feed range query fix

sdk/cosmos/azure-cosmos/CHANGELOG.md

@@ -8,6 +8,8 @@
 
 #### Bugs Fixed
 * Fixed bug where `CosmosClient` construction with AAD credentials would crash at startup if the semantic reranking inference endpoint environment variable was not set, even when semantic reranking was not being used. The inference service is now lazily initialized on first use. See [PR 46243](https://github.com/Azure/azure-sdk-for-python/pull/46243)
+* Fixed a bug in `query_items(feed_range=...)` where pagination could return incorrect results after a partition split caused the supplied feed range to overlap multiple physical partitions. See [PR 46506](https://github.com/Azure/azure-sdk-for-python/pull/46506)
+* Fixed `SELECT VALUE` aggregation classification across partitions: booleans are no longer treated as numeric aggregates, non-aggregate numeric projections are no longer merged, and `MIN`/`MAX` detection is now correct. See [PR 46506](https://github.com/Azure/azure-sdk-for-python/pull/46506)
 
 #### Other Changes
 

sdk/cosmos/azure-cosmos/azure/cosmos/_base.py

@@ -39,6 +39,11 @@
 from . import documents
 from . import http_constants
 from . import _runtime_constants
+from ._query_aggregate_utils import (
+    _AggregatePartialClassification,
+    _classify_aggregate_partial,
+    _get_select_value_aggregate_function,
+)
 from ._constants import _Constants as Constants
 from .auth import _get_authorization_header
 from .offer import ThroughputProperties
@@ -129,6 +134,7 @@ def build_options(kwargs: dict[str, Any]) -> dict[str, Any]:
         options['accessCondition'] = {'type': 'IfNoneMatch', 'condition': if_none_match}
     return options
 
+
 def _merge_query_results(
         results: dict[str, Any],
         partial_result: dict[str, Any],
@@ -168,22 +174,13 @@ def _merge_query_results(
 
     results_docs = results.get("Documents")
 
-    # Check if both results are aggregate queries
-    is_partial_agg = (
-            isinstance(partial_docs, list)
-            and len(partial_docs) == 1
-            and isinstance(partial_docs[0], dict)
-            and partial_docs[0].get("_aggregate") is not None
-    )
-    is_results_agg = (
-            results_docs
-            and isinstance(results_docs, list)
-            and len(results_docs) == 1
-            and isinstance(results_docs[0], dict)
-            and results_docs[0].get("_aggregate") is not None
-    )
+    partial_aggregate_class = _classify_aggregate_partial(partial_docs, query)
+    results_aggregate_class = _classify_aggregate_partial(results_docs, query)
 
-    if is_partial_agg and is_results_agg:
+    if (
+        partial_aggregate_class == _AggregatePartialClassification.OBJECT
+        and results_aggregate_class == _AggregatePartialClassification.OBJECT
+    ):
         agg_results = results_docs[0]["_aggregate"] # type: ignore[index]
         agg_partial = partial_docs[0]["_aggregate"]
         for key in agg_partial:
@@ -201,33 +198,22 @@ def _merge_query_results(
                 agg_results[key] += agg_partial[key]
         return results
 
-    # Check if both are VALUE aggregate queries
-    is_partial_value_agg = (
-            isinstance(partial_docs, list)
-            and len(partial_docs) == 1
-            and isinstance(partial_docs[0], (int, float))
-    )
-    is_results_value_agg = (
-            results_docs
-            and isinstance(results_docs, list)
-            and len(results_docs) == 1
-            and isinstance(results_docs[0], (int, float))
-    )
-
-    if is_partial_value_agg and is_results_value_agg:
-        query_text = query.get("query") if isinstance(query, dict) else query
-        if query_text:
-            query_upper = query_text.upper()
-            # For MIN/MAX, we find the min/max of the partial results.
-            # For COUNT/SUM, we sum the partial results.
-            # Without robust query parsing, we can't distinguish them reliably.
-            # Defaulting to sum for COUNT/SUM. MIN/MAX VALUE queries are not fully supported client-side.
-            if " SELECT VALUE MIN" in query_upper:
-                results_docs[0] = min(results_docs[0], partial_docs[0]) # type: ignore[index]
-            elif " SELECT VALUE MAX" in query_upper:
-                results_docs[0] = max(results_docs[0], partial_docs[0]) # type: ignore[index]
-            else:  # For COUNT/SUM, we sum the partial results
-                results_docs[0] += partial_docs[0] # type: ignore[index]
+    if (
+        partial_aggregate_class == _AggregatePartialClassification.VALUE
+        and results_aggregate_class == _AggregatePartialClassification.VALUE
+    ):
+        aggregate_fn = _get_select_value_aggregate_function(query)
+        if aggregate_fn is None:
+            raise ValueError(
+                "Invariant violation: VALUE aggregate classification requires a recognized aggregate function."
+            )
+        if aggregate_fn == "MIN":
+            results_docs[0] = min(results_docs[0], partial_docs[0]) # type: ignore[index]
+        elif aggregate_fn == "MAX":
+            results_docs[0] = max(results_docs[0], partial_docs[0]) # type: ignore[index]
+        else:
+            # COUNT/SUM are additive; VALUE AVG is not fully supported client-side yet.
+            results_docs[0] += partial_docs[0] # type: ignore[index]
         return results
 
     # Standard query, append documents