docker: install from the docker-ce repo on RHEL-family hosts

bootstrap failed outright on Oracle Linux: docker/install.sh piped
get.docker.com to sh, and that script allowlists distros by /etc/os-release
ID, so it aborted with "ERROR: Unsupported distribution 'ol'".

On a distro it does recognize, the convenience script only adds the repo and
installs the packages -- exactly what install_rhel() now does directly. Doing
it ourselves drops the allowlist, so every EL rebuild (Oracle, Rocky, Alma,
CentOS, RHEL) goes through one code path instead of needing to be enumerated.
Debian-family still uses get.docker.com. containerd.io needs --allowerasing to
replace the runc that Oracle Linux ships.

Also stop one failed module from killing the whole run: modules were bare
calls under `set -eu`, so docker/'s exit meant bin/, node/ and ansible/
silently never ran -- an unsupported distro string left the box with no CLIs,
no npx and no ansible. run_module warns and continues, then bootstrap exits
non-zero with a summary of what failed. Same guard 35befbe added for
individual tools in bin/install.sh, one level up.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -32,8 +32,11 @@ Already have a clone? Just run it directly:
 - `git/` — sets git `user.name`/`user.email` and configures
   `credential.helper store` (plaintext `~/.git-credentials`, 0600) for
   HTTPS auth.
-- `docker/` — installs full (rootful) Docker Engine via get.docker.com,
+- `docker/` — installs full (rootful) Docker Engine from Docker's upstream
-  enables the service (systemd hosts), and adds the invoking user to the
+  package repo (get.docker.com on Debian-family; the docker-ce repo wired up
+  directly on RHEL-family, since the convenience script rejects EL rebuilds
+  like Oracle Linux by name), enables the service (systemd hosts), and adds
+  the invoking user to the
   `docker` group (takes effect at next login). No-ops where a rootless
   Docker daemon is already running (e.g. Kasm) so it never fights that
   setup. Uses sudo.

bootstrap.sh

@@ -43,15 +43,38 @@ if ! command -v python3 >/dev/null 2>&1 && ! command -v unzip >/dev/null 2>&1; t
   pkg_install python3 || echo "bootstrap: warning: could not install python3" >&2
 fi
 
-"$SCRIPT_DIR/zsh/install.sh"
+# run_module <path> — run one module; on failure, warn and keep going.
-"$SCRIPT_DIR/git/install.sh"
+#
+# WHY: these used to be bare calls, so under `set -eu` the FIRST failing module
+# aborted bootstrap and every later module silently never ran — one unsupported
+# distro in docker/ was enough to leave a box with no CLIs, no npx and no
+# ansible. The modules are independent, so a failure in one is not a reason to
+# skip the rest. (bin/install.sh does the same for individual tools; this is
+# that guard one level up.)
+FAILED=""
+run_module() {
+  if ( set -e; "$SCRIPT_DIR/$1/install.sh" ); then return 0; fi
+  FAILED="$FAILED $1"
+  echo "bootstrap: WARNING: $1 module failed; continuing." >&2
+}
+
+run_module zsh
+run_module git
 # Runs before bin/ so the kind install gate can see the rootful daemon.
-"$SCRIPT_DIR/docker/install.sh"
+run_module docker
-"$SCRIPT_DIR/bin/install.sh"
+run_module bin
 # Provides npx, which opencode needs to spawn the npm-based MCP servers in
 # mcp-config/. Without it every MCP server silently fails to start.
-"$SCRIPT_DIR/node/install.sh"
+run_module node
-"$SCRIPT_DIR/ansible/install.sh"
+run_module ansible
 # Runs last: needs rootless Docker already up (started at boot) so it can
 # delegate cgroups to it. No-ops where that does not apply.
-"$SCRIPT_DIR/docker-rootless-cgroup/install.sh"
+run_module docker-rootless-cgroup
+
+if [ -n "$FAILED" ]; then
+  echo "" >&2
+  echo "bootstrap: WARNING: these modules did NOT complete:$FAILED" >&2
+  echo "bootstrap: everything else was applied. Fix the cause and re-run." >&2
+  exit 1
+fi
+echo "bootstrap: all modules applied." >&2

docker/install.sh

@@ -3,10 +3,10 @@
 # invoking user talk to it without sudo.
 #
 # What it does:
-#   1. Installs Docker Engine via Docker's official convenience script
+#   1. Installs Docker Engine from Docker's upstream package repo. Skipped when
-#      (get.docker.com — supports both RHEL- and Debian-family distros and
+#      `docker` is already installed. Debian-family hosts go through Docker's
-#      sets up the upstream package repo). Skipped when `docker` is already
+#      convenience script (get.docker.com); RHEL-family hosts wire up the
-#      installed.
+#      docker-ce repo directly — see install_rhel() for why.
 #   2. Enables and starts the service (systemd hosts only).
 #   3. Adds the invoking user to the `docker` group so the daemon socket is
 #      usable without sudo. Takes effect at next login.
@@ -18,8 +18,66 @@
 # Idempotent and safe to re-run. Uses sudo.
 set -eu
 
+SCRIPT_DIR="$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)"
+REPO_ROOT="$(dirname -- "$SCRIPT_DIR")"
+
+# shellcheck source=../lib/os-detect.sh
+. "$REPO_ROOT/lib/os-detect.sh"
+
 say() { printf '%s\n' "$*" >&2; }
 
+DOCKER_PKGS="docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin"
+
+# install_rhel — install docker-ce from Docker's EL repo.
+#
+# WHY NOT get.docker.com: the convenience script allowlists distros by
+# /etc/os-release ID and aborts on anything it does not recognize —
+# "ERROR: Unsupported distribution 'ol'" on Oracle Linux, and the same for
+# other EL rebuilds it has not enumerated. On a match it does nothing more
+# than what this function does: add the repo, then install the packages.
+# Wiring the repo up directly drops the allowlist, so every EL rebuild
+# (Oracle, Rocky, Alma, CentOS, RHEL) installs from one code path.
+#
+# The repo URL is keyed on $releasever/$basearch, which dnf expands per host,
+# so EL9 and EL10 both resolve without a version table here.
+install_rhel() {
+  say "docker: adding Docker CE repo (EL \$releasever/\$basearch)..."
+  sudo tee /etc/yum.repos.d/docker-ce.repo >/dev/null <<'REPO'
+[docker-ce-stable]
+name=Docker CE Stable - $basearch
+baseurl=https://download.docker.com/linux/centos/$releasever/$basearch/stable
+enabled=1
+gpgcheck=1
+gpgkey=https://download.docker.com/linux/centos/gpg
+REPO
+  # --allowerasing: containerd.io conflicts with the distro's own runc/containerd
+  # on EL rebuilds that ship them (Oracle Linux does). Let dnf swap them out
+  # rather than dead-end on the conflict.
+  if command -v dnf >/dev/null 2>&1; then
+    # shellcheck disable=SC2086
+    sudo dnf install -y --allowerasing $DOCKER_PKGS
+  else
+    # shellcheck disable=SC2086
+    sudo yum install -y --allowerasing $DOCKER_PKGS
+  fi
+}
+
+# install_debian — Docker's convenience script; it supports every Debian-family
+# distro this repo targets and sets up the apt repo and keyring.
+install_debian() {
+  say "docker: installing Docker Engine via get.docker.com..."
+  tmp="$(mktemp)"
+  if command -v curl >/dev/null 2>&1; then
+    curl -fsSL https://get.docker.com -o "$tmp"
+  elif command -v wget >/dev/null 2>&1; then
+    wget -qO "$tmp" https://get.docker.com
+  else
+    say "docker: need curl or wget"; rm -f "$tmp"; return 1
+  fi
+  sudo sh "$tmp"
+  rm -f "$tmp"
+}
+
 # --- skip on rootless-Docker hosts -------------------------------------------
 if command -v docker >/dev/null 2>&1 &&
    docker info -f '{{println .SecurityOptions}}' 2>/dev/null | grep -q 'name=rootless'; then
@@ -31,17 +89,11 @@ fi
 if command -v docker >/dev/null 2>&1; then
   say "docker: engine already installed ($(docker --version 2>/dev/null || echo 'version unknown'))."
 else
-  say "docker: installing Docker Engine via get.docker.com..."
+  case "$(detect_pkg_family)" in
-  tmp="$(mktemp)"
+    rhel)   install_rhel ;;
-  if command -v curl >/dev/null 2>&1; then
+    debian) install_debian ;;
-    curl -fsSL https://get.docker.com -o "$tmp"
+    *)      say "docker: unsupported/undetected OS family; install Docker manually."; exit 1 ;;
-  elif command -v wget >/dev/null 2>&1; then
+  esac
-    wget -qO "$tmp" https://get.docker.com
-  else
-    say "docker: need curl or wget"; exit 1
-  fi
-  sudo sh "$tmp"
-  rm -f "$tmp"
 fi
 
 # --- 2. enable + start the service (systemd only) ----------------------------