feat(app): wire LlmClient into voice loop with trigger-prefix fallback

new module crates/jarvis-app/src/llm_fallback.rs holds an optional
LlmClient + ConversationHistory built once at startup. if GROQ_TOKEN is
unset the module logs a warning and stays disabled — voice commands keep
working as before.

both the wake-word voice path (recognize_command in app.rs) and the
gui-side text command path (process_text_command) now check whether the
recognized phrase starts with one of the configured trigger phrases
(ru: 'скажи' / 'ответь' / 'произнеси'). when it does, the remainder of
the phrase is sent to Groq and the reply is published as a new
IpcEvent::LlmReply { text } so the gui can speak it.

on api error the trailing user turn is popped from history, the russian
fallback line is sent over ipc and a 'error' voice cue plays. the loop
itself never panics.

crates/jarvis-core/src/ipc/events.rs

@@ -12,6 +12,9 @@ pub enum IpcEvent {
     
     // Speech recognized
     SpeechRecognized { text: String },
+
+    // LLM produced a reply for a free-form question
+    LlmReply { text: String },
     
     // Command was executed
     CommandExecuted { id: String, success: bool },