J.A.R.V.I.S-rust/resources/commands/codebase_qa/command.toml

62 lines
1.6 KiB
TOML
Raw Normal View History

feat: hot-swap LLM backend + media keys + codebase Q&A + scheduler cancel-by-text + TTS pre-warm Single biggest user-facing change: you can now switch local↔cloud LLM by voice without restarting. Plus four new packs and a perf nudge. Shared LLM global (crates/jarvis-core/src/llm/mod.rs) - GLOBAL: Lazy<RwLock<Option<Arc<LlmClient>>>>. Single source of truth. - init_global() / current() / swap_to(LlmBackend) / current_backend_name() / parse_backend(str). - llm_fallback + llm_router migrated: they no longer own a separate LlmClient, they read from the global on each request. Hot-swap is now LIVE — change backend, next chat call uses the new one. - parse_backend accepts both english and russian aliases: "groq"/"cloud"/"облако"/"клауд" → Groq "ollama"/"local"/"локал"/"локальный" → Ollama Voice + Lua LLM switcher (resources/commands/llm_switch/, 3 commands) - "переключись на локальный" / "перейди на оллама" → swap to Ollama - "переключись на облако" / "используй грок" → swap to Groq - "какой у тебя мозг" / "облако или локально" → status query Underlying Lua API (registered globally): jarvis.llm({messages}, opts) -- as before, now uses global client jarvis.llm_status() -> "groq" | "ollama" | "none" jarvis.llm_switch(name) -> name on success, nil on failure Media keys pack (resources/commands/media_keys/, 4 commands) - "пауза" / "плей" → VK_MEDIA_PLAY_PAUSE - "следующий трек" → VK_MEDIA_NEXT_TRACK - "предыдущий трек" → VK_MEDIA_PREV_TRACK - "стоп музыка" → VK_MEDIA_STOP - Helper _media.ps1 uses user32.keybd_event (P/Invoke through Add-Type). - Works with anything that listens to global media keys: Spotify, Yandex Music, YouTube (focused tab), Foobar2000, Winamp, etc. No OAuth, no API keys. Codebase Q&A pack (resources/commands/codebase_qa/, 3 commands) - "укажи проект <path>" → stores path in jarvis.memory under codebase.root - "какой проект сейчас" → speaks current path - "что делает функция X" / "найди в коде Y" / "объясни код" → walks the folder (depth 3, 30 files cap, 4KB per file, 50KB total), filters by source extensions (rs/py/ts/lua/go/...), feeds digest to LLM with a "senior reviewer" system prompt, speaks 3-5 sentence answer. Scheduler cancel-by-text (crates/jarvis-core/src/scheduler.rs) - new pub fn find_by_text(query, limit) -> Vec<ScheduledTask> - new pub fn remove_by_text(query) -> usize (count removed) - new pure helper find_by_text_in(tasks, query, limit) for tests - Lua: jarvis.scheduler.{find_by_text, remove_by_text} - Voice: "отмени напоминание про воду" / "удали задачу про разминку" - 3 new unit tests (52 total in jarvis-core). TTS pre-warm (crates/jarvis-app/src/main.rs) - Call jarvis_core::tts::backend() once on startup so the first speak() doesn't pay Piper binary discovery + voice loading cost. Cuts first-speak latency by ~150-300ms depending on backend. Build: cargo build --release -p jarvis-app -p jarvis-gui both green. Tests: 52/52 jarvis-core unit tests pass.
2026-05-15 16:15:59 +03:00
# Codebase Q&A — point J.A.R.V.I.S. at a folder, ask questions about the code.
# Active folder stored via jarvis.memory (key="codebase.root"). Voice commands let
# you swap the folder, list it, and ask questions. The script reads files lazily
# (depth-limited, size-capped) and feeds a digest to the LLM.
[[commands]]
id = "codebase.set"
type = "lua"
script = "set.lua"
sandbox = "full"
timeout = 5000
[commands.phrases]
ru = [
"укажи проект",
"укажи папку проекта",
"укажи кодовую базу",
"выбери проект",
"проект сейчас",
]
en = ["set codebase", "set project folder", "use project"]
ua = ["вкажи проект", "вкажи папку проекту"]
[[commands]]
id = "codebase.ask"
type = "lua"
script = "ask.lua"
sandbox = "full"
timeout = 60000
[commands.phrases]
ru = [
"спроси код",
"вопрос по коду",
"что в коде",
"что делает функция",
"найди в коде",
"найди в проекте",
"объясни код",
]
en = ["ask the code", "ask the codebase", "what does the function", "explain the code"]
ua = ["що в коді", "що робить функція"]
[[commands]]
id = "codebase.where"
type = "lua"
script = "where.lua"
sandbox = "full"
timeout = 3000
[commands.phrases]
ru = [
"какой проект сейчас",
"где проект",
"какая папка проекта",
"какая кодовая база",
]
en = ["which project", "what's the codebase"]
ua = ["який проект"]