Files
felhom.eu/hub/internal/monitor/host_capability_test.go
T
admin 5121536f10 hub v0.159.0: a refused whole-guest backup has its own alarm (R-1150); a reinstall re-issues the claim code and the off-site login when the old host is stale or off (R-1154)
R-1150: the agent's localapi:backup-cadence-cap is a separate per-host state in
HostCapabilityChecker: alone it raises whole_guest_backup_refused (warning, plain text,
agent reason in details) and whole_guest_backup_refusal_cleared (info); other critical
caps keep agent_capability_degraded/_recovered unchanged. New types operator-only and
hub-origin only (not in allowedEventTypes: the suspected controller must not post them).
agent_capability_degraded/_recovered join operatorOnlyEvents (the checker's "never the
customer" claim was configuration only).

R-1154: handleHostEnroll's reuse path re-issues (claim code + off-site login) when no
controller wait is open and either deliberate_off_at is held or both the host report and
the controller report are older than alerting.stale_threshold (wired from main); once per
silence (host_reenroll_reissued record, also written at mint); a live box gets nothing
re-issued and the skip is recorded (host_reenroll_not_reissued). 05 section 8 [DESIGN].

Tests red-proved; go build/vet/test green.
2026-10-19 03:18:34 +02:00

301 lines
14 KiB
Go

package monitor
import (
"io"
"log"
"path/filepath"
"strings"
"testing"
"gitea.dooplex.hu/admin/felhom-hub/internal/store"
_ "modernc.org/sqlite"
)
// reportWith builds a host-report body carrying the given capability snapshot (the only field the
// capability checker reads). One critical-degraded entry makes the host "degraded".
func reportWith(caps string) []byte {
return []byte(`{"host_id":"h1","capabilities":` + caps + `}`)
}
const capAllOK = `[{"name":"guest-init-pid","feature":"drive-gate","critical":true,"status":"ok"}]`
const capCritDegraded = `[{"name":"guest-init-pid","feature":"drive-gate guest-sees","critical":true,"status":"degraded","reason":"sudo policy denied"}]`
const capNonCritDegraded = `[{"name":"disk-smart","feature":"SMART","critical":false,"status":"degraded","reason":"binary not found"}]`
func newCapStore(t *testing.T) *store.Store {
t.Helper()
st, err := store.New(filepath.Join(t.TempDir(), "test.db"), log.New(io.Discard, "", 0))
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { st.Close() })
st.SaveCustomerConfig(&store.CustomerConfig{CustomerID: "c1", APIKey: "ck", RetrievalPassword: "p"})
st.UpsertHost(&store.Host{HostID: "h1", CustomerID: "c1", APIKey: "k1"})
return st
}
// TestHostCapabilityChecker covers the full transition contract (§10): seed (no event), ok→degraded
// (one event), steady degraded (none), degraded→ok (recovered), and that a non-critical degradation
// never trips the host state.
func TestHostCapabilityChecker(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", reportWith(capAllOK), store.HostReportDenorm{})
var events []string
onEvent := func(_, eventType, _, _, _, _ string) { events = append(events, eventType) }
// Seed ok → no event on init.
cc := NewHostCapabilityChecker(st, onEvent, log.New(io.Discard, "", 0))
if cc.GetState("h1") != "ok" {
t.Fatalf("seed state = %s, want ok", cc.GetState("h1"))
}
if len(events) != 0 {
t.Fatalf("seed must not emit, got %v", events)
}
// ok → degraded: exactly ONE operator event.
st.SaveHostReport("h1", "c1", reportWith(capCritDegraded), store.HostReportDenorm{})
cc.Check()
if cc.GetState("h1") != "degraded" {
t.Fatalf("state = %s, want degraded", cc.GetState("h1"))
}
if len(events) != 1 || events[0] != "agent_capability_degraded" {
t.Fatalf("want one agent_capability_degraded, got %v", events)
}
// Steady degraded: NO duplicate event.
st.SaveHostReport("h1", "c1", reportWith(capCritDegraded), store.HostReportDenorm{})
cc.Check()
if len(events) != 1 {
t.Fatalf("steady degraded must not re-emit, got %v", events)
}
// degraded → ok: recovered event.
st.SaveHostReport("h1", "c1", reportWith(capAllOK), store.HostReportDenorm{})
cc.Check()
if cc.GetState("h1") != "ok" {
t.Fatalf("state = %s, want ok", cc.GetState("h1"))
}
if len(events) != 2 || events[1] != "agent_capability_recovered" {
t.Fatalf("want recovered event, got %v", events)
}
}
// A NON-critical degradation must NOT flip the host to degraded (no operator noise).
func TestHostCapabilityChecker_NonCriticalIgnored(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", reportWith(capAllOK), store.HostReportDenorm{})
var events []string
cc := NewHostCapabilityChecker(st, func(_, et, _, _, _, _ string) { events = append(events, et) }, log.New(io.Discard, "", 0))
st.SaveHostReport("h1", "c1", reportWith(capNonCritDegraded), store.HostReportDenorm{})
cc.Check()
if cc.GetState("h1") != "ok" {
t.Fatalf("non-critical degradation flipped state to %s, want ok", cc.GetState("h1"))
}
if len(events) != 0 {
t.Fatalf("non-critical degradation must not alert, got %v", events)
}
}
// A pre-v0.44.0 agent (no capabilities array) is "ok" — an old agent can't trip a false alert.
func TestHostCapabilityChecker_OldAgentNoCaps(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", []byte(`{"host_id":"h1"}`), store.HostReportDenorm{})
cc := NewHostCapabilityChecker(st, func(_, _, _, _, _, _ string) {}, log.New(io.Discard, "", 0))
if cc.GetState("h1") != "ok" {
t.Fatalf("old agent (no caps) state = %s, want ok", cc.GetState("h1"))
}
}
// F2 RED-PROOF: a host already DEGRADED at hub (re)start is left UNSEEDED by the constructor and the
// FIRST Check emits once — so a box that was already broken when the hub restarted alerts (vs the
// pre-fix path which seeded it silently and never alerted). Companion: pre-fix the constructor seeded
// "degraded" and Check saw oldState==newState → no event.
func TestHostCapabilityChecker_F2_BornDegradedAlerts(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", reportWith(capCritDegraded), store.HostReportDenorm{})
var events []string
cc := NewHostCapabilityChecker(st, func(_, et, _, _, _, _ string) { events = append(events, et) }, log.New(io.Discard, "", 0))
if len(events) != 0 {
t.Fatalf("construction must not emit, got %v", events)
}
if cc.GetState("h1") != "unknown" {
t.Fatalf("born-degraded must be left unseeded, GetState = %s want unknown", cc.GetState("h1"))
}
cc.Check()
if len(events) != 1 || events[0] != "agent_capability_degraded" {
t.Fatalf("born-degraded first Check → one agent_capability_degraded, got %v", events)
}
cc.Check() // steady degraded → no duplicate
if len(events) != 1 {
t.Fatalf("steady degraded must not re-emit, got %v", events)
}
}
// ── R-1150: a refused whole-guest backup has its own alarm ───────────────────────────────────────
const capCadenceRefused = `[{"name":"guest-init-pid","feature":"drive-gate","critical":true,"status":"ok"},` +
`{"name":"localapi:backup-cadence-cap","feature":"whole-guest restore points","critical":true,"status":"degraded",` +
`"reason":"refused a whole-guest backup of guest 9202 on target \"local\" at 2026-10-19T03:15:00Z — more than the schedule allows; the guest's controller may be misbehaving or compromised: check the guest"}]`
const capCadenceOK = `[{"name":"guest-init-pid","feature":"drive-gate","critical":true,"status":"ok"},` +
`{"name":"localapi:backup-cadence-cap","feature":"whole-guest restore points","critical":true,"status":"ok"}]`
const capGrantAndCadenceDegraded = `[{"name":"guest-init-pid","feature":"drive-gate guest-sees","critical":true,"status":"degraded","reason":"sudo policy denied"},` +
`{"name":"localapi:backup-cadence-cap","feature":"whole-guest restore points","critical":true,"status":"degraded","reason":"refused a whole-guest backup of guest 9202"}]`
const capGrantDegradedCadenceOK = `[{"name":"guest-init-pid","feature":"drive-gate guest-sees","critical":true,"status":"degraded","reason":"sudo policy denied"},` +
`{"name":"localapi:backup-cadence-cap","feature":"whole-guest restore points","critical":true,"status":"ok"}]`
type capEvent struct{ eventType, severity, message, details string }
func recordCapEvents(evs *[]capEvent) EventNotifyFunc {
return func(_, eventType, severity, message, details, _ string) {
*evs = append(*evs, capEvent{eventType, severity, message, details})
}
}
func capTypes(evs []capEvent) []string {
out := make([]string, len(evs))
for i, e := range evs {
out[i] = e.eventType
}
return out
}
// The cadence cap ALONE degraded → exactly one whole_guest_backup_refused (warning, plain text, the agent's
// reason in the details) and NOT agent_capability_degraded; steady → nothing; the window ending → one
// whole_guest_backup_refusal_cleared (info) and NOT agent_capability_recovered.
//
// COMPANION RED-PROOF (observed 2026-10-19): with the pre-fix shape restored (capabilityState counting the
// cadence cap like any grant, no separate refusal state) this test fails with
//
// host_capability_test.go: cadence cap alone → want [whole_guest_backup_refused], got [agent_capability_degraded]
//
// Restored.
func TestR1150_CadenceCapAloneRaisesWholeGuestBackupRefused(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", reportWith(capCadenceOK), store.HostReportDenorm{})
var evs []capEvent
cc := NewHostCapabilityChecker(st, recordCapEvents(&evs), log.New(io.Discard, "", 0))
st.SaveHostReport("h1", "c1", reportWith(capCadenceRefused), store.HostReportDenorm{})
cc.Check()
if got := capTypes(evs); len(got) != 1 || got[0] != "whole_guest_backup_refused" {
t.Fatalf("cadence cap alone → want [whole_guest_backup_refused], got %v", got)
}
e := evs[0]
if e.severity != "warning" {
t.Errorf("severity = %q, want warning", e.severity)
}
if !strings.Contains(e.message, "a whole-guest backup was refused") || !strings.Contains(e.message, "check the guest") {
t.Errorf("message does not say what happened in plain words: %q", e.message)
}
if strings.Contains(e.message, "privileged capability") {
t.Errorf("message still reads as a broken grant: %q", e.message)
}
if !strings.Contains(e.details, "guest 9202") || !strings.Contains(e.details, "localapi:backup-cadence-cap") {
t.Errorf("details must carry the agent's reason and the capability name: %s", e.details)
}
if cc.GetState("h1") != "ok" {
t.Errorf("the grants state = %s, want ok (the cadence cap is not a grant)", cc.GetState("h1"))
}
if cc.GetBackupRefusalState("h1") != "degraded" {
t.Errorf("refusal state = %s, want degraded", cc.GetBackupRefusalState("h1"))
}
// The event is STORED too (the operator's event list), under the new type.
if at, err := st.LastEventAt("c1", "whole_guest_backup_refused"); err != nil || at.IsZero() {
t.Errorf("whole_guest_backup_refused not stored: at=%v err=%v", at, err)
}
st.SaveHostReport("h1", "c1", reportWith(capCadenceRefused), store.HostReportDenorm{})
cc.Check()
if len(evs) != 1 {
t.Fatalf("steady refusal must not re-emit, got %v", capTypes(evs))
}
st.SaveHostReport("h1", "c1", reportWith(capCadenceOK), store.HostReportDenorm{})
cc.Check()
if got := capTypes(evs); len(got) != 2 || got[1] != "whole_guest_backup_refusal_cleared" {
t.Fatalf("refusal window ended → want [.. whole_guest_backup_refusal_cleared], got %v", got)
}
if evs[1].severity != "info" {
t.Errorf("cleared severity = %q, want info (recorded, never mailed)", evs[1].severity)
}
}
// Another critical cap degraded → agent_capability_degraded unchanged (the cadence cap never named in it);
// both degraded on ONE report → exactly one event per state; the grant restored while the refusal stands →
// agent_capability_recovered alone; nothing for a steady state.
//
// COMPANION RED-PROOF (observed 2026-10-19): with the pre-fix shape restored the both-degraded report emits a
// single event naming both caps and the test fails with
//
// host_capability_test.go: grant + cadence on one report → want [agent_capability_degraded whole_guest_backup_refused], got [agent_capability_degraded]
//
// Restored.
func TestR1150_OtherCapStillRaisesCapabilityDegraded(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", reportWith(capCadenceOK), store.HostReportDenorm{})
var evs []capEvent
cc := NewHostCapabilityChecker(st, recordCapEvents(&evs), log.New(io.Discard, "", 0))
// A grant alone: the old event, unchanged text.
st.SaveHostReport("h1", "c1", reportWith(capGrantDegradedCadenceOK), store.HostReportDenorm{})
cc.Check()
if got := capTypes(evs); len(got) != 1 || got[0] != "agent_capability_degraded" {
t.Fatalf("grant alone → want [agent_capability_degraded], got %v", got)
}
if !strings.Contains(evs[0].message, "agent privileged capability degraded — guest-init-pid") {
t.Errorf("agent_capability_degraded text changed: %q", evs[0].message)
}
// Back to clean, then both on one report.
st.SaveHostReport("h1", "c1", reportWith(capCadenceOK), store.HostReportDenorm{})
cc.Check()
evs = nil
st.SaveHostReport("h1", "c1", reportWith(capGrantAndCadenceDegraded), store.HostReportDenorm{})
cc.Check()
got := capTypes(evs)
if len(got) != 2 || got[0] != "agent_capability_degraded" || got[1] != "whole_guest_backup_refused" {
t.Fatalf("grant + cadence on one report → want [agent_capability_degraded whole_guest_backup_refused], got %v", got)
}
if strings.Contains(evs[0].message, "backup-cadence-cap") || strings.Contains(evs[0].details, "backup-cadence-cap") {
t.Errorf("agent_capability_degraded must not name the cadence cap: %q / %s", evs[0].message, evs[0].details)
}
// Steady: nothing.
st.SaveHostReport("h1", "c1", reportWith(capGrantAndCadenceDegraded), store.HostReportDenorm{})
cc.Check()
if len(evs) != 2 {
t.Fatalf("steady both-degraded must not re-emit, got %v", capTypes(evs))
}
// The grant restored, the refusal still standing: only the grants recover.
st.SaveHostReport("h1", "c1", reportWith(capCadenceRefused), store.HostReportDenorm{})
cc.Check()
if got := capTypes(evs); len(got) != 3 || got[2] != "agent_capability_recovered" {
t.Fatalf("grant restored, refusal standing → want [.. agent_capability_recovered], got %v", got)
}
if cc.GetBackupRefusalState("h1") != "degraded" {
t.Errorf("refusal state = %s, want still degraded", cc.GetBackupRefusalState("h1"))
}
}
// F2 for the refusal: a host already reporting a refused backup when the hub (re)starts alerts ONCE on the
// first Check (not at construction), and never again while steady.
//
// COMPANION RED-PROOF (observed 2026-10-19): with the pre-fix shape restored it fails with
//
// host_capability_test.go: born-refused → want exactly [whole_guest_backup_refused], got [agent_capability_degraded]
//
// Restored.
func TestR1150_BornRefusedAlertsOnce(t *testing.T) {
st := newCapStore(t)
st.SaveHostReport("h1", "c1", reportWith(capCadenceRefused), store.HostReportDenorm{})
var evs []capEvent
cc := NewHostCapabilityChecker(st, recordCapEvents(&evs), log.New(io.Discard, "", 0))
if len(evs) != 0 {
t.Fatalf("construction must not emit, got %v", capTypes(evs))
}
cc.Check()
cc.Check()
if got := capTypes(evs); len(got) != 1 || got[0] != "whole_guest_backup_refused" {
t.Fatalf("born-refused → want exactly [whole_guest_backup_refused], got %v", got)
}
}