multi-agent-mux/skills/tmux-agent-orchestrate-stop/scripts/stop_session.sh

#!/usr/bin/env bash
# stop_session.sh — tmux-agent-orchestrate-stop 의 부속 스크립트
# Usage:
#   bash stop_session.sh --session <name> [--agent claude|agy] \
#       [--mode soft|hard] [--purge-conversation] [--yes]
#
# mode:
#   soft  — YAML 을 status=archived 로 마크, tmux 세션은 그대로 둠 (P1-A:
#           terminated 는 tmux 가 실제로 죽은 상태에만 사용)
#   hard  — tmux kill-session + YAML status=terminated
# --purge-conversation: --mode hard 일 때만. 삭제 대상 세션의 *워크스페이스에
#                       격리된* conversation artifact 만 삭제 (P0-C). 전역
#                       agent_identities 를 참조하지 않음. resume 불가.
#
# Stop extension (Option A — delete 확장, 새 6번째 스킬 없이 stop 의미론 흡수):
#   --capture-id   — kill 직전에 이 워크스페이스의 conversation id 를 row 에 확정
#                    기록 (claude_session_id_own / agy_conversation_id_own) →
#                    다음 resume 이 tier-1(race-free) 로 복원. find_workspace_uuid
#                    재사용 (per-row -> workspace-scoped disk scan -> cache).
#   --reason R     — 상태 전이 사유 (stop_reason). 기본값 manual_stop.
#   --graceful     — kill-session 즉시 종료 대신 send-keys 로 정상 종료 유도 →
#                    3초 대기 → 미종료 시 kill-session(SIGTERM) → 5초 → SIGKILL.
#   위 세 옵션 중 하나라도 주면 STOP 모드: status 가 terminated 가 아니라 stopped
#   로 전이 (running -> stopped). 멱등: 이미 stopped 면 no-op + exit 0.
#   옵션 미지정 시 기존 hard/soft 동작 그대로 (backward compatible).
#
# Exit codes:
#   0 = success (or already-stopped no-op) | 1 = YAML not found / not registered
#   2 = invalid args | 3 = interactive confirmation required (--yes 누락)
set -euo pipefail

source "$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/lib.sh"

usage() {
  cat <<EOF
Usage: $0 --session <name> [--agent claude|agy] [--mode soft|hard] [--purge-conversation] [--yes]
       [--capture-id] [--reason <reason>] [--graceful]

Modes:
  soft            — update YAML to status=archived, leave tmux running
  hard  (default) — tmux kill-session + update YAML to status=terminated

Stop extension (any of these → STOP mode, status=stopped instead of terminated):
  --capture-id      — record this workspace's conversation id to the row before kill
  --reason <reason> — stop_reason field (default: manual_stop)
  --graceful        — send-keys exit → 3s → kill-session → 5s → SIGKILL fallback
  (idempotent: stopping an already-stopped session is a no-op with exit 0)
EOF
}

SESSION_NAME=""
AGENT=""
MODE="hard"   # "delete" 의 자연스러운 의미 = tmux 까지 종료
PURGE=0
YES=0
CAPTURE_ID=0
GRACEFUL=0
REASON=""
STOP_MODE=0

while [ $# -gt 0 ]; do
  case "$1" in
    --session) SESSION_NAME="$2"; shift 2 ;;
    --agent)   AGENT="$2";        shift 2 ;;
    --mode)    MODE="$2";         shift 2 ;;
    --purge-conversation) PURGE=1; shift ;;
    --yes)     YES=1; shift ;;
    --capture-id) CAPTURE_ID=1; STOP_MODE=1; shift ;;
    --reason)  REASON="$2"; STOP_MODE=1; shift 2 ;;
    --graceful) GRACEFUL=1; STOP_MODE=1; shift ;;
    -h|--help) usage; exit 0 ;;
    *) echo "ERROR: unknown arg: $1" >&2; usage; exit 2 ;;
  esac
done
[ -n "$SESSION_NAME" ] || { echo "ERROR: --session required" >&2; usage; exit 2; }
[ "$MODE" = "soft" ] || [ "$MODE" = "hard" ] || { echo "ERROR: --mode must be soft or hard" >&2; exit 2; }
[ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found" >&2; exit 1; }

# STOP 모드 기본 사유
if [ "$STOP_MODE" = "1" ] && [ -z "$REASON" ]; then
  REASON="manual_stop"
fi

export TMUX_SERVER_NAME="$(resolve_tmux_server "$SESSION_NAME")"

# --agent 미지정 시 이름 suffix 로 fallback (P1-F)
if [ -z "$AGENT" ]; then
  case "$SESSION_NAME" in
    *-creator-claude) AGENT=claude ;;
    *-creator-agy)    AGENT=agy ;;
    *) echo "ERROR: cannot infer agent from '$SESSION_NAME'; pass --agent" >&2; exit 2 ;;
  esac
fi

# 세션이 YAML 에 있는지 + 해당 row 의 워크스페이스 cwd 및 delegate_job_id 추출.
# JSON 으로 emit — cwd 에 '|' 가 들어가도 안전 (review item 7; 기존 cwd|jid 파서 대체).
MAPPED_DATA=$(env_python "$AGENT_SESSIONS_YAML" SESSION_NAME="$SESSION_NAME" <<'PYEOF'
import os, json, yaml
name = os.environ['SESSION_NAME']
with open(os.environ['YAML_PATH']) as f:
    d = yaml.safe_load(f) or {}
for s in d.get('tmux_sessions', []):
    if s.get('name') == name:
        cwd = (s.get('pane') or {}).get('cwd', '')
        jid = s.get('delegate_job_id', '') or ''
        print(json.dumps({"cwd": cwd, "job_id": jid}))
        raise SystemExit(0)
raise SystemExit(7)
PYEOF
) || {
  echo "ERROR: session '$SESSION_NAME' not in $AGENT_SESSIONS_YAML" >&2
  exit 1
}

TARGET_CWD=$(printf '%s' "$MAPPED_DATA" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("cwd",""))')
DELEGATE_JOB_ID=$(printf '%s' "$MAPPED_DATA" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("job_id",""))')

# 멱등성: STOP 모드에서 이미 stopped 인 세션이면 no-op + exit 0
if [ "$STOP_MODE" = "1" ]; then
  if STOPPED_INFO=$(is_already_stopped "$SESSION_NAME"); then
    echo "already stopped (status=stopped, $STOPPED_INFO) — no-op"
    exit 0
  fi
fi

# purge 확인
if [ "$PURGE" = "1" ] && [ "$YES" != "1" ]; then
  echo "DANGER: --purge-conversation will DELETE this workspace's on-disk conversation."
  echo "  workspace: ${TARGET_CWD:-<unknown>}"
  echo "  This means: no future tmux-agent-orchestrate-resume for this session."
  echo "  Re-run with --yes to confirm."
  exit 3
fi

# purge 대상 UUID 를 워크스페이스 격리해서 해결 (P0-C — 전역 참조 금지)
PURGE_UUID=""
if [ "$PURGE" = "1" ] && [ -n "$TARGET_CWD" ]; then
  PURGE_UUID=$(find_workspace_uuid "$TARGET_CWD" "$AGENT" || true)
fi

NOW_ISO=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
NOW_EPOCH=$(date +%s)

# tmux 상태 + 마지막 TUI 스냅샷 (살아있을 때만; capture-pane 내용은 env 로만 전달)
TMUX_ALIVE=0
LAST_STATUS=""
if tmux has-session -t "$SESSION_NAME" 2>/dev/null; then
  TMUX_ALIVE=1
  LAST_STATUS=$(tmux capture-pane -t "$SESSION_NAME" -p -S -10 2>/dev/null | tr '\n' ' ' | head -c 500 || true)
fi

# --capture-id: kill 직전에 conversation id 를 해결 (process/jsonl 이 아직 살아있을 때).
# find_workspace_uuid 가 tier-1(row) -> tier-2(workspace-scoped disk scan) -> tier-3(cache)
# 를 알아서 시도하므로 tmux 생사와 무관하게 동작.
CAPTURED_UUID=""
if [ "$CAPTURE_ID" = "1" ] && [ -n "$TARGET_CWD" ]; then
  CAPTURED_UUID=$(capture_conversation_id "$AGENT" "$TARGET_CWD" || true)
  if [ -n "$CAPTURED_UUID" ]; then
    echo "captured conversation id: $CAPTURED_UUID"
  else
    echo "WARN: --capture-id requested but no conversation id resolved (nothing on disk yet)"
  fi
fi

delegate_publish_event "$DELEGATE_JOB_ID" progress "terminating"

# --graceful: send-keys 로 정상 종료 유도 → 폴백 체인 (SIGTERM → SIGKILL).
graceful_stop() {
  local pane_pid exitkey
  pane_pid=$(tmux list-panes -t "$SESSION_NAME" -F '#{pane_pid}' 2>/dev/null | head -1 || true)
  case "$AGENT" in
    claude) exitkey="/exit" ;;
    agy)    exitkey="Exit" ;;
    *)      exitkey="/exit" ;;
  esac
  echo "graceful: send-keys '$exitkey' to $SESSION_NAME"
  tmux send-keys -t "$SESSION_NAME" "$exitkey" Enter 2>/dev/null || true
  sleep 3
  if ! tmux has-session -t "$SESSION_NAME" 2>/dev/null; then
    echo "graceful: exited cleanly"
    return 0
  fi
  echo "graceful: still alive → kill-session (SIGTERM)"
  tmux kill-session -t "$SESSION_NAME" 2>/dev/null || true
  sleep 5
  if ! tmux has-session -t "$SESSION_NAME" 2>/dev/null; then
    echo "graceful: terminated after kill-session"
    return 0
  fi
  echo "graceful: STILL alive → SIGKILL fallback (pane pid $pane_pid)"
  [ -n "$pane_pid" ] && kill -9 "$pane_pid" 2>/dev/null || true
}

# tmux 종료: graceful 이면 폴백 체인, 아니면 기존 hard kill.
if [ "$GRACEFUL" = "1" ] && [ "$TMUX_ALIVE" = "1" ]; then
  graceful_stop
elif [ "$MODE" = "hard" ] && [ "$TMUX_ALIVE" = "1" ]; then
  tmux kill-session -t "$SESSION_NAME"
  echo "killed tmux: $SESSION_NAME"
elif [ "$MODE" = "hard" ]; then
  echo "tmux already dead, just updating YAML"
fi

atomic_dump_yaml "$AGENT_SESSIONS_YAML" \
  SESSION_NAME="$SESSION_NAME" AGENT="$AGENT" MODE="$MODE" PURGE="$PURGE" \
  NOW_ISO="$NOW_ISO" NOW_EPOCH="$NOW_EPOCH" LAST_STATUS="$LAST_STATUS" \
  PURGE_UUID="$PURGE_UUID" TARGET_CWD="$TARGET_CWD" \
  STOP_MODE="$STOP_MODE" REASON="$REASON" GRACEFUL="$GRACEFUL" \
  CAPTURED_UUID="$CAPTURED_UUID" <<'PYEOF'
import shutil
name = os.environ['SESSION_NAME']
agent = os.environ['AGENT']
mode = os.environ['MODE']
purge = os.environ['PURGE'] == '1'
now = os.environ['NOW_ISO']
home = os.environ['HOME_DIR']
last_status = os.environ.get('LAST_STATUS', '')
purge_uuid = os.environ.get('PURGE_UUID', '').strip()
ws = os.environ.get('TARGET_CWD', '')
stop_mode = os.environ.get('STOP_MODE') == '1'
graceful = os.environ.get('GRACEFUL') == '1'
reason = os.environ.get('REASON', '') or 'manual_stop'
captured = os.environ.get('CAPTURED_UUID', '').strip()

target = None
for s in d.get('tmux_sessions', []):
    if s.get('name') == name:
        target = s
        break
if target is None:
    print(f"ERROR: disappeared during script: {name}", flush=True)
    raise SystemExit(1)

if mode == 'soft':
    # P1-A: soft 는 tmux 가 살아있으니 archived. terminated 아님.
    target['status'] = 'archived'
    target['archived_at'] = now
    target['termination_mode'] = 'soft'
elif stop_mode:
    # STOP 모드: running -> stopped (terminated 와 의도 구분). conversation 보존.
    target['status'] = 'stopped'
    target['stopped_at'] = now
    target['stopped_at_epoch'] = int(os.environ['NOW_EPOCH'])
    target['stop_reason'] = reason
    target['termination_mode'] = 'graceful' if graceful else 'stop'
else:
    target['status'] = 'terminated'
    target['terminated_at'] = now
    target['terminated_at_epoch'] = int(os.environ['NOW_EPOCH'])
    target['termination_mode'] = 'hard'

if last_status:
    target['last_visible_status_at_termination'] = last_status

# --capture-id: 해결된 conversation id 를 per-row own id 에 확정 기록 (tier-1 보장).
# purge 와 함께면 어차피 아래에서 지워지므로 기록하지 않는다.
if captured and not purge:
    if agent == 'claude':
        target['claude_session_id_own'] = captured
    elif agent == 'agy':
        target['agy_conversation_id_own'] = captured
    target['resumable'] = True

# --purge-conversation: 워크스페이스 격리된 UUID 의 디스크 artifact 만 삭제 (P0-C)
if purge and purge_uuid:
    if agent == 'claude':
        key = ws.replace('/', '-').replace('_', '-')
        claude_project_dir = os.environ.get('CLAUDE_PROJECT_DIR', f"{home}/.claude/projects")
        jsonl = f"{claude_project_dir}/{key}/{purge_uuid}.jsonl"
        if os.path.exists(jsonl):
            os.remove(jsonl)
            print(f"purged: {jsonl}", flush=True)
        target['claude_session_id_own'] = None
    elif agent == 'agy':
        db = f"{home}/.gemini/antigravity-cli/conversations/{purge_uuid}.db"
        if os.path.exists(db):
            os.remove(db)
            print(f"purged: {db}", flush=True)
        brain = f"{home}/.gemini/antigravity-cli/brain/{purge_uuid}"
        if os.path.isdir(brain):
            shutil.rmtree(brain)
            print(f"purged: {brain}", flush=True)
        target['agy_conversation_id_own'] = None
    # agent_identities 는 cache — 이 워크스페이스 것일 때만 비운다
    ai = (d.get('agent_identities') or {}).get(agent) or {}
    if ai.get('project_cwd') == ws:
        if agent == 'claude' and ai.get('session_id') == purge_uuid:
            ai['session_id'] = None
            ai['session_jsonl'] = None
            ai.pop('session_size_bytes', None)
            ai.pop('session_lines', None)
        elif agent == 'agy' and ai.get('conversation_id') == purge_uuid:
            ai['conversation_id'] = None
            ai['conversation_db'] = None
            ai['conversation_brain_dir'] = None
elif purge and not purge_uuid:
    print("WARN: --purge-conversation requested but no workspace-scoped UUID resolved; nothing purged", flush=True)

if purge:
    target['resumable'] = False

print(f"updated: {name} status={target['status']}", flush=True)
PYEOF

delegate_publish_event "$DELEGATE_JOB_ID" completed "session terminated"

echo
if [ "$STOP_MODE" = "1" ]; then
  echo "=== stop complete ==="
else
  echo "=== delete complete ==="
fi
echo "  session:  $SESSION_NAME"
echo "  agent:    $AGENT"
echo "  mode:     $MODE${STOP_MODE:+ (stop)}${GRACEFUL:+ +graceful}"
[ "$STOP_MODE" = "1" ] && echo "  reason:   $REASON"
[ "$CAPTURE_ID" = "1" ] && echo "  captured: ${CAPTURED_UUID:-<none>}"
echo "  purge:    $PURGE${PURGE_UUID:+ (uuid $PURGE_UUID)}"
echo "  time:     $NOW_ISO"
echo
echo "Recovery: tmux-agent-orchestrate-create + tmux-agent-orchestrate-resume 로 동일 컨텍스트 복원 가능"
echo "  (단 --purge-conversation 사용 시 복원 불가)"