feat(caption): stream live captions and polish finished lines in context

Replaces the fixed six-second batches with a streaming track per audio
source: the uncommitted audio is re-recognised every second and sent as a
partial with its agreed (stable) prefix, a short pause finalises the line,
and long unbroken speech is committed at Whisper segment boundaries. Idle
audio is trimmed so silence cannot produce invented sentences.

Finished lines are corrected by the local model against the previous lines
and replaced in place; edits that change too much are rejected. The
behaviour can be switched off in Settings.

packages/i18n/src/locales/zh.json

@@ -522,5 +522,7 @@
   "input.feedback.recommendationFailed": "无法将 {{app}} 添加到排除列表。",
   "popup.caption.loading": "正在准备语音模型…",
   "popup.caption.waiting": "正在聆听… 第一条字幕可能需要几秒钟",
-  "popup.caption.dragHint": "拖动以移动 · 双击复位"
+  "popup.caption.dragHint": "拖动以移动 · 双击复位",
+  "settings.captionRefine": "按上下文润色字幕",
+  "settings.captionRefine.desc": "本地 AI 会根据上下文修正已确定字幕的空格、标点和听错的词。"
 }