feat(caption): let live captions use their own speech model

The speech engine now keeps an auxiliary model next to the dictation model
and transcribes with whichever the request names, reloading it once if the
engine restarted. Settings > STT gains a live-caption model so captions can
run on large-v3-turbo while dictation keeps its own model. The runtime
minimum rises to 1.7.0 because older engines would silently ignore the
model choice.

Suggestion paging moves to Up/Down: the page follows the selection and the
last item waits while more candidates are being generated. The Left/Right
page shortcuts are removed; they did nothing until a page had filled and
clash with Intel's display-rotation hotkeys.

packages/i18n/src/locales/ja.json

@@ -375,7 +375,6 @@
   "popup.suggestion.hintNext": "次へ",
   "popup.suggestion.hintDismiss": "閉じる",
   "popup.suggestion.hintMove": "移動",
-  "popup.suggestion.hintPage": "ページ",
   "popup.suggestion.loading": "生成中…",
   "keybinding.ui.sectionInput": "入力サジェスト",
   "keybinding.action.suggestionAccept": "サジェストを承認",
@@ -454,10 +453,6 @@
   "popup.suggestion.hintGeneratingMore": "さらに生成中…(最大{{max}}件)",
   "keybinding.action.suggestionPrev": "前の候補",
   "keybinding.action.suggestionPrev.desc": "前の候補に移動します。",
-  "keybinding.action.suggestionPageNext": "次のページ",
-  "keybinding.action.suggestionPageNext.desc": "次の提案ページを表示します(最大12件まで)。",
-  "keybinding.action.suggestionPagePrev": "前のページ",
-  "keybinding.action.suggestionPagePrev.desc": "前の提案ページに戻ります。",
   "input.insights.tabs.graph": "グラフ",
   "input.graph.description": "Your sentences are stored as nodes and their relations as edges (what follows what, which share terms) so suggestions can pull personal context. Local only.",
   "input.graph.nodes": "文ノード",
@@ -524,5 +519,8 @@
   "popup.caption.waiting": "聞き取り中… 最初の字幕まで数秒かかることがあります",
   "popup.caption.dragHint": "ドラッグで移動 · ダブルクリックで元の位置",
   "settings.captionRefine": "文脈で字幕を整える",
-  "settings.captionRefine.desc": "確定した字幕の区切り・句読点・聞き間違いを、ローカルAIが前後の文脈に合わせて直します。"
+  "settings.captionRefine.desc": "確定した字幕の区切り・句読点・聞き間違いを、ローカルAIが前後の文脈に合わせて直します。",
+  "settings.captionModel": "リアルタイム字幕モデル",
+  "settings.captionModel.same": "音声入力と同じ",
+  "settings.captionModel.desc": "リアルタイム字幕だけを別のモデルで認識します。音声入力モデルと同時に読み込まれます。"
 }