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/app/scraper/wechat.py

@@ -1140,12 +1140,41 @@ def _parse_voice_rows(resp: Any) -> list[dict[str, Any]]:
     return rows if isinstance(rows, list) else []
 
 
-def _build_voice_body(page_num: int, page_size: int) -> dict[str, Any]:
+def _build_voice_body(
+    page_num: int,
+    page_size: int,
+    *,
+    department_id: str = "",
+    call_source: str = "0",
+    start: str = "2000-01-01 00:00:00",
+    end: str = "2099-12-31 23:59:59",
+) -> dict[str, Any]:
     """Build the ``queryWeChatVoiceList`` request body for a given page.
 
-    The live capture carries no filter parameters — just the page slice.
+    Live diagnosis (2026-08-07 browser capture) confirmed the endpoint
+    REQUIRES ``callSource`` + ``departmentId`` + ``isRoom`` + ``startTime`` +
+    ``endTime`` — omit any one and the HTTP layer returns 200 with an EMPTY
+    ``data.data`` array (0 rows). The WeChat variant uses
+    ``call_source="0"`` (the WA variant in :mod:`app.scraper.whatsapp`
+    passes ``"4"``); a wide time window (2000-01-01 .. 2099-12-31) pulls
+    the full history in one scrape. ``userId`` / ``sort`` / ``ids`` may
+    stay empty. ``departmentId`` is omitted when blank so a test/fixture
+    call without one still forms a valid body.
     """
-    return {"pageNum": page_num, "pageSize": page_size}
+    body: dict[str, Any] = {
+        "pageNum": page_num,
+        "pageSize": page_size,
+        "callSource": call_source,
+        "isRoom": "0",
+        "startTime": start,
+        "endTime": end,
+        "sort": "",
+        "ids": [],
+        "userId": "",
+    }
+    if department_id:
+        body["departmentId"] = department_id
+    return body
 
 
 def _parse_voice_start_time(value: Any) -> int | None:
@@ -1222,6 +1251,7 @@ def _normalize_voice_call(record: dict[str, Any]) -> dict[str, Any]:
 async def scrape_wechat_voice_calls(
     client: YunkeClient,
     *,
+    department_id: str = "",
     page_size: int = 50,
 ) -> AsyncIterator[dict[str, Any]]:
     """Yield normalized WeChat voice-call records from ``queryWeChatVoiceList``.
@@ -1231,6 +1261,14 @@ async def scrape_wechat_voice_calls(
     primary stop signal), mapping each record to the ``PhoneCall`` column
     shape with ``channel="voice_call"`` plus a verbatim ``raw_json`` copy.
 
+    The endpoint REQUIRES ``callSource`` + ``departmentId`` + ``isRoom`` +
+    a ``startTime``/``endTime`` window — without them it returns 200 + an
+    empty ``data.data`` (0 rows). The orchestrator resolves the
+    company-root ``department_id`` from the mirrored ``Department`` table
+    (see :func:`app.sync.orchestrator.sync_wechat_voice_calls`); the
+    default wide time window ``2000-01-01 .. 2099-12-31`` pulls the full
+    history in one scrape and is not exposed as a parameter.
+
     The envelope is the same flat shape as ``wxUser/list`` (no
     ``basicResult`` wrapper): the row list and pagination fields sit directly
     under ``data`` (``data.data`` / ``data.total`` / ``data.pageNum`` /
@@ -1241,6 +1279,10 @@ async def scrape_wechat_voice_calls(
     client:
         Authenticated :class:`YunkeClient`. Auth headers / 401 re-login are
         handled by the client.
+    department_id:
+        Company-root department id (the ``departmentId`` form field).
+        Required by the live endpoint for non-empty results; resolved by
+        the orchestrator when omitted (empty skips the field in the body).
     page_size:
         Page size to request. Defaults to 50 (a sane middle ground between
         request count and per-response payload size for this endpoint).
@@ -1252,5 +1294,6 @@ async def scrape_wechat_voice_calls(
         parse_total=_parse_voice_total,
         parse_rows=_parse_voice_rows,
         build_body=_build_voice_body,
+        department_id=department_id,
     ):
         yield _normalize_voice_call(record)

yunke-server/app/scraper/whatsapp.py

@@ -556,14 +556,39 @@ def _parse_wa_voice_rows(resp: Any) -> list[dict[str, Any]]:
     return rows if isinstance(rows, list) else []
 
 
-def _build_wa_voice_body(page_num: int, page_size: int) -> dict[str, Any]:
+def _build_wa_voice_body(
+    page_num: int,
+    page_size: int,
+    *,
+    department_id: str = "",
+    start: str = "2000-01-01 00:00:00",
+    end: str = "2099-12-31 23:59:59",
+) -> dict[str, Any]:
     """Build the WA ``queryWeChatVoiceList`` request body for a given page.
 
-    Adds ``callSource="4"`` (the WA flag; WeChat uses ``"0"``) to the
-    standard ``pageNum`` / ``pageSize`` pagination pair. No filter
-    parameters — the live capture carries none.
+    Live diagnosis (2026-08-07 browser capture) confirmed the endpoint
+    REQUIRES ``callSource`` + ``departmentId`` + ``isRoom`` + ``startTime`` +
+    ``endTime`` — omit any one and the HTTP layer returns 200 with an EMPTY
+    ``data.data`` array (0 rows). The WA variant uses ``callSource="4"``;
+    a wide time window (2000-01-01 .. 2099-12-31) pulls the full history in
+    one scrape (live total=608). ``userId`` / ``sort`` / ``ids`` may stay
+    empty. ``departmentId`` is omitted when blank so a test/fixture call
+    without one still forms a valid body.
     """
-    return {"pageNum": page_num, "pageSize": page_size, "callSource": "4"}
+    body: dict[str, Any] = {
+        "pageNum": page_num,
+        "pageSize": page_size,
+        "callSource": "4",
+        "isRoom": "0",
+        "startTime": start,
+        "endTime": end,
+        "sort": "",
+        "ids": [],
+        "userId": "",
+    }
+    if department_id:
+        body["departmentId"] = department_id
+    return body
 
 
 def _normalize_wa_voice_call(record: dict[str, Any]) -> dict[str, Any]:
@@ -632,6 +657,7 @@ def _normalize_wa_voice_call(record: dict[str, Any]) -> dict[str, Any]:
 async def scrape_wa_voice_calls(
     client: YunkeClient,
     *,
+    department_id: str = "",
     page_size: int = 50,
 ) -> AsyncIterator[dict[str, Any]]:
     """Yield normalized WhatsApp voice-call records from ``queryWeChatVoiceList``.
@@ -644,6 +670,14 @@ async def scrape_wa_voice_calls(
     the ``PhoneCall`` column shape with ``channel="wa_voice_call"`` plus a
     verbatim ``raw_json`` copy.
 
+    The endpoint REQUIRES ``callSource`` + ``departmentId`` + ``isRoom`` +
+    a ``startTime``/``endTime`` window — without them it returns 200 + an
+    empty ``data.data`` (0 rows). The orchestrator resolves the
+    company-root ``department_id`` from the mirrored ``Department`` table
+    (see :func:`app.sync.orchestrator.sync_wa_voice_calls`); the default
+    wide time window ``2000-01-01 .. 2099-12-31`` pulls the full history
+    (live total=608) and is not exposed as a parameter.
+
     The envelope is identical to the WeChat voice endpoint: rows sit under
     ``data.data``, declared total under ``data.total``, pagination fields
     under ``data.pageNum`` / ``data.pageSize``. The WA-specific fields
@@ -659,6 +693,10 @@ async def scrape_wa_voice_calls(
     client:
         Authenticated :class:`YunkeClient`. Auth headers / 401 re-login are
         handled by the client.
+    department_id:
+        Company-root department id (the ``departmentId`` form field).
+        Required by the live endpoint for non-empty results; resolved by
+        the orchestrator when omitted (empty skips the field in the body).
     page_size:
         Page size to request. Defaults to 50 (matches the WeChat voice
         scraper; a sane middle ground between request count and per-response
@@ -671,5 +709,6 @@ async def scrape_wa_voice_calls(
         parse_total=_parse_wa_voice_total,
         parse_rows=_parse_wa_voice_rows,
         build_body=_build_wa_voice_body,
+        department_id=department_id,
     ):
         yield _normalize_wa_voice_call(record)