SAFETY-52: a battery that refuses is asked for 0 W, with a 200 W probe every 15 min
checks / unit (pull_request) Failing after 9m32s
infra-pin / fresh (pull_request) Successful in 1s

At the BMS cut-out the saturation freeze held the last request for hours
(+5000 W for 11.87 h on 09-06, +1940 W for 3 h 55 m on 09-19) until the grid
error changed sign. compute() now carries a refused direction: after
SETTLE_CYCLES of a ~0 W reading against a larger ask it holds that direction
at 0 W, probes 200 W (below the gate's 250 W) every 15 minutes, and lets go
on charge, an answered probe, stop/start or another writer. A stale-reading
trip on a frozen ~0 W reading seeds the same hold, which ends SAFETY-59's
~70 s cycle. One inverter only; no SoC in the loop (SAFETY-25 Option A).

test_refusal.py drives the real Controller and gate; tools/replay_refusal.py
replays the 16-day capture. test_clamp.py and test_delivery.py re-baselined
where they asserted the old hold. DECISIONS/SAFETY-52 has the record and what
SAFETY-58/59 must take into account.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
glenn schrooyen
2026-09-27 16:43:27 +02:00
co-authored by Claude Opus 5.5
parent d1f7e3336e
commit 1f97c7652f
10 changed files with 756 additions and 6 deletions
+93
View File
@@ -39,6 +39,7 @@ from .arbiter import (
P_LOOP, P_MAINT_SHAPE, P_MAINTENANCE, P_PEAK, P_SAFETY,
Claim, Resolution, actuator_for, resolve,
)
from . import control as _ctl
from .control import Tuning, compute, maintenance_charge_floor, peak_at_risk
from .delivery import (
DELIVERY_OPTION_DEFAULTS, DeliveryConfig, UnitDelivery,
@@ -241,6 +242,10 @@ def why_key(winner: str, claims) -> str:
disagreement"). A failsafe with no claim of its own is the arbiter's "no
claim was made", or main.py's refusal to split the power ("unsplit").
"""
if winner == "loop":
# SAFETY-52: a loop holding a refused direction says so.
return next((c.reason for c in claims if c.source == "loop"
and c.reason in (_ctl.REFUSED, _ctl.PROBING)), winner)
if winner in ("safety", "failsafe"):
return next((c.reason for c in claims
if c.source == winner and c.kind == "set"),
@@ -925,6 +930,12 @@ class Controller:
self.target = 0.0
self.sat_count = 0
self.i_w = 0.0 # the loop's integrator, carried between cycles
# SAFETY-52. The direction the battery refuses (+1 / -1 / 0), carried
# like `i_w`, and when the refusal (or its last probe) started.
self.batt_refused = 0
self.batt_refused_at = None
self._now_mono = None
self._refusal_auto = False
# TEL-10. What the last cycle's loop did, kept for publication. Seeded
# to the SAME values the "stopped or blind" branch of `cycle()` writes,
# because before the first cycle the loop has not run - which is the
@@ -1058,6 +1069,68 @@ class Controller:
self.loop_pass_mono = None
# -- helpers -------------------------------------------------------------
# --- SAFETY-52: a battery that refuses is asked for 0 W ------------------
def _refusal_probe(self) -> bool:
"""True while a refused direction may try `PROBE_W` (every 15 min)."""
if (not self.batt_refused or self.batt_refused_at is None
or self._now_mono is None):
return False
held = self._now_mono - self.batt_refused_at
if held >= _ctl.PROBE_EVERY_S + _ctl.PROBE_S:
self.batt_refused_at = self._now_mono
return False
return held >= _ctl.PROBE_EVERY_S
def _refusal_start(self, sign: int, evidence: str) -> None:
self.batt_refused = sign
self.batt_refused_at = self._now_mono
self.log_event(f"BATTERY REFUSES {evidence}",
hint=messages.hint("battery_refuses"))
_LOG.info("The battery refuses to give power, so the add-on asks 0 W "
"and tries %.0f W every %.0f minutes: BATTERY_REFUSES.",
_ctl.PROBE_W, _ctl.PROBE_EVERY_S / 60)
_LOG.debug("Evidence: BATTERY_REFUSES: %s.", evidence)
def _refusal_end(self, why: str) -> None:
if not self.batt_refused:
return
self.batt_refused, self.batt_refused_at = 0, None
self.log_event(f"BATTERY REFUSES ENDED: {why}",
hint=messages.hint("battery_gives"))
_LOG.info("The battery refusal ends, control asks for power again: %s.",
why)
def _refusal_update(self, decision, asked_w, batt_w, probe) -> None:
"""Follow `compute()`'s carried refused direction, and say so."""
now = decision.refused or 0
if now and not self.batt_refused:
self._refusal_start(now, f"asked {asked_w:+.0f} W, the battery "
f"gave {batt_w:+.0f} W for "
f"{decision.sat_count} cycles")
elif self.batt_refused and not now:
answered = probe and self.batt_refused * batt_w >= _ctl.PROBE_ANSWER_W
self._refusal_end("the probe was answered" if answered
else "the grid now asks the other direction")
def _refusal_from_stale(self, inv, now_mono) -> None:
"""A stale-reading stop while the loop is frozen on ~0 W is a refusal.
Only at one inverter: with several, one empty battery must not stop the
site (OPT-09's pack limit moves its share to the others).
"""
t = self.tuning
standing = inv.standing_w()
if (len(self.inverters) == 1 and (self.auto or self.shadow)
and not self.batt_refused
and self.sat_count >= t.saturation_cycles
and inv.batt_fresh.held is not None
and abs(inv.batt_fresh.held) < t.saturation_w
and abs(standing) > t.saturation_w):
self._now_mono = now_mono
self._refusal_start(1 if standing > 0 else -1,
f"stale reading {inv.batt_fresh.held:+.0f} W "
f"while asked {standing:+.0f} W")
def log_event(self, msg: str, hint: str | None = None) -> None:
"""`msg` goes on the action log, the add-on's own technical record.
`hint` is `messages.hint()`'s plain words for the same event, and is
@@ -1840,6 +1913,7 @@ class Controller:
"""
o = self.o
now_mono = freshness.monotonic() if now_mono is None else float(now_mono)
self._now_mono = now_mono
if self.p1_enabled:
# ⚠️ P1 is the only authoritative measurement of what the utility
# sees (§5.1). When it is stale this is None, which falls into the
@@ -2003,6 +2077,7 @@ class Controller:
if inv.batt_fresh.stale and not was_stale:
self.log_event(f"STALE {inv.name}: " + inv.batt_fresh.reason,
hint=messages.hint("battery_stuck", unit=inv.name))
self._refusal_from_stale(inv, now_mono)
# ⚠️ SAFETY-57 REWROTE THE LAST SENTENCE OF THIS LINE AND NOTHING
# ELSE IN IT. The escape clause used to read "It clears itself the
# moment the register reports a different value", full stop - and
@@ -3340,6 +3415,12 @@ class Controller:
# loop should be. It is safe because the loop's `prev_w` is
# `self.target`, which the end of this method re-seeds to what is
# actually standing on the wire.
# SAFETY-52: a refusal learned while control ran does not survive a
# stop or a start (shadow mode keeps the loop running when stopped).
if bool(self.auto) != self._refusal_auto:
self._refusal_auto = bool(self.auto)
self._refusal_end("control started" if self.auto
else "control stopped")
if (self.auto or self.shadow) and self.inputs_ok:
# ⚠️ prev is the ARBITER's last output, not the loop's own last
# wish. If something outranked the loop, that is what the hardware
@@ -3357,6 +3438,13 @@ class Controller:
# stale period as power.
if self.loop_w is None or self.target != self.loop_w:
self.i_w = self.target
# SAFETY-52: another writer overrode the loop, so a refusal learned
# against the loop's own ask no longer describes the wire. A gap
# (`loop_w` None: blind or stopped) keeps it: the stale-reading stop
# is what seeds it, and dropping it there restarts the ~70 s cycle.
if self.loop_w is not None and self.target != self.loop_w:
self._refusal_end("another writer")
probe = self._refusal_probe()
# ⚠️ `actual_w` IS THE SITE SUM AND THAT IS DEV-02's OTHER HALF.
# The anti-windup test inside compute() is
# `abs(prev_w - actual_w) > saturation_w`, and `prev_w` is the SITE
@@ -3385,6 +3473,10 @@ class Controller:
tuning=self.tuning,
sat_count=self.sat_count,
i_w=self.i_w,
# SAFETY-52 at one inverter only: with several, OPT-09's pack
# limit already closes an empty battery's discharge end.
refused=self.batt_refused if len(self.inverters) == 1 else None,
probe=probe,
)
if decision.frozen and self.sat_count < self.tuning.saturation_cycles:
self.log_event(f"saturation freeze ({self.target:.0f} W vs "
@@ -3393,6 +3485,7 @@ class Controller:
self.sat_count = decision.sat_count
self.i_w = decision.i_w
self.loop_w = decision.target_w
self._refusal_update(decision, loop_prev, site_batt, probe)
# --- TEL-10 ------------------------------------------------------
# ⚠️ THE INTEGRATOR HAS NEVER LEFT THIS PROCESS, AND THAT IS WHAT
# THE CARD IS. `self.i_w` is carried between cycles and published