felhom-agent/internal/osupdate/unsent.go

package osupdate

import (
	"context"
	"encoding/json"
	"os"
	"path/filepath"
	"strings"
	"syscall"
	"time"

	"gitea.dooplex.hu/admin/felhom-agent/internal/hub"
)

// ── R-868 (v0.144.0): a pass whose agent was killed still reports ─────────────────────────────────────
//
// MEASURED 2026-10-05 02:57 UTC on demo-hp (night drill A5): the debug pass and the agent daemon were kill -9-ed while
// apt-get ran. The root wrapper (its own process under sudo) finished all six packages, but the agent that would have
// read its stdout and posted the report was gone; the hub never learned what the pass installed.
//
// THE MECHANISM: the wrapper writes its apply report to <plan dir>/report-<run>-<layer>-apply.json BEFORE printing
// it (configs/felhom-os-apply save_report). The agent deletes that copy once the hub has the report (finish). A copy
// still on disk is a report nobody sent: SendUnsent posts it — at the agent's start, and before every pass — and then
// deletes it. A pass lock (flock on <plan dir>/pass.lock, released by the kernel when a process dies) keeps the
// sender from picking up the copy of a pass that is still running, also across the daemon and a selftest process.
// Pinned by TestR868_* (unsent_test.go).

// lockPass takes the pass lock. block=false returns ok=false at once when another pass holds it. A lock that cannot
// be opened at all (no plan dir yet) does not stop a pass: the unlock is then a no-op.
func (l *Leg) lockPass(block bool) (unlock func()) {
	u, _ := l.tryLockPass(block)
	return u
}

func (l *Leg) tryLockPass(block bool) (unlock func(), ok bool) {
	dir := l.planDir()
	_ = os.MkdirAll(dir, 0o700)
	f, err := os.OpenFile(filepath.Join(dir, "pass.lock"), os.O_CREATE|os.O_RDWR, 0o600)
	if err != nil {
		l.log().Warn("osupdate: pass lock unavailable — continuing without it", "err", err)
		return func() {}, true
	}
	how := syscall.LOCK_EX
	if !block {
		how |= syscall.LOCK_NB
	}
	if err := syscall.Flock(int(f.Fd()), how); err != nil {
		f.Close()
		return func() {}, false
	}
	return func() { _ = syscall.Flock(int(f.Fd()), syscall.LOCK_UN); f.Close() }, true
}

// SendUnsent posts every report a pass kept on disk and nobody sent (R-868). It skips when a pass runs now (that
// pass sends them first). Called at the agent's start.
func (l *Leg) SendUnsent(ctx context.Context) int {
	unlock, ok := l.tryLockPass(false)
	if !ok {
		l.log().Info("osupdate: a pass is running — its start sends any kept report")
		return 0
	}
	defer unlock()
	return l.sendUnsentLocked(ctx)
}

// SendUnsentLoop runs SendUnsent now and then every `every` until ctx ends (v0.144.1). MEASURED live on demo-hp
// 2026-10-05: after a kill -9 the daemon restarted in ~5 s, while the orphaned root wrapper was still installing — its
// copy appeared ~7 s AFTER the start-time sender had looked. One look at start is therefore not enough. A glob of the
// plan dir every few minutes costs nothing; the pass lock keeps it off a running pass. Pinned by
// TestR868_ACopyWrittenAfterTheStartIsSentByTheLoop.
func (l *Leg) SendUnsentLoop(ctx context.Context, every time.Duration, onSent func(int)) {
	for {
		if n := l.SendUnsent(ctx); n > 0 && onSent != nil {
			onSent(n)
		}
		select {
		case <-ctx.Done():
			return
		case <-time.After(every):
		}
	}
}

func (l *Leg) sendUnsentLocked(ctx context.Context) int {
	if l.Hub == nil {
		return 0 // nobody to send to: keep the copies for a process that has the hub
	}
	files, _ := filepath.Glob(filepath.Join(l.planDir(), "report-*.json"))
	sent := 0
	for _, f := range files {
		b, err := os.ReadFile(f)
		if err != nil {
			l.log().Warn("osupdate: a kept report cannot be read", "path", f, "err", err)
			continue
		}
		var wr WrapperReport
		if err := json.Unmarshal(b, &wr); err != nil || wr.Layer == "" {
			l.log().Warn("osupdate: a kept report is not a report — moved aside", "path", f, "err", err)
			_ = os.Rename(f, f+".bad")
			continue
		}
		rep := l.reportFromKept(ctx, wr, f)
		lg := l.log().With("run", rep.RunID, "layer", rep.Layer, "vmid", rep.VMID, "ring", rep.Ring, "trigger", rep.Trigger)
		lg.Info("osupdate: sending a report the agent never sent (the agent stopped mid-pass, R-868)", "path", f)
		before := rep.unsent
		_ = l.finish(ctx, lg, rep)
		if _, err := os.Stat(before); os.IsNotExist(err) {
			sent++
			// the pass's plan file is left behind too when the agent was killed inside call()
			_ = os.Remove(filepath.Join(filepath.Dir(f), "plan-"+strings.TrimPrefix(filepath.Base(f), "report-")))
		}
	}
	return sent
}

// reportFromKept builds the hub report from a kept wrapper report, as runLayer would have. Health: the copy's own
// before/after reading; when that is not healthy after an install, one fresh reading (services restart after an
// install, and the pass that would have waited for them is gone).
func (l *Leg) reportFromKept(ctx context.Context, wr WrapperReport, path string) Report {
	ring := 1
	if wr.Ring != nil {
		ring = *wr.Ring
	}
	runID, trigger := wr.RunID, wr.Trigger
	if runID == "" {
		runID = strings.TrimSuffix(strings.TrimPrefix(filepath.Base(path), "report-"), ".json")
	}
	if trigger == "" {
		trigger = "unknown"
	}
	rep := Report{RunID: runID, Layer: wr.Layer, Trigger: trigger, Mode: wr.Mode, Ring: ring, ReleaseID: wr.ReleaseID,
		VMID: wr.VMID, unsent: path}
	prefix := "sent after the agent stopped mid-pass (R-868)"
	switch {
	case wr.refused():
		rep.Outcome, rep.Refused, rep.HealthReason = "refused", wr.Refused, prefix
		return rep
	case wr.failed():
		rep.Outcome, rep.Refused = "failed", wr.Failed
	case len(wr.Upgraded) == 0:
		rep.Outcome = "nothing"
	default:
		rep.Outcome = "applied"
	}
	rep.Upgraded, rep.PassSeconds = wr.Upgraded, wr.PassSeconds
	rep.DockerEngine, rep.Authority, rep.Undo = wr.DockerEngine, wr.Authority, wr.Undo
	wantEngine := ""
	for _, u := range wr.Upgraded {
		if u.Name == "docker-ce" {
			wantEngine = EngineOf(u.Version)
		}
	}
	verdict := func(h *Health) (bool, string) {
		switch wr.Layer {
		case LayerDocker:
			return DockerHealthVerdict(wr.HealthBefore, h, wantEngine, wr.DockerEngine)
		case LayerHost:
			t := hub.TunnelUnknown
			if l.Tunnel != nil {
				t, _ = l.Tunnel.Status(ctx)
			}
			return HostHealthVerdict(wr.HealthBefore, h, t)
		}
		return HealthVerdict(wr.HealthBefore, h)
	}
	ok, why := verdict(wr.HealthAfter)
	if !ok && len(wr.Upgraded) > 0 && wr.VMID > 0 {
		lane := "fast"
		if wr.Layer == LayerDocker {
			lane = "slow"
		}
		if hr, err := l.call(ctx, "kept-"+runID, map[string]any{"release_id": "kept", "layer": wr.Layer, "lane": lane,
			"vmid": wr.VMID, "mode": "health", "packages": []Package{}}); err == nil && hr.Health != nil {
			ok, why = verdict(hr.Health)
		}
	}
	rep.Healthy, rep.HealthReason = ok, prefix
	if why != "" {
		rep.HealthReason = prefix + ": " + why
	}
	if !ok && rep.Outcome == "applied" {
		rep.Outcome = "health_failed"
	}
	rep.Installed, rep.Pending = wr.Installed, wr.Pending
	rep.RestartNeeded, rep.DockerRestartNeeded, rep.RebootNeeded = wr.RestartNeeded, wr.DockerRestartNeeded, wr.RebootNeeded
	rep.RebootScanned = wr.RebootScanned
	if wr.Layer == LayerDocker {
		rep.Installed, rep.Pending = onlyDocker(wr.Installed), onlyDockerPending(wr.Pending)
	} else {
		planned := map[string]bool{}
		for _, u := range wr.Upgraded {
			planned[u.Name] = true
		}
		rep.NotCovered = notCovered(wr.Pending, ring, planned)
	}
	return rep
}