
+        context_store: ContextStore,
+        gemini_client: GeminiClient | None = None,
+    ) -> None:
+        self._conn = conn
+        self._context_store = context_store
+        self._gemini = gemini_client
+
+    def generate_scorecard(self, date: str, market: str) -> DailyScorecard:
+        """Generate a market-scoped scorecard from decision logs and trades."""
+        decision_rows = self._conn.execute(
+            """
+            SELECT action, confidence, context_snapshot
+            FROM decision_logs
+            WHERE DATE(timestamp) = ? AND market = ?
+            """,
+            (date, market),
+        ).fetchall()
+
+        total_decisions = len(decision_rows)
+        buys = sum(1 for row in decision_rows if row[0] == "BUY")
+        sells = sum(1 for row in decision_rows if row[0] == "SELL")
+        holds = sum(1 for row in decision_rows if row[0] == "HOLD")
+        avg_confidence = (
+            round(sum(int(row[1]) for row in decision_rows) / total_decisions, 2)
+            if total_decisions > 0
+            else 0.0
+        )
+
+        matched = 0
+        for row in decision_rows:
+            try:
+                snapshot = json.loads(row[2]) if row[2] else {}
+            except json.JSONDecodeError:
+                snapshot = {}
+            scenario_match = snapshot.get("scenario_match", {})
+            if isinstance(scenario_match, dict) and scenario_match:
+                matched += 1
+        scenario_match_rate = (
+            round((matched / total_decisions) * 100, 2)
+            if total_decisions
+            else 0.0
+        )
+
+        trade_stats = self._conn.execute(
+            """
+            SELECT
+                COALESCE(SUM(pnl), 0.0),
+                SUM(CASE WHEN pnl > 0 THEN 1 ELSE 0 END),
+                SUM(CASE WHEN pnl < 0 THEN 1 ELSE 0 END)
+            FROM trades
+            WHERE DATE(timestamp) = ? AND market = ?
+            """,
+            (date, market),
+        ).fetchone()
+        total_pnl = round(float(trade_stats[0] or 0.0), 2) if trade_stats else 0.0
+        wins = int(trade_stats[1] or 0) if trade_stats else 0
+        losses = int(trade_stats[2] or 0) if trade_stats else 0
+        win_rate = round((wins / (wins + losses)) * 100, 2) if (wins + losses) > 0 else 0.0
+
+        top_winners = [
+            row[0]
+            for row in self._conn.execute(
+                """
+                SELECT stock_code, SUM(pnl) AS stock_pnl
+                FROM trades
+                WHERE DATE(timestamp) = ? AND market = ?
+                GROUP BY stock_code
+                HAVING stock_pnl > 0
+                ORDER BY stock_pnl DESC
+                LIMIT 3
+                """,
+                (date, market),
+            ).fetchall()
+        ]
+
+        top_losers = [
+            row[0]
+            for row in self._conn.execute(
+                """
+                SELECT stock_code, SUM(pnl) AS stock_pnl
+                FROM trades
+                WHERE DATE(timestamp) = ? AND market = ?
+                GROUP BY stock_code
+                HAVING stock_pnl < 0
+                ORDER BY stock_pnl ASC
+                LIMIT 3
+                """,
+                (date, market),
+            ).fetchall()
+        ]
+
+        return DailyScorecard(
+            date=date,
+            market=market,
+            total_decisions=total_decisions,
+            buys=buys,
+            sells=sells,
+            holds=holds,
+            total_pnl=total_pnl,
+            win_rate=win_rate,
+            avg_confidence=avg_confidence,
+            scenario_match_rate=scenario_match_rate,
+            top_winners=top_winners,
+            top_losers=top_losers,
+            lessons=[],
+            cross_market_note="",
+        )
+
+    async def generate_lessons(self, scorecard: DailyScorecard) -> list[str]:
+        """Generate concise lessons from scorecard metrics using Gemini."""
+        if self._gemini is None:
+            return []
+
+        prompt = (
+            "You are a trading performance reviewer.\n"
+            "Return ONLY a JSON array of 1-3 short lessons in English.\n"
+            f"Market: {scorecard.market}\n"
+            f"Date: {scorecard.date}\n"
+            f"Total decisions: {scorecard.total_decisions}\n"
+            f"Buys/Sells/Holds: {scorecard.buys}/{scorecard.sells}/{scorecard.holds}\n"
+            f"Total PnL: {scorecard.total_pnl}\n"
+            f"Win rate: {scorecard.win_rate}%\n"
+            f"Average confidence: {scorecard.avg_confidence}\n"
+            f"Scenario match rate: {scorecard.scenario_match_rate}%\n"
+            f"Top winners: {', '.join(scorecard.top_winners) or 'N/A'}\n"
+            f"Top losers: {', '.join(scorecard.top_losers) or 'N/A'}\n"
+        )
+
+        try:
+            decision = await self._gemini.decide(
+                {
+                    "stock_code": "REVIEW",
+                    "market_name": scorecard.market,
+                    "current_price": 0,
+                    "prompt_override": prompt,
+                }
+            )
+            return self._parse_lessons(decision.rationale)
+        except Exception as exc:
+            logger.warning("Failed to generate daily lessons: %s", exc)
+            return []
+
+    def store_scorecard_in_context(self, scorecard: DailyScorecard) -> None:
+        """Store scorecard in L6 using market-scoped key."""
+        self._context_store.set_context(
+            ContextLayer.L6_DAILY,
+            scorecard.date,
+            f"scorecard_{scorecard.market}",
+            asdict(scorecard),
+        )
+
+    def _parse_lessons(self, raw_text: str) -> list[str]:
+        """Parse lessons from JSON array response or fallback text."""
+        raw_text = raw_text.strip()
+        try:
+            parsed = json.loads(raw_text)
+            if isinstance(parsed, list):
+                return [str(item).strip() for item in parsed if str(item).strip()][:3]
+        except json.JSONDecodeError:
+            pass
+
+        match = re.search(r"\[.*\]", raw_text, re.DOTALL)
+        if match:
+            try:
+                parsed = json.loads(match.group(0))
+                if isinstance(parsed, list):
+                    return [str(item).strip() for item in parsed if str(item).strip()][:3]
+            except json.JSONDecodeError:
+                pass
+
+        lines = [line.strip("-* \t") for line in raw_text.splitlines() if line.strip()]
+        return lines[:3]

src/evolution/scorecard.py

@@ -0,0 +1,25 @@
+"""Daily scorecard model for end-of-day performance review."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+
+
+@dataclass
+class DailyScorecard:
+    """Structured daily performance snapshot for a single market."""
+
+    date: str
+    market: str
+    total_decisions: int
+    buys: int
+    sells: int
+    holds: int
+    total_pnl: float
+    win_rate: float
+    avg_confidence: float
+    scenario_match_rate: float
+    top_winners: list[str] = field(default_factory=list)
+    top_losers: list[str] = field(default_factory=list)
+    lessons: list[str] = field(default_factory=list)
+    cross_market_note: str = ""

src/main.py

@@ -10,27 +10,32 @@ import argparse
 import asyncio
 import logging
 import signal
-import sys
 from datetime import UTC, datetime
 from typing import Any
 
-from src.analysis.scanner import MarketScanner
 from src.analysis.smart_scanner import ScanCandidate, SmartVolatilityScanner
 from src.analysis.volatility import VolatilityAnalyzer
-from src.brain.gemini_client import GeminiClient
+from src.brain.context_selector import ContextSelector
+from src.brain.gemini_client import GeminiClient, TradeDecision
 from src.broker.kis_api import KISBroker
 from src.broker.overseas import OverseasBroker
 from src.config import Settings
+from src.context.aggregator import ContextAggregator
 from src.context.layer import ContextLayer
 from src.context.store import ContextStore
 from src.core.criticality import CriticalityAssessor
 from src.core.priority_queue import PriorityTaskQueue
 from src.core.risk_manager import CircuitBreakerTripped, FatFingerRejected, RiskManager
-from src.db import init_db, log_trade
+from src.db import get_latest_buy_trade, init_db, log_trade
+from src.evolution.daily_review import DailyReviewer
 from src.logging.decision_logger import DecisionLogger
 from src.logging_config import setup_logging
 from src.markets.schedule import MarketInfo, get_next_market_open, get_open_markets
 from src.notifications.telegram_client import TelegramClient, TelegramCommandHandler
+from src.strategy.models import DayPlaybook
+from src.strategy.playbook_store import PlaybookStore
+from src.strategy.pre_market_planner import PreMarketPlanner
+from src.strategy.scenario_engine import ScenarioEngine
 
 logger = logging.getLogger(__name__)
 
@@ -75,7 +80,8 @@ TRADE_SESSION_INTERVAL_HOURS = 6  # Hours between sessions
 async def trading_cycle(
     broker: KISBroker,
     overseas_broker: OverseasBroker,
-    brain: GeminiClient,
+    scenario_engine: ScenarioEngine,
+    playbook: DayPlaybook,
     risk: RiskManager,
     db_conn: Any,
     decision_logger: DecisionLogger,
@@ -84,7 +90,7 @@ async def trading_cycle(
     telegram: TelegramClient,
     market: MarketInfo,
     stock_code: str,
-    scan_candidates: dict[str, ScanCandidate],
+    scan_candidates: dict[str, dict[str, ScanCandidate]],
 ) -> None:
     """Execute one trading cycle for a single stock."""
     cycle_start_time = asyncio.get_event_loop().time()
@@ -135,13 +141,59 @@ async def trading_cycle(
         else 0.0
     )
 
-    market_data = {
+    market_data: dict[str, Any] = {
         "stock_code": stock_code,
         "market_name": market.name,
         "current_price": current_price,
         "foreigner_net": foreigner_net,
     }
 
+    # Enrich market_data with scanner metrics for scenario engine
+    market_candidates = scan_candidates.get(market.code, {})
+    candidate = market_candidates.get(stock_code)
+    if candidate:
+        market_data["rsi"] = candidate.rsi
+        market_data["volume_ratio"] = candidate.volume_ratio
+
+    # 1.3. Record L7 real-time context (market-scoped keys)
+    timeframe = datetime.now(UTC).isoformat()
+    context_store.set_context(
+        ContextLayer.L7_REALTIME,
+        timeframe,
+        f"volatility_{market.code}_{stock_code}",
+        {
+            "momentum_score": 50.0,
+            "volume_surge": 1.0,
+            "price_change_1m": 0.0,
+        },
+    )
+    context_store.set_context(
+        ContextLayer.L7_REALTIME,
+        timeframe,
+        f"price_{market.code}_{stock_code}",
+        {"current_price": current_price},
+    )
+    if candidate:
+        context_store.set_context(
+            ContextLayer.L7_REALTIME,
+            timeframe,
+            f"rsi_{market.code}_{stock_code}",
+            {"rsi": candidate.rsi},
+        )
+        context_store.set_context(
+            ContextLayer.L7_REALTIME,
+            timeframe,
+            f"volume_ratio_{market.code}_{stock_code}",
+            {"volume_ratio": candidate.volume_ratio},
+        )
+
+    # Build portfolio data for global rule evaluation
+    portfolio_data = {
+        "portfolio_pnl_pct": pnl_pct,
+        "total_cash": total_cash,
+        "total_eval": total_eval,
+    }
+
     # 1.5. Get volatility metrics from context store (L7_REALTIME)
     latest_timeframe = context_store.get_latest_timeframe(ContextLayer.L7_REALTIME)
     volatility_score = 50.0  # Default normal volatility
@@ -152,7 +204,7 @@ async def trading_cycle(
         volatility_data = context_store.get_context(
             ContextLayer.L7_REALTIME,
             latest_timeframe,
-            f"volatility_{stock_code}",
+            f"volatility_{market.code}_{stock_code}",
         )
         if volatility_data:
             volatility_score = volatility_data.get("momentum_score", 50.0)
@@ -178,8 +230,13 @@ async def trading_cycle(
         volume_surge,
     )
 
-    # 2. Ask the brain for a decision
+    # 2. Evaluate scenario (local, no API call)
-    decision = await brain.decide(market_data)
+    match = scenario_engine.evaluate(playbook, stock_code, market_data, portfolio_data)
+    decision = TradeDecision(
+        action=match.action.value,
+        confidence=match.confidence,
+        rationale=match.rationale,
+    )
     logger.info(
         "Decision for %s (%s): %s (confidence=%d)",
         stock_code,
@@ -188,6 +245,19 @@ async def trading_cycle(
         decision.confidence,
     )
 
+    # 2.1. Notify scenario match
+    if match.matched_scenario is not None:
+        try:
+            condition_parts = [f"{k}={v}" for k, v in match.match_details.items()]
+            await telegram.notify_scenario_matched(
+                stock_code=stock_code,
+                action=decision.action,
+                condition_summary=", ".join(condition_parts) if condition_parts else "matched",
+                confidence=float(decision.confidence),
+            )
+        except Exception as exc:
+            logger.warning("Scenario matched notification failed: %s", exc)
+
     # 2.5. Log decision with context snapshot
     context_snapshot = {
         "L1": {
@@ -200,7 +270,7 @@ async def trading_cycle(
             "purchase_total": purchase_total,
             "pnl_pct": pnl_pct,
         },
-        # L3-L7 will be populated when context tree is implemented
+        "scenario_match": match.match_details,
     }
     input_data = {
         "current_price": current_price,
@@ -210,7 +280,7 @@ async def trading_cycle(
         "pnl_pct": pnl_pct,
     }
 
-    decision_logger.log_decision(
+    decision_id = decision_logger.log_decision(
         stock_code=stock_code,
         market=market.code,
         exchange_code=market.exchange_code,
@@ -222,6 +292,9 @@ async def trading_cycle(
     )
 
     # 3. Execute if actionable
+    quantity = 0
+    trade_price = current_price
+    trade_pnl = 0.0
     if decision.action in ("BUY", "SELL"):
         # Determine order size (simplified: 1 lot)
         quantity = 1
@@ -277,10 +350,22 @@ async def trading_cycle(
         except Exception as exc:
             logger.warning("Telegram notification failed: %s", exc)
 
+        if decision.action == "SELL":
+            buy_trade = get_latest_buy_trade(db_conn, stock_code, market.code)
+            if buy_trade and buy_trade.get("price") is not None:
+                buy_price = float(buy_trade["price"])
+                buy_qty = int(buy_trade.get("quantity") or 1)
+                trade_pnl = (trade_price - buy_price) * buy_qty
+                decision_logger.update_outcome(
+                    decision_id=buy_trade["decision_id"],
+                    pnl=trade_pnl,
+                    accuracy=1 if trade_pnl > 0 else 0,
+                )
+
     # 6. Log trade with selection context
     selection_context = None
-    if stock_code in scan_candidates:
+    if stock_code in market_candidates:
-        candidate = scan_candidates[stock_code]
+        candidate = market_candidates[stock_code]
         selection_context = {
             "rsi": candidate.rsi,
             "volume_ratio": candidate.volume_ratio,
@@ -294,9 +379,13 @@ async def trading_cycle(
         action=decision.action,
         confidence=decision.confidence,
         rationale=decision.rationale,
+        quantity=quantity,
+        price=trade_price,
+        pnl=trade_pnl,
         market=market.code,
         exchange_code=market.exchange_code,
         selection_context=selection_context,
+        decision_id=decision_id,
     )
 
     # 7. Latency monitoring
@@ -324,7 +413,9 @@ async def trading_cycle(
 async def run_daily_session(
     broker: KISBroker,
     overseas_broker: OverseasBroker,
-    brain: GeminiClient,
+    scenario_engine: ScenarioEngine,
+    playbook_store: PlaybookStore,
+    pre_market_planner: PreMarketPlanner,
     risk: RiskManager,
     db_conn: Any,
     decision_logger: DecisionLogger,
@@ -336,10 +427,8 @@ async def run_daily_session(
 ) -> None:
     """Execute one daily trading session.
 
-    Designed for API efficiency with Gemini Free tier:
+    V2 proactive strategy: 1 Gemini call for playbook generation,
-    - Batch decision making (1 API call per market)
+    then local scenario evaluation per stock (0 API calls).
-    - Runs N times per day at fixed intervals
-    - Minimizes API usage while maintaining trading capability
     """
     # Get currently open markets
     open_markets = get_open_markets(settings.enabled_market_list)
@@ -352,27 +441,66 @@ async def run_daily_session(
 
     # Process each open market
     for market in open_markets:
+        # Use market-local date for playbook keying
+        market_today = datetime.now(market.timezone).date()
+
         # Dynamic stock discovery via scanner (no static watchlists)
+        candidates_list: list[ScanCandidate] = []
         try:
-            candidates = await smart_scanner.scan()
+            candidates_list = await smart_scanner.scan() if smart_scanner else []
-            watchlist = [c.stock_code for c in candidates] if candidates else []
         except Exception as exc:
             logger.error("Smart Scanner failed for %s: %s", market.name, exc)
-            watchlist = []
 
-        if not watchlist:
+        if not candidates_list:
             logger.info("No scanner candidates for market %s — skipping", market.code)
             continue
 
+        watchlist = [c.stock_code for c in candidates_list]
+        candidate_map = {c.stock_code: c for c in candidates_list}
         logger.info("Processing market: %s (%d stocks)", market.name, len(watchlist))
 
+        # Generate or load playbook (1 Gemini API call per market per day)
+        playbook = playbook_store.load(market_today, market.code)
+        if playbook is None:
+            try:
+                playbook = await pre_market_planner.generate_playbook(
+                    market=market.code,
+                    candidates=candidates_list,
+                    today=market_today,
+                )
+                playbook_store.save(playbook)
+                try:
+                    await telegram.notify_playbook_generated(
+                        market=market.code,
+                        stock_count=playbook.stock_count,
+                        scenario_count=playbook.scenario_count,
+                        token_count=playbook.token_count,
+                    )
+                except Exception as exc:
+                    logger.warning("Playbook notification failed: %s", exc)
+                logger.info(
+                    "Generated playbook for %s: %d stocks, %d scenarios",
+                    market.code, playbook.stock_count, playbook.scenario_count,
+                )
+            except Exception as exc:
+                logger.error("Playbook generation failed for %s: %s", market.code, exc)
+                try:
+                    await telegram.notify_playbook_failed(
+                        market=market.code, reason=str(exc)[:200],
+                    )
+                except Exception as notify_exc:
+                    logger.warning("Playbook failed notification error: %s", notify_exc)
+                playbook = PreMarketPlanner._empty_playbook(market_today, market.code)
+
         # Collect market data for all stocks from scanner
         stocks_data = []
         for stock_code in watchlist:
             try:
                 if market.is_domestic:
                     orderbook = await broker.get_orderbook(stock_code)
-                    current_price = safe_float(orderbook.get("output1", {}).get("stck_prpr", "0"))
+                    current_price = safe_float(
+                        orderbook.get("output1", {}).get("stck_prpr", "0")
+                    )
                     foreigner_net = safe_float(
                         orderbook.get("output1", {}).get("frgn_ntby_qty", "0")
                     )
@@ -380,17 +508,23 @@ async def run_daily_session(
                     price_data = await overseas_broker.get_overseas_price(
                         market.exchange_code, stock_code
                     )
-                    current_price = safe_float(price_data.get("output", {}).get("last", "0"))
+                    current_price = safe_float(
+                        price_data.get("output", {}).get("last", "0")
+                    )
                     foreigner_net = 0.0
 
-                stocks_data.append(
+                stock_data: dict[str, Any] = {
-                    {
                     "stock_code": stock_code,
                     "market_name": market.name,
                     "current_price": current_price,
                     "foreigner_net": foreigner_net,
                 }
-                )
+                # Enrich with scanner metrics
+                cand = candidate_map.get(stock_code)
+                if cand:
+                    stock_data["rsi"] = cand.rsi
+                    stock_data["volume_ratio"] = cand.volume_ratio
+                stocks_data.append(stock_data)
             except Exception as exc:
                 logger.error("Failed to fetch data for %s: %s", stock_code, exc)
                 continue
@@ -399,17 +533,19 @@ async def run_daily_session(
             logger.warning("No valid stock data for market %s", market.code)
             continue
 
-        # Get batch decisions (1 API call for all stocks in this market)
-        logger.info("Requesting batch decision for %d stocks in %s", len(stocks_data), market.name)
-        decisions = await brain.decide_batch(stocks_data)
-
         # Get balance data once for the market
         if market.is_domestic:
             balance_data = await broker.get_balance()
             output2 = balance_data.get("output2", [{}])
-            total_eval = safe_float(output2[0].get("tot_evlu_amt", "0")) if output2 else 0
+            total_eval = safe_float(
-            total_cash = safe_float(output2[0].get("dnca_tot_amt", "0")) if output2 else 0
+                output2[0].get("tot_evlu_amt", "0")
-            purchase_total = safe_float(output2[0].get("pchs_amt_smtl_amt", "0")) if output2 else 0
+            ) if output2 else 0
+            total_cash = safe_float(
+                output2[0].get("dnca_tot_amt", "0")
+            ) if output2 else 0
+            purchase_total = safe_float(
+                output2[0].get("pchs_amt_smtl_amt", "0")
+            ) if output2 else 0
         else:
             balance_data = await overseas_broker.get_overseas_balance(market.exchange_code)
             output2 = balance_data.get("output2", [{}])
@@ -422,21 +558,37 @@ async def run_daily_session(
 
             total_eval = safe_float(balance_info.get("frcr_evlu_tota", "0") or "0")
             total_cash = safe_float(balance_info.get("frcr_dncl_amt_2", "0") or "0")
-            purchase_total = safe_float(balance_info.get("frcr_buy_amt_smtl", "0") or "0")
+            purchase_total = safe_float(
+                balance_info.get("frcr_buy_amt_smtl", "0") or "0"
+            )
 
         # Calculate daily P&L %
         pnl_pct = (
-            ((total_eval - purchase_total) / purchase_total * 100) if purchase_total > 0 else 0.0
+            ((total_eval - purchase_total) / purchase_total * 100)
+            if purchase_total > 0
+            else 0.0
         )
+        portfolio_data = {
+            "portfolio_pnl_pct": pnl_pct,
+            "total_cash": total_cash,
+            "total_eval": total_eval,
+        }
 
-        # Execute decisions for each stock
+        # Evaluate scenarios for each stock (local, no API calls)
+        logger.info(
+            "Evaluating %d stocks against playbook for %s",
+            len(stocks_data), market.name,
+        )
         for stock_data in stocks_data:
             stock_code = stock_data["stock_code"]
-            decision = decisions.get(stock_code)
+            match = scenario_engine.evaluate(
-
+                playbook, stock_code, stock_data, portfolio_data,
-            if not decision:
+            )
-                logger.warning("No decision for %s — skipping", stock_code)
+            decision = TradeDecision(
-                continue
+                action=match.action.value,
+                confidence=match.confidence,
+                rationale=match.rationale,
+            )
 
             logger.info(
                 "Decision for %s (%s): %s (confidence=%d)",
@@ -458,6 +610,7 @@ async def run_daily_session(
                     "purchase_total": purchase_total,
                     "pnl_pct": pnl_pct,
                 },
+                "scenario_match": match.match_details,
             }
             input_data = {
                 "current_price": stock_data["current_price"],
@@ -467,7 +620,7 @@ async def run_daily_session(
                 "pnl_pct": pnl_pct,
             }
 
-            decision_logger.log_decision(
+            decision_id = decision_logger.log_decision(
                 stock_code=stock_code,
                 market=market.code,
                 exchange_code=market.exchange_code,
@@ -479,6 +632,9 @@ async def run_daily_session(
             )
 
             # Execute if actionable
+            quantity = 0
+            trade_price = stock_data["current_price"]
+            trade_pnl = 0.0
             if decision.action in ("BUY", "SELL"):
                 quantity = 1
                 order_amount = stock_data["current_price"] * quantity
@@ -509,7 +665,9 @@ async def run_daily_session(
                             threshold=exc.threshold,
                         )
                     except Exception as notify_exc:
-                        logger.warning("Circuit breaker notification failed: %s", notify_exc)
+                        logger.warning(
+                            "Circuit breaker notification failed: %s", notify_exc
+                        )
                     raise
 
                 # Send order
@@ -544,9 +702,23 @@ async def run_daily_session(
                     except Exception as exc:
                         logger.warning("Telegram notification failed: %s", exc)
                 except Exception as exc:
-                    logger.error("Order execution failed for %s: %s", stock_code, exc)
+                    logger.error(
+                        "Order execution failed for %s: %s", stock_code, exc
+                    )
                     continue
 
+                if decision.action == "SELL":
+                    buy_trade = get_latest_buy_trade(db_conn, stock_code, market.code)
+                    if buy_trade and buy_trade.get("price") is not None:
+                        buy_price = float(buy_trade["price"])
+                        buy_qty = int(buy_trade.get("quantity") or 1)
+                        trade_pnl = (trade_price - buy_price) * buy_qty
+                        decision_logger.update_outcome(
+                            decision_id=buy_trade["decision_id"],
+                            pnl=trade_pnl,
+                            accuracy=1 if trade_pnl > 0 else 0,
+                        )
+
             # Log trade
             log_trade(
                 conn=db_conn,
@@ -554,13 +726,52 @@ async def run_daily_session(
                 action=decision.action,
                 confidence=decision.confidence,
                 rationale=decision.rationale,
+                quantity=quantity,
+                price=trade_price,
+                pnl=trade_pnl,
                 market=market.code,
                 exchange_code=market.exchange_code,
+                decision_id=decision_id,
             )
 
     logger.info("Daily trading session completed")
 
 
+async def _handle_market_close(
+    market_code: str,
+    market_name: str,
+    market_timezone: Any,
+    telegram: TelegramClient,
+    context_aggregator: ContextAggregator,
+    daily_reviewer: DailyReviewer,
+) -> None:
+    """Handle market-close tasks: notify, aggregate, review, and store context."""
+    await telegram.notify_market_close(market_name, 0.0)
+
+    market_date = datetime.now(market_timezone).date().isoformat()
+    context_aggregator.aggregate_daily_from_trades(
+        date=market_date,
+        market=market_code,
+    )
+
+    scorecard = daily_reviewer.generate_scorecard(market_date, market_code)
+    daily_reviewer.store_scorecard_in_context(scorecard)
+
+    lessons = await daily_reviewer.generate_lessons(scorecard)
+    if lessons:
+        scorecard.lessons = lessons
+        daily_reviewer.store_scorecard_in_context(scorecard)
+
+    await telegram.send_message(
+        f"<b>Daily Review ({market_code})</b>\n"
+        f"Date: {scorecard.date}\n"
+        f"Decisions: {scorecard.total_decisions}\n"
+        f"P&L: {scorecard.total_pnl:+.2f}\n"
+        f"Win Rate: {scorecard.win_rate:.2f}%\n"
+        f"Lessons: {', '.join(scorecard.lessons) if scorecard.lessons else 'N/A'}"
+    )
+
+
 async def run(settings: Settings) -> None:
     """Main async loop — iterate over open markets on a timer."""
     broker = KISBroker(settings)
@@ -570,6 +781,22 @@ async def run(settings: Settings) -> None:
     db_conn = init_db(settings.DB_PATH)
     decision_logger = DecisionLogger(db_conn)
     context_store = ContextStore(db_conn)
+    context_aggregator = ContextAggregator(db_conn)
+
+    # V2 proactive strategy components
+    context_selector = ContextSelector(context_store)
+    scenario_engine = ScenarioEngine()
+    playbook_store = PlaybookStore(db_conn)
+    daily_reviewer = DailyReviewer(db_conn, context_store, gemini_client=brain)
+    pre_market_planner = PreMarketPlanner(
+        gemini_client=brain,
+        context_store=context_store,
+        context_selector=context_selector,
+        settings=settings,
+    )
+
+    # Track playbooks per market (in-memory cache)
+    playbooks: dict[str, DayPlaybook] = {}
 
     # Initialize Telegram notifications
     telegram = TelegramClient(
@@ -716,15 +943,6 @@ async def run(settings: Settings) -> None:
 
     # Initialize volatility hunter
     volatility_analyzer = VolatilityAnalyzer(min_volume_surge=2.0, min_price_change=1.0)
-    market_scanner = MarketScanner(
-        broker=broker,
-        overseas_broker=overseas_broker,
-        volatility_analyzer=volatility_analyzer,
-        context_store=context_store,
-        top_n=5,
-        max_concurrent_scans=1,  # Fully serialized to avoid EGW00201
-    )
-
     # Initialize smart scanner (Python-first, AI-last pipeline)
     smart_scanner = SmartVolatilityScanner(
         broker=broker,
@@ -732,8 +950,8 @@ async def run(settings: Settings) -> None:
         settings=settings,
     )
 
-    # Track scan candidates for selection context logging
+    # Track scan candidates per market for selection context logging
-    scan_candidates: dict[str, ScanCandidate] = {}  # stock_code -> candidate
+    scan_candidates: dict[str, dict[str, ScanCandidate]] = {}  # market -> {stock_code -> candidate}
 
     # Active stocks per market (dynamically discovered by scanner)
     active_stocks: dict[str, list[str]] = {}  # market_code -> [stock_codes]
@@ -802,7 +1020,9 @@ async def run(settings: Settings) -> None:
                     await run_daily_session(
                         broker,
                         overseas_broker,
-                        brain,
+                        scenario_engine,
+                        playbook_store,
+                        pre_market_planner,
                         risk,
                         db_conn,
                         decision_logger,
@@ -846,10 +1066,19 @@ async def run(settings: Settings) -> None:
 
                                 market_info = MARKETS.get(market_code)
                                 if market_info:
-                                    await telegram.notify_market_close(market_info.name, 0.0)
+                                    await _handle_market_close(
+                                        market_code=market_code,
+                                        market_name=market_info.name,
+                                        market_timezone=market_info.timezone,
+                                        telegram=telegram,
+                                        context_aggregator=context_aggregator,
+                                        daily_reviewer=daily_reviewer,
+                                    )
                             except Exception as exc:
                                 logger.warning("Market close notification failed: %s", exc)
                             _market_states[market_code] = False
+                            # Clear playbook for closed market (new one generated next open)
+                            playbooks.pop(market_code, None)
 
                     # No markets open — wait until next market opens
                     try:
@@ -887,7 +1116,8 @@ async def run(settings: Settings) -> None:
                     # Smart Scanner: dynamic stock discovery (no static watchlists)
                     now_timestamp = asyncio.get_event_loop().time()
                     last_scan = last_scan_time.get(market.code, 0.0)
-                    if now_timestamp - last_scan >= SCAN_INTERVAL_SECONDS:
+                    rescan_interval = settings.RESCAN_INTERVAL_SECONDS
+                    if now_timestamp - last_scan >= rescan_interval:
                         try:
                             logger.info("Smart Scanner: Scanning %s market", market.name)
 
@@ -899,9 +1129,10 @@ async def run(settings: Settings) -> None:
                                     candidates
                                 )
 
-                                # Store candidates for selection context logging
+                                # Store candidates per market for selection context logging
-                                for candidate in candidates:
+                                scan_candidates[market.code] = {
-                                    scan_candidates[candidate.stock_code] = candidate
+                                    c.stock_code: c for c in candidates
+                                }
 
                                 logger.info(
                                     "Smart Scanner: Found %d candidates for %s: %s",
@@ -909,6 +1140,62 @@ async def run(settings: Settings) -> None:
                                     market.name,
                                     [f"{c.stock_code}(RSI={c.rsi:.0f})" for c in candidates],
                                 )
+
+                                # Get market-local date for playbook keying
+                                market_today = datetime.now(
+                                    market.timezone
+                                ).date()
+
+                                # Load or generate playbook (1 Gemini call per market per day)
+                                if market.code not in playbooks:
+                                    # Try DB first (survives process restart)
+                                    stored_pb = playbook_store.load(market_today, market.code)
+                                    if stored_pb is not None:
+                                        playbooks[market.code] = stored_pb
+                                        logger.info(
+                                            "Loaded existing playbook for %s from DB"
+                                            " (%d stocks, %d scenarios)",
+                                            market.code,
+                                            stored_pb.stock_count,
+                                            stored_pb.scenario_count,
+                                        )
+                                    else:
+                                        try:
+                                            pb = await pre_market_planner.generate_playbook(
+                                                market=market.code,
+                                                candidates=candidates,
+                                                today=market_today,
+                                            )
+                                            playbook_store.save(pb)
+                                            playbooks[market.code] = pb
+                                            try:
+                                                await telegram.notify_playbook_generated(
+                                                    market=market.code,
+                                                    stock_count=pb.stock_count,
+                                                    scenario_count=pb.scenario_count,
+                                                    token_count=pb.token_count,
+                                                )
+                                            except Exception as exc:
+                                                logger.warning(
+                                                    "Playbook notification failed: %s", exc
+                                                )
+                                        except Exception as exc:
+                                            logger.error(
+                                                "Playbook generation failed for %s: %s",
+                                                market.code, exc,
+                                            )
+                                            try:
+                                                await telegram.notify_playbook_failed(
+                                                    market=market.code,
+                                                    reason=str(exc)[:200],
+                                                )
+                                            except Exception:
+                                                pass
+                                            playbooks[market.code] = (
+                                                PreMarketPlanner._empty_playbook(
+                                                    market_today, market.code
+                                                )
+                                            )
                             else:
                                 logger.info(
                                     "Smart Scanner: No candidates for %s — no trades", market.name
@@ -933,13 +1220,22 @@ async def run(settings: Settings) -> None:
                         if shutdown.is_set():
                             break
 
+                        # Get playbook for this market
+                        market_playbook = playbooks.get(
+                            market.code,
+                            PreMarketPlanner._empty_playbook(
+                                datetime.now(market.timezone).date(), market.code
+                            ),
+                        )
+
                         # Retry logic for connection errors
                         for attempt in range(1, MAX_CONNECTION_RETRIES + 1):
                             try:
                                 await trading_cycle(
                                     broker,
                                     overseas_broker,
-                                    brain,
+                                    scenario_engine,
+                                    market_playbook,
                                     risk,
                                     db_conn,
                                     decision_logger,
@@ -988,7 +1284,8 @@ async def run(settings: Settings) -> None:
                 metrics = await priority_queue.get_metrics()
                 if metrics.total_enqueued > 0:
                     logger.info(
-                        "Priority queue metrics: enqueued=%d, dequeued=%d, size=%d, timeouts=%d, errors=%d",
+                        "Priority queue metrics: enqueued=%d, dequeued=%d,"
+                        " size=%d, timeouts=%d, errors=%d",
                         metrics.total_enqueued,
                         metrics.total_dequeued,
                         metrics.current_size,

src/notifications/telegram_client.py

@@ -304,6 +304,77 @@ class TelegramClient:
             NotificationMessage(priority=NotificationPriority.MEDIUM, message=message)
         )
 
+    async def notify_playbook_generated(
+        self,
+        market: str,
+        stock_count: int,
+        scenario_count: int,
+        token_count: int,
+    ) -> None:
+        """
+        Notify that a daily playbook was generated.
+
+        Args:
+            market: Market code (e.g., "KR", "US")
+            stock_count: Number of stocks in the playbook
+            scenario_count: Total number of scenarios
+            token_count: Gemini token usage for the playbook
+        """
+        message = (
+            f"<b>Playbook Generated</b>\n"
+            f"Market: {market}\n"
+            f"Stocks: {stock_count}\n"
+            f"Scenarios: {scenario_count}\n"
+            f"Tokens: {token_count}"
+        )
+        await self._send_notification(
+            NotificationMessage(priority=NotificationPriority.MEDIUM, message=message)
+        )
+
+    async def notify_scenario_matched(
+        self,
+        stock_code: str,
+        action: str,
+        condition_summary: str,
+        confidence: float,
+    ) -> None:
+        """
+        Notify that a scenario matched for a stock.
+
+        Args:
+            stock_code: Stock ticker symbol
+            action: Scenario action (BUY/SELL/HOLD/REDUCE_ALL)
+            condition_summary: Short summary of the matched condition
+            confidence: Scenario confidence (0-100)
+        """
+        message = (
+            f"<b>Scenario Matched</b>\n"
+            f"Symbol: <code>{stock_code}</code>\n"
+            f"Action: {action}\n"
+            f"Condition: {condition_summary}\n"
+            f"Confidence: {confidence:.0f}%"
+        )
+        await self._send_notification(
+            NotificationMessage(priority=NotificationPriority.HIGH, message=message)
+        )
+
+    async def notify_playbook_failed(self, market: str, reason: str) -> None:
+        """
+        Notify that playbook generation failed.
+
+        Args:
+            market: Market code (e.g., "KR", "US")
+            reason: Failure reason summary
+        """
+        message = (
+            f"<b>Playbook Failed</b>\n"
+            f"Market: {market}\n"
+            f"Reason: {reason[:200]}"
+        )
+        await self._send_notification(
+            NotificationMessage(priority=NotificationPriority.HIGH, message=message)
+        )
+
     async def notify_system_shutdown(self, reason: str) -> None:
         """
         Notify system shutdown.

src/strategy/pre_market_planner.py

@@ -0,0 +1,420 @@
+"""Pre-market planner — generates DayPlaybook via Gemini before market open.
+
+One Gemini API call per market per day. Candidates come from SmartVolatilityScanner.
+On failure, returns a defensive playbook (all HOLD, no trades).
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+from datetime import date, timedelta
+from typing import Any
+
+from src.analysis.smart_scanner import ScanCandidate
+from src.brain.context_selector import ContextSelector, DecisionType
+from src.brain.gemini_client import GeminiClient
+from src.config import Settings
+from src.context.store import ContextLayer, ContextStore
+from src.strategy.models import (
+    CrossMarketContext,
+    DayPlaybook,
+    GlobalRule,
+    MarketOutlook,
+    ScenarioAction,
+    StockCondition,
+    StockPlaybook,
+    StockScenario,
+)
+
+logger = logging.getLogger(__name__)
+
+# Mapping from string to MarketOutlook enum
+_OUTLOOK_MAP: dict[str, MarketOutlook] = {
+    "bullish": MarketOutlook.BULLISH,
+    "neutral_to_bullish": MarketOutlook.NEUTRAL_TO_BULLISH,
+    "neutral": MarketOutlook.NEUTRAL,
+    "neutral_to_bearish": MarketOutlook.NEUTRAL_TO_BEARISH,
+    "bearish": MarketOutlook.BEARISH,
+}
+
+_ACTION_MAP: dict[str, ScenarioAction] = {
+    "BUY": ScenarioAction.BUY,
+    "SELL": ScenarioAction.SELL,
+    "HOLD": ScenarioAction.HOLD,
+    "REDUCE_ALL": ScenarioAction.REDUCE_ALL,
+}
+
+
+class PreMarketPlanner:
+    """Generates a DayPlaybook by calling Gemini once before market open.
+
+    Flow:
+    1. Collect strategic context (L5-L7) + cross-market context
+    2. Build a structured prompt with scan candidates
+    3. Call Gemini for JSON scenario generation
+    4. Parse and validate response into DayPlaybook
+    5. On failure → defensive playbook (HOLD everything)
+    """
+
+    def __init__(
+        self,
+        gemini_client: GeminiClient,
+        context_store: ContextStore,
+        context_selector: ContextSelector,
+        settings: Settings,
+    ) -> None:
+        self._gemini = gemini_client
+        self._context_store = context_store
+        self._context_selector = context_selector
+        self._settings = settings
+
+    async def generate_playbook(
+        self,
+        market: str,
+        candidates: list[ScanCandidate],
+        today: date | None = None,
+    ) -> DayPlaybook:
+        """Generate a DayPlaybook for a market using Gemini.
+
+        Args:
+            market: Market code ("KR" or "US")
+            candidates: Stock candidates from SmartVolatilityScanner
+            today: Override date (defaults to date.today()). Use market-local date.
+
+        Returns:
+            DayPlaybook with scenarios. Empty/defensive if no candidates or failure.
+        """
+        if today is None:
+            today = date.today()
+
+        if not candidates:
+            logger.info("No candidates for %s — returning empty playbook", market)
+            return self._empty_playbook(today, market)
+
+        try:
+            # 1. Gather context
+            context_data = self._gather_context()
+            cross_market = self.build_cross_market_context(market, today)
+
+            # 2. Build prompt
+            prompt = self._build_prompt(market, candidates, context_data, cross_market)
+
+            # 3. Call Gemini
+            market_data = {
+                "stock_code": "PLANNER",
+                "current_price": 0,
+                "prompt_override": prompt,
+            }
+            decision = await self._gemini.decide(market_data)
+
+            # 4. Parse response
+            playbook = self._parse_response(
+                decision.rationale, today, market, candidates, cross_market
+            )
+            playbook_with_tokens = playbook.model_copy(
+                update={"token_count": decision.token_count}
+            )
+            logger.info(
+                "Generated playbook for %s: %d stocks, %d scenarios, %d tokens",
+                market,
+                playbook_with_tokens.stock_count,
+                playbook_with_tokens.scenario_count,
+                playbook_with_tokens.token_count,
+            )
+            return playbook_with_tokens
+
+        except Exception:
+            logger.exception("Playbook generation failed for %s", market)
+            if self._settings.DEFENSIVE_PLAYBOOK_ON_FAILURE:
+                return self._defensive_playbook(today, market, candidates)
+            return self._empty_playbook(today, market)
+
+    def build_cross_market_context(
+        self, target_market: str, today: date | None = None,
+    ) -> CrossMarketContext | None:
+        """Build cross-market context from the other market's L6 data.
+
+        KR planner → reads US scorecard from previous night.
+        US planner → reads KR scorecard from today.
+
+        Args:
+            target_market: The market being planned ("KR" or "US")
+            today: Override date (defaults to date.today()). Use market-local date.
+        """
+        other_market = "US" if target_market == "KR" else "KR"
+        if today is None:
+            today = date.today()
+        timeframe_date = today - timedelta(days=1) if target_market == "KR" else today
+        timeframe = timeframe_date.isoformat()
+
+        scorecard_key = f"scorecard_{other_market}"
+        scorecard_data = self._context_store.get_context(
+            ContextLayer.L6_DAILY, timeframe, scorecard_key
+        )
+
+        if scorecard_data is None:
+            logger.debug("No cross-market scorecard found for %s", other_market)
+            return None
+
+        if isinstance(scorecard_data, str):
+            try:
+                scorecard_data = json.loads(scorecard_data)
+            except (json.JSONDecodeError, TypeError):
+                return None
+
+        if not isinstance(scorecard_data, dict):
+            return None
+
+        return CrossMarketContext(
+            market=other_market,
+            date=timeframe,
+            total_pnl=float(scorecard_data.get("total_pnl", 0.0)),
+            win_rate=float(scorecard_data.get("win_rate", 0.0)),
+            index_change_pct=float(scorecard_data.get("index_change_pct", 0.0)),
+            key_events=scorecard_data.get("key_events", []),
+            lessons=scorecard_data.get("lessons", []),
+        )
+
+    def _gather_context(self) -> dict[str, Any]:
+        """Gather strategic context using ContextSelector."""
+        layers = self._context_selector.select_layers(
+            decision_type=DecisionType.STRATEGIC,
+            include_realtime=True,
+        )
+        return self._context_selector.get_context_data(layers, max_items_per_layer=10)
+
+    def _build_prompt(
+        self,
+        market: str,
+        candidates: list[ScanCandidate],
+        context_data: dict[str, Any],
+        cross_market: CrossMarketContext | None,
+    ) -> str:
+        """Build a structured prompt for Gemini to generate scenario JSON."""
+        max_scenarios = self._settings.MAX_SCENARIOS_PER_STOCK
+
+        candidates_text = "\n".join(
+            f"  - {c.stock_code} ({c.name}): price={c.price}, "
+            f"RSI={c.rsi:.1f}, volume_ratio={c.volume_ratio:.1f}, "
+            f"signal={c.signal}, score={c.score:.1f}"
+            for c in candidates
+        )
+
+        cross_market_text = ""
+        if cross_market:
+            cross_market_text = (
+                f"\n## Other Market ({cross_market.market}) Summary\n"
+                f"- P&L: {cross_market.total_pnl:+.2f}%\n"
+                f"- Win Rate: {cross_market.win_rate:.0f}%\n"
+                f"- Index Change: {cross_market.index_change_pct:+.2f}%\n"
+            )
+            if cross_market.lessons:
+                cross_market_text += f"- Lessons: {'; '.join(cross_market.lessons[:3])}\n"
+
+        context_text = ""
+        if context_data:
+            context_text = "\n## Strategic Context\n"
+            for layer_name, layer_data in context_data.items():
+                if layer_data:
+                    context_text += f"### {layer_name}\n"
+                    for key, value in list(layer_data.items())[:5]:
+                        context_text += f"  - {key}: {value}\n"
+
+        return (
+            f"You are a pre-market trading strategist for the {market} market.\n"
+            f"Generate structured trading scenarios for today.\n\n"
+            f"## Candidates (from volatility scanner)\n{candidates_text}\n"
+            f"{cross_market_text}"
+            f"{context_text}\n"
+            f"## Instructions\n"
+            f"Return a JSON object with this exact structure:\n"
+            f'{{\n'
+            f'  "market_outlook": "bullish|neutral_to_bullish|neutral'
+            f'|neutral_to_bearish|bearish",\n'
+            f'  "global_rules": [\n'
+            f'    {{"condition": "portfolio_pnl_pct < -2.0",'
+            f' "action": "REDUCE_ALL", "rationale": "..."}}\n'
+            f'  ],\n'
+            f'  "stocks": [\n'
+            f'    {{\n'
+            f'      "stock_code": "...",\n'
+            f'      "scenarios": [\n'
+            f'        {{\n'
+            f'          "condition": {{"rsi_below": 30, "volume_ratio_above": 2.0}},\n'
+            f'          "action": "BUY|SELL|HOLD",\n'
+            f'          "confidence": 85,\n'
+            f'          "allocation_pct": 10.0,\n'
+            f'          "stop_loss_pct": -2.0,\n'
+            f'          "take_profit_pct": 3.0,\n'
+            f'          "rationale": "..."\n'
+            f'        }}\n'
+            f'      ]\n'
+            f'    }}\n'
+            f'  ]\n'
+            f'}}\n\n'
+            f"Rules:\n"
+            f"- Max {max_scenarios} scenarios per stock\n"
+            f"- Only use stocks from the candidates list\n"
+            f"- Confidence 0-100 (80+ for actionable trades)\n"
+            f"- stop_loss_pct must be <= 0, take_profit_pct must be >= 0\n"
+            f"- Return ONLY the JSON, no markdown fences or explanation\n"
+        )
+
+    def _parse_response(
+        self,
+        response_text: str,
+        today: date,
+        market: str,
+        candidates: list[ScanCandidate],
+        cross_market: CrossMarketContext | None,
+    ) -> DayPlaybook:
+        """Parse Gemini's JSON response into a validated DayPlaybook."""
+        cleaned = self._extract_json(response_text)
+        data = json.loads(cleaned)
+
+        valid_codes = {c.stock_code for c in candidates}
+
+        # Parse market outlook
+        outlook_str = data.get("market_outlook", "neutral")
+        market_outlook = _OUTLOOK_MAP.get(outlook_str, MarketOutlook.NEUTRAL)
+
+        # Parse global rules
+        global_rules = []
+        for rule_data in data.get("global_rules", []):
+            action_str = rule_data.get("action", "HOLD")
+            action = _ACTION_MAP.get(action_str, ScenarioAction.HOLD)
+            global_rules.append(
+                GlobalRule(
+                    condition=rule_data.get("condition", ""),
+                    action=action,
+                    rationale=rule_data.get("rationale", ""),
+                )
+            )
+
+        # Parse stock playbooks
+        stock_playbooks = []
+        max_scenarios = self._settings.MAX_SCENARIOS_PER_STOCK
+        for stock_data in data.get("stocks", []):
+            code = stock_data.get("stock_code", "")
+            if code not in valid_codes:
+                logger.warning("Gemini returned unknown stock %s — skipping", code)
+                continue
+
+            scenarios = []
+            for sc_data in stock_data.get("scenarios", [])[:max_scenarios]:
+                scenario = self._parse_scenario(sc_data)
+                if scenario:
+                    scenarios.append(scenario)
+
+            if scenarios:
+                stock_playbooks.append(
+                    StockPlaybook(
+                        stock_code=code,
+                        scenarios=scenarios,
+                    )
+                )
+
+        return DayPlaybook(
+            date=today,
+            market=market,
+            market_outlook=market_outlook,
+            global_rules=global_rules,
+            stock_playbooks=stock_playbooks,
+            cross_market=cross_market,
+        )
+
+    def _parse_scenario(self, sc_data: dict) -> StockScenario | None:
+        """Parse a single scenario from JSON data. Returns None if invalid."""
+        try:
+            cond_data = sc_data.get("condition", {})
+            condition = StockCondition(
+                rsi_below=cond_data.get("rsi_below"),
+                rsi_above=cond_data.get("rsi_above"),
+                volume_ratio_above=cond_data.get("volume_ratio_above"),
+                volume_ratio_below=cond_data.get("volume_ratio_below"),
+                price_above=cond_data.get("price_above"),
+                price_below=cond_data.get("price_below"),
+                price_change_pct_above=cond_data.get("price_change_pct_above"),
+                price_change_pct_below=cond_data.get("price_change_pct_below"),
+            )
+
+            if not condition.has_any_condition():
+                logger.warning("Scenario has no conditions — skipping")
+                return None
+
+            action_str = sc_data.get("action", "HOLD")
+            action = _ACTION_MAP.get(action_str, ScenarioAction.HOLD)
+
+            return StockScenario(
+                condition=condition,
+                action=action,
+                confidence=int(sc_data.get("confidence", 50)),
+                allocation_pct=float(sc_data.get("allocation_pct", 10.0)),
+                stop_loss_pct=float(sc_data.get("stop_loss_pct", -2.0)),
+                take_profit_pct=float(sc_data.get("take_profit_pct", 3.0)),
+                rationale=sc_data.get("rationale", ""),
+            )
+        except (ValueError, TypeError) as e:
+            logger.warning("Failed to parse scenario: %s", e)
+            return None
+
+    @staticmethod
+    def _extract_json(text: str) -> str:
+        """Extract JSON from response, stripping markdown fences if present."""
+        stripped = text.strip()
+        if stripped.startswith("```"):
+            # Remove first line (```json or ```) and last line (```)
+            lines = stripped.split("\n")
+            lines = lines[1:]  # Remove opening fence
+            if lines and lines[-1].strip() == "```":
+                lines = lines[:-1]
+            stripped = "\n".join(lines)
+        return stripped.strip()
+
+    @staticmethod
+    def _empty_playbook(today: date, market: str) -> DayPlaybook:
+        """Return an empty playbook (no stocks, no scenarios)."""
+        return DayPlaybook(
+            date=today,
+            market=market,
+            market_outlook=MarketOutlook.NEUTRAL,
+            stock_playbooks=[],
+        )
+
+    @staticmethod
+    def _defensive_playbook(
+        today: date,
+        market: str,
+        candidates: list[ScanCandidate],
+    ) -> DayPlaybook:
+        """Return a defensive playbook — HOLD everything with stop-loss ready."""
+        stock_playbooks = [
+            StockPlaybook(
+                stock_code=c.stock_code,
+                scenarios=[
+                    StockScenario(
+                        condition=StockCondition(price_change_pct_below=-3.0),
+                        action=ScenarioAction.SELL,
+                        confidence=90,
+                        stop_loss_pct=-3.0,
+                        rationale="Defensive stop-loss (planner failure)",
+                    ),
+                ],
+            )
+            for c in candidates
+        ]
+        return DayPlaybook(
+            date=today,
+            market=market,
+            market_outlook=MarketOutlook.NEUTRAL_TO_BEARISH,
+            default_action=ScenarioAction.HOLD,
+            stock_playbooks=stock_playbooks,
+            global_rules=[
+                GlobalRule(
+                    condition="portfolio_pnl_pct < -2.0",
+                    action=ScenarioAction.REDUCE_ALL,
+                    rationale="Defensive: reduce on loss threshold",
+                ),
+            ],
+        )

tests/test_context.py

@@ -161,7 +161,7 @@ class TestContextAggregator:
         self, aggregator: ContextAggregator, db_conn: sqlite3.Connection
     ) -> None:
         """Test aggregating daily metrics from trades."""
-        date = "2026-02-04"
+        date = datetime.now(UTC).date().isoformat()
 
         # Create sample trades
         log_trade(db_conn, "005930", "BUY", 85, "Good signal", quantity=10, price=70000, pnl=500)
@@ -175,36 +175,44 @@ class TestContextAggregator:
         db_conn.commit()
 
         # Aggregate
-        aggregator.aggregate_daily_from_trades(date)
+        aggregator.aggregate_daily_from_trades(date, market="KR")
 
         # Verify L6 contexts
         store = aggregator.store
-        assert store.get_context(ContextLayer.L6_DAILY, date, "trade_count") == 3
+        assert store.get_context(ContextLayer.L6_DAILY, date, "trade_count_KR") == 3
-        assert store.get_context(ContextLayer.L6_DAILY, date, "buys") == 1
+        assert store.get_context(ContextLayer.L6_DAILY, date, "buys_KR") == 1
-        assert store.get_context(ContextLayer.L6_DAILY, date, "sells") == 1
+        assert store.get_context(ContextLayer.L6_DAILY, date, "sells_KR") == 1
-        assert store.get_context(ContextLayer.L6_DAILY, date, "holds") == 1
+        assert store.get_context(ContextLayer.L6_DAILY, date, "holds_KR") == 1
-        assert store.get_context(ContextLayer.L6_DAILY, date, "total_pnl") == 2000.0
+        assert store.get_context(ContextLayer.L6_DAILY, date, "total_pnl_KR") == 2000.0
-        assert store.get_context(ContextLayer.L6_DAILY, date, "unique_stocks") == 3
+        assert store.get_context(ContextLayer.L6_DAILY, date, "unique_stocks_KR") == 3
         # 2 wins, 0 losses
-        assert store.get_context(ContextLayer.L6_DAILY, date, "win_rate") == 100.0
+        assert store.get_context(ContextLayer.L6_DAILY, date, "win_rate_KR") == 100.0
 
     def test_aggregate_weekly_from_daily(self, aggregator: ContextAggregator) -> None:
         """Test aggregating weekly metrics from daily."""
         week = "2026-W06"
 
         # Set daily contexts
-        aggregator.store.set_context(ContextLayer.L6_DAILY, "2026-02-02", "total_pnl", 100.0)
+        aggregator.store.set_context(
-        aggregator.store.set_context(ContextLayer.L6_DAILY, "2026-02-03", "total_pnl", 200.0)
+            ContextLayer.L6_DAILY, "2026-02-02", "total_pnl_KR", 100.0
-        aggregator.store.set_context(ContextLayer.L6_DAILY, "2026-02-02", "avg_confidence", 80.0)
+        )
-        aggregator.store.set_context(ContextLayer.L6_DAILY, "2026-02-03", "avg_confidence", 85.0)
+        aggregator.store.set_context(
+            ContextLayer.L6_DAILY, "2026-02-03", "total_pnl_KR", 200.0
+        )
+        aggregator.store.set_context(
+            ContextLayer.L6_DAILY, "2026-02-02", "avg_confidence_KR", 80.0
+        )
+        aggregator.store.set_context(
+            ContextLayer.L6_DAILY, "2026-02-03", "avg_confidence_KR", 85.0
+        )
 
         # Aggregate
         aggregator.aggregate_weekly_from_daily(week)
 
         # Verify L5 contexts
         store = aggregator.store
-        weekly_pnl = store.get_context(ContextLayer.L5_WEEKLY, week, "weekly_pnl")
+        weekly_pnl = store.get_context(ContextLayer.L5_WEEKLY, week, "weekly_pnl_KR")
-        avg_conf = store.get_context(ContextLayer.L5_WEEKLY, week, "avg_confidence")
+        avg_conf = store.get_context(ContextLayer.L5_WEEKLY, week, "avg_confidence_KR")
 
         assert weekly_pnl == 300.0
         assert avg_conf == 82.5
@@ -214,9 +222,15 @@ class TestContextAggregator:
         month = "2026-02"
 
         # Set weekly contexts
-        aggregator.store.set_context(ContextLayer.L5_WEEKLY, "2026-W05", "weekly_pnl", 100.0)
+        aggregator.store.set_context(
-        aggregator.store.set_context(ContextLayer.L5_WEEKLY, "2026-W06", "weekly_pnl", 200.0)
+            ContextLayer.L5_WEEKLY, "2026-W05", "weekly_pnl_KR", 100.0
-        aggregator.store.set_context(ContextLayer.L5_WEEKLY, "2026-W07", "weekly_pnl", 150.0)
+        )
+        aggregator.store.set_context(
+            ContextLayer.L5_WEEKLY, "2026-W06", "weekly_pnl_KR", 200.0
+        )
+        aggregator.store.set_context(
+            ContextLayer.L5_WEEKLY, "2026-W07", "weekly_pnl_KR", 150.0
+        )
 
         # Aggregate
         aggregator.aggregate_monthly_from_weekly(month)
@@ -285,7 +299,7 @@ class TestContextAggregator:
         self, aggregator: ContextAggregator, db_conn: sqlite3.Connection
     ) -> None:
         """Test running all aggregations from L7 to L1."""
-        date = "2026-02-04"
+        date = datetime.now(UTC).date().isoformat()
 
         # Create sample trades
         log_trade(db_conn, "005930", "BUY", 85, "Good signal", quantity=10, price=70000, pnl=1000)
@@ -299,10 +313,18 @@ class TestContextAggregator:
 
         # Verify data exists in each layer
         store = aggregator.store
-        assert store.get_context(ContextLayer.L6_DAILY, date, "total_pnl") == 1000.0
+        assert store.get_context(ContextLayer.L6_DAILY, date, "total_pnl_KR") == 1000.0
-        current_week = datetime.now(UTC).strftime("%Y-W%V")
+        from datetime import date as date_cls
-        assert store.get_context(ContextLayer.L5_WEEKLY, current_week, "weekly_pnl") is not None
+        trade_date = date_cls.fromisoformat(date)
-        # Further layers depend on time alignment, just verify no crashes
+        iso_year, iso_week, _ = trade_date.isocalendar()
+        trade_week = f"{iso_year}-W{iso_week:02d}"
+        assert store.get_context(ContextLayer.L5_WEEKLY, trade_week, "weekly_pnl_KR") is not None
+        trade_month = f"{trade_date.year}-{trade_date.month:02d}"
+        trade_quarter = f"{trade_date.year}-Q{(trade_date.month - 1) // 3 + 1}"
+        trade_year = str(trade_date.year)
+        assert store.get_context(ContextLayer.L4_MONTHLY, trade_month, "monthly_pnl") == 1000.0
+        assert store.get_context(ContextLayer.L3_QUARTERLY, trade_quarter, "quarterly_pnl") == 1000.0
+        assert store.get_context(ContextLayer.L2_ANNUAL, trade_year, "annual_pnl") == 1000.0
 
 
 class TestLayerMetadata:

tests/test_context_scheduler.py

@@ -0,0 +1,104 @@
+"""Tests for ContextScheduler."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from datetime import UTC, datetime
+
+from src.context.scheduler import ContextScheduler
+
+
+@dataclass
+class StubAggregator:
+    """Stub aggregator that records calls."""
+
+    weekly_calls: list[str]
+    monthly_calls: list[str]
+    quarterly_calls: list[str]
+    annual_calls: list[str]
+    legacy_calls: int
+
+    def aggregate_weekly_from_daily(self, week: str) -> None:
+        self.weekly_calls.append(week)
+
+    def aggregate_monthly_from_weekly(self, month: str) -> None:
+        self.monthly_calls.append(month)
+
+    def aggregate_quarterly_from_monthly(self, quarter: str) -> None:
+        self.quarterly_calls.append(quarter)
+
+    def aggregate_annual_from_quarterly(self, year: str) -> None:
+        self.annual_calls.append(year)
+
+    def aggregate_legacy_from_annual(self) -> None:
+        self.legacy_calls += 1
+
+
+@dataclass
+class StubStore:
+    """Stub store that records cleanup calls."""
+
+    cleanup_calls: int = 0
+
+    def cleanup_expired_contexts(self) -> None:
+        self.cleanup_calls += 1
+
+
+def make_scheduler() -> tuple[ContextScheduler, StubAggregator, StubStore]:
+    aggregator = StubAggregator([], [], [], [], 0)
+    store = StubStore()
+    scheduler = ContextScheduler(aggregator=aggregator, store=store)
+    return scheduler, aggregator, store
+
+
+def test_run_if_due_weekly() -> None:
+    scheduler, aggregator, store = make_scheduler()
+    now = datetime(2026, 2, 8, 10, 0, tzinfo=UTC)  # Sunday
+
+    result = scheduler.run_if_due(now)
+
+    assert result.weekly is True
+    assert aggregator.weekly_calls == ["2026-W06"]
+    assert store.cleanup_calls == 1
+
+
+def test_run_if_due_monthly() -> None:
+    scheduler, aggregator, _store = make_scheduler()
+    now = datetime(2026, 2, 28, 12, 0, tzinfo=UTC)  # Last day of month
+
+    result = scheduler.run_if_due(now)
+
+    assert result.monthly is True
+    assert aggregator.monthly_calls == ["2026-02"]
+
+
+def test_run_if_due_quarterly() -> None:
+    scheduler, aggregator, _store = make_scheduler()
+    now = datetime(2026, 3, 31, 12, 0, tzinfo=UTC)  # Last day of Q1
+
+    result = scheduler.run_if_due(now)
+
+    assert result.quarterly is True
+    assert aggregator.quarterly_calls == ["2026-Q1"]
+
+
+def test_run_if_due_annual_and_legacy() -> None:
+    scheduler, aggregator, _store = make_scheduler()
+    now = datetime(2026, 12, 31, 12, 0, tzinfo=UTC)
+
+    result = scheduler.run_if_due(now)
+
+    assert result.annual is True
+    assert result.legacy is True
+    assert aggregator.annual_calls == ["2026"]
+    assert aggregator.legacy_calls == 1
+
+
+def test_cleanup_runs_once_per_day() -> None:
+    scheduler, _aggregator, store = make_scheduler()
+    now = datetime(2026, 2, 9, 9, 0, tzinfo=UTC)
+
+    scheduler.run_if_due(now)
+    scheduler.run_if_due(now)
+
+    assert store.cleanup_calls == 1

tests/test_daily_review.py

@@ -0,0 +1,383 @@
+"""Tests for DailyReviewer."""
+
+from __future__ import annotations
+
+import json
+import sqlite3
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from src.context.layer import ContextLayer
+from src.context.store import ContextStore
+from src.db import init_db, log_trade
+from src.evolution.daily_review import DailyReviewer
+from src.evolution.scorecard import DailyScorecard
+from src.logging.decision_logger import DecisionLogger
+
+
+@pytest.fixture
+def db_conn() -> sqlite3.Connection:
+    return init_db(":memory:")
+
+
+@pytest.fixture
+def context_store(db_conn: sqlite3.Connection) -> ContextStore:
+    return ContextStore(db_conn)
+
+
+def _log_decision(
+    logger: DecisionLogger,
+    *,
+    stock_code: str,
+    market: str,
+    action: str,
+    confidence: int,
+    scenario_match: dict[str, float] | None = None,
+) -> str:
+    return logger.log_decision(
+        stock_code=stock_code,
+        market=market,
+        exchange_code="KRX" if market == "KR" else "NASDAQ",
+        action=action,
+        confidence=confidence,
+        rationale="test",
+        context_snapshot={"scenario_match": scenario_match or {}},
+        input_data={"stock_code": stock_code},
+    )
+
+
+def test_generate_scorecard_market_scoped(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store)
+    logger = DecisionLogger(db_conn)
+
+    buy_id = _log_decision(
+        logger,
+        stock_code="005930",
+        market="KR",
+        action="BUY",
+        confidence=90,
+        scenario_match={"rsi": 29.0},
+    )
+    _log_decision(
+        logger,
+        stock_code="000660",
+        market="KR",
+        action="HOLD",
+        confidence=60,
+    )
+    _log_decision(
+        logger,
+        stock_code="AAPL",
+        market="US",
+        action="SELL",
+        confidence=80,
+        scenario_match={"volume_ratio": 2.1},
+    )
+
+    log_trade(
+        db_conn,
+        "005930",
+        "BUY",
+        90,
+        "buy",
+        quantity=1,
+        price=100.0,
+        pnl=10.0,
+        market="KR",
+        exchange_code="KRX",
+        decision_id=buy_id,
+    )
+    log_trade(
+        db_conn,
+        "000660",
+        "HOLD",
+        60,
+        "hold",
+        quantity=0,
+        price=0.0,
+        pnl=0.0,
+        market="KR",
+        exchange_code="KRX",
+    )
+    log_trade(
+        db_conn,
+        "AAPL",
+        "SELL",
+        80,
+        "sell",
+        quantity=1,
+        price=200.0,
+        pnl=-5.0,
+        market="US",
+        exchange_code="NASDAQ",
+    )
+
+    scorecard = reviewer.generate_scorecard("2026-02-14", "KR")
+
+    assert scorecard.market == "KR"
+    assert scorecard.total_decisions == 2
+    assert scorecard.buys == 1
+    assert scorecard.sells == 0
+    assert scorecard.holds == 1
+    assert scorecard.total_pnl == 10.0
+    assert scorecard.win_rate == 100.0
+    assert scorecard.avg_confidence == 75.0
+    assert scorecard.scenario_match_rate == 50.0
+
+
+def test_generate_scorecard_top_winners_and_losers(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store)
+    logger = DecisionLogger(db_conn)
+
+    for code, pnl in [("005930", 30.0), ("000660", 10.0), ("035420", -15.0), ("051910", -5.0)]:
+        decision_id = _log_decision(
+            logger,
+            stock_code=code,
+            market="KR",
+            action="BUY" if pnl >= 0 else "SELL",
+            confidence=80,
+            scenario_match={"rsi": 30.0},
+        )
+        log_trade(
+            db_conn,
+            code,
+            "BUY" if pnl >= 0 else "SELL",
+            80,
+            "test",
+            quantity=1,
+            price=100.0,
+            pnl=pnl,
+            market="KR",
+            exchange_code="KRX",
+            decision_id=decision_id,
+        )
+
+    scorecard = reviewer.generate_scorecard("2026-02-14", "KR")
+    assert scorecard.top_winners == ["005930", "000660"]
+    assert scorecard.top_losers == ["035420", "051910"]
+
+
+def test_generate_scorecard_empty_day(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store)
+    scorecard = reviewer.generate_scorecard("2026-02-14", "KR")
+
+    assert scorecard.total_decisions == 0
+    assert scorecard.total_pnl == 0.0
+    assert scorecard.win_rate == 0.0
+    assert scorecard.avg_confidence == 0.0
+    assert scorecard.scenario_match_rate == 0.0
+    assert scorecard.top_winners == []
+    assert scorecard.top_losers == []
+
+
+@pytest.mark.asyncio
+async def test_generate_lessons_without_gemini_returns_empty(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store, gemini_client=None)
+    lessons = await reviewer.generate_lessons(
+        DailyScorecard(
+            date="2026-02-14",
+            market="KR",
+            total_decisions=1,
+            buys=1,
+            sells=0,
+            holds=0,
+            total_pnl=5.0,
+            win_rate=100.0,
+            avg_confidence=90.0,
+            scenario_match_rate=100.0,
+        )
+    )
+    assert lessons == []
+
+
+@pytest.mark.asyncio
+async def test_generate_lessons_parses_json_array(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    mock_gemini = MagicMock()
+    mock_gemini.decide = AsyncMock(
+        return_value=SimpleNamespace(rationale='["Cut losers earlier", "Reduce midday churn"]')
+    )
+    reviewer = DailyReviewer(db_conn, context_store, gemini_client=mock_gemini)
+
+    lessons = await reviewer.generate_lessons(
+        DailyScorecard(
+            date="2026-02-14",
+            market="KR",
+            total_decisions=3,
+            buys=1,
+            sells=1,
+            holds=1,
+            total_pnl=-2.5,
+            win_rate=50.0,
+            avg_confidence=70.0,
+            scenario_match_rate=66.7,
+        )
+    )
+    assert lessons == ["Cut losers earlier", "Reduce midday churn"]
+
+
+@pytest.mark.asyncio
+async def test_generate_lessons_fallback_to_lines(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    mock_gemini = MagicMock()
+    mock_gemini.decide = AsyncMock(
+        return_value=SimpleNamespace(rationale="- Keep risk tighter\n- Increase selectivity")
+    )
+    reviewer = DailyReviewer(db_conn, context_store, gemini_client=mock_gemini)
+
+    lessons = await reviewer.generate_lessons(
+        DailyScorecard(
+            date="2026-02-14",
+            market="US",
+            total_decisions=2,
+            buys=1,
+            sells=1,
+            holds=0,
+            total_pnl=1.0,
+            win_rate=50.0,
+            avg_confidence=75.0,
+            scenario_match_rate=100.0,
+        )
+    )
+    assert lessons == ["Keep risk tighter", "Increase selectivity"]
+
+
+@pytest.mark.asyncio
+async def test_generate_lessons_handles_gemini_error(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    mock_gemini = MagicMock()
+    mock_gemini.decide = AsyncMock(side_effect=RuntimeError("boom"))
+    reviewer = DailyReviewer(db_conn, context_store, gemini_client=mock_gemini)
+
+    lessons = await reviewer.generate_lessons(
+        DailyScorecard(
+            date="2026-02-14",
+            market="US",
+            total_decisions=0,
+            buys=0,
+            sells=0,
+            holds=0,
+            total_pnl=0.0,
+            win_rate=0.0,
+            avg_confidence=0.0,
+            scenario_match_rate=0.0,
+        )
+    )
+    assert lessons == []
+
+
+def test_store_scorecard_in_context(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store)
+    scorecard = DailyScorecard(
+        date="2026-02-14",
+        market="KR",
+        total_decisions=5,
+        buys=2,
+        sells=1,
+        holds=2,
+        total_pnl=15.0,
+        win_rate=66.67,
+        avg_confidence=82.0,
+        scenario_match_rate=80.0,
+        lessons=["Keep position sizing stable"],
+        cross_market_note="US risk-off",
+    )
+
+    reviewer.store_scorecard_in_context(scorecard)
+
+    stored = context_store.get_context(
+        ContextLayer.L6_DAILY,
+        "2026-02-14",
+        "scorecard_KR",
+    )
+    assert stored is not None
+    assert stored["market"] == "KR"
+    assert stored["total_pnl"] == 15.0
+    assert stored["lessons"] == ["Keep position sizing stable"]
+
+
+def test_store_scorecard_key_is_market_scoped(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store)
+    kr = DailyScorecard(
+        date="2026-02-14",
+        market="KR",
+        total_decisions=1,
+        buys=1,
+        sells=0,
+        holds=0,
+        total_pnl=1.0,
+        win_rate=100.0,
+        avg_confidence=90.0,
+        scenario_match_rate=100.0,
+    )
+    us = DailyScorecard(
+        date="2026-02-14",
+        market="US",
+        total_decisions=1,
+        buys=0,
+        sells=1,
+        holds=0,
+        total_pnl=-1.0,
+        win_rate=0.0,
+        avg_confidence=70.0,
+        scenario_match_rate=100.0,
+    )
+
+    reviewer.store_scorecard_in_context(kr)
+    reviewer.store_scorecard_in_context(us)
+
+    kr_ctx = context_store.get_context(ContextLayer.L6_DAILY, "2026-02-14", "scorecard_KR")
+    us_ctx = context_store.get_context(ContextLayer.L6_DAILY, "2026-02-14", "scorecard_US")
+
+    assert kr_ctx["market"] == "KR"
+    assert us_ctx["market"] == "US"
+    assert kr_ctx["total_pnl"] == 1.0
+    assert us_ctx["total_pnl"] == -1.0
+
+
+def test_generate_scorecard_handles_invalid_context_snapshot(
+    db_conn: sqlite3.Connection, context_store: ContextStore,
+) -> None:
+    reviewer = DailyReviewer(db_conn, context_store)
+    db_conn.execute(
+        """
+        INSERT INTO decision_logs (
+            decision_id, timestamp, stock_code, market, exchange_code,
+            action, confidence, rationale, context_snapshot, input_data
+        ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+        """,
+        (
+            "d1",
+            "2026-02-14T09:00:00+00:00",
+            "005930",
+            "KR",
+            "KRX",
+            "HOLD",
+            50,
+            "test",
+            "{invalid_json",
+            json.dumps({}),
+        ),
+    )
+    db_conn.commit()
+
+    scorecard = reviewer.generate_scorecard("2026-02-14", "KR")
+    assert scorecard.total_decisions == 1
+    assert scorecard.scenario_match_rate == 0.0

tests/test_main.py

@@ -1,12 +1,61 @@
-"""Tests for main trading loop telegram integration."""
+"""Tests for main trading loop integration."""
 
-import asyncio
+from datetime import UTC, date
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import ANY, AsyncMock, MagicMock, patch
 
 import pytest
 
+from src.context.layer import ContextLayer
 from src.core.risk_manager import CircuitBreakerTripped, FatFingerRejected
-from src.main import safe_float, trading_cycle
+from src.db import init_db, log_trade
+from src.evolution.scorecard import DailyScorecard
+from src.logging.decision_logger import DecisionLogger
+from src.main import _handle_market_close, safe_float, trading_cycle
+from src.strategy.models import (
+    DayPlaybook,
+    ScenarioAction,
+    StockCondition,
+    StockScenario,
+)
+from src.strategy.scenario_engine import ScenarioEngine, ScenarioMatch
+
+
+def _make_playbook(market: str = "KR") -> DayPlaybook:
+    """Create a minimal empty playbook for testing."""
+    return DayPlaybook(date=date(2026, 2, 8), market=market)
+
+
+def _make_buy_match(stock_code: str = "005930") -> ScenarioMatch:
+    """Create a ScenarioMatch that returns BUY."""
+    return ScenarioMatch(
+        stock_code=stock_code,
+        matched_scenario=None,
+        action=ScenarioAction.BUY,
+        confidence=85,
+        rationale="Test buy",
+    )
+
+
+def _make_hold_match(stock_code: str = "005930") -> ScenarioMatch:
+    """Create a ScenarioMatch that returns HOLD."""
+    return ScenarioMatch(
+        stock_code=stock_code,
+        matched_scenario=None,
+        action=ScenarioAction.HOLD,
+        confidence=0,
+        rationale="No scenario conditions met",
+    )
+
+
+def _make_sell_match(stock_code: str = "005930") -> ScenarioMatch:
+    """Create a ScenarioMatch that returns SELL."""
+    return ScenarioMatch(
+        stock_code=stock_code,
+        matched_scenario=None,
+        action=ScenarioAction.SELL,
+        confidence=90,
+        rationale="Test sell",
+    )
 
 
 class TestSafeFloat:
@@ -81,15 +130,16 @@ class TestTradingCycleTelegramIntegration:
         return broker
 
     @pytest.fixture
-    def mock_brain(self) -> MagicMock:
+    def mock_scenario_engine(self) -> MagicMock:
-        """Create mock brain that decides to buy."""
+        """Create mock scenario engine that returns BUY."""
-        brain = MagicMock()
+        engine = MagicMock(spec=ScenarioEngine)
-        decision = MagicMock()
+        engine.evaluate = MagicMock(return_value=_make_buy_match())
-        decision.action = "BUY"
+        return engine
-        decision.confidence = 85
+
-        decision.rationale = "Test buy"
+    @pytest.fixture
-        brain.decide = AsyncMock(return_value=decision)
+    def mock_playbook(self) -> DayPlaybook:
-        return brain
+        """Create a minimal day playbook."""
+        return _make_playbook()
 
     @pytest.fixture
     def mock_risk(self) -> MagicMock:
@@ -134,6 +184,7 @@ class TestTradingCycleTelegramIntegration:
         telegram.notify_trade_execution = AsyncMock()
         telegram.notify_fat_finger = AsyncMock()
         telegram.notify_circuit_breaker = AsyncMock()
+        telegram.notify_scenario_matched = AsyncMock()
         return telegram
 
     @pytest.fixture
@@ -151,7 +202,8 @@ class TestTradingCycleTelegramIntegration:
         self,
         mock_broker: MagicMock,
         mock_overseas_broker: MagicMock,
-        mock_brain: MagicMock,
+        mock_scenario_engine: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -165,7 +217,8 @@ class TestTradingCycleTelegramIntegration:
             await trading_cycle(
                 broker=mock_broker,
                 overseas_broker=mock_overseas_broker,
-                brain=mock_brain,
+                scenario_engine=mock_scenario_engine,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -190,7 +243,8 @@ class TestTradingCycleTelegramIntegration:
         self,
         mock_broker: MagicMock,
         mock_overseas_broker: MagicMock,
-        mock_brain: MagicMock,
+        mock_scenario_engine: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -208,7 +262,8 @@ class TestTradingCycleTelegramIntegration:
             await trading_cycle(
                 broker=mock_broker,
                 overseas_broker=mock_overseas_broker,
-                brain=mock_brain,
+                scenario_engine=mock_scenario_engine,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -228,7 +283,8 @@ class TestTradingCycleTelegramIntegration:
         self,
         mock_broker: MagicMock,
         mock_overseas_broker: MagicMock,
-        mock_brain: MagicMock,
+        mock_scenario_engine: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -250,7 +306,8 @@ class TestTradingCycleTelegramIntegration:
                 await trading_cycle(
                     broker=mock_broker,
                     overseas_broker=mock_overseas_broker,
-                    brain=mock_brain,
+                    scenario_engine=mock_scenario_engine,
+                    playbook=mock_playbook,
                     risk=mock_risk,
                     db_conn=mock_db,
                     decision_logger=mock_decision_logger,
@@ -275,7 +332,8 @@ class TestTradingCycleTelegramIntegration:
         self,
         mock_broker: MagicMock,
         mock_overseas_broker: MagicMock,
-        mock_brain: MagicMock,
+        mock_scenario_engine: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -299,7 +357,8 @@ class TestTradingCycleTelegramIntegration:
                 await trading_cycle(
                     broker=mock_broker,
                     overseas_broker=mock_overseas_broker,
-                    brain=mock_brain,
+                    scenario_engine=mock_scenario_engine,
+                    playbook=mock_playbook,
                     risk=mock_risk,
                     db_conn=mock_db,
                     decision_logger=mock_decision_logger,
@@ -319,7 +378,8 @@ class TestTradingCycleTelegramIntegration:
         self,
         mock_broker: MagicMock,
         mock_overseas_broker: MagicMock,
-        mock_brain: MagicMock,
+        mock_scenario_engine: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -329,18 +389,15 @@ class TestTradingCycleTelegramIntegration:
         mock_market: MagicMock,
     ) -> None:
         """Test no trade notification sent when decision is HOLD."""
-        # Change brain decision to HOLD
+        # Scenario engine returns HOLD
-        decision = MagicMock()
+        mock_scenario_engine.evaluate = MagicMock(return_value=_make_hold_match())
-        decision.action = "HOLD"
-        decision.confidence = 50
-        decision.rationale = "Insufficient signal"
-        mock_brain.decide = AsyncMock(return_value=decision)
 
         with patch("src.main.log_trade"):
             await trading_cycle(
                 broker=mock_broker,
                 overseas_broker=mock_overseas_broker,
-                brain=mock_brain,
+                scenario_engine=mock_scenario_engine,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -472,15 +529,16 @@ class TestOverseasBalanceParsing:
         return market
 
     @pytest.fixture
-    def mock_brain_hold(self) -> MagicMock:
+    def mock_scenario_engine_hold(self) -> MagicMock:
-        """Create mock brain that always holds."""
+        """Create mock scenario engine that always returns HOLD."""
-        brain = MagicMock()
+        engine = MagicMock(spec=ScenarioEngine)
-        decision = MagicMock()
+        engine.evaluate = MagicMock(return_value=_make_hold_match("AAPL"))
-        decision.action = "HOLD"
+        return engine
-        decision.confidence = 50
+
-        decision.rationale = "Testing balance parsing"
+    @pytest.fixture
-        brain.decide = AsyncMock(return_value=decision)
+    def mock_playbook(self) -> DayPlaybook:
-        return brain
+        """Create a minimal playbook."""
+        return _make_playbook("US")
 
     @pytest.fixture
     def mock_risk(self) -> MagicMock:
@@ -517,14 +575,17 @@ class TestOverseasBalanceParsing:
     @pytest.fixture
     def mock_telegram(self) -> MagicMock:
         """Create mock telegram client."""
-        return MagicMock()
+        telegram = MagicMock()
+        telegram.notify_scenario_matched = AsyncMock()
+        return telegram
 
     @pytest.mark.asyncio
     async def test_overseas_balance_list_format(
         self,
         mock_domestic_broker: MagicMock,
         mock_overseas_broker_with_list: MagicMock,
-        mock_brain_hold: MagicMock,
+        mock_scenario_engine_hold: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -539,7 +600,8 @@ class TestOverseasBalanceParsing:
             await trading_cycle(
                 broker=mock_domestic_broker,
                 overseas_broker=mock_overseas_broker_with_list,
-                brain=mock_brain_hold,
+                scenario_engine=mock_scenario_engine_hold,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -559,7 +621,8 @@ class TestOverseasBalanceParsing:
         self,
         mock_domestic_broker: MagicMock,
         mock_overseas_broker_with_dict: MagicMock,
-        mock_brain_hold: MagicMock,
+        mock_scenario_engine_hold: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -574,7 +637,8 @@ class TestOverseasBalanceParsing:
             await trading_cycle(
                 broker=mock_domestic_broker,
                 overseas_broker=mock_overseas_broker_with_dict,
-                brain=mock_brain_hold,
+                scenario_engine=mock_scenario_engine_hold,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -594,7 +658,8 @@ class TestOverseasBalanceParsing:
         self,
         mock_domestic_broker: MagicMock,
         mock_overseas_broker_with_empty: MagicMock,
-        mock_brain_hold: MagicMock,
+        mock_scenario_engine_hold: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -609,7 +674,8 @@ class TestOverseasBalanceParsing:
             await trading_cycle(
                 broker=mock_domestic_broker,
                 overseas_broker=mock_overseas_broker_with_empty,
-                brain=mock_brain_hold,
+                scenario_engine=mock_scenario_engine_hold,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -629,7 +695,8 @@ class TestOverseasBalanceParsing:
         self,
         mock_domestic_broker: MagicMock,
         mock_overseas_broker_with_empty_price: MagicMock,
-        mock_brain_hold: MagicMock,
+        mock_scenario_engine_hold: MagicMock,
+        mock_playbook: DayPlaybook,
         mock_risk: MagicMock,
         mock_db: MagicMock,
         mock_decision_logger: MagicMock,
@@ -644,7 +711,8 @@ class TestOverseasBalanceParsing:
             await trading_cycle(
                 broker=mock_domestic_broker,
                 overseas_broker=mock_overseas_broker_with_empty_price,
-                brain=mock_brain_hold,
+                scenario_engine=mock_scenario_engine_hold,
+                playbook=mock_playbook,
                 risk=mock_risk,
                 db_conn=mock_db,
                 decision_logger=mock_decision_logger,
@@ -658,3 +726,572 @@ class TestOverseasBalanceParsing:
 
         # Verify price API was called
         mock_overseas_broker_with_empty_price.get_overseas_price.assert_called_once()
+
+
+class TestScenarioEngineIntegration:
+    """Test scenario engine integration in trading_cycle."""
+
+    @pytest.fixture
+    def mock_broker(self) -> MagicMock:
+        """Create mock broker with standard domestic data."""
+        broker = MagicMock()
+        broker.get_orderbook = AsyncMock(
+            return_value={
+                "output1": {"stck_prpr": "50000", "frgn_ntby_qty": "100"}
+            }
+        )
+        broker.get_balance = AsyncMock(
+            return_value={
+                "output2": [
+                    {
+                        "tot_evlu_amt": "10000000",
+                        "dnca_tot_amt": "5000000",
+                        "pchs_amt_smtl_amt": "9500000",
+                    }
+                ]
+            }
+        )
+        broker.send_order = AsyncMock(return_value={"msg1": "OK"})
+        return broker
+
+    @pytest.fixture
+    def mock_market(self) -> MagicMock:
+        """Create mock KR market."""
+        market = MagicMock()
+        market.name = "Korea"
+        market.code = "KR"
+        market.exchange_code = "KRX"
+        market.is_domestic = True
+        return market
+
+    @pytest.fixture
+    def mock_telegram(self) -> MagicMock:
+        """Create mock telegram with all notification methods."""
+        telegram = MagicMock()
+        telegram.notify_trade_execution = AsyncMock()
+        telegram.notify_scenario_matched = AsyncMock()
+        telegram.notify_fat_finger = AsyncMock()
+        return telegram
+
+    @pytest.mark.asyncio
+    async def test_scenario_engine_called_with_enriched_market_data(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test scenario engine receives market_data enriched with scanner metrics."""
+        from src.analysis.smart_scanner import ScanCandidate
+
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=_make_hold_match())
+        playbook = _make_playbook()
+
+        candidate = ScanCandidate(
+            stock_code="005930", name="Samsung", price=50000,
+            volume=1000000, volume_ratio=3.5, rsi=25.0,
+            signal="oversold", score=85.0,
+        )
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=playbook,
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={"KR": {"005930": candidate}},
+            )
+
+        # Verify evaluate was called
+        engine.evaluate.assert_called_once()
+        call_args = engine.evaluate.call_args
+        market_data = call_args[0][2]  # 3rd positional arg
+        portfolio_data = call_args[0][3]  # 4th positional arg
+
+        # Scanner data should be enriched into market_data
+        assert market_data["rsi"] == 25.0
+        assert market_data["volume_ratio"] == 3.5
+        assert market_data["current_price"] == 50000.0
+
+        # Portfolio data should include pnl
+        assert "portfolio_pnl_pct" in portfolio_data
+        assert "total_cash" in portfolio_data
+
+    @pytest.mark.asyncio
+    async def test_trading_cycle_sets_l7_context_keys(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test L7 context is written with market-scoped keys."""
+        from src.analysis.smart_scanner import ScanCandidate
+
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=_make_hold_match())
+        playbook = _make_playbook()
+        context_store = MagicMock(get_latest_timeframe=MagicMock(return_value=None))
+
+        candidate = ScanCandidate(
+            stock_code="005930", name="Samsung", price=50000,
+            volume=1000000, volume_ratio=3.5, rsi=25.0,
+            signal="oversold", score=85.0,
+        )
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=playbook,
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=context_store,
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={"KR": {"005930": candidate}},
+            )
+
+        context_store.set_context.assert_any_call(
+            ContextLayer.L7_REALTIME,
+            ANY,
+            "volatility_KR_005930",
+            {"momentum_score": 50.0, "volume_surge": 1.0, "price_change_1m": 0.0},
+        )
+        context_store.set_context.assert_any_call(
+            ContextLayer.L7_REALTIME,
+            ANY,
+            "price_KR_005930",
+            {"current_price": 50000.0},
+        )
+        context_store.set_context.assert_any_call(
+            ContextLayer.L7_REALTIME,
+            ANY,
+            "rsi_KR_005930",
+            {"rsi": 25.0},
+        )
+        context_store.set_context.assert_any_call(
+            ContextLayer.L7_REALTIME,
+            ANY,
+            "volume_ratio_KR_005930",
+            {"volume_ratio": 3.5},
+        )
+
+    @pytest.mark.asyncio
+    async def test_scan_candidates_market_scoped(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test scan_candidates uses market-scoped lookup, ignoring other markets."""
+        from src.analysis.smart_scanner import ScanCandidate
+
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=_make_hold_match())
+
+        # Candidate stored under US market — should NOT be found for KR market
+        us_candidate = ScanCandidate(
+            stock_code="005930", name="Overlap", price=100,
+            volume=500000, volume_ratio=5.0, rsi=15.0,
+            signal="oversold", score=90.0,
+        )
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=_make_playbook(),
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,  # KR market
+                stock_code="005930",
+                scan_candidates={"US": {"005930": us_candidate}},  # Wrong market
+            )
+
+        # Should NOT have rsi/volume_ratio because candidate is under US, not KR
+        market_data = engine.evaluate.call_args[0][2]
+        assert "rsi" not in market_data
+        assert "volume_ratio" not in market_data
+
+    @pytest.mark.asyncio
+    async def test_scenario_engine_called_without_scanner_data(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test scenario engine works when stock has no scan candidate."""
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=_make_hold_match())
+        playbook = _make_playbook()
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=playbook,
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={},  # No scanner data
+            )
+
+        # Should still work, just without rsi/volume_ratio
+        engine.evaluate.assert_called_once()
+        market_data = engine.evaluate.call_args[0][2]
+        assert "rsi" not in market_data
+        assert "volume_ratio" not in market_data
+        assert market_data["current_price"] == 50000.0
+
+    @pytest.mark.asyncio
+    async def test_scenario_matched_notification_sent(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test telegram notification sent when a scenario matches."""
+        # Create a match with matched_scenario (not None)
+        scenario = StockScenario(
+            condition=StockCondition(rsi_below=30),
+            action=ScenarioAction.BUY,
+            confidence=88,
+            rationale="RSI oversold bounce",
+        )
+        match = ScenarioMatch(
+            stock_code="005930",
+            matched_scenario=scenario,
+            action=ScenarioAction.BUY,
+            confidence=88,
+            rationale="RSI oversold bounce",
+            match_details={"rsi": 25.0},
+        )
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=match)
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=_make_playbook(),
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={},
+            )
+
+        # Scenario matched notification should be sent
+        mock_telegram.notify_scenario_matched.assert_called_once()
+        call_kwargs = mock_telegram.notify_scenario_matched.call_args.kwargs
+        assert call_kwargs["stock_code"] == "005930"
+        assert call_kwargs["action"] == "BUY"
+        assert "rsi=25.0" in call_kwargs["condition_summary"]
+
+    @pytest.mark.asyncio
+    async def test_no_scenario_matched_notification_on_default_hold(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test no scenario notification when default HOLD is returned."""
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=_make_hold_match())
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=_make_playbook(),
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={},
+            )
+
+        # No scenario matched notification for default HOLD
+        mock_telegram.notify_scenario_matched.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_decision_logger_receives_scenario_match_details(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test decision logger context includes scenario match details."""
+        match = ScenarioMatch(
+            stock_code="005930",
+            matched_scenario=None,
+            action=ScenarioAction.HOLD,
+            confidence=0,
+            rationale="No match",
+            match_details={"rsi": 45.0, "volume_ratio": 1.2},
+        )
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=match)
+        decision_logger = MagicMock()
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=_make_playbook(),
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=decision_logger,
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={},
+            )
+
+        decision_logger.log_decision.assert_called_once()
+        call_kwargs = decision_logger.log_decision.call_args.kwargs
+        assert "scenario_match" in call_kwargs["context_snapshot"]
+        assert call_kwargs["context_snapshot"]["scenario_match"]["rsi"] == 45.0
+
+    @pytest.mark.asyncio
+    async def test_reduce_all_does_not_execute_order(
+        self, mock_broker: MagicMock, mock_market: MagicMock, mock_telegram: MagicMock,
+    ) -> None:
+        """Test REDUCE_ALL action does not trigger order execution."""
+        match = ScenarioMatch(
+            stock_code="005930",
+            matched_scenario=None,
+            action=ScenarioAction.REDUCE_ALL,
+            confidence=100,
+            rationale="Global rule: portfolio loss > 2%",
+        )
+        engine = MagicMock(spec=ScenarioEngine)
+        engine.evaluate = MagicMock(return_value=match)
+
+        with patch("src.main.log_trade"):
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=MagicMock(),
+                scenario_engine=engine,
+                playbook=_make_playbook(),
+                risk=MagicMock(),
+                db_conn=MagicMock(),
+                decision_logger=MagicMock(),
+                context_store=MagicMock(get_latest_timeframe=MagicMock(return_value=None)),
+                criticality_assessor=MagicMock(
+                    assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+                    get_timeout=MagicMock(return_value=5.0),
+                ),
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={},
+            )
+
+        # REDUCE_ALL is not BUY or SELL — no order sent
+        mock_broker.send_order.assert_not_called()
+        mock_telegram.notify_trade_execution.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_sell_updates_original_buy_decision_outcome() -> None:
+    """SELL should update the original BUY decision outcome in decision_logs."""
+    db_conn = init_db(":memory:")
+    decision_logger = DecisionLogger(db_conn)
+
+    buy_decision_id = decision_logger.log_decision(
+        stock_code="005930",
+        market="KR",
+        exchange_code="KRX",
+        action="BUY",
+        confidence=85,
+        rationale="Initial buy",
+        context_snapshot={},
+        input_data={},
+    )
+    log_trade(
+        conn=db_conn,
+        stock_code="005930",
+        action="BUY",
+        confidence=85,
+        rationale="Initial buy",
+        quantity=1,
+        price=100.0,
+        pnl=0.0,
+        market="KR",
+        exchange_code="KRX",
+        decision_id=buy_decision_id,
+    )
+
+    broker = MagicMock()
+    broker.get_orderbook = AsyncMock(
+        return_value={"output1": {"stck_prpr": "120", "frgn_ntby_qty": "0"}}
+    )
+    broker.get_balance = AsyncMock(
+        return_value={
+            "output2": [
+                {
+                    "tot_evlu_amt": "100000",
+                    "dnca_tot_amt": "10000",
+                    "pchs_amt_smtl_amt": "90000",
+                }
+            ]
+        }
+    )
+    broker.send_order = AsyncMock(return_value={"msg1": "OK"})
+
+    overseas_broker = MagicMock()
+    engine = MagicMock(spec=ScenarioEngine)
+    engine.evaluate = MagicMock(return_value=_make_sell_match())
+    risk = MagicMock()
+    context_store = MagicMock(
+        get_latest_timeframe=MagicMock(return_value=None),
+        set_context=MagicMock(),
+    )
+    criticality_assessor = MagicMock(
+        assess_market_conditions=MagicMock(return_value=MagicMock(value="NORMAL")),
+        get_timeout=MagicMock(return_value=5.0),
+    )
+    telegram = MagicMock()
+    telegram.notify_trade_execution = AsyncMock()
+    telegram.notify_fat_finger = AsyncMock()
+    telegram.notify_circuit_breaker = AsyncMock()
+    telegram.notify_scenario_matched = AsyncMock()
+
+    market = MagicMock()
+    market.name = "Korea"
+    market.code = "KR"
+    market.exchange_code = "KRX"
+    market.is_domestic = True
+
+    await trading_cycle(
+        broker=broker,
+        overseas_broker=overseas_broker,
+        scenario_engine=engine,
+        playbook=_make_playbook(),
+        risk=risk,
+        db_conn=db_conn,
+        decision_logger=decision_logger,
+        context_store=context_store,
+        criticality_assessor=criticality_assessor,
+        telegram=telegram,
+        market=market,
+        stock_code="005930",
+        scan_candidates={},
+    )
+
+    updated_buy = decision_logger.get_decision_by_id(buy_decision_id)
+    assert updated_buy is not None
+    assert updated_buy.outcome_pnl == 20.0
+    assert updated_buy.outcome_accuracy == 1
+
+
+@pytest.mark.asyncio
+async def test_handle_market_close_runs_daily_review_flow() -> None:
+    """Market close should aggregate, create scorecard, lessons, and notify."""
+    telegram = MagicMock()
+    telegram.notify_market_close = AsyncMock()
+    telegram.send_message = AsyncMock()
+
+    context_aggregator = MagicMock()
+    reviewer = MagicMock()
+    reviewer.generate_scorecard.return_value = DailyScorecard(
+        date="2026-02-14",
+        market="KR",
+        total_decisions=3,
+        buys=1,
+        sells=1,
+        holds=1,
+        total_pnl=12.5,
+        win_rate=50.0,
+        avg_confidence=75.0,
+        scenario_match_rate=66.7,
+    )
+    reviewer.generate_lessons = AsyncMock(return_value=["Cut losers faster"])
+
+    await _handle_market_close(
+        market_code="KR",
+        market_name="Korea",
+        market_timezone=UTC,
+        telegram=telegram,
+        context_aggregator=context_aggregator,
+        daily_reviewer=reviewer,
+    )
+
+    telegram.notify_market_close.assert_called_once_with("Korea", 0.0)
+    context_aggregator.aggregate_daily_from_trades.assert_called_once()
+    reviewer.generate_scorecard.assert_called_once()
+    assert reviewer.store_scorecard_in_context.call_count == 2
+    reviewer.generate_lessons.assert_called_once()
+    telegram.send_message.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_handle_market_close_without_lessons_stores_once() -> None:
+    """If no lessons are generated, scorecard should be stored once."""
+    telegram = MagicMock()
+    telegram.notify_market_close = AsyncMock()
+    telegram.send_message = AsyncMock()
+
+    context_aggregator = MagicMock()
+    reviewer = MagicMock()
+    reviewer.generate_scorecard.return_value = DailyScorecard(
+        date="2026-02-14",
+        market="US",
+        total_decisions=1,
+        buys=0,
+        sells=1,
+        holds=0,
+        total_pnl=-3.0,
+        win_rate=0.0,
+        avg_confidence=65.0,
+        scenario_match_rate=100.0,
+    )
+    reviewer.generate_lessons = AsyncMock(return_value=[])
+
+    await _handle_market_close(
+        market_code="US",
+        market_name="United States",
+        market_timezone=UTC,
+        telegram=telegram,
+        context_aggregator=context_aggregator,
+        daily_reviewer=reviewer,
+    )
+
+    assert reviewer.store_scorecard_in_context.call_count == 1

tests/test_pre_market_planner.py

@@ -0,0 +1,586 @@
+"""Tests for PreMarketPlanner — Gemini prompt builder + response parser."""
+
+from __future__ import annotations
+
+import json
+from datetime import date
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from src.analysis.smart_scanner import ScanCandidate
+from src.brain.context_selector import DecisionType
+from src.brain.gemini_client import TradeDecision
+from src.config import Settings
+from src.context.store import ContextLayer
+from src.strategy.models import (
+    CrossMarketContext,
+    DayPlaybook,
+    MarketOutlook,
+    ScenarioAction,
+)
+from src.strategy.pre_market_planner import PreMarketPlanner
+
+# ---------------------------------------------------------------------------
+# Fixtures
+# ---------------------------------------------------------------------------
+
+
+def _candidate(
+    code: str = "005930",
+    name: str = "Samsung",
+    price: float = 71000,
+    rsi: float = 28.5,
+    volume_ratio: float = 3.2,
+    signal: str = "oversold",
+    score: float = 82.0,
+) -> ScanCandidate:
+    return ScanCandidate(
+        stock_code=code,
+        name=name,
+        price=price,
+        volume=1_500_000,
+        volume_ratio=volume_ratio,
+        rsi=rsi,
+        signal=signal,
+        score=score,
+    )
+
+
+def _gemini_response_json(
+    outlook: str = "neutral_to_bullish",
+    stocks: list[dict] | None = None,
+    global_rules: list[dict] | None = None,
+) -> str:
+    """Build a valid Gemini JSON response."""
+    if stocks is None:
+        stocks = [
+            {
+                "stock_code": "005930",
+                "scenarios": [
+                    {
+                        "condition": {"rsi_below": 30, "volume_ratio_above": 2.5},
+                        "action": "BUY",
+                        "confidence": 85,
+                        "allocation_pct": 15.0,
+                        "stop_loss_pct": -2.0,
+                        "take_profit_pct": 4.0,
+                        "rationale": "Oversold bounce with high volume",
+                    }
+                ],
+            }
+        ]
+    if global_rules is None:
+        global_rules = [
+            {
+                "condition": "portfolio_pnl_pct < -2.0",
+                "action": "REDUCE_ALL",
+                "rationale": "Near circuit breaker",
+            }
+        ]
+    return json.dumps(
+        {"market_outlook": outlook, "global_rules": global_rules, "stocks": stocks}
+    )
+
+
+def _make_planner(
+    gemini_response: str = "",
+    token_count: int = 200,
+    context_data: dict | None = None,
+    scorecard_data: dict | None = None,
+) -> PreMarketPlanner:
+    """Create a PreMarketPlanner with mocked dependencies."""
+    if not gemini_response:
+        gemini_response = _gemini_response_json()
+
+    # Mock GeminiClient
+    gemini = AsyncMock()
+    gemini.decide = AsyncMock(
+        return_value=TradeDecision(
+            action="HOLD",
+            confidence=0,
+            rationale=gemini_response,
+            token_count=token_count,
+        )
+    )
+
+    # Mock ContextStore
+    store = MagicMock()
+    store.get_context = MagicMock(return_value=scorecard_data)
+
+    # Mock ContextSelector
+    selector = MagicMock()
+    selector.select_layers = MagicMock(
+        return_value=[ContextLayer.L7_REALTIME, ContextLayer.L6_DAILY]
+    )
+    selector.get_context_data = MagicMock(return_value=context_data or {})
+
+    settings = Settings(
+        KIS_APP_KEY="test",
+        KIS_APP_SECRET="test",
+        KIS_ACCOUNT_NO="12345678-01",
+        GEMINI_API_KEY="test",
+    )
+
+    return PreMarketPlanner(gemini, store, selector, settings)
+
+
+# ---------------------------------------------------------------------------
+# generate_playbook
+# ---------------------------------------------------------------------------
+
+
+class TestGeneratePlaybook:
+    @pytest.mark.asyncio
+    async def test_basic_generation(self) -> None:
+        planner = _make_planner()
+        candidates = [_candidate()]
+
+        pb = await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        assert isinstance(pb, DayPlaybook)
+        assert pb.market == "KR"
+        assert pb.stock_count == 1
+        assert pb.scenario_count == 1
+        assert pb.market_outlook == MarketOutlook.NEUTRAL_TO_BULLISH
+        assert pb.token_count == 200
+
+    @pytest.mark.asyncio
+    async def test_empty_candidates_returns_empty_playbook(self) -> None:
+        planner = _make_planner()
+
+        pb = await planner.generate_playbook("KR", [], today=date(2026, 2, 8))
+
+        assert pb.stock_count == 0
+        assert pb.scenario_count == 0
+        assert pb.market_outlook == MarketOutlook.NEUTRAL
+
+    @pytest.mark.asyncio
+    async def test_gemini_failure_returns_defensive(self) -> None:
+        planner = _make_planner()
+        planner._gemini.decide = AsyncMock(side_effect=RuntimeError("API timeout"))
+        candidates = [_candidate()]
+
+        pb = await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        assert pb.default_action == ScenarioAction.HOLD
+        assert pb.market_outlook == MarketOutlook.NEUTRAL_TO_BEARISH
+        assert pb.stock_count == 1
+        # Defensive playbook has stop-loss scenarios
+        assert pb.stock_playbooks[0].scenarios[0].action == ScenarioAction.SELL
+
+    @pytest.mark.asyncio
+    async def test_gemini_failure_empty_when_defensive_disabled(self) -> None:
+        planner = _make_planner()
+        planner._settings.DEFENSIVE_PLAYBOOK_ON_FAILURE = False
+        planner._gemini.decide = AsyncMock(side_effect=RuntimeError("fail"))
+        candidates = [_candidate()]
+
+        pb = await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        assert pb.stock_count == 0
+
+    @pytest.mark.asyncio
+    async def test_multiple_candidates(self) -> None:
+        stocks = [
+            {
+                "stock_code": "005930",
+                "scenarios": [
+                    {
+                        "condition": {"rsi_below": 30},
+                        "action": "BUY",
+                        "confidence": 85,
+                        "rationale": "Oversold",
+                    }
+                ],
+            },
+            {
+                "stock_code": "AAPL",
+                "scenarios": [
+                    {
+                        "condition": {"rsi_above": 75},
+                        "action": "SELL",
+                        "confidence": 80,
+                        "rationale": "Overbought",
+                    }
+                ],
+            },
+        ]
+        planner = _make_planner(gemini_response=_gemini_response_json(stocks=stocks))
+        candidates = [_candidate(), _candidate(code="AAPL", name="Apple")]
+
+        pb = await planner.generate_playbook("US", candidates, today=date(2026, 2, 8))
+
+        assert pb.stock_count == 2
+        codes = [sp.stock_code for sp in pb.stock_playbooks]
+        assert "005930" in codes
+        assert "AAPL" in codes
+
+    @pytest.mark.asyncio
+    async def test_unknown_stock_in_response_skipped(self) -> None:
+        stocks = [
+            {
+                "stock_code": "005930",
+                "scenarios": [
+                    {
+                        "condition": {"rsi_below": 30},
+                        "action": "BUY",
+                        "confidence": 85,
+                        "rationale": "ok",
+                    }
+                ],
+            },
+            {
+                "stock_code": "UNKNOWN",
+                "scenarios": [
+                    {
+                        "condition": {"rsi_below": 20},
+                        "action": "BUY",
+                        "confidence": 90,
+                        "rationale": "bad",
+                    }
+                ],
+            },
+        ]
+        planner = _make_planner(gemini_response=_gemini_response_json(stocks=stocks))
+        candidates = [_candidate()]  # Only 005930
+
+        pb = await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        assert pb.stock_count == 1
+        assert pb.stock_playbooks[0].stock_code == "005930"
+
+    @pytest.mark.asyncio
+    async def test_global_rules_parsed(self) -> None:
+        planner = _make_planner()
+        candidates = [_candidate()]
+
+        pb = await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        assert len(pb.global_rules) == 1
+        assert pb.global_rules[0].action == ScenarioAction.REDUCE_ALL
+
+    @pytest.mark.asyncio
+    async def test_token_count_from_decision(self) -> None:
+        planner = _make_planner(token_count=450)
+        candidates = [_candidate()]
+
+        pb = await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        assert pb.token_count == 450
+
+    @pytest.mark.asyncio
+    async def test_generate_playbook_uses_strategic_context_selector(self) -> None:
+        planner = _make_planner()
+        candidates = [_candidate()]
+
+        await planner.generate_playbook("KR", candidates, today=date(2026, 2, 8))
+
+        planner._context_selector.select_layers.assert_called_once_with(
+            decision_type=DecisionType.STRATEGIC,
+            include_realtime=True,
+        )
+        planner._context_selector.get_context_data.assert_called_once()
+
+
+# ---------------------------------------------------------------------------
+# _parse_response
+# ---------------------------------------------------------------------------
+
+
+class TestParseResponse:
+    def test_parse_full_response(self) -> None:
+        planner = _make_planner()
+        response = _gemini_response_json(outlook="bearish")
+        candidates = [_candidate()]
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, None)
+
+        assert pb.market_outlook == MarketOutlook.BEARISH
+        assert pb.stock_count == 1
+        assert pb.stock_playbooks[0].scenarios[0].confidence == 85
+
+    def test_parse_with_markdown_fences(self) -> None:
+        planner = _make_planner()
+        response = f"```json\n{_gemini_response_json()}\n```"
+        candidates = [_candidate()]
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, None)
+
+        assert pb.stock_count == 1
+
+    def test_parse_unknown_outlook_defaults_neutral(self) -> None:
+        planner = _make_planner()
+        response = _gemini_response_json(outlook="super_bullish")
+        candidates = [_candidate()]
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, None)
+
+        assert pb.market_outlook == MarketOutlook.NEUTRAL
+
+    def test_parse_scenario_with_all_condition_fields(self) -> None:
+        planner = _make_planner()
+        stocks = [
+            {
+                "stock_code": "005930",
+                "scenarios": [
+                    {
+                        "condition": {
+                            "rsi_below": 25,
+                            "volume_ratio_above": 3.0,
+                            "price_change_pct_below": -2.0,
+                        },
+                        "action": "BUY",
+                        "confidence": 92,
+                        "allocation_pct": 20.0,
+                        "stop_loss_pct": -3.0,
+                        "take_profit_pct": 5.0,
+                        "rationale": "Multi-condition entry",
+                    }
+                ],
+            }
+        ]
+        response = _gemini_response_json(stocks=stocks)
+        candidates = [_candidate()]
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, None)
+
+        sc = pb.stock_playbooks[0].scenarios[0]
+        assert sc.condition.rsi_below == 25
+        assert sc.condition.volume_ratio_above == 3.0
+        assert sc.condition.price_change_pct_below == -2.0
+        assert sc.allocation_pct == 20.0
+        assert sc.stop_loss_pct == -3.0
+        assert sc.take_profit_pct == 5.0
+
+    def test_parse_empty_condition_scenario_skipped(self) -> None:
+        planner = _make_planner()
+        stocks = [
+            {
+                "stock_code": "005930",
+                "scenarios": [
+                    {
+                        "condition": {},
+                        "action": "BUY",
+                        "confidence": 85,
+                        "rationale": "No conditions",
+                    },
+                    {
+                        "condition": {"rsi_below": 30},
+                        "action": "BUY",
+                        "confidence": 80,
+                        "rationale": "Valid",
+                    },
+                ],
+            }
+        ]
+        response = _gemini_response_json(stocks=stocks)
+        candidates = [_candidate()]
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, None)
+
+        # Empty condition scenario skipped, valid one kept
+        assert pb.stock_count == 1
+        assert pb.stock_playbooks[0].scenarios[0].confidence == 80
+
+    def test_parse_max_scenarios_enforced(self) -> None:
+        planner = _make_planner()
+        # Settings default MAX_SCENARIOS_PER_STOCK = 5
+        scenarios = [
+            {
+                "condition": {"rsi_below": 20 + i},
+                "action": "BUY",
+                "confidence": 80 + i,
+                "rationale": f"Scenario {i}",
+            }
+            for i in range(8)  # 8 scenarios, should be capped to 5
+        ]
+        stocks = [{"stock_code": "005930", "scenarios": scenarios}]
+        response = _gemini_response_json(stocks=stocks)
+        candidates = [_candidate()]
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, None)
+
+        assert len(pb.stock_playbooks[0].scenarios) == 5
+
+    def test_parse_invalid_json_raises(self) -> None:
+        planner = _make_planner()
+        candidates = [_candidate()]
+
+        with pytest.raises(json.JSONDecodeError):
+            planner._parse_response("not json at all", date(2026, 2, 8), "KR", candidates, None)
+
+    def test_parse_cross_market_preserved(self) -> None:
+        planner = _make_planner()
+        response = _gemini_response_json()
+        candidates = [_candidate()]
+        cross = CrossMarketContext(market="US", date="2026-02-07", total_pnl=1.5, win_rate=60)
+
+        pb = planner._parse_response(response, date(2026, 2, 8), "KR", candidates, cross)
+
+        assert pb.cross_market is not None
+        assert pb.cross_market.market == "US"
+        assert pb.cross_market.total_pnl == 1.5
+
+
+# ---------------------------------------------------------------------------
+# build_cross_market_context
+# ---------------------------------------------------------------------------
+
+
+class TestBuildCrossMarketContext:
+    def test_kr_reads_us_scorecard(self) -> None:
+        scorecard = {
+            "total_pnl": 2.5,
+            "win_rate": 65,
+            "index_change_pct": 0.8,
+            "lessons": ["Stay patient"],
+        }
+        planner = _make_planner(scorecard_data=scorecard)
+
+        ctx = planner.build_cross_market_context("KR", today=date(2026, 2, 8))
+
+        assert ctx is not None
+        assert ctx.market == "US"
+        assert ctx.total_pnl == 2.5
+        assert ctx.win_rate == 65
+        assert "Stay patient" in ctx.lessons
+
+        # Verify it queried scorecard_US
+        planner._context_store.get_context.assert_called_once_with(
+            ContextLayer.L6_DAILY, "2026-02-07", "scorecard_US"
+        )
+        assert ctx.date == "2026-02-07"
+
+    def test_us_reads_kr_scorecard(self) -> None:
+        scorecard = {"total_pnl": -1.0, "win_rate": 40, "index_change_pct": -0.5}
+        planner = _make_planner(scorecard_data=scorecard)
+
+        ctx = planner.build_cross_market_context("US", today=date(2026, 2, 8))
+
+        assert ctx is not None
+        assert ctx.market == "KR"
+        assert ctx.total_pnl == -1.0
+
+        planner._context_store.get_context.assert_called_once_with(
+            ContextLayer.L6_DAILY, "2026-02-08", "scorecard_KR"
+        )
+
+    def test_no_scorecard_returns_none(self) -> None:
+        planner = _make_planner(scorecard_data=None)
+
+        ctx = planner.build_cross_market_context("KR", today=date(2026, 2, 8))
+
+        assert ctx is None
+
+    def test_invalid_scorecard_returns_none(self) -> None:
+        planner = _make_planner(scorecard_data="not a dict and not json")
+
+        ctx = planner.build_cross_market_context("KR", today=date(2026, 2, 8))
+
+        assert ctx is None
+
+
+# ---------------------------------------------------------------------------
+# _build_prompt
+# ---------------------------------------------------------------------------
+
+
+class TestBuildPrompt:
+    def test_prompt_contains_candidates(self) -> None:
+        planner = _make_planner()
+        candidates = [_candidate(code="005930", name="Samsung")]
+
+        prompt = planner._build_prompt("KR", candidates, {}, None)
+
+        assert "005930" in prompt
+        assert "Samsung" in prompt
+        assert "RSI=" in prompt
+        assert "volume_ratio=" in prompt
+
+    def test_prompt_contains_cross_market(self) -> None:
+        planner = _make_planner()
+        cross = CrossMarketContext(
+            market="US", date="2026-02-07", total_pnl=1.5,
+            win_rate=60, index_change_pct=0.8, lessons=["Cut losses early"],
+        )
+
+        prompt = planner._build_prompt("KR", [_candidate()], {}, cross)
+
+        assert "Other Market (US)" in prompt
+        assert "+1.50%" in prompt
+        assert "Cut losses early" in prompt
+
+    def test_prompt_contains_context_data(self) -> None:
+        planner = _make_planner()
+        context = {"L6_DAILY": {"win_rate": 0.65, "total_pnl": 2.5}}
+
+        prompt = planner._build_prompt("KR", [_candidate()], context, None)
+
+        assert "Strategic Context" in prompt
+        assert "L6_DAILY" in prompt
+        assert "win_rate" in prompt
+
+    def test_prompt_contains_max_scenarios(self) -> None:
+        planner = _make_planner()
+        prompt = planner._build_prompt("KR", [_candidate()], {}, None)
+
+        assert f"Max {planner._settings.MAX_SCENARIOS_PER_STOCK} scenarios" in prompt
+
+    def test_prompt_market_name(self) -> None:
+        planner = _make_planner()
+        prompt = planner._build_prompt("US", [_candidate()], {}, None)
+        assert "US market" in prompt
+
+
+# ---------------------------------------------------------------------------
+# _extract_json
+# ---------------------------------------------------------------------------
+
+
+class TestExtractJson:
+    def test_plain_json(self) -> None:
+        assert PreMarketPlanner._extract_json('{"a": 1}') == '{"a": 1}'
+
+    def test_with_json_fence(self) -> None:
+        text = '```json\n{"a": 1}\n```'
+        assert PreMarketPlanner._extract_json(text) == '{"a": 1}'
+
+    def test_with_plain_fence(self) -> None:
+        text = '```\n{"a": 1}\n```'
+        assert PreMarketPlanner._extract_json(text) == '{"a": 1}'
+
+    def test_with_whitespace(self) -> None:
+        text = '  \n  {"a": 1}  \n  '
+        assert PreMarketPlanner._extract_json(text) == '{"a": 1}'
+
+
+# ---------------------------------------------------------------------------
+# Defensive playbook
+# ---------------------------------------------------------------------------
+
+
+class TestDefensivePlaybook:
+    def test_defensive_has_stop_loss(self) -> None:
+        candidates = [_candidate(code="005930"), _candidate(code="AAPL")]
+        pb = PreMarketPlanner._defensive_playbook(date(2026, 2, 8), "KR", candidates)
+
+        assert pb.default_action == ScenarioAction.HOLD
+        assert pb.market_outlook == MarketOutlook.NEUTRAL_TO_BEARISH
+        assert pb.stock_count == 2
+        for sp in pb.stock_playbooks:
+            assert sp.scenarios[0].action == ScenarioAction.SELL
+            assert sp.scenarios[0].stop_loss_pct == -3.0
+
+    def test_defensive_has_global_rule(self) -> None:
+        pb = PreMarketPlanner._defensive_playbook(date(2026, 2, 8), "KR", [_candidate()])
+
+        assert len(pb.global_rules) == 1
+        assert pb.global_rules[0].action == ScenarioAction.REDUCE_ALL
+
+    def test_empty_playbook(self) -> None:
+        pb = PreMarketPlanner._empty_playbook(date(2026, 2, 8), "US")
+
+        assert pb.stock_count == 0
+        assert pb.market == "US"
+        assert pb.market_outlook == MarketOutlook.NEUTRAL

tests/test_scorecard.py

@@ -0,0 +1,81 @@
+"""Tests for DailyScorecard model."""
+
+from __future__ import annotations
+
+from src.evolution.scorecard import DailyScorecard
+
+
+def test_scorecard_initialization() -> None:
+    scorecard = DailyScorecard(
+        date="2026-02-08",
+        market="KR",
+        total_decisions=10,
+        buys=3,
+        sells=2,
+        holds=5,
+        total_pnl=1234.5,
+        win_rate=60.0,
+        avg_confidence=78.5,
+        scenario_match_rate=70.0,
+        top_winners=["005930", "000660"],
+        top_losers=["035420"],
+        lessons=["Avoid chasing breakouts"],
+        cross_market_note="US volatility spillover",
+    )
+
+    assert scorecard.market == "KR"
+    assert scorecard.total_decisions == 10
+    assert scorecard.total_pnl == 1234.5
+    assert scorecard.top_winners == ["005930", "000660"]
+    assert scorecard.lessons == ["Avoid chasing breakouts"]
+    assert scorecard.cross_market_note == "US volatility spillover"
+
+
+def test_scorecard_defaults() -> None:
+    scorecard = DailyScorecard(
+        date="2026-02-08",
+        market="US",
+        total_decisions=0,
+        buys=0,
+        sells=0,
+        holds=0,
+        total_pnl=0.0,
+        win_rate=0.0,
+        avg_confidence=0.0,
+        scenario_match_rate=0.0,
+    )
+
+    assert scorecard.top_winners == []
+    assert scorecard.top_losers == []
+    assert scorecard.lessons == []
+    assert scorecard.cross_market_note == ""
+
+
+def test_scorecard_list_isolation() -> None:
+    a = DailyScorecard(
+        date="2026-02-08",
+        market="KR",
+        total_decisions=1,
+        buys=1,
+        sells=0,
+        holds=0,
+        total_pnl=10.0,
+        win_rate=100.0,
+        avg_confidence=90.0,
+        scenario_match_rate=100.0,
+    )
+    b = DailyScorecard(
+        date="2026-02-08",
+        market="US",
+        total_decisions=1,
+        buys=0,
+        sells=1,
+        holds=0,
+        total_pnl=-5.0,
+        win_rate=0.0,
+        avg_confidence=60.0,
+        scenario_match_rate=50.0,
+    )
+
+    a.top_winners.append("005930")
+    assert b.top_winners == []

tests/test_telegram.py

@@ -160,6 +160,83 @@ class TestNotificationSending:
             assert "250.50" in payload["text"]
             assert "92%" in payload["text"]
 
+    @pytest.mark.asyncio
+    async def test_playbook_generated_format(self) -> None:
+        """Playbook generated notification has expected fields."""
+        client = TelegramClient(
+            bot_token="123:abc", chat_id="456", enabled=True
+        )
+
+        mock_resp = AsyncMock()
+        mock_resp.status = 200
+        mock_resp.__aenter__ = AsyncMock(return_value=mock_resp)
+        mock_resp.__aexit__ = AsyncMock(return_value=False)
+
+        with patch("aiohttp.ClientSession.post", return_value=mock_resp) as mock_post:
+            await client.notify_playbook_generated(
+                market="KR",
+                stock_count=4,
+                scenario_count=12,
+                token_count=980,
+            )
+
+            payload = mock_post.call_args.kwargs["json"]
+            assert "Playbook Generated" in payload["text"]
+            assert "Market: KR" in payload["text"]
+            assert "Stocks: 4" in payload["text"]
+            assert "Scenarios: 12" in payload["text"]
+            assert "Tokens: 980" in payload["text"]
+
+    @pytest.mark.asyncio
+    async def test_scenario_matched_format(self) -> None:
+        """Scenario matched notification has expected fields."""
+        client = TelegramClient(
+            bot_token="123:abc", chat_id="456", enabled=True
+        )
+
+        mock_resp = AsyncMock()
+        mock_resp.status = 200
+        mock_resp.__aenter__ = AsyncMock(return_value=mock_resp)
+        mock_resp.__aexit__ = AsyncMock(return_value=False)
+
+        with patch("aiohttp.ClientSession.post", return_value=mock_resp) as mock_post:
+            await client.notify_scenario_matched(
+                stock_code="AAPL",
+                action="BUY",
+                condition_summary="RSI < 30, volume_ratio > 2.0",
+                confidence=88.2,
+            )
+
+            payload = mock_post.call_args.kwargs["json"]
+            assert "Scenario Matched" in payload["text"]
+            assert "AAPL" in payload["text"]
+            assert "Action: BUY" in payload["text"]
+            assert "RSI < 30" in payload["text"]
+            assert "88%" in payload["text"]
+
+    @pytest.mark.asyncio
+    async def test_playbook_failed_format(self) -> None:
+        """Playbook failed notification has expected fields."""
+        client = TelegramClient(
+            bot_token="123:abc", chat_id="456", enabled=True
+        )
+
+        mock_resp = AsyncMock()
+        mock_resp.status = 200
+        mock_resp.__aenter__ = AsyncMock(return_value=mock_resp)
+        mock_resp.__aexit__ = AsyncMock(return_value=False)
+
+        with patch("aiohttp.ClientSession.post", return_value=mock_resp) as mock_post:
+            await client.notify_playbook_failed(
+                market="US",
+                reason="Gemini timeout",
+            )
+
+            payload = mock_post.call_args.kwargs["json"]
+            assert "Playbook Failed" in payload["text"]
+            assert "Market: US" in payload["text"]
+            assert "Gemini timeout" in payload["text"]
+
     @pytest.mark.asyncio
     async def test_circuit_breaker_priority(self) -> None:
         """Circuit breaker uses CRITICAL priority."""
@@ -309,6 +386,73 @@ class TestMessagePriorities:
             payload = mock_post.call_args.kwargs["json"]
             assert NotificationPriority.CRITICAL.emoji in payload["text"]
 
+    @pytest.mark.asyncio
+    async def test_playbook_generated_priority(self) -> None:
+        """Playbook generated uses MEDIUM priority emoji."""
+        client = TelegramClient(
+            bot_token="123:abc", chat_id="456", enabled=True
+        )
+
+        mock_resp = AsyncMock()
+        mock_resp.status = 200
+        mock_resp.__aenter__ = AsyncMock(return_value=mock_resp)
+        mock_resp.__aexit__ = AsyncMock(return_value=False)
+
+        with patch("aiohttp.ClientSession.post", return_value=mock_resp) as mock_post:
+            await client.notify_playbook_generated(
+                market="KR",
+                stock_count=2,
+                scenario_count=4,
+                token_count=123,
+            )
+
+            payload = mock_post.call_args.kwargs["json"]
+            assert NotificationPriority.MEDIUM.emoji in payload["text"]
+
+    @pytest.mark.asyncio
+    async def test_playbook_failed_priority(self) -> None:
+        """Playbook failed uses HIGH priority emoji."""
+        client = TelegramClient(
+            bot_token="123:abc", chat_id="456", enabled=True
+        )
+
+        mock_resp = AsyncMock()
+        mock_resp.status = 200
+        mock_resp.__aenter__ = AsyncMock(return_value=mock_resp)
+        mock_resp.__aexit__ = AsyncMock(return_value=False)
+
+        with patch("aiohttp.ClientSession.post", return_value=mock_resp) as mock_post:
+            await client.notify_playbook_failed(
+                market="KR",
+                reason="Invalid JSON",
+            )
+
+            payload = mock_post.call_args.kwargs["json"]
+            assert NotificationPriority.HIGH.emoji in payload["text"]
+
+    @pytest.mark.asyncio
+    async def test_scenario_matched_priority(self) -> None:
+        """Scenario matched uses HIGH priority emoji."""
+        client = TelegramClient(
+            bot_token="123:abc", chat_id="456", enabled=True
+        )
+
+        mock_resp = AsyncMock()
+        mock_resp.status = 200
+        mock_resp.__aenter__ = AsyncMock(return_value=mock_resp)
+        mock_resp.__aexit__ = AsyncMock(return_value=False)
+
+        with patch("aiohttp.ClientSession.post", return_value=mock_resp) as mock_post:
+            await client.notify_scenario_matched(
+                stock_code="AAPL",
+                action="BUY",
+                condition_summary="RSI < 30",
+                confidence=80.0,
+            )
+
+            payload = mock_post.call_args.kwargs["json"]
+            assert NotificationPriority.HIGH.emoji in payload["text"]
+
 
 class TestClientCleanup:
     """Test client cleanup behavior."""

tests/test_volatility.py

@@ -412,7 +412,7 @@ class TestMarketScanner:
         scan_result = context_store.get_context(
             ContextLayer.L7_REALTIME,
             latest_timeframe,
-            "KR_scan_result",
+            "scan_result_KR",
         )
         assert scan_result is not None
         assert scan_result["total_scanned"] == 3