b88def6756
Adds a GEMINI_AUTH=oauth (default) sub-mode that shells out to the Gemini CLI using the user's Google-account login instead of an API key. gemini_cli_search() runs `gemini -p <query> -o json --skip-trust --approval-mode yolo`, strips GEMINI_API_KEY/GOOGLE_API_KEY and sets GOOGLE_GENAI_USE_GCA=true so the CLI selects the account OAuth method and fails fast when no login exists. Bounded by a 30s timeout and fail-open to the DDG/Brave/Wikipedia cascade on any failure (CLI missing, login expired, quota 429, timeout). GEMINI_AUTH=apikey keeps the legacy REST path. Specs and docs/llm_contexts.md updated; behaviour covered by tests/test_realtime_gemini_cli.py. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
115 lines
5.4 KiB
Plaintext
115 lines
5.4 KiB
Plaintext
# ============================================================================
|
|
# Javis Bot — environment configuration
|
|
# Copy to `.env` and fill in. Never commit your real `.env`.
|
|
# ============================================================================
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Discord bot (normal bot account) — voice I/O + slash commands
|
|
# ---------------------------------------------------------------------------
|
|
# From https://discord.com/developers/applications → your app
|
|
DISCORD_BOT_TOKEN=
|
|
DISCORD_APP_ID=
|
|
# The (single) server this bot serves. Guild-scoped commands appear instantly.
|
|
DISCORD_GUILD_ID=
|
|
# Voice channel used by the stream-test scripts (bot/scripts/stream-test).
|
|
DISCORD_VOICE_CHANNEL_ID=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Brain bridge (Python service in bridge/) — STT + reply engine + TTS
|
|
# ---------------------------------------------------------------------------
|
|
BRIDGE_URL=http://127.0.0.1:8765
|
|
BRIDGE_HOST=127.0.0.1
|
|
BRIDGE_PORT=8765
|
|
JARVIS_BRAIN_ENABLED=1
|
|
JARVIS_TTS_ENABLED=1
|
|
# faster-whisper device/compute. GPU by default (RTX 5050 / sm_120, verified).
|
|
# Falls back to CPU automatically if no GPU is passed to the container.
|
|
WHISPER_DEVICE=cuda
|
|
WHISPER_COMPUTE_TYPE=float16
|
|
# Optional explicit Piper voice model (.onnx). If empty, the jarvis default is used.
|
|
TTS_PIPER_MODEL_PATH=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Jarvis brain (Ollama-backed). In Docker these populate the rendered
|
|
# config (docker/jarvis-config.template.json). See src/jarvis/config.py.
|
|
# ---------------------------------------------------------------------------
|
|
# In docker-compose this is overridden to http://ollama:11434 automatically.
|
|
OLLAMA_BASE_URL=http://127.0.0.1:11434
|
|
# qwen3:8b — best 8GB-VRAM pick: strongest tool-calling, ~5GB Q4, fits the RTX 5050.
|
|
OLLAMA_CHAT_MODEL=qwen3:8b
|
|
OLLAMA_EMBED_MODEL=nomic-embed-text
|
|
WHISPER_MODEL=small
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Docker desktop (VNC) — used only by the container image
|
|
# ---------------------------------------------------------------------------
|
|
# VNC viewer password (max 8 chars effective). Watch the screen at localhost:5901.
|
|
# Also used by the broadcast keepalive: TigerVNC only refreshes its framebuffer
|
|
# while a VNC client is attached, so the stream keeps a tiny client connected to
|
|
# avoid a choppy (~1.5 fps) capture. Must match the VNC server's password. If
|
|
# unset, the keepalive falls back to the obfuscated passwd file (VNC_PASSWD_FILE,
|
|
# default ~/.config/tigervnc/passwd).
|
|
VNC_PASSWORD=javis123
|
|
# VNC_PASSWD_FILE=/home/claude/.config/tigervnc/passwd
|
|
# Auto-opened page in the in-container Chrome.
|
|
CHROME_START_URL=about:blank
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Screen-share + browser mode.
|
|
# true = the bot may go Live (screen-share the VNC desktop) and drive the
|
|
# on-screen browser for real-time info (search / play / read screen).
|
|
# false = no screen share; voice only, real-time info via the Gemini API.
|
|
STREAM_BROWSER=true
|
|
# Gemini auth for real-time info when STREAM_BROWSER=false.
|
|
# oauth = use the Gemini CLI with a Google-account login (no API key).
|
|
# Install once: npm i -g @google/gemini-cli ; then run `gemini` and
|
|
# "Sign in with Google". Uses the CLI's built-in web-search grounding.
|
|
# apikey = legacy REST path; needs GEMINI_API_KEY below
|
|
# (get one at https://aistudio.google.com/app/apikey).
|
|
GEMINI_AUTH=oauth
|
|
GEMINI_API_KEY=
|
|
GEMINI_MODEL=gemini-2.0-flash
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# VNC screen broadcast
|
|
# selfbot = real live "Go Live" stream (needs a USER/burner token; ToS risk)
|
|
# novnc = share a noVNC browser link (safe, real-time, not native)
|
|
# screenshot = periodic screenshots to the channel (safe, low fps)
|
|
# none = disabled
|
|
# ---------------------------------------------------------------------------
|
|
STREAM_BACKEND=selfbot
|
|
|
|
# The VNC desktop runs on X display :1 (see docs/vnc-xfce-setup.md)
|
|
VNC_DISPLAY=:1
|
|
VNC_RESOLUTION=1920x1080
|
|
# 1080p60 broadcast. 8 Mbps suits 60fps (YouTube-style 1080p60 sits ~8-12 Mbps);
|
|
# drop to 30/4000 for a lighter stream. Max bitrate is 1.5x this value.
|
|
VNC_FRAMERATE=60
|
|
VNC_BITRATE_KBPS=8000
|
|
|
|
# --- selfbot backend ---
|
|
# A THROWAWAY/burner Discord user account token. NEVER your main account.
|
|
# Using a selfbot violates Discord ToS and can get the account banned.
|
|
DISCORD_SELFBOT_TOKEN=
|
|
# Hardware (NVENC) encode for the stream. 1 = use the GPU (recommended for
|
|
# 1080p60), 0 = software x264. Requires an NVIDIA GPU + ffmpeg built with nvenc.
|
|
STREAM_HW=1
|
|
# Capture desktop audio into the broadcast so the stream has sound. 1 = on,
|
|
# 0 = mute. Pulls the PipeWire/Pulse monitor of the default sink; override the
|
|
# source with STREAM_AUDIO_SOURCE (e.g. a specific "<sink>.monitor").
|
|
STREAM_AUDIO=1
|
|
STREAM_AUDIO_SOURCE=@DEFAULT_MONITOR@
|
|
|
|
# --- novnc backend ---
|
|
# e.g. http://192.168.10.9:6080/vnc.html (websockify --web=/usr/share/novnc 6080 localhost:5901)
|
|
NOVNC_URL=
|
|
|
|
# --- screenshot backend ---
|
|
SCREENSHOT_INTERVAL_SEC=5
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Voice behaviour
|
|
# ---------------------------------------------------------------------------
|
|
# Silence (ms) that marks the end of an utterance before sending to the brain.
|
|
VOICE_SILENCE_MS=800
|