#!/usr/bin/env bash
# ubi-runner — run a command on an ephemeral Ubicloud VM.
#
#   UBICLOUD_API_KEY=... scripts/ubicloud/ubi-runner.sh run --setup S.sh -- 'make test'
#
# UBICLOUD_API_TOKEN is accepted as an alias for UBICLOUD_API_KEY. SSH
# connections are multiplexed per VM, and `pack` / `unpack` upload one prebuilt
# checkout tarball to many VMs. This is the repo copy the user-scope Capy
# `ubicloud` skill and gbrain's scripts/ubicloud/ubi-runner.sh are kept in sync
# with (plan E2); `bun run test:ubicloud` drives it through test-free.sh.
#
# Scratch record: every VM this machine creates is appended to a VM-id file
# (UBI_VM_RECORD; default ~/.capy/work/ubi-runner/vms.tsv when ~/.capy/work
# exists, else $STATE_ROOT/vms.tsv) as `name location owner created_at pid`,
# and removed once `down` confirms it gone. A resumed Capy thread reads that
# file to find VMs an earlier turn left behind (docs/TESTING_INTERNALS.md,
# "Resuming after a wake").
#
# Creates a VM (standard-16 by default), streams the checkout to it (tracked +
# untracked-unignored files + .git, so uncommitted edits are included), runs an
# optional setup script and the command, copies requested artifacts back, and
# destroys the VM on every exit path. Exits with the command's status.
# Needs only bash, curl, python3, ssh, ssh-keygen, and tar locally, so it works
# from dev boxes, containers, and cloud sandboxes.
#
# Ownership: VMs are named ubirun-<owner>-<epoch>-<suffix>-t<hours>. <owner> is UBI_OWNER
# (lowercased, letters and digits only, at most 12 characters, starting with a
# letter). `up`, `run` and `verify` refuse without it (UBI_OWNER_REQUIRED), so
# every VM names whoever can be asked about it; read-only commands fall back to a
# per-machine id kept in $STATE_ROOT/owner-id. Ubicloud names allow 63 characters
# of [a-z0-9-], so a full name stays under 45.
#
# Teardown: `up` records each VM's state (location, create status) before it
# sends the create request, and `down` destroys and polls until the VM is
# confirmed gone or provably never existed, waiting out a create that may still
# be in flight. An interrupted `up` or `run` (EXIT, INT, TERM, QUIT, and HUP
# until a remote phase is live) runs that `down`; further signals are ignored
# until it finishes. A create refused
# for vCPU quota prints the project's usage per owner.
#
# The owner-age sweep is off by default (the TTL reap below always runs). With UBI_GC_HOURS set to a positive
# number, every `up` first destroys this owner's VMs older than that; `gc HOURS`
# runs the same sweep on demand. Neither ever touches another owner's VMs.
#
# TTL and reaper: a name this script generates ends in -t<hours> (UBI_TTL_HOURS,
# 1-999, default 3), the creator's own declaration of how long the VM may live.
# `reap` destroys every VM in the project whose TTL expired more than ten
# minutes ago, whichever owner made it, and this owner's own ubirun-<owner>-*
# names with no TTL once they are UBI_LEGACY_HOURS old (default 4; another
# owner's or an untagged TTL-less VM is never reaped); every `up` runs it first (UBI_REAP=0 skips it), so a runner
# killed by a sleeping machine leaves nothing behind for longer than its TTL.
# Names outside the ubirun- prefix are never reaped.
#
# Leftover line: `run` and `verify` end with
#   UBICLOUD: left=<0|1|unknown> owner=<owner> vm=<name> others=<n>
# after teardown: left counts this invocation's own VM, checked against the
# project's VM list, and others counts this owner's other VMs (information only).
# A left other than 0 turns a passing command into exit 1; `run --keep` reports
# its live VM as left=1 kept=1 and keeps its exit status. With UBI_LEFT_FILE set,
# the line is also appended to that file, out of reach of the command's output.
#
# Quota preflight: when the project's vCPU ceiling is known (UBI_QUOTA_VCPUS, or
# the maximum a refusal printed, cached in $STATE_ROOT/quota-max), `up` adds the
# size's vCPUs to the project's running VMs and refuses before any create when
# that exceeds it; UBI_QUOTA_WAIT=<seconds> waits for room instead.
#
# Watchdog: `run`, `verify` and `ssh NAME COMMAND` stream the remote output
# through a watchdog that logs a heartbeat every UBI_HEARTBEAT seconds (300)
# and kills a command silent for UBI_IDLE_TIMEOUT seconds (1800) or older than
# UBI_RUN_TIMEOUT seconds (0, unlimited), exiting 124 with the last 40 lines,
# so a hung verify fails fast instead of holding the VM until its TTL.
#
# Detached phases and reattach: `run` and `verify` start their setup, command
# and tier phases on the VM detached from the ssh connection (setsid; stdout to
# ~/.ubirun-<phase>.out, stderr to .err, the session leader's pid in .pid, and
# the exit status in .exit, written by rename once the streams are closed) and
# stream both files back. Before creating a VM they compute a run key locally
# (the checkout's content tree, the command, the setup script's content, every
# --env entry, each --pass name with a sha256 of its value, size, location,
# image, storage, origin/HEAD, tiers and this script's own sha256) and look for
# a run record (<state dir>/<vm>/run) with the same key whose VM still exists:
# its runner alive (lease pid and start time) refuses with UBI_ATTACH_BUSY,
# otherwise the run reattaches, printing `reattached to <vm> created_at=<epoch>
# key=<k12>`, and continues from the first phase without an exit file. After
# unpack the VM recomputes the tree and refuses a mismatch (UBI_VM_TREE_MISMATCH).
# A leader gone with no exit file exits 125 (UBI_ATTACH_LOST). Signals: INT
# and TERM tear the VM down as before; HUP once a remote phase is live detaches
# (UBI_DETACHED, exit 129) and leaves the VM under its TTL; SIGKILL or a machine
# stop leaves the record and the VM, and the next run of the same command
# reattaches. `attach NAME` resumes a recorded run explicitly. Reattach never
# extends a TTL, and the reaper still applies.
#
# Tier checkpoints: a .gstack/ubicloud.json with `tiers` runs each tier as its
# own detached phase after setup, and records start/pass/fail per tier under
# UBI_CHECKPOINT_DIR/<run key>/ (write-once JSON plus the tier's log, published
# under a lock with a monotonic generation). A rerun reuses a pass younger than
# UBI_CHECKPOINT_MAX_AGE whose log re-hashes, so a resume on a fresh VM reruns
# only setup and the tiers without a pass.
#
# `verify` is the one entry point for a repository's full remote verify: it
# reads .gstack/ubicloud.json (setup, command, size, location, env, pass, pull)
# and runs it through `run`, so lanes share one committed definition instead of
# per-lane wrappers.
set -euo pipefail
# Keep heredoc bodies on temp files, not the pipe window (test/heredoc-pipe-deadlock.test.ts).
BASH_COMPAT=50

API="${UBICLOUD_API_URL:-https://api.ubicloud.com}"
STATE_ROOT="${UBI_RUNNER_STATE:-${XDG_STATE_HOME:-$HOME/.local/state}/ubi-runner}"
DEFAULT_SIZE="${UBI_SIZE:-standard-16}"
DEFAULT_LOCATION="${UBI_LOCATION:-eu-central-h1}"
GC_HOURS="${UBI_GC_HOURS:-0}"
API_TIMEOUT="${UBI_API_TIMEOUT:-120}"
CREATE_GRACE="${UBI_CREATE_GRACE:-180}"
DOWN_TIMEOUT="${UBI_DOWN_TIMEOUT:-900}"
POLL="${UBI_POLL_SECONDS:-5}"
ALLOWED_STORAGE="${UBI_ALLOWED_STORAGE:-320 640}"
TTL_HOURS="${UBI_TTL_HOURS:-3}"
LEGACY_HOURS="${UBI_LEGACY_HOURS:-4}"
REAP="${UBI_REAP:-1}"
REAP_GRACE=600
IDLE_TIMEOUT="${UBI_IDLE_TIMEOUT:-1800}"
RUN_TIMEOUT="${UBI_RUN_TIMEOUT:-0}"
HEARTBEAT="${UBI_HEARTBEAT:-300}"
QUOTA_VCPUS="${UBI_QUOTA_VCPUS:-}"
QUOTA_WAIT="${UBI_QUOTA_WAIT:-0}"
PREFIX="ubirun"
if [ -n "${UBI_VM_RECORD:-}" ]; then VM_RECORD="$UBI_VM_RECORD"
elif [ -d "$HOME/.capy/work" ]; then VM_RECORD="$HOME/.capy/work/ubi-runner/vms.tsv"
else VM_RECORD="$STATE_ROOT/vms.tsv"; fi
if [ -n "${UBI_CHECKPOINT_DIR:-}" ]; then CHECKPOINT_DIR="$UBI_CHECKPOINT_DIR"
elif [ -d "$HOME/.capy/work" ]; then CHECKPOINT_DIR="$HOME/.capy/work/ubi-runner/checkpoints"
else CHECKPOINT_DIR="$STATE_ROOT/checkpoints"; fi
CHECKPOINT_MAX_AGE="${UBI_CHECKPOINT_MAX_AGE:-86400}"
REATTACH_MARGIN="${UBI_REATTACH_MARGIN:-900}"

die() { echo "ubi-runner: $*" >&2; exit 1; }
log() { echo "ubi-runner: $*" >&2; }

for bin in curl python3 ssh ssh-keygen tar; do
  command -v "$bin" >/dev/null || die "$bin is required"
done
UBICLOUD_API_KEY="${UBICLOUD_API_KEY:-${UBICLOUD_API_TOKEN:-}}"
[[ "$GC_HOURS" =~ ^[0-9]+$ ]] || die "UBI_GC_HOURS must be a whole number of hours (unset or 0 disables the sweep)"
for v in IDLE_TIMEOUT RUN_TIMEOUT HEARTBEAT QUOTA_WAIT CHECKPOINT_MAX_AGE REATTACH_MARGIN; do
  [[ "${!v}" =~ ^[0-9]+$ ]] || die "UBI_$v must be a whole number of seconds (0 disables it)"
done
[ -z "$QUOTA_VCPUS" ] || [[ "$QUOTA_VCPUS" =~ ^[0-9]+$ ]] || die "UBI_QUOTA_VCPUS must be a whole number of vCPUs"

owner_id() {
  local raw=${UBI_OWNER:-} file="$STATE_ROOT/owner-id" tmp
  if [ -z "$raw" ]; then
    if [ ! -s "$file" ]; then
      mkdir -p "$STATE_ROOT"
      tmp="$file.$$"
      echo "m$(head -c4 /dev/urandom | od -An -tx1 | tr -d ' \n')" >"$tmp"
      mv -n "$tmp" "$file"
      rm -f "$tmp"
    fi
    raw=$(cat "$file")
  fi
  raw=$(printf %s "$raw" | tr '[:upper:]' '[:lower:]' | tr -cd 'a-z0-9')
  [ -n "$raw" ] || die "UBI_OWNER must contain letters or digits"
  [[ "$raw" =~ ^[a-z] ]] || raw="u$raw"
  echo "${raw:0:12}"
}
OWNER=$(owner_id)

# require_owner: up, run and verify create VMs, and a VM must name its owner
# and carry a TTL. Only creates check UBI_TTL_HOURS, so an old value never
# blocks down, reap or list.
require_owner() {
  [ -n "${UBI_OWNER:-}" ] || die "UBI_OWNER is not set: every VM must carry its owner; export UBI_OWNER=<your thread or session code> (for example gsta164) and rerun (UBI_OWNER_REQUIRED)"
  [[ "$TTL_HOURS" =~ ^[1-9][0-9]{0,2}$ ]] || die "UBI_TTL_HOURS must be a whole number of hours from 1 to 999 with no leading zero (every VM carries a TTL; set it above your longest run)"
}

# leftover FIELDS...: print the UBICLOUD: leftover line, and append it to
# UBI_LEFT_FILE when set, so a caller can read it apart from the command's output.
leftover() {
  echo "UBICLOUD: $*" >&2
  [ -z "${UBI_LEFT_FILE:-}" ] || echo "UBICLOUD: $*" >>"$UBI_LEFT_FILE"
}

# api OUT ARGS...: send one Ubicloud CLI command, write the body to OUT, and
# print the HTTP status (000 when no response arrived).
api() {
  local out=$1 code
  shift
  code=$(python3 -c 'import json,sys; print(json.dumps({"argv": sys.argv[1:]}))' "$@" \
    | curl -sS -o "$out" -w '%{http_code}' --max-time "$API_TIMEOUT" -X POST \
        -H "Authorization: Bearer $UBICLOUD_API_KEY" \
        -H 'Accept: text/plain' -H 'Content-Type: application/json' \
        -H 'X-Ubi-Version: 1.0.0' --data @- "$API/cli") || true
  echo "${code:-000}"
}

cli() {
  local out code
  out=$(mktemp)
  code=$(api "$out" "$@")
  if [ "$code" = 000 ]; then
    rm -f "$out"
    die "request failed: ubi $*"
  fi
  if [ "$code" != 200 ]; then
    cat "$out" >&2
    rm -f "$out"
    return 1
  fi
  cat "$out"
  rm -f "$out"
}

state_dir() { echo "$STATE_ROOT/$1"; }

load() {
  local dir
  dir=$(state_dir "$1")
  [ -f "$dir/env" ] || die "no local state for VM '$1' (created on another machine?)"
  # shellcheck disable=SC1091
  . "$dir/env"
  KEY="$dir/key"
}

ssh_opts() {
  echo -i "$KEY" -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \
    -o LogLevel=ERROR -o ServerAliveInterval=30 -o ServerAliveCountMax=6 -o ConnectTimeout=10 \
    -o ControlMaster=auto -o "ControlPath=$(dirname "$KEY")/ctl" -o ControlPersist=300
}

# Ubuntu's default umask (002) leaves new directories group-writable, which
# permission-checking code under test rejects; every remote command uses 022.
remote() {
  local name=$1; shift
  load "$name"
  # shellcheck disable=SC2046
  ssh $(ssh_opts) "ubi@$IP" "umask 022; $*"
}

mtime() { stat -c %Y "$1" 2>/dev/null || stat -f %m "$1"; }

# sq STRING: STRING as one single-quoted shell word.
sq() { printf "'%s'" "$(printf %s "$1" | sed "s/'/'\\\\''/g")"; }

# remote_cancel NAME SIDFILE: end the session a watched command started on the
# VM (its leader pid is in SIDFILE there), bounded to 20 seconds. Killing the
# local ssh client alone leaves a silent remote command running until it next
# writes to the closed channel.
remote_cancel() {
  local name=$1 sidf=$2 cpid i=0
  remote "$name" "sid=\$(cat $sidf 2>/dev/null); rm -f $sidf; [ -z \"\$sid\" ] || { pkill -TERM -s \"\$sid\"; sleep 2; pkill -KILL -s \"\$sid\"; }; true" >/dev/null 2>&1 </dev/null &
  cpid=$!
  while kill -0 "$cpid" 2>/dev/null && [ "$i" -lt 20 ]; do sleep 1; i=$(( i + 1 )); done
  kill "$cpid" 2>/dev/null || true
  wait "$cpid" 2>/dev/null || true
}

# watched NAME PHASE COMMAND: run COMMAND on the VM, streaming its output and
# keeping a copy of both streams in the VM's state dir, with a heartbeat every HEARTBEAT
# seconds and a watchdog that kills it after IDLE_TIMEOUT seconds of silence or
# RUN_TIMEOUT seconds in total: exit 124, reason and the last 40 lines on
# stderr. The ssh runs in its own session (python3's setsid) so the watchdog
# kills it and anything it started, not just the shell that launched it; on
# the VM the command runs in its own session too (setsid where the image has
# it), whose leader pid is written to ~/.ubirun-PHASE-<runner pid>.sid so
# remote_cancel can end it when the client is killed.
watched() {
  local name=$1 phase=$2 cmd=$3 out pid rc=0 start now last_beat idle elapsed why="" old_traps inner sidf
  sidf="~/.ubirun-$phase-$$.sid"
  load "$name"
  out="$(state_dir "$name")/$phase.log"
  : >"$out"
  inner=$(sq "printf %s \$\$ >$sidf; $cmd")
  # The sid file outlives the command on purpose: a background child it left
  # behind keeps the ssh channel open after the wrapper exits, and remote_cancel
  # still needs the session id to end it. remote_cancel removes the file.
  cmd="if command -v setsid >/dev/null 2>&1; then setsid -w bash -c $inner; else bash -c $inner; fi"
  # The caller's stdin is handed to the background ssh explicitly (a background
  # job in a non-interactive shell would otherwise read /dev/null), so piped
  # input reaches the remote command as it did before the watchdog.
  exec 3<&0
  # shellcheck disable=SC2046
  ( exec python3 -c 'import os, sys; os.setsid(); os.execvp(sys.argv[1], sys.argv[1:])' \
      ssh $(ssh_opts) "ubi@$IP" "umask 022; $cmd" ) <&3 > >(tee -a "$out") 2> >(tee -a "$out" >&2) &
  pid=$!
  exec 3<&-
  # A signal to this process takes the ssh session down with it, so Ctrl-C on
  # `ssh NAME COMMAND` leaves no orphaned client behind.
  old_traps=$(trap -p INT TERM)
  trap 'kill -TERM -- "-$pid" 2>/dev/null; exit 130' INT TERM
  start=$(date +%s)
  last_beat=$start
  while :; do
    sleep 1
    kill -0 "$pid" 2>/dev/null || break
    now=$(date +%s)
    elapsed=$(( now - start ))
    idle=$(( now - $(mtime "$out") ))
    if [ "$IDLE_TIMEOUT" -gt 0 ] && [ "$idle" -ge "$IDLE_TIMEOUT" ]; then
      why="printed nothing for ${idle}s (UBI_IDLE_TIMEOUT=$IDLE_TIMEOUT)"
    elif [ "$RUN_TIMEOUT" -gt 0 ] && [ "$elapsed" -ge "$RUN_TIMEOUT" ]; then
      why="ran ${elapsed}s (UBI_RUN_TIMEOUT=$RUN_TIMEOUT)"
    fi
    if [ -n "$why" ]; then
      # The command may have finished while the clock was read; a finished
      # command is never reported as a timeout.
      kill -0 "$pid" 2>/dev/null || break
      log "watchdog: $phase $why; killing it. Last output:"
      tail -n 40 "$out" >&2
      kill -TERM -- "-$pid" 2>/dev/null || kill "$pid" 2>/dev/null || true
      wait "$pid" 2>/dev/null || rc=$?
      trap - INT TERM; eval "$old_traps"
      # A command killed by the watchdog never exits 0; a 0 here means it
      # finished in the instant before the kill, and that result stands.
      if [ "$rc" -eq 0 ]; then
        log "watchdog: $phase finished before it could be killed; its exit 0 stands"
        return 0
      fi
      remote_cancel "$name" "$sidf"
      return 124
    fi
    if [ "$HEARTBEAT" -gt 0 ] && [ $(( now - last_beat )) -ge "$HEARTBEAT" ]; then
      log "heartbeat: $phase ${elapsed}s elapsed, last output ${idle}s ago"
      last_beat=$now
    fi
  done
  wait "$pid" || rc=$?
  trap - INT TERM; eval "$old_traps"
  return "$rc"
}

proc_start() { ps -o lstart= -p "$1" 2>/dev/null | tr -s ' ' || true; }
fsize() { if [ -f "$1" ]; then wc -c <"$1" | tr -d ' '; else echo 0; fi; }
sha256() { if command -v sha256sum >/dev/null 2>&1; then sha256sum | cut -d' ' -f1; else shasum -a 256 | cut -d' ' -f1; fi; }

# TREE_SH: print the content tree of the current directory, the same way here
# and on the VM: at a checkout's root, `git add -A` into a copy of its index
# (tracked plus untracked files that are not ignored, the files pack uploads);
# elsewhere, the same into a scratch repository over the directory.
TREE_SH='idx=$(mktemp -d "${TMPDIR:-/tmp}/ubirun-tree.XXXXXX") || exit 1
if [ "$(git rev-parse --show-toplevel 2>/dev/null)" = "$(pwd -P)" ]; then
  gi=$(git rev-parse --git-path index)
  if [ "$(git config --bool core.splitIndex)" != true ] && [ -f "$gi" ]; then cp "$gi" "$idx/index"; fi
else
  git init -q --bare "$idx/git" && export GIT_DIR="$idx/git" GIT_WORK_TREE=.
fi
GIT_INDEX_FILE="$idx/index" git add -A >/dev/null 2>&1 && GIT_INDEX_FILE="$idx/index" git write-tree
rc=$?; rm -rf "$idx"; exit $rc'

# vm_tree NAME QDEST: the content tree of QDEST on the VM.
vm_tree() {
  remote "$1" "command -v git >/dev/null || { sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq git; } >/dev/null 2>&1; cd $2 && bash -c $(sq "$TREE_SH")" </dev/null
}

base_sha() { git -C "$1" rev-parse -q --verify 'refs/remotes/origin/HEAD^{commit}' 2>/dev/null || echo none; }

# phase_status NAME PHASE: "exit <rc>" once the phase wrote its exit file,
# "alive" while its session leader runs, "lost" when the leader is gone with no
# exit file, "none" when it never started.
phase_status() {
  local p="~/.ubirun-$2"
  remote "$1" "if [ -f $p.exit ]; then echo exit \$(cat $p.exit); elif [ -s $p.pid ] && kill -0 \$(cat $p.pid) 2>/dev/null; then echo alive; elif [ -s $p.pid ]; then echo lost; else echo none; fi" </dev/null
}

# phase_start NAME PHASE INNER: start INNER on the VM in its own session,
# detached from this ssh connection. The leader records its pid, runs INNER with
# stdout and stderr in files, and writes the exit status by rename only after
# INNER's streams are closed.
phase_start() {
  local p="~/.ubirun-$2" inner
  inner=$(sq "echo \$\$ >$p.pid.tmp && mv $p.pid.tmp $p.pid; ( $3 ) >$p.out 2>$p.err </dev/null; echo \$? >$p.exit.tmp && mv $p.exit.tmp $p.exit")
  remote "$1" "rm -f $p.exit $p.pid; : >$p.out; : >$p.err; if command -v setsid >/dev/null 2>&1; then setsid -f bash -c $inner </dev/null >/dev/null 2>&1; else nohup bash -c $inner </dev/null >/dev/null 2>&1 & fi" </dev/null >/dev/null
}

# stream_cmd PHASE OUT_OFFSET ERR_OFFSET: follow both output files from the
# given byte offsets until the session leader exits.
stream_cmd() {
  local p="~/.ubirun-$1"
  printf '%s' "i=0; while [ ! -s $p.pid ] && [ ! -f $p.exit ] && [ \$i -lt 600 ]; do sleep 0.1; i=\$((i + 1)); done; pid=\$(cat $p.pid 2>/dev/null); f=; [ -z \"\$pid\" ] || f=\"-f --pid=\$pid\"; tail -c +$(( $3 + 1 )) \$f $p.err >&2 & tail -c +$(( $2 + 1 )) \$f $p.out; wait"
}

PHASE_LIVE="" STREAM_PID="" RUN_KEY="" TREE=""

# on_hup: once a remote phase is live, HUP detaches: the VM keeps running under
# its TTL and the next run of the same command reattaches. Before that, HUP
# tears down like INT and TERM.
on_hup() {
  [ -n "$PHASE_LIVE" ] || exit 130
  [ -z "$STREAM_PID" ] || kill -TERM -- "-$STREAM_PID" 2>/dev/null || true
  trap - EXIT
  rm -f "$(state_dir "$RUN_VM")/lease"
  leftover "left=1 owner=$OWNER vm=$RUN_VM detached=1"
  echo "UBI_DETACHED: vm=$RUN_VM key=${RUN_KEY:0:12} reattach: rerun the same command" >&2
  exit 129
}

# detached NAME PHASE INNER: run INNER as a detached phase (or reattach to it),
# streaming its output to this process and to the VM's state dir
# (<phase>.out, <phase>.err and the combined <phase>.log) under the same
# heartbeat and watchdog as watched. RUN_TIMEOUT counts from the phase's
# recorded start, not from a reattach. Returns the phase's exit status, 124
# after a watchdog kill, 125 when the session is gone without an exit status.
detached() {
  local name=$1 phase=$2 inner=$3 dir st rc=0 tries=0 start now idle elapsed last_beat why old_traps spid sst oo oe
  load "$name"
  dir=$(state_dir "$name")
  local lout="$dir/$phase.out" lerr="$dir/$phase.err" out="$dir/$phase.log" p="~/.ubirun-$phase"
  st=none
  if [ -f "$dir/phase.$phase.start" ]; then
    st=$(phase_status "$name" "$phase") || st=""
  fi
  case $st in
    none)
      : >"$lout"; : >"$lerr"; : >"$out"
      date +%s >"$dir/phase.$phase.start"
      phase_start "$name" "$phase" "$inner" || { log "could not start $phase on $name"; return 255; } ;;
    alive) log "$phase is still running on $name; following it" ;;
    "exit "*) ;;
    lost) log "UBI_ATTACH_LOST: vm=$name phase=$phase: its session is gone and left no exit status ($p.exit)"; return 125 ;;
    *) log "could not read the state of $phase on $name"; return 255 ;;
  esac
  PHASE_LIVE=1
  start=$(cat "$dir/phase.$phase.start")
  # A runner killed on this machine leaves its stream client behind; it would
  # append to the same local copies.
  if [ -f "$dir/stream" ] && read -r spid sst <"$dir/stream" && [ -n "$spid" ] && [ "$(proc_start "$spid")" = "$sst" ]; then
    kill -TERM -- "-$spid" 2>/dev/null || true
  fi
  oo=$(fsize "$lout") oe=$(fsize "$lerr")
  if [ "$st" != none ]; then head -c "$oo" "$lout"; head -c "$oe" "$lerr" >&2; fi
  old_traps=$(trap -p INT TERM)
  trap '[ -z "$STREAM_PID" ] || kill -TERM -- "-$STREAM_PID" 2>/dev/null; exit 130' INT TERM
  last_beat=$(date +%s)
  while :; do
    touch "$out"
    # shellcheck disable=SC2046
    ( exec python3 -c 'import os, sys; os.setsid(); os.execvp(sys.argv[1], sys.argv[1:])' \
        ssh $(ssh_opts) "ubi@$IP" "umask 022; $(stream_cmd "$phase" "$oo" "$oe")" ) \
      </dev/null > >(tee -a "$lout" | tee -a "$out") 2> >(tee -a "$lerr" | tee -a "$out" >&2) &
    STREAM_PID=$!
    echo "$STREAM_PID $(proc_start "$STREAM_PID")" >"$dir/stream"
    why=""
    while :; do
      sleep 1
      kill -0 "$STREAM_PID" 2>/dev/null || break
      now=$(date +%s)
      elapsed=$(( now - start ))
      idle=$(( now - $(mtime "$out") ))
      if [ "$IDLE_TIMEOUT" -gt 0 ] && [ "$idle" -ge "$IDLE_TIMEOUT" ]; then
        why="printed nothing for ${idle}s (UBI_IDLE_TIMEOUT=$IDLE_TIMEOUT)"
      elif [ "$RUN_TIMEOUT" -gt 0 ] && [ "$elapsed" -ge "$RUN_TIMEOUT" ]; then
        why="ran ${elapsed}s (UBI_RUN_TIMEOUT=$RUN_TIMEOUT)"
      fi
      [ -z "$why" ] || break
      if [ "$HEARTBEAT" -gt 0 ] && [ $(( now - last_beat )) -ge "$HEARTBEAT" ]; then
        log "heartbeat: $phase ${elapsed}s elapsed, last output ${idle}s ago"
        last_beat=$now
      fi
    done
    if [ -n "$why" ]; then
      log "watchdog: $phase $why; killing it. Last output:"
      tail -n 40 "$out" >&2
      kill -TERM -- "-$STREAM_PID" 2>/dev/null || kill "$STREAM_PID" 2>/dev/null || true
      wait "$STREAM_PID" 2>/dev/null || true
      STREAM_PID=""
      # A phase that finished in the instant before the kill keeps its exit 0.
      if [ "$(phase_status "$name" "$phase" 2>/dev/null)" = "exit 0" ]; then
        log "watchdog: $phase finished before it could be killed; its exit 0 stands"
        rc=0
      else
        remote_cancel "$name" "$p.pid"
        rc=124
      fi
      break
    fi
    wait "$STREAM_PID" 2>/dev/null || true
    STREAM_PID=""
    st=$(phase_status "$name" "$phase") || st=""
    case $st in
      "exit "*) rc=${st#exit }; break ;;
      lost|none) log "UBI_ATTACH_LOST: vm=$name phase=$phase: its session is gone and left no exit status ($p.exit)"; rc=125; break ;;
    esac
    tries=$(( tries + 1 ))
    if [ "$tries" -ge 5 ]; then log "lost the connection to $phase on $name 5 times; giving up (the VM keeps it until teardown)"; rc=255; break; fi
    log "the stream of $phase on $name dropped; following it again"
    sleep "$POLL"
    oo=$(fsize "$lout") oe=$(fsize "$lerr")
  done
  rm -f "$dir/stream"
  trap - INT TERM; eval "$old_traps"
  return "$rc"
}

# write_record DIR: the run record a later run of the same command reattaches
# by (key, tree, and this invocation for `attach NAME`). Remote files of each
# phase: ~/.ubirun-<phase>.{out,err,exit,pid} (setup, command, tier-<name>).
qwords() { local x; for x in "$@"; do printf '%q ' "$x"; done; }
write_record() {
  {
    printf 'RUN_KEY=%q\nTREE=%q\nPULL_ROOT=%q\nRESUME=%q\nRERUN_FAILED=%q\n' "$RUN_KEY" "$TREE" "$PULL_ROOT" "$RESUME" "$RERUN_FAILED"
    printf 'RUN_ARGS=(%s)\n' "$(qwords "${RUN_ARGS[@]}")"
    printf 'TIER_NAMES=(%s)\n' "$(qwords ${TIER_NAMES[@]+"${TIER_NAMES[@]}"})"
    printf 'TIER_CMDS=(%s)\n' "$(qwords ${TIER_CMDS[@]+"${TIER_CMDS[@]}"})"
    echo "# remote files: ~/.ubirun-<phase>.{out,err,exit,pid}; phase starts: phase.<phase>.start; lease: lease (pid start time)"
  } >"$1/run.$$" && mv "$1/run.$$" "$1/run"
}

lease_take() { echo "$$ $(proc_start $$)" >"$1/lease.$$" && mv "$1/lease.$$" "$1/lease"; }
lease_busy() {
  local pid st
  [ -f "$1/lease" ] || return 1
  read -r pid st <"$1/lease" || true
  [ -n "$pid" ] && [ "$pid" != "$$" ] && kill -0 "$pid" 2>/dev/null && [ "$(proc_start "$pid")" = "$st" ]
}

# vm_alive NAME: the recorded VM still answers show. One confirmed gone is
# cleaned up (state dir and scratch record), so its record is never tried again.
vm_alive() {
  local n=$1 out code
  ( load "$n"; [ "$CREATED" = yes ] && [ -n "$IP" ] ) 2>/dev/null || return 1
  out=$(mktemp)
  code=$(load "$n"; api "$out" vm "$LOCATION/$n" show)
  rm -f "$out"
  case $code in
    200) return 0 ;;
    404) log "run record for $n: the VM is gone; starting a new one"; cmd_down "$n" >/dev/null 2>&1 || true; return 1 ;;
    *) return 1 ;;
  esac
}

# ttl_short NAME SETUP: true when NAME's TTL (its created_at plus the name's
# -t<hours>, minus now) does not cover the run still to do plus
# REATTACH_MARGIN, with the numbers in TTL_WHY. The run still to do is the
# UBI_RUN_TIMEOUT bound of each phase that has not finished (setup when SETUP is
# set, then the command or every tier the plan does not reuse), counted from a
# started phase's recorded start; it is 0 when UBI_RUN_TIMEOUT is 0.
TTL_WHY=""
ttl_short() {
  local name=$1 dir created left now need=0 p i phases=()
  [[ "$name" =~ -t([0-9]{1,3})$ ]] || return 1
  dir=$(state_dir "$name")
  created=$(load "$name"; echo "$CREATE_AT")
  now=$(date +%s)
  left=$(( created + 10#${BASH_REMATCH[1]} * 3600 - now ))
  [ -z "$2" ] || phases+=(setup)
  if [ ${#TIER_NAMES[@]} -gt 0 ]; then
    for i in "${!TIER_NAMES[@]}"; do [ "${TIER_ACT[i]}" = reuse ] || phases+=("tier-${TIER_NAMES[i]}"); done
  else
    phases+=(command)
  fi
  if [ "$RUN_TIMEOUT" -gt 0 ]; then
    for p in "${phases[@]}"; do
      if [ -f "$dir/phase.$p.start" ]; then i=$(( RUN_TIMEOUT - (now - $(cat "$dir/phase.$p.start")) )); [ "$i" -gt 0 ] || i=0
      else i=$RUN_TIMEOUT; fi
      need=$(( need + i ))
    done
  fi
  TTL_WHY="ttl_left=${left}s needs=$(( need + REATTACH_MARGIN ))s (run still to do ${need}s + UBI_REATTACH_MARGIN=${REATTACH_MARGIN}s)"
  [ "$left" -lt $(( need + REATTACH_MARGIN )) ]
}

# find_record: the VM of a run record with this RUN_KEY whose VM still exists.
find_record() {
  local f n
  for f in "$STATE_ROOT"/*/run; do
    [ -f "$f" ] || continue
    grep -qx "RUN_KEY=$RUN_KEY" "$f" || continue
    n=$(basename "$(dirname "$f")")
    if vm_alive "$n"; then echo "$n"; return 0; fi
  done
}

# Tier checkpoints: write-once records <tier>.<epoch>.<pid>.json beside a copy
# of the tier's log, under CHECKPOINT_DIR/<run key>/, published under a lock
# with a monotonic generation; the newest generation per tier decides.
CKPT_PY='
import fcntl, hashlib, json, os, shutil, sys, time
op, d = sys.argv[1], sys.argv[2]
def records():
    out = []
    for f in (os.listdir(d) if os.path.isdir(d) else []):
        if not f.endswith(".json") or f.startswith("."):
            continue
        try:
            r = json.load(open(os.path.join(d, f)))
        except (OSError, ValueError):
            continue
        if isinstance(r, dict) and isinstance(r.get("generation"), int):
            r["_file"] = f
            out.append(r)
    return out
def newest(rs, tier):
    rs = [r for r in rs if r.get("tier") == tier]
    return max(rs, key=lambda r: r["generation"]) if rs else None
def sha(p):
    h = hashlib.sha256()
    with open(p, "rb") as fh:
        for b in iter(lambda: fh.read(65536), b""):
            h.update(b)
    return h.hexdigest()
if op == "decide":
    now, maxage, resume, rerun = int(sys.argv[3]), int(sys.argv[4]), sys.argv[5] == "1", sys.argv[6] == "1"
    rs = records()
    for tier in sys.argv[7:]:
        r = newest(rs, tier)
        f = r["_file"] if r else "-"
        age = now - int(r.get("finished_at") or r.get("started_at") or now) if r else 0
        dur = int(r.get("duration_s") or 0) if r else 0
        code = str(r.get("exit", "-")) if r else "-"
        log = os.path.join(d, str(r.get("log"))) if r and r.get("log") else ""
        if not resume:
            act, why = "run", "--no-resume"
        elif r is None:
            act, why = "run", "no record"
        elif r.get("status") == "start":
            act, why = "run", "interrupted (only a start record, %s)" % f
        elif r.get("status") == "pass":
            if age >= maxage:
                act, why = "run", "pass %s is %ds old (UBI_CHECKPOINT_MAX_AGE=%d)" % (f, age, maxage)
            elif not log or not os.path.isfile(log) or sha(log) != r.get("log_sha256"):
                act, why = "run", "pass %s: its log does not re-hash" % f
            else:
                act, why = "reuse", "-"
        elif r.get("status") == "fail":
            act, why = ("rerun", "prior fail %s (exit %s; --rerun-failed)" % (f, code)) if rerun else ("blocked", "-")
        else:
            act, why = "run", "unreadable record %s" % f
        print("\t".join([tier, act, f, str(age), str(dur), code, why]))
elif op == "publish":
    tier, status, vm, started, finished, code, log, startgen, key, tree, pid = sys.argv[3:14]
    os.makedirs(d, exist_ok=True)
    with open(os.path.join(d, ".lock"), "a") as lk:
        fcntl.flock(lk, fcntl.LOCK_EX)
        rs = records()
        gen = max([r["generation"] for r in rs] + [0]) + 1
        if status != "start":
            r = newest(rs, tier)
            if r is None or str(r["generation"]) != startgen:
                print("stale writer: its start record is generation %s, the newest for %s is %s" % (startgen, tier, r["generation"] if r else "none"), file=sys.stderr)
                sys.exit(2)
        rec = {"tier": tier, "status": status, "generation": gen, "vm": vm, "key": key, "tree": tree, "started_at": int(started)}
        if status != "start":
            rec.update(finished_at=int(finished), duration_s=int(finished) - int(started), exit=int(code))
        epoch = int(time.time())
        while os.path.exists(os.path.join(d, "%s.%d.%s.json" % (tier, epoch, pid))) or os.path.exists(os.path.join(d, "%s.%d.%s.log" % (tier, epoch, pid))):
            epoch += 1
        stem = "%s.%d.%s" % (tier, epoch, pid)
        if status != "start":
            shutil.copyfile(log, os.path.join(d, stem + ".log"))
            rec["log"], rec["log_sha256"] = stem + ".log", sha(os.path.join(d, stem + ".log"))
        tmp = os.path.join(d, ".%s.tmp" % stem)
        with open(tmp, "w") as fh:
            json.dump(rec, fh, sort_keys=True)
            fh.write("\n")
        os.link(tmp, os.path.join(d, stem + ".json"))
        os.unlink(tmp)
        print(gen)
'

# ckpt_publish TIER STATUS VM STARTED FINISHED EXIT LOG STARTGEN: print the new
# record's generation; fails (nothing published) for a stale writer.
ckpt_publish() { python3 -c "$CKPT_PY" publish "$CHECKPOINT_DIR/$RUN_KEY" "$@" "$RUN_KEY" "$TREE" "$$"; }

TIER_ACT=() TIER_TO_RUN=0 TIER_PASSED=0 TIER_REUSED="" TIER_FAILED="" TIER_PRIOR="" TIER_SAVED=0 TIER_BLOCKED="" TIER_BLOCKED_RC=1

# tier_plan: decide each tier from its newest checkpoint and print one
# UBI_VERIFY_RESUME line per tier before anything runs.
tier_plan() {
  local plan t act f age dur code why
  plan=$(python3 -c "$CKPT_PY" decide "$CHECKPOINT_DIR/$RUN_KEY" "$(date +%s)" "$CHECKPOINT_MAX_AGE" "$RESUME" "$RERUN_FAILED" "${TIER_NAMES[@]}") \
    || die "verify: could not read the tier checkpoints in $CHECKPOINT_DIR/$RUN_KEY"
  while IFS=$'\t' read -r t act f age dur code why; do
    case $act in
      reuse)
        echo "UBI_VERIFY_RESUME: tier=$t reuse $f (${age}s)" >&2
        TIER_REUSED=${TIER_REUSED:+$TIER_REUSED,}$t TIER_SAVED=$(( TIER_SAVED + dur )) TIER_PASSED=$(( TIER_PASSED + 1 )) ;;
      blocked)
        echo "UBI_VERIFY_RESUME: tier=$t fail $f (${age}s, exit $code): not rerun without --rerun-failed" >&2
        if [ -z "$TIER_BLOCKED" ]; then TIER_BLOCKED=$t; if [[ "$code" =~ ^[0-9]+$ ]]; then TIER_BLOCKED_RC=$code; fi; fi ;;
      rerun)
        echo "UBI_VERIFY_RESUME: tier=$t run: $why" >&2
        TIER_PRIOR=${TIER_PRIOR:+$TIER_PRIOR,}$t:$code TIER_TO_RUN=$(( TIER_TO_RUN + 1 )) ;;
      *)
        echo "UBI_VERIFY_RESUME: tier=$t run: $why" >&2
        TIER_TO_RUN=$(( TIER_TO_RUN + 1 )) ;;
    esac
    TIER_ACT+=("$act")
  done <<<"$plan"
}

verify_line() {
  echo "UBI_VERIFY: tree=${TREE:0:12} key=${RUN_KEY:0:12} tiers=${#TIER_NAMES[@]} passed=$TIER_PASSED reused=${TIER_REUSED:-none} failed=${TIER_FAILED:-none} prior_failures=${TIER_PRIOR:-none} saved_s=$TIER_SAVED"
}

# run_tiers NAME QDEST: run every tier the plan did not reuse, in order, each
# as its own detached phase; stop at the first failure and return its status.
# A pass is recorded only when the VM's tree after the tier equals the tree
# before it.
run_tiers() {
  local name=$1 qdest=$2 dir i t phase before after trc started finished gen
  dir=$(state_dir "$name")
  for i in "${!TIER_NAMES[@]}"; do
    [ "${TIER_ACT[i]}" != reuse ] || continue
    t=${TIER_NAMES[i]} phase="tier-${TIER_NAMES[i]}"
    if [ ! -f "$dir/phase.$phase.start" ]; then
      before=$(vm_tree "$name" "$qdest") || before=unavailable
      echo "$before" >"$dir/phase.$phase.tree"
      if gen=$(ckpt_publish "$t" start "$name" "$(date +%s)" 0 0 "" 0); then echo "$gen" >"$dir/phase.$phase.gen"
      else echo "UBI_CHECKPOINT_WRITE_FAILED: tier=$t start record (the tier still runs)" >&2; fi
    fi
    log "running tier $t on $name: ${TIER_CMDS[i]}"
    trc=0
    detached "$name" "$phase" "cd $qdest && . ~/.ubirun-env && bash -lc $(printf %q "${TIER_CMDS[i]}")" || trc=$?
    started=$(cat "$dir/phase.$phase.start" 2>/dev/null || date +%s) finished=$(date +%s)
    log "tier $t exited $trc after $(( finished - started ))s"
    case $trc in 125|255) TIER_FAILED=$t; return "$trc" ;; esac
    gen=$(cat "$dir/phase.$phase.gen" 2>/dev/null || echo 0)
    if [ "$trc" -ne 0 ]; then
      ckpt_publish "$t" fail "$name" "$started" "$finished" "$trc" "$dir/$phase.log" "$gen" >/dev/null \
        || echo "UBI_CHECKPOINT_WRITE_FAILED: tier=$t fail record (the result stands)" >&2
      TIER_FAILED=$t
      return "$trc"
    fi
    TIER_PASSED=$(( TIER_PASSED + 1 ))
    after=$(vm_tree "$name" "$qdest") || after=unavailable
    before=$(cat "$dir/phase.$phase.tree" 2>/dev/null || echo unavailable)
    if [ "$after" != "$before" ] || [ "$after" = unavailable ]; then
      echo "UBI_VERIFY_TREE_MOVED: tier=$t before=${before:0:12} after=${after:0:12}: a tier must leave the source tree as it found it; no pass record" >&2
      continue
    fi
    ckpt_publish "$t" pass "$name" "$started" "$finished" 0 "$dir/$phase.log" "$gen" >/dev/null \
      || echo "UBI_CHECKPOINT_WRITE_FAILED: tier=$t pass record (the result stands)" >&2
  done
}

# vm_rows: "location name owner expires created" for every VM in the project;
# owner is "-" for untagged ubirun-<epoch>-* names and "." for VMs this runner
# did not name; expires is the epoch the name's -t<hours> TTL ends at, or "-";
# created is the name's epoch, or "-".
vm_rows() {
  local loc name owner created expires
  cli vm list -N -f location,name | while read -r loc name; do
    owner=. created="" expires=-
    if [[ "$name" =~ ^${PREFIX}-([a-z][a-z0-9]{0,11})-([0-9]{10})- ]]; then
      owner=${BASH_REMATCH[1]} created=${BASH_REMATCH[2]}
    elif [[ "$name" =~ ^${PREFIX}-([0-9]{10})- ]]; then
      owner=- created=${BASH_REMATCH[1]}
    fi
    if [ -n "$created" ] && [[ "$name" =~ -t([0-9]{1,3})$ ]]; then
      expires=$(( 10#$created + 10#${BASH_REMATCH[1]} * 3600 ))
    fi
    echo "$loc $name $owner $expires ${created:--}"
  done
}

# reap: destroy every VM whose name carries a TTL that ended more than
# REAP_GRACE seconds ago, whichever owner created it (the TTL is that owner's
# own declaration), and the caller's own TTL-less ubirun-<UBI_OWNER>-* names at
# least LEGACY_HOURS old. Another owner's TTL-less VM, an untagged one, and names
# outside the prefix are never touched: only a TTL lets reap judge another lane's VM.
cmd_reap() {
  local now rows loc name owner expires created n=0 failed=0
  [[ "$LEGACY_HOURS" =~ ^[1-9][0-9]{0,3}$ ]] || die "UBI_LEGACY_HOURS must be a whole number of hours from 1 to 9999 with no leading zero (how old a TTL-less ubirun-* VM must be before reap destroys it)"
  now=$(date +%s)
  rows=$(vm_rows) || { log "reap: could not list the project's VMs; nothing destroyed"; return 1; }
  while read -r loc name owner expires created; do
    [ -n "$name" ] || continue
    if [ "$expires" != - ]; then
      [ "$now" -ge $(( expires + REAP_GRACE )) ] || continue
      log "reaping expired $loc/$name (owner $owner; its TTL ended $(( (now - expires) / 60 )) min ago)"
    else
      [ -n "${UBI_OWNER:-}" ] && [ "$owner" = "$OWNER" ] && [ "$created" != - ] || continue
      [ $(( now - 10#$created )) -ge $(( LEGACY_HOURS * 3600 )) ] || continue
      log "reaping TTL-less $loc/$name (owner $owner; $(( (now - 10#$created) / 3600 ))h old, legacy sweep at ${LEGACY_HOURS}h)"
    fi
    n=$(( n + 1 ))
    cmd_down "$name" -l "$loc" || { failed=$(( failed + 1 )); log "failed to reap $loc/$name"; }
  done <<<"$rows"
  [ "$n" -gt 0 ] || log "reap: no expired VMs"
  [ "$failed" -eq 0 ] || { log "reap: $failed of $n expired VMs could not be destroyed"; return 1; }
}

cmd_gc() {
  local hours=${1:-$GC_HOURS} now loc name owner
  [[ "$hours" =~ ^[0-9]+$ ]] || die "gc: HOURS must be a whole number (or set UBI_GC_HOURS)"
  if [ "$hours" -eq 0 ]; then log "gc: no sweep (give HOURS > 0 or set UBI_GC_HOURS); nothing listed, nothing destroyed"; return 0; fi
  now=$(date +%s)
  vm_rows | while read -r loc name owner _; do
    [ "$owner" = "$OWNER" ] || continue
    [[ "$name" =~ -([0-9]{10})- ]] || continue
    if [ $(( (now - BASH_REMATCH[1]) / 3600 )) -ge "$hours" ]; then
      log "destroying stale $loc/$name (owner $OWNER, older than ${hours}h)"
      cmd_down "$name" -l "$loc" || log "failed to destroy $loc/$name"
    fi
  done
}

cmd_list() {
  case ${1:-} in
    "") cli vm list ;;
    --mine) vm_rows | awk -v o="$OWNER" '$3==o {print $1 "  " $2}' ;;
    *) die "list: unknown option $1 (use --mine)" ;;
  esac
}

# usage: VMs and vCPUs per owner, from each VM's size (standard-16 = 16 vCPUs).
cmd_usage() {
  local tmp loc name owner i=0
  tmp=$(mktemp -d)
  while read -r loc name owner _; do
    i=$(( i + 1 ))
    cli vm "$loc/$name" show 2>/dev/null | sed -n "s/^size: /$owner /p" >"$tmp/$i" &
    [ $(( i % 8 )) -ne 0 ] || wait
  done < <(vm_rows)
  wait
  cat "$tmp"/* 2>/dev/null | awk -v me="$OWNER" '
    { n = $2; sub(/^.*-/, "", n); o = $1 == "-" ? "(untagged)" : $1 == "." ? "(other)" : $1
      vms[o]++; cpu[o] += n; total += n; count++ }
    END {
      printf "%-14s %4s %6s\n", "OWNER", "VMS", "VCPUS"
      for (o in cpu) printf "%-14s %4d %6d%s\n", o, vms[o], cpu[o], o == me ? "  (you)" : "" | "sort -k3,3nr"
      close("sort -k3,3nr")
      printf "%-14s %4d %6d\n", "total", count, total
    }'
  rm -rf "$tmp"
}

write_state() {
  printf 'NAME=%q\nLOCATION=%q\nSIZE=%q\nIP=%q\nCREATED=%q\nCREATE_AT=%q\nCREATE_PID=%q\n' \
    "$1" "$2" "$3" "$4" "$5" "$6" "$$" >"$(state_dir "$1")/env"
}

# record_vm NAME LOCATION: append to the scratch VM-id file (record-before-create).
record_vm() {
  mkdir -p "$(dirname "$VM_RECORD")" 2>/dev/null || return 0
  printf '%s\t%s\t%s\t%s\t%s\n' "$1" "$2" "$OWNER" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" "$$" >>"$VM_RECORD"
}

# forget_vm NAME: drop the VM from the scratch file once it is confirmed gone.
forget_vm() {
  [ -f "$VM_RECORD" ] || return 0
  local tmp="$VM_RECORD.$$"
  awk -F'\t' -v n="$1" '$1!=n' "$VM_RECORD" >"$tmp" && mv "$tmp" "$VM_RECORD"
}

# records: print the scratch file (VMs this machine created and has not confirmed gone).
cmd_records() {
  echo "record: $VM_RECORD"
  [ -s "$VM_RECORD" ] || { echo "(no VMs recorded)"; return 0; }
  printf '%-40s %-14s %-12s %-20s %s\n' NAME LOCATION OWNER CREATED_AT PID
  awk -F'\t' '{ printf "%-40s %-14s %-12s %-20s %s\n", $1, $2, $3, $4, $5 }' "$VM_RECORD"
}

new_name() {
  echo "$PREFIX-$OWNER-$(date +%s)-$(head -c4 /dev/urandom | od -An -tx1 | tr -d ' \n')-t$TTL_HOURS"
}

# vcpus SIZE: the vCPU count a Ubicloud size name carries (standard-16 -> 16).
vcpus() { [[ "$1" =~ -([0-9]+)$ ]] && echo "${BASH_REMATCH[1]}"; }

# quota_preflight LOCATION NAME SIZE: refuse (or wait UBI_QUOTA_WAIT seconds)
# before the create request when the project's running VMs plus this size
# exceed the known vCPU ceiling. The ceiling comes from UBI_QUOTA_VCPUS or the
# maximum the last refusal printed; without either the API's own refusal rules.
QUOTA_CACHE_MAX_AGE=86400
quota_preflight() {
  local location=$1 name=$2 size=$3 need max used remaining step source="UBI_QUOTA_VCPUS" cache="$STATE_ROOT/quota-max"
  need=$(vcpus "$size") || return 0
  max=$QUOTA_VCPUS
  if [ -z "$max" ] && [ -f "$cache" ]; then
    # A refusal's maximum is remembered for a day: after that (a raised quota,
    # another project's key) the API's own answer decides again.
    if [ $(( $(date +%s) - $(mtime "$cache") )) -lt "$QUOTA_CACHE_MAX_AGE" ]; then
      max=$(cat "$cache" 2>/dev/null || true); source="the last refusal, cached in $cache"
    else
      rm -f "$cache"
    fi
  fi
  [[ "$max" =~ ^[0-9]+$ ]] || return 0
  # The budget counts seconds spent waiting for room, not the usage calls
  # between them: a slow first usage read must not shave the printed budget.
  remaining=$QUOTA_WAIT
  while :; do
    used=$(cmd_usage 2>/dev/null | awk '$1=="total" {print $3}')
    [[ "$used" =~ ^[0-9]+$ ]] || return 0
    [ $(( used + need )) -gt "$max" ] || return 0
    if [ "$remaining" -le 0 ]; then
      log "quota preflight refused $location/$name ($size): it needs $need vCPUs and the project's VMs already use $used of $max (ceiling from $source; other usage such as managed runners counts on top)"
      cmd_usage >&2 || true
      die "create refused before any request: vCPU quota exhausted (quota full); wait for running VMs to finish (UBI_QUOTA_WAIT=<seconds> waits here), run $0 reap, use a smaller size, or set UBI_QUOTA_VCPUS to the project's real ceiling"
    fi
    log "quota: $used of $max vCPUs in use and $need needed; waiting up to ${remaining}s more for room"
    step=$(( remaining < 30 ? remaining : 30 ))
    sleep "$step"
    remaining=$(( remaining - step ))
  done
}

valid_name() { [[ "$1" =~ ^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$ ]]; }

# check_storage GIB: Ubicloud accepts only these disk sizes; refuse before any API call.
check_storage() {
  case " $ALLOWED_STORAGE " in
    *" $1 "*) [ -n "$1" ] && return 0 ;;
  esac
  die "invalid storage '$1' GiB (allowed: $ALLOWED_STORAGE; set UBI_ALLOWED_STORAGE when Ubicloud adds sizes)"
}

UP_NAME=""
UP_READY=""
cmd_up() {
  require_owner
  local size=$DEFAULT_SIZE location=$DEFAULT_LOCATION name="" storage="" image=ubuntu-noble
  while [ $# -gt 0 ]; do
    case $1 in
      -s|--size) size=$2; shift 2 ;;
      -l|--location) location=$2; shift 2 ;;
      -n|--name) name=$2; shift 2 ;;
      -S|--storage) check_storage "$2"; storage=$2; shift 2 ;;
      -b|--image) image=$2; shift 2 ;;
      *) die "up: unknown option $1" ;;
    esac
  done
  [ -n "$name" ] || name=$(new_name)
  valid_name "$name" || die "invalid VM name '$name' (Ubicloud allows 1-63 of a-z, 0-9 and '-', starting and ending with a letter or digit)"
  if [ "$REAP" != 0 ]; then
    cmd_reap || log "reap failed; continuing"
  fi
  if [ "$GC_HOURS" -gt 0 ]; then
    cmd_gc "$GC_HOURS" || log "stale-VM cleanup failed; continuing"
  fi
  quota_preflight "$location" "$name" "$size"

  local dir create_at
  dir=$(state_dir "$name")
  mkdir -p "$dir"
  chmod 700 "$dir"
  ssh-keygen -q -t ed25519 -N '' -C "$name" -f "$dir/key"

  local args=(vm "$location/$name" create -s "$size" -b "$image")
  [ -z "$storage" ] || args+=(-S "$storage")
  args+=("$(cat "$dir/key.pub")")
  create_at=$(date +%s)
  write_state "$name" "$location" "$size" "" unknown "$create_at"
  record_vm "$name" "$location"
  UP_NAME=$name
  log "creating $location/$name ($size)"
  # Hold signals until the create answer is recorded, so teardown knows
  # whether the VM exists instead of waiting out UBI_CREATE_GRACE.
  local interrupted="" created=yes refusal need used max
  trap 'interrupted=1' INT TERM HUP QUIT
  cli "${args[@]}" >/dev/null 2>"$dir/create.err" || created=no
  write_state "$name" "$location" "$size" "" "$created" "$create_at"
  trap 'exit 130' INT TERM HUP QUIT
  [ -z "$interrupted" ] || exit 130
  if [ "$created" = no ]; then
    refusal=$(sed -n 's/.*Requested vCPU count: \([0-9]*\), currently used vCPU count: \([0-9]*\), maximum allowed vCPU count: \([0-9]*\).*/\1 \2 \3/p' "$dir/create.err")
    if [ -z "$refusal" ]; then
      cat "$dir/create.err" >&2
      die "create failed"
    fi
    read -r need used max <<<"$refusal"
    echo "$max" >"$STATE_ROOT/quota-max"
    log "quota refused $location/$name ($size): it needs $need vCPUs and the project already uses $used of $max"
    log "VMs in the project by owner (the rest of the used count is other usage, such as managed GitHub runners):"
    cmd_usage >&2 || true
    die "create failed: vCPU quota exhausted; wait for running VMs to finish, or use fewer or smaller VMs (ci:ubicloud --vms N)"
  fi

  local deadline=$(( $(date +%s) + 600 )) show state ip
  while :; do
    show=$(cli vm "$location/$name" show 2>/dev/null || true)
    state=$(sed -n 's/^state: //p' <<<"$show")
    ip=$(sed -n 's/^ip4: //p' <<<"$show")
    [ "$state" = running ] && [ -n "$ip" ] && break
    [ "$(date +%s)" -lt "$deadline" ] || die "VM did not reach running in 10 minutes (last state: ${state:-unknown})"
    sleep "$POLL"
  done
  write_state "$name" "$location" "$size" "$ip" yes "$create_at"

  load "$name"
  deadline=$(( $(date +%s) + 300 ))
  # shellcheck disable=SC2046
  until ssh $(ssh_opts) "ubi@$IP" true 2>/dev/null; do
    [ "$(date +%s)" -lt "$deadline" ] || die "SSH did not come up on $IP"
    sleep "$POLL"
  done
  remote "$name" 'cloud-init status --wait >/dev/null 2>&1 || true'
  UP_READY=1
  log "ready: $name ($IP)"
  echo "$name"
}

# down NAME [-l LOCATION]: destroy NAME and return 0 only once it is confirmed
# gone or never existed. While this machine's create request for NAME may
# still be in flight (its `up` process is alive, or the create was sent less
# than UBI_CREATE_GRACE seconds ago with no answer), "not found" is not final.
cmd_down() {
  local name=${1:-} loc="" dir
  [ -n "$name" ] || die "down: missing NAME"
  shift
  while [ $# -gt 0 ]; do
    case $1 in
      -l|--location) loc=$2; shift 2 ;;
      *) die "down: unknown option $1" ;;
    esac
  done
  valid_name "$name" || die "invalid VM name '$name'"
  dir=$(state_dir "$name")
  local CREATED=none CREATE_AT=0 CREATE_PID="" IP="" LOCATION="" KEY=""
  if [ -f "$dir/env" ]; then
    load "$name"
    loc=$LOCATION
    if [ -S "$dir/ctl" ] && [ -n "$IP" ]; then
      # shellcheck disable=SC2046
      ssh $(ssh_opts) -O exit "ubi@$IP" >/dev/null 2>&1 || true
    fi
  fi

  local deadline=$(( $(date +%s) + DOWN_TIMEOUT )) seen=0 asked=0 out code now
  out=$(mktemp)
  while :; do
    now=$(date +%s)
    if [ -z "$loc" ]; then
      loc=$(vm_rows 2>/dev/null | awk -v n="$name" '$2==n {print $1}') || loc=""
      code=404
      [ -z "$loc" ] || code=$(api "$out" vm "$loc/$name" show)
    else
      code=$(api "$out" vm "$loc/$name" show)
    fi
    if [ "$code" = 200 ]; then
      seen=1
      if [ $(( now - asked )) -ge 60 ]; then
        code=$(api "$out" vm "$loc/$name" destroy -f)
        if [ "$code" != 200 ]; then
          cat "$out" >&2
          rm -f "$out"
          log "FAILED to destroy $loc/$name (HTTP $code); retry: $0 down $name"
          return 1
        fi
        asked=$now
        log "destroy requested: $loc/$name"
      fi
    elif [ "$code" = 404 ]; then
      if [ "$seen" = 1 ] || [ "$CREATED" != unknown ] || { [ $(( now - CREATE_AT )) -ge "$CREATE_GRACE" ] \
        && { [ "$CREATE_PID" = "$$" ] || ! kill -0 "$CREATE_PID" 2>/dev/null; }; }; then
        rm -f "$out"
        rm -rf "$dir"
        forget_vm "$name"
        if [ "$seen" = 1 ]; then log "destroyed ${loc:-?}/$name"; else log "gone: ${loc:-?}/$name (never existed or already destroyed)"; fi
        return 0
      fi
      log "waiting for an in-flight create of $name to resolve"
    fi
    if [ "$now" -ge "$deadline" ]; then
      rm -f "$out"
      log "WARNING: could not confirm ${loc:-?}/$name is gone after ${DOWN_TIMEOUT}s; rerun: $0 down $name"
      return 1
    fi
    sleep "$POLL"
  done
}

# pack SRC: write a gzipped checkout tarball to stdout (tracked + untracked
# files that are not ignored, plus a .git snapshot; a non-git directory is
# taken whole). The live .git is never tarred: another process running git in
# the checkout (a review subagent's diff, a trial merge's worktree add) writes
# index.lock, packed-refs and objects while tar reads, and GNU tar exits 1
# on a file that changed under it (GSTA-121's PREGATE_REMOTE_INFRA). Instead
# the refs are fetched into a fresh repository through git's own transport,
# which reads a consistent view, the remote.* config is replayed so
# origin/<base> still resolves, and the index is copied (git writes it
# atomically through a rename). A linked worktree's .git is a one-line
# pointer into the main repository, useless on the VM; the same snapshot
# replaces it, on the worktree's own branch and index. Not carried: submodule
# repositories (.git/modules) and a partial clone's promisor (the fetch pulls
# every missing blob first); gstack has neither.
cmd_pack() {
  local src tmp gitdir branch head entry
  src=$(cd "${1:-.}" && pwd)
  if git -C "$src" rev-parse --is-inside-work-tree >/dev/null 2>&1; then
    head=$(git -C "$src" rev-parse --verify -q HEAD) || die "pack: $src has no commits; the VM needs a HEAD to fingerprint"
    branch=$(git -C "$src" symbolic-ref -q --short HEAD || true)
    tmp=$(mktemp -d)
    # The path is baked in: a set -e failure unwinds the function before the trap runs, and a local $tmp is unset there.
    trap "rm -rf $(printf %q "$tmp")" EXIT
    # No template hooks from a global init.templateDir, and no auto-gc under the tar.
    git -c gc.auto=0 init -q --bare --template= "$tmp/.git"
    git -C "$tmp/.git" -c gc.auto=0 fetch -q --no-tags --update-shallow "$src" '+refs/*:refs/*' \
      || die "pack: could not snapshot the refs of $src"
    if [ -z "$branch" ]; then
      branch="detached-${head:0:12}"
      git -C "$tmp/.git" fetch -q --no-tags --update-shallow "$src" "+HEAD:refs/heads/$branch"
    fi
    git -C "$tmp/.git" symbolic-ref HEAD "refs/heads/$branch"
    git -C "$tmp/.git" config core.bare false
    gitdir=$(cd "$src" && cd "$(git rev-parse --git-common-dir)" && pwd)
    while IFS= read -r -d '' entry; do
      # A key with no value (`[remote "x"] mirror`) is boolean true.
      case $entry in *$'\n'*) ;; *) entry="$entry"$'\n'true ;; esac
      git -C "$tmp/.git" config --add "${entry%%$'\n'*}" "${entry#*$'\n'}"
    done < <(git -C "$gitdir" config --local --null --get-regexp '^(remote|branch)\.' 2>/dev/null || true)
    # The checkout's index rides along so the VM's status matches, except a
    # split index, whose shared half lives only in the original git dir. The
    # index's blobs that HEAD's tree lacks (staged, intent-to-add, the stages
    # of an unmerged entry) are behind no ref, so they travel as a pack of
    # their own; without them the VM's write-tree (gstack-wtree) cannot read a
    # staged file.
    if [ "$(git -C "$src" config --bool core.splitIndex 2>/dev/null)" != true ]; then
      cp "$(cd "$src" && cd "$(dirname "$(git rev-parse --git-path index)")" && pwd)/index" "$tmp/.git/index"
      # Read the copy, not the live index, so the pack matches it; a gitlink's
      # sha (mode 160000) is a submodule commit this object store lacks.
      GIT_INDEX_FILE="$tmp/.git/index" git -C "$src" ls-files -s | awk '$1 != "160000" {print $2}' | sort -u \
        | comm -23 - <(git -C "$src" ls-tree -r HEAD | awk '{print $3}' | sort -u) \
        | git -C "$src" pack-objects -q --stdout \
        | git -C "$tmp/.git" unpack-objects -q \
        || die "pack: could not snapshot the staged blobs of $src"
    fi
    (
      cd "$src"
      git ls-files -z -co --exclude-standard \
        | while IFS= read -r -d '' f; do
            if [ -e "$f" ] || [ -L "$f" ]; then printf '%s\0' "$f"; fi
          done \
        | tar --null -T - -c -C "$tmp" .git -zf -
    )
    rm -rf "$tmp"; trap - EXIT
  else
    tar -C "$src" -czf - .
  fi
}

# unpack NAME DEST: extract a tarball read from stdin into DEST on the VM.
cmd_unpack() {
  local qdest
  qdest=$(printf %q "$2")
  remote "$1" "mkdir -p $qdest && tar -xzf - -C $qdest"
}

cmd_sync() {
  local name=$1 src=${2:-.} dest=${3:-}
  src=$(cd "$src" && pwd)
  [ -n "$dest" ] || dest="work/$(basename "$src")"
  cmd_pack "$src" | cmd_unpack "$name" "$dest"
  log "synced $src -> $name:$dest"
}

# pull NAME REMOTE_GLOB LOCAL_DIR: copy matching remote entries into LOCAL_DIR.
# Relative remote paths start at /home/ubi. A glob that matches nothing (for
# example an optional flake ledger) is reported and skipped, not a failure.
cmd_pull() {
  local name=$1 from=$2 to=$3 dir
  dir=$(printf %q "$(dirname "$from")")
  if ! remote "$name" "cd $dir 2>/dev/null && ls -d -- $(basename "$from") >/dev/null 2>&1"; then
    log "pull: nothing matches $from"
    return 0
  fi
  mkdir -p "$to"
  remote "$name" "cd $dir && tar -czf - $(basename "$from")" | tar -xzf - -C "$to"
}

# pass_name NAME: a variable this runner may forward to a VM. Its own
# credentials (UBICLOUD_*) never leave this machine, whoever asks.
pass_name() {
  [[ "$1" =~ ^[A-Za-z_][A-Za-z0-9_]*$ ]] || die "--pass $1: not a variable name"
  case $1 in UBICLOUD_*) die "--pass $1: the runner never forwards its own Ubicloud credentials to a VM" ;; esac
}

# inside_dir DIR ROOT: DIR resolves, symlinks followed, to ROOT or below it.
# Its nearest existing ancestor is checked first, so a refused destination
# creates nothing (not even outside the root); only then is DIR created and
# checked again.
inside_dir() {
  local a b near=$1
  b=$(cd "$2" 2>/dev/null && pwd -P) || return 1
  while [ ! -d "$near" ]; do
    [ "$near" != "$(dirname "$near")" ] || return 1
    near=$(dirname "$near")
  done
  a=$(cd "$near" 2>/dev/null && pwd -P) || return 1
  [ "$a" = "$b" ] || [[ "$a" = "$b"/* ]] || return 1
  mkdir -p "$1" 2>/dev/null || return 1
  a=$(cd "$1" 2>/dev/null && pwd -P) || return 1
  [ "$a" = "$b" ] || [[ "$a" = "$b"/* ]]
}

# PULL_ROOT: set by verify; every pull destination must resolve inside it at
# pull time (an earlier pull may have placed a symlink where a later one lands).
PULL_ROOT=""

# run_teardown RC: run's EXIT handler. Destroys RUN_VM, ignoring further
# signals, then checks the project's VM list for it and prints the leftover
# line; a VM still listed, or a list that cannot be read, fails the run.
run_teardown() {
  local rc=$1 rows left others
  trap "" INT TERM HUP QUIT
  cmd_down "$RUN_VM" || log "WARNING: failed to destroy $RUN_VM; run: $0 down $RUN_VM"
  if rows=$(vm_rows 2>/dev/null); then
    left=$(awk -v n="$RUN_VM" '$2==n' <<<"$rows" | grep -c . || true)
    others=$(awk -v n="$RUN_VM" -v o="$OWNER" '$3==o && $2!=n' <<<"$rows" | grep -c . || true)
  else
    left=unknown others=unknown
  fi
  leftover "left=$left owner=$OWNER vm=$RUN_VM others=$others"
  [ "$left" = 0 ] && return 0
  log "VM cleanup not confirmed for $RUN_VM (left=$left); destroy it with: $0 down $RUN_VM"
  [ "$rc" -ne 0 ] || exit 1
}

TIER_NAMES=() TIER_CMDS=() RESUME=1 RERUN_FAILED=0 FORCE_ATTACH="" RUN_ARGS=()
cmd_run() {
  require_owner
  local up_args=() src=. dest="" setup="" keep=0 pulls=() envs=() passes=() key_inputs=() probe=0
  RUN_ARGS=("$@")
  while [ $# -gt 0 ]; do
    case $1 in
      -S|--storage) check_storage "$2"; up_args+=("$1" "$2"); shift 2 ;;
      -s|--size|-l|--location|-n|--name|-b|--image) up_args+=("$1" "$2"); shift 2 ;;
      --src) src=$2; shift 2 ;;
      --dest) dest=$2; shift 2 ;;
      --setup) setup=$2; shift 2 ;;
      --env) envs+=("$2"); shift 2 ;;
      --pass) pass_name "$2"; [ -n "${!2+x}" ] || die "--pass $2: not set locally"; passes+=("$2"); shift 2 ;;
      --pull) pulls+=("$2"); shift 2 ;;
      --keep) keep=1; shift ;;
      --key-input) key_inputs+=("$2"); shift 2 ;;
      --probe) probe=1; shift ;;
      --resume) RESUME=1; shift ;;
      --no-resume) RESUME=0; shift ;;
      --rerun-failed) RERUN_FAILED=1; shift ;;
      --) shift; break ;;
      *) die "run: unknown option $1" ;;
    esac
  done
  [ $# -gt 0 ] || [ ${#TIER_NAMES[@]} -gt 0 ] || die "run: missing command after --"
  [ -z "$setup" ] || [ -f "$setup" ] || die "setup script not found: $setup"
  command -v git >/dev/null || die "git is required: the run key fingerprints the checkout with it"
  src=$(cd "$src" && pwd)
  [ -n "$dest" ] || dest="work/$(basename "$src")"

  local i name="" size=$DEFAULT_SIZE location=$DEFAULT_LOCATION image=ubuntu-noble storage="" e n
  for (( i = 0; i < ${#up_args[@]}; i += 2 )); do
    case ${up_args[i]} in
      -n|--name) name=${up_args[i+1]} ;;
      -s|--size) size=${up_args[i+1]} ;;
      -l|--location) location=${up_args[i+1]} ;;
      -b|--image) image=${up_args[i+1]} ;;
      -S|--storage) storage=${up_args[i+1]} ;;
    esac
  done
  # The run key: everything that decides what the VM runs, computed before any
  # VM exists. Pass values enter only as their sha256.
  if [ -z "$FORCE_ATTACH" ]; then
    TREE=$(cd "$src" && bash -c "$TREE_SH") || die "could not fingerprint $src (git add -A into a temporary index failed)"
    RUN_KEY=$({
      echo "ubi-runner run key v1"
      echo "tree $TREE"
      printf 'command %q\n' "$*"
      if [ -n "$setup" ]; then echo "setup $(sha256 <"$setup")"; else echo "setup none"; fi
      for e in ${envs[@]+"${envs[@]}"}; do printf 'env %q\n' "$e"; done
      for n in ${passes[@]+"${passes[@]}"}; do printf 'pass %s %s\n' "$n" "$(printf %s "${!n}" | sha256)"; done
      printf 'vm %q %q %q %q\n' "$size" "$location" "$image" "$storage"
      echo "base $(base_sha "$src")"
      echo "runner $(sha256 <"${BASH_SOURCE[0]}")"
      for e in ${key_inputs[@]+"${key_inputs[@]}"}; do printf 'input %q\n' "$e"; done
      for i in "${!TIER_NAMES[@]}"; do printf 'tier %q %q\n' "${TIER_NAMES[i]}" "${TIER_CMDS[i]}"; done
    } | sha256)
  fi
  [ ${#TIER_NAMES[@]} -eq 0 ] || tier_plan

  local attach=""
  if [ -n "$FORCE_ATTACH" ]; then
    vm_alive "$FORCE_ATTACH" || die "attach: $FORCE_ATTACH no longer exists; rerun the original command to start fresh"
    attach=$FORCE_ATTACH
  else
    attach=$(find_record)
  fi
  if [ "$probe" = 1 ]; then
    if [ -z "$attach" ]; then echo "UBI_ATTACH_INFO: none key=${RUN_KEY:0:12}"
    else
      local busy=0
      ! lease_busy "$(state_dir "$attach")" || busy=1
      if [ "$busy" = 0 ] && [ -z "$FORCE_ATTACH" ] && ttl_short "$attach" "$setup"; then
        echo "UBI_ATTACH_INFO: none key=${RUN_KEY:0:12} ttl_short vm=$attach $TTL_WHY"
      else
        echo "UBI_ATTACH_INFO: vm=$attach created_at=$(load "$attach"; echo "$CREATE_AT") key=${RUN_KEY:0:12} busy=$busy"
      fi
    fi
    return 0
  fi
  if [ ${#TIER_NAMES[@]} -gt 0 ] && { [ -n "$TIER_BLOCKED" ] || [ "$TIER_TO_RUN" -eq 0 ]; } && [ -n "$attach" ] && ! lease_busy "$(state_dir "$attach")"; then
    log "verify: no tier needs $attach, which a dead runner left behind; destroying it"
    cmd_down "$attach" >/dev/null || log "WARNING: failed to destroy $attach; run: $0 down $attach"
  fi
  if [ ${#TIER_NAMES[@]} -gt 0 ] && [ -n "$TIER_BLOCKED" ]; then
    TIER_FAILED=$TIER_BLOCKED
    verify_line
    return "$TIER_BLOCKED_RC"
  fi
  if [ ${#TIER_NAMES[@]} -gt 0 ] && [ "$TIER_TO_RUN" -eq 0 ]; then
    log "verify: every tier passed under this key; no VM needed"
    verify_line
    return 0
  fi
  if [ -n "$attach" ] && lease_busy "$(state_dir "$attach")"; then
    die "UBI_ATTACH_BUSY: vm=$attach key=${RUN_KEY:0:12}: runner pid $(cut -d' ' -f1 <"$(state_dir "$attach")/lease") on this machine still owns it; wait for it or stop it, then rerun"
  fi
  if [ -n "$attach" ] && [ -z "$FORCE_ATTACH" ] && ttl_short "$attach" "$setup"; then
    log "UBI_REATTACH_TTL_SHORT: vm=$attach key=${RUN_KEY:0:12} $TTL_WHY: starting a fresh VM (tier checkpoints carry over) and destroying $attach"
    cmd_down "$attach" >/dev/null || log "WARNING: failed to destroy $attach; run: $0 down $attach"
    attach=""
  fi
  [ -z "$attach" ] || name=$attach
  [ -n "$name" ] || { name=$(new_name); up_args+=(-n "$name"); }
  RUN_VM=$name
  # Armed before the create request: an interrupted `up` still destroys its VM.
  # A second signal must not cut teardown short, so the EXIT handler ignores them.
  trap 'run_teardown "$?"' EXIT
  trap 'exit 130' INT TERM QUIT
  trap on_hup HUP
  if [ -n "$attach" ]; then
    load "$name"
    log "reattached to $name created_at=$CREATE_AT key=${RUN_KEY:0:12}"
  else
    cmd_up "${up_args[@]}" >/dev/null
    trap 'exit 130' INT TERM QUIT
    trap on_hup HUP
    if [[ "$name" =~ -t([0-9]+)$ ]]; then
      log "$name carries a ${BASH_REMATCH[1]}h TTL (any later run of this script reaps it); if this process dies first: $0 down $name"
    elif [[ "$name" =~ ^$PREFIX-$OWNER-[0-9]{10}- ]]; then
      log "$name has no TTL (reap destroys it once it is ${LEGACY_HOURS}h old); if this process dies before its teardown line, destroy it with: $0 down $name"
    else
      log "$name has no TTL and no reapable name, so nothing reaps it; if this process dies before its teardown line, destroy it with: $0 down $name"
    fi
  fi
  local dir
  dir=$(state_dir "$name")
  write_record "$dir"
  lease_take "$dir"
  if [ "$keep" = 1 ]; then
    # A kept VM's finished run is not reattached by the next run; a detach (HUP) keeps the record.
    trap 'rm -f "$(state_dir "$RUN_VM")/run"' EXIT
    leftover "left=1 owner=$OWNER vm=$name kept=1"
    log "--keep: leaving $name running; destroy with: $0 down $name"
  fi

  local qdest rc=0 vmt
  qdest=$(printf %q "$dest")
  if [ ! -f "$dir/synced" ]; then
    { for e in ${envs[@]+"${envs[@]}"}; do printf 'export %s=%q\n' "${e%%=*}" "${e#*=}"; done
      for n in ${passes[@]+"${passes[@]}"}; do printf 'export %s=%q\n' "$n" "${!n}"; done; } \
      | remote "$name" 'umask 077 && cat > ~/.ubirun-env'
    cmd_sync "$name" "$src" "$dest"
    # A subdirectory of a checkout uploads the whole .git with only its own
    # files, so its tree is compared VM to VM (tiers) but not to this side.
    if [ -z "$(git -C "$src" rev-parse --show-prefix 2>/dev/null)" ]; then
      vmt=$(vm_tree "$name" "$qdest") || vmt=unavailable
      if [ "$vmt" != "$TREE" ]; then
        log "UBI_VM_TREE_MISMATCH: vm=$name tree=${vmt:0:12} expected=${TREE:0:12}: the unpacked checkout is not the one this run was keyed on"
        exit 3
      fi
    fi
    [ -z "$setup" ] || remote "$name" 'cat > ~/.ubirun-setup.sh' <"$setup"
    : >"$dir/synced"
  fi
  if [ -n "$setup" ]; then
    log "running setup $(basename "$setup")"
    detached "$name" setup "cd $qdest && . ~/.ubirun-env && bash -l ~/.ubirun-setup.sh" || { rc=$?; log "setup failed (exit $rc)"; exit "$rc"; }
  fi

  if [ ${#TIER_NAMES[@]} -gt 0 ]; then
    run_tiers "$name" "$qdest" || rc=$?
  else
    log "running on $name: $*"
    detached "$name" command "cd $qdest && . ~/.ubirun-env && bash -lc $(printf %q "$*")" || rc=$?
    log "command exited $rc after $(( $(date +%s) - $(cat "$dir/phase.command.start" 2>/dev/null || date +%s) ))s"
  fi

  local p
  for p in ${pulls[@]+"${pulls[@]}"}; do
    if [ -n "$PULL_ROOT" ] && ! inside_dir "${p#*:}" "$PULL_ROOT"; then
      log "pull refused: ${p#*:} resolves outside $PULL_ROOT"
      [ "$rc" -ne 0 ] || rc=1
      continue
    fi
    cmd_pull "$name" "${p%%:*}" "${p#*:}" || log "pull failed: $p"
  done
  [ ${#TIER_NAMES[@]} -eq 0 ] || verify_line
  return "$rc"
}

# attach NAME: resume the run recorded for NAME on this machine (the same
# invocation, key and tiers), as a rerun of the same command would.
cmd_attach() {
  local name=${1:-}
  [ -n "$name" ] || die "attach: missing NAME"
  valid_name "$name" || die "invalid VM name '$name'"
  [ -f "$(state_dir "$name")/run" ] || die "attach: no run record for $name on this machine ($(state_dir "$name")/run); a machine replacement loses it"
  # shellcheck disable=SC1091
  . "$(state_dir "$name")/run"
  FORCE_ATTACH=$name
  cmd_run "${RUN_ARGS[@]}"
}

# verify [run opts] [--trust-config] [-- COMMAND]: run the repository's
# committed remote verify. .gstack/ubicloud.json under --src (default .)
# supplies setup, command, size, location, storage, image, env, pass and pull;
# flags given here and a trailing -- COMMAND override it. Without the file it
# refuses, so every lane runs the one committed definition instead of its own
# wrapper.
#
# The file is repository content and gets no reach beyond the checkout on its
# own: its setup script and pull destinations must resolve inside --src, and a
# local variable it lists under pass is forwarded only when this command line
# also names it (--pass NAME) or grants every listed name (--trust-config).
cmd_verify() {
  local src=. i j g n cfg cfg_setup cfg_cmd parsed err rc=0 trust=0 cfg_args=() cfg_pass=() user_pre=() user_cmd=() granted=() missing=() cfg_tier_names=() cfg_tier_cmds=()
  for (( i = 1; i <= $#; i++ )); do
    [ "${!i}" = -- ] && break
    if [ "${!i}" = --src ]; then j=$(( i + 1 )); src=${!j}; fi
  done
  cfg="$src/.gstack/ubicloud.json"
  [ -f "$cfg" ] || die "verify: no $cfg; commit one ({\"setup\": \"scripts/ubicloud/bootstrap.sh\", \"command\": \"bash scripts/ubicloud/verify.sh\"}) so every lane runs the same verify instead of its own wrapper"
  err=$(mktemp)
  parsed=$(python3 -c '
import json, os, re, shlex, sys
cfg, src = sys.argv[1], sys.argv[2]
try:
    c = json.load(open(cfg))
except ValueError:
    sys.exit(3)
if not isinstance(c, dict):
    sys.exit(3)
base, root = os.path.abspath(src), os.path.realpath(src)
def inside(rel, what):
    if not isinstance(rel, str) or not rel or os.path.isabs(rel) or rel.startswith("~") or ".." in rel.replace("\\", "/").split("/"):
        print("%s %r must be a relative path inside the checkout" % (what, rel), file=sys.stderr); sys.exit(2)
    full = os.path.realpath(os.path.join(root, rel))
    if full != root and not full.startswith(root + os.sep):
        print("%s %r resolves outside the checkout (%s)" % (what, rel, full), file=sys.stderr); sys.exit(2)
    return os.path.join(base, rel)
q = lambda s: shlex.quote(str(s))
args = []
for key, flag in (("size", "-s"), ("location", "-l"), ("storage", "-S"), ("image", "-b")):
    if key in c: args += [flag, q(c[key])]
for item in c.get("env", []): args += ["--env", q(item)]
for item in c.get("pull", []):
    remote, sep, local = str(item).partition(":")
    if not sep or not remote:
        print("pull entry %r must be REMOTE_GLOB:LOCAL_DIR" % (item,), file=sys.stderr); sys.exit(2)
    args += ["--pull", q(remote + ":" + inside(local, "pull destination"))]
tiers = c.get("tiers")
names = []
if tiers is not None:
    if "command" in c:
        print("UBI_CONFIG_TIERS_AND_COMMAND: give either command or tiers, not both", file=sys.stderr); sys.exit(2)
    if not isinstance(tiers, list) or not tiers:
        print("UBI_CONFIG_TIER_NAME: tiers must be a non-empty list of {\"name\", \"command\"}", file=sys.stderr); sys.exit(2)
    for t in tiers:
        name = t.get("name") if isinstance(t, dict) else None
        if not isinstance(name, str) or not re.fullmatch(r"[a-z0-9][a-z0-9_-]{0,31}", name):
            print("UBI_CONFIG_TIER_NAME: tier name %r must match ^[a-z0-9][a-z0-9_-]{0,31}$" % (name,), file=sys.stderr); sys.exit(2)
        if name in names:
            print("UBI_CONFIG_TIER_NAME: tier name %r appears twice" % name, file=sys.stderr); sys.exit(2)
        if not isinstance(t.get("command"), str) or not t["command"].strip():
            print("UBI_CONFIG_TIER_NAME: tier %r needs a command" % name, file=sys.stderr); sys.exit(2)
        names.append(name)
setup = c.get("setup", "")
print("cfg_tier_names=(" + " ".join(q(n) for n in names) + ")")
print("cfg_tier_cmds=(" + " ".join(q(t["command"]) for t in (tiers or [])) + ")")
print("cfg_args=(" + " ".join(args) + ")")
print("cfg_pass=(" + " ".join(q(x) for x in c.get("pass", [])) + ")")
print("cfg_setup=" + q(inside(setup, "setup") if setup else ""))
print("cfg_cmd=" + q(c.get("command", "")))
' "$cfg" "$src" 2>"$err") || rc=$?
  case $rc in
    0) ;;
    2) local why; why=$(cat "$err"); rm -f "$err"; die "verify: $cfg: $why" ;;
    *) rm -f "$err"; die "verify: $cfg is not valid JSON" ;;
  esac
  rm -f "$err"
  eval "$parsed"
  while [ $# -gt 0 ]; do
    case $1 in
      --) shift; user_cmd=("$@"); break ;;
      --trust-config) trust=1; shift ;;
      --keep|--resume|--no-resume|--rerun-failed|--probe) user_pre+=("$1"); shift ;;
      --pass|-S|--storage|-s|--size|-l|--location|-n|--name|-b|--image|--src|--dest|--setup|--env|--pull)
        [ $# -ge 2 ] || die "verify: $1 needs a value"
        [ "$1" != --pass ] || granted+=("$2")
        user_pre+=("$1" "$2"); shift 2 ;;
      *) die "verify: unknown option $1" ;;
    esac
  done
  for n in ${cfg_pass[@]+"${cfg_pass[@]}"}; do
    pass_name "$n"
    if [ "$trust" = 1 ]; then cfg_args+=(--pass "$n"); continue; fi
    for g in ${granted[@]+"${granted[@]}"}; do [ "$g" = "$n" ] && continue 2; done
    missing+=("$n")
  done
  [ ${#missing[@]} -eq 0 ] || die "verify: $cfg asks to forward local ${missing[*]}; grant each on this command line with --pass NAME, or every name it lists with --trust-config"
  # A trailing -- COMMAND replaces the configured tiers as it replaces command.
  if [ ${#user_cmd[@]} -eq 0 ] && [ ${#cfg_tier_names[@]} -gt 0 ]; then
    TIER_NAMES=("${cfg_tier_names[@]}") TIER_CMDS=("${cfg_tier_cmds[@]}")
  else
    [ ${#user_cmd[@]} -gt 0 ] || [ -n "$cfg_cmd" ] || die "verify: $cfg names no command and none was given after --"
    [ ${#user_cmd[@]} -gt 0 ] || user_cmd=("$cfg_cmd")
  fi
  log "verify: $cfg"
  PULL_ROOT=$(cd "$src" && pwd)
  cmd_run ${cfg_args[@]+"${cfg_args[@]}"} ${cfg_setup:+--setup "$cfg_setup"} --src "$src" ${user_pre[@]+"${user_pre[@]}"} -- ${user_cmd[@]+"${user_cmd[@]}"}
}

usage() {
  cat <<EOF
usage: ubi-runner.sh <command> [args]

  run [up opts] [--src DIR] [--dest PATH] [--setup FILE] [--env K=V]...
      [--pass NAME]... [--pull REMOTE_GLOB:LOCAL_DIR]... [--keep] [--key-input S]... [--probe] -- COMMAND
                         up + sync + setup + command + pull + destroy; exits with COMMAND's status.
                         A rerun of the same command (same run key) reattaches to its live VM;
                         --probe prints UBI_ATTACH_INFO (and the tier plan) and exits
  verify [run opts] [--trust-config] [--resume|--no-resume] [--rerun-failed] [-- COMMAND]
                         run the repository's committed verify (.gstack/ubicloud.json under --src);
                         its setup script and every pull destination stay inside --src (checked
                         again at pull time), and its pass names are forwarded only when granted
                         here (--pass NAME, or all: --trust-config). With tiers, a pass checkpoint
                         under the same run key is reused (resume is the default)
  attach NAME            resume the run recorded for NAME on this machine, as a rerun would
  up [-s SIZE] [-l LOCATION] [-n NAME] [-S STORAGE_GIB] [-b IMAGE]
                         create a VM and wait for SSH; prints its name
                         (STORAGE_GIB: one of $ALLOWED_STORAGE)
  ssh NAME [COMMAND]     shell or login-shell command on the VM (user ubi, passwordless sudo)
  sync NAME [SRC] [DEST] stream a checkout (tracked + untracked-unignored + .git)
  pack [SRC]             write that checkout tarball to stdout
  unpack NAME DEST       extract a tarball from stdin into DEST on the VM
  pull NAME REMOTE_GLOB LOCAL_DIR
                         copy matching remote entries into LOCAL_DIR
  down NAME [-l LOC]     destroy the VM; returns once it is confirmed gone or never existed
  list [--mine]          list all VMs in the project, or only this owner's
  usage                  VMs and vCPUs per owner across the project
  owner                  print this caller's owner tag ($OWNER)
  records                VMs this machine created and has not confirmed gone ($VM_RECORD)
  gc HOURS               destroy this owner's VMs older than HOURS (never other owners')
  reap                   destroy every VM whose -t<hours> TTL has ended (any owner) and this
                         owner's TTL-less ubirun-* VMs older than UBI_LEGACY_HOURS
  cli ARGS...            raw Ubicloud CLI passthrough (e.g. cli vm list)

signals: INT and TERM tear the VM down. HUP, once a remote phase is live, detaches
(UBI_DETACHED, exit 129; the VM runs on under its TTL). SIGKILL or a machine stop leaves
the run record and the VM; rerun the same command to reattach (UBI_ATTACH_BUSY while
another runner owns it; exit 125 UBI_ATTACH_LOST when the remote session left no status).

VMs are named $PREFIX-<owner>-<epoch>-<suffix>-t<ttl hours>; up, run and verify need
UBI_OWNER (e.g. your thread code); run and verify end with a UBICLOUD: left=<n> line.
defaults: size=$DEFAULT_SIZE location=$DEFAULT_LOCATION (env UBI_SIZE, UBI_LOCATION)
env: UBI_TTL_HOURS (${TTL_HOURS}h in the name, 1-999), UBI_REAP (0: up skips the reap),
     UBI_LEGACY_HOURS (${LEGACY_HOURS}h: reap's bound for this owner's TTL-less ubirun-* names),
     UBI_IDLE_TIMEOUT (${IDLE_TIMEOUT}s of silence kills the remote command, exit 124; 0 disables),
     UBI_RUN_TIMEOUT (${RUN_TIMEOUT}s wall clock; 0 unlimited), UBI_HEARTBEAT (${HEARTBEAT}s between heartbeat lines),
     UBI_QUOTA_VCPUS (project vCPU ceiling for the preflight; else the last refusal's maximum),
     UBI_QUOTA_WAIT (${QUOTA_WAIT}s to wait for quota room instead of refusing),
     UBI_GC_HOURS (unset/0: no sweep on up), UBI_CREATE_GRACE (${CREATE_GRACE}s),
     UBI_DOWN_TIMEOUT (${DOWN_TIMEOUT}s), UBI_API_TIMEOUT (${API_TIMEOUT}s), UBI_VM_RECORD (scratch VM-id file),
     UBI_ALLOWED_STORAGE (the -S sizes Ubicloud accepts; default "320 640"),
     UBI_CHECKPOINT_DIR (tier checkpoints; $CHECKPOINT_DIR), UBI_CHECKPOINT_MAX_AGE (${CHECKPOINT_MAX_AGE}s a pass is reused)
EOF
}

cmd=${1:-help}
[ $# -eq 0 ] || shift
case $cmd in
  owner|pack|records|help|-h|--help) ;;
  *) [ -n "${UBICLOUD_API_KEY:-}" ] || die "UBICLOUD_API_KEY is not set (create a token under your Ubicloud project's Tokens page)" ;;
esac
case $cmd in
  run) cmd_run "$@" ;;
  verify) cmd_verify "$@" ;;
  attach) cmd_attach "$@" ;;
  up) trap 'trap "" INT TERM HUP QUIT; [ -z "$UP_NAME" ] || [ -n "$UP_READY" ] || cmd_down "$UP_NAME" || log "WARNING: failed to destroy $UP_NAME; run: $0 down $UP_NAME"' EXIT
      trap 'exit 130' INT TERM HUP QUIT
      cmd_up "$@" ;;
  ssh) name=$1; shift; load "$name"
       # shellcheck disable=SC2046
       if [ $# -eq 0 ]; then exec ssh -t $(ssh_opts) "ubi@$IP"; else watched "$name" ssh "bash -lc $(printf %q "$*")"; fi ;;
  sync) cmd_sync "$@" ;;
  pack) cmd_pack "$@" ;;
  unpack) cmd_unpack "$@" ;;
  pull) cmd_pull "$@" ;;
  down) cmd_down "$@" ;;
  list) cmd_list "$@" ;;
  usage) cmd_usage ;;
  owner) echo "$OWNER" ;;
  records) cmd_records ;;
  gc) cmd_gc "$@" ;;
  reap) cmd_reap ;;
  cli) cli "$@" ;;
  help|-h|--help) usage ;;
  *) usage >&2; exit 2 ;;
esac