fix(plant): alert hygiene — watchdog gate, trend smoothing, UPS [#344]

Three live-fire defects: unconditional 30-min watchdog page, tsys6 flap
false-positive, Tripp Lite runtime-low gap. TDD: 4 new regression tests.
On-box ha core check passed before commit.

Meat + verification: https://projects.knownelement.com/issues/344#note-4966

automations.yaml

@@ -68,15 +68,25 @@
   mode: single
 - id: pfv_plant_ups_runtime_low
   alias: PFV plant - UPS runtime low while on battery
-  description: On battery and runtime burned below 10 min — the graceful
-    shutdown window is closing. VMs before hypervisors per #455.
+  description: >-
+    On battery and runtime burned below 10 min — the graceful shutdown
+    window is closing. VMs before hypervisors per #455 ordering. Covers
+    BOTH UPSes (APC + Tripp Lite — the Tripp Lite gap closed 2026-09-06);
+    the status check maps each runtime sensor to its own UPS status.
   triggers:
   - trigger: numeric_state
-    entity_id: sensor.pfv_ups_runtime_minutes
+    entity_id:
+    - sensor.pfv_ups_runtime_minutes
+    - sensor.pfv_tripp_lite_runtime_minutes
     below: 10
   conditions:
   - condition: template
-    value_template: "{{ states('sensor.tsys1_ups_status') not in ['Online', 'unknown', 'unavailable'] }}"
+    value_template: >-
+      {% set status_map = {
+           'sensor.pfv_ups_runtime_minutes': 'sensor.tsys1_ups_status',
+           'sensor.pfv_tripp_lite_runtime_minutes': 'sensor.tsys1_triplite_status'} %}
+      {{ states(status_map.get(trigger.entity_id, 'sensor.tsys1_ups_status'))
+         not in ['Online', 'OL', 'unknown', 'unavailable'] }}
   actions:
   - action: notify.send_message
     target:
@@ -86,7 +96,7 @@
     data:
       title: UPS RUNTIME LOW
       url: /lovelace-pfv-server-room/ups
-      message: On battery {{ states('sensor.pfv_ups_runtime_minutes') }} min left — start graceful shutdown now (#455 ordering).
+      message: '{{ state_attr(trigger.entity_id, ''friendly_name'') }}: {{ states(trigger.entity_id) }} min left — start graceful shutdown now (#455 ordering).'
   mode: single
 - id: pfv_plant_ups_power_restored
   alias: PFV plant - utility power restored
@@ -190,31 +200,55 @@
   mode: single
 - id: pfv_plant_sensor_watchdog
   alias: PFV plant - sensor watchdog (unavailable sensors)
-  description: HA is the environmental brain (#344) — a silent sensor is an outage.
-    Re-alert suppressed by 4h cooldown via last_notified input_text if present.
+  description: >
+    HA is the environmental brain (#344) — a silent sensor is an outage.
+    Fleet-wide sweep (every pfv_* sensor, broader than the 5-min critical
+    watchdog). PUSHES ONLY when sensors are actually dead, and re-pages a
+    still-dead fleet at most every 4h — the unconditional 30-min page was
+    retired 2026-09-06 after live-fire alert fatigue. All-OK cycles log
+    quietly; the Kuma dead-man heartbeat (#792) owns liveness signaling.
+  mode: single
+  max_exceeded: silent
   triggers:
   - trigger: time_pattern
     minutes: /30
   actions:
-  - action: notify.send_message
-    target:
-      entity_id:
-      - notify.ultix_sidecar_new
-      - notify.allthes_ipad
-    data:
-      title: SENSOR WATCHDOG
-      url: /lovelace-pfv-server-room/overview
-      message: >-
-        {% set fleet = states.sensor | selectattr('entity_id', 'match', 'sensor\.pfv_')
-          | list %}
-        {% set dead = fleet | selectattr('state', 'in', ['unavailable', 'unknown']) | list %}
-        {% if dead | length > 0 %}
+  - variables:
+      fleet: "{{ states.sensor | selectattr('entity_id', 'match', 'sensor\\.pfv_') | list }}"
+      dead: "{{ fleet | selectattr('state', 'in', ['unavailable', 'unknown']) | list }}"
+      # 4h cooldown: page again only if the last page is older than 4h
+      # (or we never paged). Fresh HA start (no restore) counts as never.
+      # as_timestamp math — aware/naive datetime subtraction throws in Jinja.
+      notify_gate: >-
+        {{ states('input_datetime.pfv_plant_watchdog_last_notify') in ['unknown', 'unavailable', 'none']
+           or as_timestamp(now()) - as_timestamp(states('input_datetime.pfv_plant_watchdog_last_notify')) > 14400 }}
+  - if:
+    - condition: template
+      value_template: "{{ dead | length > 0 and notify_gate }}"
+    then:
+    - action: notify.send_message
+      target:
+        entity_id:
+        - notify.ultix_sidecar_new
+        - notify.allthes_ipad
+      data:
+        title: SENSOR WATCHDOG
+        url: /lovelace-pfv-server-room/overview
+        message: >-
           {{ dead | length }} of {{ fleet | length }} fleet sensors silent:
           {{ dead | map(attribute='entity_id') | join(', ') }}
-        {% else %}
-          all {{ fleet | length }} fleet sensors OK
-        {% endif %}
-  mode: single
+    - action: input_datetime.set_datetime
+      target:
+        entity_id: input_datetime.pfv_plant_watchdog_last_notify
+      data:
+        datetime: "{{ now().strftime('%Y-%m-%d %H:%M:%S') }}"
+    else:
+    - action: logbook.log
+      data:
+        name: Plant watchdog
+        message: >-
+          Sweep: all {{ fleet | length }} fleet sensors answering
+          ({{ dead | length }} silent, cooldown {{ 'active' if not notify_gate else 'n/a' }}).
 - id: pfv_plant_temp_rising_fast
   alias: PFV plant - temperature rising fast (rate-of-change)
   description: Catches dead AC minutes before the 104F threshold trips.