OS updates host fast lane + true tunnel status + fast leg: wrapper host layer (R12 appliance proof from the root-owned install record, R14 kernel/boot/firmware refused), select pending-fast, one call per layer, host-side version checks, restart scan only after an install, reboot-needed for PID 1/lxc-start; the leg runs the host step after a healthy guest step; GuestTunnelProber reads the cloudflared container + its readiness check (R-841)
gates / gates (push) Successful in 19s

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
This commit is contained in:
2026-10-04 12:54:02 +02:00
parent a55eedcf2c
commit c3d08b4821
15 changed files with 929 additions and 403 deletions
+72 -12
View File
@@ -785,7 +785,7 @@ func runDaemon(cfg config.Config, logger *slog.Logger, logRing *applog.Ring) int
pbsStore := pbs.NewSnapshotStore()
pbsTargets := pbsTargetsFromPVE(cfg, px, logger)
pbsReporter := pbs.NewLiveSnapshotReporter(pbsTargets, pbsStore, pbs.DefaultLiveSnapshotTimeout, logger)
collector := hub.NewCollector(px, hub.SystemctlProber{}, observer, backupStore, backupStore, pbsReporter, cfg.Hub.HostID, version, logger)
collector := hub.NewCollector(px, newTunnelProber(cfg, px), observer, backupStore, backupStore, pbsReporter, cfg.Hub.HostID, version, logger)
collector.SetBackupTargetResolver(primaryBackupTargetOf(cfg)) // R-109: the recipe names the live target
// Privileged-capability self-check (v0.44.0): probe the sudoers grants the non-root agent
// depends on. The probe runs `sudo -n -l` LITERALLY (a policy LIST, never executing the
@@ -844,7 +844,7 @@ func runDaemon(cfg config.Config, logger *slog.Logger, logRing *applog.Ring) int
desiredSyncer := desired.NewSyncer(client, desiredProvider, logger)
// OS updates, guest fast lane (agent v0.140.0, `11-os-updates.md` §8 step 2): the leg consumes the hub's
// os_update block and runs after each successful primary whole-guest backup (wired on the local API below).
osLeg := newOSLeg(cfg, client, logger)
osLeg := newOSLeg(cfg, client, px, logger)
desiredSyncer.AddConsumer(osLeg)
// S5: consume a host_loss restore_directive into an inspectable restore PLAN (derive + surface,
// execute nothing). The recipe is fetched on-demand (rare directive) via a fresh Collect.
@@ -1127,7 +1127,7 @@ func runDaemon(cfg config.Config, logger *slog.Logger, logRing *applog.Ring) int
return
case <-time.After(90 * time.Second):
}
osLeg.Run(ctx, vmid, "night")
_, _ = osLeg.Run(ctx, vmid, "night")
})
}
if localTokens != nil {
@@ -2026,7 +2026,7 @@ func runSelftestHub(ctx context.Context, cfg config.Config, logger *slog.Logger)
// pbs coord. The live reporter lists snapshots directly (fresh store, last-known-good fallback) so
// the selftest reflects exactly what a freshly-restarted daemon's first collect emits.
pbsReporter := pbs.NewLiveSnapshotReporter(pbsTargetsFromPVE(cfg, px, logger), pbs.NewSnapshotStore(), pbs.DefaultLiveSnapshotTimeout, logger)
collector := hub.NewCollector(px, hub.SystemctlProber{}, observer, nil, nil, pbsReporter, cfg.Hub.HostID, version, logger)
collector := hub.NewCollector(px, newTunnelProber(cfg, px), observer, nil, nil, pbsReporter, cfg.Hub.HostID, version, logger)
// R-109: wire the backup-target resolver here TOO. Without it selftest=hub would print a recipe whose
// backup_target reads unknown/agent_backup_config_unavailable while the daemon's is resolved — and
// this one-shot exists precisely so "the report it would send" can be trusted to match.
@@ -3508,7 +3508,7 @@ func (f *selftestFlag) Set(v string) error {
// newOSLeg builds the OS-update leg (agent v0.140.0). The wrapper runs through sudo (FELHOM_OSAPPLY); the plan and
// the once-per-night marker live in the agent's own os/ dir.
func newOSLeg(cfg config.Config, client *hub.Client, logger *slog.Logger) *osupdate.Leg {
func newOSLeg(cfg config.Config, client *hub.Client, px *proxmox.Client, logger *slog.Logger) *osupdate.Leg {
mode := proxmox.RunnerMode(cfg.Privileged.Mode)
if mode == "" {
mode = proxmox.RunnerSudo
@@ -3518,6 +3518,9 @@ func newOSLeg(cfg config.Config, client *hub.Client, logger *slog.Logger) *osupd
Logger: logger,
PlanDir: osupdate.DefaultPlanDir,
StatePath: filepath.Join(osupdate.DefaultPlanDir, "last-night-run"),
// The host step (agent v0.141.0) runs only on an appliance install; the wrapper re-checks the ROOT-owned record.
Appliance: cfg.IsAppliance(),
Tunnel: newTunnelProber(cfg, px),
}
if client != nil {
l.Hub = client
@@ -3539,7 +3542,12 @@ func runSelftestOSUpdate(ctx context.Context, cfg config.Config, logger *slog.Lo
fmt.Fprintln(os.Stderr, "selftest=os-update: hub client:", err)
return 1
}
leg := newOSLeg(cfg, client, logger)
px, perr := newProxmoxClient(cfg)
if perr != nil {
fmt.Fprintln(os.Stderr, "selftest=os-update: proxmox client:", perr)
return 1
}
leg := newOSLeg(cfg, client, px, logger)
resp, err := client.FetchDesiredState(ctx)
if err != nil {
fmt.Fprintln(os.Stderr, "selftest=os-update: desired state:", err)
@@ -3547,15 +3555,67 @@ func runSelftestOSUpdate(ctx context.Context, cfg config.Config, logger *slog.Lo
}
leg.SetBlock(resp.DesiredState.OSUpdate)
b := leg.Block()
fmt.Printf("=== felhom-agent %s selftest=os-update vmid=%d ring=%d enabled=%v release=%v ===\n", version, vmid, b.Ring, b.Enabled, b.Release != nil)
rep := leg.Run(ctx, vmid, "debug")
printJSON("os-update report", map[string]any{"run_id": rep.RunID, "ring": rep.Ring, "release_id": rep.ReleaseID,
"mode": rep.Mode, "outcome": rep.Outcome, "healthy": rep.Healthy, "health_reason": rep.HealthReason,
"upgraded": rep.Upgraded, "pending": len(rep.Pending), "not_covered": rep.NotCovered,
"restart_needed": rep.RestartNeeded, "docker_restart_needed": rep.DockerRestartNeeded, "refused": rep.Refused})
fmt.Printf("=== felhom-agent %s selftest=os-update vmid=%d ring=%d enabled=%v guest-release=%v host-release=%v appliance=%v ===\n",
version, vmid, b.Ring, b.Enabled, b.Release != nil, b.HostRelease != nil, leg.Appliance)
start := time.Now()
g, h := leg.Run(ctx, vmid, "debug")
for _, rep := range []osupdate.Report{g, h} {
if rep.Layer == "" {
fmt.Println(" host step: skipped (see the log line above)")
continue
}
printJSON("os-update report ("+rep.Layer+")", map[string]any{"run_id": rep.RunID, "ring": rep.Ring, "release_id": rep.ReleaseID,
"mode": rep.Mode, "outcome": rep.Outcome, "healthy": rep.Healthy, "health_reason": rep.HealthReason,
"upgraded": rep.Upgraded, "pending": len(rep.Pending), "not_covered": rep.NotCovered,
"restart_needed": rep.RestartNeeded, "reboot_needed": rep.RebootNeeded, "wrapper_seconds": rep.PassSeconds, "refused": rep.Refused})
}
fmt.Printf(" pass took %s\n", time.Since(start).Round(100*time.Millisecond))
rep := g
if h.Layer != "" && !(h.Outcome == "applied" || h.Outcome == "nothing" || h.Outcome == "inventory") {
rep = h
}
switch rep.Outcome {
case "applied", "nothing", "inventory", "skipped":
return 0
}
return 1
}
// newTunnelProber reads the box's REAL tunnel (R-841, agent v0.141.0): the cloudflared container in each running
// customer guest — a guest that binds /mnt/felhom-drives, the same rule the OS wrapper's R10 uses — through the
// existing `pct exec [0-9]* -- docker inspect -f *` sudoers line.
func newTunnelProber(cfg config.Config, px *proxmox.Client) hub.CloudflaredProber {
mode := proxmox.RunnerMode(cfg.Privileged.Mode)
if mode == "" {
mode = proxmox.RunnerSudo
}
return hub.GuestTunnelProber{
Runner: &proxmox.ExecRunner{Mode: mode, SudoPath: cfg.Privileged.SudoPath},
Guests: func(ctx context.Context) ([]int, error) {
if px == nil {
return nil, fmt.Errorf("no proxmox client")
}
gs, err := px.ListLXC(ctx)
if err != nil {
return nil, err
}
var out []int
for _, g := range gs {
if g.Status != "running" {
continue
}
gc, err := px.GuestConfig(ctx, g.VMID)
if err != nil {
continue
}
for _, v := range gc.MountPoints() {
if src, _, _ := strings.Cut(v, ","); src == "/mnt/felhom-drives" {
out = append(out, g.VMID)
break
}
}
}
return out, nil
},
}
}