feat(learn): choosing how much an assistant thinks, and the assistants by provider in the field

Halkyon Learn's ADR 0021, D60 and D63:

- A chip after the scope's offers the efforts the operator allows for the
  assistant asked, its own marked; the one picked is kept per assistant on
  the device (DeviceSettings.askEfforts) and asked at, also by a
  conversation continued from the history. One the operator no longer
  allows counts as none.
- Every question asks for its effort's ceiling on output, as the thinking
  counts towards it (8,192 to 65,536 tokens; 16,384 at the model's own),
  where it asked for 4,096; the flashcards proposed, Explain and Why? ask
  at the assistant's own effort, a person's own key at none and 4,096.
- The field's picker lists the assistants under their providers' names,
  each in its colour.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Tizian 「ティツィアーン」 <raisondetredev@pm.me>

apps/learn/halkyon_learn_flutter/lib/l10n/app_localizations.dart

@@ -10791,6 +10791,18 @@ abstract class AppLocalizations {
   /// **'What it may look up'**
   String get assistantScope;
 
+  /// Tooltip of the effort chip in the field (ADR 0021, D63): more effort thinks longer and uses more of the budget.
+  ///
+  /// In en, this message translates to:
+  /// **'Effort: how much it thinks before it answers'**
+  String get assistantEffortTooltip;
+
+  /// The effort the operator set up for an assistant, among those to choose, by its name.
+  ///
+  /// In en, this message translates to:
+  /// **'{effort} (default)'**
+  String assistantEffortDefault(String effort);
+
   /// No description provided for @assistantScopeTicked.
   ///
   /// In en, this message translates to: