feat(host_agent): a disk out of inodes reads as full (#5745)

VDNT-Util01's / ran out of inodes (956 free of 60.8M) with 274G of space
left; every file create failed and Steward's page read healthy at 66%.

- Agent 1.13.0 reports each mount's inodes (statvfs; a filesystem reporting
  none, like btrfs, is left without).
- Ingest records inodes_used_pct per mount, and disk_used_pct_worst is the
  fullest mount by space or inodes, so existing disk-full rules and the
  overview see it.
- The host's health strip, the Hosts widget and the host glance grade / by
  whichever is fuller and name inodes when they are ("Disk / 66% · inodes
  100%", "Inodes on / ... past its critical threshold").

Hosts pick up the inode figures once their agent is updated to 1.13.0.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

plugins/host_agent/routes.py

@@ -127,6 +127,9 @@ def _expand_sample_to_metrics(
     if sample.get("uptime_secs") is not None:
         row("uptime_secs", host_name, sample["uptime_secs"])
 
+    # The fullest disk is the fullest by space or by inodes (#5745): out of
+    # inodes, every file create fails with space to spare, so the disk rules
+    # and the overview, which read disk_used_pct_worst, see either.
     worst_pct = 0.0
     for disk in sample.get("storage") or []:
         total = disk.get("total_bytes", 0)
@@ -136,6 +139,10 @@ def _expand_sample_to_metrics(
         row("disk_used_pct", mount_res, pct)
         row("disk_used_bytes", mount_res, used)
         row("disk_total_bytes", mount_res, total)
+        if disk.get("inodes_total"):
+            inode_pct = 100.0 * disk.get("inodes_used", 0) / disk["inodes_total"]
+            row("inodes_used_pct", mount_res, inode_pct)
+            pct = max(pct, inode_pct)
         if pct > worst_pct:
             worst_pct = pct
     if sample.get("storage"):
@@ -750,6 +757,8 @@ async def host_vitals(host_id: str):
     # At-a-glance disk = the root filesystem (what people actually care about),
     # not the "worst" mount which is opaque. Worst stays on the full-metrics page.
     disk_root = (latest.get(host.name + ":/", {}) or {}).get("disk_used_pct")
+    # Out of inodes, "/" is full with space to spare (#5745): named when worse.
+    inodes_root = (latest.get(host.name + ":/", {}) or {}).get("inodes_used_pct")
     sparks = {k: sparkline_svg(v, height=24, fill_width=True) for k, v in series_raw.items()}
     # Normalize load by core count so it's comparable across hardware (load/core
     # as %). Cores derived from the per-core CPU sub-resources already collected.
@@ -767,12 +776,12 @@ async def host_vitals(host_id: str):
     cpu, mem = hostlvl.get("cpu_pct"), hostlvl.get("mem_used_pct")
     thresholds = current_app.config.get("THRESHOLDS", {})
     worst = worst_reading((("CPU", cpu, "cpu"), ("Memory", mem, "mem"), ("Disk /", disk_root, "disk"),
-                           ("Load per core", load_per_core, "load")),
+                           ("Inodes on /", inodes_root, "disk"), ("Load per core", load_per_core, "load")),
                           thresholds, host_svc.host_normals(norms, thresholds))
     # Each tile's grade; CPU, memory and load within the host's own normal
     # for the hour read healthy, and say what is usual (#5742).
-    grades = host_svc.host_grades({"cpu": cpu, "mem": mem, "disk": disk_root, "load": load_per_core},
-                                  norms, thresholds)
+    grades = host_svc.host_grades({"cpu": cpu, "mem": mem, "disk": host_svc.fuller(disk_root, inodes_root),
+                                   "load": load_per_core}, norms, thresholds)
     usual = [f"{label} {value:.0f}% is {grades[kind][1]}"
              for label, value, kind in (("CPU", cpu, "cpu"), ("Memory", mem, "mem"),
                                         ("load per core", load_per_core, "load"))
@@ -780,6 +789,7 @@ async def host_vitals(host_id: str):
     return await render_template(
         "_host_vitals.html",
         reg=reg, cpu=cpu, mem=mem, disk_root=disk_root, load_per_core=load_per_core,
+        inodes_root=inodes_root,
         sparks=sparks, psi=psi, reporting=reporting, stale=stale, worst=worst,
         grades=grades, usual=usual,
         clock=clock_words(reg.clock_offset_s if reg else None, current_app.config.get("THRESHOLDS", {})),