feat: LLM router with chat intent and Cyrillic wake-word support

- Add LLMRouter: grammar-constrained LFM call for intent classification
  after stage-0, before classifier cascade. Errors fall through gracefully.
- Add IntentChat: conversational intent with no store side-effect, routed
  through LLM -> phraser chat endpoint.
- Extract slots for Chat: no structured slots, full utterance is payload.
- Extend stage-0 grammars to fire through Cyrillic wake-word spellings
  (Мэйвен/Мейвен/Майвен/etc.) produced by Russian STT model.
- StripWakeToken helper strips leading wake in any script so time/date
  grammars still match when wake is present.
- Add classifier examples for chat utterances (EN + RU).
- Wire LLMRouter into Router.Config; optional, nil-safe.

internal/router/slots.go

@@ -74,6 +74,9 @@ func (e Extractor) Extract(ctx context.Context, intent Intent, utterance string,
 				s.HasKey = true
 			}
 		}
+	case IntentChat:
+		// Chat has no structured slots — the full utterance is the payload.
+		// Slots.Text is already set to utterance at the top of Extract.
 	}
 	return s
 }