Rudder's robot voice keeps a sentence whole across a breath, and splits only real run-ons

First live use: one sentence came out as two.
- A pause is not a sentence end: the engine finalises after 0.8 s of silence, a breath mid-sentence
  included, and the robot spoke that fragment alone. A final that doesn't end in . ! or ? is now held and
  joined to what's said next; spoken as it is after 2.5 s of silence or on Stop.
- The comma break for run-ons now needs ≥20 words waiting (was 14) and keeps ≥10 in the piece, so ordinary
  long sentences are no longer cut at their comma.
- Checked by running the page's own functions on scripted streams: a sentence paused mid-way → one spoken
  sentence; a 30-word run-on → two clause-sized pieces; a 16-word sentence with a comma → not split; an
  unfinished thought then Stop → still spoken.

plugin-designs/rudder-voice/rudder-voice.vue

@@ -146,6 +146,8 @@ const SENTENCE_END = /[.!?]["')\]]?$/
 // end for 20+ seconds. So a long pending stretch also breaks at a clause: ≥14 words waiting → speak up to the
 // last comma (keeping ≥8 words); ≥35 words with no comma at all → speak the first 25, so the robot never
 // falls silent for long.
+// ★ OVER-SPLITTING (measured 2026-09-28, first live use): at ≥14 words the comma rule also cut ordinary
+// long sentences in two. Raised to ≥20 words waiting, keeping ≥10 in the piece spoken.
 const CLAUSE_END = /[,;:]$/
 function robotOnPartial(full) {
   if (!robotOn.value) return
@@ -154,19 +156,42 @@ function robotOnPartial(full) {
   const pending = done - robotSpoken
   let end = -1
   for (let i = robotSpoken; i < done; i++) if (SENTENCE_END.test(w[i])) end = i
-  if (end < 0 && pending >= 14) {
-    for (let i = robotSpoken + 7; i < done; i++) if (CLAUSE_END.test(w[i])) end = i
+  if (end < 0 && pending >= 20) {
+    for (let i = robotSpoken + 9; i < done; i++) if (CLAUSE_END.test(w[i])) end = i
     if (end < 0 && pending >= 35) end = robotSpoken + 24
   }
   if (end >= robotSpoken && end - robotSpoken + 1 >= 3) {
-    speak(w.slice(robotSpoken, end + 1).join(' '))
+    speak(takeHeld() + w.slice(robotSpoken, end + 1).join(' '))
     robotSpoken = end + 1
   }
 }
+// ★ A PAUSE IS NOT A SENTENCE END. The engine finalises after 0.8 s of silence — a breath in the middle of a
+// sentence included — and the robot used to speak that fragment on its own, so one sentence came out as two.
+// A final that doesn't end in . ! or ? is HELD and joined to whatever is said next; if nothing follows within
+// 2.5 s (or recording stops) it is spoken as it is.
+let robotHeld = ''
+let robotHoldTimer = null
+function takeHeld() {
+  clearTimeout(robotHoldTimer)
+  const h = robotHeld
+  robotHeld = ''
+  return h ? h + ' ' : ''
+}
+function speakHeld() {
+  const h = takeHeld().trim()
+  if (h && robotOn.value) speak(h)
+}
 function robotOnFinal(text) {
   const rest = wordsOf(text).slice(robotSpoken)
   robotSpoken = 0
-  if (robotOn.value && rest.length) speak(rest.join(' '))
+  if (!robotOn.value || !rest.length) return
+  if (SENTENCE_END.test(rest[rest.length - 1])) {
+    speak(takeHeld() + rest.join(' '))
+  } else {
+    robotHeld = (robotHeld ? robotHeld + ' ' : '') + rest.join(' ')
+    clearTimeout(robotHoldTimer)
+    robotHoldTimer = setTimeout(speakHeld, 2500)
+  }
 }
 
 // A light clean-up of what the ROBOT says (the box keeps exactly what was said): drop filler sounds, collapse
@@ -607,6 +632,7 @@ function closeStream() {
 // Recording stopped mid-sentence: the streamed words are already in the box, so just let go of them.
 function flushPartial() {
   robotSpoken = 0
+  speakHeld()
   clearTimeout(flushTimer)
   const finals = pendingFinals.splice(0)
   const p = pendingPartial