CI-02 probe F: the ORIGINAL gate, unchanged, on the same unmergeable PR

goodwe_controller/test_tariff.py

@@ -85,6 +85,13 @@ regression fixture that CI cannot see is not a regression fixture.
 
 The recorder's window rolls: 2026-08-01 leaves it around 2026-09-15, which is
 why the committed copy is the artefact and not the API call.
+
+⚠️ MUTATING THE MODULE THIS FILE GRADES? PURGE `__pycache__` FIRST - or run
+`tools/mutation_run.sh`, which does. `python3 -B` alone does NOT save you: it
+stops bytecode being WRITTEN, not a stale one being READ, and a size-preserving
+edit reverted inside one second is invisible to CPython's staleness test. That
+is TEST-15, and it has already turned one live mutation into a false survivor.
+Read MUTATION.md before you report a survivor.
 """
 
 import asyncio
@@ -863,7 +870,12 @@ check("...and syncing the same quarter again banks nothing new, so the count "
 check("...and the peak is unchanged by the repeat",
       near(c.peak.peak(B).peak_w, 4998.0, 1e-6))
 
-rows = [r for r in c.checks() if "capacity-tariff" in r["text"] or "peak" in r["text"]]
+# ⚠️ `when=B`, AND THAT ARGUMENT IS THE TICKET (TEST-17). Without it `checks()`
+# reads the peak for `datetime.now()`'s month while this fixture banked its
+# quarter in August, so every check below passed in August and failed from
+# 2026-09-01 - on a commit nobody had touched. The suite must grade the month
+# it created, not the month the machine happens to be running in.
+rows = [r for r in c.checks(when=B) if "capacity-tariff" in r["text"] or "peak" in r["text"]]
 peak_rows = [r for r in rows if "peak" in r["text"] and "quarter(s) banked" in r["text"]]
 print("    status row: " + (peak_rows[0]["text"] if peak_rows else "(none)"))
 check("the status page carries exactly one capacity-tariff peak row",
@@ -879,7 +891,7 @@ check("...and it is FLAGGED, because 4998 W is over §9.1's 80 % warning point "
 
 # The half that matters: the same page with a store that cannot answer.
 c2 = built(TMP / "no-such-dir" / "nope.db")
-u_rows = [r for r in c2.checks() if "capacity-tariff peak" in r["text"]]
+u_rows = [r for r in c2.checks(when=B) if "capacity-tariff peak" in r["text"]]
 print("    status row (unreadable store): "
       + (u_rows[0]["text"] if u_rows else "(none)"))
 check("an unreadable store gets its OWN row, saying UNREADABLE", len(u_rows) == 1)
@@ -891,6 +903,58 @@ check("...and the healthy row and the unreadable row are different text",
       bool(u_rows) and bool(peak_rows)
       and u_rows[0]["text"] != peak_rows[0]["text"])
 
+# --- TEST-17: the page must be graded at a stated time, and prove it ----------
+# Three ways this can regress, so three checks. The first two would both go
+# green again if `checks()` quietly went back to reading the clock, which is
+# exactly the mutation this section could not previously detect.
+
+# ⚠️ SELECTED ON "quarter(s) banked", NOT ON "peak". The NO_RECORD row reads
+# "2026-10: no completed quarter recorded yet - ..." and contains neither the
+# word "peak" nor "capacity-tariff" - only the UNREADABLE branch prefixes the
+# family name. Filtering these rows the way the checks above do would drop the
+# row and then grade its absence, which is the very mistake this ticket fixes.
+# (That asymmetry in the row's own text is worth a look on its own; it is what
+# made the original filter brittle. Not changed here - it is product text with
+# other suites reading it.)
+_peak_rows = lambda rows: [r for r in rows if "quarter(s) banked" in r["text"]]
+
+_later = B + timedelta(days=45)          # same fixture, a later billing month
+_other_peak = _peak_rows(c.checks(when=_later))
+print(f"    the SAME controller read at {_later.date()}: "
+      + (_other_peak[0]["text"] if _other_peak else "(no peak row)"))
+check("asked for a LATER month, the same controller reports that month's "
+      "absence of a quarter, not August's 4998 W - the row follows `when`",
+      bool(_other_peak) and "4998 W" not in _other_peak[0]["text"]
+      and "no completed quarter recorded yet" in _other_peak[0]["text"])
+check("...and that is NO_RECORD, distinguishable from BOTH an observed peak and "
+      "an unreadable store - a month with no quarter is not a broken instrument",
+      bool(_other_peak) and bool(peak_rows)
+      and "UNREADABLE" not in _other_peak[0]["text"]
+      and _other_peak[0]["text"] != peak_rows[0]["text"])
+check("...and it is not FLAGGED, because an empty month is not an exceedance",
+      bool(_other_peak) and _other_peak[0]["ok"] and not _other_peak[0]["warn"])
+
+# The mutation guard. `checks()` ignoring `when` is the whole defect, and it is
+# invisible to every check above whenever the machine's clock happens to sit in
+# the fixture's own month - which is how this shipped. Grading two DIFFERENT
+# reference months against each other cannot be satisfied by a clock at all.
+check("the peak row differs between two reference months, so a `checks()` that "
+      "dropped `when` and read datetime.now() would fail HERE regardless of "
+      "what day the suite is run on",
+      bool(peak_rows) and bool(_other_peak)
+      and peak_rows[0]["text"] != _other_peak[0]["text"])
+
+# And the production meaning is unchanged: no argument still means today.
+_now_peak = _peak_rows(c.checks())
+_today_is_fixture_month = month_key(datetime.now(timezone.utc)) == month_key(B)
+check("calling checks() with NO argument still reads the month being billed "
+      "today - the live status page's meaning is untouched",
+      bool(_now_peak) and (bool(peak_rows)
+                           and _now_peak[0]["text"] == peak_rows[0]["text"]
+                           if _today_is_fixture_month
+                           else "no completed quarter recorded yet"
+                                in _now_peak[0]["text"]))
+
 # THE MEASUREMENT IS OF DELIVERED POWER (SAFETY-20). Graded on the parsed
 # SYNTAX, not on the text: the module docstring argues this at length and names
 # every forbidden word while doing so, so a grep over the source would be