chore: retrigger CI for PR #405

Reviewed-on: #404
Reviewed-by: jihoson <kiparang7th@gmail.com>

CLAUDE.md

@@ -1,187 +1,9 @@
-# The Ouroboros
+# Agent Entry Point
 
-AI-powered trading agent for global stock markets with self-evolution capabilities.
+This file moved to [agents.md](./agents.md).
 
-## Quick Start
+Follow `agents.md` as the single source of truth for Claude/Codex session behavior and project workflow gates.
 
-```bash
+Core process references:
-# Setup
+- [Workflow Guide](docs/workflow.md)
-pip install -e ".[dev]"
+- [Command Reference](docs/commands.md)
-cp .env.example .env
-# Edit .env with your KIS and Gemini API credentials
-
-# Test
-pytest -v --cov=src
-
-# Run (paper trading)
-python -m src.main --mode=paper
-
-# Run with dashboard
-python -m src.main --mode=paper --dashboard
-```
-
-## Telegram Notifications (Optional)
-
-Get real-time alerts for trades, circuit breakers, and system events via Telegram.
-
-### Quick Setup
-
-1. **Create bot**: Message [@BotFather](https://t.me/BotFather) on Telegram → `/newbot`
-2. **Get chat ID**: Message [@userinfobot](https://t.me/userinfobot) → `/start`
-3. **Configure**: Add to `.env`:
-   ```bash
-   TELEGRAM_BOT_TOKEN=1234567890:ABCdefGHIjklMNOpqrsTUVwxyz
-   TELEGRAM_CHAT_ID=123456789
-   TELEGRAM_ENABLED=true
-   ```
-4. **Test**: Start bot conversation (`/start`), then run the agent
-
-**Full documentation**: [src/notifications/README.md](src/notifications/README.md)
-
-### What You'll Get
-
-- 🟢 Trade execution alerts (BUY/SELL with confidence)
-- 🚨 Circuit breaker trips (automatic trading halt)
-- ⚠️ Fat-finger rejections (oversized orders blocked)
-- ℹ️ Market open/close notifications
-- 📝 System startup/shutdown status
-
-### Interactive Commands
-
-With `TELEGRAM_COMMANDS_ENABLED=true` (default), the bot supports 9 bidirectional commands: `/help`, `/status`, `/positions`, `/report`, `/scenarios`, `/review`, `/dashboard`, `/stop`, `/resume`.
-
-**Fail-safe**: Notifications never crash the trading system. Missing credentials or API errors are logged but trading continues normally.
-
-## Smart Volatility Scanner (Optional)
-
-Python-first filtering pipeline that reduces Gemini API calls by pre-filtering stocks using technical indicators.
-
-### How It Works
-
-1. **Fetch Rankings** — KIS API volume surge rankings (top 30 stocks)
-2. **Python Filter** — RSI + volume ratio calculations (no AI)
-   - Volume > 200% of previous day
-   - RSI(14) < 30 (oversold) OR RSI(14) > 70 (momentum)
-3. **AI Judgment** — Only qualified candidates (1-3 stocks) sent to Gemini
-
-### Configuration
-
-Add to `.env` (optional, has sensible defaults):
-```bash
-RSI_OVERSOLD_THRESHOLD=30    # 0-50, default 30
-RSI_MOMENTUM_THRESHOLD=70    # 50-100, default 70
-VOL_MULTIPLIER=2.0           # Volume threshold (2.0 = 200%)
-SCANNER_TOP_N=3              # Max candidates per scan
-```
-
-### Benefits
-
-- **Reduces API costs** — Process 1-3 stocks instead of 20-30
-- **Python-based filtering** — Fast technical analysis before AI
-- **Evolution-ready** — Selection context logged for strategy optimization
-- **Fault-tolerant** — Falls back to static watchlist on API failure
-
-### Trading Mode Integration
-
-Smart Scanner runs in both `TRADE_MODE=realtime` and `daily` paths. On API failure, domestic stocks fall back to a static watchlist; overseas stocks fall back to a dynamic universe (active positions, recent holdings).
-
-## Documentation
-
-- **[Documentation Hub](docs/README.md)** — Top-level doc routing and reading order
-- **[Workflow Guide](docs/workflow.md)** — Git workflow policy and agent-based development
-- **[Command Reference](docs/commands.md)** — Common failures, build commands, troubleshooting
-- **[Architecture](docs/architecture.md)** — System design, components, data flow
-- **[Context Tree](docs/context-tree.md)** — L1-L7 hierarchical memory system
-- **[Testing](docs/testing.md)** — Test structure, coverage requirements, writing tests
-- **[Agent Policies](docs/agents.md)** — Prime directives, constraints, prohibited actions
-- **[Requirements Log](docs/requirements-log.md)** — User requirements and feedback tracking
-- **[Live Trading Checklist](docs/live-trading-checklist.md)** — 모의→실전 전환 체크리스트
-
-## Core Principles
-
-1. **Safety First** — Risk manager is READ-ONLY and enforces circuit breakers
-2. **Test Everything** — 80% coverage minimum, all changes require tests
-3. **Issue-Driven Development** — All work goes through Gitea issues → feature branches → PRs
-4. **Agent Specialization** — Use dedicated agents for design, coding, testing, docs, review
-
-## Requirements Management
-
-User requirements and feedback are tracked in [docs/requirements-log.md](docs/requirements-log.md):
-
-- New requirements are added chronologically with dates
-- Code changes should reference related requirements
-- Helps maintain project evolution aligned with user needs
-- Preserves context across conversations and development cycles
-
-## Project Structure
-
-```
-src/
-├── analysis/        # Technical analysis (RSI, volatility, smart scanner)
-├── backup/          # Disaster recovery (scheduler, cloud storage, health)
-├── brain/           # Gemini AI decision engine (prompt optimizer, context selector)
-├── broker/          # KIS API client (domestic + overseas)
-├── context/         # L1-L7 hierarchical memory system
-├── core/            # Risk manager (READ-ONLY)
-├── dashboard/       # FastAPI read-only monitoring (10 API endpoints)
-├── data/            # External data integration (news, market data, calendar)
-├── evolution/       # Self-improvement (optimizer, daily review, scorecard)
-├── logging/         # Decision logger (audit trail)
-├── markets/         # Market schedules and timezone handling
-├── notifications/   # Telegram alerts + bidirectional commands (9 commands)
-├── strategy/        # Pre-market planner, scenario engine, playbook store
-├── db.py            # SQLite trade logging
-├── main.py          # Trading loop orchestrator
-└── config.py        # Settings (from .env)
-
-tests/               # 998 tests across 41 files
-docs/                # Extended documentation
-```
-
-## Key Commands
-
-```bash
-pytest -v --cov=src              # Run tests with coverage
-ruff check src/ tests/           # Lint
-mypy src/ --strict               # Type check
-
-python -m src.main --mode=paper  # Paper trading
-python -m src.main --mode=paper --dashboard  # With dashboard
-python -m src.main --mode=live   # Live trading (⚠️ real money)
-
-# Gitea workflow (requires tea CLI)
-YES="" ~/bin/tea issues create --repo jihoson/The-Ouroboros --title "..." --description "..."
-YES="" ~/bin/tea pulls create --head feature-branch --base main --title "..." --description "..."
-```
-
-## Markets Supported
-
-- 🇰🇷 Korea (KRX)
-- 🇺🇸 United States (NASDAQ, NYSE, AMEX)
-- 🇯🇵 Japan (TSE)
-- 🇭🇰 Hong Kong (SEHK)
-- 🇨🇳 China (Shanghai, Shenzhen)
-- 🇻🇳 Vietnam (Hanoi, HCM)
-
-Markets auto-detected based on timezone and enabled in `ENABLED_MARKETS` env variable.
-
-## Critical Constraints
-
-⚠️ **Non-Negotiable Rules** (see [docs/agents.md](docs/agents.md)):
-
-- `src/core/risk_manager.py` is **READ-ONLY** — changes require human approval
-- Circuit breaker at -3.0% P&L — may only be made **stricter**
-- Fat-finger protection: max 30% of cash per order — always enforced
-- Confidence 임계값 (market_outlook별, 낮출 수 없음): BEARISH ≥ 90, NEUTRAL/기본 ≥ 80, BULLISH ≥ 75
-- All code changes → corresponding tests → coverage ≥ 80%
-
-## Contributing
-
-See [docs/workflow.md](docs/workflow.md) for the complete development process.
-
-**TL;DR:**
-1. Create issue in Gitea
-2. Create feature branch: `feature/issue-N-description`
-3. Implement with tests
-4. Open PR
-5. Merge after review

agents.md

@@ -0,0 +1,199 @@
+# The Ouroboros
+
+AI-powered trading agent for global stock markets with self-evolution capabilities.
+
+## Agent Workflow Gate (Claude/Codex)
+
+Before any implementation, both Claude and Codex must align on the same project process:
+
+1. Read `docs/workflow.md` first (branch policy, issue/PR flow, merge rules).
+2. Read `docs/commands.md` for required verification commands and failure handling.
+3. Read `docs/agent-constraints.md` and `docs/agents.md` for safety constraints.
+4. Check `workflow/session-handover.md` and append a session entry when starting or handing off work.
+5. Confirm current branch is based on `main` or an explicitly designated temporary/base branch before editing.
+
+If any instruction conflicts, default to the safer path and document the reason in the handover log.
+
+## Quick Start
+
+```bash
+# Setup
+pip install -e ".[dev]"
+cp .env.example .env
+# Edit .env with your KIS and Gemini API credentials
+
+# Test
+pytest -v --cov=src
+
+# Run (paper trading)
+python -m src.main --mode=paper
+
+# Run with dashboard
+python -m src.main --mode=paper --dashboard
+```
+
+## Telegram Notifications (Optional)
+
+Get real-time alerts for trades, circuit breakers, and system events via Telegram.
+
+### Quick Setup
+
+1. **Create bot**: Message [@BotFather](https://t.me/BotFather) on Telegram → `/newbot`
+2. **Get chat ID**: Message [@userinfobot](https://t.me/userinfobot) → `/start`
+3. **Configure**: Add to `.env`:
+   ```bash
+   TELEGRAM_BOT_TOKEN=1234567890:ABCdefGHIjklMNOpqrsTUVwxyz
+   TELEGRAM_CHAT_ID=123456789
+   TELEGRAM_ENABLED=true
+   ```
+4. **Test**: Start bot conversation (`/start`), then run the agent
+
+**Full documentation**: [src/notifications/README.md](src/notifications/README.md)
+
+### What You'll Get
+
+- 🟢 Trade execution alerts (BUY/SELL with confidence)
+- 🚨 Circuit breaker trips (automatic trading halt)
+- ⚠️ Fat-finger rejections (oversized orders blocked)
+- ℹ️ Market open/close notifications
+- 📝 System startup/shutdown status
+
+### Interactive Commands
+
+With `TELEGRAM_COMMANDS_ENABLED=true` (default), the bot supports 9 bidirectional commands: `/help`, `/status`, `/positions`, `/report`, `/scenarios`, `/review`, `/dashboard`, `/stop`, `/resume`.
+
+**Fail-safe**: Notifications never crash the trading system. Missing credentials or API errors are logged but trading continues normally.
+
+## Smart Volatility Scanner (Optional)
+
+Python-first filtering pipeline that reduces Gemini API calls by pre-filtering stocks using technical indicators.
+
+### How It Works
+
+1. **Fetch Rankings** — KIS API volume surge rankings (top 30 stocks)
+2. **Python Filter** — RSI + volume ratio calculations (no AI)
+   - Volume > 200% of previous day
+   - RSI(14) < 30 (oversold) OR RSI(14) > 70 (momentum)
+3. **AI Judgment** — Only qualified candidates (1-3 stocks) sent to Gemini
+
+### Configuration
+
+Add to `.env` (optional, has sensible defaults):
+```bash
+RSI_OVERSOLD_THRESHOLD=30    # 0-50, default 30
+RSI_MOMENTUM_THRESHOLD=70    # 50-100, default 70
+VOL_MULTIPLIER=2.0           # Volume threshold (2.0 = 200%)
+SCANNER_TOP_N=3              # Max candidates per scan
+```
+
+### Benefits
+
+- **Reduces API costs** — Process 1-3 stocks instead of 20-30
+- **Python-based filtering** — Fast technical analysis before AI
+- **Evolution-ready** — Selection context logged for strategy optimization
+- **Fault-tolerant** — Falls back to static watchlist on API failure
+
+### Trading Mode Integration
+
+Smart Scanner runs in both `TRADE_MODE=realtime` and `daily` paths. On API failure, domestic stocks fall back to a static watchlist; overseas stocks fall back to a dynamic universe (active positions, recent holdings).
+
+## Documentation
+
+- **[Documentation Hub](docs/README.md)** — Top-level doc routing and reading order
+- **[Workflow Guide](docs/workflow.md)** — Git workflow policy and agent-based development
+- **[Command Reference](docs/commands.md)** — Common failures, build commands, troubleshooting
+- **[Architecture](docs/architecture.md)** — System design, components, data flow
+- **[Context Tree](docs/context-tree.md)** — L1-L7 hierarchical memory system
+- **[Testing](docs/testing.md)** — Test structure, coverage requirements, writing tests
+- **[Agent Policies](docs/agents.md)** — Prime directives, constraints, prohibited actions
+- **[Requirements Log](docs/requirements-log.md)** — User requirements and feedback tracking
+- **[Live Trading Checklist](docs/live-trading-checklist.md)** — 모의→실전 전환 체크리스트
+
+## Core Principles
+
+1. **Safety First** — Risk manager is READ-ONLY and enforces circuit breakers
+2. **Test Everything** — 80% coverage minimum, all changes require tests
+3. **Issue-Driven Development** — All work goes through Gitea issues → feature branches → PRs
+4. **Agent Specialization** — Use dedicated agents for design, coding, testing, docs, review
+
+## Requirements Management
+
+User requirements and feedback are tracked in [docs/requirements-log.md](docs/requirements-log.md):
+
+- New requirements are added chronologically with dates
+- Code changes should reference related requirements
+- Helps maintain project evolution aligned with user needs
+- Preserves context across conversations and development cycles
+
+## Project Structure
+
+```
+src/
+├── analysis/        # Technical analysis (RSI, volatility, smart scanner)
+├── backup/          # Disaster recovery (scheduler, cloud storage, health)
+├── brain/           # Gemini AI decision engine (prompt optimizer, context selector)
+├── broker/          # KIS API client (domestic + overseas)
+├── context/         # L1-L7 hierarchical memory system
+├── core/            # Risk manager (READ-ONLY)
+├── dashboard/       # FastAPI read-only monitoring (10 API endpoints)
+├── data/            # External data integration (news, market data, calendar)
+├── evolution/       # Self-improvement (optimizer, daily review, scorecard)
+├── logging/         # Decision logger (audit trail)
+├── markets/         # Market schedules and timezone handling
+├── notifications/   # Telegram alerts + bidirectional commands (9 commands)
+├── strategy/        # Pre-market planner, scenario engine, playbook store
+├── db.py            # SQLite trade logging
+├── main.py          # Trading loop orchestrator
+└── config.py        # Settings (from .env)
+
+tests/               # 998 tests across 41 files
+docs/                # Extended documentation
+```
+
+## Key Commands
+
+```bash
+pytest -v --cov=src              # Run tests with coverage
+ruff check src/ tests/           # Lint
+mypy src/ --strict               # Type check
+
+python -m src.main --mode=paper  # Paper trading
+python -m src.main --mode=paper --dashboard  # With dashboard
+python -m src.main --mode=live   # Live trading (⚠️ real money)
+
+# Gitea workflow (requires tea CLI)
+YES="" ~/bin/tea issues create --repo jihoson/The-Ouroboros --title "..." --description "..."
+YES="" ~/bin/tea pulls create --head feature-branch --base main --title "..." --description "..."
+```
+
+## Markets Supported
+
+- 🇰🇷 Korea (KRX)
+- 🇺🇸 United States (NASDAQ, NYSE, AMEX)
+- 🇯🇵 Japan (TSE)
+- 🇭🇰 Hong Kong (SEHK)
+- 🇨🇳 China (Shanghai, Shenzhen)
+- 🇻🇳 Vietnam (Hanoi, HCM)
+
+Markets auto-detected based on timezone and enabled in `ENABLED_MARKETS` env variable.
+
+## Critical Constraints
+
+⚠️ **Non-Negotiable Rules** (see [docs/agents.md](docs/agents.md)):
+
+- `src/core/risk_manager.py` is **READ-ONLY** — changes require human approval
+- Circuit breaker at -3.0% P&L — may only be made **stricter**
+- Fat-finger protection: max 30% of cash per order — always enforced
+- Confidence 임계값 (market_outlook별, 낮출 수 없음): BEARISH ≥ 90, NEUTRAL/기본 ≥ 80, BULLISH ≥ 75
+- All code changes → corresponding tests → coverage ≥ 80%
+
+## Contributing
+
+See [docs/workflow.md](docs/workflow.md) for the complete development process.
+
+**TL;DR:**
+1. Create issue in Gitea
+2. Create feature branch: `feature/issue-N-description`
+3. Implement with tests
+4. Open PR
+5. Merge after review

scripts/run_overnight.sh

@@ -8,8 +8,32 @@ CHECK_INTERVAL="${CHECK_INTERVAL:-30}"
 TMUX_AUTO="${TMUX_AUTO:-true}"
 TMUX_ATTACH="${TMUX_ATTACH:-true}"
 TMUX_SESSION_PREFIX="${TMUX_SESSION_PREFIX:-ouroboros_overnight}"
+STARTUP_GRACE_SEC="${STARTUP_GRACE_SEC:-3}"
+dashboard_port="${DASHBOARD_PORT:-8080}"
+APP_CMD_BIN="${APP_CMD_BIN:-}"
+APP_CMD_ARGS="${APP_CMD_ARGS:-}"
+RUNS_DASHBOARD="false"
 
-if [ -z "${APP_CMD:-}" ]; then
+# Custom override contract:
+# 1) Preferred: APP_CMD_BIN + APP_CMD_ARGS
+#    - APP_CMD_BIN is treated as a single executable token.
+#    - APP_CMD_ARGS uses shell-style word splitting; quote/escape inside this
+#      variable is NOT preserved as a nested shell parse.
+# 2) Legacy fallback: APP_CMD (raw shell command string)
+#    - This path remains for backward compatibility.
+#    - When APP_CMD includes --dashboard, caller should include explicit
+#      DASHBOARD_PORT assignment in APP_CMD if non-default port is required.
+
+if [ -n "$APP_CMD_BIN" ]; then
+    USE_DEFAULT_APP_CMD="false"
+    USE_SAFE_CUSTOM_APP_CMD="true"
+    APP_CMD="${APP_CMD_BIN} ${APP_CMD_ARGS}"
+    if [[ " $APP_CMD_ARGS " == *" --dashboard "* ]]; then
+        RUNS_DASHBOARD="true"
+    fi
+elif [ -z "${APP_CMD:-}" ]; then
+    USE_DEFAULT_APP_CMD="true"
+    USE_SAFE_CUSTOM_APP_CMD="false"
     if [ -x ".venv/bin/python" ]; then
         PYTHON_BIN=".venv/bin/python"
     elif command -v python3 >/dev/null 2>&1; then
@@ -21,9 +45,14 @@ if [ -z "${APP_CMD:-}" ]; then
         exit 1
     fi
 
-    dashboard_port="${DASHBOARD_PORT:-8080}"
+    APP_CMD="$PYTHON_BIN -m src.main --mode=live --dashboard"
-
+    RUNS_DASHBOARD="true"
-    APP_CMD="DASHBOARD_PORT=$dashboard_port $PYTHON_BIN -m src.main --mode=live --dashboard"
+else
+    USE_DEFAULT_APP_CMD="false"
+    USE_SAFE_CUSTOM_APP_CMD="false"
+    if [[ "$APP_CMD" == *"--dashboard"* ]]; then
+        RUNS_DASHBOARD="true"
+    fi
 fi
 
 mkdir -p "$LOG_DIR"
@@ -34,6 +63,24 @@ WATCHDOG_LOG="$LOG_DIR/watchdog_${timestamp}.log"
 PID_FILE="$LOG_DIR/app.pid"
 WATCHDOG_PID_FILE="$LOG_DIR/watchdog.pid"
 
+is_port_in_use() {
+    local port="$1"
+    if command -v ss >/dev/null 2>&1; then
+        ss -ltn 2>/dev/null | grep -Eq ":${port}[[:space:]]"
+        return $?
+    fi
+    if command -v lsof >/dev/null 2>&1; then
+        lsof -nP -iTCP:"$port" -sTCP:LISTEN >/dev/null 2>&1
+        return $?
+    fi
+    if command -v netstat >/dev/null 2>&1; then
+        netstat -ltn 2>/dev/null | grep -Eq "[:.]${port}[[:space:]]"
+        return $?
+    fi
+    # No supported socket inspection command found.
+    return 1
+}
+
 if [ -f "$PID_FILE" ]; then
     old_pid="$(cat "$PID_FILE" || true)"
     if [ -n "$old_pid" ] && kill -0 "$old_pid" 2>/dev/null; then
@@ -43,7 +90,29 @@ if [ -f "$PID_FILE" ]; then
 fi
 
 echo "[$(date -u +"%Y-%m-%dT%H:%M:%SZ")] starting: $APP_CMD" | tee -a "$RUN_LOG"
-nohup bash -lc "$APP_CMD" >>"$RUN_LOG" 2>&1 &
+if [ "$RUNS_DASHBOARD" = "true" ] && is_port_in_use "$dashboard_port"; then
+    echo "[$(date -u +"%Y-%m-%dT%H:%M:%SZ")] startup failed: dashboard port ${dashboard_port} already in use" | tee -a "$RUN_LOG"
+    exit 1
+fi
+
+if [ "$USE_DEFAULT_APP_CMD" = "true" ]; then
+    # Default path avoids shell word-splitting on executable paths.
+    nohup env DASHBOARD_PORT="$dashboard_port" "$PYTHON_BIN" -m src.main --mode=live --dashboard >>"$RUN_LOG" 2>&1 &
+elif [ "$USE_SAFE_CUSTOM_APP_CMD" = "true" ]; then
+    # Safer custom path: executable path is handled as a single token.
+    if [ -n "$APP_CMD_ARGS" ]; then
+        # shellcheck disable=SC2206
+        app_args=( $APP_CMD_ARGS )
+        nohup env DASHBOARD_PORT="$dashboard_port" "$APP_CMD_BIN" "${app_args[@]}" >>"$RUN_LOG" 2>&1 &
+    else
+        nohup env DASHBOARD_PORT="$dashboard_port" "$APP_CMD_BIN" >>"$RUN_LOG" 2>&1 &
+    fi
+else
+    # Custom APP_CMD is treated as a shell command string.
+    # If executable paths include spaces, they must be quoted inside APP_CMD.
+    # Legacy compatibility path: caller owns quoting and env var injection.
+    nohup bash -lc "exec env $APP_CMD" >>"$RUN_LOG" 2>&1 &
+fi
 app_pid=$!
 echo "$app_pid" > "$PID_FILE"
 
@@ -54,6 +123,20 @@ nohup env PID_FILE="$PID_FILE" LOG_FILE="$WATCHDOG_LOG" CHECK_INTERVAL="$CHECK_I
 watchdog_pid=$!
 echo "$watchdog_pid" > "$WATCHDOG_PID_FILE"
 
+sleep "$STARTUP_GRACE_SEC"
+if ! kill -0 "$app_pid" 2>/dev/null; then
+    echo "[$(date -u +"%Y-%m-%dT%H:%M:%SZ")] startup failed: app process exited early (pid=$app_pid)" | tee -a "$RUN_LOG"
+    [ -n "${watchdog_pid:-}" ] && kill "$watchdog_pid" 2>/dev/null || true
+    tail -n 20 "$RUN_LOG" || true
+    exit 1
+fi
+if ! kill -0 "$watchdog_pid" 2>/dev/null; then
+    echo "[$(date -u +"%Y-%m-%dT%H:%M:%SZ")] startup failed: watchdog exited early (pid=$watchdog_pid)" | tee -a "$WATCHDOG_LOG"
+    kill "$app_pid" 2>/dev/null || true
+    tail -n 20 "$WATCHDOG_LOG" || true
+    exit 1
+fi
+
 cat <<EOF
 시작 완료
 - app pid: $app_pid

scripts/runtime_verify_monitor.sh

@@ -7,12 +7,15 @@ ROOT_DIR="${ROOT_DIR:-/home/agentson/repos/The-Ouroboros}"
 LOG_DIR="${LOG_DIR:-$ROOT_DIR/data/overnight}"
 INTERVAL_SEC="${INTERVAL_SEC:-60}"
 MAX_HOURS="${MAX_HOURS:-24}"
+MAX_LOOPS="${MAX_LOOPS:-0}"
 POLICY_TZ="${POLICY_TZ:-Asia/Seoul}"
+DASHBOARD_PORT="${DASHBOARD_PORT:-8080}"
 
 cd "$ROOT_DIR"
 
 OUT_LOG="$LOG_DIR/runtime_verify_$(date +%Y%m%d_%H%M%S).log"
 END_TS=$(( $(date +%s) + MAX_HOURS*3600 ))
+loops=0
 
 log() {
   printf '%s %s\n' "$(date -u +%Y-%m-%dT%H:%M:%SZ)" "$1" | tee -a "$OUT_LOG" >/dev/null
@@ -31,6 +34,11 @@ check_signal() {
   return 1
 }
 
+find_live_pids() {
+  # Detect live-mode process even when run_overnight pid files are absent.
+  pgrep -af "[s]rc.main --mode=live" 2>/dev/null | awk '{print $1}' | tr '\n' ',' | sed 's/,$//'
+}
+
 check_forbidden() {
   local name="$1"
   local pattern="$2"
@@ -44,42 +52,94 @@ check_forbidden() {
   return 0
 }
 
+is_port_listening() {
+  local port="$1"
+
+  if command -v ss >/dev/null 2>&1; then
+    ss -ltn 2>/dev/null | grep -Eq ":${port}[[:space:]]"
+    return $?
+  fi
+  if command -v lsof >/dev/null 2>&1; then
+    lsof -nP -iTCP:"$port" -sTCP:LISTEN >/dev/null 2>&1
+    return $?
+  fi
+  if command -v netstat >/dev/null 2>&1; then
+    netstat -ltn 2>/dev/null | grep -Eq "[:.]${port}[[:space:]]"
+    return $?
+  fi
+  return 1
+}
+
 log "[INFO] runtime verify monitor started interval=${INTERVAL_SEC}s max_hours=${MAX_HOURS} policy_tz=${POLICY_TZ}"
 
 while true; do
+  loops=$((loops + 1))
   now=$(date +%s)
   if [ "$now" -ge "$END_TS" ]; then
     log "[INFO] monitor completed (time window reached)"
     exit 0
   fi
+  if [ "$MAX_LOOPS" -gt 0 ] && [ "$loops" -gt "$MAX_LOOPS" ]; then
+    log "[INFO] monitor completed (max loops reached)"
+    exit 0
+  fi
 
   latest_run="$(ls -t "$LOG_DIR"/run_*.log 2>/dev/null | head -n1 || true)"
-  if [ -z "$latest_run" ]; then
-    log "[ANOMALY] no run log found"
-    sleep "$INTERVAL_SEC"
-    continue
-  fi
 
   # Basic liveness hints.
   app_pid="$(cat "$LOG_DIR/app.pid" 2>/dev/null || true)"
   wd_pid="$(cat "$LOG_DIR/watchdog.pid" 2>/dev/null || true)"
+  live_pids="$(find_live_pids)"
   app_alive=0
   wd_alive=0
   port_alive=0
   [ -n "$app_pid" ] && kill -0 "$app_pid" 2>/dev/null && app_alive=1
   [ -n "$wd_pid" ] && kill -0 "$wd_pid" 2>/dev/null && wd_alive=1
-  ss -ltnp 2>/dev/null | rg -q ':8080' && port_alive=1
+  if [ "$app_alive" -eq 0 ] && [ -n "$live_pids" ]; then
-  log "[HEARTBEAT] run_log=$latest_run app_alive=$app_alive watchdog_alive=$wd_alive port8080=$port_alive"
+    app_alive=1
+  fi
+  is_port_listening "$DASHBOARD_PORT" && port_alive=1
+  log "[HEARTBEAT] run_log=${latest_run:-none} app_alive=$app_alive watchdog_alive=$wd_alive port=${DASHBOARD_PORT} alive=$port_alive live_pids=${live_pids:-none}"
+
+  defer_log_checks=0
+  if [ -z "$latest_run" ] && [ "$app_alive" -eq 1 ]; then
+    defer_log_checks=1
+    log "[INFO] run log not yet available; defer log-based coverage checks"
+  fi
+
+  if [ -z "$latest_run" ] && [ "$defer_log_checks" -eq 0 ]; then
+    log "[ANOMALY] no run log found"
+  fi
 
   # Coverage matrix rows (session paths and policy gate evidence).
   not_observed=0
-  check_signal "LIVE_MODE" "Mode: live" "$latest_run" || not_observed=$((not_observed+1))
+  if [ "$app_alive" -eq 1 ]; then
-  check_signal "KR_LOOP" "Processing market: Korea Exchange" "$latest_run" || not_observed=$((not_observed+1))
+    log "[COVERAGE] LIVE_MODE=PASS source=process_liveness"
-  check_signal "NXT_PATH" "NXT_PRE|NXT_AFTER|session=NXT_" "$latest_run" || not_observed=$((not_observed+1))
+  else
-  check_signal "US_PRE_PATH" "US_PRE|session=US_PRE" "$latest_run" || not_observed=$((not_observed+1))
+    if [ -n "$latest_run" ]; then
-  check_signal "US_DAY_PATH" "US_DAY|session=US_DAY|Processing market: .*NASDAQ|Processing market: .*NYSE|Processing market: .*AMEX" "$latest_run" || not_observed=$((not_observed+1))
+      check_signal "LIVE_MODE" "Mode: live" "$latest_run" || not_observed=$((not_observed+1))
-  check_signal "US_AFTER_PATH" "US_AFTER|session=US_AFTER" "$latest_run" || not_observed=$((not_observed+1))
+    else
-  check_signal "ORDER_POLICY_SESSION" "Order policy rejected .*\\[session=" "$latest_run" || not_observed=$((not_observed+1))
+      log "[COVERAGE] LIVE_MODE=NOT_OBSERVED reason=no_run_log_no_live_pid"
+      not_observed=$((not_observed+1))
+    fi
+  fi
+  if [ "$defer_log_checks" -eq 1 ]; then
+    for deferred in KR_LOOP NXT_PATH US_PRE_PATH US_DAY_PATH US_AFTER_PATH ORDER_POLICY_SESSION; do
+      log "[COVERAGE] ${deferred}=DEFERRED reason=no_run_log_process_alive"
+    done
+  elif [ -n "$latest_run" ]; then
+    check_signal "KR_LOOP" "Processing market: Korea Exchange" "$latest_run" || not_observed=$((not_observed+1))
+    check_signal "NXT_PATH" "NXT_PRE|NXT_AFTER|session=NXT_" "$latest_run" || not_observed=$((not_observed+1))
+    check_signal "US_PRE_PATH" "US_PRE|session=US_PRE" "$latest_run" || not_observed=$((not_observed+1))
+    check_signal "US_DAY_PATH" "US_DAY|session=US_DAY|Processing market: .*NASDAQ|Processing market: .*NYSE|Processing market: .*AMEX" "$latest_run" || not_observed=$((not_observed+1))
+    check_signal "US_AFTER_PATH" "US_AFTER|session=US_AFTER" "$latest_run" || not_observed=$((not_observed+1))
+    check_signal "ORDER_POLICY_SESSION" "Order policy rejected .*\\[session=" "$latest_run" || not_observed=$((not_observed+1))
+  else
+    for missing in KR_LOOP NXT_PATH US_PRE_PATH US_DAY_PATH US_AFTER_PATH ORDER_POLICY_SESSION; do
+      log "[COVERAGE] ${missing}=NOT_OBSERVED reason=no_run_log"
+      not_observed=$((not_observed+1))
+    done
+  fi
 
   if [ "$not_observed" -gt 0 ]; then
     log "[ANOMALY] coverage_not_observed=$not_observed (treat as FAIL)"
@@ -95,11 +155,17 @@ while true; do
     is_weekend=1
   fi
 
-  if [ "$is_weekend" -eq 1 ]; then
+  if [ "$defer_log_checks" -eq 1 ]; then
+    log "[FORBIDDEN] WEEKEND_KR_SESSION_ACTIVE=SKIP reason=no_run_log_process_alive"
+  elif [ "$is_weekend" -eq 1 ]; then
     # Weekend policy: KR regular session loop must never appear.
-    check_forbidden "WEEKEND_KR_SESSION_ACTIVE" \
+    if [ -n "$latest_run" ]; then
-      "Market session active: KR|session=KRX_REG|Processing market: Korea Exchange" \
+      check_forbidden "WEEKEND_KR_SESSION_ACTIVE" \
-      "$latest_run" || forbidden_hits=$((forbidden_hits+1))
+        "Market session active: KR|session=KRX_REG|Processing market: Korea Exchange" \
+        "$latest_run" || forbidden_hits=$((forbidden_hits+1))
+    else
+      log "[FORBIDDEN] WEEKEND_KR_SESSION_ACTIVE=SKIP reason=no_run_log"
+    fi
   else
     log "[FORBIDDEN] WEEKEND_KR_SESSION_ACTIVE=SKIP reason=weekday"
   fi

scripts/validate_pr_body.py

@@ -5,6 +5,8 @@ from __future__ import annotations
 
 import argparse
 import json
+import os
+import shutil
 import re
 import subprocess
 import sys
@@ -12,11 +14,31 @@ from pathlib import Path
 
 HEADER_PATTERN = re.compile(r"^##\s+\S+", re.MULTILINE)
 LIST_ITEM_PATTERN = re.compile(r"^\s*(?:-|\*|\d+\.)\s+\S+", re.MULTILINE)
+FENCED_CODE_PATTERN = re.compile(r"```.*?```", re.DOTALL)
+INLINE_CODE_PATTERN = re.compile(r"`[^`]*`")
+
+
+def _strip_code_segments(text: str) -> str:
+    without_fences = FENCED_CODE_PATTERN.sub("", text)
+    return INLINE_CODE_PATTERN.sub("", without_fences)
+
+
+def resolve_tea_binary() -> str:
+    tea_from_path = shutil.which("tea")
+    if tea_from_path:
+        return tea_from_path
+
+    tea_home = Path.home() / "bin" / "tea"
+    if tea_home.exists() and tea_home.is_file() and os.access(tea_home, os.X_OK):
+        return str(tea_home)
+
+    raise RuntimeError("tea binary not found (checked PATH and ~/bin/tea)")
 
 
 def validate_pr_body_text(text: str) -> list[str]:
     errors: list[str] = []
-    if "\\n" in text and "\n" not in text:
+    searchable = _strip_code_segments(text)
+    if "\\n" in searchable:
         errors.append("body contains escaped newline sequence (\\n)")
     if text.count("```") % 2 != 0:
         errors.append("body has unbalanced fenced code blocks (``` count is odd)")
@@ -28,10 +50,11 @@ def validate_pr_body_text(text: str) -> list[str]:
 
 
 def fetch_pr_body(pr_number: int) -> str:
+    tea_binary = resolve_tea_binary()
     try:
         completed = subprocess.run(
             [
-                "tea",
+                tea_binary,
                 "api",
                 "-R",
                 "origin",
@@ -41,7 +64,7 @@ def fetch_pr_body(pr_number: int) -> str:
             capture_output=True,
             text=True,
         )
-    except (subprocess.CalledProcessError, FileNotFoundError) as exc:
+    except (subprocess.CalledProcessError, FileNotFoundError, PermissionError) as exc:
         raise RuntimeError(f"failed to fetch PR #{pr_number}: {exc}") from exc
 
     try:

src/main.py

@@ -2084,6 +2084,15 @@ async def trading_cycle(
                 quantity=quantity,
                 price=order_price,
             )
+            if result.get("rt_cd", "0") != "0":
+                order_succeeded = False
+                msg1 = result.get("msg1") or ""
+                logger.warning(
+                    "KR order not accepted for %s: rt_cd=%s msg=%s",
+                    stock_code,
+                    result.get("rt_cd"),
+                    msg1,
+                )
         else:
             # For overseas orders, always use limit orders (지정가):
             # - KIS market orders (ORD_DVSN=01) calculate quantity based on upper limit
@@ -3293,6 +3302,15 @@ async def run_daily_session(
                             quantity=quantity,
                             price=order_price,
                         )
+                        if result.get("rt_cd", "0") != "0":
+                            order_succeeded = False
+                            daily_msg1 = result.get("msg1") or ""
+                            logger.warning(
+                                "KR order not accepted for %s: rt_cd=%s msg=%s",
+                                stock_code,
+                                result.get("rt_cd"),
+                                daily_msg1,
+                            )
                     else:
                         # KIS VTS only accepts limit orders; use 0.5% premium for BUY
                         if decision.action == "BUY":

tests/test_main.py

@@ -913,6 +913,46 @@ class TestTradingCycleTelegramIntegration:
         # Verify notification was attempted
         mock_telegram.notify_trade_execution.assert_called_once()
 
+    @pytest.mark.asyncio
+    async def test_kr_rejected_order_does_not_notify_or_log_trade(
+        self,
+        mock_broker: MagicMock,
+        mock_overseas_broker: MagicMock,
+        mock_scenario_engine: MagicMock,
+        mock_playbook: DayPlaybook,
+        mock_risk: MagicMock,
+        mock_db: MagicMock,
+        mock_decision_logger: MagicMock,
+        mock_context_store: MagicMock,
+        mock_criticality_assessor: MagicMock,
+        mock_telegram: MagicMock,
+        mock_market: MagicMock,
+    ) -> None:
+        """KR orders rejected by KIS should not trigger success side effects."""
+        mock_broker.send_order = AsyncMock(
+            return_value={"rt_cd": "1", "msg1": "장운영시간이 아닙니다."}
+        )
+
+        with patch("src.main.log_trade") as mock_log_trade:
+            await trading_cycle(
+                broker=mock_broker,
+                overseas_broker=mock_overseas_broker,
+                scenario_engine=mock_scenario_engine,
+                playbook=mock_playbook,
+                risk=mock_risk,
+                db_conn=mock_db,
+                decision_logger=mock_decision_logger,
+                context_store=mock_context_store,
+                criticality_assessor=mock_criticality_assessor,
+                telegram=mock_telegram,
+                market=mock_market,
+                stock_code="005930",
+                scan_candidates={},
+            )
+
+        mock_telegram.notify_trade_execution.assert_not_called()
+        mock_log_trade.assert_not_called()
+
     @pytest.mark.asyncio
     async def test_fat_finger_notification_sent(
         self,

tests/test_runtime_overnight_scripts.py

@@ -0,0 +1,160 @@
+from __future__ import annotations
+
+import os
+import signal
+import socket
+import subprocess
+from pathlib import Path
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+RUN_OVERNIGHT = REPO_ROOT / "scripts" / "run_overnight.sh"
+RUNTIME_MONITOR = REPO_ROOT / "scripts" / "runtime_verify_monitor.sh"
+
+
+def _latest_runtime_log(log_dir: Path) -> str:
+    logs = sorted(log_dir.glob("runtime_verify_*.log"))
+    assert logs, "runtime monitor did not produce log output"
+    return logs[-1].read_text(encoding="utf-8")
+
+
+def test_runtime_verify_monitor_detects_live_process_without_pid_files(tmp_path: Path) -> None:
+    log_dir = tmp_path / "overnight"
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    fake_live = subprocess.Popen(
+        ["bash", "-lc", 'exec -a "src.main --mode=live" sleep 10'],
+        cwd=REPO_ROOT,
+    )
+    try:
+        env = os.environ.copy()
+        env.update(
+            {
+                "ROOT_DIR": str(REPO_ROOT),
+                "LOG_DIR": str(log_dir),
+                "INTERVAL_SEC": "1",
+                "MAX_HOURS": "1",
+                "MAX_LOOPS": "1",
+                "POLICY_TZ": "UTC",
+            }
+        )
+        completed = subprocess.run(
+            ["bash", str(RUNTIME_MONITOR)],
+            cwd=REPO_ROOT,
+            env=env,
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        assert completed.returncode == 0, completed.stderr
+
+        log_text = _latest_runtime_log(log_dir)
+        assert "app_alive=1" in log_text
+        assert "[COVERAGE] LIVE_MODE=PASS source=process_liveness" in log_text
+        assert "[ANOMALY]" not in log_text
+    finally:
+        fake_live.terminate()
+        fake_live.wait(timeout=5)
+
+
+def test_run_overnight_fails_fast_when_dashboard_port_in_use(tmp_path: Path) -> None:
+    log_dir = tmp_path / "overnight"
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    sock.bind(("127.0.0.1", 0))
+    sock.listen(1)
+    port = sock.getsockname()[1]
+    try:
+        env = os.environ.copy()
+        env.update(
+            {
+                "LOG_DIR": str(log_dir),
+                "TMUX_AUTO": "false",
+                "DASHBOARD_PORT": str(port),
+            }
+        )
+        completed = subprocess.run(
+            ["bash", str(RUN_OVERNIGHT)],
+            cwd=REPO_ROOT,
+            env=env,
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        assert completed.returncode != 0
+        output = f"{completed.stdout}\n{completed.stderr}"
+        assert "already in use" in output
+    finally:
+        sock.close()
+
+
+def test_run_overnight_writes_live_pid_and_watchdog_pid(tmp_path: Path) -> None:
+    log_dir = tmp_path / "overnight"
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    env = os.environ.copy()
+    env.update(
+        {
+            "LOG_DIR": str(log_dir),
+            "TMUX_AUTO": "false",
+            "STARTUP_GRACE_SEC": "1",
+            "CHECK_INTERVAL": "2",
+            "APP_CMD_BIN": "sleep",
+            "APP_CMD_ARGS": "10",
+        }
+    )
+    completed = subprocess.run(
+        ["bash", str(RUN_OVERNIGHT)],
+        cwd=REPO_ROOT,
+        env=env,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    assert completed.returncode == 0, f"{completed.stdout}\n{completed.stderr}"
+
+    app_pid = int((log_dir / "app.pid").read_text(encoding="utf-8").strip())
+    watchdog_pid = int((log_dir / "watchdog.pid").read_text(encoding="utf-8").strip())
+
+    os.kill(app_pid, 0)
+    os.kill(watchdog_pid, 0)
+
+    for pid in (watchdog_pid, app_pid):
+        try:
+            os.kill(pid, signal.SIGTERM)
+        except ProcessLookupError:
+            pass
+
+
+def test_run_overnight_fails_when_process_exits_before_grace_period(tmp_path: Path) -> None:
+    log_dir = tmp_path / "overnight"
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    env = os.environ.copy()
+    env.update(
+        {
+            "LOG_DIR": str(log_dir),
+            "TMUX_AUTO": "false",
+            "STARTUP_GRACE_SEC": "1",
+            "APP_CMD_BIN": "false",
+        }
+    )
+    completed = subprocess.run(
+        ["bash", str(RUN_OVERNIGHT)],
+        cwd=REPO_ROOT,
+        env=env,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    assert completed.returncode != 0
+    output = f"{completed.stdout}\n{completed.stderr}"
+    assert "startup failed:" in output
+
+    watchdog_pid_file = log_dir / "watchdog.pid"
+    if watchdog_pid_file.exists():
+        watchdog_pid = int(watchdog_pid_file.read_text(encoding="utf-8").strip())
+        with pytest.raises(ProcessLookupError):
+            os.kill(watchdog_pid, 0)

tests/test_validate_pr_body.py

@@ -24,9 +24,24 @@ def test_validate_pr_body_text_detects_escaped_newline() -> None:
     assert any("escaped newline" in err for err in errors)
 
 
-def test_validate_pr_body_text_allows_literal_sequence_when_multiline() -> None:
+def test_validate_pr_body_text_detects_escaped_newline_in_multiline_body() -> None:
     module = _load_module()
-    text = "## Summary\n- escaped sequence example: \\\\n"
+    text = "## Summary\n- first line\n- broken line with \\n literal"
+    errors = module.validate_pr_body_text(text)
+    assert any("escaped newline" in err for err in errors)
+
+
+def test_validate_pr_body_text_allows_escaped_newline_in_code_blocks() -> None:
+    module = _load_module()
+    text = "\n".join(
+        [
+            "## Summary",
+            "- example uses `\\n` for explanation",
+            "```bash",
+            "printf 'line1\\nline2\\n'",
+            "```",
+        ]
+    )
     assert module.validate_pr_body_text(text) == []
 
 
@@ -63,12 +78,13 @@ def test_fetch_pr_body_reads_body_from_tea_api(monkeypatch) -> None:
     module = _load_module()
 
     def fake_run(cmd, check, capture_output, text):  # noqa: ANN001
-        assert "tea" in cmd[0]
+        assert cmd[0] == "/tmp/tea-bin"
         assert check is True
         assert capture_output is True
         assert text is True
         return SimpleNamespace(stdout=json.dumps({"body": "## Summary\n- item"}))
 
+    monkeypatch.setattr(module, "resolve_tea_binary", lambda: "/tmp/tea-bin")
     monkeypatch.setattr(module.subprocess, "run", fake_run)
     assert module.fetch_pr_body(391) == "## Summary\n- item"
 
@@ -79,6 +95,32 @@ def test_fetch_pr_body_rejects_non_string_body(monkeypatch) -> None:
     def fake_run(cmd, check, capture_output, text):  # noqa: ANN001
         return SimpleNamespace(stdout=json.dumps({"body": 123}))
 
+    monkeypatch.setattr(module, "resolve_tea_binary", lambda: "/tmp/tea-bin")
     monkeypatch.setattr(module.subprocess, "run", fake_run)
     with pytest.raises(RuntimeError):
         module.fetch_pr_body(391)
+
+
+def test_resolve_tea_binary_falls_back_to_home_bin(monkeypatch, tmp_path) -> None:
+    module = _load_module()
+    tea_home = tmp_path / "bin" / "tea"
+    tea_home.parent.mkdir(parents=True)
+    tea_home.write_text("#!/usr/bin/env bash\n", encoding="utf-8")
+    tea_home.chmod(0o755)
+
+    monkeypatch.setattr(module.shutil, "which", lambda _: None)
+    monkeypatch.setattr(module.Path, "home", lambda: tmp_path)
+    assert module.resolve_tea_binary() == str(tea_home)
+
+
+def test_resolve_tea_binary_rejects_non_executable_home_bin(monkeypatch, tmp_path) -> None:
+    module = _load_module()
+    tea_home = tmp_path / "bin" / "tea"
+    tea_home.parent.mkdir(parents=True)
+    tea_home.write_text("not executable\n", encoding="utf-8")
+    tea_home.chmod(0o644)
+
+    monkeypatch.setattr(module.shutil, "which", lambda _: None)
+    monkeypatch.setattr(module.Path, "home", lambda: tmp_path)
+    with pytest.raises(RuntimeError):
+        module.resolve_tea_binary()