feat: Ollama LLM backend + 5 utility packs (daily briefing, pomodoro, currency convert, stocks, habits, translate clipboard)

Local-LLM support so J.A.R.V.I.S. works offline without GROQ_TOKEN.

LLM multi-backend (crates/jarvis-core/src/llm/client.rs)
  - LlmBackend enum {Groq, Ollama}. Both use OpenAI-compatible /v1/chat/completions
    (Ollama exposes one natively at :11434/v1).
  - LlmClient::from_env() now dispatches on JARVIS_LLM=groq|ollama. Auto-detect:
    Groq if GROQ_TOKEN set, else Ollama.
  - New helpers: LlmClient::groq() (was: from_env), LlmClient::ollama().
  - Reqwest client now has a 60s timeout (was: unbounded — Groq freezes could hang).
  - api_key skipped when empty (Ollama doesn't need auth).
  - Defaults: OLLAMA_BASE_URL=http://localhost:11434/v1, OLLAMA_MODEL=qwen2.5:3b.
    Override via OLLAMA_BASE_URL / OLLAMA_MODEL env.
  - llm_fallback + llm_router log the active backend on init.
  - Tests: 32/32 pass. Renamed `from_env_fails` → `groq_fails_when_token_missing`,
    added `ollama_works_without_token`.

Daily briefing pack (resources/commands/daily_briefing/, 3 commands)
  - setup.lua: "настрой утренний брифинг на 9:00" → adds a daily scheduled task
    that runs now.lua via the scheduler's Lua-action support.
  - now.lua: greeting + time + active profile + scheduled task count + memory recap
    + LLM motivational nudge. Voice-triggered ("утренний брифинг") works the same.
  - off.lua: removes the scheduled task.

Pomodoro pack (resources/commands/pomodoro/, 2 commands)
  - start.lua / stop.lua + tick.lua (re-scheduled by itself). State stored in
    jarvis.state — phase alternates work (25 min) / break (5 min) until stop.

Currency conversion (resources/commands/currency/convert.lua)
  - "сколько будет 1000 долларов в рублях" — fetches CBR daily rates from
    cbr-xml-daily.ru, normalises by Nominal, prints both directions.
  - Recognises USD/EUR/CNY/GBP/JPY/RUB by substring. Pluralises russian units.

Stocks pack (resources/commands/stocks/, 1 command)
  - "сколько Сбер" → MOEX ISS /iss/engines/stock/markets/shares/securities/<TKR>.
  - Mapping of 22 popular Russian tickers to common names (Сбер→SBER, Газпром→GAZP,
    Лукойл→LKOH, Яндекс→YDEX, Т-банк→T, etc).
  - Picks TQBR (main board) row, reports LAST + LASTTOPREVPRICE%.

Habit nudges (resources/commands/habit_nudge/, 4 commands)
  - "напоминай мне пить воду"     → every 2 hours
  - "напоминай мне размяться"     → every 50 minutes
  - "напоминай отдыхать глазам"  → every 20 minutes (20-20-20 rule)
  - "отключи все привычки"        → stops all three by id.

Translate clipboard (resources/commands/translate/clipboard.lua)
  - "переведи буфер на английский" → grabs clipboard, sends to LLM, speaks first
    sentence, replaces clipboard with full translation, fires notification.

Build: cargo build --release -p jarvis-app -p jarvis-gui both green. 32/32 tests.

To use Ollama:
  1. Install + run Ollama (https://ollama.com).
  2. `ollama pull qwen2.5:3b` (or any chat model).
  3. Optional: `set JARVIS_LLM=ollama` (auto-picked if GROQ_TOKEN unset).

crates/jarvis-app/src/llm_fallback.rs

@@ -31,7 +31,7 @@ fn build_state() -> Option<State> {
     let client = match LlmClient::from_env() {
         Ok(c) => c,
         Err(e) => {
-            warn!("LLM fallback disabled: {}. Set GROQ_TOKEN to enable.", e);
+            warn!("LLM fallback disabled: {}. Set GROQ_TOKEN or run Ollama to enable.", e);
             return None;
         }
     };
@@ -40,7 +40,7 @@ fn build_state() -> Option<State> {
     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());
+    info!("LLM fallback enabled (backend: {}, model: {}).", client.backend().name(), client.model());
     Some(State {
         client,
         history,