Show each sensor's longest report gap; stop recording volatile attributes

Choosing room and weather freshness limits required knowing how long
each sensor normally goes without reporting, which HA does not show.
Add max_age_seconds_24h to every source in input_quality: the largest
report age seen at polls over the last 24 hours (hourly buckets, reset
on reload, underestimates by up to one poll interval).

input_quality and weather_comparison change every poll, so the Recorder
stored a new attribute row every five minutes. Mark them unrecorded;
they remain visible on the Status entity. Model coefficients and other
attributes are still recorded.

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

custom_components/heating_mpc/coordinator.py

@@ -19,7 +19,7 @@ from .const import (
     CONF_HORIZON, CONF_MIN_ON, CONF_MIN_OFF, CONF_SWITCH_COST, CONF_HEAT_COST,
     CONF_BAND, DEFAULTS,
 )
-from .data_quality import freshness
+from .data_quality import ReportAgeHistory, freshness
 from .physics import (
     LAG_LEARN_MAX_UNCERTAINTY, LAG_TAU_SECONDS, Learner, advance_lag,
     lag_from_time_in_state, optimize, relay_segments,
@@ -44,6 +44,7 @@ class HeatingMPCCoordinator(DataUpdateCoordinator[dict[str, Any]]):
         self.rooms: list[str] = self.config[CONF_ROOMS]
         self.learners: dict[str, Learner] = {room: Learner() for room in self.rooms}
         self._retired: dict[str, dict[str, Any]] = {}
+        self._report_ages = ReportAgeHistory()
         self._store = Store(hass, 1, f"{DOMAIN}.{entry.entry_id}")
         self._previous: dict[str, Any] | None = None
         # Radiator-lag proxy at the last poll with a valid relay state. Tracked
@@ -95,8 +96,12 @@ class HeatingMPCCoordinator(DataUpdateCoordinator[dict[str, Any]]):
         if state.state in ("unknown", "unavailable"):
             return {"status": state.state, "age_seconds": None}
         # last_updated is a conservative compatibility fallback for older HA.
-        return freshness(getattr(state, "last_reported", getattr(state, "last_updated", None)),
+        quality = freshness(getattr(state, "last_reported", getattr(state, "last_updated", None)),
                             now, limit * 60)
+        if quality["status"] in ("valid", "stale"):
+            quality["max_age_seconds_24h"] = round(
+                self._report_ages.observe(entity_id, now, quality["age_seconds"]), 1)
+        return quality
 
     @callback
     def async_relay_changed(self, event: Event) -> None:

custom_components/heating_mpc/data_quality.py

@@ -1,6 +1,7 @@
 """Pure timestamp validation for reported sensor snapshots."""
 from __future__ import annotations
 
+from collections import deque
 from datetime import datetime
 from math import isfinite
 
@@ -16,3 +17,23 @@ def freshness(reported: datetime | None, now: datetime, max_age_seconds: float)
         return {"status": "future_timestamp", "age_seconds": round(age, 1)}
     return {"status": "stale" if age > max_age_seconds else "valid",
             "age_seconds": round(age, 1)}
+
+
+class ReportAgeHistory:
+    """Largest report age seen at polls per entity over the last 24 hours.
+
+    Helps choose freshness limits: a limit below a sensor's normal maximum
+    marks it stale during ordinary operation. Hourly buckets keep memory bounded.
+    """
+
+    def __init__(self) -> None:
+        self._buckets: dict[str, deque[list[float]]] = {}
+
+    def observe(self, entity_id: str, now: datetime, age_seconds: float) -> float:
+        hour = now.timestamp() // 3600
+        buckets = self._buckets.setdefault(entity_id, deque(maxlen=25))
+        if buckets and buckets[-1][0] == hour:
+            buckets[-1][1] = max(buckets[-1][1], age_seconds)
+        else:
+            buckets.append([hour, age_seconds])
+        return max(age for start, age in buckets if hour - 24 < start <= hour)

custom_components/heating_mpc/sensor.py

@@ -19,6 +19,9 @@ class MPCStatus(CoordinatorEntity, SensorEntity):
     _attr_has_entity_name = True
     _attr_name = "Heating MPC Status"
     _attr_icon = "mdi:brain"
+    # Per-source report ages change every poll; recording them adds a new
+    # attribute row to the database every five minutes. Current values stay visible.
+    _unrecorded_attributes = frozenset({"input_quality", "weather_comparison"})
 
     def __init__(self, coordinator, entry_id):
         super().__init__(coordinator)

tests/ha/test_lifecycle.py

@@ -27,6 +27,11 @@ async def test_setup_reload_unload(hass, entry, inputs):
     assert len(entities) == 5
     ids = {e.unique_id: e.entity_id for e in entities}
     assert coordinator.data["status"] == "learning"
+    status = hass.states.get(ids[f"{entry.entry_id}_status"])
+    assert status.attributes["input_quality"]["rooms"]["sensor.room"]["max_age_seconds_24h"] == 0
+    # Volatile diagnostics stay visible but are not written to the Recorder.
+    assert {"input_quality", "weather_comparison"} <= status.state_info["unrecorded_attributes"]
+    assert "models" not in status.state_info["unrecorded_attributes"]
     proposal_id = registry.async_get_entity_id("binary_sensor", DOMAIN, f"{entry.entry_id}_proposal")
     assert hass.states.get(proposal_id).state == "unavailable"
     assert await hass.config_entries.async_reload(entry.entry_id)

tests/test_coordinator.py

@@ -524,3 +524,18 @@ class BoundaryTests(unittest.IsolatedAsyncioTestCase):
         self.c._store.async_load.return_value = {'retired_learners': retired}
         await self.c.async_restore_model()
         self.assertEqual(list(self.c._retired), [f'sensor.old{i}' for i in range(6, 30)])
+
+    async def test_report_gap_maximum_is_exposed_per_sensor(self):
+        await self.sample(2400)  # the room then stays silent for 40 minutes
+        self.states['sensor.outside'].last_reported = self.now
+        data = await self.sample()
+        room = data['input_quality']['rooms']['sensor.room']
+        self.assertEqual((room['status'], room['max_age_seconds_24h']), ('stale', 2400))
+        self.states['sensor.room'].last_reported = self.now
+        self.states['sensor.outside'].last_reported = self.now
+        data = await self.sample()
+        room = data['input_quality']['rooms']['sensor.room']
+        self.assertEqual((room['status'], room['age_seconds'], room['max_age_seconds_24h']),
+                         ('valid', 0, 2400))
+        weather = data['input_quality']['weather']['temperature']['sensor.outside']
+        self.assertEqual(weather['max_age_seconds_24h'], 0)  # kept reporting; tracked separately

tests/test_data_quality.py

@@ -31,6 +31,18 @@ class FreshnessTests(unittest.TestCase):
             with self.assertRaises(ValueError):
                 quality.freshness(now, now, limit)
 
+    def test_report_age_history_keeps_24_hour_maximum(self):
+        history = quality.ReportAgeHistory()
+        start = datetime(2026, 10, 26, tzinfo=timezone.utc)
+        self.assertEqual(history.observe('sensor.a', start, 2400), 2400)
+        self.assertEqual(history.observe('sensor.b', start, 60), 60)
+        for minutes in range(5, 24 * 60, 5):
+            result = history.observe('sensor.a', start + timedelta(minutes=minutes), 300)
+        self.assertEqual(result, 2400)  # still inside the 24-hour window
+        later = start + timedelta(hours=24, minutes=5)
+        self.assertEqual(history.observe('sensor.a', later, 300), 300)
+        self.assertEqual(history.observe('sensor.b', later, 30), 30)
+
     def test_freshness_settings_translated(self):
         for name in ('strings.json', 'translations/en.json', 'translations/ro.json'):
             data = json.loads((ROOT / name).read_text())