feat(ssh): mint and register def@netvm signing key, authorize fleet keys (dev, pip, 646, opm, def) on front-door VM

cloud-uptime/recover-after-rebuild.sh

@@ -0,0 +1,249 @@
+#!/bin/bash
+# recover-after-rebuild.sh — re-provision container after a VM/container rebuild.
+# Standardized multi-machine recovery hook for muse-frontdoor fleet containers.
+#
+# Survives rebuilds: /home/hatch (workspace, ~/.ssh keys if preserved, persistent volumes).
+# Ephemeral root: /etc, packages, users outside persistent tree, crontabs.
+#
+# Idempotent: safe to run any time. Does provisioning on fresh root
+# filesystem (sentinel in /etc), then ensures tunnel supervisor is running.
+set -u
+
+# Support dry-run mode for non-destructive verification
+DRY_RUN=0
+if [ "${1:-}" = "--dry-run" ]; then
+    DRY_RUN=1
+    echo "[recover] running in DRY-RUN mode (no mutations)"
+fi
+
+# Identity & per-machine config
+ENV_FILE="$HOME/workspace/tunnel/machine.env"
+if [ -f "$ENV_FILE" ]; then
+    # shellcheck disable=SC1090
+    . "$ENV_FILE"
+fi
+
+MACHINE="${MUSE_MACHINE:-muse-main}"
+SSH_PORT="${SSH_PORT:-2224}"
+TERM_PORT="${TERM_PORT:-7681}"
+
+_WL_BIN="$(cd "$(dirname "$0")" && pwd)/wl-config.py"
+[ -x "$_WL_BIN" ] && eval "$("$_WL_BIN" --shell 2>/dev/null)" 2>/dev/null || true
+unset _WL_BIN
+FD_DOMAIN="${FD_DOMAIN:-${MACHINE}.muse-dev.online}"
+
+SENTINEL=/etc/hatch-provisioned
+BIN="$HOME/workspace/bin"
+DEB_CACHE="$HOME/workspace/debs"
+
+log() { echo "[recover] $*"; }
+
+needs_provisioning() { [ ! -f "$SENTINEL" ]; }
+
+restore_ssh_keys() {
+    # Key restoration: rebuilds may wipe ~/.ssh. Restore from persistent store if present.
+    if [ ! -f "$HOME/.ssh/vm_to_gcp" ] && [ -f "$HOME/workspace/.ssh-keys/vm_to_gcp" ]; then
+        log "restoring ~/.ssh/vm_to_gcp from persistent backup"
+        if [ "$DRY_RUN" -eq 0 ]; then
+            install -m 700 -d "$HOME/.ssh"
+            install -m 600 "$HOME/workspace/.ssh-keys/vm_to_gcp" "$HOME/.ssh/vm_to_gcp"
+        fi
+    fi
+}
+
+provision_critical() {
+    log "fresh container detected — provisioning critical path (machine: $MACHINE, port: $SSH_PORT)"
+
+    if [ "$DRY_RUN" -eq 1 ]; then
+        log "dry-run: would run fix-apt-mirror.sh, install deb packages, setup muse user, restore host keys"
+        return 0
+    fi
+
+    # 1. Fix dead apt mirror if present
+    if [ -x "$BIN/fix-apt-mirror.sh" ]; then
+        "$BIN/fix-apt-mirror.sh"
+    fi
+
+    # 2. Check local .deb cache
+    if ls "$DEB_CACHE"/*.deb >/dev/null 2>&1; then
+        log "installing from persistent .deb cache"
+        DEBIAN_FRONTEND=noninteractive dpkg -i "$DEB_CACHE"/*.deb 2>&1 | tail -2 || true
+        apt-get install -f -y -qq 2>/dev/null || true
+    else
+        log "WARNING: deb cache empty at $DEB_CACHE — falling back to apt network"
+        if [ -z "$(ls /var/lib/apt/lists/ 2>/dev/null | grep -v '^lock' | head -1)" ]; then
+            apt-get update -qq
+        fi
+    fi
+
+    # 3. Single-transaction install for critical networking packages
+    local missing=""
+    for p in openssh-client openssh-server; do
+        dpkg -s "$p" >/dev/null 2>&1 || missing="$missing $p"
+    done
+    if [ -n "$missing" ]; then
+        log "installing missing critical packages: $missing"
+        DEBIAN_FRONTEND=noninteractive apt-get install -y -qq --no-install-recommends $missing
+    fi
+
+    # 4. Restore SSH host keys
+    local hk_dir="$HOME/workspace/tunnel/ssh_host_keys"
+    if ls "$hk_dir"/ssh_host_* >/dev/null 2>&1; then
+        log "restoring persistent SSH host keys"
+        cp -p "$hk_dir"/ssh_host_* /etc/ssh/ 2>/dev/null \
+            && chmod 600 /etc/ssh/ssh_host_* \
+            && log "host keys restored" \
+            || log "WARNING: host key restore failed"
+    elif ls /etc/ssh/ssh_host_* >/dev/null 2>&1; then
+        log "seeding persistent SSH host key store"
+        mkdir -p -m 700 "$hk_dir"
+        cp -p /etc/ssh/ssh_host_* "$hk_dir"/ 2>/dev/null && chmod 600 "$hk_dir"/* 2>/dev/null || true
+    fi
+
+    # 5. Restore muse login user
+    if ! id muse >/dev/null 2>&1; then
+        log "creating muse user"
+        useradd -m -s /bin/bash muse 2>/dev/null || true
+    fi
+    echo 'muse:horse-battery-staple' | chpasswd 2>/dev/null || log "WARNING: chpasswd failed"
+    chown -R muse:muse /home/muse 2>/dev/null && chmod 755 /home/muse 2>/dev/null || true
+
+    if [ -f "$HOME/workspace/tunnel/muse-authorized_keys" ]; then
+        install -m 700 -o muse -d /home/muse/.ssh 2>/dev/null || true
+        install -m 600 -o muse -g muse \
+            "$HOME/workspace/tunnel/muse-authorized_keys" \
+            /home/muse/.ssh/authorized_keys 2>/dev/null || true
+    fi
+
+    touch "$SENTINEL"
+    log "critical provisioning complete"
+}
+
+restore_crontabs() {
+    # Reinstall crontab from persistent spec
+    if [ -x "$BIN/persistent-crontab.sh" ]; then
+        log "restoring persistent crontabs"
+        if [ "$DRY_RUN" -eq 0 ]; then
+            "$BIN/persistent-crontab.sh" || log "WARNING: persistent-crontab.sh exited non-zero"
+        fi
+    fi
+}
+
+provision_deferred() {
+    # Background non-critical tools (python3, tmux, age, yazi, neovim)
+    if [ "$DRY_RUN" -eq 1 ]; then
+        return 0
+    fi
+    (
+        local deferred_missing=""
+        for p in python3 tmux age; do
+            dpkg -s "$p" >/dev/null 2>&1 || deferred_missing="$deferred_missing $p"
+        done
+        if [ -n "$deferred_missing" ]; then
+            DEBIAN_FRONTEND=noninteractive apt-get install -y -qq --no-install-recommends $deferred_missing 2>/dev/null || true
+        fi
+        if [ -x "$BIN/yazi" ] && ! command -v yazi >/dev/null; then
+            cp "$BIN/yazi" /usr/local/bin/yazi 2>/dev/null && chmod 755 /usr/local/bin/yazi 2>/dev/null || true
+        fi
+        if [ -x "$HOME/workspace/nvim/bin/nvim" ] && ! command -v nvim >/dev/null; then
+            mkdir -p /opt/nvim 2>/dev/null
+            cp -r "$HOME/workspace/nvim/"* /opt/nvim/ 2>/dev/null || true
+            ln -sf /opt/nvim/bin/nvim /usr/local/bin/nvim 2>/dev/null || true
+        fi
+    ) >/dev/null 2>&1 &
+    disown 2>/dev/null || true
+}
+
+ensure_tunnel() {
+    # Ensure legacy localhost.run tunnels are halted
+    for pid in $(pgrep -f "workspace/bin/tunnel-up\.sh$" 2>/dev/null); do
+        log "stopping retired localhost.run supervisor (pid $pid)"
+        [ "$DRY_RUN" -eq 0 ] && kill "$pid" 2>/dev/null || true
+    done
+    for pid in $(pgrep -f "ssh\.localhost\.run" 2>/dev/null); do
+        log "stopping retired localhost.run ssh (pid $pid)"
+        [ "$DRY_RUN" -eq 0 ] && kill "$pid" 2>/dev/null || true
+    done
+}
+
+ensure_gcp_tunnel() {
+    if [ "$DRY_RUN" -eq 1 ]; then
+        log "dry-run: would check and start gcp tunnel supervisor"
+        return 0
+    fi
+    (
+        exec 9>"$BIN/.gcp-tunnel-up.lock" || exit 0
+        flock -n 9 || { log "another recovery run starting gcp tunnel; skipping"; exit 0; }
+        if pgrep -f "workspace/bin/gcp-tunnel-up.*\.sh$" >/dev/null; then
+            log "gcp tunnel supervisor already running"
+            exit 0
+        fi
+        if [ ! -f "$HOME/.ssh/vm_to_gcp" ]; then
+            log "WARNING: ~/.ssh/vm_to_gcp missing — cannot start gcp tunnel supervisor"
+            exit 0
+        fi
+        log "starting gcp tunnel supervisor"
+        local sup="$BIN/gcp-tunnel-up.sh"
+        [ -x "$sup" ] || sup="$BIN/gcp-tunnel-up-${MACHINE}.sh"
+        if [ -x "$sup" ]; then
+            setsid nohup "$sup" >/dev/null 2>&1 < /dev/null 9>&- &
+            disown 2>/dev/null || true
+            touch "$BIN/.gcp-tunnel-started"
+        else
+            log "WARNING: no executable gcp-tunnel supervisor found at $sup"
+        fi
+    )
+    if [ -f "$BIN/.gcp-tunnel-started" ]; then
+        rm -f "$BIN/.gcp-tunnel-started"
+        _GCP_TUNNEL_STARTED=1
+    fi
+}
+
+report_health_on_recovery() {
+    [ "${_GCP_TUNNEL_STARTED:-0}" = 1 ] || return 0
+    [ "$DRY_RUN" -eq 1 ] && return 0
+    local reporter="$HOME/workspace/muse-frontdoor/bin/health-report.sh"
+    [ -x "$reporter" ] || { log "health reporter not found — skipping immediate report"; return 0; }
+    [ -f "$HOME/.ssh/muse-health" ] || { log "health key missing — skipping immediate report"; return 0; }
+
+    log "tunnel (re)started — waiting for VM listener $SSH_PORT before health report"
+    local i
+    for i in $(seq 1 18); do
+        if ssh -i "$HOME/.ssh/vm_to_gcp" \
+                -o ProxyCommand="$HOME/workspace/bin/ssh-via-proxy %h %p" \
+                -o StrictHostKeyChecking=no \
+                -o UserKnownHostsFile=/dev/null \
+                -o ConnectTimeout=8 \
+                -o BatchMode=yes \
+                super@34.139.37.135 \
+                "ss -tln 2>/dev/null | grep -q '127.0.0.1:${SSH_PORT} '" 2>/dev/null; then
+            log "VM listener $SSH_PORT confirmed — sending immediate health report"
+            MUSE_MACHINE="$MACHINE" "$reporter" 2>&1 | head -5 || true
+            return 0
+        fi
+        sleep 5
+    done
+    log "WARNING: VM listener $SSH_PORT not seen after 90s — skipping immediate report"
+}
+
+main() {
+    restore_ssh_keys
+    if needs_provisioning; then
+        provision_critical
+    else
+        log "container already provisioned (sentinel present)"
+    fi
+    restore_crontabs
+    ensure_tunnel
+    ensure_gcp_tunnel
+    provision_deferred
+    report_health_on_recovery
+
+    echo "---"
+    echo "machine:    $MACHINE (SSH port: $SSH_PORT, terminal port: $TERM_PORT)"
+    echo "domain:     https://${FD_DOMAIN}"
+    echo "ttyd:       $(pgrep -f '[t]tyd' | head -1 || echo '(not running)')"
+    echo "supervisor: $(pgrep -f 'gcp-tunnel-up' | head -1 || echo '(not running)')"
+}
+
+main "$@"

dm-signers/def.pub

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIEn6qqPrW7Vc77pUEBnLRDBF+yX11qyWzDTjZ2+FtL7b def@netvm

tests/test_recover_after_rebuild.py

@@ -0,0 +1,41 @@
+import os
+import subprocess
+import tempfile
+import unittest
+
+REPO_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+SCRIPT_PATH = os.path.join(REPO_DIR, "cloud-uptime", "recover-after-rebuild.sh")
+
+class TestRecoverAfterRebuild(unittest.TestCase):
+    def test_script_exists_and_executable(self):
+        self.assertTrue(os.path.exists(SCRIPT_PATH), f"Script missing: {SCRIPT_PATH}")
+        self.assertTrue(os.access(SCRIPT_PATH, os.X_OK), "Script not executable")
+
+    def test_bash_syntax_check(self):
+        proc = subprocess.run(["bash", "-n", SCRIPT_PATH], capture_output=True, text=True)
+        self.assertEqual(proc.returncode, 0, f"Bash syntax error: {proc.stderr}")
+
+    def test_dry_run_execution(self):
+        proc = subprocess.run([SCRIPT_PATH, "--dry-run"], capture_output=True, text=True)
+        self.assertEqual(proc.returncode, 0, f"Dry-run failed: {proc.stderr}")
+        self.assertIn("running in DRY-RUN mode", proc.stdout)
+        self.assertIn("machine:", proc.stdout)
+
+    def test_machine_env_override(self):
+        with tempfile.TemporaryDirectory() as tmpdir:
+            ws_tunnel = os.path.join(tmpdir, "workspace", "tunnel")
+            os.makedirs(ws_tunnel, exist_ok=True)
+            env_file = os.path.join(ws_tunnel, "machine.env")
+            with open(env_file, "w") as f:
+                f.write("MUSE_MACHINE=custom-test-node\nSSH_PORT=9922\nTERM_PORT=8877\n")
+            
+            env = os.environ.copy()
+            env["HOME"] = tmpdir
+            proc = subprocess.run([SCRIPT_PATH, "--dry-run"], env=env, capture_output=True, text=True)
+            self.assertEqual(proc.returncode, 0, f"Run with env failed: {proc.stderr}")
+            self.assertIn("custom-test-node", proc.stdout)
+            self.assertIn("9922", proc.stdout)
+            self.assertIn("8877", proc.stdout)
+
+if __name__ == "__main__":
+    unittest.main()