fix(alerts): iOS data.url only — clickAction rejected by apns schema [#344 #778]

Watchdog notify crash root-caused: iOS companion schema rejects
data.clickAction; url is the iOS deep-link key. Suite updated to
assert url presence per alert.
https://projects.knownelement.com/issues/778

.gitea/workflows/ci.yml

@@ -0,0 +1,28 @@
+# pfv-bms CI [#784 #778] — fleet standard per Discourse "CI/CD: Gitea Actions".
+# Runs on dev (pre-release gate) and release (final gate before live pull).
+name: ci
+on:
+  push:
+    branches: [dev, release]
+jobs:
+  lint:
+    runs-on: ultix
+    container:
+      image: node:20-bookworm
+    steps:
+      - uses: actions/checkout@v4
+      - name: yamllint
+        run: |
+          apt-get update -qq >/dev/null && apt-get install -qq -y python3-pip >/dev/null && pip install --quiet --break-system-packages yamllint
+          yamllint -c .yamllint .
+      - name: secret scan
+        run: |
+          if grep -rInE "BEGIN (RSA |OPENSSH |EC |DSA )?PRIVATE KEY|aws_secret_access_key *=|AKIA[0-9A-Z]{16}" --exclude-dir=.git .; then
+            echo "::error::secret material committed"; exit 1
+          else
+            echo "secret scan clean"
+          fi
+      - name: sdlc regression tests
+        run: |
+          chmod +x tests/test_sdlc.sh
+          bash tests/test_sdlc.sh

.yamllint

@@ -0,0 +1,22 @@
+# HA-config-aware yamllint [#784]: keep the checks that catch real bugs
+# (duplicates, structure), relax the stylistic ones HA templates trip.
+extends: default
+ignore: |
+  docs/
+  secrets.yaml
+  *.db
+rules:
+  line-length: disable
+  comments: disable
+  comments-indentation: disable
+  document-start: disable
+  truthy:
+    check-keys: false
+  indentation:
+    spaces: consistent
+    indent-sequences: consistent
+  key-duplicates: enable
+  new-line-at-end-of-file: disable
+  trailing-spaces: disable
+  empty-lines:
+    max-end: 2

README.md

@@ -134,16 +134,23 @@ apps.
 
 ## 🚀 Deployment pipeline
 
+**Branch model (2026-09-04):** `dev` = WIP integration — the pipeline
+IGNORES it. `release` = what the box runs — pushing release IS the deploy.
+`master` is frozen (pre-branch-model history). A PR process with AI +
+human reviewers will gate dev → release (founder, upcoming).
+
 ```mermaid
 flowchart LR
-    PUSH[📝 git push] --> HOOK[gitea webhook<br/>fast path]
+    PUSH[📝 push to dev] --> NOOP[🚫 pipeline ignores dev]
-    PUSH --> SHA[sha-watch<br/>safety net · 300 s poll]
+    REL[🚀 merge dev → release<br/>and push] --> HOOK[gitea webhook<br/>fast path]
+    REL --> SHA[sha-watch<br/>release sha · 300 s poll]
     HOOK & SHA --> CHECK{changed files?}
-    CHECK -->|packages/**| RESTART[♻️ core restart<br/>webhook triggers need it]
+    CHECK -->|configuration.yaml,<br/>packages/**| RESTART[♻️ core restart<br/>webhook triggers need it]
     CHECK -->|other YAML| RELOAD[⚡ reload only<br/>~5 min to live]
 ```
 
-Gate before pushing `packages/**`: `ha core check` must pass on-box.
+Gate before pushing `release` (and after any `packages/**` change on
+`dev`): `ha core check` must pass on-box.
 Measured end-to-end: 4 m 52 s commit → live.
 
 ## 🗺️ Repo map

automations.yaml

@@ -4,7 +4,7 @@
   - trigger: state
     entity_id:
     - sensor.tsys1_ups_status
-    - sensor.tsys9_ups_status
+    - sensor.tsys1_triplite_status
   conditions:
   - condition: template
     value_template: '{{ ''On Battery'' in states(trigger.entity_id) }}'
@@ -16,7 +16,6 @@
       - notify.allthes_ipad
     data:
       title: POWER OUTAGE
-      clickAction: /lovelace-pfv-server-room/ups
       url: /lovelace-pfv-server-room/ups
       message: '{{ state_attr(trigger.entity_id, ''friendly_name'') }} lost utility
         power and is ON BATTERY at {{ states(''sensor.'' ~ trigger.entity_id.split(''.'')[1]
@@ -28,6 +27,7 @@
   - trigger: numeric_state
     entity_id:
     - sensor.tsys1_ups_battery_charge
+    - sensor.tsys1_triplite_battery_charge
     below: 40
   conditions:
   - condition: template
@@ -41,7 +41,6 @@
       - notify.allthes_ipad
     data:
       title: UPS BATTERY LOW
-      clickAction: /lovelace-pfv-server-room/ups
       url: /lovelace-pfv-server-room/ups
       message: '{{ trigger.entity_id }} at {{ states(trigger.entity_id) }}% while
         on battery. Start graceful shutdown of VMs before hypervisors (#455 ordering).'
@@ -52,7 +51,7 @@
   - trigger: state
     entity_id:
     - sensor.tsys1_ups_status
-    - sensor.tsys9_ups_status
+    - sensor.tsys1_triplite_status
     to: unavailable
     for: 00:05:00
   actions:
@@ -63,7 +62,6 @@
       - notify.allthes_ipad
     data:
       title: UPS COMMS LOST
-      clickAction: /lovelace-pfv-server-room/ups
       url: /lovelace-pfv-server-room/ups
       message: '{{ trigger.entity_id }} unreachable for 5 minutes (nut-server or network
         path down; tsys1 also hosts pfv-bms itself).'
@@ -87,7 +85,6 @@
       - notify.allthes_ipad
     data:
       title: UPS RUNTIME LOW
-      clickAction: /lovelace-pfv-server-room/ups
       url: /lovelace-pfv-server-room/ups
       message: On battery {{ states('sensor.pfv_ups_runtime_minutes') }} min left — start graceful shutdown now (#455 ordering).
   mode: single
@@ -97,7 +94,7 @@
   - trigger: state
     entity_id:
     - sensor.tsys1_ups_status
-    - sensor.tsys9_ups_status
+    - sensor.tsys1_triplite_status
   conditions:
   - condition: template
     value_template: "{{ trigger.from_state is not none and 'On Battery' in trigger.from_state.state\n
@@ -110,7 +107,6 @@
       - notify.allthes_ipad
     data:
       title: Power restored
-      clickAction: /lovelace-pfv-server-room/ups
       url: /lovelace-pfv-server-room/ups
       message: '{{ state_attr(trigger.entity_id, ''friendly_name'') }} is back ONLINE.'
   mode: single
@@ -188,7 +184,6 @@
       - notify.allthes_ipad
     data:
       title: HIGH TEMPERATURE
-      clickAction: /lovelace-pfv-server-room/temps
       url: /lovelace-pfv-server-room/temps
       message: '{{ trigger.entity_id }} is {{ states(trigger.entity_id) }}°F (class
         threshold exceeded). Check cooling/airflow.'
@@ -208,7 +203,6 @@
       - notify.allthes_ipad
     data:
       title: SENSOR WATCHDOG
-      clickAction: /lovelace-pfv-server-room/overview
       url: /lovelace-pfv-server-room/overview
       message: >-
         {% set fleet = states.sensor | selectattr('entity_id', 'match', 'sensor\.pfv_')
@@ -242,11 +236,10 @@
       - notify.allthes_ipad
     data:
       title: TEMP RISING FAST
-      clickAction: /lovelace-pfv-server-room/temps
       url: /lovelace-pfv-server-room/temps
       message: '{{ trigger.entity_id }} climbing ~10F/15min — check cooling
         before the 104F threshold. (rate-of-change early warning)'
-# Deploy pipeline [#734]: gitea repo webhook (master pushes) -> forced pull
+# Deploy pipeline [#734]: gitea repo webhook (release pushes) -> forced pull
 # -> minimal reload. Core restarts ONLY when configuration.yaml or a
 # packages platform-sensor file changed; everything else reloads with no
 # bounce. The git_pull add-on's auto_restart is disabled - this webhook
@@ -254,7 +247,7 @@
 - id: pfv_deploy_git_webhook
   alias: PFV deploy - git push to pull + minimal reload
   description: >-
-    Gitea webhook on master pushes. Forces a git pull now, then
+    Gitea webhook on release pushes. Forces a git pull now, then
     homeassistant.reload_all unless files that require a core restart
     changed. Replaces the git_pull add-on timer auto-restart [#734].
   mode: queued
@@ -269,9 +262,9 @@
   actions:
   - if:
     - condition: template
-      value_template: "{{ trigger.json.ref | default('') != 'refs/heads/master' }}"
+      value_template: "{{ trigger.json.ref | default('') != 'refs/heads/release' }}"
     then:
-    - stop: "deploy webhook: non-master ref {{ trigger.json.ref | default('') }} ignored"
+    - stop: "deploy webhook: non-release ref {{ trigger.json.ref | default('') }} ignored"
   - variables:
       changed_files: >-
         {{ (trigger.json.commits | default([]) | map(attribute='added') | flatten | list)
@@ -337,7 +330,7 @@
       data:
         title: PFV deploy complete
         message: "Pulled + reloaded YAML at {{ now().strftime('%H:%M:%S') }} - no core restart. Files: {{ changed_files | join(', ') | truncate(120) }}"
-# Deploy pipeline safety net [#734]: polls gitea master HEAD (rest sensor
+# Deploy pipeline safety net [#734]: polls gitea release HEAD (rest sensor
 # in packages/deploy_pipeline.yaml) and applies pulls reload-only. The
 # gitea webhook is the fast path once gitea's SSRF allowlist permits
 # pfv-bms.knel.net; until then this net catches every push within 5 min
@@ -346,7 +339,7 @@
 - id: pfv_deploy_sha_watch
   alias: PFV deploy - gitea sha watch safety net
   description: >-
-    Master HEAD sha changed -> pull + CORE RESTART. Interim deploy
+    Release HEAD sha changed -> pull + CORE RESTART. Interim deploy
     trigger while gitea webhook delivery is blocked by its SSRF host
     allowlist [#734]. Restart (not reload) is REQUIRED: automation
     reload loses webhook-trigger registration - found live 2026-09-03
@@ -354,12 +347,12 @@
     scan ingest, this pipeline's own fast path) silently stop firing
     while the endpoint still returns HTTP 200. Core restart
     re-registers them. Accepted trade-off: ~1 min HA outage per
-    master deploy.
+    release deploy.
   mode: single
   max_exceeded: silent
   triggers:
   - trigger: state
-    entity_id: sensor.pfv_deploy_gitea_master_head
+    entity_id: sensor.pfv_deploy_gitea_release_head
   conditions:
   - condition: template
     value_template: >-
@@ -383,7 +376,7 @@
     data:
       title: PFV deploy (sha watch)
       message: >-
-        New master HEAD {{ states('sensor.pfv_deploy_gitea_master_head')[:7] }}
+        New release HEAD {{ states('sensor.pfv_deploy_gitea_release_head')[:7] }}
         pulled. Restarting HA core (webhook re-registration) - back in
         ~1 min.
   - action: homeassistant.restart
@@ -518,10 +511,119 @@
       - notify.allthes_ipad
     data:
       title: TEMPERATURE RECOVERED
-      clickAction: /lovelace-pfv-server-room/temps
       url: /lovelace-pfv-server-room/temps
       message: >-
         {{ state_attr(trigger.entity_id, 'friendly_name') | default(trigger.entity_id) }}
         back to {{ states(trigger.entity_id) }}°F and holding — was
         {{ trigger.from_state.state }}°F when the alert cleared (tier fire line {{ fire }}°F).
   mode: single
+- id: pfv_watchdog_stale_entities
+  alias: PFV watchdog - stale entity auto-heal
+  description: >
+    Detects silent poller wedges (2026-09-04: snmp tsys9 went 12h
+    undetected; NUT APC 3h) and auto-heals config-entry platforms via
+    homeassistant.reload_config_entry — no restart needed. Escalates to
+    notify when reload does not recover. Auto core restart ONLY while
+    input_boolean.pfv_watchdog_auto_restart is ON and entities stay
+    stale — restart costs ~1 min downtime and re-registers webhooks
+    (#345, #789). v1 notify repeats each cycle while stale (visible
+    alarm); throttle in v2.
+  mode: single
+  max_exceeded: silent
+  triggers:
+  - trigger: time_pattern
+    minutes: /5
+  variables:
+    checks:
+    - [sensor.pfv_tsys1_rack_temperature, 20]
+    - [sensor.pfv_tsys1_drive_temperature, 30]
+    - [sensor.pfv_tsys3_cpu_temperature, 20]
+    - [sensor.pfv_tsys4_ambient_temperature, 20]
+    - [sensor.pfv_tsys6_cpu_temperature, 20]
+    - [sensor.pfv_tsys6_drac_ambient, 30]
+    - [sensor.pfv_tsys7_cpu_temperature, 20]
+    - [sensor.pfv_tsys7_drac_inlet, 30]
+    - [sensor.pfv_tsys9_cpu_temperature, 20]
+    - [sensor.pfv_tsys9_drive_temperature, 30]
+    - [sensor.tsys1_ups_status, 15]
+    - [sensor.tsys1_triplite_status, 15]
+    - [sensor.pfv_deploy_gitea_release_head, 30]
+  actions:
+  - variables:
+      stale_list: >-
+        {% set ns = namespace(stale=[]) %}
+        {% for pair in checks %}
+          {% set s = states[pair[0]] %}
+          {% if s is not none and s.last_updated is defined
+                and (now() - s.last_updated).total_seconds() > pair[1] * 60 %}
+            {% set ns.stale = ns.stale + [pair[0]] %}
+          {% endif %}
+        {% endfor %}
+        {{ ns.stale }}
+  - condition: template
+    value_template: "{{ stale_list | length > 0 }}"
+  - repeat:
+      for_each: "{{ stale_list }}"
+      sequence:
+      - action: homeassistant.reload_config_entry
+        data:
+          entity_id: "{{ repeat.item }}"
+  - delay:
+      hours: 0
+      minutes: 2
+      seconds: 0
+  - variables:
+      still_stale: >-
+        {% set ns = namespace(stale=[]) %}
+        {% for pair in checks %}
+          {% set s = states[pair[0]] %}
+          {% if s is not none and s.last_updated is defined
+                and (now() - s.last_updated).total_seconds() > pair[1] * 60 %}
+            {% set ns.stale = ns.stale + [pair[0]] %}
+          {% endif %}
+        {% endfor %}
+        {{ ns.stale }}
+  - action: notify.send_message
+    target:
+      entity_id:
+      - notify.ultix_sidecar_new
+      - notify.allthes_ipad
+    data:
+      title: WATCHDOG
+      url: /lovelace-pfv-server-room/temps
+      message: >-
+        Stale after auto-reload: {{ still_stale | join(', ') }}.
+        Auto-restart is {{ 'ON' if is_state('input_boolean.pfv_watchdog_auto_restart','on')
+        else 'OFF (arm it on the watchdog switch if you want unattended restarts)' }}.
+  - if:
+    - condition: template
+      value_template: "{{ is_state('input_boolean.pfv_watchdog_auto_restart','on') }}"
+    then:
+    - delay:
+        hours: 0
+        minutes: 30
+        seconds: 0
+    - variables:
+        hard_stale: >-
+          {% set ns = namespace(stale=[]) %}
+          {% for pair in checks %}
+            {% set s = states[pair[0]] %}
+            {% if s is not none and s.last_updated is defined
+                  and (now() - s.last_updated).total_seconds() > pair[1] * 60 %}
+              {% set ns.stale = ns.stale + [pair[0]] %}
+            {% endif %}
+          {% endfor %}
+          {{ ns.stale }}
+    - if:
+      - condition: template
+        value_template: "{{ hard_stale | length > 0 }}"
+      then:
+      - action: notify.send_message
+        target:
+          entity_id:
+          - notify.ultix_sidecar_new
+          - notify.allthes_ipad
+        data:
+          title: WATCHDOG — restarting core
+          message: "Still stale after reload + 30 min: {{ hard_stale | join(', ') }}. Restarting HA core now."
+      - action: homeassistant.restart

configuration.yaml

@@ -20,6 +20,21 @@ prometheus:
 lovelace:
   mode: storage
   dashboards:
+    pfv-overview:
+      mode: yaml
+      title: Ops Overview
+      filename: dashboards/overview.yaml
+      icon: mdi:view-dashboard-outline
+    pfv-power:
+      mode: yaml
+      title: Power
+      filename: dashboards/power.yaml
+      icon: mdi:flash
+    pfv-thermal:
+      mode: yaml
+      title: Thermal
+      filename: dashboards/thermal.yaml
+      icon: mdi:thermometer-lines
     pfv-server-room:
       mode: yaml
       title: Server Room
@@ -34,3 +49,10 @@ lovelace:
       title: STLP
       filename: dashboards/stlp.yaml
       icon: mdi:home
+
+# Watchdog arm switch (#789): auto core restart on unresolved staleness.
+# Default OFF — reload_config_entry heals config-entry wedges without it.
+input_boolean:
+  pfv_watchdog_auto_restart:
+    name: Watchdog auto core restart
+    icon: mdi:restart-alert

dashboards/overview.yaml

@@ -0,0 +1,79 @@
+title: Ops Overview
+views:
+  - title: Overview
+    type: sections
+    sections:
+      - type: grid
+        cards:
+          - type: markdown
+            content: >
+              ## Ops Overview
+
+              One screen: is anything on fire? Details live in
+              [Power](/lovelace-pfv-power), [Thermal](/lovelace-pfv-thermal),
+              [Server Room](/lovelace-pfv-server-room) and
+              [STLP](/lovelace-pfv-stlp).
+      - type: grid
+        cards:
+          - type: heading
+            heading: Room & cooling
+          - type: gauge
+            entity: sensor.pfv_tsys1_rack_temperature
+            name: Server room
+            min: 50
+            max: 110
+            severity:
+              green: 60
+              yellow: 85
+              red: 95
+          - type: entities
+            entities:
+              - sensor.pfv_garage_temperature
+              - sensor.pfv_artroom_temperature
+      - type: grid
+        cards:
+          - type: heading
+            heading: Power
+          - type: gauge
+            entity: sensor.tsys1_ups_battery_charge
+            name: APC charge
+            min: 0
+            max: 100
+            severity:
+              green: 60
+              yellow: 40
+              red: 20
+          - type: gauge
+            entity: sensor.tsys1_triplite_battery_charge
+            name: Tripp Lite charge
+            min: 0
+            max: 100
+            severity:
+              green: 60
+              yellow: 40
+              red: 20
+          - type: entities
+            entities:
+              - sensor.tsys1_ups_status
+              - sensor.tsys1_triplite_status
+              - sensor.pfv_ups_runtime_minutes
+              - sensor.pfv_tripp_lite_runtime_minutes
+      - type: grid
+        cards:
+          - type: heading
+            heading: Alerts & self-healing
+          - type: entities
+            entities:
+              - automation.pfv_plant_ups_on_battery
+              - automation.pfv_plant_ups_battery_low
+              - automation.pfv_plant_ups_communication_lost
+              - automation.pfv_plant_high_temperature
+              - automation.pfv_watchdog_stale_entity_auto_heal
+              - input_boolean.pfv_watchdog_auto_restart
+      - type: grid
+        cards:
+          - type: markdown
+            content: >
+              **Pipeline:** deploy sensor tracks `release` on KNEL/KNELBMS.
+              CI runs on every dev/release push (Actions tab in gitea).
+              Out-of-band paging: Uptime Kuma (Cloudron).

dashboards/power.yaml

@@ -0,0 +1,114 @@
+title: Power
+views:
+  - title: UPS detail
+    type: sections
+    sections:
+      - type: grid
+        cards:
+          - type: heading
+            heading: APC Smart-UPS C 1500 (battery-side USB HID)
+          - type: gauge
+            entity: sensor.tsys1_ups_battery_charge
+            name: Charge
+            min: 0
+            max: 100
+            severity:
+              green: 60
+              yellow: 40
+              red: 20
+          - type: gauge
+            entity: sensor.pfv_ups_runtime_minutes
+            name: Runtime (min)
+            min: 0
+            max: 60
+            severity:
+              green: 25
+              yellow: 15
+              red: 5
+      - type: grid
+        cards:
+          - type: entities
+            title: APC status
+            entities:
+              - sensor.tsys1_ups_status
+              - sensor.tsys1_ups_status_data
+              - sensor.tsys1_ups_battery_charge
+              - sensor.pfv_ups_runtime_minutes
+              - sensor.tsys1_ups_battery_runtime
+              - sensor.tsys1_ups_battery_voltage
+              - sensor.tsys1_ups_nominal_battery_voltage
+              - sensor.tsys1_ups_low_battery_setpoint
+              - sensor.tsys1_ups_beeper_status
+          - type: markdown
+            content: >
+              Serial AS1213210423 · mfr 2012-03 · fw UPS 02.2 · 24 V
+              nominal. USB HID exposes battery-side metrics only — no
+              input/output voltage or watts on this unit.
+      - type: grid
+        cards:
+          - type: heading
+            heading: Tripp Lite 1500 VA (moved from tsys9, #372)
+          - type: gauge
+            entity: sensor.tsys1_triplite_battery_charge
+            name: Charge
+            min: 0
+            max: 100
+            severity:
+              green: 60
+              yellow: 40
+              red: 20
+          - type: gauge
+            entity: sensor.tsys1_triplite_load
+            name: Load %
+            min: 0
+            max: 100
+            severity:
+              green: 70
+              yellow: 85
+              red: 95
+      - type: grid
+        cards:
+          - type: entities
+            title: Tripp Lite status
+            entities:
+              - sensor.tsys1_triplite_status
+              - sensor.tsys1_triplite_status_data
+              - sensor.tsys1_triplite_battery_charge
+              - sensor.tsys1_triplite_apparent_power
+              - sensor.tsys1_triplite_output_current
+              - sensor.tsys1_triplite_load
+              - sensor.pfv_tripp_lite_runtime_minutes
+              - sensor.tsys1_triplite_battery_runtime
+              - sensor.tsys1_triplite_input_voltage
+              - sensor.tsys1_triplite_output_voltage
+              - sensor.tsys1_triplite_nominal_power
+  - title: Trends
+    type: sections
+    sections:
+      - type: grid
+        cards:
+          - type: history-graph
+            title: UPS charge (7 days)
+            entities:
+              - sensor.tsys1_ups_battery_charge
+              - sensor.tsys1_triplite_battery_charge
+            hours_to_show: 168
+      - type: grid
+        cards:
+          - type: history-graph
+            title: Tripp Lite apparent power (24h)
+            entities:
+              - sensor.tsys1_triplite_apparent_power
+            hours_to_show: 24
+          - type: history-graph
+            title: UPS load % (24h)
+            entities:
+              - sensor.tsys1_triplite_load
+            hours_to_show: 24
+      - type: grid
+        cards:
+          - type: markdown
+            content: >
+              **Planned sections** (land with their data sources):
+              Emporia CT rental-bank feed (#623), whole-house kWh vs
+              solar production (#760), garage PDU circuits (#733).

dashboards/server-room.yaml

@@ -103,6 +103,46 @@ views:
               fw UPS 02.2 · PbAc, 24 V nominal · usbhid-ups via pfv-tsys1
               (NUT :3493). This unit reports no input/output voltage over
               USB HID — battery-side metrics only.
+      - type: grid
+        cards:
+          - type: gauge
+            entity: sensor.tsys1_triplite_battery_charge
+            name: Tripp Lite charge
+            min: 0
+            max: 100
+            severity:
+              green: 60
+              yellow: 40
+              red: 20
+          - type: gauge
+            entity: sensor.tsys1_triplite_load
+            name: Tripp Lite load %
+            min: 0
+            max: 100
+            severity:
+              green: 70
+              yellow: 85
+              red: 95
+      - type: grid
+        cards:
+          - type: entities
+            title: Tripp Lite status
+            entities:
+              - sensor.tsys1_triplite_status
+              - sensor.tsys1_triplite_status_data
+              - sensor.tsys1_triplite_battery_charge
+              - sensor.tsys1_triplite_apparent_power
+              - sensor.tsys1_triplite_output_current
+              - sensor.tsys1_triplite_load
+              - sensor.tsys1_triplite_input_voltage
+              - sensor.tsys1_triplite_output_voltage
+              - sensor.tsys1_triplite_battery_runtime
+          - type: markdown
+            content: >
+              **Tripp Lite UPS** · usbhid-ups via pfv-tsys1 (NUT :3493);
+              moved from tsys9 2026-09-04 (#372). Carries ~46% load
+              (~414 VA apparent / 1500 VA nominal) — mind runtime
+              before adding gear.
       - type: grid
         cards:
           - type: entities

dashboards/thermal.yaml

@@ -0,0 +1,119 @@
+title: Thermal
+views:
+  - title: Rooms
+    type: sections
+    sections:
+      - type: grid
+        cards:
+          - type: gauge
+            entity: sensor.pfv_tsys1_rack_temperature
+            name: Server room
+            min: 50
+            max: 110
+            severity:
+              green: 60
+              yellow: 85
+              red: 95
+          - type: history-graph
+            title: Server room (24h)
+            entities:
+              - sensor.pfv_tsys1_rack_temperature
+            hours_to_show: 24
+      - type: grid
+        cards:
+          - type: gauge
+            entity: sensor.pfv_garage_temperature
+            name: Garage
+            min: 30
+            max: 110
+            severity:
+              green: 40
+              yellow: 90
+              red: 100
+          - type: history-graph
+            title: Garage (24h)
+            entities:
+              - sensor.pfv_garage_temperature
+            hours_to_show: 24
+      - type: grid
+        cards:
+          - type: gauge
+            entity: sensor.pfv_artroom_temperature
+            name: Art room
+            min: 40
+            max: 110
+            severity:
+              green: 60
+              yellow: 85
+              red: 95
+          - type: history-graph
+            title: Art room (24h)
+            entities:
+              - sensor.pfv_artroom_temperature
+            hours_to_show: 24
+      - type: grid
+        cards:
+          - type: markdown
+            content: >
+              **Minisplit** — climate entity lands with the Carrier dongle
+              commissioning (#629). Manual setpoint tonight: 62°F, with the
+              oscillating fan improving distribution. Alert tiers:
+              ambient 104°F · drives 140°F · NVMe 150°F · PCH 160°F ·
+              GPU 185°F.
+  - title: Racks & silicon
+    type: sections
+    sections:
+      - type: grid
+        cards:
+          - type: entities
+            title: R3 · PowerEdge (DRAC)
+            entities:
+              - sensor.pfv_tsys6_cpu_temperature
+              - sensor.pfv_tsys6_drac_ambient
+              - sensor.pfv_tsys7_cpu_temperature
+              - sensor.pfv_tsys7_drac_inlet
+              - sensor.pfv_tsys7_drac_exhaust
+              - sensor.pfv_tsys7_drac_cpu1
+              - sensor.pfv_tsys7_drac_cpu2
+      - type: grid
+        cards:
+          - type: entities
+            title: R3 · Pis + Jetson
+            entities:
+              - sensor.pfv_svrpi_temperature
+              - sensor.pfv_subopi3_temperature
+              - sensor.pfv_subopi_dev_3_temperature
+              - sensor.pfv_subopi_dev_4_temperature
+              - sensor.pfv_jetson_temperature
+              - sensor.pfv_jetson_gpu_temperature
+      - type: grid
+        cards:
+          - type: entities
+            title: R5 · Laptops
+            entities:
+              - sensor.pfv_tsys3_cpu_temperature
+              - sensor.pfv_tsys3_gpu_temperature
+              - sensor.pfv_tsys3_nvme_temperature
+              - sensor.pfv_tsys5_nvme_temperature
+      - type: grid
+        cards:
+          - type: entities
+            title: R5 · Desktops / OptiPlex-class
+            entities:
+              - sensor.pfv_tsys1_rack_temperature
+              - sensor.pfv_tsys4_ambient_temperature
+              - sensor.pfv_tsys1_cpu_temperature
+              - sensor.pfv_tsys4_cpu_temperature
+              - sensor.pfv_tsys9_cpu_temperature
+              - sensor.pfv_tsys9_pch_temperature
+      - type: grid
+        cards:
+          - type: history-graph
+            title: CPU temperatures (24h)
+            entities:
+              - sensor.pfv_tsys1_cpu_temperature
+              - sensor.pfv_tsys3_cpu_temperature
+              - sensor.pfv_tsys6_cpu_temperature
+              - sensor.pfv_tsys7_cpu_temperature
+              - sensor.pfv_tsys9_cpu_temperature
+            hours_to_show: 24

packages/deploy_pipeline.yaml

@@ -1,4 +1,4 @@
-# Deploy pipeline [#734]: gitea master-HEAD sha watcher. Feeds the
+# Deploy pipeline [#734]: gitea release-branch sha watcher. Feeds the
 # sha-watch deploy automation (reload-only apply). The gitea webhook
 # (gitea hook #10 -> pfv_deploy_git_webhook automation) is the fast path
 # with full restart mapping, but gitea cannot deliver webhooks to
@@ -6,15 +6,15 @@
 # (founder action via Cloudron file manager); this watcher is the
 # always-works safety net.
 rest:
-  - resource: https://git.knownelement.com/api/v1/repos/KNEL/pfv-bms/commits?limit=1
+  - resource: https://git.knownelement.com/api/v1/repos/KNEL/KNELBMS/commits?sha=release&limit=1
     headers:
       Authorization: !secret gitea_auth_header
       User-Agent: pfv-bms-deploy-watch
     scan_interval: 300
     verify_ssl: true
     sensor:
-      - name: PFV deploy gitea master head
+      - name: PFV deploy gitea release head
-        unique_id: pfv_deploy_gitea_master_head
+        unique_id: pfv_deploy_gitea_release_head
         value_template: "{{ value_json[0].sha if value_json is list and value_json | length > 0 else (value_json | string | truncate(90)) }}"
 
 # E2E self-deploy proof commit [#734] - if you can read this in /config,

packages/doorman.yaml

@@ -7,6 +7,7 @@
 # PR gate). The roster is fetched live from the gitea API — NO git
 # mechanics, NO submodule (git_pull add-on lacks submodule support),
 # NO local copy: access-roster remains the single source of truth.
+# Reader/door contract (webhook JSON + unlock endpoint): KNEL/doorman README
 #
 # UNLOCK PATH (founder-approved 2026-09-03): valid badge + the
 # doorman_unlock_enabled input_boolean ON -> rest_command fires the
@@ -81,6 +82,15 @@ input_boolean:
     name: Doorman unlock armed
     icon: mdi:lock-open-variant
 
+shell_command:
+  # Unlock dispatch via curl — swapped from rest_command 2026-09-04: the
+  # rest_command integration silently fails to register on this box
+  # (404 on /api/services/rest_command despite valid config + secret;
+  # root-cause pending in #345/#741). curl is present in the HA core
+  # container. Token lives in the URL secret — process-list exposure
+  # accepted (isolated container).
+  doorman_unlock: "curl -sS -m 10 '{{ doorman_unlock_url }}'"
+
 rest_command:
   # Fires the doorctl endpoint on pfvsvrpi (systemd socket-activated,
   # Tailscale-bound, token+source allowlisted; self-securing relay).
@@ -173,7 +183,7 @@ automation:
                       {{ is_state('input_boolean.doorman_unlock_enabled', 'on')
                          and not (trigger.json.local_unlock | default(false) | bool(false)) }}
                 then:
-                  - action: rest_command.doorman_unlock
+                  - action: shell_command.doorman_unlock
                     continue_on_error: true
                   - action: logbook.log
                     data:

packages/plant_snmp.yaml

@@ -800,6 +800,13 @@ template:
         state: >-
           {% set v = states('sensor.tsys1_ups_battery_runtime') %}
           {{ (v | float / 60) | round(0) if is_number(v) else none }}
+      - name: "PFV Tripp Lite runtime minutes"
+        unique_id: pfv_triplite_runtime_minutes
+        device_class: duration
+        unit_of_measurement: "min"
+        state: >-
+          {% set v = states('sensor.tsys1_triplite_battery_runtime') %}
+          {{ (v | float / 60) | round(0) if is_number(v) else none }}
       - name: "PFV tsys1 drive temperature"
         unique_id: pfv_tsys1_drive_temperature
         device_class: temperature

scenes.yaml

@@ -0,0 +1 @@
+# intentionally empty — scenes are authored in the HA UI if ever needed

scripts.yaml

@@ -0,0 +1 @@
+# intentionally empty — scripts are authored in the HA UI if ever needed

tests/test_sdlc.sh

@@ -0,0 +1,51 @@
+#!/bin/bash
+# SDLC regression tests (#778) — run in CI (see .gitea/workflows/ci.yml).
+# Each test guards a rule that exists because of a real incident or ruling.
+set -uo pipefail
+cd "$(dirname "$0")/.." || exit 1
+
+FAIL=0
+t() {
+  # $1 = label, $2 = shell command string
+  if eval "$2"; then
+    echo "  OK   $1"
+  else
+    echo "  FAIL $1"
+    FAIL=$((FAIL + 1))
+  fi
+}
+
+echo "=== alert twins (every alert ships a recovery twin) ==="
+t "utility power restored twin" \
+  "grep -q 'id: pfv_plant_ups_power_restored' automations.yaml"
+t "temperature recovered twin" \
+  "grep -q 'id: pfv_plant_temperature_recovered' automations.yaml"
+
+echo "=== alert deep links (taps land on dashboards, #344) ==="
+ALERTS="POWER OUTAGE|UPS BATTERY LOW|UPS COMMS LOST|UPS RUNTIME LOW|Power restored|HIGH TEMPERATURE|SENSOR WATCHDOG|TEMP RISING FAST|TEMPERATURE RECOVERED"
+DL_OK=1
+IFS='|' read -ra ALERT_ARR <<< "$ALERTS"
+for a in "${ALERT_ARR[@]}"; do
+  if ! grep -A2 "title: $a$" automations.yaml | grep -q "      url: "; then
+    echo "  (missing deep link: $a)"
+    DL_OK=0
+  fi
+done
+t "all alerts deep-linked" "[ \"$DL_OK\" -eq 1 ]"
+
+echo "=== watchdog coverage (#789) ==="
+t "watchdog watches the deploy sensor" \
+  "grep -q 'sensor.pfv_deploy_gitea_release_head, 30' automations.yaml"
+t "watchdog automation exists" \
+  "grep -q 'id: pfv_watchdog_stale_entities' automations.yaml"
+
+echo "=== ghost entities (dead references never return) ==="
+t "no tsys9_ups ghost refs" \
+  "! grep -rq 'tsys9_ups' automations.yaml packages/ dashboards/"
+
+echo "=== secrets ==="
+t "no private keys in tree" \
+  "! grep -rInE 'BEGIN (RSA |OPENSSH |EC |DSA )?PRIVATE KEY' --exclude-dir=.git --exclude-dir=docs ."
+
+echo "=== SDLC SUITE: $FAIL failures ==="
+exit "$FAIL"

themes/.gitkeep

@@ -0,0 +1,2 @@
+# intentional placeholder: themes dir must exist for the
+# !include_dir_merge_named in configuration.yaml [#784 gardening]