Commit graph

2 commits

Author SHA1 Message Date
Bossiara13
df799b6cd2 feat: Wave 5 — sysinfo speaks, smart reminders, outlook COM, time tracker, WOL, conversation tools
Some checks are pending
Rust CI / cargo test (jarvis-core) (push) Waiting to run
Rust CI / cargo clippy (push) Waiting to run
Rust CI / cargo check (workspace) (push) Waiting to run
Voice sysinfo overhaul (6 scripts: battery/cpu/ram/disk/time/all):
- Now SPEAK the result via jarvis.cmd.ok instead of notify-only. Toast
  still fires for visual reference, but real Jarvis tells you out loud.
- `all` joins lines with commas so TTS doesn't over-pause on linebreaks.

Smart reminders (`reminders/set.lua` rewrite):
- Was: detached `Start-Sleep` PowerShell subprocesses that died on
  jarvis-app restart and spawned a hidden process per timer.
- Now: routes through `jarvis.scheduler.add(... type=speak ...)`. Persists
  to schedule.json, survives restart, no zombie processes. Trade-off:
  sub-minute timers round up to 1 min (rare in voice UX).
- Drops UA triggers from earlier UA-removal sweep.

Translation polish (`translate/translate.lua` + `clipboard.lua`):
- Drops UA target language; adds Italian, Polish, Turkish, French ru
  triggers + English target detectors.
- `language_iso()` helper picks the SAPI voice locale for the TARGET
  language (German translation → German SAPI voice if installed).

LLM system prompt (config.rs):
- New LLM_SYSTEM_PROMPT_EN counterpart. Both languages now mention the
  assistant's tooling (memory / scheduler / profiles / macros / vision /
  clipboard) so the LLM knows it can DO things, not suggest the user
  install something.
- `get_llm_system_prompt(lang)` picks EN/RU.

Conversation pack (NEW `conversation/`):
- 2 commands. `conversation.summary` ("о чём мы говорили") pulls the
  last 12 turns from persisted history, asks LLM for a 1-3 sentence
  recap in Jarvis tone. Falls back gracefully when offline.
- `conversation.repeat` ("повтори") re-speaks the last assistant message.
- New Lua API `jarvis.llm_history()` returns array of {role, content}
  tables, excluding the system prompt.

WOL pack (NEW `wol/`):
- Voice "разбуди сервер" / "wake server" fires a magic packet at a MAC
  stored in long-term memory under `wol_<alias>` (default alias "server").
- Setup via voice: "запомни wol_server AA:BB:CC:DD:EE:FF". Falls back to
  `JARVIS_WOL_TARGET` env if memory empty. Handles every standard MAC
  format (colons / dashes / dots / bare). Broadcast on UDP 9 via
  PowerShell System.Net.Sockets.UdpClient.

Outlook COM pack (NEW `outlook/`, via subagent):
- 4 commands: unread_count, latest, send_clipboard, summarize_inbox.
- PowerShell COM bridge `_outlook.ps1` with tab-delimited line protocol.
- summarize_inbox calls LLM for a one-paragraph summary. Graceful
  failure when Outlook isn't running.

Time tracker pack (NEW `time_tracker/`, via subagent):
- 5 commands: start, stop, today, week, reset.
- Persists via `jarvis.state` (structured object: current_session_start
  + sessions array of {start, end}).
- Local-calendar "today" boundary, full Russian pluralisation
  (час/часа/часов, минута/минуты/минут, сессия/сессии/сессий).

Tests: 139 rust (no regression), 81 python (60 → 81, +14 time_tracker
+7 outlook). Release build green for jarvis-app and jarvis-cli.

Pack count: 88 → 92 rust packs.
2026-05-16 14:34:29 +03:00
Bossiara13
45243c3e3c 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).
2026-05-15 15:51:24 +03:00