GodopuandClaude Opus 5.5
1d63e882bc
With MAM_DELEGATION_PY=0 the legacy helper still found the monitor with an unanchored pgrep -f, so a process that only named the monitor path was reported as the restarted monitor and none was started. lib.sh _monitor_pids is the shell twin of daemon.find_running; update.sh and post_update.sh check the PID start_watchdog printed with mam_monitor_started before saying "monitor: restarted". Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
268 lines
10 KiB
Bash
Executable File
268 lines
10 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# update.sh — multi-agent-mux-update (Issue #72): update an installed workspace in place.
|
|
# Usage:
|
|
# bash .agents/skills/multi-agent-mux-update/scripts/update.sh [-y|--yes]
|
|
#
|
|
# Phase 1 (this script, the installed code): publish .mam/update-in-progress
|
|
# under the admission lock (lib.sh mam_update_admit is the other side), refuse
|
|
# while anything live could see the tree change (lib_py/update.py precheck, a
|
|
# live loop marker, a monitor.lock held by a monitor the skills did not start),
|
|
# stop the monitor daemon, back up what the install can change into
|
|
# .mam/update-backup/, then exec a copy of install_phase.sh outside the tree.
|
|
# That copy runs the installer (MAM_INSTALLER_URL) in place, rolls back on
|
|
# failure, and runs phase 2 (post_update.sh of the NEW tree) on success.
|
|
#
|
|
# Exit codes:
|
|
# 0 = updated (registry converted or nothing to convert)
|
|
# 1 = refused or failed; what was changed and restored is printed
|
|
# 2 = invalid args
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
WS="$(cd -P "$SCRIPT_DIR/../../../.." && pwd -P)"
|
|
export WORKSPACE_ROOT="$WS"
|
|
export AGENT_SESSIONS_YAML="$WS/.mam/agent-sessions.yaml"
|
|
# shellcheck disable=SC1091
|
|
source "$WS/.agents/skills/lib.sh"
|
|
# shellcheck disable=SC1091
|
|
source "$SKILL_DIR/multi-agent-mux-loop/scripts/loop_lock.sh"
|
|
|
|
YES=0
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
-y|--yes) YES=1; shift ;;
|
|
-h|--help) sed -n '2,4p' "${BASH_SOURCE[0]}"; exit 0 ;;
|
|
*) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
|
|
esac
|
|
done
|
|
|
|
MAM="$WS/.mam"
|
|
MARKER="$MAM/update-in-progress"
|
|
BK="$MAM/update-backup"
|
|
PY="$(_delegate_py_bin)"
|
|
|
|
if [ ! -f "$WS/.mam_deploy/remove.sh" ] && [ ! -f "$WS/remove.sh" ]; then
|
|
echo "ERROR: $WS is not an installed MAM workspace (no .mam_deploy/remove.sh); a git checkout updates with git pull" >&2
|
|
exit 1
|
|
fi
|
|
|
|
if [ "$YES" != "1" ]; then
|
|
if [ ! -t 0 ]; then
|
|
echo "ERROR: not a terminal; run with -y/--yes" >&2
|
|
exit 1
|
|
fi
|
|
ans=""
|
|
read -r -p "Update MAM in $WS to the latest version? [y/N]: " ans || ans=""
|
|
case "$ans" in
|
|
y|Y|yes|Yes|YES) ;;
|
|
*) echo "Update cancelled."; exit 0 ;;
|
|
esac
|
|
fi
|
|
|
|
# --- the marker, published under the exclusive admission lock (decision 8) ---
|
|
mkdir -p "$MAM"
|
|
exec 7>>"$MAM/update-admission.lock"
|
|
case "$("$PY" -m lib_py.pane_lock acquire --fd 7 --wait-env MAM_UPDATE_ADMISSION_WAIT_S)" in
|
|
locked) ;;
|
|
timeout)
|
|
echo "ERROR: a create, resume, loop, delegate submit, stop or orc-onboard kept the admission lock past MAM_UPDATE_ADMISSION_WAIT_S; nothing was changed, try again" >&2
|
|
exit 1 ;;
|
|
*)
|
|
echo "ERROR: the admission lock $MAM/update-admission.lock could not be decided (lib_py.pane_lock); nothing was changed" >&2
|
|
exit 1 ;;
|
|
esac
|
|
if [ -f "$MARKER" ] && [ "$(_mam_lock_holder_state "$MARKER")" = "stale" ]; then
|
|
echo "NOTE: stale update marker (pid $(_mam_lock_field "$MARKER" pid)) taken over; its update is gone"
|
|
fi
|
|
marker_rc=0
|
|
mam_acquire_loop_lock "$MARKER" || marker_rc=$?
|
|
exec 7>&-
|
|
case "$marker_rc" in
|
|
0) ;;
|
|
3) echo "ERROR: another update is in progress (pid $(_mam_lock_field "$MARKER" pid)); nothing was changed" >&2; exit 1 ;;
|
|
*) echo "ERROR: cannot tell whether another update is in progress (ps unavailable?); nothing was changed" >&2; exit 1 ;;
|
|
esac
|
|
|
|
TMPD=""
|
|
MONITOR_WAS_RUNNING=0
|
|
RESTART_MONITOR=0
|
|
_phase1_exit() {
|
|
local rc=$?
|
|
if [ "$RESTART_MONITOR" = "1" ]; then
|
|
_restart_monitor || true
|
|
fi
|
|
mam_release_loop_lock "$MARKER" || true
|
|
[ -z "$TMPD" ] || rm -rf "$TMPD"
|
|
exit "$rc"
|
|
}
|
|
trap _phase1_exit EXIT
|
|
|
|
_restart_monitor() {
|
|
if [ "${MAM_NO_SUBSCRIBER_DAEMON:-0}" = "1" ]; then
|
|
echo "monitor: not restarted (MAM_NO_SUBSCRIBER_DAEMON=1)"
|
|
return 0
|
|
fi
|
|
local pid
|
|
pid=$(start_watchdog update "$WS") || { echo "ERROR: could not restart the monitor daemon" >&2; return 1; }
|
|
# shellcheck disable=SC2086
|
|
mam_monitor_started "$WS" $pid || { echo "ERROR: could not restart the monitor daemon (PID ${pid:-none} is not its monitor)" >&2; return 1; }
|
|
echo "monitor: restarted (PID $pid)"
|
|
}
|
|
|
|
_monitor_json() {
|
|
"$PY" -m lib_py.update monitor --workspace "$WS"
|
|
}
|
|
_json_field() {
|
|
"$PY" -c 'import json,sys; v=json.load(sys.stdin)[sys.argv[1]]; print(" ".join(v) if isinstance(v, list) else v)' "$1"
|
|
}
|
|
|
|
# --- pre-check: refuse before any change (decisions 1, 7; U3) ---
|
|
BLOCKERS=""
|
|
_block() { BLOCKERS="${BLOCKERS} - $1
|
|
"; }
|
|
|
|
if [ -f "$MAM/loop-guard-active" ]; then
|
|
loop_st="$(_mam_lock_holder_state "$MAM/loop-guard-active")"
|
|
case "$loop_st" in
|
|
stale) echo "NOTE: stale loop marker $MAM/loop-guard-active (its loop is gone); not a reason to refuse" ;;
|
|
*) _block "a review loop is running (pid $(_mam_lock_field "$MAM/loop-guard-active" pid), holder $loop_st); wait for it to end" ;;
|
|
esac
|
|
fi
|
|
|
|
STATE_JSON=""
|
|
if ! STATE_JSON="$(load_state_json strict)"; then
|
|
_block "the registry $AGENT_SESSIONS_YAML cannot be read; fix it first"
|
|
STATE_JSON='{}'
|
|
fi
|
|
REAL_HERDR="$(_resolve_real_herdr_path || true)"
|
|
if [ -z "$REAL_HERDR" ]; then
|
|
_block "no herdr binary found on PATH, so the live agents cannot be listed"
|
|
else
|
|
pre_out=""
|
|
pre_rc=0
|
|
pre_out="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.update precheck --workspace "$WS" --herdr "$REAL_HERDR")" || pre_rc=$?
|
|
if [ "$pre_rc" -ne 0 ]; then
|
|
while IFS= read -r line; do
|
|
[ -n "$line" ] && _block "$line"
|
|
done <<< "${pre_out:-lib_py.update precheck failed (rc $pre_rc)}"
|
|
fi
|
|
fi
|
|
|
|
MON_JSON="$(_monitor_json)" || { _block "cannot inspect the monitor daemon (lib_py.update monitor)"; MON_JSON='{"pids": [], "lock": "free"}'; }
|
|
MON_PIDS="$(printf '%s' "$MON_JSON" | _json_field pids)"
|
|
MON_LOCK="$(printf '%s' "$MON_JSON" | _json_field lock)"
|
|
if [ -z "$MON_PIDS" ] && [ "$MON_LOCK" = "held" ]; then
|
|
_block "$MAM/monitor.lock is held by a monitor the skills did not start (not 'bash $WS/.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --subscribe'); stop it (find it with: pgrep -af reconcile.sh) and try again"
|
|
fi
|
|
|
|
if [ -n "$BLOCKERS" ]; then
|
|
echo "ERROR: update refused; nothing was changed:" >&2
|
|
printf '%s' "$BLOCKERS" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# --- stop the monitor daemon (decision 2) ---
|
|
_monitor_gone() {
|
|
local p
|
|
for p in "$@"; do
|
|
kill -0 "$p" 2>/dev/null && return 1
|
|
done
|
|
[ "$(_monitor_json | _json_field lock)" = "free" ]
|
|
}
|
|
_wait_monitor_gone() {
|
|
local deadline=$(( $(date +%s) + $1 ))
|
|
shift
|
|
while :; do
|
|
_monitor_gone "$@" && return 0
|
|
[ "$(date +%s)" -lt "$deadline" ] || return 1
|
|
sleep 0.5
|
|
done
|
|
}
|
|
if [ -n "$MON_PIDS" ]; then
|
|
MONITOR_WAS_RUNNING=1
|
|
# shellcheck disable=SC2086
|
|
set -- $MON_PIDS
|
|
kids=""
|
|
for p in "$@"; do kids="$kids $(pgrep -P "$p" 2>/dev/null | tr '\n' ' ' || true)"; done
|
|
echo "monitor: stopping the daemon (PID $MON_PIDS)"
|
|
kill -TERM "$@" 2>/dev/null || true
|
|
if ! _wait_monitor_gone "$(mam_int_knob MAM_UPDATE_MONITOR_STOP_S 30 1)" "$@"; then
|
|
# SIGKILL only what is still this workspace's monitor: a PID that ended
|
|
# during the wait may already be another process's.
|
|
still=""
|
|
for p in $(_monitor_json | _json_field pids); do
|
|
case " $* " in *" $p "*) still="$still $p" ;; esac
|
|
done
|
|
# shellcheck disable=SC2086
|
|
set -- $still
|
|
for p in "$@"; do kids="$kids $(pgrep -P "$p" 2>/dev/null | tr '\n' ' ' || true)"; done
|
|
echo "WARNING: the monitor did not stop within MAM_UPDATE_MONITOR_STOP_S; sending SIGKILL to $* $kids" >&2
|
|
# shellcheck disable=SC2086
|
|
kill -KILL "$@" $kids 2>/dev/null || true
|
|
# shellcheck disable=SC2086
|
|
if _wait_monitor_gone 5 "$@" $kids; then
|
|
echo "ERROR: the monitor did not stop in time; it was killed and is started again. Nothing else was changed." >&2
|
|
_restart_monitor || true
|
|
exit 1
|
|
fi
|
|
echo "ERROR: could not restore the monitor state: PIDs still alive or monitor.lock still held ($*$kids; lock $(_monitor_json | _json_field lock)). Nothing else was changed." >&2
|
|
exit 1
|
|
fi
|
|
RESTART_MONITOR=1
|
|
fi
|
|
|
|
TMPD="$(mktemp -d "${TMPDIR:-/tmp}/mam-update.XXXXXX")"
|
|
cp "$SCRIPT_DIR/install_phase.sh" "$TMPD/install_phase.sh"
|
|
|
|
# --- a leftover backup of an update that died (U4) ---
|
|
if [ -e "$BK" ]; then
|
|
left_st="$(cat "$BK/state" 2>/dev/null || true)"
|
|
case "$left_st" in
|
|
""|backing-up|installed)
|
|
echo "NOTE: removing the backup a previous update left (state ${left_st:-none}); nothing to restore"
|
|
rm -rf "$BK" ;;
|
|
installing)
|
|
echo "NOTE: a previous update died during its install; restoring its backup (the registry is left as it is)"
|
|
if ! bash "$TMPD/install_phase.sh" restore "$WS" --skip-registry; then
|
|
RESTART_MONITOR=0
|
|
echo "ERROR: restoring the previous update's backup failed; it is kept at $BK. Nothing more was changed; the monitor stays stopped." >&2
|
|
exit 1
|
|
fi
|
|
rm -rf "$BK"
|
|
echo "the previous update was rolled back" ;;
|
|
*)
|
|
echo "ERROR: $BK has an unknown state '$left_st'; it is kept and nothing was changed. Check it and remove it by hand." >&2
|
|
exit 1 ;;
|
|
esac
|
|
fi
|
|
|
|
# --- the rollback backup (decisions 3, 10; U4) ---
|
|
_set_state() { printf '%s\n' "$1" > "$BK/state.tmp" && mv -f "$BK/state.tmp" "$BK/state"; }
|
|
ITEMS=".agents .mam_deploy AGENTS.md MESSAGING.md BOOTSTRAP.md BOOTSTRAP.ko.md .mam.env.example .mam.env .gitignore remove.sh update.sh .venv .mam/install_manifest.txt .mam/install_state .mam/asset_hashes.txt .mam/version.txt .mam/base .mam/skill-backups"
|
|
_backup() {
|
|
mkdir -p "$BK/files" || return 1
|
|
_set_state backing-up || return 1
|
|
: > "$BK/items" && : > "$BK/absent" || return 1
|
|
local rel
|
|
for rel in $ITEMS; do
|
|
printf '%s\n' "$rel" >> "$BK/items" || return 1
|
|
if [ -e "$WS/$rel" ] || [ -L "$WS/$rel" ]; then
|
|
mkdir -p "$BK/files/$(dirname "$rel")" && cp -pPR "$WS/$rel" "$BK/files/$rel" || return 1
|
|
else
|
|
printf '%s\n' "$rel" >> "$BK/absent" || return 1
|
|
fi
|
|
done
|
|
"$PY" -m lib_py.update backup-registry --workspace "$WS" --dest "$BK/registry" >/dev/null
|
|
}
|
|
echo "backup: $BK"
|
|
if ! _backup; then
|
|
rm -rf "$BK"
|
|
echo "ERROR: the backup could not be made; nothing was changed" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# --- hand over to the copy (decision 5): same pid, so the marker stays live ---
|
|
RESTART_MONITOR=0
|
|
trap - EXIT
|
|
exec bash "$TMPD/install_phase.sh" run "$WS" "$MONITOR_WAS_RUNNING" "$TMPD"
|