feat: TTS backend abstraction + 4 'imba' features + Lua packs

Big push driven by user feedback ("делай имбу") and web research on what
voice assistants need to be the ideal:

TTS backend abstraction (P0.1)
  - new module crates/jarvis-core/src/tts/{mod,sapi,piper,silero}.rs
  - TtsBackend trait with SapiBackend (current PowerShell), PiperBackend
    (rhasspy/piper, neural quality), SileroBackend (python subprocess)
  - JARVIS_TTS env var picks (sapi|piper|silero). Auto-detect Piper if
    binary + voice present in tools/piper/. Falls back to SAPI on missing.
  - SpeakOpts {lang, detached, raw} replaces ad-hoc args. text_utils
    sanitiser applied unless raw=true.
  - llm_fallback + lua/api/tts both routed through tts::backend().
  - tools/piper/install.ps1 downloads piper.exe + ru_RU-irina-medium.onnx
    from rhasspy releases + huggingface. Smoke-test included.
  - tools/silero/silero_tts.py helper (PyTorch); rust spawns it as subprocess.

IMBA-1 Agentic LLM router
  - crates/jarvis-app/src/llm_router.rs
  - When fuzzy/intent matcher fails, LLM picks the closest command from the
    full registry. Returns JSON {command_id, confidence, reason}.
  - Threshold-gated re-dispatch via substitute phrase. JARVIS_LLM_ROUTER=1
    enables; JARVIS_LLM_ROUTER_THRESHOLD overrides 0.55 default.
  - Inserted in app.rs::execute_command between "no match" and existing
    llm_fallback chat fallback.

IMBA-2 Long-term memory
  - crates/jarvis-core/src/long_term_memory.rs — JSON store at
    APP_CONFIG_DIR/long_term_memory.json. Atomic write-through.
  - remember/recall/search/forget/all/build_context API.
  - Lua bindings: jarvis.memory.* (5 functions).
  - llm_fallback auto-injects relevant facts (substring search of prompt)
    into system message before LLM call.
  - Pack resources/commands/memory_pack/ with 4 commands: remember, recall,
    forget, list.

IMBA-3 Profile switching (work/game/sleep/driving/default)
  - crates/jarvis-core/src/profiles.rs — JSON profiles at APP_CONFIG_DIR/profiles/
    Auto-seeds 5 defaults on first run with personality + allow/deny lists +
    greetings + emoji icons.
  - active_profile.txt persists choice across restart.
  - Lua bindings: jarvis.profile.{active,set,list,allows,active_name}.
  - llm_fallback prepends profile personality to system prompt.
  - Pack resources/commands/profile_switch/ with 6 voice triggers.

IMBA-4 Multimodal screenshot + vision LLM
  - crates/jarvis-core/src/lua/api/vision.rs — gated on HTTP sandbox.
  - jarvis.vision.screenshot() captures via PowerShell System.Drawing.
  - jarvis.vision.describe(prompt?) sends base64 PNG to Groq vision model
    (default llama-3.2-11b-vision-preview, override via GROQ_VISION_MODEL).
  - Pack resources/commands/vision/ with 2 commands: describe + read_error.

P0.2 Continuous conversation grace window
  - config::CONVERSATION_GRACE_MS = 30_000.
  - app.rs: after command result, if grace_ms > 0 keep listening WITHOUT
    re-wake for the grace duration. Existing CMS_WAIT_DELAY back-dated so
    the existing timeout fires at start + grace_ms.

Tests: 24/24 jarvis-core unit tests pass (including 5 text_utils).
Build: cargo build --release -p jarvis-app and -p jarvis-gui both succeed
on Windows MSVC (VS 2026 Enterprise vcvars64).

Notes for setup:
  - Piper voice install: pwsh tools/piper/install.ps1 (downloads ~90 MB).
  - GROQ_TOKEN needed for IMBA-1 (router) and IMBA-4 (vision).
  - All features are opt-in via env vars or auto-detect; existing SAPI +
    fuzzy match path remains the default.

crates/jarvis-app/src/llm_fallback.rs

@@ -5,6 +5,9 @@ use jarvis_core::config;
 use jarvis_core::i18n;
 use jarvis_core::ipc::{self, IpcEvent};
 use jarvis_core::llm::{ChatMessage, ConversationHistory, LlmClient};
+use jarvis_core::long_term_memory;
+use jarvis_core::profiles;
+use jarvis_core::tts::{self, SpeakOpts};
 use jarvis_core::voices;
 
 struct State {
@@ -90,7 +93,27 @@ pub fn handle(prompt: &str) {
     let snapshot: Vec<ChatMessage> = {
         let mut h = state.history.lock();
         h.push_user(prompt);
-        h.snapshot()
+        let mut snap = h.snapshot();
+
+        // Inject (a) profile personality (b) relevant long-term memory as a fresh
+        // system message right after the base prompt. Both are optional.
+        let profile = profiles::active();
+        let mut overlay = String::new();
+        if !profile.llm_personality.is_empty() {
+            overlay.push_str(&format!("Активный профиль: {} {}\nХарактер для ответа: {}\n",
+                profile.icon, profile.name, profile.llm_personality));
+        }
+        let mem_ctx = long_term_memory::build_context(prompt, 5);
+        if !mem_ctx.is_empty() {
+            overlay.push_str(&mem_ctx);
+        }
+        if !overlay.is_empty() {
+            // Insert after the base system prompt (index 0 typically), before user msgs.
+            let insert_at = if !snap.is_empty() && snap[0].role == "system" { 1 } else { 0 };
+            snap.insert(insert_at, ChatMessage::system(overlay));
+        }
+
+        snap
     };
 
     match state.client.complete(&snapshot, state.max_tokens) {
@@ -100,7 +123,7 @@ pub fn handle(prompt: &str) {
             state.history.lock().push_assistant(reply.clone());
             ipc::send(IpcEvent::LlmReply { text: reply.clone() });
             voices::play_ok();
-            speak_via_sapi(&reply);
+            speak_reply(&reply);
         }
         Err(e) => {
             error!("LLM request failed: {}", e);
@@ -108,41 +131,14 @@ pub fn handle(prompt: &str) {
             let err_text = config::LLM_FALLBACK_ERROR_RU.to_string();
             ipc::send(IpcEvent::LlmReply { text: err_text.clone() });
             voices::play_error();
-            speak_via_sapi(&err_text);
+            speak_reply(&err_text);
         }
     }
 }
 
-#[cfg(target_os = "windows")]
-fn speak_via_sapi(text: &str) {
+fn speak_reply(text: &str) {
     if std::env::var("JARVIS_LLM_TTS").as_deref() == Ok("false") {
         return;
     }
-    let cleaned = jarvis_core::text_utils::sanitize_for_speech(text);
-    let escaped = cleaned.replace('\'', "''");
-    let ps = format!(
-        "Add-Type -AssemblyName System.Speech; \
-         $s = New-Object System.Speech.Synthesis.SpeechSynthesizer; \
-         foreach ($v in $s.GetInstalledVoices()) {{ \
-           if ($v.VoiceInfo.Culture.TwoLetterISOLanguageName -eq 'ru') {{ \
-             try {{ $s.SelectVoice($v.VoiceInfo.Name); break }} catch {{ }} \
-           }} \
-         }} \
-         $s.Speak('{}')",
-        escaped,
-    );
-    match std::process::Command::new("powershell")
-        .args(["-NoProfile", "-Command", &ps])
-        .stdout(std::process::Stdio::null())
-        .stderr(std::process::Stdio::null())
-        .spawn()
-    {
-        Ok(_) => {}
-        Err(e) => warn!("SAPI spawn failed: {}", e),
-    }
-}
-
-#[cfg(not(target_os = "windows"))]
-fn speak_via_sapi(_text: &str) {
-    // No-op on non-Windows; LLM reply still arrives via IPC for the GUI to render.
+    tts::speak(text, &SpeakOpts::lang("ru"));
 }