Files
oikos/internal/remote/remote_test.go
dtoro b8b4aa2aee feat(remote): route LXC/VM checks through the Proxmox host, not direct SSH
The scheduler SSHed each guest directly and assumed a deployed probe script
plus working root SSH at the guest's address — false for headless (nfs-export),
keyless (teddycloud), mesh-only (rclone), and macOS (mac-mini) targets, which
left 49 enabled checks stuck "down" on a healthy fleet.

Extract the MCP run tool's resolveExecTarget into a shared internal/remote
package and make it the single execution path for both the scheduler and MCP.
LXC/VM checks now host-hop via pct exec / qm guest exec through the owning
Proxmox host (no per-guest lan_ip, sshd, or authorized key needed); hosts and
workstations resolve their address and user live, so mac-mini's `user: dtoro`
is honored without a re-seed. Address preference now prefers public_ipv4 over
mesh, so netbird-vps is probeable from the scheduler container.

cpu_check.sh gains a real Darwin branch (it reported cpu_pct 0 before).
checkdefaults.resolveSSHUser reads the top-level `user` attribute too.
A machine-target resolution failure is now logged before falling back to baked
config, so a broken probe-config is distinguishable from a real outage.
2026-07-29 13:37:00 +02:00

173 lines
6.0 KiB
Go

package remote
import (
"context"
"encoding/base64"
"strings"
"testing"
"github.com/dtoro/oikos/internal/db"
"github.com/google/uuid"
)
// guestWrap and IsGuest are pure logic — always tested. The DB-backed
// resolvers are integration tests guarded by OIKOS_TEST_DATABASE_URL, the
// same convention as internal/scheduler/coverage_test.go.
func TestIsGuest(t *testing.T) {
cases := map[string]bool{
"lxc": true, "vm": true,
"proxmox-host": false, "workstation": false,
"service": false, "docker-container": false,
}
for typ, want := range cases {
if got := IsGuest(typ); got != want {
t.Errorf("IsGuest(%q) = %v, want %v", typ, got, want)
}
}
}
func TestGuestWrapLXC(t *testing.T) {
w := guestWrap("lxc", "132")
out := w("/opt/oikos/checks/cpu_check.sh 'svc'")
if !strings.Contains(out, "pct exec 132 -- bash -c ") {
t.Fatalf("lxc wrap must use pct exec: %q", out)
}
if strings.Contains(out, "qm guest exec") {
t.Fatalf("lxc wrap must not use qm: %q", out)
}
// The base64 payload must round-trip to the original command.
i := strings.Index(out, "echo ")
j := strings.LastIndex(out, " | base64 -d | bash")
if i < 0 || j < 0 || j <= i {
t.Fatalf("cannot locate base64 payload in %q", out)
}
dec, err := base64.StdEncoding.DecodeString(out[i+len("echo ") : j])
if err != nil {
t.Fatalf("decode payload: %v", err)
}
if string(dec) != "/opt/oikos/checks/cpu_check.sh 'svc'" {
t.Fatalf("round-trip mismatch: %q", string(dec))
}
}
func TestGuestWrapVM(t *testing.T) {
w := guestWrap("vm", "108")
out := w("uname -a")
if !strings.Contains(out, "qm guest exec 108") {
t.Fatalf("vm wrap must use qm guest exec: %q", out)
}
}
func TestResolveExecTargetUnsupported(t *testing.T) {
// No DB needed: an unsupported slug prefix errors before any query.
if _, err := ResolveExecTarget(context.Background(), nil, "service:gitea", DefaultUser); err == nil {
t.Fatal("expected error for unsupported target prefix")
}
}
// --- integration tests (require a real Postgres) ---
func newRemotePool(t *testing.T) *db.Pool {
t.Helper()
base := testDatabaseURL(t)
return createTestDB(t, base)
}
func testDatabaseURL(t *testing.T) string {
t.Helper()
u := getenvOrDefault("OIKOS_TEST_DATABASE_URL", "")
if u == "" {
t.Skip("OIKOS_TEST_DATABASE_URL not set — skipping integration test")
}
return u
}
func TestResolveHostPrefersLAN(t *testing.T) {
pool := newRemotePool(t)
ctx := context.Background()
mustExec(t, pool, ctx, `INSERT INTO entities (id, slug, type, name, state, attributes, version, created_at, updated_at)
VALUES ($1,'host:x','proxmox-host','x','active','{"lan_ip":"10.0.0.1","public_ipv4":"1.2.3.4","mesh":{"netbird":{"ip":"100.64.0.1"}}}'::jsonb,1,now(),now())`,
uuid.New())
addr, user, err := ResolveHost(ctx, pool, "host:x", DefaultUser)
if err != nil {
t.Fatalf("ResolveHost: %v", err)
}
if addr != "10.0.0.1" {
t.Errorf("addr = %q, want lan_ip 10.0.0.1", addr)
}
if user != "root" {
t.Errorf("user = %q, want root", user)
}
}
func TestResolveHostFallsBackToPublicIPv4(t *testing.T) {
// netbird-vps: no lan_ip, has public_ipv4 + mesh ip. Must prefer
// public_ipv4 — the scheduler container has no mesh interface.
pool := newRemotePool(t)
ctx := context.Background()
mustExec(t, pool, ctx, `INSERT INTO entities (id, slug, type, name, state, attributes, version, created_at, updated_at)
VALUES ($1,'host:vps','standalone-server','vps','active','{"public_ipv4":"82.165.190.79","mesh":{"netbird":{"ip":"100.122.165.149"}}}'::jsonb,1,now(),now())`,
uuid.New())
addr, _, err := ResolveHost(ctx, pool, "host:vps", DefaultUser)
if err != nil {
t.Fatalf("ResolveHost: %v", err)
}
if addr != "82.165.190.79" {
t.Errorf("addr = %q, want public_ipv4 (mesh unreachable from container)", addr)
}
}
func TestResolveExecTargetForCheckLXCRoutesViaHost(t *testing.T) {
// An LXC guest with a `hosts` edge to a proxmox host must resolve to the
// HOST's address (the host-hop target), wrapped as `pct exec`.
pool := newRemotePool(t)
ctx := context.Background()
hostID := uuid.New()
guestID := uuid.New()
mustExec(t, pool, ctx, `INSERT INTO entities (id, slug, type, name, state, attributes, version, created_at, updated_at)
VALUES ($1,'host:hubris','proxmox-host','hubris','active','{"lan_ip":"192.168.8.77"}'::jsonb,1,now(),now())`, hostID)
mustExec(t, pool, ctx, `INSERT INTO entities (id, slug, type, name, state, attributes, version, created_at, updated_at)
VALUES ($1,'lxc:rclone','lxc','rclone','active','{"pve_id":"132"}'::jsonb,1,now(),now())`, guestID)
mustExec(t, pool, ctx, `INSERT INTO relationships (source_id, target_id, type, valid_from, created_at)
VALUES ($1,$2,'hosts',now(),now())`, hostID, guestID)
et, err := ResolveExecTargetForCheck(ctx, pool, guestID, "lxc", DefaultUser)
if err != nil {
t.Fatalf("ResolveExecTargetForCheck: %v", err)
}
if et.Host != "192.168.8.77" {
t.Errorf("Host = %q, want proxmox host lan_ip 192.168.8.77 (host-hop)", et.Host)
}
out := et.Wrap("/opt/oikos/checks/cpu_check.sh")
if !strings.Contains(out, "pct exec 132") {
t.Errorf("guest wrap must use pct exec 132, got %q", out)
}
}
func TestResolveExecTargetForCheckHostIsDirect(t *testing.T) {
// A host-like target resolves to its own address with identity wrap.
pool := newRemotePool(t)
ctx := context.Background()
hid := uuid.New()
mustExec(t, pool, ctx, `INSERT INTO entities (id, slug, type, name, state, attributes, version, created_at, updated_at)
VALUES ($1,'ws:mini','workstation','mini','active','{"lan_ip":"192.168.178.182","user":"dtoro"}'::jsonb,1,now(),now())`, hid)
et, err := ResolveExecTargetForCheck(ctx, pool, hid, "workstation", DefaultUser)
if err != nil {
t.Fatalf("ResolveExecTargetForCheck: %v", err)
}
if et.Host != "192.168.178.182" {
t.Errorf("Host = %q, want 192.168.178.182", et.Host)
}
// Workstation's top-level `user` must be honored (the mac-mini fix).
if et.User != "dtoro" {
t.Errorf("User = %q, want dtoro (top-level user attr)", et.User)
}
if cmd := et.Wrap("uptime"); cmd != "uptime" {
t.Errorf("host wrap must be identity, got %q", cmd)
}
}