Commit graph

90 commits

Author SHA1 Message Date
Bossiara13
59a1258dcc feat: Wave 3 — plugin loader + Flet GUI (parity with Rust fork)
Plugin loader (mirrors Rust #29):
- plugins_store.py walks %APPDATA%\com.priler.jarvis\plugins\<name>\
  for commands.yaml fragments and merges them into VA_CMD_LIST at
  startup. Same schema as the project root commands.yaml. Per-pack
  `disabled` flag file skips a pack without deletion. Built-in ids
  win conflicts so a malicious pack can't silently override
  open_browser. 9 unit tests (parity with the Rust tests).
- main.py: plugin merge runs after the root yaml load; logs the
  number of extra commands picked up.

Flet GUI (#27 — first parity with the Rust Tauri GUI):
- New gui/ package: __main__.py launches via `python -m gui` (or
  gui.bat). app.py routes between 7 pages (Главная / Команды /
  Макросы / Расписание / Память / Плагины / Настройки) via
  NavigationRail; dark theme matching the Tauri look.
- gui/services.py centralises every store-module call the pages
  share — single place to swap implementations later.
- One file per page in gui/pages/, all expose `build(page)` and use
  the same card layout idiom. Pages mirror the Tauri ones feature-
  for-feature: home (status + counters + launcher), commands
  (filterable list of all VA_CMD_LIST entries), macros (list +
  delete + recording banner), scheduler (list + remove), memory
  (add/forget/search), plugins (toggle/open folder), settings
  (profile + LLM hot-swap).
- requirements.txt: flet>=0.85 (optional; assistant runs without).
- 3 smoke tests verify imports + build callables; skip cleanly when
  Flet isn't installed.

README: documents both the GUI and the plugin layout in user-facing
terms. Tests: 42 → 54 (+9 plugins +3 GUI smoke).
2026-05-16 13:27:04 +03:00
Bossiara13
2bef1d5ea7 feat: Wave 1 python parity — 20 new commands (154 → 174)
Mirrors all 10 packs from rust commit c4b2261 to python.

wave1_handlers.py (new, ~480 lines)
  Self-contained module with 20 handlers + DPAPI helpers + http/ps wrappers.
  Imports memory_store for state-backed packs (vault, clip, habit, rss, weather).

  Coverage:
    do_magic_8ball         — 15 random answers
    do_github_list_issues  — gh issue list (uses memory[github.repo])
    do_github_my_issues    — gh issue list --assignee @me
    do_weather_tomorrow    — Open-Meteo + ipinfo auto-detect
    do_weather_week        — 7-day forecast min/max range
    do_rss_add/read/list   — RSS subscriptions + parse <title> tags
    do_ics_create          — write .ics, open via os.startfile
    do_backup_export       — zipfile of long_term_memory.json + schedule + macros
                              + profiles/ + active_profile + llm_backend + settings
                              (searches script_dir + %APPDATA%/Jarvis)
    do_clip_save/list/restore — 20-slot rolling clipboard history in memory
    do_notif_missed/clear  — enumerate memory[notif.*] / purge
    do_vault_save/get/list — DPAPI encrypt via PowerShell, clears clipboard
                              after 30 sec via threading.Thread
    do_habit_checkin/streak — date-keyed memory state, consecutive-day counter

extensions.py: +20 proxy functions + wave1_handlers import + set_speak wiring.

main.py: +20 dispatch entries.

commands.yaml: +20 entries (154 → 174).

Tests: ast.parse passes for all .py files. 42 pytest still green.
2026-05-16 01:08:17 +03:00
Bossiara13
4e62049a98 feat+test: pytest suite + Now Playing + World Clock + Daily Quote packs (154 commands)
Adds first formal test suite for Python fork — 42 tests covering memory_store,
profiles_store, scheduler_store, macros_store, llm_backend. All pass.

Tests (tests/, ~290 lines)
  conftest.py — `isolated_state` fixture: rewires _PATH/_PROFILES_DIR etc to
                a per-test tmp_path so concurrent runs don't touch real data.
  test_memory_store.py     — 9 tests: remember/recall/forget round-trip,
                              search by key/value, limit/empty query,
                              persistence across reload, build_llm_context
  test_profiles_store.py   — 7 tests: seeded defaults, set_active persistence,
                              allows_command logic (default/work/driving)
  test_scheduler_store.py  — 12 tests: parser (daily/at/every/in, ru units,
                              bad input), add/remove/clear/remove_by_text,
                              _next_fire for each schedule kind
  test_macros_store.py     — 8 tests: is_macro_control filter, start/save
                              round-trip, control-phrase filtering, list_names
                              sorted, replay unknown raises
  test_llm_backend.py      — 6 tests: parse_backend aliases (ru + en),
                              persist round-trip, auto-detect logic

Run: cd /c/Jarvis/python && python -m pytest tests/

Three new fun packs (commands.yaml: 151 → 154)

now_playing — Windows Media Session API via PowerShell
              "что играет" / "что за песня" / "какой трек"
              Works with Spotify, YouTube, Foobar, Yandex Music, anything
              that exposes SMTC (Win10 1803+).

world_clock — worldtimeapi.org (free, no key)
              "сколько времени в Токио" / "время в Лондоне"
              21 Russian + world cities pre-mapped to IANA timezones.

daily_quote — zenquotes.io (free, no key) + LLM translation
              "цитата дня" / "вдохнови меня"
              Fetches English quote, translates to Russian via active LLM
              (Groq or Ollama), speaks "text — author."

Pack count: 151 → 154. Tests: 42 pytest + ast.parse + yaml.safe_load.
2026-05-16 00:56:02 +03:00
Bossiara13
8d3da4ea06 feat: LLM hot-swap voice command + Ollama backend (148 → 151 commands)
Closes the last functional parity gap with rust. Python now has voice-driven
Ollama↔Groq switching, persistent across restarts.

llm_backend.py (new, ~130 lines)
  Singleton module:
    current_client()     → active OpenAI client (or None)
    current_backend()    → 'groq' | 'ollama' | 'none'
    current_model()      → active model name
    swap_to(name)        → hot-swap + persist to <here>/llm_backend.txt
    parse_backend(name)  → ru/en alias normaliser ('облако'→groq, 'локальный'→ollama)

  Backends:
    - Groq:   config.GROQ_TOKEN + GROQ_BASE_URL + GROQ_MODEL (defaults)
    - Ollama: OLLAMA_BASE_URL (default http://localhost:11434/v1) +
              OLLAMA_MODEL (default qwen2.5:3b). api_key='ollama' (placeholder,
              openai lib insists on a non-empty string; Ollama ignores it).

  Init precedence (idempotent _ensure_init):
    1. Persisted choice from llm_backend.txt
    2. JARVIS_LLM env var
    3. Auto-detect: Groq if token present, else Ollama

Voice commands (commands.yaml, +3 entries → 151)
  llm_switch_local  → ollama
  llm_switch_cloud  → groq
  llm_status        → speaks current backend

extensions.py
  + do_llm_switch / do_llm_status handlers
  + llm_backend import
  do_interesting_fact migrated off direct OpenAI(...) to use llm_backend.current_*

dev_handlers.py
  + llm_backend import
  do_codebase_ask + do_github_summarize_pr migrated to llm_backend.current_*

vision_handler.py
  Vision call documented as Groq-specific (Ollama doesn't expose vision via
  OpenAI-compat in our stack), kept direct config.GROQ_TOKEN reading.

Tests: ast.parse passes for all 5 modules. yaml.safe_load = 151 entries.

PYTHON PARITY VS RUST IS NOW FUNCTIONALLY COMPLETE.
Only remaining rust-only feature: the Tauri GUI (python is console-only).
2026-05-16 00:44:42 +03:00
Bossiara13
31ff997782 feat: codebase_qa + github_pr in Python (142 → 148 commands)
Closes the Python parity gap with rust. All major imba features now mirrored
EXCEPT live LLM hot-swap (python LLM backend is still env-driven, not voice-
switchable like rust).

dev_handlers.py (new, ~250 lines)
  Codebase Q&A:
    do_codebase_set        "укажи проект C:\path" → memory_store.remember("codebase.root", ...)
    do_codebase_where      "какой проект сейчас"
    do_codebase_ask        "что делает функция X" / "найди в коде Y"
                           Walks the root with same caps as rust:
                             depth=3, files=30, file_bytes=4096, total=50000
                           Filters by extension (rs/py/ts/lua/go/...).
                           Skips .git/target/node_modules/__pycache__/.venv etc.
                           Feeds digest to Groq LLM with "senior reviewer" prompt.

  GitHub PR review (requires `gh` CLI authenticated):
    do_github_set_repo     "текущий репо owner/repo" → memory_store
    do_github_list_prs     "какие пиары" → `gh pr list --json number,title,author`,
                           speaks count + first 3 titles
    do_github_summarize_pr "разбери последний пиар" → gh pr view of latest open
                           PR, feeds title+body+diff stat to LLM, speaks 3-5
                           sentence review.

extensions.py — 6 new proxy handlers + import dev_handlers + set_speak wires it.

main.py — 6 new action_type dispatches in run_action.

commands.yaml (+6 entries, 142 → 148):
  codebase_set, codebase_where, codebase_ask,
  github_set_repo, github_list_prs, github_summarize_pr.

Tests: ast.parse passes for all .py files. yaml.safe_load = 148 entries.

PYTHON PARITY VS RUST IS NOW COMPLETE except:
  ✗ LLM hot-swap voice command (rust calls llm::swap_to + persists DB;
    python config.GROQ_TOKEN is read once at startup)
  ✗ GUI pages (rust has Tauri+Svelte, python is console-only)

Everything else has full parity: memory / profiles / vision / macros /
scheduler / codebase Q&A / GitHub PR review / 14 utility packs.
2026-05-16 00:40:08 +03:00
Bossiara13
6a328077bc feat: vision + macros + scheduler in Python (129 → 142 commands)
Three big rust packs ported. Python parity now covers the FULL imba lineup
except codebase_qa and github_pr.

vision_handler.py (new, ~125 lines)
  - Screenshot via PowerShell System.Drawing → temp PNG → base64 → Groq
    vision API (llama-3.2-11b-vision-preview, override via GROQ_VISION_MODEL).
  - do_vision_describe   "что на экране" / "опиши экран"
  - do_vision_read_error "прочитай ошибку"
  - Requires GROQ_TOKEN; speaks "Не удалось" on missing.

macros_store.py (new, ~170 lines)
  - JSON store at <here>/macros.json (atomic write-through).
  - start(name) / save() / cancel() / replay(name, dispatch_fn)
  - is_recording / recording_name / list_names / get / delete
  - record_step(phrase) called by execute_cmd hook (see main.py)
  - is_macro_control filter blocks "запиши макрос ..." from recording itself
    (no infinite recursion).
  - replay spawns daemon thread, fires each step with 800ms delay.

scheduler_store.py (new, ~220 lines)
  - JSON store at <here>/schedule.json.
  - parse_schedule(spec) handles "daily HH:MM", "at HH:MM",
    "every/in N minutes|hours|seconds" — Russian (минут/час/секунд) + English.
  - Background daemon thread ticks every 30s, fires Speak actions through the
    same speak callback used by main.py.
  - Once-tasks auto-delete after firing; daily/interval cycle forever.
  - add/remove/clear/remove_by_text/list_all.

extensions.py (+13 handlers)
  do_vision_describe / do_vision_read_error → thin proxies to vision_handler
  do_macros_start / save / cancel / replay / list / delete
  do_scheduler_add_reminder / add_recurring / list / clear / cancel_by_text

main.py
  - extensions.init_background_services() at startup → scheduler thread boots.
  - Wraps execute_cmd so every successful dispatch feeds macros_store.record_step.
  - set_dispatch_fn(_execute_phrase_for_macro) enables macro replay through the
    normal command pipeline (recognize_cmd → execute_cmd).

commands.yaml (+13 entries, 129 → 142)
  vision_describe, vision_read_error, macros_start, macros_save, macros_cancel,
  macros_replay, macros_list, macros_delete, scheduler_reminder,
  scheduler_recurring, scheduler_list, scheduler_clear, scheduler_cancel_text.

Tests: ast.parse passes for all five .py files. yaml.safe_load = 142 entries.

Python parity status vs rust (72 packs):
  ✓ memory_pack, profile_switch, vision, scheduler, macros, llm switch
    (via env), llm_context (basic), media_keys (existing), screenshot, net_info,
    unit_convert, generators, disk, date_math, sleep_timer (via shutdown),
    interesting_fact, mailto, self_check, ssl_check, intro/echo
  ✗ codebase_qa, github_pr (require gh CLI + file walk — TODO)
  ✗ pomodoro / daily_briefing / habit_nudge / quick_search / diagnostics
    (could be ported but need scheduler integration + LLM glue)
2026-05-16 00:00:22 +03:00
Bossiara13
02c6f2f90d feat: memory_store + profiles_store + 10 new yaml entries (119 → 129)
Mirrors `long_term_memory` and `profiles` modules from rust fork.

memory_store.py (new, ~95 lines)
  - JSON store at <here>/long_term_memory.json (atomic write).
  - remember(key, value) / recall(key) / forget(key) / search(query, limit) /
    all_facts() / build_llm_context(prompt, limit).
  - Uses the same JSON shape as the rust side, so the file is
    interoperable if you ever symlink the two installations to the same dir.

profiles_store.py (new, ~145 lines)
  - Profiles at <here>/profiles/<name>.json. active_profile.txt persists.
  - Seeds 5 defaults on first init: default ★, work 💼, game 🎮, sleep 🌙,
    driving 🚗 — same as rust fork.
  - active() / active_name() / set_active(name) / list_names() /
    allows_command(cmd_id).

extensions.py (+6 handlers, +160 lines)
  - do_memory_remember  — derives key (first 6 words or split on '=')
  - do_memory_recall    — substring search or top-3 if no query
  - do_memory_forget    — exact then substring fallback
  - do_memory_list      — count + first 5 keys
  - do_profile_set      — target via action.target or voice ("работа" → work)
  - do_profile_what     — speaks current profile + description

main.py
  - +6 dispatch entries for the new action types.

commands.yaml (+10 entries, 119 → 129)
  - memory_remember, memory_recall, memory_forget, memory_list
  - profile_work, profile_game, profile_sleep, profile_driving, profile_default
  - profile_what

Tests: ast.parse passes for all .py files. yaml.safe_load gives 129 entries.

Python parity is now meaningful: memory + profiles are usable by voice
without any rust install. Still missing for full parity: scheduler (needs
background thread), macros (needs phrase-capture state), vision (needs
Groq vision model call), codebase_qa, github_pr.
2026-05-15 23:54:33 +03:00
Bossiara13
f82427c7b6 feat: extensions module + 19 new commands (100 → 119)
Mirror of new packs from the rust fork. Self-contained `extensions.py` with
new do_* handlers, registered via 'set_speak' / 'set_clipboard_fn' callbacks
from main.py.

Wiring (main.py)
  - `import extensions` at top.
  - `extensions.set_speak(_speak)` + `extensions.set_clipboard_fn(_set_clipboard)`
    right after _set_clipboard is defined.
  - Added 15 new action-type dispatches in run_action.

extensions.py (new, ~360 lines)
  Action types:
    lock_workstation  → rundll32 user32.dll,LockWorkStation
    screenshot {mode} → clipboard via System.Windows.Forms.Clipboard.SetImage
                        OR file → ~/Pictures/Screenshots/jarvis-<ts>.png
    disk_free / disk_list → PowerShell Get-PSDrive
    coin_flip / uuid_gen / password_gen (length 6..64, copies to clipboard,
                        speaks length only — never echoes the password)
    ssl_check {domain} → PowerShell TCP+SslStream→X509Certificate2 expiry
    wifi_ssid → netsh wlan show interfaces parser (ru + en field names)
    public_ip → urllib request to api.ipify.org
    unit_convert {mode: length|weight|temperature|speed}
                  Russian-grammar pluralisation (фут/фута/футов).
    date_math {mode: days_until|day_of_week}
                  Recognises Новый год, Рождество, 8 марта, 9 мая + "до N <месяц>".
    echo_repeat / self_ping — debug commands
    interesting_fact → Groq LLM (requires GROQ_TOKEN)

commands.yaml — 19 new entries:
  lock_workstation, screenshot_clipboard, screenshot_file, disk_free, disk_list,
  coin_flip, password_gen, uuid_gen, ssl_check, wifi_ssid, public_ip,
  convert_length, convert_weight, convert_temperature, convert_speed,
  days_until, day_of_week, echo_repeat, self_ping, interesting_fact.

Tests: python syntax check + yaml.safe_load both pass. Total commands: 119.

NOT YET mirrored from rust (would require deeper rework):
  memory_pack / profile_switch / scheduler / macros / vision / codebase_qa
  / github_pr / llm_switch / llm_context / media_keys / mood_log / pomodoro
  / habit_nudge / daily_briefing / quick_search / diagnostics / sleep_timer
  / wikipedia (the rewritten one) / intro / mailto / generators (UUID, coin,
  password ARE included — others can follow).

The reason these weren't mirrored: they need new state files
(memory.json, profiles.json, schedule.json, macros.json) and background
threads (scheduler tick). Doable as a follow-up but out of scope here.
2026-05-15 23:51:13 +03:00
Bossiara13
ef8da9cba8 feat: parity — brightness, window switch, spelling, network, summarize (100 commands)
Mirrors the rust tier-3 batch. 90 → 100 commands (round number — feels
right for an "имба" milestone).

main.py:
+ do_brightness: WMI WmiMonitorBrightness read + WmiSetBrightness write,
  ±20% step or 100/10 absolute, "no_wmi" sentinel for desktops.
+ do_window_switch: same alias map as process_kill (xrom→chrome/...),
  PS finds process by name OR window-title substring, picks newest
  StartTime, AppActivate via WScript.Shell.
+ do_spell_out: split chars, join with ". ", _speak.
+ do_network_settings: action.section = wifi|bluetooth|network →
  matching ms-settings:* URI via cmd /c start "".
+ do_my_ip: Get-NetIPAddress filtered to non-loopback non-APIPA IPv4,
  WAN via Invoke-RestMethod ipify, speaks "Локальный X. Внешний Y".
+ do_summarize_selection: pyautogui.hotkey(ctrl, c) → 250ms wait →
  Get-Clipboard → Groq @ temp 0.3 ("3-5 sentence retell") → speak +
  clipboard.

commands.yaml +10 entries: brightness_up/down/max/min, switch_to_window,
spell_out, open_wifi_settings, open_bluetooth_settings, my_ip,
summarize_selection.

Backlog: closed all "Tier-3 still TODO" pure-Lua items. Remaining
TODOs (pomodoro, currency-math, stocks, translate-clipboard, daily
briefing, etc.) are even smaller LOC and can roll in the next batch.
2026-05-15 13:11:37 +03:00
Bossiara13
b3a5bcabe5 feat: parity — games, mouse, random_choice + new packs (90 commands)
Mirrors the rust feature/pc-tools work. yaml.safe_load + ast.parse pass.
82 → 90 commands (+8).

main.py:
+ do_launch_game / do_list_games: reads ~/Documents/jarvis-games.json
  (creates sample on first call with dota / cs2 / elden ring / witcher
  3 / factorio entries). Fuzzy name+alias match, launches via
  steam://rungameid/<appid> (webbrowser.open), epic_uri, or
  cmd /c start "" path.
+ do_mouse: action param op = left|right|middle|double|scroll_up|
  scroll_down. Embedded PowerShell P/Invokes user32!mouse_event with
  the right flag pairs.
+ do_random_choice: strips trigger, splits on " или " / " or " / ", " /
  " либо " / " чи ", picks one with random.choice.

commands.yaml +8 entries:
+ launch_game / list_games
+ mouse_left_click / mouse_right_click / mouse_double_click /
  mouse_scroll_up / mouse_scroll_down (all action:mouse, op:...)
+ random_choice
2026-05-15 12:58:32 +03:00
Bossiara13
40a46567b8 feat: parity — news, currency, crypto, fun, wiki, power, help (82 commands)
Mirrors the rust analog-inspired tier-2 packs. yaml + ast smoke pass.
56 → 82 commands (+26 yaml entries; 14 of them are power/fun/wiki/
news/etc. permutations).

main.py — 7 new action handlers, all built on stdlib urllib.request
(no new dep). Helper _http_get() with User-Agent header so RSS feeds
that 403 default UAs go through.

+ do_news: pulls RSS (default Lenta.ru), extracts <title> via regex,
  skips channel title (idx 0), takes 5, sends to Groq for a 2-3
  sentence summary at temp 0.4. Falls back to reading first 3
  headlines verbatim if no token.
+ do_currency_rate: cbr-xml-daily.ru daily_json.js. Recognises
  USD/EUR/CNY/GBP/JPY/KZT in the phrase, computes value/nominal,
  diffs against Previous, speaks Russian with direction.
+ do_crypto_price: CoinGecko simple/price for BTC/ETH/SOL/DOGE/TON
  with 24h change, picked by phrase keywords.
+ do_fun_ask: joke / fact / quote / compliment via Groq at temp 1.0
  with per-kind system prompts, random seed in user message.
+ do_wiki_lookup: ru.wikipedia opensearch → page summary, optional
  Groq retell when extract > 350 chars.
+ do_power: dispatch table for shutdown / restart / sleep /
  hibernate / logoff / cancel — runs shutdown.exe /s|/r|/h|/l|/a
  or rundll32 powrprof,SetSuspendState. 30-second grace on shutdown
  and restart with /c message so "отмени выключение" works.
+ do_help_commands: sorts VA_CMD_LIST.keys(), speaks first 12 + total,
  full list to clipboard.

commands.yaml +26 entries:
news_headlines, currency_rate, crypto_price, joke / fact / quote /
compliment (action:fun_ask, kind: ...), wiki_lookup, shutdown_pc /
restart_pc / sleep_pc / hibernate_pc / logoff_user / cancel_shutdown
(action:power, op: ...), help.

Inspired by what mainstream voice assistants (Siri/Alexa/Алиса/
Cortana) ship by default + power-user utilities (shutdown,
window/process control).
2026-05-15 12:43:26 +03:00
Bossiara13
5790ca18af feat: parity — reminders, today/tomorrow/yesterday, voice type, dice, stopwatch (67 commands)
Mirrors the rust feature/pc-tools work. yaml.safe_load + ast.parse pass.
Commands count: 56 → 67 (+11).

main.py:
+ do_set_reminder — strips trigger, parses "N (секунд|минут|часов)"
  with Russian-word numeral support (один/две/пять/десять/...).
  Spawns a daemon thread that time.sleep()s then runs tts.va_speak
  + PowerShell WScript.Shell.Popup. Defaults to 5 min when number/
  unit are missing.
+ do_date_query — accepts {offset: 0/1/-1}, computes target date with
  datetime.timedelta, formats with hardcoded Russian weekday/month
  names (no locale dependency), speaks "Сегодня/Завтра/Вчера + ...".
+ do_type_text — clipboard + pyautogui.hotkey('ctrl', 'v') so it
  works in any focused window.
+ do_dice — coin/dice/random via random.choice / random.randint.
+ do_stopwatch — stores start ts in
  %LOCALAPPDATA%\com.priler.jarvis\stopwatch.txt; start/check/stop
  ops with humanised elapsed string.

commands.yaml +11 entries:
+ set_reminder
+ today / tomorrow / yesterday (action: date_query, offset: 0/1/-1)
+ type_text
+ coin_flip / roll_dice / random_number (action: dice, kind: ...)
+ stopwatch_start / stopwatch_check / stopwatch_stop
  (action: stopwatch, op: start/check/stop)
2026-05-15 12:28:57 +03:00
Bossiara13
69359ed5c0 feat: "Python edition" startup banner + one-click run.bat launcher
main.py: prints a 3-line banner at startup with name, version, edition
label ("Python edition") and the command count from the loaded YAML.
Makes the console window self-identifying when both python and rust
forks run simultaneously.

run.bat at repo root: cd /d into repo, sets the cmd title to
"J.A.R.V.I.S. (Python edition)", picks the venv interpreter at
.venv\Scripts\python.exe if present (falls back to system python),
runs main.py, then pauses at exit so the user can read any traceback
instead of the console window vanishing on crash.

Desktop shortcut "Jarvis (Python).lnk" points at this batch file
with the project icon (the rust fork's icon.ico, since python has
no .ico of its own).
2026-05-15 12:12:21 +03:00
Bossiara13
3795a0b4ec feat: tier-1 parity — translate, math, theme toggle, projects, sound panel (56 commands total)
Mirrors the rust packs from the same iteration. yaml.safe_load + ast.parse
both pass.

main.py — six new action handlers + a _speak_in_lang helper:
+ do_translate: picks target language from "переведи на X" / "translate to X"
  triggers, defaults to English, sends to Groq with strict "translation only"
  prompt, drops to clipboard, speaks via SAPI in matching ISO voice
+ do_math_eval: strips trigger, Groq at temp=0.0 max_tokens=64,
  short-circuits on "нет" sentinel for non-math
+ do_theme_set: writes AppsUseLightTheme + SystemUsesLightTheme via
  Set-ItemProperty under HKCU\...\Themes\Personalize, action param
  mode: dark|light
+ do_open_project / do_list_projects: reads/creates
  %USERPROFILE%\Documents\jarvis-projects.json (a flat list of
  {name, path}), exact-match → substring-match, opens in VS Code if
  code.cmd on PATH else Explorer. First call writes a sample config
  pointing under USERPROFILE so it works on any host.
+ do_open_sound_panel: rundll32 mmsys.cpl,,1 — Recording tab

commands.yaml — 8 new entries:
+ translate, math_eval
+ theme_dark, theme_light (action params mode:dark/light)
+ open_project, list_projects
+ open_sound_panel

SAPI voice selection iterates GetInstalledVoices() and picks first
matching TwoLetterISOLanguageName — Russian phrases sound Russian,
English/German/etc. sound right too, falls back to default if no
matching voice is installed.

Total commands: 56 (was 49).
2026-05-15 12:06:44 +03:00
Bossiara13
7d83bf8299 feat: tier-1 PC tools parity — window mgmt, clipboard, notes, process killer, web search
Mirrors the new rust packs from the same iteration. Total commands in
commands.yaml is now 49 (was 33). yaml.safe_load + ast.parse both pass.

Window management (8 commands) — uses the existing `keys` action with
pyautogui hotkey strings: winleft+d (show_desktop), winleft+up/down
(maximize/minimize), winleft+left/right (snap left/right), alt+f4
(close_window), winleft+shift+m (restore_all), winleft+tab (task_view).
No new action type needed.

Clipboard read aloud — new clipboard_read action. Shells to
PowerShell Get-Clipboard, caps preview at 400 chars, speaks via the
existing tts.va_speak (which already handles recorder.stop/start).

Notes — new notes_add + notes_open actions. notes_add strips the
trigger phrase, appends "[YYYY-MM-DD HH:MM] body\n" to
%USERPROFILE%\Documents\jarvis-notes.txt, creates the dir if needed.
notes_open shells "cmd /c start" so .txt opens in the user-default
editor.

Process killer — new process_kill action. Strips the trigger ("убей
процесс"/"закрой программу"/etc.), looks up the remainder in the same
alias map as the rust version (хром→chrome, телега→telegram, спотифай
→spotify, едж/эдж/edge→msedge, дискорд→discord, стим→steam, обс→obs64,
проводник/блокнот/калькулятор/диспетчер задач, vs code→code, etc.),
appends .exe if needed, runs taskkill /F /IM, speaks success or
"не нашёл процесс N".

Web search — new websearch action with a `service` param. Bases:
google → https://www.google.com/search?q=
youtube → https://www.youtube.com/results?search_query=
wiki → https://ru.wikipedia.org/wiki/Special:Search?search=
yandex → https://yandex.ru/search/?text=
Strips trigger, urllib.parse.quote-s the rest, opens via webbrowser.open
(respects the user'\''s default browser; config.BROWSER_PATHS only kicks in
for the older url-action commands).

Portability: USERPROFILE used for notes path, no other hardcoded paths.
2026-05-15 11:27:19 +03:00
Bossiara13
80a685230c feat: parity with rust fork — LLM auto-fallback + 6 new action types + 20+ commands
Brings the python fork in line with the new feature/pc-tools work that
landed in rust. Same UX, same trigger phrases, same env vars.

config.py:
  + LLM_AUTO_FALLBACK = True
  + LLM_AUTO_FALLBACK_MIN_CHARS = 4
    Mirrors the rust config knobs. The old "скажи X" trigger still works
    (VA_TBR strips it before intent matching, so what remains hits this
    fallback anyway) — but now ANY unrecognized query goes to Groq, not
    just "скажи" ones.

main.py:
  va_respond: replaced the fuzz-on-"скажи" gate with a unified auto-
  fallback that fires whenever no command matches, GROQ_TOKEN is set,
  and the utterance is at least LLM_AUTO_FALLBACK_MIN_CHARS long.

  + _speak(text): recorder.stop() → tts.va_speak → start, used by the
    new action handlers so the mic doesn't pick up the assistant.
  + _set_clipboard(text): subprocess to PowerShell Set-Clipboard, no
    new python deps.
  + _strip_trigger(voice, triggers): shared helper for codegen/file_search
    where we need the text AFTER the trigger phrase.

  New action handlers (registered in run_action dispatch):
  + groq_codegen — extracts query, calls Groq with strict "code only"
    system prompt at temp 0.2, strips ```lang ... ``` fences, puts the
    result in the clipboard, speaks "Код в буфере, сэр. Строк: N".
  + ocr_screen — PowerShell System.Drawing screenshot to a temp PNG,
    shells to tesseract.exe (-l rus+eng), speaks a 120-char preview,
    clipboard. Looks for tesseract on PATH first then standard install
    dirs; gives a clear "Tesseract не установлен" if missing.
  + sysinfo — CIM-based battery/cpu/ram/disk via PS one-liners, time
    via python datetime (gets us localized weekday for free). Topics:
    time / battery / cpu / ram / disk / all.
  + file_search — strips trigger, recursive Get-ChildItem in Desktop/
    Documents/Downloads (depth 3, top 5), opens explorer /select on
    the first hit, speaks count and basename.
  + audio_devices_panel — opens mmsys.cpl. Proper COM-based device
    switching (like the rust IPolicyConfig version) is deferred — TODO
    in backlog.

commands.yaml:
  Total 33 commands (was 19). New:
  + open_notepad / open_calculator / open_explorer / open_terminal
    / open_settings / open_task_manager / lock_screen / screenshot
    — all via shell action (no AHK exes needed).
  + volume_up / volume_down — five chained keys=volumeup/volumedown
    presses each, like rust's _volume_helper.ps1 with Times=5.
  + media_stop — keys=stop.
  + sysinfo_time / sysinfo_battery / sysinfo_cpu / sysinfo_ram /
    sysinfo_disk / sysinfo_all — sysinfo action.
  + file_search, codegen, read_screen, switch_audio_device.

  Replaced (were AHK exes that Priler ships and we don't have):
  ~ music → keys playpause
  ~ music_off → keys playpause (toggle)
  ~ music_next → keys nexttrack
  ~ music_prev → keys prevtrack

  Removed (Priler hardware/setup specific, can't sensibly port):
  - gaming_mode_on / gaming_mode_off (display config switch)
  - music_save (depends on the specific player AHK was driving)
  - switch_to_headphones / switch_to_dynamics (replaced with the
    generic switch_audio_device that opens mmsys.cpl)

  Kept as-is (worked already, no AHK dependency):
  open_browser / open_youtube / open_google (url action)
  sound_off / sound_on (pycaw via system.volume_mute/unmute)
  thanks / stupid / off

Smoke-tested: yaml.safe_load → 33 commands, ast.parse main.py → OK.

Portability: USERPROFILE for screenshot path, $env:SystemDrive for disk,
PATH lookup for tesseract before falling back to standard install dirs.
No hardcoded user-specific paths.
2026-05-15 01:48:34 +03:00
Bossiara13
53678fbdfa Release v0.4.1 — browser choice for url-action 2026-04-27 20:06:58 +03:00
Bossiara13
b8fc7b4eb7 chore: bump VA_VER to 0.4.1 2026-04-27 20:06:52 +03:00
Bossiara13
d0eac79275 Merge feature/browser-choice-in-url into dev 2026-04-27 20:06:51 +03:00
Bossiara13
a4171ec6b1 feat(url): optional browser field (yandex/chrome/firefox/edge)
Adds optional 'browser' field to url-action; runtime resolves it via
config.BROWSER_PATHS (subprocess.Popen with the chosen exe). When
omitted, falls back to webbrowser.open (system default). Constructor
GUI gains a browser dropdown on URL action and on multi-step URL.
Existing open_browser/youtube/google updated to use yandex by default
since user prefers Yandex Browser.
2026-04-27 20:06:26 +03:00
Bossiara13
47927fcf41 Release v0.4.0 — semantic intent (ONNX MiniLM) + optional denoise 2026-04-23 11:09:54 +03:00
Bossiara13
d22a35c9c7 chore: bump VA_VER to 0.4.0 2026-04-23 11:09:48 +03:00
Bossiara13
59aece53da Merge feature/onnx-intent-and-denoise into dev
Replaces fuzzywuzzy intent matching with ONNX MiniLM-L6-v2 sentence
embeddings (cosine similarity, threshold 0.45). Now triggers on
semantically equivalent phrases not literally in commands.yaml.
Adds optional noisereduce preprocessing before Vosk (off by default,
DENOISE_ENABLED config flag). Inference latency: 2.5ms median CPU.
2026-04-23 11:09:46 +03:00
Bossiara13
8655b4fc69 docs: README — semantic intent + denoise 2026-04-23 10:55:07 +03:00
Bossiara13
cc3fa60c28 chore: pin onnxruntime / tokenizers / noisereduce in requirements 2026-04-23 10:54:38 +03:00
Bossiara13
13370da5b7 feat: optional noisereduce preprocessing before vosk 2026-04-23 10:54:20 +03:00
Bossiara13
6a710c55b8 feat: onnx intent classifier replacing fuzzy match 2026-04-23 10:53:18 +03:00
Bossiara13
9cb55f4730 chore: vendor MiniLM-L6-v2 onnx model from Qdrant 2026-04-23 10:51:53 +03:00
Bossiara13
31a2dd1a6c chore: enable git lfs for .onnx files 2026-04-23 10:51:29 +03:00
Bossiara13
e7d4304a62 Release v0.3.0 — TTS effects + GUI command constructor 2026-04-23 02:17:09 +03:00
Bossiara13
1eaaf9eddc Merge feature/command-builder into dev
GUI command constructor (pywebview, Russian, dark theme matching
Rust GUI palette). 3-step stepper + LLM-suggest tab. Writes to
commands.yaml with ruamel-preserved comments and .bak backup.
Three new action types: shell / url / keys (pyautogui-based).
2026-04-23 02:17:02 +03:00
Bossiara13
e86906801a Merge feature/ai-style-postproc into dev
Optional bandpass + short reverb on Silero TTS output. Off by default
(TTS_EFFECTS_ENABLED in config.py). Preview script in utils/.
2026-04-23 02:17:02 +03:00
Bossiara13
fbfe3a7ff6 chore: bump VA_VER to 0.3.0 2026-04-23 02:13:49 +03:00
Bossiara13
b535d025f3 docs: command builder README + user-facing README section + run_builder.bat 2026-04-23 02:13:47 +03:00
Bossiara13
521b124f05 feat(ui): keyboard nav (Enter advances step) + yaml-health warning on launch 2026-04-23 02:13:43 +03:00
Bossiara13
0b1604e018 feat(tools): llm-suggest via groq with JSON response format 2026-04-23 02:11:45 +03:00
Bossiara13
e4d4bf7a08 feat(ui): steps 1-3 (trigger / action / params) with live YAML preview 2026-04-23 02:11:01 +03:00
Bossiara13
232490d9fa chore: vendor js-yaml.min.js 2026-04-23 02:10:57 +03:00
Bossiara13
9814181d1a feat(tools): pywebview bootstrap + python bridge API
Single window (900x720, dark background) loading web/index.html with a
Python bridge exposing list_existing_commands, list_exes,
list_sound_names, preview_sound, slugify, validate_draft, save_command,
plus llm_suggest hook for M3. Sound preview spawned on a daemon thread
so the GUI does not block.
2026-04-22 23:21:20 +03:00
Bossiara13
80d9eedead chore: add ruamel.yaml + pyautogui deps
ruamel.yaml is needed by tools/command_builder/yaml_writer to round-trip
commands.yaml without losing comments. pyautogui drives the new keys
action. pywebview is added now too so M2's GUI bootstrap can land
without another deps bump.
2026-04-22 23:17:44 +03:00
Bossiara13
7b8cd31cf3 feat: add shell / url / keys action types to runtime dispatcher
shell uses subprocess (with shell=True so user can write a normal
command line); url uses webbrowser.open; keys uses pyautogui.hotkey
for combinations or pyautogui.typewrite for raw text. pyautogui is
imported lazily so the bot still starts on machines without a GUI.
2026-04-22 23:17:40 +03:00
Bossiara13
0f6b794db9 feat(tools): yaml writer with ruamel (preserves comments, atomic + backup)
Uses ruamel.yaml so existing comments / formatting in commands.yaml
survive a save. Each write creates commands.yaml.bak first, then
atomically renames a .tmp file into place. Tests cover round-trip for
all action types plus comment-preservation on append.
2026-04-22 23:17:24 +03:00
Bossiara13
68e73b3c53 feat(tools): scaffold command builder schema
Dataclass-based schema mirroring commands.yaml plus new action types
(shell, url, keys). Round-trip dict<->dataclass with validation.
Russian-aware slugify for auto-generating command IDs.
2026-04-22 23:17:17 +03:00
Bossiara13
f9e1e2468f chore: gitignore voice_ref/ and sound/_*.wav experiments 2026-04-22 23:10:54 +03:00
Bossiara13
e5903d8076 docs: README — TTS effects section 2026-04-22 20:00:04 +03:00
Bossiara13
34f5cd4f5a chore: add utils/preview_effects.py for A/B comparison 2026-04-22 19:59:45 +03:00
Bossiara13
64ad7b963e feat: wire effects into va_speak behind config.TTS_EFFECTS_ENABLED 2026-04-22 19:58:42 +03:00
Bossiara13
bd6bc294ad feat: add tts effects module (bandpass + reverb + optional pitch) 2026-04-22 19:58:20 +03:00
Bossiara13
f45ac77a2e Release v0.2.0 — VAD + YAML plugin commands 2026-04-22 19:43:57 +03:00
Bossiara13
4f3b827a47 Merge feature/vad-and-yaml-plugins into dev
Adds webrtcvad-based smart command-end detection (fixed 10s window
replaced by VAD with configurable silence/min/max thresholds) and
migrates execute_cmd to a YAML-driven plugin system with typed
actions (exe, play_sound, system, multi, sleep). 17 commands
migrated; all original behavior preserved.
2026-04-22 19:43:52 +03:00