feat: persist LLM/TTS backend choice + reset/repeat context + quick-search + diagnostics

Closes the UX hole I created in 5c72450: voice-swap to Ollama used to vanish
after restart. Plus P0.3 (long-standing roadmap item) and two new packs.

Persistent backend choice (crates/jarvis-core/src/db/structs.rs)
  - Settings struct gains llm_backend + tts_backend fields (both String,
    "" / "auto" = follow env/auto-detect).
  - set("llm_backend", "groq"|"ollama"|"auto") validates input.
  - llm::init_global() reads DB first, then JARVIS_LLM env, then auto-detect.
  - llm::swap_to() now persists the choice via db::save_settings.
  - Voice swap "переключись на локальный" now survives restart.

Shared conversation history (P0.3, crates/jarvis-core/src/llm/mod.rs)
  - HISTORY: Lazy<RwLock<Option<ConversationHistory>>> singleton.
  - Helpers: init_history, history_push_user, history_push_assistant,
    history_snapshot, history_clear, history_pop_last_user, history_last_assistant.
  - llm_fallback migrated off its own Mutex<History> — now reads/writes shared.
  - ConversationHistory gains last_assistant() method.

New Lua APIs
  - jarvis.llm_reset()        → clear conversation turns (keeps system prompt).
  - jarvis.llm_last_reply()   → string or nil (last assistant message text).
  - jarvis.health()           → debug table {tts_backend, llm_backend, llm_model,
                                  active_profile, memory_facts, scheduled_tasks,
                                  language, voice, microphone, vosk_model,
                                  noise_suppression}. No secrets included.

New voice packs
  - resources/commands/llm_context/   (P0.3)
    * "сбрось контекст" / "забудь разговор"     → llm.reset
    * "повтори последнее" / "повтори ответ"     → llm.repeat (uses last_assistant)
  - resources/commands/quick_search/   (imba P1 item)
    * "найди в гугле <X>" / "загугли <X>"
    * Uses DuckDuckGo Instant Answer API (api.duckduckgo.com, no key required).
      Pulls AbstractText or RelatedTopics into LLM prompt; falls back to pure
      LLM knowledge if DDG returns nothing useful. Speaks 2-4 sentence answer.
  - resources/commands/diagnostics/
    * "диагностика" / "доложи о себе" / "статус"
    * Reads jarvis.health() and speaks a one-line summary. Useful when
      debugging — user can read out their current state for a bug report.

Build: cargo build --release -p jarvis-app -p jarvis-gui green.
Tests: 52/52 jarvis-core unit tests pass.

resources/commands/diagnostics/command.toml

@@ -0,0 +1,21 @@
+# Diagnostics — speak a summary of the active runtime state. Useful when
+# something is misbehaving and you want to know which backends are active.
+
+[[commands]]
+id = "diagnostics.health"
+type = "lua"
+script = "health.lua"
+sandbox = "standard"
+timeout = 3000
+
+[commands.phrases]
+ru = [
+    "диагностика",
+    "состояние системы",
+    "статус",
+    "что у тебя сейчас",
+    "проверка системы",
+    "доложи о себе",
+]
+en = ["diagnostics", "status report", "health check"]
+ua = ["діагностика", "стан системи"]

resources/commands/diagnostics/health.lua

@@ -0,0 +1,11 @@
+local h = jarvis.health()
+local line = string.format(
+    "TTS: %s. LLM: %s. Профиль: %s. Памяти фактов: %d. Запланировано: %d. Язык: %s.",
+    h.tts_backend or "—",
+    h.llm_backend or "—",
+    h.active_profile or "—",
+    h.memory_facts or 0,
+    h.scheduled_tasks or 0,
+    h.language or "—"
+)
+return jarvis.cmd.ok(line)