test(waterdata): add stats hash-drop unit tests

Two mocked-response tests for ``get_stats_data``:
- ``test_get_stats_data_drops_hash_ids_by_default`` asserts
  ``computation_id`` and ``parent_time_series_id`` are removed when
  ``include_hash_ids=False`` (the new default).
- ``test_get_stats_data_keeps_hash_ids_when_opted_in`` asserts the
  opt-in path preserves them, matching the legacy behavior.

Both use ``monkeypatch`` to stub ``_handle_stats_nesting`` so the
fake response only needs to carry the column shape, not the full
nested-percentile body.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: thodson-usgs

tests/waterdata_utils_test.py

@@ -256,6 +256,88 @@ def test_get_stats_data_warning_includes_next_token(caplog, monkeypatch):
     assert any("tok2" in m for m in warnings_), warnings_
 
 
+def test_get_stats_data_drops_hash_ids_by_default(monkeypatch):
+    """``get_stats_data`` drops ``computation_id`` and
+    ``parent_time_series_id`` from the result by default — the
+    ``include_hash_ids=False`` counterpart for the stats path."""
+    from dataretrieval.waterdata.utils import get_stats_data
+
+    monkeypatch.setattr(
+        _utils_module,
+        "_handle_stats_nesting",
+        mock.MagicMock(
+            return_value=pd.DataFrame(
+                {
+                    "monitoring_location_id": ["USGS-1"],
+                    "parameter_code": ["00060"],
+                    "computation_id": ["7d70379f-8452-44cd-b026-24dfa11f8503"],
+                    "parent_time_series_id": ["9cca880dec4846ec8cbdd05f3e22603e"],
+                    "value": [1.0],
+                }
+            )
+        ),
+    )
+
+    page1 = mock.MagicMock()
+    page1.status_code = 200
+    page1.json.return_value = {"next": None, "features": []}
+    page1.elapsed = __import__("datetime").timedelta(milliseconds=1)
+    page1.headers = {}
+    page1.url = "https://example/stats"
+    client = mock.MagicMock(spec=requests.Session)
+    client.send.return_value = page1
+
+    df, _ = get_stats_data(
+        args={"monitoring_location_id": "USGS-1"},
+        service="observationNormals",
+        expand_percentiles=False,
+        client=client,
+    )
+    assert "computation_id" not in df.columns
+    assert "parent_time_series_id" not in df.columns
+    assert "monitoring_location_id" in df.columns
+    assert "parameter_code" in df.columns
+    assert "value" in df.columns
+
+
+def test_get_stats_data_keeps_hash_ids_when_opted_in(monkeypatch):
+    """``include_hash_ids=True`` preserves the legacy stats columns."""
+    from dataretrieval.waterdata.utils import get_stats_data
+
+    monkeypatch.setattr(
+        _utils_module,
+        "_handle_stats_nesting",
+        mock.MagicMock(
+            return_value=pd.DataFrame(
+                {
+                    "monitoring_location_id": ["USGS-1"],
+                    "computation_id": ["7d70379f-8452-44cd-b026-24dfa11f8503"],
+                    "parent_time_series_id": ["9cca880dec4846ec8cbdd05f3e22603e"],
+                }
+            )
+        ),
+    )
+
+    page1 = mock.MagicMock()
+    page1.status_code = 200
+    page1.json.return_value = {"next": None, "features": []}
+    page1.elapsed = __import__("datetime").timedelta(milliseconds=1)
+    page1.headers = {}
+    page1.url = "https://example/stats"
+    client = mock.MagicMock(spec=requests.Session)
+    client.send.return_value = page1
+
+    df, _ = get_stats_data(
+        args={"monitoring_location_id": "USGS-1"},
+        service="observationNormals",
+        expand_percentiles=False,
+        client=client,
+        include_hash_ids=True,
+    )
+    assert "computation_id" in df.columns
+    assert "parent_time_series_id" in df.columns
+
+
 def test_handle_stats_nesting_tolerates_missing_drop_columns():
     """If the upstream stats response shape ever changes such that one of
     the columns we try to drop ("type", "properties.data") is absent, the