feat(hosts): the live strip shows the hottest sensor's temperature, get_host marks sensors that don't count, and the Monitors card's button reads "Add" (#6803)

- The host page's live strip gains a Temperature tile: temp_c_max (real
  thermometers only), its last 6 h and the sensor setting it, graded by
  Settings → Thresholds and counted in the header's worst reading, in °C.
- MCP get_host: each temperature carries `counted`; an unwired input is
  `counted: false` with `not_counted_because`, listed after the real ones.
  host_agent registers the judge (judge_sensors), so core imports no plugin.
- The Monitors card's "Add monitor" wrapped into two lines beside the
  uptime; it reads "Add", titled "Add a monitor for this host".

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

plugins/host_agent/__init__.py

@@ -29,6 +29,10 @@ def setup(app: "Quart") -> None:
     from steward.core.alerts import names_behind
     from .routes import name_hottest_sensor
     names_behind("host_agent", "temp_c_max", name_hottest_sensor)
+    # get_host over MCP marks the sensors the host's temperature leaves out.
+    from steward.mcp.tools.hosts import judge_sensors
+    from .routes import split_temps
+    judge_sensors(lambda host, temps: {k: why for k, (_c, why) in split_temps(host, temps)[1].items()})
     # A reboot the agent announced is silence with a reason, for a while (#5756).
     from datetime import datetime, timezone
     from steward.core.alerts import agents_away

plugins/host_agent/routes.py

@@ -1003,7 +1003,7 @@ def _new_token_pair() -> tuple[str, str]:
 @host_agent_bp.get("/vitals/<host_id>")
 @require_role(UserRole.viewer)
 async def host_vitals(host_id: str):
-    """Compact live vitals strip (CPU/MEM/DISK/LOAD + pressure) for the Hosts hub.
+    """Compact live vitals strip (CPU/MEM/DISK/LOAD/temperature + pressure) for the Hosts hub.
 
     Self-contained fragment, polled by hosts/detail.html. Renders nothing until
     the agent reports — the Agent panel below then carries provisioning.
@@ -1018,15 +1018,16 @@ async def host_vitals(host_id: str):
         latest = await _latest_metrics_for_host(db, host.name) if reg else {}
         norms = await host_svc.host_norms(db, host.name) if reg else {}
 
-        # The last 6 h for the at-a-glance sparklines (cpu/mem/load host-level,
+        # The last 6 h for the at-a-glance sparklines (cpu/mem/load/temp host-level,
         # disk from the root mount), averaged into ~120 points in SQL, so the
         # line spans the whole window and only what is drawn is fetched.
-        series_raw: dict[str, list[float]] = {"cpu": [], "mem": [], "disk": [], "load": []}
+        series_raw: dict[str, list[float]] = {"cpu": [], "mem": [], "disk": [], "load": [], "temp": []}
         if reg:
             since = datetime.now(timezone.utc) - timedelta(hours=6)
             for key, resource, metric in (("cpu", host.name, "cpu_pct"),
                                           ("mem", host.name, "mem_used_pct"),
                                           ("load", host.name, "load_1m"),
+                                          ("temp", host.name, "temp_c_max"),
                                           ("disk", host.name + ":/", "disk_used_pct")):
                 series_raw[key] = [v for _t, v in await metric_points(
                     db, SOURCE_MODULE, resource, metric, since, target=120)]
@@ -1053,9 +1054,16 @@ async def host_vitals(host_id: str):
     reporting = bool(reg) and ls is not None
     stale = reporting and (datetime.now(timezone.utc) - ls).total_seconds() > _stale_after_seconds()
     cpu, mem = hostlvl.get("cpu_pct"), hostlvl.get("mem_used_pct")
+    # The hottest sensor that counts (temp_c_max leaves out unwired inputs),
+    # named so the tile says what it is reading.
+    temp = hostlvl.get("temp_c_max")
+    prefix = host.name + ":temp:"
+    hottest = hottest_sensor(host.name, {r[len(prefix):]: m["temp_c"] for r, m in latest.items()
+                                         if r.startswith(prefix) and m.get("temp_c") is not None})
     thresholds = current_app.config.get("THRESHOLDS", {})
     worst = worst_reading((("CPU", cpu, "cpu"), ("Memory", mem, "mem"), ("Disk /", disk_root, "disk"),
-                           ("Inodes on /", inodes_root, "disk"), ("Load per core", load_per_core, "load")),
+                           ("Inodes on /", inodes_root, "disk"), ("Load per core", load_per_core, "load"),
+                           ("Temperature", temp, "temp")),
                           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).
@@ -1068,7 +1076,7 @@ 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,
+        inodes_root=inodes_root, temp=temp, hottest=hottest[0].rsplit(" at ", 1)[0] if hottest else None,
         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", {})),

plugins/host_agent/templates/_host_vitals.html

@@ -1,10 +1,11 @@
 {# Host health header — live polled into the host hub: live or stale, the worst
    reading against Settings → Thresholds, last seen, then CPU / memory / disk /
-   load tiles graded by the same cutoffs (`grades`; CPU, memory and load within
+   load tiles, and the hottest sensor that counts with its name, graded by the same cutoffs (`grades`; CPU, memory and load within
    the host's own normal for the hour read healthy, and `usual` says so). Renders nothing until the agent
    reports (the Agent panel below then shows provisioning). #}
 {% from "_macros.html" import status_badge, stat_tile %}
 {% macro pct(v) %}{{ '%.0f%%'|format(v) if v is not none else '—' }}{% endmacro %}
+{% macro deg(v) %}{{ '%.0f°C'|format(v) if v is not none else '—' }}{% endmacro %}
 {% set grades = grades or {} %}
 {% if reporting %}
 <section class="card host-health" aria-label="Host health">
@@ -12,7 +13,7 @@
     {{ status_badge('stale' if stale else 'up', 'Stale' if stale else 'Live') }}
     <span class="host-health-summary">
       {%- if stale %}No report since {{ reg.last_seen_at|ago }}; the readings below are from then.
-      {%- elif worst %}<span class="tone-{{ worst[2] }}">{{ worst[0] }} {{ pct(worst[1]) }}</span> is past its {{ "critical" if worst[2] == "crit" else "warning" }} threshold.
+      {%- elif worst %}<span class="tone-{{ worst[2] }}">{{ worst[0] }} {{ deg(worst[1]) if worst[0] == "Temperature" else pct(worst[1]) }}</span> is past its {{ "critical" if worst[2] == "crit" else "warning" }} threshold.
       {%- elif usual %}Every reading is within its thresholds or its usual level for this hour.
       {%- else %}Every reading is within its thresholds.{% endif -%}
     </span>
@@ -24,13 +25,17 @@
     {# Charts, every mount, interface, disk and temperature sensor. #}
     <a href="/plugins/host_agent/{{ reg.host_id }}/" class="btn btn-sm btn-ghost" style="margin-left:auto;">Full metrics →</a>
   </div>
-  <div class="stat-strip host-health-tiles" style="margin-bottom:0;">
+  <div class="stat-strip host-health-tiles" style="margin-bottom:0;--tiles:{{ 5 if temp is not none else 4 }};">
     {{ stat_tile("CPU", pct(cpu), state=(grades.cpu or [status_class(cpu, 'cpu')])[0], hint=sparks.cpu|safe) }}
     {{ stat_tile("Memory", pct(mem), state=(grades.mem or [status_class(mem, 'mem')])[0], hint=sparks.mem|safe) }}
     {%- set inodes_worse = inodes_root is defined and inodes_root is not none and (disk_root is none or inodes_root > disk_root) %}
     {{ stat_tile("Disk /", pct(disk_root) ~ (" · inodes " ~ pct(inodes_root) if inodes_worse else ""),
                  state=(grades.disk or [status_class(disk_root, 'disk')])[0], hint=sparks.disk|safe) }}
     {{ stat_tile("Load per core", pct(load_per_core), state=(grades.load or [status_class(load_per_core, 'load')])[0], hint=sparks.load|safe) }}
+    {% if temp is not none %}
+    {%- set temp_hint %}{{ sparks.temp|safe }}{% if hottest %}<span class="stat-tile-sensor" title="{{ hottest }}">{{ hottest }}</span>{% endif %}{% endset %}
+    {{ stat_tile("Temperature", deg(temp), state=status_class(temp, 'temp'), hint=temp_hint) }}
+    {% endif %}
   </div>
   {% if usual and not stale %}
   <p class="field-hint" style="margin-top:0.6rem;">{{ usual | join("; ") | capitalize }}.</p>