#!/usr/bin/env bash
# ci-reclaim-docker.sh — free disk on the CI runner's Docker daemon WITHOUT
# deleting a smoke image that another job is still testing.
#
# Used by every docker-publish.yml job that reclaims disk (build-base, smoke,
# smoke-studio, build-variant, build-variant-studio). Not shipped in the image.
#
#   bash scripts/ci-reclaim-docker.sh                       # reclaim (default)
#   bash scripts/ci-reclaim-docker.sh assert-protected IMG  # smoke preflight
#   bash scripts/ci-reclaim-docker.sh hold IMG              # pin IMG while testing
#   bash scripts/ci-reclaim-docker.sh release IMG           # drop the pin + IMG
#   bash scripts/ci-reclaim-docker.sh lint WORKFLOW...      # lint.yml guard
#
# WHY THIS EXISTS. Everything that runs on one runner host shares its Docker
# daemon: concurrent jobs of a runner with capacity > 1 (runner-a1 had
# smoke-studio and build-variant going together in run 740), and the jobs of
# other act_runner containers on the same VM (runner-2 has one registered with
# gitea.jordbo.se and one with gitea.egl.lan). Each pi-devbox job used to start
# with `docker system prune -af --volumes`. That removes every image no
# container is using at that instant, and a smoke image is
# exactly that for most of its life: smoke-test.sh runs one `docker run --rm`
# per assertion, so between assertions nothing holds the image. v1.12.2 run 740
# (2026-10-22): smoke passed, build-variant started and pruned, and its log
# shows `untagged: pi-devbox:smoke-studio` at 22:58:49.11Z, 30 ms after
# smoke-studio had imported that image (22:58:49.08Z). Every smoke-studio
# assertion then failed with "Unable to find image 'pi-devbox:smoke-studio'
# locally", build-variant-studio was skipped, and the release went out without
# its -studio tags. Job ORDER cannot close this: smoke and smoke-studio prune
# each other too whenever their start times drift apart, and other runs share
# the daemon. Two defences, because we only control our own jobs:
#   - the smoke images carry a label, and this script never prunes an image
#     that has it (covers pi-devbox's own jobs, before and during the test);
#   - `hold` starts a container from the image for the whole smoke step. No
#     prune removes an image a running container uses, so this also covers
#     jobs that never call this script (opencode-devbox's raw prunes,
#     anything gitea.egl.lan runs). What is left is the few seconds between
#     the build step loading the image and `hold` starting.
#
# WHAT IT DOES. The same reclaim as `docker system prune -af --volumes` +
# `docker builder prune -af`, done per object type so the image step can take
# a filter:
#   1. stopped containers                  (running ones are never touched)
#   2. unused images WITHOUT the label     (the old `system prune -a` image step)
#   3. unused images WITH the label, older than SMOKE_IMAGE_MAX_AGE
#      — orphans of a smoke job that died before its own cleanup step
#   4. unused networks, anonymous volumes  (what `system prune --volumes` did)
#   5. the build cache
# Each step is `|| true`, as before: failing to reclaim disk must not fail the
# job. A filter the daemon rejected would show up as an error line in the log.
#
# `assert-protected IMG` is the smoke jobs' preflight: it fails unless IMG is in
# the daemon AND carries the label. Without it, a build that silently lost the
# label would look fine until the next time a sibling job's prune landed
# mid-test; and a missing image gets one clear error line instead of every
# assertion failing with "Unable to find image ... locally".
#
# `lint WORKFLOW...` fails if any workflow runs `docker system prune` or
# `docker image prune` itself. One such line in any job reopens the race, so
# lint.yml runs this on every push rather than relying on review.
#
# Environment:
#   SMOKE_IMAGE_LABEL    label key that protects an image (default below; the
#                        workflow sets it once in its top-level env)
#   SMOKE_IMAGE_MAX_AGE  `until=` value for the orphan sweep (default 6h; a
#                        smoke job takes ~10 min). Compared against the image's
#                        Created time, which is the build time: nothing here
#                        sets SOURCE_DATE_EPOCH.
set -u

SMOKE_IMAGE_LABEL="${SMOKE_IMAGE_LABEL:-se.jordbo.pi-devbox.ci-smoke-image}"
SMOKE_IMAGE_MAX_AGE="${SMOKE_IMAGE_MAX_AGE:-6h}"

step() { printf '+ %s\n' "$*"; "$@" || true; }

reclaim() {
  step docker container prune -f
  step docker image prune -af --filter "label!=${SMOKE_IMAGE_LABEL}"
  step docker image prune -af --filter "label=${SMOKE_IMAGE_LABEL}" \
    --filter "until=${SMOKE_IMAGE_MAX_AGE}"
  step docker network prune -f
  step docker volume prune -f
  step docker builder prune -af
}

assert_protected() {
  local img="${1:?usage: $0 assert-protected <image>}" val
  if ! val=$(docker image inspect \
      --format "{{ index .Config.Labels \"${SMOKE_IMAGE_LABEL}\" }}" "$img" 2>&1); then
    echo "::error::${img} is not in the runner's Docker daemon (${val}). Was it removed by a concurrent prune that does not honour ${SMOKE_IMAGE_LABEL}?"
    return 1
  fi
  if [ "$val" != "true" ]; then
    echo "::error::${img} lacks the label ${SMOKE_IMAGE_LABEL}=true (got '${val}'), so a sibling job's reclaim could delete it mid-test. Check the build step's labels: input."
    return 1
  fi
  echo "OK: ${img} is present and carries ${SMOKE_IMAGE_LABEL}=true"
}

holder_name() { printf 'ci-hold-%s' "$(printf '%s' "$1" | tr -c 'A-Za-z0-9_.-' '_')"; }

# The holder exits on its own after an hour (--rm), so a job killed before
# `release` does not pin its image forever; the age sweep then removes it.
hold() {
  local img="${1:?usage: $0 hold <image>}" name
  name=$(holder_name "$img")
  docker rm -f "$name" >/dev/null 2>&1 || true
  if ! docker run -d --rm --name "$name" --network none --entrypoint "" \
      "$img" sleep 3600 >/dev/null; then
    echo "::error::could not start holder ${name} for ${img}; is the image still in the daemon?"
    return 1
  fi
  echo "OK: ${img} pinned by running container ${name} (exits by itself after 1 h)"
}

release() {
  local img="${1:?usage: $0 release <image>}"
  docker rm -f "$(holder_name "$img")" >/dev/null 2>&1 || true
  docker image rm "$img" >/dev/null 2>&1 || true
  echo "released ${img}"
}

lint_workflows() {
  [ "$#" -gt 0 ] || { echo "usage: $0 lint <workflow.yml>..." >&2; return 2; }
  local hits
  hits=$(grep -nE '^[^#]*docker[[:space:]]+(system|image)[[:space:]]+prune' "$@" || true)
  if [ -n "$hits" ]; then
    echo "::error::raw docker prune in a workflow. It deletes smoke images other jobs are testing on the shared runner daemon; call 'bash scripts/ci-reclaim-docker.sh' instead."
    printf '%s\n' "$hits"
    return 1
  fi
  echo "OK: no raw 'docker system|image prune' in $# workflow file(s)"
}

case "${1:-reclaim}" in
  reclaim)          reclaim ;;
  assert-protected) shift; assert_protected "$@" ;;
  hold)             shift; hold "$@" ;;
  release)          shift; release "$@" ;;
  lint)             shift; lint_workflows "$@" ;;
  *) echo "usage: $0 [reclaim | assert-protected <image> | hold <image> | release <image> | lint <workflow.yml>...]" >&2; exit 2 ;;
esac