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

#!/usr/bin/env bash
# stop_session.sh — multi-agent-mux-stop 의 부속 스크립트
# Usage:
#   bash stop_session.sh --session <name> [--agent claude|agy|hermes|cline] [--herdr-session <name>] \
#       [--reason <reason>] [--purge-conversation] [--yes]
#
# 동작: 항상 graceful stop 입니다. send-keys 로 정상 종료를 유도하고
#       (미종료 시 SIGTERM → SIGKILL 폴백), kill 직전에 이 워크스페이스의
#       conversation id 를 row 에 확정 기록해 다음 resume 이 tier-1(race-free)
#       으로 복원되게 합니다. status 는 running -> stopped 로 전이합니다.
#       멱등: 이미 stopped 면 no-op + exit 0.
#
# 옵션:
#   --session <name>        — 대상 세션 (필수)
#   --agent <type>          — claude | agy | hermes | cline
#                             (권장: 항상 명시. 미지정 시 레지스트리 기록으로
#                              해석 — agent 필드 → 세션명 접미사 → pane.cmd;
#                              셋 다 실패하면 exit 2)
#   --herdr-session <name>  — isolated herdr session name (alias: --herdr-server)
#   --reason <reason>       — 상태 전이 사유 (stop_reason). 기본값 manual_stop
#   --purge-conversation    — 디스크의 conversation artifact 까지 삭제.
#                             status=terminated, resumable=false 로 전이하며
#                             resume 불가. --yes 없이는 확인 프롬프트(exit 3)
#   --yes                   — --purge-conversation 의 확인 프롬프트 생략
#
# 폐지된 옵션: --mode / --capture-id / --graceful 는 각각 exit 2 로 거부됩니다.
#              graceful 종료와 id 캡처는 이제 무조건 수행되며, soft/hard 모드
#              구분은 --purge-conversation 유무로 대체되었습니다.
#
# Exit codes:
#   0 = success (or already-stopped no-op) | 1 = YAML not found / not registered
#   2 = invalid args | 3 = interactive confirmation required (--yes 누락)
#   4 = purge aborted (herdr session survived the kill chain)
set -euo pipefail

# shellcheck disable=SC1091
_script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
_lib_sh="$(cd "$_script_dir/../.." && pwd)/lib.sh"
[ -f "$_lib_sh" ] || _lib_sh="${WORKSPACE_ROOT:-$PWD}/.agents/skills/lib.sh"
source "$_lib_sh"

usage() {
  cat <<EOF
Usage: $0 --session <name> [--agent claude|agy|hermes|cline] [--herdr-session <name>]
          [--reason <reason>] [--purge-conversation] [--yes]

Arguments:
  --session <name>     — target session name (required)
  --agent <type>       — claude | agy | hermes | cline (recommended: always pass it)
                         (falls back to the registry record: agent field ->
                          session-name suffix -> pane.cmd)
  --herdr-session <name> — specify isolated herdr session name (alias: --herdr-server)
  --reason <reason>    — stop_reason field (default: manual_stop)
  --purge-conversation — also delete on-disk conversation artifacts;
                         status becomes terminated and resume is impossible
  --yes                — skip the --purge-conversation confirmation prompt

Stop is always graceful and always captures the conversation id.
(idempotent: stopping an already-stopped session is a no-op with exit 0)
EOF
}

SESSION_NAME=""
AGENT=""
HERDR_SERVER_OPT=""
PURGE=0
YES=0
CAPTURE_ID=1
GRACEFUL=1
REASON="manual_stop"
STOP_MODE=1

while [ $# -gt 0 ]; do
  case "$1" in
    --session) SESSION_NAME="$2"; shift 2 ;;
    --agent)   AGENT="$2";        shift 2 ;;
    --herdr-session|--herdr-server) HERDR_SERVER_OPT="$2"; shift 2 ;;
    --purge-conversation) PURGE=1; shift ;;
    --yes)     YES=1; shift ;;
    --reason)  REASON="$2";       shift 2 ;;
    --mode|--capture-id|--graceful)
      echo "ERROR: $1 option is deprecated. Stop now always stops gracefully and captures IDs." >&2
      exit 2
      ;;
    -h|--help) usage; exit 0 ;;
    *) echo "ERROR: unknown arg: $1" >&2; usage; exit 2 ;;
  esac
done
if [ -n "$AGENT" ]; then
  case "$AGENT" in
    claude|agy|hermes|cline) ;;
    *) echo "ERROR: invalid agent type '$AGENT'. Allowed types are: claude, agy, hermes, cline." >&2; exit 2 ;;
  esac
fi
[ -n "$SESSION_NAME" ] || { echo "ERROR: --session required" >&2; usage; exit 2; }
[ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found" >&2; exit 1; }

# Implement the purging-<session> file lock mechanism
if [ "$PURGE" = "1" ]; then
  touch "$WORKSPACE_ROOT/.mam/purging-$SESSION_NAME"
  trap 'rm -f "$WORKSPACE_ROOT/.mam/purging-$SESSION_NAME"' EXIT
fi

if [ -n "$HERDR_SERVER_OPT" ]; then
  export HERDR_SESSION_NAME="$HERDR_SERVER_OPT"
else
  HERDR_SESSION_NAME="$(resolve_herdr_workspace "$SESSION_NAME" "${WORKSPACE:-$WORKSPACE_ROOT}")"
  export HERDR_SESSION_NAME
fi

# --agent 미지정 시 레지스트리 기록으로 해석 (B-21).
# ① row['agent'] → ② 세션명 접미사 → ③ pane.cmd 순. 셋 다 실패하면
# 종전과 동일하게 exit 2 (헤더 :27-30 의 종료 코드 계약 유지).
if [ -z "$AGENT" ]; then
  AGENT="$(resolve_agent_type_from_registry "$SESSION_NAME")" || AGENT=""
  [ -n "$AGENT" ] || {
    echo "ERROR: cannot infer agent from '$SESSION_NAME'; pass --agent" >&2
    exit 2
  }
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=$(MAM_STATE_JSON="$(load_state_json)" SESSION_NAME="$SESSION_NAME" python3 -c "
import sys, os, json
name = os.environ['SESSION_NAME']
d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
for s in d.get('herdr_sessions', []):
    if s.get('name') == name:
        cwd = (s.get('pane') or {}).get('cwd', '')
        jid = s.get('delegate_job_id', '') or ''
        print(json.dumps({'cwd': cwd, 'job_id': jid}))
        sys.exit(0)
sys.exit(7)
") || {
  echo "ERROR: session '$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 세션이고 purge 가 아닐 때만 no-op + exit 0
if [ "$STOP_MODE" = "1" ] && [ "$PURGE" != "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 multi-agent-mux-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" "$AGENT" "$SESSION_NAME" || true)
fi

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

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

# 캡처: 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)
# 를 알아서 시도하므로 herdr 생사와 무관하게 동작.
CAPTURED_UUID=""
if [ "$CAPTURE_ID" = "1" ] && [ -n "$TARGET_CWD" ]; then
  CAPTURED_UUID=$(capture_conversation_id "$AGENT" "$TARGET_CWD" "$SESSION_NAME" || true)
  if [ -n "$CAPTURED_UUID" ]; then
    echo "captured conversation id: $CAPTURED_UUID"
  else
    echo "WARN: no conversation id resolved before stop (nothing on disk yet)"
  fi
fi

delegate_publish_event "$DELEGATE_JOB_ID" progress "terminating"

# graceful 종료: send-keys 로 정상 종료 유도 → 폴백 체인 (SIGTERM → SIGKILL).
graceful_stop() {
  local pane_pid exitkey
  pane_pid=$(herdr list-panes -t "$SESSION_NAME" -F '#{pane_pid}' 2>/dev/null | head -1 || true)
  exitkey="$("$(_delegate_py_bin)" -m lib_py.agents exit-key "$AGENT" 2>/dev/null || echo "/exit")"
  echo "graceful: send-keys '$exitkey' to $SESSION_NAME"
  send_keys_safe "$SESSION_NAME" "$exitkey" "stop$$" || echo "graceful: safe delivery failed (rc=$?) — falling back to kill chain"
  _wait_session_gone "$SESSION_NAME" 5 || true
  if ! herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
    echo "graceful: exited cleanly"
    return 0
  fi
  echo "graceful: still alive → kill-session (SIGTERM)"
  herdr kill-session -t "$SESSION_NAME" 2>/dev/null || true
  _wait_session_gone "$SESSION_NAME" 8 || true
  if ! herdr has-session -t "$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
}

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

# Purge pre-gate: 레코드 제거는 herdr 사망이 확인된 경우에만 허용한다.
# (kill 체인은 best-effort — 세션이 살아남으면 monitor drift-B 가
#  레코드 없는 세션을 running 으로 자동 재등록해 purge 가 조용히 뒤집힌다)
if [ "$PURGE" = "1" ] && [ "$HERDR_ALIVE" = "1" ]; then
  _wait_session_gone "$SESSION_NAME" 5 || true   # SIGKILL 폴백의 비동기 회수 윈도우 흡수
  if herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
    echo "ERROR: session '$SESSION_NAME' is still alive after the kill chain." >&2
    echo "  Refusing registry removal — records preserved (no state was modified)." >&2
    echo "  Diagnose the stuck TUI (herdr session attach '$SESSION_NAME'), then re-run" >&2
    echo "  stop_session.sh --purge-conversation --yes (retry is safe/idempotent)." >&2
    delegate_publish_event "$DELEGATE_JOB_ID" cancelled "purge aborted: session still alive; no state was modified"
    exit 4
  fi
fi

# INVARIANT: Terminal events for a job must be published AFTER atomic_dump_yaml updates the session status
atomic_dump_yaml "$AGENT_SESSIONS_YAML" \
  SESSION_NAME="$SESSION_NAME" AGENT="$AGENT" PURGE="$PURGE" \
  NOW_ISO="$NOW_ISO" NOW_EPOCH="$NOW_EPOCH" LAST_STATUS="$LAST_STATUS" \
  PURGE_UUID="$PURGE_UUID" TARGET_CWD="$TARGET_CWD" \
  REASON="$REASON" CAPTURED_UUID="$CAPTURED_UUID" <<'PYEOF'
import shutil
name = os.environ['SESSION_NAME']
agent = os.environ['AGENT']
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', '')
reason = os.environ.get('REASON', '') or 'manual_stop'
captured = os.environ.get('CAPTURED_UUID', '').strip()

target = None
for s in d.get('herdr_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 not purge:
    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 last_status:
    target['last_visible_status_at_termination'] = last_status

# 항상 captured UUID 기록 (purge 가 아닐 때만)
if captured and not purge:
    if agent == 'claude':
        target['claude_session_id_own'] = captured
    elif agent == 'agy':
        target['agy_conversation_id_own'] = captured
    elif agent == 'hermes':
        target['hermes_conversation_id_own'] = captured
    elif agent == 'cline':
        target['cline_conversation_id_own'] = captured
    target['resumable'] = True

if purge and purge_uuid:
    from lib_py.agents.registry import get_adapter
    from lib_py.agents.base import DiscoveryContext
    adapter = get_adapter(agent)
    if adapter:
        ctx = DiscoveryContext(workspace=ws, agent_name=agent, home_dir=home)
        for item in adapter.purge_artifacts(purge_uuid, ctx):
            print(f"purged: {item}", flush=True)
        target[adapter.own_key] = None
elif purge and not purge_uuid:
    print("WARN: --purge-conversation requested but no workspace-scoped UUID resolved; nothing purged", flush=True)

if purge:
    d['herdr_sessions'] = [s for s in d.get('herdr_sessions', []) if s.get('name') != name]
    if purge_uuid:
        print(f"removed: {name} (registry entry fully purged from YAML+DB)", flush=True)
    else:
        print(f"removed: {name} (registry entry purged from YAML+DB; WARN: conversation artifacts unresolved — disk copies may remain)", flush=True)
else:
    print(f"updated: {name} status={target['status']}", flush=True)
PYEOF

delegate_publish_event "$DELEGATE_JOB_ID" cancelled "session stopped by operator before job completion"

echo
echo "=== stop complete ==="
echo "  session:  $SESSION_NAME"
echo "  agent:    $AGENT"
echo "  reason:   $REASON"
echo "  captured: ${CAPTURED_UUID:-<none>}"
echo "  purge:    $PURGE${PURGE_UUID:+ (uuid $PURGE_UUID)}"
echo "  time:     $NOW_ISO"
echo
echo "Recovery: multi-agent-mux-create + multi-agent-mux-resume 로 동일 컨텍스트 복원 가능"
echo "  (단 --purge-conversation 사용 시 복원 불가)"