The settings band was a third of the card on a phone, and the space around the
automatic-updates row was the worst of it: 33.5 logical px above the switch and
38 below, measured ink-to-ink, against declared gaps of 16 and 12.

Two causes, both invisible in the source.

The switch sat in a `ConstrainedBox(minWidth: step9, minHeight: step9)` whose
comment claimed it "keeps a full-size interaction target for anyone who cannot
land on 24px". It did not. `DesignSystemToggle` owns its own `InkWell` wrapping
the 40x24 track, and that outer box is not a gesture detector — so it reserved
48px of column height while the only thing a finger could actually hit stayed
the 24px track. It bought airiness and paid for nothing.

And every row in the band is a touch-target box taller than its own ink, each
contributing ~10px of air above and below the visible text. The declared gaps
sat on top of that, so the band paid for the same space twice.

So: the whole settings row is the gesture now — tapping the label toggles the
setting, which is a target the width of the band rather than a 40x24 track —
and it drops to the `step8` minimum every other row in the footer already uses.
The row publishes `excludeFromSemantics` so it does not add a second unlabelled
button node beside the switch's own. The stacked column and the gap before the
identity region declare no vertical space at all; the row boxes supply the
rhythm.

Measured, ink-to-ink: trigger row to switch row 33.5 -> 13.5, switch row to
model row 38.0 -> 22.0. Card height: 466 -> 430 on a phone, 716 -> 647 in
German at 320px and 1.3x, 386 -> 366 on desktop. The split-attribution state
nets to zero, because the attribution row's own step8 box costs back what the
gap removal saves — the trade that keeps the card's bottom margin from moving.

Also two more review findings on #3602:

The report row's tooltip entered semantics. Excluding it alone would have made
that row worse — its visible route sheds whole segments, so the children and
the tooltip carry different strings, and excluding only the tooltip leaves the
*shortened* route as the sole announcement. It now publishes one node with the
untruncated attribution, the shape `DesignSystemInlineAction` uses a row above.

And both concepts carried a `generated.at` of 14:00:00Z against a 13:04:50Z
commit, claiming a snapshot from the future.

Review findings on #3604.

Making the whole settings row tappable gave it a focus stop of its own beside
the switch's, so Tab landed twice on one setting and both stops toggled it.
`excludeFromSemantics` suppresses the semantic node and does nothing whatever
to traversal. The wrapper is pointer-only now via `canRequestFocus: false`, and
a test counts focusable InkWells in the row — it reports 2 without the flag.

The concept also stated the old layout contract in two places the new prose
contradicted: the flow diagram's stack node still promised "a larger gap above"
the schedule, and the automation section still claimed "the toggle keeps a full
`spacing.step9` interaction slot around its 40x24 track" — the very claim this
branch exists to delete, since that slot was inert. Both now describe the
full-row target on the shared `step8` minimum. The one remaining step9 mention
narrates the earlier revision as history, not as a contract.

And `component-contracts.md` is dropped from this branch entirely. Its only
change here was a `generated.at` rewound from 14:00:00Z to 13:56:33Z — bulk
collateral from #3602 that rode along in the cherry-pick — which would have
claimed an unchanged document predates its own revision. `ui-surfaces.md` keeps
its bump because its prose does change.