J.A.R.V.I.S-rust/crates/jarvis-core/src/llm/mod.rs

67 lines
2.4 KiB
Rust
Raw Normal View History

mod client;
mod history;
pub use client::{
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
ChatMessage, ConfigError, LlmBackend, LlmClient, LlmError,
DEFAULT_BASE_URL, DEFAULT_MODEL, ENV_BASE_URL, ENV_MODEL, ENV_TOKEN,
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
OLLAMA_DEFAULT_BASE_URL, OLLAMA_DEFAULT_MODEL,
};
pub use history::ConversationHistory;
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
use once_cell::sync::Lazy;
use parking_lot::RwLock;
use std::sync::Arc;
/// Shared mutable LLM client. Modules read via `current()`; the user can
/// hot-swap backends at runtime via `swap_to(LlmBackend::Ollama)` etc.
///
/// `None` means LLM is disabled (no GROQ_TOKEN and no Ollama reachable, or
/// `init_global()` was never called).
static GLOBAL: Lazy<RwLock<Option<Arc<LlmClient>>>> = Lazy::new(|| RwLock::new(None));
/// Initialise the global client from env vars (`JARVIS_LLM`, `GROQ_TOKEN`, ...).
/// Idempotent — replaces any previous global. Returns Ok even when the chosen
/// backend can't be probed: an Ollama server may not be running yet but we
/// stash the client anyway and let calls fail on first request.
pub fn init_global() -> Result<(), ConfigError> {
let c = LlmClient::from_env()?;
log::info!("LLM global initialised: backend={}, model={}", c.backend().name(), c.model());
*GLOBAL.write() = Some(Arc::new(c));
Ok(())
}
/// Return a clone of the active client. Cheap (Arc).
pub fn current() -> Option<Arc<LlmClient>> {
GLOBAL.read().clone()
}
/// Name of the currently active backend, or "none" if not initialised.
pub fn current_backend_name() -> &'static str {
match GLOBAL.read().as_ref().map(|c| c.backend()) {
Some(LlmBackend::Groq) => "groq",
Some(LlmBackend::Ollama) => "ollama",
None => "none",
}
}
/// Hot-swap to a different backend. Returns the new backend's name on success.
pub fn swap_to(backend: LlmBackend) -> Result<&'static str, ConfigError> {
let c = match backend {
LlmBackend::Groq => LlmClient::groq()?,
LlmBackend::Ollama => LlmClient::ollama(),
};
let name = c.backend().name();
log::info!("LLM swapped → backend={}, model={}", name, c.model());
*GLOBAL.write() = Some(Arc::new(c));
Ok(name)
}
/// Parse a backend name (case-insensitive) into the enum.
pub fn parse_backend(name: &str) -> Option<LlmBackend> {
match name.trim().to_lowercase().as_str() {
"groq" | "cloud" | "облако" | "клауд" => Some(LlmBackend::Groq),
"ollama" | "local" | "локал" | "локальн" | "локальный" => Some(LlmBackend::Ollama),
_ => None,
}
}