v0.144.0 code: R8 measures the real download (R-865); an OS pass's report survives a killed agent (R-868); the debug pass runs from the saved block when the hub is away (R-866)

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

cmd/felhom-agent/main.go

@@ -868,6 +868,13 @@ func runDaemon(cfg config.Config, logger *slog.Logger, logRing *applog.Ring) int
 	logger.Info("felhom-agent daemon starting",
 		"version", version, "host_id", cfg.Hub.HostID, "hub_url", cfg.Hub.URL,
 		"interval_s", hcfg.PollSeconds) // hub key intentionally not logged
+	// R-868 (v0.144.0): an OS pass whose agent was killed kept its report on disk — send it now (a pass that starts
+	// first sends it itself; the pass lock keeps the two apart).
+	go func() {
+		if n := osLeg.SendUnsent(ctx); n > 0 {
+			logger.Info("osupdate: sent kept report(s) at start", "count", n)
+		}
+	}()
 
 	// Reconcile (slice 4) runs alongside the hub loop, sharing the per-guest queue
 	// (doc 03 §10). At slice 4 the desired-state provider is empty (no hub serving
@@ -3575,15 +3582,15 @@ func runSelftestOSUpdate(ctx context.Context, cfg config.Config, logger *slog.Lo
 		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)
+	blk, source, ok := selftestOSBlock(ctx, client, leg.PlanDir)
+	if !ok {
+		fmt.Fprintln(os.Stderr, "selftest=os-update:", source)
 		return 1
 	}
-	leg.SetBlock(resp.DesiredState.OSUpdate)
+	leg.SetBlock(blk)
 	b := leg.Block()
-	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)
+	fmt.Printf("=== felhom-agent %s selftest=os-update vmid=%d ring=%d enabled=%v guest-release=%v host-release=%v appliance=%v block=%s ===\n",
+		version, vmid, b.Ring, b.Enabled, b.Release != nil, b.HostRelease != nil, leg.Appliance, source)
 	start := time.Now()
 	pass := leg.Run(ctx, vmid, "debug")
 	worst := pass.Guest
@@ -3609,6 +3616,24 @@ func runSelftestOSUpdate(ctx context.Context, cfg config.Config, logger *slog.Lo
 	return 1
 }
 
+// selftestOSBlock is the debug pass's os_update block (R-866, v0.144.0): the hub's, fetched fresh; when the hub cannot
+// be reached, the block the daemon last saved — named in the selftest's first line, so a pass with the hub away can
+// be exercised by hand (the daemon's own leg already ran from its last block; the selftest stopped). No saved block
+// and no hub → not run (ok=false), never a guessed block.
+func selftestOSBlock(ctx context.Context, f interface {
+	FetchDesiredState(context.Context) (*hub.DesiredStateResponse, error)
+}, planDir string) (*hub.WireOSUpdate, string, bool) {
+	resp, err := f.FetchDesiredState(ctx)
+	if err == nil {
+		return resp.DesiredState.OSUpdate, "hub", true
+	}
+	saved, at, ok := osupdate.LoadSavedBlock(planDir)
+	if !ok {
+		return nil, fmt.Sprintf("desired state: %v — and no saved block (the daemon saves one when the hub sends it)", err), false
+	}
+	return saved, fmt.Sprintf("SAVED(%s; hub unreachable: %v)", at.UTC().Format(time.RFC3339), err), true
+}
+
 // runSelftestFacts prints the versions the host report carries (R-852, agent v0.142.0) — read-only.
 //
 //	sudo -u felhom-agent felhom-agent --config … --selftest=os-facts -vmid 9201

cmd/felhom-agent/r866_selftest_block_test.go

@@ -0,0 +1,55 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+
+	"gitea.dooplex.hu/admin/felhom-agent/internal/hub"
+	"gitea.dooplex.hu/admin/felhom-agent/internal/osupdate"
+)
+
+type r866Fetcher struct{ err error }
+
+func (f r866Fetcher) FetchDesiredState(context.Context) (*hub.DesiredStateResponse, error) {
+	if f.err != nil {
+		return nil, f.err
+	}
+	r := &hub.DesiredStateResponse{}
+	r.DesiredState.OSUpdate = &hub.WireOSUpdate{Ring: 1, Enabled: true}
+	return r, nil
+}
+
+// R-866 (v0.144.0). THE NIGHT'S SHAPE (A3, Tester 1 box, hub blocked): `selftest=os-update: desired state: hub:
+// transport error … connect: invalid argument` — the debug pass could not run at all. Now it runs from the block the
+// daemon saved, and its header says so.
+// COMPANION RED-PROOF: return at once on a fetch error in selftestOSBlock → "the pass did not run from the saved block".
+func TestR866_DebugPassUsesTheSavedBlockWhenTheHubIsAway(t *testing.T) {
+	dir := t.TempDir()
+	leg := &osupdate.Leg{PlanDir: dir}
+	r := &hub.DesiredStateResponse{}
+	r.DesiredState.OSUpdate = &hub.WireOSUpdate{Ring: 0, Enabled: true}
+	leg.OnDesiredState(context.Background(), r) // the daemon received a block and saved it
+	away := r866Fetcher{err: errors.New("hub: transport error: connect: invalid argument")}
+	b, src, ok := selftestOSBlock(context.Background(), away, dir)
+	if !ok || b == nil || b.Ring != 0 {
+		t.Fatalf("the pass did not run from the saved block: ok=%v block=%+v src=%q", ok, b, src)
+	}
+	if !strings.HasPrefix(src, "SAVED(") || !strings.Contains(src, "hub unreachable") {
+		t.Fatalf("the header must say the block is the saved one: %q", src)
+	}
+	// the hub reachable: its block wins, and the header says "hub"
+	b, src, ok = selftestOSBlock(context.Background(), r866Fetcher{}, dir)
+	if !ok || b.Ring != 1 || src != "hub" {
+		t.Fatalf("hub block not used: %+v %q", b, src)
+	}
+}
+
+// No hub and nothing saved: the pass does not run on a guessed block.
+func TestR866_NoHubNoSavedBlockDoesNotRun(t *testing.T) {
+	_, why, ok := selftestOSBlock(context.Background(), r866Fetcher{err: errors.New("down")}, t.TempDir())
+	if ok || !strings.Contains(why, "no saved block") {
+		t.Fatalf("ok=%v why=%q", ok, why)
+	}
+}