fix(insights): raise device overheating thresholds for outdoor equipment

Warning: 65°C → 80°C, Critical: 75°C → 90°C. Outdoor gear in Texas
routinely runs at 70-75°C ambient. The old thresholds generated useless
AI insights like "Verona to Altoga at 72°C may be overheating" — that's
normal for an enclosure in summer, not actionable.

lib/towerops/llm/insight_prompt.ex

@@ -121,7 +121,7 @@ defmodule Towerops.LLM.InsightPrompt do
     """,
     "device_overheating" => """
     Rule context: a device has at least one temperature sensor above
-    65 °C (warning) or 75 °C (critical). Metadata fields:
+    80 °C (warning) or 90 °C (critical). Metadata fields:
       temperature_c, sensor_descr, qoe_score, warning_threshold_c,
       critical_threshold_c.
     If qoe_score is also low (<60), highlight that the QoE drop is

lib/towerops/llm/network_snapshot.ex

@@ -187,16 +187,18 @@ defmodule Towerops.LLM.NetworkSnapshot do
     |> Repo.all()
   end
 
-  # Devices with at least one temperature sensor reading > 60°C in the
-  # last hour. The `last_value` field on `Sensor` is updated on every
-  # poll, so we don't need a time-series join.
+  # Devices with at least one temperature sensor reading > 80°C.
+  # Outdoor equipment in hot climates routinely hits 70-75°C — we only
+  # surface devices that are approaching thermal-throttling territory.
+  # The `last_value` field on `Sensor` is updated on every poll, so we
+  # don't need a time-series join.
   defp hottest_devices(organization_id) do
     Sensor
     |> join(:inner, [s], sd in SnmpDevice, on: s.snmp_device_id == sd.id)
     |> join(:inner, [_s, sd], d in Device, on: sd.device_id == d.id)
     |> where([s, _sd, d], d.organization_id == ^organization_id)
     |> where([s], s.sensor_type == "temperature")
-    |> where([s], not is_nil(s.last_value) and s.last_value > 60.0)
+    |> where([s], not is_nil(s.last_value) and s.last_value > 80.0)
     |> order_by([s], desc: s.last_value)
     |> limit(@top_n)
     |> select([s, _sd, d], %{device_id: d.id, name: d.name, max_temp_c: s.last_value})

lib/towerops/recommendations/rules/device_overheating.ex

@@ -23,8 +23,11 @@ defmodule Towerops.Recommendations.Rules.DeviceOverheating do
   alias Towerops.Snmp.Device, as: SnmpDevice
   alias Towerops.Snmp.Sensor
 
-  @warning_threshold_c 65.0
-  @critical_threshold_c 75.0
+  # Outdoor equipment in hot climates routinely runs at 70-75°C ambient.
+  # Thresholds are set at levels where thermal throttling or hardware
+  # damage is actually imminent, not just "warm to the touch."
+  @warning_threshold_c 80.0
+  @critical_threshold_c 90.0
   @qoe_concern_threshold 60.0
   # Anything above this is implausible for routing/wireless gear and
   # almost always indicates a missing divisor in the SNMP profile. Skip

test/towerops/recommendations/rules/device_overheating_test.exs

@@ -51,21 +51,21 @@ defmodule Towerops.Recommendations.Rules.DeviceOverheatingTest do
     assert DeviceOverheating.evaluate(org.id) == []
   end
 
-  test "warning insight at 65–75°C", %{org: org, device: device, snmp: snmp} do
-    insert_temp(snmp, 68.0)
+  test "warning insight at 80–90°C", %{org: org, device: device, snmp: snmp} do
+    insert_temp(snmp, 85.0)
 
     assert [insight] = DeviceOverheating.evaluate(org.id)
     assert insight.type == "device_overheating"
     assert insight.urgency == "warning"
     assert insight.device_id == device.id
-    assert insight.metadata["temperature_c"] == 68.0
+    assert insight.metadata["temperature_c"] == 85.0
     assert insight.metadata["sensor_descr"] == "Enclosure"
     assert insight.title =~ "AP-Hot"
-    assert insight.title =~ "68"
+    assert insight.title =~ "85"
   end
 
-  test "critical insight at 75°C+", %{org: org, snmp: snmp} do
-    insert_temp(snmp, 78.0)
+  test "critical insight at 90°C+", %{org: org, snmp: snmp} do
+    insert_temp(snmp, 92.0)
 
     assert [insight] = DeviceOverheating.evaluate(org.id)
     assert insight.urgency == "critical"
@@ -81,17 +81,17 @@ defmodule Towerops.Recommendations.Rules.DeviceOverheatingTest do
   end
 
   test "uses the hottest sensor when multiple are present", %{org: org, snmp: snmp} do
-    insert_temp(snmp, 60.0, descr: "CPU")
-    insert_temp(snmp, 70.0, descr: "Enclosure")
+    insert_temp(snmp, 75.0, descr: "CPU")
+    insert_temp(snmp, 88.0, descr: "Enclosure")
 
     assert [insight] = DeviceOverheating.evaluate(org.id)
-    assert insight.metadata["temperature_c"] == 70.0
+    assert insight.metadata["temperature_c"] == 88.0
     assert insight.metadata["sensor_descr"] == "Enclosure"
   end
 
   test "correlates with Preseem QoE degradation when AP is linked",
        %{org: org, device: device, snmp: snmp} do
-    insert_temp(snmp, 72.0)
+    insert_temp(snmp, 85.0)
 
     {:ok, _ap} =
       %AccessPoint{}
@@ -112,7 +112,7 @@ defmodule Towerops.Recommendations.Rules.DeviceOverheatingTest do
   end
 
   test "scopes to organization", %{snmp: snmp} do
-    insert_temp(snmp, 78.0)
+    insert_temp(snmp, 85.0)
 
     other_user = user_fixture()
     other_org = organization_fixture(other_user.id)
@@ -120,7 +120,7 @@ defmodule Towerops.Recommendations.Rules.DeviceOverheatingTest do
   end
 
   test "ignores non-temperature sensors", %{org: org, snmp: snmp} do
-    insert_temp(snmp, 78.0, type: "voltage")
+    insert_temp(snmp, 85.0, type: "voltage")
     assert DeviceOverheating.evaluate(org.id) == []
   end
 end