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-app/src/app.rs

@@ -250,7 +250,20 @@ fn recognize_command(
                     }
 
                     first_recognition = false;
-                    
+
+                    if crate::llm_fallback::is_enabled() {
+                        if let Some(prompt) = crate::llm_fallback::extract_prompt(&recognized_voice) {
+                            crate::llm_fallback::handle(&prompt);
+                            stt::reset_speech_recognizer();
+                            vad_state = VadState::WaitingForVoice;
+                            silence_frames = 0;
+                            start = SystemTime::now();
+                            audio_buffer.clear();
+                            ipc::send(IpcEvent::Listening);
+                            continue;
+                        }
+                    }
+
                     // filter activation phrases
                     // for tbr in config::ASSISTANT_PHRASES_TBR {
                     //     recognized_voice = recognized_voice.replace(tbr, "");
@@ -317,9 +330,17 @@ fn recognize_command(
 
 fn process_text_command(text: &str, rt: &tokio::runtime::Runtime) {
     info!("Processing text command: {}", text);
-    
+
     ipc::send(IpcEvent::SpeechRecognized { text: text.to_string() });
-    
+
+    if crate::llm_fallback::is_enabled() {
+        if let Some(prompt) = crate::llm_fallback::extract_prompt(text) {
+            crate::llm_fallback::handle(&prompt);
+            ipc::send(IpcEvent::Idle);
+            return;
+        }
+    }
+
     let mut filtered = text.to_lowercase();
     // for tbr in config::ASSISTANT_PHRASES_TBR {
     //     filtered = filtered.replace(tbr, "");

crates/jarvis-app/src/llm_fallback.rs

@@ -0,0 +1,113 @@
+use once_cell::sync::OnceCell;
+use parking_lot::Mutex;
+
+use jarvis_core::config;
+use jarvis_core::i18n;
+use jarvis_core::ipc::{self, IpcEvent};
+use jarvis_core::llm::{ChatMessage, ConversationHistory, LlmClient};
+use jarvis_core::voices;
+
+struct State {
+    client: LlmClient,
+    history: Mutex<ConversationHistory>,
+    max_tokens: u32,
+}
+
+static STATE: OnceCell<Option<State>> = OnceCell::new();
+
+pub fn init() {
+    let _ = STATE.set(build_state());
+}
+
+fn build_state() -> Option<State> {
+    if !config::LLM_DEFAULT_ENABLED {
+        info!("LLM fallback disabled by config.");
+        return None;
+    }
+
+    let client = match LlmClient::from_env() {
+        Ok(c) => c,
+        Err(e) => {
+            warn!("LLM fallback disabled: {}. Set GROQ_TOKEN to enable.", e);
+            return None;
+        }
+    };
+
+    let lang = i18n::get_language();
+    let prompt = config::get_llm_system_prompt(&lang);
+    let history = Mutex::new(ConversationHistory::new(prompt, config::LLM_DEFAULT_MAX_HISTORY));
+
+    info!("LLM fallback enabled (model: {}).", client.model());
+    Some(State {
+        client,
+        history,
+        max_tokens: config::LLM_DEFAULT_MAX_TOKENS,
+    })
+}
+
+pub fn is_enabled() -> bool {
+    STATE.get().and_then(|s| s.as_ref()).is_some()
+}
+
+pub fn extract_prompt(text: &str) -> Option<String> {
+    let lang = i18n::get_language();
+    let triggers = config::get_llm_trigger_phrases(&lang);
+    let lowered = text.to_lowercase();
+
+    for trig in triggers {
+        if let Some(rest) = strip_trigger(&lowered, trig) {
+            let trimmed = rest.trim();
+            if !trimmed.is_empty() {
+                return Some(trimmed.to_string());
+            }
+        }
+    }
+    None
+}
+
+fn strip_trigger(text: &str, trigger: &str) -> Option<String> {
+    let t = text.trim_start();
+    if let Some(after) = t.strip_prefix(trigger) {
+        let next = after.chars().next();
+        if next.map_or(true, |c| !c.is_alphanumeric()) {
+            return Some(after.to_string());
+        }
+    }
+    None
+}
+
+pub fn handle(prompt: &str) {
+    let state = match STATE.get().and_then(|s| s.as_ref()) {
+        Some(s) => s,
+        None => {
+            warn!("LLM fallback called while disabled — ignoring.");
+            return;
+        }
+    };
+
+    info!("LLM prompt: {}", prompt);
+
+    let snapshot: Vec<ChatMessage> = {
+        let mut h = state.history.lock();
+        h.push_user(prompt);
+        h.snapshot()
+    };
+
+    match state.client.complete(&snapshot, state.max_tokens) {
+        Ok(reply) => {
+            let reply = reply.trim().to_string();
+            info!("LLM reply: {}", reply);
+            state.history.lock().push_assistant(reply.clone());
+            ipc::send(IpcEvent::LlmReply { text: reply });
+            voices::play_ok();
+        }
+        Err(e) => {
+            error!("LLM request failed: {}", e);
+            state.history.lock().pop_last_user();
+            ipc::send(IpcEvent::LlmReply {
+                text: config::LLM_FALLBACK_ERROR_RU.to_string(),
+            });
+            voices::play_error();
+        }
+    }
+}

crates/jarvis-app/src/main.rs

@@ -18,6 +18,7 @@ mod log;
 
 // include app
 mod app;
+mod llm_fallback;
 
 // include tray
 // @TODO. macOS currently not supported for tray functionality.
@@ -55,6 +56,9 @@ fn main() -> Result<(), String> {
     // init i18n
     i18n::init(&settings.lock().language);
 
+    // init LLM fallback (no-op if GROQ_TOKEN missing)
+    llm_fallback::init();
+
     // init recorder
     if recorder::init().is_err() {
         app::close(1);

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 },