test(performance): [ENG-13] enforce measured teardown observation minimum

test/performance-report.test.js

@@ -7,7 +7,7 @@ import { test } from 'node:test'
 import { fileURLToPath } from 'node:url'
 import { hash } from '../refactor/scripts/releases.mjs'
 import { verifyPerformanceArtifacts } from '../scripts/performance-artifacts.mjs'
-import { performanceHtml, performanceScript } from '../scripts/performance-fixture.mjs'
+import { performanceHtml, performanceScript, waitForObservation } from '../scripts/performance-fixture.mjs'
 import { validatePairedPerformance } from '../scripts/performance-report.mjs'
 
 const baseline = JSON.parse(fs.readFileSync(new URL('../refactor/baselines/performance.json', import.meta.url), 'utf8')).runs[0]
@@ -44,6 +44,7 @@ test('paired performance requires comparable cohorts, real playback and strict c
     report => report.runs[1].measurements.resources[0].after.timers.push({ kind: 'interval' }),
     report => report.runs[1].measurements.resources[0].after.lateCallbacks.push({ kind: 'timeout' }),
     report => report.runs[1].measurements.resources[0].after.lateResizeEvents++,
+    report => report.runs[1].measurements.resources[0].after.observedMs = 349,
   ]) {
     const report = fixture()
     mutate(report)
@@ -60,17 +61,51 @@ test('paired performance requires comparable cohorts, real playback and strict c
   assert(comparison.reviewRequired && comparison.groups.every(group => group.reviewSignals.some(signal => signal.metric === 'constructorMs')))
 })
 
-test('performance adapter changes only delivery while retaining the frozen measurement procedure', () => {
+test('performance adapter preserves frozen measurements except delivery and enforcing the observation minimum', () => {
   const frozen = fs.readFileSync(new URL('../refactor/fixtures/performance.js', import.meta.url), 'utf8')
   const adapted = performanceScript()
   const before = 'const response = await fetch(\'/reports/performance\', { method: \'POST\', headers: { \'Content-Type\': \'application/json\' }, body: JSON.stringify(report) })'
   const after = 'window.artplayerPerformanceReport = report; const response = { ok: true }'
-  assert.equal(adapted.replace(after, before), frozen)
+  const prefix = `${waitForObservation.toString()}\n`
+  assert(adapted.startsWith(prefix))
+  assert.equal(adapted.slice(prefix.length).replace(after, before).replace('await waitForObservation(probe.wait, now, waitStarted, 350)', 'await probe.wait(350)'), frozen)
   assert.match(performanceHtml('candidate'), /src="\/candidate\/artplayer.js"/)
   assert.match(performanceHtml('published'), /src="\/published\/artplayer-plugin-chapter.js"/)
   assert.throws(() => performanceHtml('../uncompiled'))
 })
 
+test('resource observation re-arms after an early timer without rounding up evidence', async () => {
+  let clock = 1000
+  const delays = []
+  await waitForObservation(async (delay) => {
+    delays.push(delay)
+    clock += delays.length === 1 ? 349 : 1
+  }, () => clock, 1000, 350)
+  assert.deepEqual(delays, [350, 1])
+  assert.equal(clock - 1000, 350)
+})
+
+test('resource observation retains overshoot and does not wait again after the minimum', async () => {
+  let clock = 1000
+  const delays = []
+  const wait = async (delay) => {
+    delays.push(delay)
+    clock += 364
+  }
+  await waitForObservation(wait, () => clock, 1000, 350)
+  assert.deepEqual(delays, [350])
+  assert.equal(clock - 1000, 364)
+  await waitForObservation(wait, () => clock, 1000, 350)
+  assert.deepEqual(delays, [350])
+})
+
+test('resource observation propagates timer failures rather than certifying an incomplete window', async () => {
+  const failure = new Error('timer unavailable')
+  await assert.rejects(waitForObservation(async () => {
+    throw failure
+  }, () => 0, 0, 350), error => error === failure)
+})
+
 test('performance refuses stale sources, build tools and altered installed bundles', () => {
   const cache = fileURLToPath(new URL('../refactor/.cache/performance/', import.meta.url))
   fs.mkdirSync(cache, { recursive: true })

test/performance/README.md

@@ -9,8 +9,9 @@ worker, no trace/video recording and the same media and viewport within a pair.
 Each engine runs three alternating published/candidate pairs. Each side retains
 one warm-up and five timed samples for both core and core + chapter, followed by
 separate instrumented resource probes. `scripts/performance-fixture.mjs` adapts
-only the frozen BASE-06 fixture's script URLs and report transport. Its original
-files remain unchanged and their existing baseline tests still run.
+the frozen BASE-06 fixture's script URLs, report transport and enforcement of its
+minimum observation window. The frozen files and all timed samples remain
+unchanged, and their existing baseline tests still run.
 
 The candidate must come from an isolated package installation. Artifact hashes,
 source snapshots, package inputs and build tools are checked before measurement;
@@ -28,3 +29,12 @@ A successful test proves the measurement contract and candidate resource cleanup
 approval. CORE-22 and release reviews must resolve the corresponding risks before
 publishing. These counters do not measure native heap/GPU memory, real mobile
 hardware or screen-reader behavior. See `refactor/coverage-performance.md`.
+
+## Observation window
+
+The current performance fixture adapter enforces the existing 350 ms teardown
+observation using the measured clock. It re-arms the probe's original timer if
+the nominal delay returns before that minimum, without rounding up reported
+time or relaxing validation. This applies equally to both variants and leaves
+the frozen BASE-06 fixture and all timed samples unchanged. See
+`test/performance-report.test.js` and `refactor/changes/2026-09-14-ENG-13-observation-window.md`.