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/llm_context/command.toml

@@ -0,0 +1,39 @@
+# P0.3: Conversation context controls — reset / repeat last reply.
+
+[[commands]]
+id = "llm.reset"
+type = "lua"
+script = "reset.lua"
+sandbox = "standard"
+timeout = 2000
+
+[commands.phrases]
+ru = [
+    "сбрось контекст",
+    "сбрось разговор",
+    "забудь о чём мы говорили",
+    "забудь разговор",
+    "начни разговор заново",
+    "очисти контекст",
+]
+en = ["reset context", "forget conversation", "start fresh"]
+ua = ["скинь контекст", "забудь розмову"]
+
+
+[[commands]]
+id = "llm.repeat"
+type = "lua"
+script = "repeat.lua"
+sandbox = "standard"
+timeout = 5000
+
+[commands.phrases]
+ru = [
+    "повтори последнее",
+    "повтори что сказал",
+    "повтори ответ",
+    "что ты сказал",
+    "повтори",
+]
+en = ["repeat", "say it again", "repeat the last answer"]
+ua = ["повтори", "повтори що сказав"]

resources/commands/llm_context/repeat.lua

@@ -0,0 +1,5 @@
+local last = jarvis.llm_last_reply()
+if not last or last == "" then
+    return jarvis.cmd.not_found("Мне нечего повторить.")
+end
+return jarvis.cmd.ok(last)

resources/commands/llm_context/reset.lua

@@ -0,0 +1,2 @@
+jarvis.llm_reset()
+return jarvis.cmd.ok("Контекст сброшен.")