Strip silence: preserve music intro, fix ad normalization, smart loop range

- Preserve first silence in first DIALOG region (music intro before host speaks)
- Fix ad/ident normalization using direct WAV reading (accessor failed after splits)
- Loop range starts 0.5s before audible music, ends at last item
- Disable broken music lead-in nudge (intro preservation handles it)
- Caller dialog model set to Grok for testing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/config.py

@@ -37,7 +37,7 @@ class Settings(BaseSettings):
     # Categories: caller_dialog, devon_monitor, devon_ask, background_gen,
     #             call_summary, news_summary, topic_gen, unknown
     category_models: dict = {
-        "caller_dialog": "anthropic/claude-sonnet-4-5",       # quality matters — this IS the show
+        "caller_dialog": "x-ai/grok-4-fast",                   # testing edgier dialog — revert to anthropic/claude-sonnet-4-5
         "devon_ask": "google/gemini-2.5-flash",               # Devon direct questions
         "devon_monitor": "google/gemini-2.5-flash",           # Devon polling — biggest cost saver
         "background_gen": "google/gemini-2.5-flash",          # JSON caller backgrounds