Persist endpoint disk health

Adds diskhealthjson with its migration in the same change, so the model never references a column the schema has not applied.

Kept separate from disksjson rather than merged into it. That column is per volume and answers how full a drive is; this one is per physical device and answers whether the hardware is dying. They come from different WMI sources with different failure modes, so merging them would make a capacity collection failure indistinguishable from a health collection failure.

Nullable with no backfill: a drive whose health has never been reported is not a healthy drive, and defaulting to an empty list would read as no disks have problems on every endpoint predating the column.

plugins/endpoints/plugin.py

@@ -53,7 +53,7 @@ KNOWN_PAYLOAD_KEYS = frozenset({
     'cpupercent', 'memorypercent', 'services', 'ports', 'interfaces',
     'scheduledtasks', 'applications', 'events',
     'disks', 'bios', 'memory', 'processor', 'osinfo', 'domain',
-    'pendingreboot', 'usercontext',
+    'pendingreboot', 'usercontext', 'diskhealth',
 })
 
 
@@ -572,6 +572,30 @@ class EndpointsPlugin(BasePlugin):
                 'position': 17,
                 'group': 'monitors',
             },
+            {
+                # Sits directly under Storage because an operator looking at a
+                # full disk and an operator looking at a dying disk are usually
+                # the same person in the same minute. Kept a separate panel
+                # because storage is per volume and this is per physical
+                # device; the two do not share a key.
+                'id': 'endpoints-diskhealth',
+                'title': 'Disk health',
+                'assettypes': ['computer'],
+                'endpoint': '/api/endpoints/asset/{assetid}/diskhealth',
+                'render': 'table',
+                'collapsible': True,
+                'columns': [
+                    {'key': 'model', 'label': 'Drive'},
+                    {'key': 'mediatype', 'label': 'Media'},
+                    {'key': 'bustype', 'label': 'Bus'},
+                    {'key': 'healthstatus', 'label': 'Health'},
+                    {'key': 'verdict', 'label': 'Verdict'},
+                    {'key': 'source', 'label': 'Source'},
+                ],
+                'empty': 'No disk health reported.',
+                'position': 18,
+                'group': 'monitors',
+            },
             {
                 # The listening set is the box's exposed network surface. The
                 # full connection table is deliberately not here: it is an
@@ -757,6 +781,15 @@ class EndpointsPlugin(BasePlugin):
                                        'reboot. Absent means never reported, '
                                        'which is not the same as false.',
                     },
+                    'diskhealth': {
+                        'type': 'array',
+                        'description': 'Per-drive health from two sources: '
+                                       'physicaldisk (the only one reporting '
+                                       'NVMe) and diskdrive (ATA/SATA and '
+                                       'fallback). Each entry carries a '
+                                       'precomputed predictfailure; null there '
+                                       'means the drive did not answer.',
+                    },
                     'usercontext': {
                         'type': 'object',
                         'description': 'Session-scoped data collected by a probe '
@@ -1000,6 +1033,8 @@ class EndpointsPlugin(BasePlugin):
             state.domain = payload.get('domain')
         if 'pendingreboot' in payload:
             state.pendingreboot = payload.get('pendingreboot')
+        if 'diskhealth' in payload:
+            state.diskhealthjson = _as_json(payload.get('diskhealth'))
 
         # Session-scoped probe output. The agent repeats its last result between
         # probe runs and omits the key entirely when nobody is signed in, so the