Test disk health rows

Every test pins a way the card could start showing a failing or unreadable drive as fine, which is the only failure mode that matters here: nobody investigates a disk that looks healthy.

Covers failure-first ordering, null predictfailure reading as unknown rather than OK, unknown outranking OK, both sources surviving for one drive, order independence, and malformed payloads. The ranking was mutation-checked: swapping the unknown and OK ranks fails the suite.

Also updates the panel count assertion, which correctly caught the new card.

tests/test_plugins/test_endpoints_disk_health.py

@@ -0,0 +1,108 @@
+"""Disk health rows: a dying drive must never render as a healthy one.
+
+The agent reports drive health from two sources because neither covers the
+fleet. MSFT_PhysicalDisk is the only one that reports NVMe - verified on a
+two-NVMe box where the classic ATA SMART class returned zero instances while
+both drives were present and healthy. Win32_DiskDrive covers ATA/SATA and hosts
+where the Storage namespace is missing.
+
+That means the panel can receive the same physical drive twice, from sources
+that may disagree, plus rows where health could not be read at all. Every test
+here pins a way this card could start showing a failing or unreadable drive as
+fine, which is the only failure mode that matters: nobody investigates a disk
+that looks healthy.
+"""
+
+from plugins.endpoints.api.routes import _diskhealth_rows
+
+
+def _drive(deviceid, predictfailure, healthstatus='Healthy',
+           source='physicaldisk', model='Samsung SSD'):
+    return {
+        'deviceid': deviceid,
+        'model': model,
+        'mediatype': 'SSD',
+        'bustype': 'NVMe',
+        'healthstatus': healthstatus,
+        'predictfailure': predictfailure,
+        'source': source,
+    }
+
+
+def test_a_failing_drive_sorts_above_healthy_ones():
+    """On a multi-disk box the bad drive must not be below the fold."""
+    rows = _diskhealth_rows([
+        _drive('0', False),
+        _drive('1', True, healthstatus='Unhealthy'),
+        _drive('2', False),
+    ])
+
+    assert [row['deviceid'] for row in rows] == ['1', '0', '2']
+    assert rows[0]['verdict'] == 'Failure predicted'
+
+
+def test_a_drive_that_did_not_answer_reads_as_unknown_not_ok():
+    """Null predictfailure is an unread drive, not a healthy one."""
+    rows = _diskhealth_rows([_drive('0', None, healthstatus='')])
+
+    assert rows[0]['verdict'] == 'Unknown'
+    assert rows[0]['healthstatus'] == 'Unknown'
+
+
+def test_unknown_outranks_ok_so_silence_is_not_buried_under_health():
+    """A drive that stopped answering is a weaker claim than one saying OK."""
+    rows = _diskhealth_rows([
+        _drive('0', False),
+        _drive('1', None),
+    ])
+
+    assert [row['verdict'] for row in rows] == ['Unknown', 'OK']
+
+
+def test_both_sources_survive_for_the_same_hardware():
+    """Two disagreeing views of one drive is the signal, not noise.
+
+    Collapsing them would hide the case worth looking at: one source calling a
+    drive healthy while the other predicts failure.
+    """
+    rows = _diskhealth_rows([
+        _drive('0', False, source='physicaldisk'),
+        _drive('0', True, healthstatus='Pred Fail', source='diskdrive'),
+    ])
+
+    assert len(rows) == 2
+    assert {row['source'] for row in rows} == {'physicaldisk', 'diskdrive'}
+    assert rows[0]['verdict'] == 'Failure predicted'
+
+
+def test_input_order_does_not_change_which_drive_is_shown_first():
+    """The verdict ranking must decide the order, not arrival order."""
+    healthy = _drive('0', False)
+    failing = _drive('1', True)
+
+    forward = _diskhealth_rows([healthy, failing])
+    backward = _diskhealth_rows([failing, healthy])
+
+    assert forward == backward
+    assert forward[0]['deviceid'] == '1'
+
+
+def test_an_nvme_drive_is_reported_rather_than_dropped():
+    """The whole reason for the second source: ATA SMART returns nothing here."""
+    rows = _diskhealth_rows([_drive('0', False, source='physicaldisk')])
+
+    assert rows[0]['bustype'] == 'NVMe'
+    assert rows[0]['verdict'] == 'OK'
+
+
+def test_a_malformed_payload_does_not_take_the_panel_down():
+    rows = _diskhealth_rows([_drive('0', False), 'not a dict', None])
+
+    assert len(rows) == 1
+    assert rows[0]['deviceid'] == '0'
+
+
+def test_a_missing_or_wrong_shaped_payload_is_an_empty_panel():
+    assert _diskhealth_rows(None) == []
+    assert _diskhealth_rows({}) == []
+    assert _diskhealth_rows([]) == []

tests/test_plugins/test_endpoints_plugin.py

@@ -69,7 +69,7 @@ def test_endpoints_asset_panels_are_computer_scoped():
     """Every asset panel targets computer assets only, with an endpoint."""
     plugin = EndpointsPlugin()
     panels = plugin.get_asset_panels()
-    assert len(panels) == 12
+    assert len(panels) == 13
     for panel in panels:
         assert panel['assettypes'] == ['computer']
         assert panel['endpoint'].startswith('/api/endpoints/')