Garry's Opinionated OpenClaw/Hermes Agent Brain
TypeScript
#!/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'
#
# Vendored from gstack's scripts/ubicloud/ubi-runner.sh (synced at gstack
# 5532345a, v1.91.341.0, plus gstack #3746 at 74836e41 and #3756 at 693ee713:
# macOS pack and usage, empty projects, owner-scoped reap). 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.
#
# gbrain additions (keep them when syncing; each is marked "gbrain:" below):
# - UBI_REAP defaults to 0: `up` reaps nothing unless UBI_REAP=1, and says so.
# - --ttl-hours H on up and run (overrides UBI_TTL_HOURS); with -n NAME it
# appends -t<H>, and a ubirun- NAME without a -t<H> TTL is refused.
# - vm_rows also reads the older ubirun-<owner>-<epoch>-x<expiry>-<suffix> names.
# - list --mine and gc cover every VM this machine created, under any owner tag.
# - pack ships a slim .git (HEAD's branch and origin/master only), and a
# split index's shared half.
# - --env is checked like --pass (NAME=VALUE, never UBICLOUD_*).
# - watched keeps one log per call (ci:ubicloud runs several on one VM at
# once) and only after a kill.
# - Bash 5.2 lost-signal-trap guard (set -E, FAILED, finish).
# - UBI_REAP takes the usual false spellings (0/false/no/off) and refuses
# anything it cannot read, instead of treating every value but 0 as on.
# - down retries a destroy request that timed out or got a 5xx (also 408,
# 429 and 404) inside its poll loop, backing off 1, 2, 4 ... 60 s, until
# UBI_DOWN_TIMEOUT, and gives up early only on another 4xx; reap bounds
# each VM's wait with
# UBI_REAP_DOWN_TIMEOUT. Both are pending upstream (GSTA-36).
#
# 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, HUP, QUIT) 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 only this owner's VMs: its ubirun-<owner>-* names whose TTL
# expired more than ten minutes ago, and those with no TTL once they are
# UBI_LEGACY_HOURS old (default 4). Another owner's VM, an untagged one and
# names outside the ubirun- prefix are never reaped, expired or not; reap only
# counts other owners' expired VMs in its log (cloud deletes stay owner-scoped,
# GST-573). Every `up` runs it first when UBI_REAP=1 (gbrain: off by default
# until gbrain's TTL-less VMs older than 4 h are gone; the operator reaper,
# scripts/ubicloud/reap-expired.ts, still destroys expired TTL VMs of every
# owner), so a lane killed by a sleeping machine has its leftovers destroyed by
# its own next `up`. --ttl-hours H (gbrain) sets one VM's TTL.
#
# 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 $STATE_ROOT/quota-max), `up` adds the
# size's vCPUs to the project's running VMs and refuses before any create when
# that exceeds it; UBI_QUOTA_WAIT=<seconds> waits for room instead.
#
# Watchdog: `run`, `verify` and `ssh NAME COMMAND` stream the remote output
# through a watchdog that logs a heartbeat every UBI_HEARTBEAT seconds (300)
# and kills a command silent for UBI_IDLE_TIMEOUT seconds (1800) or older than
# UBI_RUN_TIMEOUT seconds (0, unlimited), exiting 124 with the last 40 lines,
# so a hung verify fails fast instead of holding the VM until its TTL.
#
# `verify` is the one entry point for a repository's full remote verify: it
# reads .gstack/ubicloud.json (setup, command, size, location, env, pass, pull)
# and runs it through `run`, so lanes share one committed definition instead of
# per-lane wrappers.
set -Eeuo pipefail
# Keep heredoc bodies on temp files, not the pipe window (test/heredoc-pipe-deadlock.test.ts).
BASH_COMPAT=50
API="${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="${UBI_DOWN_TIMEOUT:-900}"
REAP_DOWN_TIMEOUT="${UBI_REAP_DOWN_TIMEOUT:-180}"
POLL="${UBI_POLL_SECONDS:-5}"
ALLOWED_STORAGE="${UBI_ALLOWED_STORAGE:-320 640}"
TTL_HOURS="${UBI_TTL_HOURS:-3}"
LEGACY_HOURS="${UBI_LEGACY_HOURS:-4}"
# gbrain: no reap before up unless UBI_REAP=1 (GBRA-108).
REAP="${UBI_REAP:-0}"
REAP_GRACE=600
IDLE_TIMEOUT="${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
die() { echo "ubi-runner: $*" >&2; exit 1; }
log() { echo "ubi-runner: $*" >&2; }
# gbrain: Bash 5.2 can lose a signal trap: when the signal lands just before
# the shell parses a $(...), the trap runs inside that parse, fails to parse
# itself ("trap: line 2: unexpected EOF while looking for matching `)'") and the
# shell exits 2 without running it (fixed in bash 5.3). The EXIT trap still
# runs. The only other exit 2 here is a failed command, which sets FAILED
# through the ERR trap, so an exit 2 without FAILED is reported as the
# signal's 130.
FAILED=""
trap 'FAILED=1' ERR
# finish STATUS NAME: EXIT handler of `up`. Destroys NAME unless it is empty,
# then exits with STATUS.
finish() {
local rc=$1
[ "$rc" != 2 ] || [ -n "$FAILED" ] || rc=130
[ -z "$2" ] || cmd_down "$2" || log "WARNING: failed to destroy $2; run: $0 down $2"
exit "$rc"
}
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; 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"
# check_seconds VAR: UBI_DOWN_TIMEOUT and UBI_REAP_DOWN_TIMEOUT are checked only
# by the commands that read them (up and down, reap), so a stale value never
# blocks list, usage or a teardown that does not read it.
check_seconds() {
[[ "${!1}" =~ ^[1-9][0-9]*$ ]] || die "UBI_$1 must be a whole number of seconds from 1"
}
owner_id() {
local raw=${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 PHASE-<runner pid>.log in the VM's state
# dir (gbrain: one file per call, since ci:ubicloud runs several commands on
# one VM at once; kept only after a kill), 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"
rm -f "$out"
return 0
fi
remote_cancel "$name" "$sidf"
log "watchdog: kept the output in $out"
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"
rm -f "$out"
return "$rc"
}
# 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 (gbrain:
# or the older -x<expiry epoch>- form's expiry, when later than its creation),
# 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
[ -n "$name" ] || continue
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]}
if [[ "$name" =~ ^${PREFIX}-[a-z][a-z0-9]{0,11}-[0-9]{10}-x([0-9]{10})-[a-z0-9]+$ ]] && [ "${BASH_REMATCH[1]}" -gt "$created" ]; then
expires=$(( 10#${BASH_REMATCH[1]} ))
fi
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
}
# mine_rows: vm_rows for the VMs tagged with this owner or created from this
# machine (their `up` state is still here). gbrain: list --mine and gc use it,
# so a run started under another UBI_OWNER is still found.
mine_rows() {
local loc name owner rest
vm_rows | while read -r loc name owner rest; do
if [ "$owner" = "$OWNER" ] || [ -f "$(state_dir "$name")/env" ]; then echo "$loc $name $owner $rest"; fi
done
}
# reap: destroy the caller's own VMs whose TTL ended more than REAP_GRACE
# seconds ago, and its TTL-less ubirun-<UBI_OWNER>-* names at least LEGACY_HOURS
# old. Every other VM is never touched, whatever its TTL says: a delete stays
# with the owner that created the VM. Other owners' expired VMs are only counted.
cmd_reap() {
local now rows loc name owner expires created n=0 failed=0 others=0
check_seconds REAP_DOWN_TIMEOUT
# cmd_down reads DOWN_TIMEOUT; a reap waits at most REAP_DOWN_TIMEOUT per VM.
local DOWN_TIMEOUT=$REAP_DOWN_TIMEOUT
[[ "$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 [ "$owner" != "$OWNER" ]; then
[ "$expires" = - ] || [ "$now" -lt $(( expires + REAP_GRACE )) ] || others=$(( others + 1 ))
continue
fi
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:-}" ] && [ "$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"
[ "$others" -eq 0 ] || log "reap: left $others expired VMs of other owners; only their owners reap them"
[ "$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)
mine_rows | while read -r loc name owner _; do
[[ "$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)
local rows others
rows=$(mine_rows)
others=$(printf '%s\n' "$rows" | awk -v o="$OWNER" 'NF && $3!=o {print $3}' | sort -u | paste -sd, -)
log "list --mine: owner tag $OWNER plus VMs this machine created${others:+ (also under: $others)}"
[ -z "$rows" ] || printf '%s\n' "$rows" | awk '{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 rows loc name owner f i=0 unread=0
rows=$(vm_rows) || { log "usage: could not list the project's VMs"; return 1; }
tmp=$(mktemp -d)
while read -r loc name owner _; do
[ -n "$name" ] || continue
i=$(( i + 1 ))
{
case $(api "$tmp/$i.show" vm "$loc/$name" show) in
200) sed -n "s/^size: /$owner /p" "$tmp/$i.show" >"$tmp/$i" ;;
404) ;;
*) : >"$tmp/$i" ;;
esac
rm -f "$tmp/$i.show"
} &
[ $(( i % 8 )) -ne 0 ] || wait
done <<<"$rows"
wait
for f in "$tmp"/*; do [ ! -e "$f" ] || [ -s "$f" ] || unread=$(( unread + 1 )); done
if [ "$unread" -gt 0 ]; then
rm -rf "$tmp"
log "usage: could not read the size of $unread of $i VMs"
return 1
fi
find "$tmp" -type f -exec cat {} + | 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 [TTL]: a fresh name for this owner ending in -t<TTL> (default UBI_TTL_HOURS).
new_name() {
echo "$PREFIX-$OWNER-$(date +%s)-$(head -c4 /dev/urandom | od -An -tx1 | tr -d ' \n')-t${1:-$TTL_HOURS}"
}
# gbrain: check_ttl H validates --ttl-hours.
check_ttl() {
[[ "$1" =~ ^[1-9][0-9]{0,2}$ ]] || die "--ttl-hours must be a whole number of hours from 1 to 999"
}
# gbrain: vm_name NAME TTL: the name up and run create. No NAME: a generated
# one, with TTL hours (else UBI_TTL_HOURS). -n NAME with --ttl-hours gets
# -t<TTL> appended. A ubirun- NAME must end in a -t<hours> TTL, or no reaper
# could ever judge it (#8050); names outside the prefix are the caller's to manage.
vm_name() {
local name=$1 ttl=$2
if [ -z "$name" ]; then new_name "$ttl"; return; fi
if [ -n "$ttl" ]; then
[[ ! "$name" =~ -t[0-9]+$ ]] || die "-n $name already ends in a TTL; drop --ttl-hours or the -t<hours> suffix"
name="$name-t$ttl"
fi
if [[ "$name" = "$PREFIX"-* ]] && [[ ! "$name" =~ -t[1-9][0-9]{0,2}$ ]]; then
die "-n $name has no -t<hours> TTL, so no reaper could destroy it if this run dies; add --ttl-hours H (1-999) or name it outside the $PREFIX- prefix"
fi
echo "$name"
}
# 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=$QUOTA_WAIT
while :; do
if ! used=$(cmd_usage 2>/dev/null | awk '$1=="total" {print $3}') || ! [[ "$used" =~ ^[0-9]+$ ]]; then
if [ "$remaining" -le 0 ]; then
log "quota preflight: could not read the project's vCPU usage; the API's own answer decides"
return 0
fi
log "quota: could not read the project's vCPU usage; retrying, up to ${remaining}s more"
step=$(( remaining < 30 ? remaining : 30 ))
sleep "$step"
remaining=$(( remaining - step ))
continue
fi
[ $(( used + need )) -gt "$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 (it frees only this owner's expired VMs; $0 usage shows who holds the rest, and scripts/ubicloud/reap-expired.ts destroys other owners' expired ones), 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
check_seconds DOWN_TIMEOUT
# gbrain: UBI_REAP=false (or no/off) must not turn reaping on; only up reads it.
case $(printf %s "$REAP" | tr '[:upper:]' '[:lower:]') in
0|false|no|off) REAP=0 ;;
1|true|yes|on) REAP=1 ;;
*) die "UBI_REAP must be 1 or 0 (true/false, yes/no and on/off also work), not '$REAP'" ;;
esac
local size=$DEFAULT_SIZE location=$DEFAULT_LOCATION name="" storage="" image=ubuntu-noble ttl=""
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 ;;
--ttl-hours) check_ttl "$2"; ttl=$2; shift 2 ;;
*) die "up: unknown option $1" ;;
esac
done
name=$(vm_name "$name" "$ttl")
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 [ "$REAP" != 0 ]; then
cmd_reap || log "reap failed; continuing"
elif [ -z "${UBI_REAP:-}" ]; then
log "reap skipped: gbrain defaults UBI_REAP=0 until its TTL-less VMs older than ${LEGACY_HOURS}h are gone (UBI_REAP=1 reaps; reap-expired.ts still destroys expired TTL VMs)"
fi
if [ "$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=$(( $(date +%s) + DOWN_TIMEOUT )) seen=0 asked=0 backoff=1 out code now failed=""
out=$(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
asked=$now
backoff=1
failed=""
log "destroy requested: $loc/$name"
elif [[ "$code" =~ ^4[0-9][0-9]$ ]] && [ "$code" != 404 ] && [ "$code" != 408 ] && [ "$code" != 429 ]; then
cat "$out" >&2
rm -f "$out"
log "FAILED to destroy $loc/$name (HTTP $code); retry: $0 down $name"
return 1
else
[ "$code" = "$failed" ] || log "destroy request for $loc/$name got HTTP $code; retrying until ${DOWN_TIMEOUT}s have passed"
failed=$code
asked=$(( now - 60 + backoff ))
backoff=$(( backoff * 2 > 60 ? 60 : backoff * 2 ))
fi
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 ${DOWN_TIMEOUT}s${failed:+ (last destroy request: HTTP $failed)}; 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. The archive is built in two
# passes inside the snapshot directory because macOS's bsdtar stops reading
# options at the first operand and resolves -T names after a -C, so no single
# tar command line works on both it and GNU tar (gstack #3680). COPYFILE_DISABLE=1
# keeps Apple's tar from adding ._* AppleDouble entries for files with
# extended attributes, which the VM would see as untracked files.
cmd_pack() {
local src tmp gitdir branch head entry shared specs
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= "$tmp/.git"
# gbrain: a slim snapshot, only HEAD (on its branch) and origin/master, so a
# checkout that fetched many branches does not upload all of them to every VM.
[ -n "$branch" ] || branch="detached-${head:0:12}"
specs=("+HEAD:refs/heads/$branch")
if git -C "$src" rev-parse -q --verify refs/remotes/origin/master >/dev/null; then
specs+=("+refs/remotes/origin/master:refs/remotes/origin/master")
fi
git -C "$tmp/.git" -c gc.auto=0 fetch -q --no-tags --update-shallow "$src" "${specs[@]}" \
|| die "pack: could not snapshot the refs of $src"
git -C "$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 (gbrain: a
# split index with its shared half, sharedindex.<sha>, which git looks up
# beside it). 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
# cannot read a staged file.
cp "$(cd "$src" && cd "$(dirname "$(git rev-parse --git-path index)")" && pwd)/index" "$tmp/.git/index"
shared=$(cd "$src" && git rev-parse --shared-index-path)
[ -z "$shared" ] || cp "$(cd "$src" && cd "$(dirname "$shared")" && pwd)/$(basename "$shared")" "$tmp/.git/"
# Read the copy, not the live index, so the pack matches it; a gitlink's
# sha (mode 160000) is a submodule commit this object store lacks.
GIT_INDEX_FILE="$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 $src"
(
cd "$src"
export COPYFILE_DISABLE=1
git ls-files -z -co --exclude-standard \
| while IFS= read -r -d '' f; do
if [ -e "$f" ] || [ -L "$f" ]; then printf '%s\0' "$f"; fi
done \
| tar --null -T - -cf "$tmp/files.tar" \
&& tar -rf "$tmp/files.tar" -C "$tmp" .git \
&& gzip -c "$tmp/files.tar"
)
rm -rf "$tmp"; trap - EXIT
else
COPYFILE_DISABLE=1 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 OPTION NAME: a variable this runner may forward to a VM. Its own
# credentials (UBICLOUD_*) never leave this machine, whoever asks (gbrain:
# --env NAME=VALUE is checked the same way).
pass_name() {
[[ "$2" =~ ^[A-Za-z_][A-Za-z0-9_]*$ ]] || die "$1 $2: not a variable name"
case $2 in UBICLOUD_*) die "$1 $2: 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=$1 rows left others
# gbrain: an exit 2 without FAILED is a lost signal trap (see finish).
[ "$rc" != 2 ] || [ -n "$FAILED" ] || rc=130
trap "" INT TERM HUP QUIT
cmd_down "$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"
if [ "$left" != 0 ]; then
log "VM cleanup not confirmed for $RUN_VM (left=$left); destroy it with: $0 down $RUN_VM"
[ "$rc" -ne 0 ] || rc=1
fi
exit "$rc"
}
cmd_run() {
require_owner
local up_args=() src=. dest="" setup="" keep=0 pulls=() envs=() name="" ttl=""
while [ $# -gt 0 ]; do
case $1 in
-S|--storage) check_storage "$2"; up_args+=("$1" "$2"); shift 2 ;;
-s|--size|-l|--location|-b|--image) up_args+=("$1" "$2"); shift 2 ;;
-n|--name) name=$2; shift 2 ;;
--ttl-hours) check_ttl "$2"; ttl=$2; shift 2 ;;
--src) src=$2; shift 2 ;;
--dest) dest=$2; shift 2 ;;
--setup) setup=$2; shift 2 ;;
--env) [[ "$2" == *=* ]] || die "--env $2: give NAME=VALUE"; pass_name --env "${2%%=*}"; envs+=("$2"); shift 2 ;;
--pass) pass_name --pass "$2"; [ -n "${!2+x}" ] || die "--pass $2: not set locally"; envs+=("$2=${!2}"); shift 2 ;;
--pull) pulls+=("$2"); shift 2 ;;
--keep) keep=1; shift ;;
--) shift; break ;;
*) die "run: unknown option $1" ;;
esac
done
[ $# -gt 0 ] || die "run: missing command after --"
[ -z "$setup" ] || [ -f "$setup" ] || die "setup script not found: $setup"
src=$(cd "$src" && pwd)
[ -n "$dest" ] || dest="work/$(basename "$src")"
name=$(vm_name "$name" "$ttl")
up_args+=(-n "$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 HUP QUIT
cmd_up "${up_args[@]}" >/dev/null
if [[ "$name" =~ -t([0-9]+)$ ]]; then
log "$name carries a ${BASH_REMATCH[1]}h TTL (this owner's next up with UBI_REAP=1, or reap, destroys it once it expires); 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 $name"
fi
if [ "$keep" = 1 ]; then
trap - EXIT
leftover "left=1 owner=$OWNER vm=$name kept=1"
log "--keep: leaving $name running; destroy with: $0 down $name"
fi
local e
for e in ${envs[@]+"${envs[@]}"}; do printf 'export %s=%q\n' "${e%%=*}" "${e#*=}"; done \
| remote "$name" 'umask 077 && cat > ~/.ubirun-env'
cmd_sync "$name" "$src" "$dest"
local qdest rc=0
qdest=$(printf %q "$dest")
if [ -n "$setup" ]; then
remote "$name" 'cat > ~/.ubirun-setup.sh' <"$setup"
log "running setup $(basename "$setup")"
watched "$name" setup "cd $qdest && . ~/.ubirun-env && bash -l ~/.ubirun-setup.sh" || { rc=$?; log "setup failed (exit $rc)"; exit "$rc"; }
fi
local start
start=$(date +%s)
log "running on $name: $*"
watched "$name" command "cd $qdest && . ~/.ubirun-env && bash -lc $(printf %q "$*")" || rc=$?
log "command exited $rc after $(( $(date +%s) - start ))s"
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: $p"
done
return "$rc"
}
# 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=()
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=$(python3 -c '
import json, os, shlex, sys
cfg, src = sys.argv[1], sys.argv[2]
try:
c = json.load(open(cfg))
except ValueError:
sys.exit(3)
if not isinstance(c, dict):
sys.exit(3)
base, root = os.path.abspath(src), os.path.realpath(src)
def inside(rel, what):
if not isinstance(rel, str) or not rel or os.path.isabs(rel) or rel.startswith("~") or ".." in rel.replace("\\", "/").split("/"):
print("%s %r must be a relative path inside the checkout" % (what, rel), file=sys.stderr); sys.exit(2)
full = os.path.realpath(os.path.join(root, rel))
if full != root and not full.startswith(root + os.sep):
print("%s %r resolves outside the checkout (%s)" % (what, rel, full), file=sys.stderr); sys.exit(2)
return os.path.join(base, rel)
q = lambda s: shlex.quote(str(s))
args = []
for key, flag in (("size", "-s"), ("location", "-l"), ("storage", "-S"), ("image", "-b")):
if key in c: args += [flag, q(c[key])]
for item in c.get("env", []): args += ["--env", q(item)]
for item in c.get("pull", []):
remote, sep, local = str(item).partition(":")
if not sep or not remote:
print("pull entry %r must be REMOTE_GLOB:LOCAL_DIR" % (item,), file=sys.stderr); sys.exit(2)
args += ["--pull", q(remote + ":" + inside(local, "pull destination"))]
setup = c.get("setup", "")
print("cfg_args=(" + " ".join(args) + ")")
print("cfg_pass=(" + " ".join(q(x) for x in c.get("pass", [])) + ")")
print("cfg_setup=" + q(inside(setup, "setup") if setup else ""))
print("cfg_cmd=" + q(c.get("command", "")))
' "$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) user_pre+=("$1"); shift ;;
--pass|-S|--storage|-s|--size|-l|--location|-n|--name|-b|--image|--ttl-hours|--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 --pass "$n"
if [ "$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"
[ ${#user_cmd[@]} -gt 0 ] || [ -n "$cfg_cmd" ] || die "verify: $cfg names no command and none was given after --"
[ ${#user_cmd[@]} -gt 0 ] || user_cmd=("$cfg_cmd")
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[@]}"
}
usage() {
cat <<EOF
usage: ubi-runner.sh <command> [args]
run [up opts] [--ttl-hours H] [--src DIR] [--dest PATH] [--setup FILE] [--env K=V]...
[--pass NAME]... [--pull REMOTE_GLOB:LOCAL_DIR]... [--keep] -- COMMAND
up + sync + setup + command + pull + destroy; exits with COMMAND's status
verify [run opts] [--trust-config] [-- 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)
up [-s SIZE] [-l LOCATION] [-n NAME] [--ttl-hours H] [-S STORAGE_GIB] [-b IMAGE]
create a VM and wait for SSH; prints its name
(STORAGE_GIB: one of $ALLOWED_STORAGE). --ttl-hours H (1-999)
sets its TTL (default UBI_TTL_HOURS) and is appended to -n NAME;
a $PREFIX- NAME must carry a -t<hours> TTL
ssh NAME [COMMAND] shell or login-shell command on the VM (user ubi, passwordless sudo)
sync NAME [SRC] [DEST] stream a checkout (tracked + untracked-unignored + .git)
pack [SRC] write that checkout tarball to stdout (slim .git: HEAD + origin/master)
unpack NAME DEST extract a tarball from stdin into DEST on the VM
pull NAME REMOTE_GLOB LOCAL_DIR
copy matching remote entries into LOCAL_DIR
down NAME [-l LOC] destroy the VM; returns once it is confirmed gone or never existed
list [--mine] list all VMs in the project, or this owner's and this machine's
usage VMs and vCPUs per owner across the project
owner print this caller's owner tag ($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 this owner's VMs whose -t<hours> TTL has ended and its
TTL-less ubirun-* VMs older than UBI_LEGACY_HOURS (never other owners')
cli ARGS... raw Ubicloud CLI passthrough (e.g. cli vm list)
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 (default 0 in gbrain; 1/true/yes/on: up reaps first),
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 (${DOWN_TIMEOUT}s), UBI_REAP_DOWN_TIMEOUT (${REAP_DOWN_TIMEOUT}s per VM in reap), UBI_API_TIMEOUT (${API_TIMEOUT}s), UBI_VM_RECORD (scratch VM-id file),
UBI_ALLOWED_STORAGE (the -S sizes Ubicloud accepts; default "320 640")
EOF
}
cmd=${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 "$@" ;;
up) trap 'rc=$?; trap "" INT TERM HUP QUIT; [ -z "$UP_READY" ] || UP_NAME=""; finish "$rc" "$UP_NAME"' EXIT
trap 'exit 130' INT TERM HUP QUIT
cmd_up "$@" ;;
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) check_seconds DOWN_TIMEOUT; 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