fix(scraper): voice body 加 departmentId/isRoom/时间窗 + sync 解析 root department_id

实测 queryWeChatVoiceList 必须带 callSource+departmentId+isRoom+startTime+endTime，
否则 200 但 data 空（0 数据）。WA callSource=4 / 微信 callSource=0，宽窗抓全量。
sync_*_voice_calls 照 sync_wechat_accounts 模式解析 _find_root_department_id。

Co-Authored-By: Claude <noreply@anthropic.com>

yunke-server/tests/test_scrape_wa_voice_calls.py

@@ -91,10 +91,13 @@ def _ms(date_str: str) -> int:
 async def test_scrape_wa_voice_calls_yields_records_and_paginates():
     """Two pages + a terminating empty page -> 3 records, 3 calls.
 
-    Body must carry ``callSource=4`` (the WA flag) plus the standard
-    ``pageNum``/``pageSize`` pagination pair. Each yielded record is
-    normalized to the ``PhoneCall`` shape with ``channel="wa_voice_call"``
-    and the WA-specific fields preserved via ``raw_json``.
+    Body must carry the full filter set the live endpoint REQUIRES
+    (``callSource=4`` + ``departmentId`` + ``isRoom`` + ``startTime`` +
+    ``endTime`` — omit any and the endpoint returns 200 with empty
+    ``data.data``, 0 rows) plus the standard ``pageNum``/``pageSize``
+    pagination pair. Each yielded record is normalized to the ``PhoneCall``
+    shape with ``channel="wa_voice_call"`` and the WA-specific fields
+    preserved via ``raw_json``.
     """
     page1 = make_wa_voice_list_response(
         WA_VOICE_RECORDS[:2], total=TOTAL, page_num=1, page_size=DEFAULT_PAGE_SIZE
@@ -119,7 +122,7 @@ async def test_scrape_wa_voice_calls_yields_records_and_paginates():
         results = [
             r
             async for r in scrape_wa_voice_calls(
-                client, page_size=DEFAULT_PAGE_SIZE
+                client, department_id="DEPT_TEST", page_size=DEFAULT_PAGE_SIZE
             )
         ]
     finally:
@@ -132,11 +135,29 @@ async def test_scrape_wa_voice_calls_yields_records_and_paginates():
     assert len(results) == len(WA_VOICE_RECORDS)
     assert {r["call_id"] for r in results} == {rec["id"] for rec in WA_VOICE_RECORDS}
 
-    # First request body: callSource=4 (WA) + standard pagination pair.
+    # First request body: full required filter set the live endpoint demands.
+    # callSource=4 (WA) + departmentId + isRoom="0" + wide time window +
+    # empty userId/sort/ids (the live endpoint accepts these blank).
     body1 = _json.loads(route.calls[0].request.content.decode())
     assert body1["callSource"] == "4"
+    assert body1["departmentId"] == "DEPT_TEST"
+    assert body1["isRoom"] == "0"
+    assert body1["startTime"] == "2000-01-01 00:00:00"
+    assert body1["endTime"] == "2099-12-31 23:59:59"
     assert body1["pageNum"] == 1
     assert body1["pageSize"] == DEFAULT_PAGE_SIZE
+    # The blank-but-required keys are present (the live endpoint expects
+    # them in the body even when empty).
+    assert body1["userId"] == ""
+    assert body1["sort"] == ""
+    assert body1["ids"] == []
+
+    # Second page advances pageNum and keeps the same filter set verbatim.
+    body2 = _json.loads(route.calls[1].request.content.decode())
+    assert body2["pageNum"] == 2
+    assert body2["pageSize"] == DEFAULT_PAGE_SIZE
+    assert body2["callSource"] == "4"
+    assert body2["departmentId"] == "DEPT_TEST"
 
     # Field mapping for each record (compare against the source record).
     for result, record in zip(results, WA_VOICE_RECORDS, strict=True):

yunke-server/tests/test_scrape_wechat_voice_calls.py

@@ -205,7 +205,15 @@ async def test_scrape_wechat_voice_calls_null_oss_file_name_yields_none_record_f
 
 @respx.mock
 async def test_scrape_wechat_voice_calls_sends_pagination_body():
-    """Outgoing request body carries pageNum/pageSize; advances per page."""
+    """Body carries the full required filter set + advancing pageNum/pageSize.
+
+    Live diagnosis (2026-08-07) showed ``queryWeChatVoiceList`` REQUIRES
+    ``callSource=0`` + ``departmentId`` + ``isRoom`` + ``startTime`` +
+    ``endTime`` — omit any and the endpoint returns 200 with an empty
+    ``data.data`` (0 rows). The WeChat variant uses ``callSource="0"``;
+    the wide time window ``2000-01-01 .. 2099-12-31`` pulls the full
+    history in one scrape.
+    """
     page1 = make_voice_list_response(
         VOICE_RECORDS[:1], total=TOTAL, page_num=1, page_size=1
     )
@@ -221,7 +229,12 @@ async def test_scrape_wechat_voice_calls_sends_pagination_body():
 
     client = _primed_client()
     try:
-        results = [r async for r in scrape_wechat_voice_calls(client, page_size=1)]
+        results = [
+            r
+            async for r in scrape_wechat_voice_calls(
+                client, department_id="DEPT_TEST", page_size=1
+            )
+        ]
     finally:
         await client.aclose()
 
@@ -229,13 +242,30 @@ async def test_scrape_wechat_voice_calls_sends_pagination_body():
     assert len(results) == 1
     assert route.call_count == 2
 
+    # Page 1 body: full required filter set + standard pagination pair.
     body1 = _json.loads(route.calls[0].request.content.decode())
+    assert body1["callSource"] == "0"
+    assert body1["departmentId"] == "DEPT_TEST"
+    assert body1["isRoom"] == "0"
+    assert body1["startTime"] == "2000-01-01 00:00:00"
+    assert body1["endTime"] == "2099-12-31 23:59:59"
     assert body1["pageNum"] == 1
     assert body1["pageSize"] == 1
+    # Blank-but-required keys are present (the live endpoint expects them
+    # in the body even when empty).
+    assert body1["userId"] == ""
+    assert body1["sort"] == ""
+    assert body1["ids"] == []
 
+    # Page 2 advances pageNum and keeps the same filter set verbatim.
     body2 = _json.loads(route.calls[1].request.content.decode())
     assert body2["pageNum"] == 2
     assert body2["pageSize"] == 1
+    assert body2["callSource"] == "0"
+    assert body2["departmentId"] == "DEPT_TEST"
+    assert body2["isRoom"] == "0"
+    assert body2["startTime"] == "2000-01-01 00:00:00"
+    assert body2["endTime"] == "2099-12-31 23:59:59"
 
 
 # ---------------------------------------------------------------------------