#!/usr/bin/env bash
###############################################################################
# infra/agent/build-image.sh — build the pinned `agent-runner` image and prove it works.
#
#   ./build-image.sh                 # build + verify + print the image id
#   ./build-image.sh --no-verify     # build only (skip the in-image proof)
#   ENGINE=docker ./build-image.sh   # build with docker instead of podman
#   AGENT_BASE_IMAGE=home-k3s-dev:local ./build-image.sh
#                                    # build on a LOCAL toolbox instead of the pinned one
#                                    #   (`infra/devcontainer/dev.sh build` makes that tag)
#   IMAGE_TAG=foo ./build-image.sh   # override the local tag (CI uses this)
#
# THIS SCRIPT NEVER PUSHES — and nobody pushes this image from a workstation either.
# Publishing is done by CI: .gitea/workflows/images.yaml calls this script, and on a push to
# `main` it pushes what this script built AND verified to the Gitea registry, records the
# registry-returned digest in the job summary, and Renovate then opens the pull request that
# moves platform/pm-agent/ onto that digest. So this script's job is to build, and to prove
# the toolchain and both entrypoints work INSIDE the image as the non-root uid with the
# read-only root filesystem the admission policy forces — the same proof locally and in CI.
#
# VERSIONS ARE NOT DEFINED HERE. infra/agent/versions.env holds the pins this image adds
# (base image, node, Claude Code CLI, model) and infra/devcontainer/versions.env holds the
# platform toolchain the base already carries. Nothing in this file invents a version.
#
# THE BASE. AGENT_BASE_IMAGE in versions.env is the PUBLISHED toolbox, pinned by digest and
# kept current by Renovate. An AGENT_BASE_IMAGE in the environment overrides it — CI passes
# the toolbox it built in the same run, and a developer can pass `home-k3s-dev:local`.
#
# ENGINE PORTABILITY. CI runs this with ENGINE=docker against a Docker-in-Docker daemon, so
# nothing below may be podman-only (`image exists`, `--digestfile`, `{{.Digest}}`), and
# nothing may BIND-MOUNT a file from this checkout into a container: under DinD the daemon
# resolves bind sources on ITS filesystem, where this checkout does not exist, and silently
# mounts an empty directory instead. Files go in over stdin.
###############################################################################
set -euo pipefail

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "${HERE}/../.." && pwd)"
ENGINE="${ENGINE:-podman}"

VERIFY=1
for arg in "$@"; do
  case "$arg" in
    --no-verify) VERIFY=0 ;;
    -h|--help) sed -n '2,/^####/p' "${BASH_SOURCE[0]}" | sed '$d' | sed 's/^# \{0,1\}//'; exit 0 ;;
    *) echo "unknown argument: $arg" >&2; exit 2 ;;
  esac
done

log()  { printf '\n\033[1m==> %s\033[0m\n' "$*"; }
info() { printf '    %s\n' "$*"; }
die()  { printf '\033[31mERROR: %s\033[0m\n' "$*" >&2; exit 1; }

command -v "${ENGINE}" >/dev/null 2>&1 || die "'${ENGINE}' not on PATH (set ENGINE=docker to use docker)"

# --- pins: sourced, never invented -------------------------------------------
AGENT_ENV="${HERE}/versions.env"
[ -f "${AGENT_ENV}" ] || die "missing ${AGENT_ENV} — the pins live there, not here"
BASE_OVERRIDE="${AGENT_BASE_IMAGE:-}"
TAG_OVERRIDE="${IMAGE_TAG:-}"
# shellcheck disable=SC1090
source "${AGENT_ENV}"
[ -z "${BASE_OVERRIDE}" ] || AGENT_BASE_IMAGE="${BASE_OVERRIDE}"
: "${AGENT_BASE_IMAGE:?AGENT_BASE_IMAGE not set in ${AGENT_ENV}}"
: "${NODEJS_MAJOR:?NODEJS_MAJOR not set in ${AGENT_ENV}}"
: "${CLAUDE_CODE_VERSION:?CLAUDE_CODE_VERSION not set in ${AGENT_ENV}}"
: "${CLAUDE_CODE_MIN_VERSION:?CLAUDE_CODE_MIN_VERSION not set in ${AGENT_ENV}}"
: "${AGENT_MODEL:?AGENT_MODEL not set in ${AGENT_ENV}}"
: "${AGENT_IMAGE_REPO:?AGENT_IMAGE_REPO not set in ${AGENT_ENV}}"

# --- the base must exist, locally or in the registry ---------------------------
# Deliberately NOT built on demand. The toolbox is its own reviewed artefact with its own
# pins, and silently building it here would mean this script could change the toolchain a
# worker gates with as a side effect of rebuilding the agent image.
case "${AGENT_BASE_IMAGE}" in
  *@sha256:0000000000000000000000000000000000000000000000000000000000000000)
    die "AGENT_BASE_IMAGE is still the all-zero placeholder in ${AGENT_ENV}: the toolbox has
       not been published yet. Either let CI publish it (.gitea/workflows/images.yaml) and
       merge Renovate's digest bump, or build on a local toolbox:
         ${REPO_ROOT}/infra/devcontainer/dev.sh build
         AGENT_BASE_IMAGE=home-k3s-dev:local $0" ;;
esac
if ! "${ENGINE}" image inspect "${AGENT_BASE_IMAGE}" >/dev/null 2>&1; then
  info "base ${AGENT_BASE_IMAGE} is not local; pulling it"
  "${ENGINE}" pull "${AGENT_BASE_IMAGE}" >/dev/null \
    || die "base image '${AGENT_BASE_IMAGE}' is neither local nor pullable (registry login?).
       To build on a local toolbox instead:
         ${REPO_ROOT}/infra/devcontainer/dev.sh build
         AGENT_BASE_IMAGE=home-k3s-dev:local $0"
fi

IMAGE_TAG="${TAG_OVERRIDE:-claude${CLAUDE_CODE_VERSION}-node${NODEJS_MAJOR}}"
IMAGE_REF="${AGENT_IMAGE_REPO}:${IMAGE_TAG}"

log "Building ${IMAGE_REF}"
info "engine        ${ENGINE} ($(${ENGINE} --version 2>/dev/null | head -1))"
info "pins from     ${AGENT_ENV}"
info "  base        ${AGENT_BASE_IMAGE}"
info "  node        ${NODEJS_MAJOR}"
info "  claude      ${CLAUDE_CODE_VERSION} (floor ${CLAUDE_CODE_MIN_VERSION})"
info "  model       ${AGENT_MODEL}"

# Provenance: CI passes the commit it is building, so a pulled image names its source tree.
LABEL_ARGS=()
[ -z "${BUILD_REVISION:-}" ] || LABEL_ARGS+=(--label "org.opencontainers.image.revision=${BUILD_REVISION}")

"${ENGINE}" build "${LABEL_ARGS[@]}" \
  --file "${HERE}/Containerfile" \
  --tag "${IMAGE_REF}" \
  --build-arg "AGENT_BASE_IMAGE=${AGENT_BASE_IMAGE}" \
  --build-arg "NODEJS_MAJOR=${NODEJS_MAJOR}" \
  --build-arg "CLAUDE_CODE_VERSION=${CLAUDE_CODE_VERSION}" \
  --build-arg "CLAUDE_CODE_MIN_VERSION=${CLAUDE_CODE_MIN_VERSION}" \
  --build-arg "AGENT_MODEL=${AGENT_MODEL}" \
  "${HERE}"

# --- verify: the point of the whole exercise ---------------------------------
# A build that merely succeeded is not evidence this image is usable. Prove the tools
# EXECUTE, as the NON-ROOT uid, with a READ-ONLY root filesystem and only the two volumes
# the admission policy admits — the exact shape a worker Job runs in. Anything that works
# here but not there is a 3am discovery.
if [ "${VERIFY}" -eq 1 ]; then
  log "Verifying inside the image (uid 65532, read-only rootfs, workspace+tmp only)"
  "${ENGINE}" run --rm \
    --user 65532:65532 \
    --read-only \
    --tmpfs /workspace:rw,mode=1777 \
    --tmpfs /tmp:rw,mode=1777 \
    --network none \
    --entrypoint "" \
    "${IMAGE_REF}" \
    /bin/bash -euo pipefail -c '
      echo "--- id ---";                id
      echo "--- HOME ---";              echo "HOME=${HOME}  CLAUDE_CONFIG_DIR=${CLAUDE_CONFIG_DIR}"
      echo "--- baked versions ---";    cat /etc/agent-runner-versions
      echo "--- the gate toolchain the worker needs (CLAUDE.md §3) ---"
      for t in git python3 bash yamllint check-jsonschema kyverno promtool chainsaw flux sops age kubectl jq diff; do
        if command -v "$t" >/dev/null 2>&1; then printf "    ok      %s\n" "$t";
        else printf "    MISSING %s\n" "$t"; missing=1; fi
      done
      [ -z "${missing:-}" ] || { echo "the gate cannot run in this image"; exit 1; }
      echo "--- python can import the renderer dependency ---"
      python3 -c "import yaml; print(\"PyYAML\", yaml.__version__)"
      echo "--- claude ---";             claude --version
      echo "--- the two entrypoints refuse arguments ---"
      /usr/local/bin/pm-worker   --anything 2>&1 | grep -q "takes no arguments" && echo "    pm-worker: rejected"
      /usr/local/bin/pm-dispatch --anything 2>&1 | grep -q "takes no arguments" && echo "    pm-dispatch: rejected"
      echo "--- the dispatcher selftest (branch vocabulary, result envelopes, Job template, persona) ---"
      PM_SELFTEST=1 /usr/local/bin/pm-dispatch
      echo "--- the entrypoints are root-owned and NOT writable by the runtime uid ---"
      for f in /usr/local/bin/pm-worker /usr/local/bin/pm-dispatch /etc/pm-agent/worker-job-template.yaml; do
        stat -c "    %n %U:%G %a" "$f"
        if [ -w "$f" ]; then echo "UNEXPECTED: uid $(id -u) can write $f"; exit 1; fi
      done
      echo "    confirmed: not writable by uid $(id -u)"
      echo "--- rootfs is read-only (expected: a failure) ---"
      if touch /should-fail 2>/dev/null; then echo "UNEXPECTED: rootfs is writable"; exit 1; fi
      echo "    confirmed: / is read-only"
      echo "--- the two writable paths really are writable ---"
      touch "${HOME}/.probe" /tmp/.probe && echo "    confirmed: ${HOME} and /tmp are writable"
      echo "--- uid is non-zero ---"
      [ "$(id -u)" -ne 0 ] && echo "    confirmed: uid $(id -u), not root"
      echo "--- no Anthropic API key is baked into the image (it would outrank the subscription token) ---"
      [ -z "${ANTHROPIC_API_KEY:-}${ANTHROPIC_AUTH_TOKEN:-}" ] && echo "    confirmed: neither is set"
    '
  # The worker's input guards, exercised in the image, with the interpreter and the script
  # that will actually run in the cluster. The probe is mounted read-only rather than baked
  # in: it is a build-time check, not something a worker Job has any business carrying.
  log "Probing pm-worker's input validation inside the image"
  #
  # The probe goes in over STDIN, not as a bind mount: under Docker-in-Docker (CI) a bind
  # source is resolved on the daemon's filesystem, where this file does not exist, and the
  # container would get an empty directory. PM_WORKER_PATH points it at the baked worker,
  # since the probe's own default (a sibling of the probe file) has no meaning on stdin.
  "${ENGINE}" run --rm -i \
    --user 65532:65532 \
    --read-only \
    --tmpfs /workspace:rw,mode=1777 \
    --tmpfs /tmp:rw,mode=1777 \
    --network none \
    -e PM_WORKER_PATH=/usr/local/bin/pm-worker \
    --entrypoint "" \
    "${IMAGE_REF}" \
    /bin/bash -s < "${HERE}/probe-validation.sh"

  log "Image verified"
fi

# --- result ------------------------------------------------------------------
# No digest is printed: a manifest digest does not exist until a registry has the manifest,
# and the only digest anything may pin is the one the REGISTRY returns. CI captures that at
# push time and prints it in the job summary (.gitea/workflows/scripts/images.sh).
SIZE="$("${ENGINE}" image inspect --format '{{.Size}}' "${IMAGE_REF}")"
log "Built ${IMAGE_REF}"
info "image id  $("${ENGINE}" image inspect --format '{{.Id}}' "${IMAGE_REF}")"
info "size      $(( SIZE / 1024 / 1024 )) MiB"
info "Not pushed. CI publishes this image from main (.gitea/workflows/images.yaml); see"
info "platform/pm-agent/README.md for how a new digest reaches the cluster."