test: target question card title by testid instead of text

Add data-testid to NativeChatQuestionCard's title element and update the
e2e test to query by testid with a text filter. The transcript row also
renders the question text, so the previous test could match either location,
causing flaky results. Gating on the card's own title node ensures the
assertion verifies the card is actually rendered.

Fixes #20724

src/renderer/src/lib/browser-history-match-budget.ts

@@ -4,18 +4,18 @@
  * These are ceilings for catching order-of-magnitude regressions, not targets —
  * the measured numbers on a developer machine sit far under each one.
  *
- * The ceilings are asserted against the *fastest* sample of a batch, never the
- * slowest: a vitest worker sharing cores with the rest of the suite gets
- * preempted mid-measurement, so the slowest sample measures the machine while
- * the fastest still approximates the matcher.
+ * The ceilings are asserted against the *lower quartile* of a batch, never the
+ * slowest sample: a vitest worker sharing cores with the rest of the suite gets
+ * preempted mid-measurement, so the slow tail measures the machine. A quartile
+ * rather than the minimum keeps one lucky sample from carrying a regressed batch.
  *
  * Raising any value requires a fresh measurement recorded in the PR.
  */
 export const BROWSER_HISTORY_MATCH_BUDGET = {
   /** Entries prepared in one omnibox open. Tracks MAX_BROWSER_HISTORY_ENTRIES. */
   candidateCount: 200,
-  /** Milliseconds to prepare the whole corpus once (cold open), fastest sample. Measured 0.08 ms. */
+  /** Milliseconds to prepare the whole corpus once (cold open), lower quartile. Measured 0.07 ms. */
   prepareMs: 2,
-  /** Milliseconds to match the prepared corpus against one query, fastest sample. Measured 0.03 ms. */
+  /** Milliseconds to match the prepared corpus against one query, lower quartile. Measured 0.03 ms. */
   matchMs: 2
 } as const

src/renderer/src/lib/browser-history-match.performance.test.ts

@@ -25,13 +25,19 @@ const entries = Array.from({ length: candidateCount }, (_, index) => makeEntry(i
 const WORST_QUERY = 'observability rollout'
 
 /**
- * Why the fastest sample and not p95: this runs in a vitest worker competing for
- * cores with the rest of the suite, so a slow sample records a preemption rather
- * than the matcher. Measured across idle and full-suite runs, the fastest sample
- * moved 0.05 ms -> 0.08 ms while p95 of the same batches swung 0.09 ms -> 0.50 ms.
+ * Why the lower quartile and not p95 or the minimum: this runs in a vitest worker
+ * competing for cores with the rest of the suite, so a slow sample records a
+ * preemption rather than the matcher, while a single fastest sample would pass
+ * with the other 19 runs over budget. Requiring a quarter of the batch inside the
+ * ceiling still discards the preempted tail: measured for preparation, the lower
+ * quartile moved 0.07 ms -> 0.15 ms between idle and 4x core oversubscription,
+ * while p95 of those same batches swung 0.10 ms -> 0.81 ms and the slowest sample
+ * reached 6.9 ms.
  */
-function fastestSample(samples: readonly number[]): number {
-  return Math.min(...samples)
+function lowerQuartileSample(samples: readonly number[]): number {
+  const sorted = [...samples].sort((a, b) => a - b)
+  // Nearest-rank p25: ceil(n*0.25)-1, so 20 samples pick the 5th fastest.
+  return sorted[Math.max(0, Math.ceil(sorted.length * 0.25) - 1)]
 }
 
 describe('browser history match performance budget', () => {
@@ -51,7 +57,7 @@ describe('browser history match performance budget', () => {
       prepareBrowserHistoryEntries(entries.slice())
       samples.push(performance.now() - start)
     }
-    expect(fastestSample(samples)).toBeLessThan(prepareMs)
+    expect(lowerQuartileSample(samples)).toBeLessThan(prepareMs)
   })
 
   it('matches one query against the prepared corpus within budget', () => {
@@ -67,6 +73,6 @@ describe('browser history match performance budget', () => {
       run()
       samples.push(performance.now() - start)
     }
-    expect(fastestSample(samples)).toBeLessThan(matchMs)
+    expect(lowerQuartileSample(samples)).toBeLessThan(matchMs)
   })
 })