hub v0.114.0: self-bind auto-send while a customer waits for a box (R-509); node_* bypass the quiet hour (ruling 2026-09-15); PBS re-issue adopts an endpoint token (R-511); controller supervisor events (R-523); event registers

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
2026-09-15 10:05:41 +02:00
parent a028a9a7f5
commit 07959e61b5
16 changed files with 693 additions and 9 deletions
@@ -0,0 +1,95 @@
+package monitor
+
+import (
+	"io"
+	"log"
+	"sync"
+	"testing"
+
+	"gitea.dooplex.hu/admin/felhom-hub/internal/store"
+)
+
+// R-523 — the checker that turns the agent's controller_supervisor stanza into events.
+// The JSON below is the exact wire shape the agent's TestControllerSupervisorStanza_WireShape pins.
+
+func supReport(guests string) []byte {
+	return []byte(`{"host_id":"h1","controller_supervisor":{"guests":` + guests + `}}`)
+}
+
+type evRec struct {
+	mu  sync.Mutex
+	evs []string
+}
+
+func (r *evRec) fn(_, et, sev, _, _, _ string) {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	r.evs = append(r.evs, et+"/"+sev)
+}
+func (r *evRec) take() []string {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	out := r.evs
+	r.evs = nil
+	return out
+}
+
+// The consequence: an agent restart of a controller reaches the dispatcher as
+// controller_restarted_by_agent, once; a crash-loop reaches it as controller_crashloop (error).
+//
+// RED-PROOF: make observe() skip the `LastRestartAt != prev.lastRestartAt` branch → the second
+// Check emits nothing → "restart did not produce controller_restarted_by_agent".
+func TestControllerSupervisorChecker_EmitsOnMovement(t *testing.T) {
+	st := newCapStore(t)
+	rec := &evRec{}
+	c := NewControllerSupervisorChecker(st, rec.fn, log.New(io.Discard, "", 0))
+
+	// Seed: an old restart already recorded at first sight → silent.
+	st.SaveHostReport("h1", "c1", supReport(`[{"vmid":9201,"restarts_total":1,"last_restart_at":"2026-09-15T08:00:00Z","last_reason":"exited","crashloop":false,"parked":false}]`), store.HostReportDenorm{})
+	c.Check()
+	if evs := rec.take(); len(evs) != 0 {
+		t.Fatalf("first observation must seed silently, got %v", evs)
+	}
+	// Same record again → silent.
+	c.Check()
+	if evs := rec.take(); len(evs) != 0 {
+		t.Fatalf("unchanged record emitted %v", evs)
+	}
+	// A new restart.
+	st.SaveHostReport("h1", "c1", supReport(`[{"vmid":9201,"restarts_total":2,"last_restart_at":"2026-09-15T09:00:00Z","last_reason":"exited","crashloop":false,"parked":false}]`), store.HostReportDenorm{})
+	c.Check()
+	if evs := rec.take(); len(evs) != 1 || evs[0] != "controller_restarted_by_agent/info" {
+		t.Fatalf("restart did not produce controller_restarted_by_agent (got %v)", evs)
+	}
+	// Agent restarted (counter back to 1) with a NEW timestamp → still an event.
+	st.SaveHostReport("h1", "c1", supReport(`[{"vmid":9201,"restarts_total":1,"last_restart_at":"2026-09-15T10:00:00Z","last_reason":"absent","crashloop":false,"parked":false}]`), store.HostReportDenorm{})
+	c.Check()
+	if evs := rec.take(); len(evs) != 1 || evs[0] != "controller_restarted_by_agent/info" {
+		t.Fatalf("a restart after an agent restart (counter reset) was lost: %v", evs)
+	}
+	// Crash-loop.
+	st.SaveHostReport("h1", "c1", supReport(`[{"vmid":9201,"restarts_total":4,"last_restart_at":"2026-09-15T10:00:00Z","last_reason":"exited","crashloop":true,"crashloop_since":"2026-09-15T10:05:00Z","parked":false}]`), store.HostReportDenorm{})
+	c.Check()
+	if evs := rec.take(); len(evs) != 1 || evs[0] != "controller_crashloop/error" {
+		t.Fatalf("crash-loop did not produce controller_crashloop/error (got %v)", evs)
+	}
+	// A pre-v0.131.0 report (no stanza) → nothing.
+	st.SaveHostReport("h1", "c1", []byte(`{"host_id":"h1"}`), store.HostReportDenorm{})
+	c.Check()
+	if evs := rec.take(); len(evs) != 0 {
+		t.Fatalf("a report without the stanza emitted %v", evs)
+	}
+}
+
+// A hub restarted DURING a crash-loop must say so once, not seed it away.
+func TestControllerSupervisorChecker_CrashloopAtFirstSightEmits(t *testing.T) {
+	st := newCapStore(t)
+	rec := &evRec{}
+	c := NewControllerSupervisorChecker(st, rec.fn, log.New(io.Discard, "", 0))
+	st.SaveHostReport("h1", "c1", supReport(`[{"vmid":9201,"restarts_total":3,"last_restart_at":"2026-09-15T10:00:00Z","crashloop":true,"crashloop_since":"2026-09-15T10:05:00Z"}]`), store.HostReportDenorm{})
+	c.Check()
+	c.Check()
+	if evs := rec.take(); len(evs) != 1 || evs[0] != "controller_crashloop/error" {
+		t.Fatalf("crash-loop at first sight: want exactly one controller_crashloop, got %v", evs)
+	}
+}