PRICE-02 round 2: require now, undo the test loosening, analyse ties
checks / unit (pull_request) Successful in 47m49s
infra-pin / fresh (pull_request) Successful in 2s

- TariffPlan.arbitrage(now=...) is required (keyword-only, no default); so are
  homeview.trade_verdict/refusal_key's now. Existing test calls pass one.
- test_arbitrage.py: no module-level decide wrapper. Fixtures that probed a
  one-day plan after its extremes now hold two days (as a site does); the
  flap day gets a unique cheapest and dearest hour; the replay breaks its
  ties without direction. The flap bound is <= 4 and the replay check is
  len(_trades) < 365 again. 228 checks pass on the old and the new code.
- test_price02.py part 6: ties (equal quarters, a real 15-minute day,
  alternating hourly prices) and the required now.
- Identity pins: the masked digest is only for the older-tree comparison;
  this tree's own digests are pinned with nothing hidden.
- DECISIONS: the tie analysis with numbers.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
glenn schrooyen
2026-10-22 10:37:43 +02:00
co-authored by Claude
parent 2ff9be710c
commit 891ed7bdd7
14 changed files with 362 additions and 134 deletions
+29 -24
View File
@@ -82,6 +82,11 @@ from app.validate import validate_startup_config
HERE = Path(__file__).resolve().parent
UTC = timezone.utc
# PRICE-02: `TariffPlan.arbitrage(now=...)` is required. This instant is before every
# point these fixtures build, so no period has ended and the whole series counts.
from datetime import datetime as _DT, timezone as _TZ # noqa: E402
LONG_AGO = _DT(2000, 1, 1, tzinfo=_TZ.utc)
fails = []
@@ -333,8 +338,8 @@ check(f"...while the two-period spread is the day/night difference "
f"{_spread_two}, re-derived here as {DAY_P - NIGHT_P:.4f}",
near(_spread_two, DAY_P - NIGHT_P, 1e-9))
_v_fixed = p_fixed.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset())
_v_two = p_two.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset())
_v_fixed = p_fixed.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset())
_v_two = p_two.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset())
check("a fully-fixed tariff REFUSES arbitrage", _v_fixed.kind == "refused")
check("...for the true reason - the series is flat, so there is nothing to buy "
"low and sell high, not because a FIXED enum was matched on",
@@ -354,7 +359,7 @@ _flat_dayahead = TariffPlan(
None, "provider")
check("a DAY_AHEAD series that happens to be flat is refused too, so the rule "
"is arithmetic and not a product label",
_flat_dayahead.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused")
_flat_dayahead.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused")
# The numbers an optimiser needs exist ONLY on the permitting variant.
check("the allowed verdict carries the spread, the cheapest hour and the "
@@ -379,16 +384,16 @@ check("...and there is no falsy variant, so `if verdict:` cannot look like a "
# §10.1 priority 2 over priority 3, expressed so OPT-04 cannot skip it.
check("peak shaving outranks arbitrage: the SAME allowed plan is refused when "
"the peak guard is holding",
p_two.arbitrage(peak_guard_active=True, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused")
p_two.arbitrage(now=LONG_AGO, peak_guard_active=True, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused")
check("...and the reason names the ordering rather than the tariff",
"priority 2" in p_two.arbitrage(peak_guard_active=True, min_spread_eur_kwh=0.0, uncertainty=frozenset()).reason)
"priority 2" in p_two.arbitrage(now=LONG_AGO, peak_guard_active=True, min_spread_eur_kwh=0.0, uncertainty=frozenset()).reason)
check("...and the question cannot be skipped: peak_guard_active is required "
"and keyword-only, so a spread is not obtainable without answering it",
raises(lambda: p_two.arbitrage(), TypeError)
and raises(lambda: p_two.arbitrage(False), TypeError))
check("...nor answered with a truthy 'unknown'",
raises(lambda: p_two.arbitrage(peak_guard_active=None), TypeError)
and raises(lambda: p_two.arbitrage(peak_guard_active="no"), TypeError))
raises(lambda: p_two.arbitrage(now=LONG_AGO, peak_guard_active=None), TypeError)
and raises(lambda: p_two.arbitrage(now=LONG_AGO, peak_guard_active="no"), TypeError))
# --------------------------------------------------------------------------- #
@@ -524,7 +529,7 @@ check("...and its underlying read has no .points at all, so `min(read.points)` "
"cannot run against it",
raises(lambda: _none.read.points, Absence))
check("...and arbitrage is refused, per §11.4",
_none.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused"
_none.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused"
and arbitrage_allowed(_none.read) is False)
check("...and static_status() says so in words rather than reporting a price",
static_status(opts(None), THU) == (False, "No fixed tariff set"))
@@ -776,12 +781,12 @@ check("...marked PROVISIONAL, which is the one flag that differs",
_fb.provisional and plan_is_provisional(_fb.read))
check("...and arbitrage is refused on it, per §11.4, even though a full series "
"exists and has a real spread",
_fb.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused"
_fb.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "refused"
and near(_fb.spread_eur_kwh(), DAY_P - NIGHT_P))
check("...while the SAME profile as the configured product allows it - so the "
"refusal is about provisionality and not about the profile",
static_plan(opts(TWO_PERIOD), THU, THU + timedelta(days=1)
).arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "allowed")
).arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "allowed")
check("...and the provisional plan has no cheap window either: §8.3 forbids an "
"irreversible action on a provisional price, and a grid top-up is one",
not any(_fb.cheap_now(at_local(THU, h)) for h in range(24)))
@@ -821,8 +826,8 @@ check("a live feed is used in preference to the static profile",
and _live_plan.product is PriceProduct.DAY_AHEAD)
check("...and arbitrage is allowed on it, with the spread derived from the "
"feed rather than from the profile",
_live_plan.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "allowed"
and near(_live_plan.arbitrage(peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).spread_eur_kwh,
_live_plan.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).kind == "allowed"
and near(_live_plan.arbitrage(now=LONG_AGO, peak_guard_active=False, min_spread_eur_kwh=0.0, uncertainty=frozenset()).spread_eur_kwh,
0.023, 1e-9))
@@ -1036,7 +1041,7 @@ check(f"each tiny-spread probe really carries the spread it is named for, and "
all(near(p.spread_eur_kwh(), d, 1e-12)
and len([q for q in p.read.points if not q.provisional]) == 2
for d, p in _tiny9))
_tinyv9 = [(d, rung9(p.arbitrage(**_A9))) for d, p in _tiny9]
_tinyv9 = [(d, rung9(p.arbitrage(now=LONG_AGO, **_A9))) for d, p in _tiny9]
check(f"TEST-16 AC1: a spread that is SMALL BUT REAL is ALLOWED at "
f"min_spread_eur_kwh=0.0 - down to 0.000001 EUR/kWh, so the flat rung is "
f"`spread == 0.0` and not `spread <= epsilon` for any epsilon "
@@ -1045,7 +1050,7 @@ check(f"TEST-16 AC1: a spread that is SMALL BUT REAL is ALLOWED at "
check("...and the exactly flat series on the OTHER side of that boundary is "
"still refused, and refused BY THE FLAT RUNG - without this the sweep "
"above would also pass for a rung that had been deleted outright",
rung9(plan9([0.20000, 0.20000]).arbitrage(**_A9)) == "flat")
rung9(plan9([0.20000, 0.20000]).arbitrage(now=LONG_AGO, **_A9)) == "flat")
_q9 = plan9([0.20000, 0.2000005])
check(f"...and a difference below the rung's own 6-decimal rounding is flat BY "
f"CONSTRUCTION and says so: the raw difference is "
@@ -1056,10 +1061,10 @@ check(f"...and a difference below the rung's own 6-decimal rounding is flat BY "
f"to bisect further",
not near(_q9.spread_eur_kwh(), 0.0, 1e-9)
and near(round(_q9.spread_eur_kwh(), 6), 0.0, 1e-12)
and rung9(_q9.arbitrage(**_A9)) == "flat")
and rung9(_q9.arbitrage(now=LONG_AGO, **_A9)) == "flat")
# --- and what D's survival actually costs: the sentence, not the verdict -----
_lie9 = plan9([0.20000, 0.20050]).arbitrage(**_A9)
_lie9 = plan9([0.20000, 0.20050]).arbitrage(now=LONG_AGO, **_A9)
check(f"TEST-16 AC4: the 0.0005 verdict carries the real spread rather than a "
f"flatness claim about a tariff that is not flat - the false sentence is "
f"what a loosened rung ships to the operator while the outcome at a "
@@ -1085,19 +1090,19 @@ check(f"the one-firm probe is well formed: exactly ONE firm hour out of three, "
check("TEST-16 AC2: one firm hour is refused BY §8.3's FIRM-PAIR RUNG, named "
"in the reason - not by the flat rung that would also have refused it. "
"This is what takes `len(firm) < 2` -> `< 1` red on its own",
rung9(_one9.arbitrage(**_A9)) == "firm-pair")
rung9(_one9.arbitrage(now=LONG_AGO, **_A9)) == "firm-pair")
check("...and the sentence is §8.3's in full, so the operator is told the "
"series is half-published rather than told it is fixed-price",
"§8.3" in _one9.arbitrage(**_A9).reason
and "only 1 of 3" in _one9.arbitrage(**_A9).reason
and "flat" not in _one9.arbitrage(**_A9).reason)
"§8.3" in _one9.arbitrage(now=LONG_AGO, **_A9).reason
and "only 1 of 3" in _one9.arbitrage(now=LONG_AGO, **_A9).reason
and "flat" not in _one9.arbitrage(now=LONG_AGO, **_A9).reason)
# The rung pinned from ABOVE as well. Without this, `len(firm) < 3` - the same
# +0 B edit in the other direction - would pass everything above.
_two9 = plan9([0.20, 0.40, 0.10], [False, False, True])
check("...and TWO firm hours are ALLOWED on the identical series shape, so the "
"rung is pinned from above too and `< 3` is red as well as `< 1`",
rung9(_two9.arbitrage(**_A9)) == "allowed"
and near(_two9.arbitrage(**_A9).spread_eur_kwh, 0.20))
rung9(_two9.arbitrage(now=LONG_AGO, **_A9)) == "allowed"
and near(_two9.arbitrage(now=LONG_AGO, **_A9).spread_eur_kwh, 0.20))
# ...and from below, where the failure is not a wrong sentence but a crash:
# `max()` over an empty `firm` raises ValueError, so `< 0` does not degrade the
# reason, it takes the verdict away entirely.
@@ -1105,7 +1110,7 @@ _zero9 = plan9([0.20, 0.40, 0.10], [True, True, True])
check("...and a FULLY provisional series is refused by the same rung and does "
"not raise - `max()` over an empty firm set is a ValueError, so this row "
"is what makes `len(firm) < 0` red",
rung9(derived(lambda: _zero9.arbitrage(**_A9))) == "firm-pair")
rung9(derived(lambda: _zero9.arbitrage(now=LONG_AGO, **_A9))) == "firm-pair")
# --- AC3: the two rungs do not mask each other ------------------------------
# ⚠️ THE POINT OF THE TICKET, AND IT IS A PROPERTY OF THE TABLE, NOT OF A ROW.
@@ -1130,7 +1135,7 @@ _TABLE9 = (
("two firm hours of three", _two9, "allowed"),
("no firm hours at all", _zero9, "firm-pair"),
)
_got9 = [(name, want, rung9(derived(lambda p=pl: p.arbitrage(**_A9))))
_got9 = [(name, want, rung9(derived(lambda p=pl: p.arbitrage(now=LONG_AGO, **_A9))))
for name, pl, want in _TABLE9]
check(f"TEST-16 AC3: each stimulus is answered by the rung that OWNS it, and "
f"by no other - the flat rung is asked a question the firm-pair rung "