fix: remove timestamp normalization instead of gating it by max_count

Review feedback (Vitor): gating the batch-max normalization behind
max_count == 1 just hid the same collapsing behavior for the single-point
case, where it's redundant anyway (aggregation/export don't need it) while
still being the wrong fix conceptually. Removed the normalization block
entirely so every record always keeps its own real timestamp from the PI
Web API, regardless of max_count.

Updated unit tests accordingly and confirmed no e2e scenario needs
adjustment: aggregate_data groups by (tag, name) and always collapses to
one output row per tag per execution, independent of per-record timestamp
values, so pi_web_api_scouter_multiple_tags' aggregated-value assertions
are unaffected.

SIENTIAPDE-1993

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

CLAUDE.md

@@ -48,7 +48,7 @@ Parent/child Temporal workflow pattern, two independent worker task queues shari
 ```
 Scouter (scouter/workflow/scouter.py)              PIWebAPIScouter (scouter/workflow/pi_web_api_scouter.py)
   reads raw_{schedule_name} from MongoDB              queries PI Web API directly (get_tag_values)
-  tracks last-processed timestamp in Redis             normalizes all timestamps to the batch max
+  tracks last-processed timestamp in Redis             preserves each record's real timestamp
         │                                                     │
         └───────────────► CoreScouter (scouter/workflow/sub_workflows/core_scouter.py) ◄───────┘
                               1. data_quality_gate   (NULL_VALUES_FILTER / OUT_OF_BOUNDS_FILTER, DISCARD policy)

scouter/activities/api.py

@@ -86,13 +86,8 @@ class API(SientiaMonitoring):
         for a set of configured tags. It returns the data as a list of dictionaries
         suitable for further processing in the workflow.
 
-        Timestamps are converted to string format. When max_count is 1 (one point per
+        Timestamps are converted to string format and each record keeps its own real
-        tag), timestamps are additionally normalized to the maximum timestamp value
+        timestamp as returned by the PI Web API.
-        (lexicographically) found in the dataset, to align minor sampling differences
-        across tags. When max_count > 1 (multiple historical points per tag), each
-        record's real timestamp is preserved instead, since collapsing them would make
-        distinct historical points collide on the (model_id, timestamp, variable)
-        unique constraint downstream.
 
         Args:
             input_data (dict[str, Any]): Activity input parameters.
@@ -106,8 +101,7 @@ class API(SientiaMonitoring):
 
         Returns:
             list[dict]: List of data records, each containing:
-                - timestamp: Timestamp string (normalized to a shared value only when
+                - timestamp: Each record's real timestamp string
-                  max_count is 1; otherwise each record's real timestamp)
                 - name: Tag name
                 - value: Numeric value
                 - tag: WebId
@@ -152,15 +146,6 @@ class API(SientiaMonitoring):
 
         self.debug(f'Latest values: {latest_values.to_string()}', metadata=metadata)
 
-        if max_count == 1:
-            # Normalize the package timestamp - only meaningful when a single point per tag
-            # is retrieved, to align minor sampling differences across tags. With
-            # max_count > 1 each historical point's real timestamp must be preserved,
-            # otherwise distinct records collide on the (model_id, timestamp, variable)
-            # unique constraint and are silently dropped downstream.
-            valid_timestamp_values = latest_values['timestamp'].dropna()
-            latest_values['timestamp'] = valid_timestamp_values.max()
-
         self.info(f'Gathered {len(latest_values)} tag values', metadata=metadata)
 
         return latest_values.to_dict(orient='records')

tests/activities/test_api.py

@@ -87,7 +87,7 @@ def test_close(mock_sientia_monitoring, api_activity):
 
 
 def test_get_tag_values_success(api_activity):
-    """Test get_tag_values with max_count=1 normalizes timestamps across tags."""
+    """Test get_tag_values with successful data retrieval preserves each record's real timestamp."""
     # Setup test data
     test_data = {
         **metadata,
@@ -110,7 +110,7 @@ def test_get_tag_values_success(api_activity):
             },
         },
         'period': '*-1d',
-        'max_count': 1,
+        'max_count': 10,
         'api_timeout': 30,
     }
 
@@ -145,7 +145,7 @@ def test_get_tag_values_success(api_activity):
         },
         start_time='*-1d',
         end_time='*',
-        max_count=1,
+        max_count=10,
         metadata=metadata['metadata'],
         request_timeout=30,
     )
@@ -155,17 +155,17 @@ def test_get_tag_values_success(api_activity):
     assert result[0]['value'] == pytest.approx(10.5)
     assert result[1]['name'] == 'tag2'
     assert result[2]['name'] == 'tag3'
-    # With max_count=1, timestamps are normalized to the batch max across tags
+    # Each record keeps its own real timestamp, no cross-tag normalization
-    assert result[0]['timestamp'] == '2023-01-01 12:02:00+0000'
+    assert result[0]['timestamp'] == '2023-01-01 12:00:00+0000'
-    assert result[1]['timestamp'] == '2023-01-01 12:02:00+0000'
+    assert result[1]['timestamp'] == '2023-01-01 12:01:00+0000'
     assert result[2]['timestamp'] == '2023-01-01 12:02:00+0000'
 
 
 def test_get_tag_values_with_max_count_greater_than_one_preserves_timestamps(api_activity):
     """Regression test for SIENTIAPDE-1993: with max_count > 1, each historical point's
-    real timestamp must be preserved instead of being collapsed to the batch max,
+    real timestamp must be preserved, otherwise distinct records collide on the
-    otherwise distinct records collide on the (model_id, timestamp, variable) unique
+    (model_id, timestamp, variable) unique constraint downstream and are silently
-    constraint downstream and are silently dropped."""
+    dropped."""
     test_data = {
         **metadata,
         'endpoint': '/streamsets/recorded',