# Gateway data-plane image (PRD 0024 bundle shape; PRD 0070 gateway).
#
# The egress / git-gate / supervise *data plane* — one image, run by
# the consolidated per-host gateway (PRD 0070). It is NOT the
# orchestrator control plane: that is the separate, lean
# `bot-bottle-orchestrator` image (Dockerfile.orchestrator, #384), which
# ships only python + the stdlib-only `bot_bottle` package and none of
# this image's mitmproxy / git / gitleaks payload.
#
# Collapses the prior per-daemon images (egress, git-gate,
# supervise) into one. A small stdlib-Python init supervisor at
# /app/gateway_init.py spawns all daemons, forwards SIGTERM, and
# propagates per-daemon stdout/stderr to the container log with a
# `[name]` prefix. See PRD 0024 for the rationale.
#
# Layout:
#
#   /usr/bin/gitleaks                    gitleaks binary
#   /app/egress_addon.py + siblings      mitmproxy addon (egress)
#   /app/egress-entrypoint.sh            mitmdump launcher
#   /app/supervise_server.py + .py       supervise MCP server
#   /app/gateway_init.py                 PID 1 supervisor
#   /etc/egress/routes.yaml              bind-mounted at run time
#   /etc/git-gate/pre-receive            docker-cp'd at start time
#   /git-gate-entrypoint.sh              docker-cp'd at start time
#   /git-gate/creds/*                    docker-cp'd at start time
#   /git/*                               bare repos, populated at runtime
#   /run/supervise/bot-bottle.db         bind-mounted at run time
#   /home/mitmproxy/.mitmproxy/          mitmproxy CA dir
#
# Exposed ports inside the container:
#   9099  egress (mitmproxy, agent-facing HTTPS proxy)
#   9418  git-gate (git-daemon)
#   9420  git-gate smart HTTP (VM-backend agent-facing transport)
#   9100  supervise (MCP HTTP)

# Based on `python:3.12-slim` (Debian trixie) rather than the
# `mitmproxy/mitmproxy` image (Debian bookworm) so the whole stack —
# gateway here, and the firecracker infra image that builds FROM this —
# lands on trixie, whose buildah (1.39) can build agent Dockerfiles that
# use heredocs. mitmproxy is pip-installed to the same effect as the
# upstream image. (bookworm's buildah is 1.28, which can't parse
# `RUN ... <<EOF`; see the infra image + PR discussion.)
FROM python:3.12-slim

# Runtime system deps:
#   git supplies the `git daemon` subcommand (no separate package)
#     plus the core `git` binary the pre-receive hook invokes.
#   openssh-client supplies the upstream SSH transport the
#     pre-receive hook uses to forward accepted refs.
#   ca-certificates is needed for mitmdump upstream TLS.
RUN apt-get update \
 && apt-get install -y --no-install-recommends \
      git openssh-client ca-certificates \
 && rm -rf /var/lib/apt/lists/*

# mitmdump (the egress data plane). The upstream mitmproxy image baked
# this in; on the plain python base we pip-install the same pinned
# version. Its CA dir is set explicitly via `--set confdir=` in
# egress-entrypoint.sh, so it doesn't depend on a `mitmproxy` home user.
RUN pip install --no-cache-dir mitmproxy==11.1.3

# gitleaks (the pre-receive hook's secret scanner). Installed from its
# official release, pinned by version + SHA256 and verified — rather than
# using a third-party image as a build stage (supply-chain surface, and it
# would pin us to that image's cadence). python (already present) does the
# download so we add no curl/wget. trixie apt also ships gitleaks, but an
# older 8.16; the pinned download keeps the verified 8.30.1.
#
# Arch-aware: the asset + SHA are picked from the build's target
# architecture so an arm64 host (Apple Silicon) gets the arm64 binary
# rather than an x86_64 one that dies with "Exec format error" the first
# time the pre-receive hook runs it. TARGETARCH is auto-populated by
# BuildKit; the dpkg fallback keeps it correct under a legacy builder.
ARG GITLEAKS_VERSION=8.30.1
ARG GITLEAKS_SHA256_AMD64=551f6fc83ea457d62a0d98237cbad105af8d557003051f41f3e7ca7b3f2470eb
ARG GITLEAKS_SHA256_ARM64=e4a487ee7ccd7d3a7f7ec08657610aa3606637dab924210b3aee62570fb4b080
ARG TARGETARCH
RUN arch="${TARGETARCH:-$(dpkg --print-architecture)}" \
 && case "$arch" in \
      amd64) asset="linux_x64";   sha="${GITLEAKS_SHA256_AMD64}" ;; \
      arm64) asset="linux_arm64"; sha="${GITLEAKS_SHA256_ARM64}" ;; \
      *) echo "unsupported gitleaks target arch: $arch" >&2; exit 1 ;; \
    esac \
 && url="https://github.com/gitleaks/gitleaks/releases/download/v${GITLEAKS_VERSION}/gitleaks_${GITLEAKS_VERSION}_${asset}.tar.gz" \
 && python3 -c "import sys,urllib.request; urllib.request.urlretrieve(sys.argv[1], '/tmp/gitleaks.tar.gz')" "$url" \
 && echo "${sha}  /tmp/gitleaks.tar.gz" | sha256sum -c - \
 && tar -xzf /tmp/gitleaks.tar.gz -C /usr/bin gitleaks \
 && rm /tmp/gitleaks.tar.gz

# Project Python: addon + server modules + the init supervisor.
# Kept flat under /app/ so mitmdump's loader resolves them as
# top-level siblings (absolute imports), matching the prior
# Dockerfile.egress / Dockerfile.supervise layout.
COPY bot_bottle/egress_addon_core.py /app/egress_addon_core.py
COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.py
COPY bot_bottle/egress_addon.py      /app/egress_addon.py
COPY bot_bottle/policy_resolver.py   /app/policy_resolver.py
COPY bot_bottle/dlp_detectors.py     /app/dlp_detectors.py
COPY bot_bottle/yaml_subset.py       /app/yaml_subset.py
COPY bot_bottle/paths.py             /app/paths.py
COPY bot_bottle/migrations.py        /app/migrations.py
COPY bot_bottle/db_store.py          /app/db_store.py
COPY bot_bottle/supervise_types.py   /app/supervise_types.py
COPY bot_bottle/queue_store.py       /app/queue_store.py
COPY bot_bottle/audit_store.py       /app/audit_store.py
COPY bot_bottle/store_manager.py     /app/store_manager.py
COPY bot_bottle/supervise.py         /app/supervise.py
COPY bot_bottle/supervise_server.py  /app/supervise_server.py
COPY bot_bottle/gateway_init.py      /app/gateway_init.py
COPY bot_bottle/git_http_backend.py  /app/git_http_backend.py
COPY bot_bottle/egress_entrypoint.sh /app/egress-entrypoint.sh
RUN chmod +x /app/egress-entrypoint.sh

# Pre-create runtime directories the compose renderer + start
# step expect to exist. `docker cp` does not create intermediate
# dirs, and bind mounts won't either if the parent is missing.
RUN mkdir -p \
      /etc/egress \
      /etc/git-gate \
      /git-gate/creds \
      /git \
      /run/supervise \
      /home/mitmproxy/.mitmproxy

# Documentation only — the compose renderer publishes whichever
# subset the bottle uses.
EXPOSE 8888 9099 9418 9420 9100

# WORKDIR matches Dockerfile.supervise's prior layout so the
# in-app same-dir import in supervise_server.py stays deterministic.
WORKDIR /app

# PID 1 is the supervisor. It owns signal handling and exit-code
# propagation; no `exec` chain in the entrypoint itself.
ENTRYPOINT ["python3", "/app/gateway_init.py"]