ui: give the worst-call ordering test margins a stall cannot invert

`the_worst_call_is_one_calls_cost_and_not_the_mean` reads both its
orderings off a wall clock, and the margins were too thin to survive the
full suite: it failed about one run in three, on an idle box as well as a
loaded one. One of the steady handler's ten calls would pick up a ~0.9 ms
scheduler stall and overtake the spike it is meant to rank below —
`self_us` 5109 / `worst_us` 1405 against the spike's 1398 / 1361.

Twenty steady calls instead of ten raise the window cost without raising
any single call's, and an 8x spike instead of 3x puts the worst-call
margin about four times beyond the stall that broke it. Six consecutive
full-suite runs clean, then a full gate chain. The doc comment carries
the measured numbers and says to keep both ratios, since the absolute
durations are not what the test rests on.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SgstFWtn1RxEJ5kVrpgYwn

crates/benilla-ui/src/script/tests/handler_prof.rs

@@ -198,27 +198,35 @@ fn disarming_clears_the_window() {
     );
 }
 
-/// The column the mean cannot show: a handler that stalls one frame in ten ranks below a steadier
-/// one by self time and still has the larger worst call. The two bodies differ by 3x in work per
-/// the ratio below, which is the margin the ordering rests on — not an absolute duration.
+/// The column the mean cannot show: a handler that stalls one frame in twenty ranks below a
+/// steadier one by self time and still has the larger worst call.
+///
+/// Both orderings are read off a wall clock, so the margins are what make the test an assertion
+/// rather than a coin toss, and they are set against a measured stall, not a guess. At 10 steady
+/// calls against one spike of 3x their size this failed about one run in three inside the full
+/// suite: one steady call would pick up a ~0.9 ms scheduler stall and overtake the spike's 1.4 ms
+/// (`self_us` 5109 / `worst_us` 1405 against 1398 / 1361). Twenty steady calls raise the *window*
+/// cost without raising any single call's, and an 8x spike puts the worst-call margin about four
+/// times beyond the stall that broke it. Keep both ratios if these numbers are ever tuned; the
+/// absolute durations do not matter.
 #[test]
 fn the_worst_call_is_one_calls_cost_and_not_the_mean() {
     let mut s = armed();
     s.run(
         r#"
         local function burn(n) local x = 0 for i = 1, n do x = x + i end return x end
-        -- 10 calls of 50k: the larger self time, the smaller single call.
+        -- 20 calls of 50k: the larger self time, the smaller single call.
         local steady = CreateFrame("Frame", "Steady")
         steady:SetScript("OnUpdate", function() burn(50000) end)
-        -- One call of 150k, on the first tick only: the smaller self time, the larger single call.
+        -- One call of 400k, on the first tick only: the smaller self time, the larger single call.
         local spiky = CreateFrame("Frame", "Spiky")
         spiky:SetScript("OnUpdate", function()
-          if not this.done then this.done = true burn(150000) end
+          if not this.done then this.done = true burn(400000) end
         end)
         "#,
     )
     .unwrap();
-    for _ in 0..10 {
+    for _ in 0..20 {
         s.tick(0.016);
     }
     assert!(s.errors().is_empty(), "{:?}", s.errors());
@@ -226,7 +234,7 @@ fn the_worst_call_is_one_calls_cost_and_not_the_mean() {
     let rows = s.handler_profile();
     let steady = row(&rows, "Steady", "OnUpdate").expect("the steady handler");
     let spiky = row(&rows, "Spiky", "OnUpdate").expect("the spiky handler");
-    assert_eq!((steady.calls, spiky.calls), (10, 10));
+    assert_eq!((steady.calls, spiky.calls), (20, 20));
     assert!(
         steady.self_us > spiky.self_us,
         "the steady handler costs more over the window, so it ranks first: {rows:#?}"
@@ -243,7 +251,7 @@ fn the_worst_call_is_one_calls_cost_and_not_the_mean() {
     let spiky_mean = spiky.self_us / f64::from(spiky.calls);
     assert!(
         spiky.worst_us > spiky_mean * 2.0,
-        "nine of its ten calls do nothing, so the mean hides the stall by about tenfold: \
+        "nineteen of its twenty calls do nothing, so the mean hides the stall by about twentyfold: \
          worst {:.1} us against a mean of {spiky_mean:.1} us",
         spiky.worst_us
     );