feat: choose an available agent Web port from 3080 to 3100

This commit is contained in:
OpenAI Coding Assistant
2026-09-06 13:59:32 -05:00
parent 14285a5ee5
commit a58dd24efe
9 changed files with 213 additions and 31 deletions
+30 -9
View File
@@ -4,6 +4,7 @@ if [[ ${1:-} == --help ]]; then
echo 'Usage: nix run .#agent -- [run | ssh [command ...] | url | stop]'
echo 'Workspace = cwd. RW config/credentials/skills = DSH_HOME (default ~/.dsh)'
echo 'Also shares DSH_AGENTS_HOME/skills (default ~/.agents/skills). RAM/CPU/network: flake.'
echo "Web UI tries $AGENT_WEB_PORT-$AGENT_WEB_PORT_END in order; url prints the selected port."
exit 0
fi
[[ $EUID != 0 ]] || { echo 'Run as your normal host user, not sudo/root.' >&2; exit 1; }
@@ -26,13 +27,18 @@ ssh_cmd=(ssh -F /dev/null -i "$state/client-key" -p "$AGENT_SSH_PORT"
-o StrictHostKeyChecking=yes -o HostKeyAlias=agent-vm -o ConnectTimeout=3
-o "UserKnownHostsFile=$state/known_hosts" -o GlobalKnownHostsFile=/dev/null)
remote="root@$AGENT_SSH_HOST"
# Relative ControlPath avoids Unix-socket path limits with long state directories.
web_control() { (cd "$state" && "${ssh_cmd[@]}" -S web.sock "$@" "$remote"); }
url() {
local found address=$AGENT_WEB_BIND
local found port address=$AGENT_WEB_BIND
[[ -f $state/web-port ]] && read -r port < "$state/web-port" || return 1
[[ $port =~ ^[1-9][0-9]{0,4}$ ]] && (( port <= 65535 )) || return 1
web_control -O check >/dev/null 2>&1 || return 1
[[ $address != 0.0.0.0 ]] || address=127.0.0.1
found=$("${ssh_cmd[@]}" "$remote" 'journalctl -u agent -b -o cat --no-pager' |
grep -oE 'http://127\.0\.0\.1:3080/\?token=[a-zA-Z0-9_%.-]+' | tail -1) || return 1
[[ -n $found ]] || return 1
printf '%s\n' "${found/http:\/\/127.0.0.1:3080/http:\/\/$address:$AGENT_WEB_PORT}"
printf '%s\n' "${found/http:\/\/127.0.0.1:3080/http:\/\/$address:$port}"
}
# Expand cwd inside the guest, not on the host.
# shellcheck disable=SC2016
@@ -52,6 +58,9 @@ for dir in "$state" "$dsh"; do
done
exec 9>"$state/run.lock"
flock -n 9 || { echo 'This project VM is already running.' >&2; exit 1; }
# Clean up only this project's stale forwarding state, after acquiring its lock.
web_control -O exit >/dev/null 2>&1 || true
rm -f "$state/web.sock" "$state/web-port"
for key in client-key ssh-host-key; do
[[ -f $state/$key ]] || ssh-keygen -q -t ed25519 -N '' -C agent-vm -f "$state/$key"
done
@@ -63,15 +72,15 @@ if [[ $AGENT_WEB_BIND != 127.0.0.1 ]]; then
echo 'WARNING: off-host Web access is plaintext HTTP. Use a VPN/TLS; never expose directly to the Internet.' >&2
fi
vm_pid=''
tunnel_pid=''
cleanup() {
trap - EXIT INT TERM
web_control -O exit >/dev/null 2>&1 || true
rm -f "$state/web-port" "$state/web.sock"
if [[ -n $vm_pid ]] && kill -0 "$vm_pid" 2>/dev/null; then
(cd "$state"; timeout 30 "$AGENT_RUNNER/microvm-shutdown") >/dev/null 2>&1 || true
kill "$vm_pid" 2>/dev/null || true
wait "$vm_pid" 2>/dev/null || true
fi
if [[ -n $tunnel_pid ]]; then kill "$tunnel_pid" 2>/dev/null || true; wait "$tunnel_pid" 2>/dev/null || true; fi
}
trap cleanup EXIT
trap 'exit 130' INT
@@ -99,16 +108,28 @@ done
$ready || { echo "SSH boot timeout; see $state/console.log" >&2; exit 1; }
# DSH deliberately refuses --host 0.0.0.0. Keep its own authenticated browser
# endpoint on guest loopback and publish an SSH forward on the chosen host IP.
"${ssh_cmd[@]}" -N -g -o ExitOnForwardFailure=yes -o ServerAliveInterval=10 \
-o ServerAliveCountMax=3 -L "$AGENT_WEB_BIND:$AGENT_WEB_PORT:127.0.0.1:3080" \
"$remote" >>"$state/console.log" 2>&1 &
tunnel_pid=$!
web_control -M -fN -g -o ExitOnForwardFailure=yes -o ServerAliveInterval=10 \
-o ServerAliveCountMax=3 >>"$state/console.log" 2>&1 || {
echo "Cannot start Web SSH tunnel; see $state/console.log" >&2; exit 1;
}
# Ask SSH to actually bind each port: no probe-then-bind race or extra port helper.
for ((port=AGENT_WEB_PORT; port<=AGENT_WEB_PORT_END; port++)); do
if web_control -O forward -L "$AGENT_WEB_BIND:$port:127.0.0.1:3080" >>"$state/console.log" 2>&1; then
printf '%s\n' "$port" > "$state/web-port"
break
fi
done
[[ -f $state/web-port ]] || {
echo "No available Web UI port on $AGENT_WEB_BIND in $AGENT_WEB_PORT-$AGENT_WEB_PORT_END; see $state/console.log" >&2
exit 1
}
echo "Web UI selected host port $port."
echo "Booted. DSH resolves npm @latest on startup; first launch may take a few minutes."
echo 'Use another terminal: nix run .#agent -- url (or: ssh / stop)'
printed=false
while kill -0 "$vm_pid" 2>/dev/null; do
# Normal guest poweroff can close SSH slightly before QEMU exits.
if ! kill -0 "$tunnel_pid" 2>/dev/null; then
if ! web_control -O check >/dev/null 2>&1; then
timeout 30 tail --pid="$vm_pid" -f /dev/null || true
if kill -0 "$vm_pid" 2>/dev/null; then echo "Web tunnel exited; see $state/console.log" >&2; exit 1; fi
break