109dbc7e16
- Install xdotool + wmctrl (late Docker layer, preserves the melo cache) so the on-screen Chrome gets real X input (visible cursor, char-by-char typing) instead of synthetic events; falls back to the Playwright API if absent. - Fix active-tab detection (probe document.visibilityState instead of assuming tab 0) so sequential ops target the right tab. - Add back / forward / refresh; new/switch/close tabs via real keyboard (Ctrl+T / Ctrl+<n> / Ctrl+W) when xdotool is present. - Auto-dismiss native JS dialogs; closePopups clears blank/popup tabs. - Report broadcast (Go-Live) state in status from the turn context. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
90 lines
4.0 KiB
Docker
90 lines
4.0 KiB
Docker
# ============================================================================
|
|
# Javis Bot — all-in-one container
|
|
# VNC + XFCE desktop + Chrome + Python brain bridge + Node/bun Discord bot.
|
|
# Ollama (the LLM backend) runs as a separate service (see docker-compose.yml).
|
|
# ============================================================================
|
|
FROM ubuntu:24.04
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive \
|
|
LANG=C.UTF-8 \
|
|
DISPLAY=:1 \
|
|
PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1 \
|
|
PATH=/opt/venv/bin:/root/.bun/bin:/usr/local/bin:/usr/bin:/bin \
|
|
NVIDIA_VISIBLE_DEVICES=all \
|
|
NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
|
|
# --- System packages: desktop, VNC, Chrome deps, ffmpeg, python, ocr ---
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ca-certificates curl wget gnupg unzip procps \
|
|
tigervnc-standalone-server tigervnc-common tigervnc-tools \
|
|
xfce4 xfce4-goodies dbus-x11 x11-utils xfonts-base \
|
|
fonts-noto-cjk fonts-noto-cjk-extra fonts-nanum \
|
|
ffmpeg tesseract-ocr \
|
|
pulseaudio pulseaudio-utils \
|
|
python3 python3-venv python3-pip \
|
|
novnc websockify supervisor gettext-base \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# --- Google Chrome (stable) ---
|
|
RUN wget -q -O /tmp/chrome.deb https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb \
|
|
&& (apt-get update && apt-get install -y --no-install-recommends /tmp/chrome.deb || (apt-get -f install -y)) \
|
|
&& rm -f /tmp/chrome.deb && rm -rf /var/lib/apt/lists/*
|
|
|
|
# --- bun (Discord bot runtime/package manager) ---
|
|
RUN curl -fsSL https://bun.sh/install | bash
|
|
|
|
# --- Node.js + Gemini CLI (the GEMINI_AUTH=oauth real-time search path shells
|
|
# out to `gemini`; it needs a real Node runtime, not bun). The account
|
|
# login itself is provided at runtime via the mounted ~/.gemini (see
|
|
# docker-compose.yml); here we only install the binary. ---
|
|
ARG GEMINI_CLI_VERSION=0.46.0
|
|
RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
|
|
&& apt-get install -y --no-install-recommends nodejs \
|
|
&& npm install -g "@google/gemini-cli@${GEMINI_CLI_VERSION}" \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& gemini --version
|
|
|
|
# --- Python brain/bridge deps (slim set) ---
|
|
COPY bridge/requirements-bridge.txt /app/bridge/requirements-bridge.txt
|
|
RUN python3 -m venv /opt/venv \
|
|
&& /opt/venv/bin/pip install --no-cache-dir --upgrade pip \
|
|
&& /opt/venv/bin/pip install --no-cache-dir -r /app/bridge/requirements-bridge.txt
|
|
|
|
# faster-whisper>=1.1 / ctranslate2 self-locates these pip CUDA libs at runtime,
|
|
# so no hardcoded LD_LIBRARY_PATH is needed. We also register them with the
|
|
# dynamic linker (full path to ldconfig; PATH excludes /sbin) as a robust
|
|
# fallback. Path-glob is python-version agnostic.
|
|
RUN ls -d /opt/venv/lib/python*/site-packages/nvidia/cublas/lib \
|
|
/opt/venv/lib/python*/site-packages/nvidia/cudnn/lib \
|
|
> /etc/ld.so.conf.d/nvidia-cu12.conf 2>/dev/null \
|
|
&& /sbin/ldconfig || true
|
|
|
|
# --- MeloTTS Korean voice (separate /opt/melo py3.11 venv; see setup-melo.sh).
|
|
# Heavy layer (torch CPU + transformers + MeCab); placed before the app
|
|
# COPY so it stays cached across source-only changes. ---
|
|
COPY docker/setup-melo.sh /app/docker/setup-melo.sh
|
|
RUN bash /app/docker/setup-melo.sh
|
|
|
|
# --- Human input + window management for the on-screen Chrome control tool.
|
|
# Placed AFTER the heavy melo layer so it doesn't bust that cache. xdotool
|
|
# injects real X pointer/keyboard events (visible cursor, char-by-char
|
|
# typing) into the broadcast; wmctrl lists/moves windows. ---
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
xdotool wmctrl \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# --- Discord bot deps (cache layer on lockfile) ---
|
|
COPY bot/package.json bot/bun.lock /app/bot/
|
|
RUN cd /app/bot && bun install --frozen-lockfile || bun install
|
|
|
|
# --- App source ---
|
|
COPY . /app
|
|
WORKDIR /app
|
|
|
|
# --- Default Piper voice (best-effort at build; entrypoint retries if absent) ---
|
|
RUN bash docker/download-piper.sh || true
|
|
|
|
EXPOSE 5901 6080 8765
|
|
|
|
ENTRYPOINT ["/app/docker/entrypoint.sh"]
|