fix(agent-office): dead-letter _dl_notified 갱신을 발송성공 시로 한정 + collect_status 예외방어 (B4 리뷰)

- _dl_notified[name] = dl을 if ok: 블록 안으로 이동 — 텔레그램 실패 시 갱신 방지
- check_and_alert에 collect_status try/except 추가 — 스케줄러 잡 생존 보장
- tests: import app.node_monitor as nm 최상단 이동
- tests: test_dl_notified_not_updated_on_telegram_failure 회귀 테스트 추가

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019LV86jBozkNhSFXJA412fq

agent-office/app/node_monitor.py

@@ -107,7 +107,11 @@ async def check_and_alert(status=None) -> list[str]:
     """
     from .telegram.messaging import send_raw
     from .db import add_log
-    st = status or await collect_status()
+    try:
+        st = status or await collect_status()
+    except Exception:
+        logger.exception("collect_status 예외")
+        return []
     sent: list[str] = []
     for w in st["workers"]:
         name, alive = w["name"], w.get("alive", False)
@@ -129,7 +133,7 @@ async def check_and_alert(status=None) -> list[str]:
             if (await send_raw(text=text)).get("ok"):
                 add_log("node_monitor", f"{name} dead-letter {dl}", "warning")
                 sent.append(text)
-            _dl_notified[name] = dl
+                _dl_notified[name] = dl
         elif dl == 0:
             _dl_notified.pop(name, None)
     return sent

agent-office/tests/test_node_monitor.py

@@ -1,6 +1,7 @@
 # agent-office/tests/test_node_monitor.py
 import json, pytest
 from app import node_monitor
+import app.node_monitor as nm
 
 class FakeRedis:
     """worker heartbeat + queue llen + scan_iter 흉내."""
@@ -98,8 +99,6 @@ async def test_llen_exception_returns_redis_ok_false():
     assert st["redis_ok"] is False
 
 
-import app.node_monitor as nm
-
 @pytest.mark.asyncio
 async def test_alert_on_alive_to_dead(monkeypatch):
     sent = []
@@ -124,3 +123,25 @@ async def test_alert_on_dead_letter_growth(monkeypatch):
     s = {"workers": [{"name":"video-render","alive":True,"dead_letter":2}], "links": []}
     await nm.check_and_alert(status=s)
     assert any("dead-letter" in t for t in sent)
+
+@pytest.mark.asyncio
+async def test_dl_notified_not_updated_on_telegram_failure(monkeypatch):
+    """텔레그램 실패(ok=False) 시 _dl_notified 갱신 안 됨 → 다음 사이클에서 재시도."""
+    calls = []
+    async def fake_send_raw(text, **kw):
+        calls.append(text)
+        if len(calls) == 1:
+            return {"ok": False}   # 첫 호출: 텔레그램 다운
+        return {"ok": True}        # 두 번째 호출: 성공
+    monkeypatch.setattr("app.telegram.messaging.send_raw", fake_send_raw)
+    monkeypatch.setattr("app.db.add_log", lambda *a, **k: None)
+    nm._node_state.clear(); nm._dl_notified.clear()
+    s = {"workers": [{"name": "video-render", "alive": True, "dead_letter": 2}], "links": []}
+    # 첫 호출: 텔레그램 다운 → ok=False → _dl_notified 갱신 안 됨
+    result1 = await nm.check_and_alert(status=s)
+    assert result1 == []
+    assert nm._dl_notified.get("video-render", 0) == 0
+    # 두 번째 호출: 같은 dl=2 → _dl_notified 미갱신으로 조건 재만족 → 재시도 발송
+    result2 = await nm.check_and_alert(status=s)
+    assert any("dead-letter" in t for t in result2)
+    assert nm._dl_notified.get("video-render") == 2