R-898: ring 0 stages exactly the told kernel (select listed, KernelSet(kver))

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

CHANGELOG.md

@@ -1,3 +1,16 @@
+## Unreleased — part of v0.153.0: ring 0 stages exactly the told kernel (R-898; `09` §3 decision 176) (2026-10-07)
+
+**Delivery: the agent binary only** — no root file changed (the wrapper is unchanged; its tests gained two cases).
+
+- `internal/osupdate/kernel.go`: ring 0's night kernel step stages EXACTLY the kernel the household was told about
+  (select `listed`, `KernelSet(kver)` = the series meta-package and the signed image at the kernel's own version) instead
+  of "whatever is pending tonight". Seen 2026-10-07: demo-felhom was told about 7.0.14-20 while its sources offered
+  7.0.14-22 by night — the old code staged `pending-kernel` and the wrapper refused it (R23), losing the night. A told
+  version that is no longer installable is refused by the wrapper before any change (R7) and the hub tells the household
+  again for the newer kernel (hub v0.143.1). Tests `TestKernel_Ring0ToldNightStagesThenReboots` (red-proved against the
+  old select), `TestKernelSet`; wrapper `test_ring0_listed_installs_the_told_kernel_not_the_newest`,
+  `test_ring0_told_kernel_gone_is_refused_before_any_change`.
+
 ## v0.152.0 — the kernel lane (R-836; `09` §3 decisions 164, 172; `11` §5.11) (2026-10-07)
 
 Released by `scripts/release-agent.sh`: binary sha256 `95ff42208e36ba49b6e2b09a97e81a6fa11562ecc8042f1ed18d378b8b1f88b1`,

configs/test_felhom_os_apply.py

@@ -1838,6 +1838,33 @@ class KernelLane(unittest.TestCase):
         m.origins = {"proxmox-kernel-7.0": DEB}
         self.refused(m, "R2")
 
+    # R-898: ring 0 stages EXACTLY the told kernel (select listed, the set derived from it) — even when the sources
+    # offer a newer one by night; a told version that can no longer be installed is refused BEFORE any change (R7).
+    def test_ring0_listed_installs_the_told_kernel_not_the_newest(self):
+        f = kfake()
+        f.live["proxmox-kernel-7.0"] = {"7.0.14-20", "7.0.14-22", "7.0.2-6"}
+        f.live["proxmox-kernel-7.0.14-20-pve-signed"] = {"7.0.14-20"}
+        told = [{"name": "proxmox-kernel-7.0", "version": "7.0.14-20", "origin": "Proxmox Debian Repository"},
+                {"name": "proxmox-kernel-7.0.14-20-pve-signed", "version": "7.0.14-20", "origin": "Proxmox Debian Repository"}]
+        f.plan.update(select="listed", packages=told, expect_kver="7.0.14-20-pve")
+        rc, rep = run(f)
+        self.assertEqual(rc, 0, rep)
+        self.assertEqual(rep["authority"], "ring0")
+        self.assertEqual(f.env, {"felhom_next": "7.0.14-20-pve"})
+        self.assertEqual(f.installed["proxmox-kernel-7.0"], "7.0.14-20")
+        self.assertNotIn("7.0.14-22-pve", f.boot)
+
+    def test_ring0_told_kernel_gone_is_refused_before_any_change(self):
+        f = kfake()
+        f.live["proxmox-kernel-7.0"] = {"7.0.14-22"}   # 7.0.14-20 is no longer in the archive
+        told = [{"name": "proxmox-kernel-7.0", "version": "7.0.14-20", "origin": "Proxmox Debian Repository"},
+                {"name": "proxmox-kernel-7.0.14-20-pve-signed", "version": "7.0.14-20", "origin": "Proxmox Debian Repository"}]
+        f.plan.update(select="listed", packages=told, expect_kver="7.0.14-20-pve")
+        rep = self.refused(f, "R7")
+        self.assertIsNone(f.env)
+        self.assertNotIn(osapply.KERNEL_DEFAULT_CFG, f.tree, "refused before the default was even pinned")
+        self.assertEqual(f.installed["proxmox-kernel-7.0"], "7.0.2-6")
+
     def test_nothing_pending_changes_nothing(self):
         f = kfake(kernel_pending=[])
         rc, rep = run(f)

internal/osupdate/kernel.go

@@ -119,8 +119,12 @@ func (l *Leg) runKernel(ctx context.Context, runID string, vmid int, trigger str
 		lg.Info("osupdate: kernel step skipped — ring 1 boots only a kernel a signed os_kernel_step staged", "phase", st.Phase, "staged", st.To, "want", want)
 		return Report{}
 	default:
+		// R-898: EXACTLY the kernel the household was told about — never "whatever is pending tonight" (the sources can
+		// offer a newer one by night; the step then refused, R23, and the night was lost). A version no longer
+		// installable is refused by the wrapper before any change (R7) and the hub tells the household again.
 		wr, cerr := l.call(ctx, runID, kernelPlan("apply", vmid, map[string]any{"release_id": "ring0-" + runID,
-			"select": "pending-kernel", "expect_kver": want, "run_id": runID, "trigger": trigger, "ring": blk.Ring}))
+			"select": "listed", "packages": KernelSet(want), "expect_kver": want, "run_id": runID, "trigger": trigger,
+			"ring": blk.Ring}))
 		rep.unsent = reportFile(l.planDir(), runID, LayerKernel, "apply")
 		rep.Kernel = rawOrNil(wr.Kernel)
 		switch {
@@ -322,6 +326,21 @@ func truncate(s string, n int) string {
 	return s[:n]
 }
 
+// KernelSet is the package set that installs exactly kver (R-898; the hub's kernelSet, field-exact): the series
+// meta-package and the signed image, both at the kernel's own version. Proxmox keeps old kernel versions in its archive.
+// nil for a string that is not a kernel version.
+func KernelSet(kver string) []Package {
+	m := kverSeriesRE.FindStringSubmatch(kver)
+	if m == nil {
+		return nil
+	}
+	v := kver[:len(kver)-len("-pve")]
+	return []Package{{Name: "proxmox-kernel-" + m[1], Version: v, Origin: PVEOrigin},
+		{Name: "proxmox-kernel-" + kver + "-signed", Version: v, Origin: PVEOrigin}}
+}
+
+var kverSeriesRE = regexp.MustCompile(`^([0-9]+\.[0-9]+)\.[0-9]+-[0-9]+-pve$`)
+
 // KernelStepParams are a signed os_kernel_step's params: the exact kernel set (the wrapper compares it with the plan).
 type KernelStepParams struct {
 	ReleaseID string    `json:"release_id"`

internal/osupdate/kernel_test.go

@@ -54,8 +54,12 @@ func TestKernel_Ring0ToldNightStagesThenReboots(t *testing.T) {
 			ap = x
 		}
 	}
-	if ap["select"] != "pending-kernel" || ap["expect_kver"] != kNew || ap["lane"] != "slow" {
-		t.Fatalf("stage plan = %v", ap)
+	// R-898: EXACTLY the told kernel — the listed set derived from it, never "pending" (red before the fix: select was
+	// pending-kernel, so a newer kernel in the sources by night was refused R23 and the night was lost)
+	pk, _ := json.Marshal(ap["packages"])
+	if ap["select"] != "listed" || ap["expect_kver"] != kNew || ap["lane"] != "slow" ||
+		string(pk) != `[{"name":"proxmox-kernel-7.0","origin":"Proxmox Debian Repository","version":"7.0.14-22"},{"name":"proxmox-kernel-7.0.14-22-pve-signed","origin":"Proxmox Debian Repository","version":"7.0.14-22"}]` {
+		t.Fatalf("stage plan = %v (packages %s)", ap, pk)
 	}
 	if p.Kernel.Outcome != "staged" || !p.Kernel.Healthy {
 		t.Fatalf("kernel report = %+v", p.Kernel)
@@ -312,3 +316,13 @@ func TestKernel_KeptStageReportIsStaged(t *testing.T) {
 		t.Fatalf("kept = %+v", rep)
 	}
 }
+
+func TestKernelSet(t *testing.T) {
+	if got := KernelSet("7.0.14-20-pve"); len(got) != 2 || got[0].Name != "proxmox-kernel-7.0" || got[0].Version != "7.0.14-20" ||
+		got[1].Name != "proxmox-kernel-7.0.14-20-pve-signed" {
+		t.Fatalf("%+v", got)
+	}
+	if KernelSet("7.0; reboot") != nil || KernelSet("") != nil {
+		t.Fatal("a non-kernel string must give no set")
+	}
+}