# Full Unsloth image: base training stack + Studio + JupyterLab + sshd.
#
# This is the image published as docker.io/unsloth/unsloth:latest. It layers
# Unsloth Studio on top of the lean base image (Dockerfile, published under
# the `base` tags) and runs the same service trio as the previous production
# image: Studio on 8000, JupyterLab on 8888, key-only sshd on 22.
#
# Build (local):
#   docker buildx build \
#     --build-arg BASE_IMAGE=unsloth-blackwell:test \
#     -f docker/Dockerfile.studio \
#     -t unsloth-blackwell:studio docker/
#
# Run:
#   docker run --rm --gpus all -p 8000:8000 -p 8888:8888 \
#     -v $HOME/.cache/huggingface:/workspace/.cache/huggingface \
#     unsloth-blackwell:studio
#
# Open http://localhost:8000 for Studio (first-boot admin password is printed
# in the container logs and persisted under /opt/unsloth-studio/auth/) and
# http://localhost:8888 for JupyterLab (password: JUPYTER_PASSWORD env,
# default `unsloth`). On hosts without GPU passthrough (Docker Desktop on
# macOS, Windows without WSL2 GPU) add -e UNSLOTH_ALLOW_CPU=1: training is
# unavailable but Studio chat / Data Recipes / GGUF tooling / Jupyter work.
#
# CI pins BASE_IMAGE to the just-published multi-arch base digest so the two
# images always ship the same stack.

ARG BASE_IMAGE=unsloth-blackwell:test
FROM ${BASE_IMAGE}

# Studio source ref to clone. Defaults to `main`, but a CI publish pipeline
# that pins BASE_IMAGE to a digest should pin this too (same UNSLOTH_REF as
# the base) so the published image is reproducible against a known ref.
ARG UNSLOTH_STUDIO_REF=main
ARG TARGETARCH

USER root
ENV UNSLOTH_STUDIO_HOME=/opt/unsloth-studio \
    DEBIAN_FRONTEND=noninteractive

# install.sh needs curl + git; supervisor + openssh-server run the service
# trio. The base image already has python + uv + pip.
RUN apt-get update \
 && apt-get install -y --no-install-recommends \
        curl git ca-certificates supervisor openssh-server \
 && rm -rf /var/lib/apt/lists/*

# Clone + install Studio into a dedicated venv under $UNSLOTH_STUDIO_HOME.
# --local makes install.sh use the just-cloned source tree (editable
# install), so the source dir MUST persist for the venv's `unsloth_cli`
# entrypoint to keep resolving. Move it under $UNSLOTH_STUDIO_HOME/src
# (already inside the persistent layer) instead of deleting it. Strip
# .git to save ~120MB.
#
# The llama.cpp symlink BEFORE install.sh points Studio's prebuilt dir at
# the bundle already baked into the base image (validated, sha256-checked,
# UNSLOTH_PREBUILT_INFO.json present), so the installer's prebuilt step
# recognises it and skips a second ~400MB download. The
# .unsloth-studio-owned marker satisfies setup.sh's ownership assertion for
# custom STUDIO_HOMEs -- the dir IS provisioned exclusively for Studio.
#
# UNSLOTH_TORCH_INDEX_FAMILY pins the torch wheel index for the Studio
# venv: at build time there is no GPU and no nvidia-smi, so install.sh's
# probing would land on cpu or cu126 wheels depending on which host built
# the image. The image targets CUDA: cu128 on amd64 (Turing..Blackwell,
# same line as the base venv), cu130 on arm64 (DGX Spark / Grace, the
# aarch64 CUDA wheel line).
#
# fetch+checkout FETCH_HEAD instead of `clone --branch` because the CI
# pipeline passes a commit SHA as the ref (clone --branch only accepts
# branch/tag names).
RUN set -eux \
 && case "${TARGETARCH:-amd64}" in \
        amd64) TORCH_FAMILY="cu128" ;; \
        arm64) TORCH_FAMILY="cu130" ;; \
        *)     echo "ERROR: unsupported TARGETARCH=${TARGETARCH}" >&2; exit 1 ;; \
    esac \
 && mkdir -p "${UNSLOTH_STUDIO_HOME}" \
 && ln -s /opt/unsloth/llama.cpp "${UNSLOTH_STUDIO_HOME}/llama.cpp" \
 && touch /opt/unsloth/llama.cpp/.unsloth-studio-owned \
 && git init -q "${UNSLOTH_STUDIO_HOME}/src" \
 && cd "${UNSLOTH_STUDIO_HOME}/src" \
 && git remote add origin https://github.com/unslothai/unsloth \
 && git fetch -q --depth 1 origin "${UNSLOTH_STUDIO_REF}" \
 && git checkout -q FETCH_HEAD \
 && UNSLOTH_STUDIO_HOME="${UNSLOTH_STUDIO_HOME}" \
    UNSLOTH_TORCH_INDEX_FAMILY="${TORCH_FAMILY}" \
    bash install.sh --local \
 && rm -rf "${UNSLOTH_STUDIO_HOME}/src/.git" /root/.cache

COPY supervisord.conf /etc/supervisor/supervisord.conf
COPY studio_launch.sh /usr/local/bin/unsloth-studio-launch
RUN chmod +x /usr/local/bin/unsloth-studio-launch

# Studio web UI, JupyterLab, sshd. All bind 0.0.0.0 inside the container's
# network namespace; the operator publishes them explicitly with -p.
EXPOSE 8000 8888 22

# The base ENTRYPOINT (unsloth-entrypoint) still runs its GPU pre-flight
# first, then hands off to the service launcher.
CMD ["/usr/local/bin/unsloth-studio-launch"]