felhom-agent/internal/backup/r874_first_eval_test.go

package backup

import (
	"context"
	"fmt"
	"sync/atomic"
	"testing"
	"time"

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

// R-874 (v0.145.0). THE MEASURED SHAPE (Part F spike, Tester 2): power-on sessions of ~1.5 h and ~5 min against a
// 6 h evaluation ticker that restarts at every start — no restore-test ever evaluated. Now the first evaluation runs
// FirstEval after start.
// COMPANION RED-PROOF: drop the first-evaluation timer in Run (back to the bare ticker) → "no evaluation within".
func TestR874_FirstEvaluationAfterStart(t *testing.T) {
	var picks int32
	s := NewScheduler(SchedulerOptions{
		Runner: &fakeRTRunner{res: reconcile.RestoreTestResult{Pass: true, Verified: "boot+running"}},
		Pick: func(context.Context) (string, error) {
			atomic.AddInt32(&picks, 1)
			return fmt.Sprintf("local:backup/vzdump-lxc-9201-%d.tar.zst", atomic.LoadInt32(&picks)), nil
		},
		Store: NewStore(), Spec: (&specSpy{}).build,
		Cadence: 6 * time.Hour, FirstEval: 30 * time.Millisecond, Logger: quiet(),
	})
	ctx, cancel := context.WithCancel(context.Background())
	done := make(chan struct{})
	go func() { _ = s.Run(ctx); close(done) }()
	deadline := time.Now().Add(3 * time.Second)
	for atomic.LoadInt32(&picks) == 0 && time.Now().Before(deadline) {
		time.Sleep(10 * time.Millisecond)
	}
	cancel()
	<-done
	if atomic.LoadInt32(&picks) == 0 {
		t.Fatal("no evaluation within 3 s of start (FirstEval 30 ms) — a box with short sessions never gets a restore-test")
	}
}

// The earned restraint stays: an agent that restarts before FirstEval never evaluates (a crash loop does not
// hammer a failing tier).
func TestR874_CrashLoopNeverEvaluates(t *testing.T) {
	var picks int32
	for i := 0; i < 5; i++ { // five quick "restarts"
		s := NewScheduler(SchedulerOptions{
			Runner: &fakeRTRunner{res: reconcile.RestoreTestResult{Pass: true}},
			Pick:   func(context.Context) (string, error) { atomic.AddInt32(&picks, 1); return "x", nil },
			Store:  NewStore(), Spec: (&specSpy{}).build,
			Cadence: 6 * time.Hour, FirstEval: 200 * time.Millisecond, Logger: quiet(),
		})
		ctx, cancel := context.WithTimeout(context.Background(), 20*time.Millisecond)
		_ = s.Run(ctx)
		cancel()
	}
	if n := atomic.LoadInt32(&picks); n != 0 {
		t.Fatalf("a restart before FirstEval evaluated %d time(s)", n)
	}
	if DefaultFirstEval != 30*time.Minute {
		t.Fatalf("DefaultFirstEval = %s, the documented 30 min", DefaultFirstEval)
	}
}