From 8edc6956da701efcc87fd54c17292f6157352e3d Mon Sep 17 00:00:00 2001
From: "benjamin.baker" <benjamin.baker@geaerospace.com>
Date: Sat, 5 Sep 2026 06:25:55 -0400
Subject: [PATCH] Add the disk health panel

Its own card rather than folded into Storage: Storage is per volume and this is per physical device, and one drive can back several volumes or none the operator sees, so the two do not share a key.

Rows sort failure-first, then unknown, then OK. A failing drive must not sit below the fold on a multi-disk box, and a drive that stopped answering is a weaker claim of health than one that said OK. An unrecognised verdict sorts as unknown rather than last, so a future verdict string cannot bury itself under the healthy drives.

Both agent sources are shown rather than merged, matching the mapped-drive card: when two sources disagree about one drive, that disagreement is the thing worth looking at.
---
 plugins/endpoints/api/routes.py | 60 +++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/plugins/endpoints/api/routes.py b/plugins/endpoints/api/routes.py
index 53afb2b0..9a63a92d 100644
--- a/plugins/endpoints/api/routes.py
+++ b/plugins/endpoints/api/routes.py
@@ -640,6 +640,66 @@ def panel_storage(asset_id: int):
     return success_response(rows)
 
 
+def _diskhealth_rows(drives):
+    """Turn the agent's disk health list into display rows, worst first.
+
+    Both agent sources are kept rather than merged. MSFT_PhysicalDisk is the
+    only source that reports NVMe at all, and Win32_DiskDrive covers hardware
+    and hosts where the Storage namespace is unavailable. When both answer for
+    the same hardware, two rows that disagree is the useful signal; collapsing
+    them would hide exactly the case worth looking at.
+    """
+    if not isinstance(drives, list):
+        return []
+
+    rows = []
+    for drive in drives:
+        if not isinstance(drive, dict):
+            continue
+        predictfailure = drive.get('predictfailure')
+        if predictfailure is None:
+            verdict = 'Unknown'
+        elif predictfailure:
+            verdict = 'Failure predicted'
+        else:
+            verdict = 'OK'
+        rows.append({
+            'deviceid': drive.get('deviceid'),
+            'model': drive.get('model') or '',
+            'mediatype': drive.get('mediatype') or '',
+            'bustype': drive.get('bustype') or '',
+            'healthstatus': drive.get('healthstatus') or 'Unknown',
+            'verdict': verdict,
+            'source': drive.get('source') or '',
+        })
+
+    # Failure first, then unknown, then OK. Unknown outranks OK because a drive
+    # that stopped answering is a weaker claim of health than one that said OK.
+    # An unrecognised verdict sorts as unknown rather than last, so a future
+    # verdict string cannot bury itself under the healthy drives.
+    order = {'Failure predicted': 0, 'Unknown': 1, 'OK': 2}
+    rows.sort(key=lambda row: (order.get(row['verdict'], 1),
+                               row['deviceid'] or ''))
+    return rows
+
+
+@endpoints_bp.route('/asset/<int:asset_id>/diskhealth', methods=['GET'])
+@require_permission('endpoints.view')
+def panel_diskhealth(asset_id: int):
+    """Table panel: physical drive health.
+
+    Separate from the storage panel because the two do not share a key. Storage
+    is per volume (C:, D:), this is per physical device, and one physical drive
+    can back several volumes or none the operator can see.
+
+    Rows are ordered so anything predicting failure sorts first: a failing
+    drive must not be below the fold on a machine with several disks.
+    """
+    state = EndpointState.query.filter_by(assetid=asset_id).first()
+    drives = _state_json(state, 'diskhealthjson') if state else None
+    return success_response(_diskhealth_rows(drives))
+
+
 @endpoints_bp.route('/asset/<int:asset_id>/listeners', methods=['GET'])
 @require_permission('endpoints.view')
 def panel_listeners(asset_id: int):