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>
check_design_parity.py reads its checklist from the audit page's own
proposals; it now reports every one of the 31 as implemented, with no
deliberate divergences left.
* Schedule: the Kanban/Calendar drop-list became a pair of tabs, and the
Running lane is outlined while it holds anything — dropping a card there
starts the task for real, so it should not look like the other six.
* Cowork: agent / routing / usage / folder moved out of the typing box into
their own status strip beneath it, styled as status rather than a second
toolbar. All of them stay interactive; the design's read-only strip would
have cost features.
* Folder: the path is written as the screen's title instead of sitting in a
read-only text box that looked editable and cost a row.
* GraphRAG: the second toolbar row is gone (Export joined the first), and
the one button that relabelled itself became Đồ thị | Tin nhắn tabs, so
the view you are NOT in is named too.
* Settings gained the theme picker, so language / provider / theme are all
reachable there as well as on the rail's account row.
* Task editor: the five group boxes are grouped into three step tabs
(Nội dung → Lịch chạy → Liên kết). All 22 fields verified present after
the move; only the old section index is gone, replaced by the tabs.
* The assistant dot now clears a screen's own bottom bar (Cowork's
composer), measured from the composer's top edge in window coordinates.
Also adds .gitattributes: without it a Windows checkout records CRLF and
every file reads as fully rewritten to a Linux CI runner.
Verification: 7 check_*.py suites green, no screen clipped at 1920/1366/1280,
and no dialog scrolls sideways at 9/11/14pt.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The Gitea repo was initialised from an earlier snapshot, so main and the
machine this runs on had drifted apart in 153 files before any UI work
started. This commit brings the branch up to the local tree as it stood
on 2026-08-15 21:31 (from cowork_local.7z), so the redesign that follows
shows up as its own reviewable diff instead of being mixed in with the
pre-existing divergence.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
