Merge remote-tracking branch 'origin/enterprise' into feat/TG-1115-add-job-execution-relationship-to-run-models

Author: testgen-ci-bot

testgen/common/models/test_result.py

@@ -101,6 +101,7 @@ class RunDiff:
 
     total_baseline: int
     total_target: int
+    stable_passes: int = 0
     regressions: list[DiffRow] = field(default_factory=list)
     improvements: list[DiffRow] = field(default_factory=list)
     persistent_failures: list[DiffRow] = field(default_factory=list)
@@ -471,12 +472,16 @@ def _row(tid: UUID, baseline_info: dict | None, target_info: dict | None) -> Dif
 
         for tid in baseline_results.keys() & target_results.keys():
             baseline_info, target_info = baseline_results[tid], target_results[tid]
+            baseline_status, target_status = baseline_info["status"], target_info["status"]
+            if baseline_status == TestResultStatus.Passed and target_status == TestResultStatus.Passed:
+                diff.stable_passes += 1
+                continue
             row = _row(tid, baseline_info, target_info)
-            if baseline_info["status"] == TestResultStatus.Passed and target_info["status"] in failing:
+            if baseline_status == TestResultStatus.Passed and target_status in failing:
                 diff.regressions.append(row)
-            elif baseline_info["status"] in failing and target_info["status"] == TestResultStatus.Passed:
+            elif baseline_status in failing and target_status == TestResultStatus.Passed:
                 diff.improvements.append(row)
-            elif baseline_info["status"] in failing and target_info["status"] in failing:
+            elif baseline_status in failing and target_status in failing:
                 diff.persistent_failures.append(row)
 
         for tid in target_results.keys() - baseline_results.keys():

testgen/mcp/tools/test_results.py

@@ -593,6 +593,7 @@ def _require_completed(run: TestRun, label: str) -> None:
     doc.table(
         headers=["Category", "Count"],
         rows=[
+            ["Stable passes (Baseline passed → Target passed)", diff.stable_passes],
             ["Regressions (Baseline passed → Target failed/warning)", len(diff.regressions)],
             ["Improvements (Baseline failed/warning → Target passed)", len(diff.improvements)],
             ["Persistent failures", len(diff.persistent_failures)],

tests/unit/mcp/test_tools_test_results.py

@@ -1005,6 +1005,7 @@ def test_compare_test_runs_happy_path(
     diff = MagicMock()
     diff.total_baseline = 100
     diff.total_target = 100
+    diff.stable_passes = 98
     diff.regressions = [
         _mock_diff_row(
             TestResultStatus.Passed,
@@ -1025,6 +1026,8 @@ def test_compare_test_runs_happy_path(
         out = compare_test_runs(str(uuid4()), str(uuid4()))
 
     assert "Test Run Comparison" in out
+    assert "Stable passes (Baseline passed → Target passed)" in out
+    assert "| Stable passes (Baseline passed → Target passed) | 98 |" in out
     assert "Regressions" in out
     assert "Pattern Match" in out
     assert "Passed → Failed" in out
@@ -1034,6 +1037,51 @@ def test_compare_test_runs_happy_path(
     mock_result.diff_with_details.assert_called_once_with(baseline_run.id, target_run.id)
 
 
+def _fetch_row(test_definition_id, status):
+    row = MagicMock()
+    row.test_definition_id = test_definition_id
+    row.test_type = "Pattern_Match"
+    row.test_name_short = "Pattern Match"
+    row.table_name = "orders"
+    row.column_names = "customer_id"
+    row.status = status
+    row.result_measure = "0"
+    row.threshold_value = "0"
+    return row
+
+
+def test_diff_with_details_counts_stable_passes():
+    from testgen.common.models.test_result import TestResult
+
+    stable_1, stable_2, regressed, improved = uuid4(), uuid4(), uuid4(), uuid4()
+    baseline_rows = [
+        _fetch_row(stable_1, TestResultStatus.Passed),
+        _fetch_row(stable_2, TestResultStatus.Passed),
+        _fetch_row(regressed, TestResultStatus.Passed),
+        _fetch_row(improved, TestResultStatus.Failed),
+    ]
+    target_rows = [
+        _fetch_row(stable_1, TestResultStatus.Passed),
+        _fetch_row(stable_2, TestResultStatus.Passed),
+        _fetch_row(regressed, TestResultStatus.Failed),
+        _fetch_row(improved, TestResultStatus.Passed),
+    ]
+    session = MagicMock()
+    session.execute.side_effect = [baseline_rows, target_rows]
+
+    with patch("testgen.common.models.test_result.get_current_session", return_value=session):
+        diff = TestResult.diff_with_details(uuid4(), uuid4())
+
+    assert diff.stable_passes == 2
+    assert len(diff.regressions) == 1
+    assert len(diff.improvements) == 1
+    assert len(diff.persistent_failures) == 0
+    # Internal consistency: with no out-of-bucket statuses (Error/Log) in the fixture, the four
+    # named buckets account for every shared test definition.
+    shared = diff.total_target - len(diff.new_tests)
+    assert diff.stable_passes + len(diff.regressions) + len(diff.improvements) + len(diff.persistent_failures) == shared
+
+
 @patch("testgen.mcp.tools.test_results.TestSuite")
 @patch("testgen.mcp.tools.test_results.TestResult")
 @patch("testgen.mcp.tools.test_results.TestRun")