diff --git a/apps/api/src/services/drift_narrator_service.py b/apps/api/src/services/drift_narrator_service.py
index 18a8a162..1806f398 100644
--- a/apps/api/src/services/drift_narrator_service.py
+++ b/apps/api/src/services/drift_narrator_service.py
@@ -204,27 +204,66 @@ class DriftNarratorService:
                 _raw = text.strip()
                 if _raw.startswith("```"):
                     _raw = _raw.strip("`").lstrip("json").strip()
+
+                # 解析策略: 3 路 fallback
+                # Path 1: 直接我們的 {narrative, items} 結構 (純 Ollama 或 LLM 守規矩)
+                # Path 2: NEMOTRON wrapper {description,...} 且 description 內含我們的結構
+                # Path 3: NEMOTRON wrapper,description 是純敘述 → 用它當 narrative + Python fallback items
+                _parsed_narrative = None
+                _parsed_items = None
                 try:
                     _parsed = _json.loads(_raw)
                     if isinstance(_parsed, dict):
-                        _narrative = str(_parsed.get("narrative", "")).strip()
-                        _items = _parsed.get("items", [])
-                        if isinstance(_items, list) and _narrative:
-                            clean_items = []
-                            for it in _items[:5]:
-                                if isinstance(it, dict) and it.get("field") and it.get("summary"):
-                                    clean_items.append({
-                                        "level": it.get("level", "medium"),
-                                        "field": str(it["field"])[:60],
-                                        "summary": str(it["summary"])[:80],
-                                    })
-                            if clean_items:
-                                narrative = _narrative
-                                items = clean_items
-                                status = "success"
-                                llm_accepted = True
+                        # Path 1
+                        if "narrative" in _parsed and isinstance(_parsed.get("items"), list):
+                            _parsed_narrative = str(_parsed["narrative"]).strip()
+                            _parsed_items = _parsed["items"]
+                        else:
+                            # Path 2 / Path 3: NEMOTRON wrapper
+                            _desc = (
+                                _parsed.get("description")
+                                or _parsed.get("action_title")
+                                or _parsed.get("reasoning")
+                                or ""
+                            )
+                            _desc = str(_desc).strip()
+                            # Path 2: description 本身是巢狀 JSON 含我們結構?
+                            if _desc.startswith("{") and "narrative" in _desc:
+                                try:
+                                    _inner = _json.loads(_desc)
+                                    if isinstance(_inner, dict) and "narrative" in _inner:
+                                        _parsed_narrative = str(_inner.get("narrative", "")).strip()
+                                        _parsed_items = _inner.get("items", []) if isinstance(_inner.get("items"), list) else None
+                                except (_json.JSONDecodeError, ValueError):
+                                    pass
+                            # Path 3: 只有 narrative(來自 description),items 用 Python fallback
+                            if _parsed_narrative is None and _desc:
+                                _parsed_narrative = _desc
+                                _parsed_items = None  # 觸發下方 fallback_items
                 except (_json.JSONDecodeError, ValueError) as e:
-                    logger.warning("drift_narrator_json_parse_fail", err=str(e), raw_prefix=_raw[:80])
+                    logger.warning("drift_narrator_json_parse_fail", err=str(e),
+                                   raw_prefix=_raw[:100], provider=provider)
+
+                # 驗證 + 清洗
+                if _parsed_narrative:
+                    # 清洗 items (若 LLM 有給)
+                    clean_items = []
+                    if isinstance(_parsed_items, list):
+                        for it in _parsed_items[:5]:
+                            if isinstance(it, dict) and it.get("field") and it.get("summary"):
+                                clean_items.append({
+                                    "level": it.get("level", "medium"),
+                                    "field": str(it["field"])[:60],
+                                    "summary": str(it["summary"])[:80],
+                                })
+                    # items 空就用 Python smart fallback (不是 str()[:30])
+                    if not clean_items:
+                        clean_items = self._fallback_items(report)
+
+                    narrative = _parsed_narrative
+                    items = clean_items
+                    status = "success"
+                    llm_accepted = True
 
             if not llm_accepted:
                 logger.warning("drift_narrator_openclaw_failed", provider=provider)
@@ -314,6 +353,8 @@ class DriftNarratorService:
             parent_op_id = parent_row.scalar() if parent_row else None
 
             # 寫 automation_operation_log
+            # 2026-04-18 hotfix: tags 要傳 Python list（不是 PG array literal 字串）
+            #                   否則 asyncpg 會報 "a sized iterable container expected"
             op_row = await db.execute(
                 _sql("""
                     INSERT INTO automation_operation_log (
@@ -327,7 +368,7 @@ class DriftNarratorService:
                         CAST(:input AS jsonb),
                         CAST(:output AS jsonb),
                         :duration_ms, :parent_op_id,
-                        CAST(:tags AS text[])
+                        :tags
                     )
                     RETURNING op_id
                 """),
@@ -337,7 +378,7 @@ class DriftNarratorService:
                     "output": output_json,
                     "duration_ms": duration_ms,
                     "parent_op_id": parent_op_id,
-                    "tags": "{drift,type4d,llm_summary}",
+                    "tags": ["drift", "type4d", "llm_summary"],
                 },
             )
             op_id = op_row.scalar()