Issue 7887 Fix insert select planner to exclude identity columns from target list on partial inserts

src/backend/distributed/planner/insert_select_planner.c

@@ -1438,6 +1438,80 @@ CreateNonPushableInsertSelectPlan(uint64 planId, Query *parse, ParamListInfo bou
 	/* get the SELECT query (may have changed after PrepareInsertSelectForCitusPlanner) */
 	Query *selectQuery = selectRte->subquery;
 
+	/*
+	 * 1) Open the target relation to inspect its attributes and detect identity columns.
+	 */
+	Relation targetRel = RelationIdGetRelation(targetRelationId);
+	if (RelationIsValid(targetRel))
+	{
+
+		ListCell *lcInsert = NULL;
+		// ListCell *lcSelect = list_head(selectQuery->targetList);
+
+		/* We'll build new lists for both sides */
+		List *newInsertTList = NIL;
+		List *newSelectTList = NIL;
+
+		int insertIndex = 0;
+
+		foreach(lcInsert, insertSelectQuery->targetList)
+		{
+			TargetEntry *insertTle = (TargetEntry *) lfirst(lcInsert);
+			insertIndex++;
+
+			/* Get the corresponding TLE from the SELECT by position or resno */
+			TargetEntry *selectTle = NULL;
+
+			/*
+			* If your plan is guaranteed to keep them in the same order, you can
+			* do "selectTle = (TargetEntry *) list_nth(selectQuery->targetList, insertIndex - 1)".
+			*
+			* Alternatively, if you rely on resno alignment, you'd find the TLE with resno==insertTle->resno.
+			* For simplicity, let's assume same ordering:
+			*/
+			selectTle = (TargetEntry *) list_nth(selectQuery->targetList, insertIndex - 1);
+
+			/*
+			* Check if the insertTle is an identity column that the user didn't supply,
+			* e.g. by checking 'attr->attidentity == ATTRIBUTE_IDENTITY_ALWAYS' etc.
+			* If we skip it, also skip the SELECT TLE at the same position.
+			*/
+
+			int attno = insertTle->resno;
+			if (attno > 0 && attno <= targetRel->rd_att->natts)
+			{
+				Form_pg_attribute attr = TupleDescAttr(targetRel->rd_att, attno - 1);
+
+				/*
+				* If 'attr->attidentity' is 'a' or 'd' => It's an identity column. 
+				* If the user hasn't explicitly specified a value (which is presumably 
+				* indicated by something in the parse tree?), we remove or convert 
+				* the TLE to a default. 
+				*/
+				// bool userSpecifiedValue = CheckIfUserSpecifiedValue(tle, parse); 
+				bool userSpecifiedValue = false; 
+				if ((attr->attidentity == ATTRIBUTE_IDENTITY_ALWAYS ||
+					attr->attidentity == ATTRIBUTE_IDENTITY_BY_DEFAULT) &&
+					!userSpecifiedValue)
+				{
+					/* Skip adding TLE => effectively uses default identity generation */
+					continue; 
+				}
+			}
+
+			/* else keep both TLEs */
+			newInsertTList = lappend(newInsertTList, insertTle);
+			newSelectTList = lappend(newSelectTList, selectTle);
+		}
+
+		/* Now we have 1:1 matching lists with the identity column removed from both sides */
+		insertSelectQuery->targetList = newInsertTList;
+		selectQuery->targetList = newSelectTList;
+
+		RelationClose(targetRel);
+	}
+
+
 	/*
 	 * Later we might need to call WrapTaskListForProjection(), which requires
 	 * that select target list has unique names, otherwise the outer query

src/test/regress/multi_schedule

@@ -103,7 +103,7 @@ test: multi_dropped_column_aliases foreign_key_restriction_enforcement
 test: binary_protocol
 test: alter_table_set_access_method
 test: alter_distributed_table
-test: issue_5248 issue_5099 issue_5763 issue_6543 issue_6758 issue_7477
+test: issue_5248 issue_5099 issue_5763 issue_6543 issue_6758 issue_7477 issue_7887
 test: object_propagation_debug
 test: undistribute_table
 test: run_command_on_all_nodes

src/test/regress/sql/issue_7887.sql

@@ -0,0 +1,33 @@
+CREATE SCHEMA issue_7887;
+CREATE SCHEMA issue_7887;
+
+CREATE TABLE local1 (
+    id text not null primary key
+);
+
+CREATE TABLE reference1 (
+    id int not null primary key,
+    reference_col1 text not null
+);
+SELECT create_reference_table('reference1');
+
+CREATE TABLE local2 (
+    id int not null generated always as identity,
+    local1fk text not null,
+    reference1fk int not null,
+    constraint loc1fk foreign key (local1fk) references local1(id),
+    constraint reference1fk foreign key (reference1fk) references reference1(id),
+    constraint testlocpk primary key (id)
+);
+
+INSERT INTO local1(id) VALUES ('aaaaa'), ('bbbbb'), ('ccccc');
+INSERT INTO reference1(id, reference_col1) VALUES (1, 'test'), (2, 'test2'), (3, 'test3');
+
+-- The statement that triggers the bug:
+INSERT INTO local2(local1fk, reference1fk)
+    SELECT id, 1
+    FROM local1;
+
+-- If you want to see the error in the regression output, you might do something like:
+-- NOTE: The next line is typically how you'd test for an error in a .sql regression test
+-- but with a custom "expected" file you'll confirm you get the "invalid string enlargement request size: -4" text