MAINT-13: a full pack that stops at 98-99 % is not a failed charge

A charge is complete at SoC >= target, or at >= target - 3 once the SoC has
made no new high for 60 min of allowed charging, or when the charging time
runs out at >= target - 3. The 36 h timeout counts only the minutes the price
gate let the pack charge (plus a 7 day wall-clock backstop). A cycle that
fails (stuck drain, charge below target - 3) backs off 7 days, tells the
operator once (EN + NL), and no cycle starts on that pack in that time unless
the operator forces one. State survives a restart; old state files load.

No option added. DECISIONS/MAINT-13-full-pack-is-complete.md.

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

goodwe_controller/app/main.py

@@ -77,7 +77,7 @@ from .inverter import (LINK_STALE_S, UNIT_A, build_roster,
                        roster_entries, roster_names)
 from .maintenance import (
     CHARGE, DRAIN, HOLD, IDLE, POWER_MOVING, MaintConfig, Maintenance,
-    MaintResult, arbitrate as maint_arbitrate, site_zone,
+    FAIL_BACKOFF_DAYS, MaintResult, arbitrate as maint_arbitrate, site_zone,
 )
 from .mqtt import (MODE_CONFIGS_KEY, MODE_LABELS, USE_OFF, USE_ON,
                    MqttPublisher, announced_units, mode_configs,
@@ -3923,10 +3923,24 @@ class Controller:
             if blocked is None:
                 maint_results.append(MaintResult(IDLE, False, None, False, []))
                 continue
-            res = machine.tick(now, inv.soc, blocked_by=blocked)
+            # MAINT-13: the charge timeout counts only the minutes the price
+            # gate (`self.cheap`) let the pack charge.
+            res = machine.tick(now, inv.soc, blocked_by=blocked,
+                               gate_open=bool(self.cheap))
             for msg in res.events:
-                self.log_event(msg, hint=messages.hint("maintenance",
-                                                       phase=machine.phase))
+                self.log_event(msg, hint=messages.hint(
+                    "maint_failed" if res.failed else "maintenance",
+                    phase=machine.phase))
+            if res.failed:
+                # Said once: only the tick that failed carries `res.failed`.
+                multi = len(self.inverters) > 1
+                slug = (unit_slugs(self.units)[self.inverters.index(inv)]
+                        if multi else "battery")
+                await self.hass.call(
+                    "persistent_notification", "create",
+                    messages.maint_failed(
+                        res.failed, FAIL_BACKOFF_DAYS,
+                        unit=inv.name if multi else "", slug=slug).data())
             maint_results.append(res)
         # ⚠️ CARRIED TO THE STATUS PAGE, NOT LEFT IN THE 40-LINE ACTION LOG. The
         # deferral is edge-logged (it lasts as long as the other pack's cycle),
@@ -7100,6 +7114,7 @@ class Controller:
         # date, unchanged.
         _now = datetime.now(timezone.utc)
         _dues = [m.next_due(_now) for m in self.maints]
+        _waits = [u for u in (m.backoff_until(_now) for m in self.maints) if u]
         next_due = None if any(d is None for d in _dues) else min(_dues)
         rows = [
             ("Grid", w(self.grid)),
@@ -7147,6 +7162,10 @@ class Controller:
             *((("Maintenance waiting", "; ".join(f"{n}: {why}"
                                                  for n, why in self._maint_deferred)),)
               if self._maint_deferred else ()),
+            # MAINT-13: only while a failed cycle waits, so a site with nothing
+            # failed carries exactly the rows it carried before.
+            *((("Maintenance paused", messages.row_maint_waits(
+                min(_waits).strftime("%Y-%m-%d"))),) if _waits else ()),
             ("Maintenance due", "now" if next_due is None else next_due.strftime("%Y-%m-%d")),
             ("Cheap window", "yes" if self.cheap else "no"),
             ("Tariff", self.tariff_words),

goodwe_controller/app/maintenance.py

@@ -65,10 +65,26 @@ POWER_MOVING = (DRAIN, CHARGE, HOLD)
 # 12 h means the battery is not following commands - a fault, not a slow day. The charge phase deliberately waits for sun and for cheap hours, so
 # it is expected to span a night; 36 h still bounds it.
 DRAIN_TIMEOUT_MIN = 720
+# MAINT-13: minutes the pack was ALLOWED to charge (the price gate open), not
+# wall-clock minutes since the charge began. See CHARGE_WALL_TIMEOUT_MIN.
 CHARGE_TIMEOUT_MIN = 2160
 # After an abort, do not immediately re-trigger in the same start hour.
 RESTART_COOLDOWN_MIN = 90
 
+# MAINT-13 (DECISIONS/MAINT-13-full-pack-is-complete.md). Constants, not options.
+# A pack that reaches target - 3 and then takes no more charge for this many
+# minutes of allowed charging counts as full.
+CHARGE_NEAR_FULL_PCT = 3
+CHARGE_STALL_MIN = 60
+# Wall-clock backstop for a charge whose gate never opens (no cheap hours, no sun).
+CHARGE_WALL_TIMEOUT_MIN = 10080
+# A failed cycle (stuck drain or charge) is not retried before this many days.
+FAIL_BACKOFF_DAYS = 7
+# One tick counts at most this many minutes: a gap means the add-on was down.
+CHARGE_TICK_MAX_MIN = 5
+# The charge accounting is written to the state file at most this often.
+CHARGE_SAVE_MIN = 5
+
 # ⚠️ CFG-03. THE ONE IN-CODE MIRROR OF config.yaml FOR EVERY `maintenance_*`
 # OPTION, and the only place in the add-on where one of these numbers is typed.
 #
@@ -257,6 +273,9 @@ class MaintResult:
     # showing an idle machine and a due date in the past. Empty on every path
     # that is not deferring, so a roster of one never sees it.
     deferred: str = ""
+    # MAINT-13: "drain" or "charge" on the one tick where a cycle FAILED, so
+    # the Controller can tell the operator once. Empty on every other tick.
+    failed: str = ""
 
 
 class UnitHistory:
@@ -344,6 +363,10 @@ class Maintenance:
         # per cycle would flush the very context that explains it. Same pattern
         # as `Controller._arb_action` and `_maint_shape_suspended`.
         self._deferred = ""
+        # MAINT-13: the charge accounting (see _charge_account), in memory and
+        # written to the state file every CHARGE_SAVE_MIN minutes.
+        self._trk = None
+        self._trk_saved = None
 
     # -- state ---------------------------------------------------------------
     @property
@@ -351,6 +374,9 @@ class Maintenance:
         return self.store.get("phase", IDLE)
 
     def _enter(self, phase: str, now: datetime, events: list, msg: str) -> None:
+        self._trk = None
+        if self.store.get("charge_track") is not None:
+            self.store.set("charge_track", None)
         self.store.set("phase", phase)
         self.store.set_time("phase_started", now)
         _LOG.info("%s", msg)
@@ -391,6 +417,21 @@ class Maintenance:
         return (last_try is None
                 or (now - last_try) >= timedelta(minutes=RESTART_COOLDOWN_MIN))
 
+    def backoff_until(self, now: datetime):
+        """MAINT-13: when a failed cycle may be tried again, or None.
+
+        None when nothing failed, when the back-off is over, or when a cycle
+        completed after the failure (a forced start that worked ends it).
+        """
+        failed = self.store.get_time("last_failed")
+        if failed is None:
+            return None
+        done = self.store.get_time("last_completed")
+        if done is not None and done >= failed:
+            return None
+        until = failed + timedelta(days=FAIL_BACKOFF_DAYS)
+        return until if now < until else None
+
     def wants_start(self, now: datetime) -> bool:
         """Would this pack begin a cycle on this tick if the site let it?
 
@@ -402,7 +443,8 @@ class Maintenance:
         return (self.phase == IDLE and self.cfg.enabled
                 and in_start_slot(now, self.cfg.start_hour, self.tz)
                 and self.due(now)
-                and self._cooled(now))
+                and self._cooled(now)
+                and self.backoff_until(now) is None)
 
     # -- operations ----------------------------------------------------------
     def force_start(self, now: datetime, blocked_by: str = "") -> list:
@@ -430,6 +472,55 @@ class Maintenance:
         self._enter(DRAIN, now, events, "maintenance: forced start -> drain")
         return events
 
+    def _charge_account(self, now: datetime, soc: float, gate_open: bool) -> dict:
+        """MAINT-13: what this charge has used so far, as minutes of ALLOWED time.
+
+        `open_min` counts only ticks with the price gate open; `flat_min` counts
+        gate-open minutes since the SoC last beat its best; a closed gate pauses
+        both. One tick adds at most CHARGE_TICK_MAX_MIN, so a gap (add-on down)
+        counts for nothing. A state file from before MAINT-13, or from another
+        charge, starts from the wall-clock minutes so far: the old behaviour.
+        """
+        since = self.store.get("phase_started")
+        trk = self._trk
+        if trk is None:
+            raw = self.store.get("charge_track")
+            if isinstance(raw, dict) and raw.get("since") == since:
+                trk = dict(raw)
+            else:
+                trk = {"since": since, "open_min": self._elapsed_min(now),
+                       "flat_min": 0.0, "best": float(soc), "at": None}
+            self._trk = trk
+        at = trk.get("at")
+        try:
+            last = datetime.fromisoformat(at) if at else None
+        except (TypeError, ValueError):
+            last = None
+        dt = 0.0 if last is None else min(
+            CHARGE_TICK_MAX_MIN, max(0.0, (now - last).total_seconds() / 60.0))
+        trk["at"] = now.isoformat()
+        if soc > trk["best"]:
+            trk["best"], trk["flat_min"] = float(soc), 0.0
+        elif gate_open:
+            trk["flat_min"] += dt
+        if gate_open:
+            trk["open_min"] += dt
+        saved = self._trk_saved
+        if saved is None or (now - saved).total_seconds() >= CHARGE_SAVE_MIN * 60:
+            self.store.set("charge_track", dict(trk))
+            self._trk_saved = now
+        return trk
+
+    def _fail(self, now: datetime, kind: str, why: str) -> MaintResult:
+        """MAINT-13: stand down, remember the failure, and tell the Controller."""
+        events = self.abort(now, why)
+        self.store.set_time("last_failed", now)
+        msg = (f"maintenance: the cycle did not finish. It waits "
+               f"{FAIL_BACKOFF_DAYS} days before it tries again.")
+        _LOG.warning("%s", msg)
+        events.append(msg)
+        return MaintResult(IDLE, True, 0.0, False, events, failed=kind)
+
     def abort(self, now: datetime, why: str) -> list:
         events = []
         self._enter(IDLE, now, events, f"maintenance: ABORT ({why})")
@@ -457,13 +548,16 @@ class Maintenance:
 
     # -- the machine ---------------------------------------------------------
     def tick(self, now: datetime, soc: float | None,
-             blocked_by: str = "") -> MaintResult:
+             blocked_by: str = "", gate_open: bool = True) -> MaintResult:
         """One cycle of this pack's state machine.
 
         `blocked_by` is `arbitrate()`'s answer for THIS pack: empty when the
         site's one maintenance slot is available to it, otherwise the reason it
         is not. It gates two things and nothing else - a start, and a phase that
         is already moving power on a pack that does not hold the slot.
+
+        `gate_open` (MAINT-13) is whether the pack may charge now (the price
+        gate); only those minutes count towards the charge timeout.
         """
         events: list = []
         phase = self.phase
@@ -531,8 +625,8 @@ class Maintenance:
                             f"after {elapsed:.0f} min -> charge")
                 return MaintResult(CHARGE, False, None, True, events)
             if elapsed > DRAIN_TIMEOUT_MIN:
-                events += self.abort(now, f"drain stuck at {soc:.0f} % after {elapsed:.0f} min")
-                return MaintResult(IDLE, True, 0.0, False, events)
+                return self._fail(now, "drain", f"drain stuck at {soc:.0f} % "
+                                                f"after {elapsed:.0f} min")
             return MaintResult(DRAIN, True, self.cfg.discharge_w, False, events)
 
         if phase == CHARGE:
@@ -541,9 +635,27 @@ class Maintenance:
                             f"maintenance: charge complete at {soc:.0f} % after "
                             f"{elapsed:.0f} min -> holding {self.cfg.hold_min} min to balance")
                 return MaintResult(HOLD, True, 0.0, False, events)
-            if elapsed > CHARGE_TIMEOUT_MIN:
-                events += self.abort(now, f"charge stuck at {soc:.0f} % after {elapsed:.0f} min")
-                return MaintResult(IDLE, True, 0.0, False, events)
+            trk = self._charge_account(now, soc, gate_open)
+            near = soc >= self.cfg.soc_target - CHARGE_NEAR_FULL_PCT
+            # MAINT-13 rule 1: close to full and no longer taking charge.
+            if near and trk["flat_min"] >= CHARGE_STALL_MIN:
+                self._enter(HOLD, now, events,
+                            f"maintenance: the battery takes no more charge at "
+                            f"{soc:.0f} %, so the charge counts as done -> holding "
+                            f"{self.cfg.hold_min} min to balance")
+                return MaintResult(HOLD, True, 0.0, False, events)
+            if (trk["open_min"] > CHARGE_TIMEOUT_MIN
+                    or elapsed > CHARGE_WALL_TIMEOUT_MIN):
+                # MAINT-13 rule 2: out of time close to full is complete.
+                if near:
+                    self._enter(HOLD, now, events,
+                                f"maintenance: charge time is up at {soc:.0f} %, "
+                                f"close enough to full, so the charge counts as "
+                                f"done -> holding {self.cfg.hold_min} min to balance")
+                    return MaintResult(HOLD, True, 0.0, False, events)
+                return self._fail(now, "charge",
+                                  f"charge stuck at {soc:.0f} % after "
+                                  f"{trk['open_min']:.0f} min of charging time")
             return MaintResult(CHARGE, False, None, True, events)
 
         if phase == HOLD:

goodwe_controller/app/messages.py

@@ -102,6 +102,7 @@ class Notice:
     title: str
     body: str
     section: str = ""   # the DOCS.md heading, when it is not the title itself
+    body_nl: str = ""   # MAINT-13: the same words in Dutch, shown under the English
 
     @property
     def docs(self) -> str:
@@ -110,7 +111,9 @@ class Notice:
     def data(self) -> dict:
         """The `persistent_notification.create` payload."""
         return {"notification_id": self.id, "title": self.title,
-                "message": f"{self.body}\n\n{details(self.docs)}"}
+                "message": f"{self.body}\n\n"
+                           + (f"{self.body_nl}\n\n" if self.body_nl else "")
+                           + details(self.docs)}
 
 
 # --- the catalogue ----------------------------------------------------------
@@ -124,6 +127,8 @@ T_CIRCULATING = "Inverters working against each other"
 T_NOT_DELIVERING = "{unit} is not delivering"
 S_NOT_DELIVERING = "An inverter is not delivering"
 T_METER_FROZEN = "Meter reading may be stuck"
+T_MAINT_FAILED = "Battery cycle did not finish"
+T_MAINT_FAILED_NL = "Batterijcyclus niet afgerond"
 
 ID_LOOP_BOUND = "goodwe_integrator_bound"
 ID_OUTPUT_CLAMP = "goodwe_output_clamp"
@@ -132,6 +137,7 @@ ID_PEAK_RESERVE = "goodwe_peak_soc_floor"
 ID_CIRCULATING = "goodwe_circulating_power"
 ID_NOT_DELIVERING = "goodwe_not_delivering_{slug}"
 ID_METER_FROZEN = "goodwe_meter_frozen"
+ID_MAINT_FAILED = "goodwe_maint_failed_{slug}"
 
 # Which limit cut a command (clamp.ClampResult.bound, plus the loop's own).
 # The setting is named by its label, "Inverter rating (W)".
@@ -295,6 +301,24 @@ def meter_frozen(unchanged_s) -> Notice:
                   f"stop control on the add-on page.")
 
 
+def maint_failed(kind: str, days: int, unit: str = "", slug: str = "") -> Notice:
+    """MAINT-13: a monthly cycle stopped before it was done. Said once."""
+    full = kind == "charge"
+    who = unit or "The battery"
+    who_nl = unit or "De batterij"
+    en = f"{who} did not {'fill up' if full else 'empty'}, so its cycle " \
+         f"stopped and tries again in {days} days."
+    nl = f"{who_nl} raakte niet {'vol' if full else 'leeg'}, dus de cyclus is " \
+         f"gestopt en probeert het over {days} dagen opnieuw."
+    return Notice(ID_MAINT_FAILED.format(slug=slug or "battery"), WARNING,
+                  T_MAINT_FAILED, en, body_nl=f"{T_MAINT_FAILED_NL}. {nl}")
+
+
+def row_maint_waits(until_text: str) -> str:
+    """MAINT-13: the status row while a failed cycle waits."""
+    return f"Waits until {until_text} after a cycle that did not finish."
+
+
 # --- the status page (UX-08 phase 2b) ----------------------------------------
 # The rows of the Commissioning list and the banner at the top of the add-on
 # page. `main.py` decides WHEN a row shows and its colour (ok / warn / bad);
@@ -947,6 +971,7 @@ HINTS = {
     "not_delivering_cleared": "{unit}: not-delivering alarm cleared",
     "maintenance": "Battery maintenance: {phase}",
     "maint_paused": "Maintenance charging paused to stay under the peak limit",
+    "maint_failed": "The battery cycle did not finish, so it waits before trying again",
     "pack_on": "{unit}: battery switched on",
     "pack_off": "{unit}: battery switched off, it is asked for 0 W",
     "pack_mode": "{unit}: battery mode changed",
@@ -1118,6 +1143,7 @@ def status_samples() -> list:
         ("row_battery_refuses", AMBER, row_battery_refuses("inverter-b", 1,
                                                            True)),
         ("row_circulating_check", GREEN, row_circulating_check(0, 0, 60)),
+        ("row_maint_waits", AMBER, row_maint_waits("2026-10-13")),
     ]
 
 
@@ -1148,6 +1174,8 @@ def samples() -> list:
         not_delivering("inverter-b", "inverter_b"),
         meter_frozen(600),
         meter_frozen(90),
+        maint_failed("charge", 7),
+        maint_failed("drain", 7, "inverter-b", "inverter_b"),
     ]
 
 

goodwe_controller/app/store.py

@@ -94,6 +94,7 @@ DEFAULTS = {
     "phase_started": None,
     "last_completed": None,
     "last_start_attempt": None,
+    "last_failed": None,
     "sign_tripped": False,
     "sign_reason": "",
     "circ_tripped": False,
@@ -171,7 +172,7 @@ MAINT_SCHEMA_KEY = "maint_schema_version"
 # silently stop being migrated - the same property `UNIT_STORE_KEYS` gives the
 # SAFETY-02 pair.
 MAINT_UNIT_KEYS = ("phase", "phase_started", "last_completed",
-                   "last_start_attempt")
+                   "last_start_attempt", "last_failed")
 
 
 def unit_key(unit: str, key: str) -> str: