#!/usr/bin/env bash
# shellcheck shell=bash
# - - - - - - - - - - - - - - - - - - - - - - - - -
##@Version           :  202610031200-git
# @@Author           :  Jason Hempstead
# @@Contact          :  jason@casjaysdev.pro
# @@License          :  LICENSE.md
# @@ReadME           :  cleanup-runners --help
# @@Copyright        :  Copyright: (c) 2026 Jason Hempstead, Casjays Developments
# @@Created          :  Saturday, Oct 03, 2026 12:00 EDT
# @@File             :  cleanup-runners
# @@Description      :  Prune docker and act cache leftovers from act runner jobs
# @@Changelog        :  New script
# @@TODO             :  Better documentation
# @@Other            :
# @@Resource         :
# @@Terminal App     :  no
# @@sudo/root        :  no
# @@Template         :  shell/bash
# - - - - - - - - - - - - - - - - - - - - - - - - -
# shellcheck disable=SC1001,SC1003,SC2001,SC2003,SC2016,SC2031,SC2090,SC2115,SC2120,SC2155,SC2199,SC2229,SC2317,SC2329
# - - - - - - - - - - - - - - - - - - - - - - - - -
VERSION="202610031200-git"
set -eo pipefail
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Settings - all overridable via environment
# Only prune containers/networks/build cache older than this (docker duration, e.g. 72h)
RUNNER_CLEANUP_UNTIL="${RUNNER_CLEANUP_UNTIL:-72h}"
# Remove all unused images (not just dangling) once the docker data dir reaches this usage percent
RUNNER_CLEANUP_DISK_PERCENT="${RUNNER_CLEANUP_DISK_PERCENT:-80}"
# Directory holding the nested dockerd's data, used for the disk usage check
RUNNER_CLEANUP_DOCKER_DIR="${RUNNER_CLEANUP_DOCKER_DIR:-/data/docker}"
# Remove cloned actions in act's cache that have not changed in this many days (0 disables)
RUNNER_CLEANUP_ACT_CACHE_DAYS="${RUNNER_CLEANUP_ACT_CACHE_DAYS:-7}"
# Space separated list of act action cache directories
RUNNER_CLEANUP_ACT_CACHE_DIRS="${RUNNER_CLEANUP_ACT_CACHE_DIRS:-$HOME/.cache/act /root/.cache/act}"
RUNNER_CLEANUP_LOG_FILE="${RUNNER_CLEANUP_LOG_FILE:-/data/logs/act_runner/cleanup.log}"
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
__log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" >>"$RUNNER_CLEANUP_LOG_FILE" 2>&1; }
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Run a prune command, log its reclaimed-space line; a failure is logged, never fatal
__prune() {
	local output=""
	if output="$("$@" 2>&1)"; then
		__log "$* :: $(printf '%s\n' "$output" | grep -i -- 'reclaimed' | tail -n1)"
	else
		__log "FAILED: $* :: $output"
	fi
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Print the usage percent of the filesystem holding $1
__disk_percent() {
	df -P "$1" 2>/dev/null | awk 'NR==2 {gsub("%", "", $5); print $5}'
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if [ "$1" = "--help" ] || [ "$1" = "-h" ]; then
	printf '%s\n' "Usage: cleanup-runners [--help|--version]" \
		"Prunes docker containers, volumes, networks, build cache and images left by act runner jobs." \
		"Env: RUNNER_CLEANUP_UNTIL RUNNER_CLEANUP_DISK_PERCENT RUNNER_CLEANUP_DOCKER_DIR" \
		"     RUNNER_CLEANUP_ACT_CACHE_DAYS RUNNER_CLEANUP_ACT_CACHE_DIRS RUNNER_CLEANUP_LOG_FILE"
	exit 0
elif [ "$1" = "--version" ]; then
	echo "$VERSION"
	exit 0
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
mkdir -p "$(dirname -- "$RUNNER_CLEANUP_LOG_FILE")"
if ! docker info >/dev/null 2>&1; then
	__log "docker is not reachable, skipping docker cleanup"
else
	__log "Starting cleanup"
	# Exited job containers left behind when a runner died mid-job (running containers are never touched)
	__prune docker container prune -f --filter "until=$RUNNER_CLEANUP_UNTIL"
	# Job networks that no container uses anymore
	__prune docker network prune -f --filter "until=$RUNNER_CLEANUP_UNTIL"
	# Unused act-* job volumes; docker recreates a named volume if a starting job needs it
	act_volumes="$(docker volume ls -q --filter dangling=true --filter name=act- 2>/dev/null || true)"
	if [ -n "$act_volumes" ]; then
		# shellcheck disable=SC2086
		__prune docker volume rm $act_volumes
	fi
	# Anonymous volumes no container uses
	__prune docker volume prune -f
	# Build cache from jobs that run docker build
	__prune docker builder prune -af --filter "until=$RUNNER_CLEANUP_UNTIL"
	# Untagged (dangling) images
	__prune docker image prune -f
	# Every image not used by a container, only when disk is getting full; jobs re-pull what they need
	disk_used="$(__disk_percent "$RUNNER_CLEANUP_DOCKER_DIR" || true)"
	if [[ "$disk_used" =~ ^[0-9]+$ ]] && [ "$disk_used" -ge "$RUNNER_CLEANUP_DISK_PERCENT" ]; then
		__log "$RUNNER_CLEANUP_DOCKER_DIR is ${disk_used}% used (limit ${RUNNER_CLEANUP_DISK_PERCENT}%), removing unused images"
		__prune docker image prune -af
	fi
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Cloned actions (one directory per action@ref) that have not been updated recently
if [[ "$RUNNER_CLEANUP_ACT_CACHE_DAYS" =~ ^[1-9][0-9]*$ ]]; then
	for act_cache_dir in $RUNNER_CLEANUP_ACT_CACHE_DIRS; do
		[ -d "$act_cache_dir" ] || continue
		removed="$(find "$act_cache_dir" -mindepth 1 -maxdepth 1 -mtime +"$RUNNER_CLEANUP_ACT_CACHE_DAYS" 2>/dev/null | wc -l || true)"
		find "$act_cache_dir" -mindepth 1 -maxdepth 1 -mtime +"$RUNNER_CLEANUP_ACT_CACHE_DAYS" -exec rm -rf {} + 2>/dev/null || true
		__log "Removed $removed stale entries from $act_cache_dir"
	done
fi
__log "Cleanup finished"
exit 0
