initial: canary multi-agent skills with tmux isolation support

- lib.sh: TMUX_SERVER_NAME env var, _tmux helper, shim externalized to TMPDIR with recursive guard, resolve_tmux_server helper for YAML-driven server routing - multi-agent-create: --tmux-server opt-in flag, YAML tmux_server field for orphan prevention - multi-agent-delete/resume/status/agent-sessions-monitor: use resolve_tmux_server to auto-route to correct isolated server - SKILL.md × 4: documented isolation server workflow - Verified by claude review (R1+re-run) + agy R2 patches (orphan prevention + shim location fix)
2026-06-19 13:32:36 +00:00
commit 8a3abff2d6
13 changed files with 2184 additions and 0 deletions
@@ -0,0 +1,274 @@
+#!/usr/bin/env bash
+# reconcile.sh — agent-sessions-monitor 의 부속 스크립트
+# YAML ↔ tmux ↔ 디스크 artifact 간 drift 감지 (+ YAML 자동 갱신).
+#
+# Usage:
+#   bash reconcile.sh --once --emit-diff            # drift 감지 + 갱신
+#   bash reconcile.sh --once --emit-diff --dry-run  # drift 만 계산, 쓰기 안 함 (P1-E)
+#
+# --dry-run: 부수효과 없는 read-only. "지금 뭐 돌고 있지?" 질문에 안전.
+#            multi-agent-status 스킬이 이걸 재사용.
+#
+# 출력 (JSON): {timestamp, yaml_path, tmux_sessions_alive, tmux_confirmed, drifts, actions}
+#
+# Exit codes: 0 = ok | 1 = YAML not found | 2 = error
+set -euo pipefail
+
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/lib.sh"
+
+STATE_DIR="${AGENT_SESSIONS_STATE_DIR:-$HOME/.cache/agent-sessions-monitor}"
+
+ONCE=0
+EMIT_DIFF=0
+DRY_RUN=0
+
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --once) ONCE=1; shift ;;
+    --emit-diff) EMIT_DIFF=1; shift ;;
+    --dry-run) DRY_RUN=1; shift ;;
+    -h|--help) echo "Usage: $0 [--once] [--emit-diff] [--dry-run]"; exit 0 ;;
+    *) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
+  esac
+done
+
+[ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found" >&2; exit 1; }
+mkdir -p "$STATE_DIR"
+
+# 모든 비교 로직을 단일 소스로 둔다. dry-run 은 env_python(읽기전용), 그 외엔
+# atomic_dump_yaml(flock + temp+rename) 로 같은 소스를 돌린다. atomic 래퍼에서는
+# 'actions' 가 없으면 SystemExit(0) 으로 쓰기를 건너뛴다 (불필요한 재포맷 방지).
+read -r -d '' RECON_SRC <<'PYEOF' || true
+import os, json, glob, subprocess, time
+from datetime import datetime, timezone
+import yaml
+
+yaml_path = os.environ['YAML_PATH']
+home = os.environ['HOME_DIR']
+
+now_iso = datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')
+
+# atomic 래퍼에서는 d 가 이미 로드돼 있음. env_python(dry-run)에서는 여기서 로드.
+try:
+    d
+except NameError:
+    with open(yaml_path) as f:
+        d = yaml.safe_load(f) or {}
+
+drifts = []
+actions = []
+
+# === 현재 tmux 상태 — transient 실패를 'no sessions' 와 구분 (P1-E) ===
+tmux_sessions = []
+tmux_confirmed = True
+
+# YAML 에 등록된 고유한 tmux_server 목록 수집 + 환경변수 TMUX_SERVER_NAME 포함
+unique_servers = {'default'}
+if 'TMUX_SERVER_NAME' in os.environ:
+    unique_servers.add(os.environ['TMUX_SERVER_NAME'])
+for s in d.get('tmux_sessions', []):
+    srv = s.get('tmux_server') or 'default'
+    unique_servers.add(srv)
+
+try:
+    for srv in sorted(unique_servers):
+        cmd = ['tmux']
+        if srv != 'default':
+            cmd += ['-L', srv]
+        cmd += ['ls', '-F', '#{session_name}|#{session_created}']
+        r = subprocess.run(cmd, capture_output=True, text=True)
+        if r.returncode == 0:
+            for line in r.stdout.strip().split('\n'):
+                if not line:
+                    continue
+                name, created = line.split('|', 1)
+                tmux_sessions.append({'name': name, 'created': int(created), 'server': srv})
+        else:
+            err = (r.stderr or '').lower()
+            is_empty = ('no server running' in err) or ('no sessions' in err) or ('failed to connect' in err)
+            if not is_empty:
+                tmux_confirmed = False
+except Exception:
+    tmux_confirmed = False
+
+
+def pane_meta(session, srv):
+    try:
+        cmd = ['tmux']
+        if srv != 'default':
+            cmd += ['-L', srv]
+        cmd += ['list-panes', '-t', session, '-F',
+                '#{pane_pid}|#{pane_current_path}|#{pane_current_command}']
+        out = subprocess.check_output(cmd, text=True)
+        parts = out.strip().split('\n')[0].split('|')
+        return {'pid': int(parts[0]), 'cwd': parts[1], 'cmd': parts[2]}
+    except Exception:
+        return None
+
+
+yaml_sessions = d.get('tmux_sessions', [])
+yaml_session_names = {s['name'] for s in yaml_sessions if s.get('name')}
+alive_set = {(t['name'], t.get('server', 'default')) for t in tmux_sessions}
+
+# === drift A: tmux dead + YAML running → auto-terminate ===
+# tmux 응답을 확정했을 때만. transient 실패 시 모두 terminated 로 마크하지 않음 (P1-E)
+if tmux_confirmed:
+    for s in yaml_sessions:
+        name = s.get('name')
+        if not name:
+            continue
+        if s.get('status') in ('terminated', 'archived'):
+            continue
+        srv = s.get('tmux_server') or 'default'
+        if (name, srv) not in alive_set:
+            s['status'] = 'terminated'
+            s['terminated_at'] = now_iso
+            s['terminated_at_epoch'] = int(datetime.now(timezone.utc).timestamp())
+            s['termination_mode'] = 'auto-detected (tmux gone)'
+            pane = s.get('pane') or {}
+            drifts.append({'class': 'A', 'name': name,
+                           'msg': f"{name}: tmux gone (was pane {pane.get('pid')}, cmd {pane.get('cmd')}). Marked terminated."})
+            actions.append(f"terminated: {name}")
+
+# === drift B: tmux alive + not in YAML → auto-register ===
+if tmux_confirmed:
+    for t in tmux_sessions:
+        name = t['name']
+        if name in yaml_session_names:
+            continue
+        if not (name.endswith('-creator-claude') or name.endswith('-creator-agy')):
+            continue
+        srv = t.get('server', 'default')
+        pm = pane_meta(name, srv)
+        if not pm:
+            continue
+        agent = 'claude' if name.endswith('-creator-claude') else 'agy'
+        cmd_full = 'claude' if agent == 'claude' else 'agy --dangerously-skip-permissions'
+        server_opt = f"-L {srv} " if srv != 'default' else ""
+        entry = {
+            'name': name,
+            'status': 'running',
+            'tmux_session_created_at': datetime.fromtimestamp(t['created'], tz=timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ'),
+            'tmux_session_epoch': t['created'],
+            'tmux_server': srv,
+            'pane': {'index': 0, 'pid': pm['pid'], 'cmd': agent, 'cmd_full': cmd_full, 'cwd': pm['cwd']},
+            # P2: cwd 인용
+            'start_command': f'tmux {server_opt}new-session -d -s "{name}" -x 140 -y 40 -c "{pm["cwd"]}" "{cmd_full}"',
+            'attach_command': f'tmux {server_opt}attach -t {name}',
+            'kill_command': f'tmux {server_opt}kill-session -t {name}',
+            'last_visible_status': 'auto-registered by monitor',
+        }
+        if agent == 'claude':
+            entry['tui'] = {'model': '(unknown — capture after first message)', 'provider': 'anthropic',
+                            'plan': '(unknown)', 'account': '(unknown)', 'version': '(unknown)'}
+            entry['claude_session_id_own'] = None
+        else:
+            entry['child_pid'] = 0
+            entry['agy_conversation_id_own'] = None
+            entry['mcp_attachments'] = [
+                {
+                    'name': 'stitch',
+                    'transport': 'mcp-remote',
+                    'endpoint': 'https://stitch.googleapis.com/mcp'
+                }
+            ]
+        d.setdefault('tmux_sessions', []).append(entry)
+        yaml_session_names.add(name)
+        drifts.append({'class': 'B', 'name': name,
+                       'msg': f"{name}: tmux found but not in YAML. Auto-registered (pane {pm['pid']}, cmd {pm['cmd']}, cwd {pm['cwd']})."})
+        actions.append(f"registered: {name}")
+
+# === drift C: claude 새 session id materialize (per-row own id) ===
+for s in d.get('tmux_sessions', []):
+    if not s.get('name', '').endswith('-creator-claude'):
+        continue
+    if s.get('status') != 'running':
+        continue
+    if s.get('claude_session_id_own'):
+        continue
+    cwd = (s.get('pane') or {}).get('cwd', '')
+    if not cwd:
+        continue
+    proj_key = cwd.replace('/', '-').replace('_', '-')
+    proj_dir = f"{home}/.claude/projects/{proj_key}"
+    if not os.path.isdir(proj_dir):
+        continue
+    jsonls = sorted(glob.glob(f"{proj_dir}/*.jsonl"), key=os.path.getmtime, reverse=True)
+    if not jsonls:
+        continue
+    latest = jsonls[0]
+    if time.time() - os.path.getmtime(latest) > 300:
+        continue
+    try:
+        with open(latest) as f:
+            first = f.readline().strip()
+        if not first:
+            continue
+        sid = json.loads(first).get('sessionId')
+        if not sid:
+            continue
+    except Exception:
+        continue
+    s['claude_session_id_own'] = sid
+    drifts.append({'class': 'C', 'name': s['name'], 'msg': f"{s['name']}: session id materialized: {sid}"})
+    actions.append(f"updated session id: {sid}")
+
+# === drift C (agy): agy 새 session id materialize (per-row own id) ===
+for s in d.get('tmux_sessions', []):
+    if not s.get('name', '').endswith('-creator-agy'):
+        continue
+    if s.get('status') != 'running':
+        continue
+    if s.get('agy_conversation_id_own'):
+        continue
+    cwd = (s.get('pane') or {}).get('cwd', '')
+    if not cwd:
+        continue
+    lc = f"{home}/.gemini/antigravity-cli/cache/last_conversations.json"
+    if os.path.exists(lc):
+        try:
+            with open(lc) as f:
+                lc_data = json.load(f)
+            cid = lc_data.get(cwd)
+            if cid and os.path.exists(f"{home}/.gemini/antigravity-cli/conversations/{cid}.db"):
+                s['agy_conversation_id_own'] = cid
+                drifts.append({'class': 'C', 'name': s['name'], 'msg': f"{s['name']}: conversation id materialized: {cid}"})
+                actions.append(f"updated conversation id: {cid}")
+        except Exception:
+            pass
+
+# === drift D: stale UUID (cache 의 artifact 가 사라짐) — 보고만, 변경 없음 ===
+ai = d.get('agent_identities', {}) or {}
+cl = (ai.get('claude') or {})
+if cl.get('session_id'):
+    sid = cl['session_id']
+    if not glob.glob(f"{home}/.claude/projects/*/{sid}.jsonl"):
+        drifts.append({'class': 'D', 'name': '(claude identity cache)',
+                       'msg': f"stale UUID in agent_identities.claude.session_id: {sid} (jsonl missing)"})
+ag = (ai.get('agy') or {})
+if ag.get('conversation_id'):
+    cid = ag['conversation_id']
+    if not os.path.exists(f"{home}/.gemini/antigravity-cli/conversations/{cid}.db"):
+        drifts.append({'class': 'D', 'name': '(agy identity cache)',
+                       'msg': f"stale UUID in agent_identities.agy.conversation_id: {cid} (.db missing)"})
+
+result = {
+    'timestamp': now_iso,
+    'yaml_path': yaml_path,
+    'tmux_sessions_alive': sorted(f"{t['name']}|{t.get('server', 'default')}" for t in tmux_sessions),
+    'tmux_confirmed': tmux_confirmed,
+    'drifts': drifts,
+    'actions': actions,
+}
+print(json.dumps(result, indent=2, ensure_ascii=False))
+
+# atomic 래퍼: actions 가 없으면 쓰기를 건너뛴다. env_python(dry-run)에선 무해.
+if not actions:
+    raise SystemExit(0)
+PYEOF
+
+if [ "$DRY_RUN" = "1" ]; then
+  printf '%s' "$RECON_SRC" | env_python "$AGENT_SESSIONS_YAML"
+else
+  printf '%s' "$RECON_SRC" | atomic_dump_yaml "$AGENT_SESSIONS_YAML"
+fi