feat(session): persist model tier overrides per session

Store per-session config in SQLite and route /model and /reset through command fast-paths so channel sessions keep independent model selection across reconnects and restarts.

src/models/capabilities.ts

@@ -1,6 +1,6 @@
 /**
  * Model capability detection for native audio input support.
- * 
+ *
  * Models that support native audio will receive raw audio data directly.
  * Models that don't will receive a Whisper transcript as text instead.
  */
@@ -27,12 +27,12 @@ const AUDIO_INCAPABLE_MODELS = new Set<string>([
 
 /**
  * Check whether a provider+model combination supports native audio input.
- * 
+ *
  * Returns true if the model can receive raw audio data directly via its API,
  * false if audio must be transcribed to text before sending.
  */
 export function supportsAudioInput(provider: string, model: string, override?: boolean): boolean {
-  if (override !== undefined) return override;
+  if (override !== undefined) {return override;}
 
   // Provider must be in the capable set
   if (!AUDIO_CAPABLE_PROVIDERS.has(provider)) {