fix(deploy): resolve SQL timeouts, YAML drift, and orphaned tmux sessions

- lib.sh: update atomic_dump_yaml to sync with YAML on any active session status change; set reader timeouts to 60.0s
- create_session.sh: add exit trap cleanup_tmux_on_error to rollback spawned tmux sessions on initialization failures
- reconcile.sh, update_yaml_resumed.sh, status.sh, stop_session.sh: align SQLite connection timeout values to 60.0s

.agents/skills/lib.sh

@@ -115,7 +115,7 @@ yaml_path = os.environ['YAML_PATH']
 db_path = os.path.splitext(yaml_path)[0] + '.db'
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         try:
             row = conn.execute('SELECT data FROM sessions WHERE name=?', (name,)).fetchone()
             if row:
@@ -315,6 +315,9 @@ def _validate(d):
 def get_terminal_set(d):
     return {s.get('name'): s.get('status') for s in d.get('tmux_sessions', []) if s.get('status') in ('stopped', 'terminated', 'archived')}
 
+def get_all_sessions_status(d):
+    return {s.get('name'): s.get('status') for s in d.get('tmux_sessions', [])}
+
 os.makedirs(os.path.dirname(db_path) or '.', exist_ok=True)
 conn = sqlite3.connect(db_path, timeout=60.0)
 
@@ -367,7 +370,7 @@ try:
     elif 'tmux_sessions' not in d:
         d['tmux_sessions'] = []
 
-    old_terminals = get_terminal_set(d)
+    old_sessions = get_all_sessions_status(d)
     old_roles = {s.get('name'): s.get('role') for s in db_sessions if s.get('role')}
 
     # --- caller mutation (module scope: sees d, yaml, os, glob, subprocess) ---
@@ -400,13 +403,12 @@ try:
     else:
         conn.execute('DELETE FROM sessions')
 
-    new_terminals = get_terminal_set(d)
+    new_sessions = get_all_sessions_status(d)
 
     conn.commit()
     
-    # Write to YAML ONLY when a session transitions to a finished state
-    # (Moved after conn.commit() per Claude's feedback)
-    if new_terminals != old_terminals:
+    # Write to YAML when sessions status or session list changes (e.g. create/stop/resume)
+    if new_sessions != old_sessions:
         if os.path.exists(yaml_path):
             try:
                 shutil.copy2(yaml_path, yaml_path + '.bak')
@@ -509,7 +511,7 @@ def emit(u):
 sessions = []
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         has_sessions_table = False
         try:
             cursor = conn.execute('SELECT data FROM sessions WHERE pane_cwd=?', (ws,))
@@ -621,7 +623,7 @@ elif agent == 'cline':
 ai = {}
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         row = conn.execute('SELECT data FROM state WHERE id=1').fetchone()
         if row:
             ai = json.loads(row[0]).get('agent_identities', {})
@@ -687,7 +689,7 @@ yaml_path = os.environ['YAML_PATH']
 db_path = os.path.splitext(yaml_path)[0] + '.db'
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         has_sessions_table = False
         try:
             row = conn.execute('SELECT status, data FROM sessions WHERE name=?', (name,)).fetchone()

.agents/skills/multi-agent-mux-create/scripts/create_session.sh

@@ -145,6 +145,16 @@ fi
 
 spawn
 
+# Trap for rolling back/cleaning up tmux session if script exits due to error
+cleanup_tmux_on_error() {
+  local exit_code=$?
+  if [ $exit_code -ne 0 ]; then
+    echo "⚠️ Error occurred during initialization. Rolling back and killing tmux session '$SESSION_NAME'..." >&2
+    _tmux kill-session -t "$SESSION_NAME" 2>/dev/null || true
+  fi
+}
+trap cleanup_tmux_on_error EXIT
+
 # TUI 준비 대기
 wait_for_tui_ready "$SESSION_NAME" "$AGENT"
 
@@ -333,6 +343,8 @@ Task: $SUBMIT_JOB_PROMPT"
   WD_PID=$(start_watchdog "$DELEGATE_JOB_ID" "$WORKSPACE")
   echo "watchdog PID: $WD_PID"
 fi
+# Clear cleanup trap as registration was fully successful
+trap - EXIT
 echo "agent-sessions.yaml updated"
 echo
 if [ -n "${TMUX_SERVER_NAME:-}" ] && [ "$TMUX_SERVER_NAME" != "default" ]; then

.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh

@@ -301,7 +301,7 @@ except NameError:
     d = {}
     try:
         if os.path.exists(db_path):
-            conn = sqlite3.connect(db_path, timeout=10.0)
+            conn = sqlite3.connect(db_path, timeout=60.0)
             row = conn.execute('SELECT data FROM state WHERE id=1').fetchone()
             if row: d = json.loads(row[0])
             

.agents/skills/multi-agent-mux-resume/scripts/update_yaml_resumed.sh

@@ -65,7 +65,7 @@ db_path = os.path.splitext(yaml_path)[0] + '.db'
 d = {}
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         try:
             row = conn.execute('SELECT data FROM sessions WHERE name=?', (name,)).fetchone()
             if row:

.agents/skills/multi-agent-mux-status/scripts/status.sh

@@ -42,7 +42,7 @@ d = {}
 import sqlite3
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         row = conn.execute('SELECT data FROM state WHERE id=1').fetchone()
         if row: d = json.loads(row[0])
         

.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh

@@ -91,7 +91,7 @@ db_path = os.path.splitext(yaml_path)[0] + '.db'
 d = {}
 try:
     if os.path.exists(db_path):
-        conn = sqlite3.connect(db_path, timeout=10.0)
+        conn = sqlite3.connect(db_path, timeout=60.0)
         try:
             row = conn.execute('SELECT data FROM sessions WHERE name=?', (name,)).fetchone()
             if row: