Use prompt history for online mining records

skills/online-mining-v2/scripts/online_mining_common.py

@@ -89,9 +89,32 @@ def source_config(source: str) -> dict[str, Any]:
     return SOURCE_CONFIGS[source]
 
 
-def date_range_ms(date_str: str | None) -> tuple[int, int]:
+def parse_date(value: str) -> datetime:
+    text = str(value).strip()
+    for fmt in ("%Y%m%d", "%Y-%m-%d"):
+        try:
+            return datetime.strptime(text, fmt)
+        except ValueError:
+            continue
+    raise OnlineMiningError("date must be YYYYMMDD or YYYY-MM-DD")
+
+
+def date_range_ms(date_str: str | None, *, date_from: str | None = None, date_to: str | None = None, lookback_days: int | None = None) -> tuple[int, int]:
+    if date_from or date_to:
+        if not date_from or not date_to:
+            raise OnlineMiningError("date_from and date_to must be provided together")
+        start_obj = parse_date(date_from)
+        end_obj = parse_date(date_to) + timedelta(days=1)
+        if end_obj <= start_obj:
+            raise OnlineMiningError("date_to must be greater than or equal to date_from")
+        return int(start_obj.timestamp() * 1000), int(end_obj.timestamp() * 1000) - 1
+    if lookback_days is not None:
+        if lookback_days <= 0 or lookback_days > 31:
+            raise OnlineMiningError("lookback_days must be between 1 and 31")
+        end = datetime.now()
+        return int((end - timedelta(days=lookback_days)).timestamp() * 1000), int(end.timestamp() * 1000)
     if date_str:
-        date_obj = datetime.strptime(str(date_str), "%Y%m%d")
+        date_obj = parse_date(date_str)
         start_ms = int(date_obj.timestamp() * 1000)
         end_ms = int((date_obj + timedelta(days=1)).timestamp() * 1000) - 1
     else:
@@ -266,10 +289,13 @@ def search_docs(
     date: str | None,
     size: int,
     query_filters: list[dict[str, Any]] | None = None,
+    date_from: str | None = None,
+    date_to: str | None = None,
+    lookback_days: int | None = None,
 ) -> list[dict[str, Any]]:
     config = source_config(source)
     client = build_client(source)
-    start_ms, end_ms = date_range_ms(date)
+    start_ms, end_ms = date_range_ms(date, date_from=date_from, date_to=date_to, lookback_days=lookback_days)
     filters = [{"range": {str(config["time_field"]): {"gte": start_ms, "lte": end_ms}}}]
     filters.extend(deepcopy(query_filters or []))
     body = {
@@ -281,7 +307,15 @@ def search_docs(
     return [deep_parse(hit.get("_source", {})) for hit in response.get("hits", {}).get("hits", [])]
 
 
-def fetch_one_by_request_id(source: str, request_id: str, date: str | None = None) -> dict[str, Any] | None:
+def fetch_one_by_request_id(
+    source: str,
+    request_id: str,
+    date: str | None = None,
+    *,
+    date_from: str | None = None,
+    date_to: str | None = None,
+    lookback_days: int | None = None,
+) -> dict[str, Any] | None:
     config = source_config(source)
     id_field = str(config["id_field"])
     # 精确查优先用 .keyword；部分索引字段本身就是 keyword，所以再兜底原字段。
@@ -292,56 +326,20 @@ def fetch_one_by_request_id(source: str, request_id: str, date: str | None = Non
         {"wildcard": {id_field: {"value": f"{request_id}*"}}},
     ]
     for query_filter in attempts:
-        docs = search_docs(source=source, date=date, size=1, query_filters=[query_filter])
+        docs = search_docs(
+            source=source,
+            date=date,
+            size=1,
+            query_filters=[query_filter],
+            date_from=date_from,
+            date_to=date_to,
+            lookback_days=lookback_days,
+        )
         if docs:
             return docs[0]
     return None
 
 
-def fetch_session_turns(
-    *,
-    session_id: str,
-    before_timestamp: int,
-    date: str | None = None,
-    limit: int = 10,
-) -> list[dict[str, Any]]:
-    """按主表 session_id 拉当前请求之前的多轮上下文。"""
-
-    if not session_id or not before_timestamp:
-        return []
-    docs: list[dict[str, Any]] = []
-    # arch-flat-nlp-log-f-* 里 session_id 在部分索引没有 .keyword 子字段，
-    # 所以必须先试 keyword，再兜底原字段。
-    for session_field in ("session_id.keyword", "session_id"):
-        filters = [
-            {"term": {session_field: session_id}},
-            {"range": {"timestamp": {"lt": before_timestamp}}},
-        ]
-        docs = search_docs(source="main", date=date, size=max(limit * 3, limit), query_filters=filters)
-        if docs:
-            break
-    cases = [extract_main_case(doc) for doc in docs]
-    cases = [
-        case
-        for case in cases
-        if str(case.get("session_id") or "") == session_id
-        and isinstance(case.get("timestamp"), (int, str))
-        and int(case.get("timestamp") or 0) < before_timestamp
-        and str(case.get("query") or "").strip()
-    ]
-    cases.sort(key=lambda item: int(item.get("timestamp") or 0))
-    return cases[-limit:]
-
-
-def fetch_session_turns_for_case(case: dict[str, Any], *, date: str | None = None, limit: int = 10) -> list[dict[str, Any]]:
-    session_id = str(case.get("session_id") or "").strip()
-    try:
-        timestamp = int(case.get("timestamp") or 0)
-    except (TypeError, ValueError):
-        timestamp = 0
-    return fetch_session_turns(session_id=session_id, before_timestamp=timestamp, date=date, limit=limit)
-
-
 def fetch_by_terms(source: str, *, field: str, value: str, date: str | None = None, size: int = 10) -> list[dict[str, Any]]:
     """小范围精确字段查询，供脚本探测 session/request 字段时使用。"""