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/intent.go

@@ -28,7 +28,7 @@ package router
 
 import "time"
 
-// Intent — the five save-where labels from the spec's routing table. The
+// Intent — the six save-where labels from the spec's routing table. The
 // discriminator is "does the loop evaluate a predicate against it?":
 //
 //   - act:      command now, not stored (function call into the allowlist)
@@ -36,6 +36,8 @@ import "time"
 //   - fact:     structured state the loop reasons over → facts (sqlite)
 //   - note:     recall/preference, no predicate touches it → chroma
 //   - query:    answer, don't store → slm reads sqlite or chroma (RAG)
+//   - chat:     conversational, no store side-effect — LLM replies from
+//     dialogue history + general knowledge
 //
 // fact-vs-note is the whole line: predicate will read it → structured facts
 // row; just "recall when relevant" → semantic store. reminder splits off by
@@ -48,6 +50,7 @@ const (
 	IntentFact     Intent = "fact"
 	IntentNote     Intent = "note"
 	IntentQuery    Intent = "query"
+	IntentChat     Intent = "chat"
 	IntentSystem   Intent = "system"
 )