26 → 52px, 14 → 28px for the sparkle. The audit page draws 26 ("26×26 · không
chữ, không chevron"); doubled at the user's request. Still half the area of the
84×64 button it replaced: 2704 vs 5376px².
Four checks pinned the old number. Three now read the size the design actually
claims rather than a literal — square, at least 24px to hit, and smaller than
what it replaced — and check_design_parity records the deviation in its item
label instead of scoring 52px against a 26px expectation.
The fourth attempt was worse than the literal: I had check_layout_geometry
import _DOT and compare against it, which makes it unfailable — change the
constant and the expectation moves too. check_probes_bite caught that, reporting
that doubling _DOT again left the checker green. It now bounds the range
(24..64, square), which the mutation does break.
24/24 checkers pass; check_multi_screen took the teardown segfault once in three
standalone runs.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Settings sat 7px further in than the Dashboard/Giám sát rows above it — its
QSS gave it a 6px side margin where those rows start at the rail edge. At the
collapsed 54px width that put its icon near the middle of the rail, which is
what "thu gọn menu lại ra giữa" was describing. Icon and label now start on
the same x as the rows, open and collapsed, in both themes.
The help panel's transcript is rendered HTML, so switching language re-labelled
the chrome but left the greeting — and the "AI Assistant" speaker label — in
whatever language the panel was built in. retranslate() now rewrites the
greeting (matched by identity, so a real reply is never touched) and re-renders.
The sparkle is #FDBE59, sampled from the audit page's own render. Its CSS says
.spark{color:#0F9B8A}, but the glyph is the ✨ emoji and a colour emoji ignores
CSS colour, so the page has always drawn a gold star.
Behind all three: MainWindow does not style itself — run() calls
app.setStyleSheet — so 12 of 13 checkers were measuring a window with no
padding, margins or borders. Every QSS-driven layout bug was invisible to them,
and an unstyled window reported an icon drift that does not exist. Added
_apply_theme() and wired it through.
Two checker repairs that followed:
· check_no_hscroll flagged the 9pt dialogs on sizeHintForColumn(0), which
returns 182px at 9pt, 11pt and 14pt alike. Nothing was clipped. It now
compares the painted text against the width actually on screen, and fails
on a squeezed list (24 combos) where the old test passed.
· the checkers print Vietnamese and died mid-report on a cp932 console.
New: check_rail_align (icons hold one line, both themes, both states) and
check_help_i18n (transcript follows the language). Both verified to fail
without their fix.
15/15 checkers pass. check_nav and check_design_parity segfault in Qt teardown
roughly one run in three — pre-existing, after the verdict prints, and it
happens with or without the theme change.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two problems, both only visible at the window size this machine actually opens
(1024×571 on a 1280×672 work area):
* The rail drew the "GẦN ĐÂY" heading on top of the last nav row. nav and the
bottom group have fixed heights, so a short window put the entire squeeze on
RECENTS; once that hit zero the layout had nowhere left to give. The
destinations and RECENTS now scroll together inside their own area, while
the bottom group, Settings and the account row stay pinned.
* Overview did not look like the drawing. Fixed, in the order the page draws
them: sections are quiet caps headings with flat content instead of six
bordered boxes; the four resource metrics sit ACROSS one row rather than
stacked four deep; and "Hoạt động gần đây" moved from second place to the
bottom beside the audit log, so the reading order is cost → machine →
permissions → prices → what happened. At 1280×760 the page now reaches the
price table on first screen; before it showed one and a half sections.
Two deliberate differences from the drawing, both because matching it would
remove information: the wireframe shows four KPI tiles where the app has five
real metrics plus the budget entry card, and it writes resources as one text
line where the app keeps the CPU/RAM gauges.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two things differ between machines and only one of them is width: a 4K panel
has more pixels, while a 125%/150% display has the same logical pixels holding
LESS, because every label and margin is taller. Breakpoints written as raw
pixels only hold on the machine they were tuned on.
* ui_scale() derives a factor from font height (1.0 at the 15px line the
layouts were measured against) and every narrow-guard threshold is
multiplied by it, so panes fold when the content is cramped rather than
when a number is crossed.
* The window takes a share of the available screen (80% × 85%) with the old
1180×760 as the floor, instead of opening at that size on any monitor.
* Moving the window to another screen re-pins the assistant and re-decides
the fold, since the new screen's work area and scaling may differ.
Found by tools/check_multi_screen.py, which walks 5 window sizes × 3 font
scales:
* At 150%, Schedule was clipped on 1280 and 1366 screens and the window's
own minimum grew to 1459px — wider than a 1280 laptop, so the app could
not fit at all. The cause was not the lanes: the one-line lane-count
summary in the header reported a sizeHint wide enough to set the minimum
width of the entire window. It now yields first (its text stays in the
tooltip); the window minimum drops 1459 → 752 and holds there at every
scale.
Also: these checkers exited 0xC0000409 from a Qt teardown crash AFTER printing
their verdict. check_probes_bite decides whether a probe caught its mutation by
reading exit codes, so a crash would have counted as "caught" — the round could
have passed while proving nothing. They now flush and os._exit with the real
verdict, and round 5 still catches all six mutations.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Five rounds, each looking from an angle the previous one cannot:
1. text — every "Thay đổi" bullet on the page vs a probe (existing)
2. geometry — check_layout_geometry.py: reading order of the rail, section
order down Monitoring, which side each pane is on, and the size
relationships the design names (hero card, 26px dot)
3. inventory— check_controls_alive.py: every control in controls.json still
present in the built app, attributed to its owning CLASS via the
baseline commit (a file holds several classes, so a per-file
check reported eight dialog controls as missing)
4. eyes — rendered screens read against the wireframes
5. adversarial — check_probes_bite.py: break one feature at a time and fail if
the matching check still passes
What rounds 4 and 5 caught, which 1-3 could not:
* Schedule showed six of seven lanes; the seventh needed a horizontal
scroll. The design says "giữ đủ 7 lane, thu hẹp cho vừa một màn". Lane
minimum width 190 → 150, so 7 × 150 + gaps fits a 1280 window. Round 2 now
measures this instead of relying on someone noticing.
* check_design_parity ALWAYS returned 0. It was a report, not a check: every
probe in it was incapable of failing, so a regression would print on screen
and still exit green. It now exits non-zero when anything is CHUA — which
is what let round 5 detect the two mutations it had been sleeping through.
Also fixed in the harness itself: it rewrote line endings while restoring
mutated files (read_text/write_text translate both ways), and it compared the
tree against "clean" rather than against its own starting state.
All ten checkers green by exit code.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
