# ============================================================================
# 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

# `video` is REQUIRED for NVENC/NVDEC: it tells the NVIDIA Container Toolkit to
# inject libnvidia-encode.so.1 / libnvidia-decode.so.1 into the container. With
# only `compute,utility` you get CUDA (ollama/whisper/melo) + nvidia-smi, but the
# Go-Live broadcast's h264_nvenc fails with "Cannot load libnvidia-encode.so.1".
# Applies on both Linux (CDI) and Windows Docker Desktop (WSL2).
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility,video

# --- 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

# --- Korean voice: Microsoft Edge TTS (online neural). No model is baked — the
#     `edge-tts` pip package (in requirements-bridge.txt) calls the MS service at
#     runtime and the bridge transcodes the MP3 to PCM16 with ffmpeg. No heavy
#     TTS build layer is needed. ---

# --- Human input + window management for the on-screen Chrome control tool.
#     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

# Normalise all container shell scripts to LF. On a Windows checkout (autocrlf)
# these arrive as CRLF, which would break their shebangs at runtime (entrypoint,
# run-*.sh) the same way it broke setup-melo.sh at build time.
RUN find /app/docker /app/scripts -name '*.sh' -exec sed -i 's/\r$//' {} +

# --- 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"]