hyperguild/ingestion/internal/startupretry/startupretry_test.go

// ingestion/internal/startupretry/startupretry_test.go
package startupretry

import (
	"context"
	"errors"
	"testing"
	"time"
)

func fastPolicy(attempts int) Policy {
	return Policy{Attempts: attempts, Base: time.Millisecond, Max: 2 * time.Millisecond}
}

func TestDo_ReturnsImmediatelyOnFirstSuccess(t *testing.T) {
	calls := 0
	got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
		calls++
		return "ready", nil
	})
	if err != nil {
		t.Fatalf("Do: %v", err)
	}
	if got != "ready" {
		t.Errorf("got %q, want %q", got, "ready")
	}
	if calls != 1 {
		t.Errorf("calls = %d, want 1", calls)
	}
}

func TestDo_SurvivesTransientFailuresThenSucceeds(t *testing.T) {
	// The observed cold-boot race: dex is not serving yet, ingress answers
	// 502 for the first few attempts, then discovery works.
	calls := 0
	got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
		calls++
		if calls < 4 {
			return "", errors.New("oidc discovery: status 502")
		}
		return "ready", nil
	})
	if err != nil {
		t.Fatalf("Do returned %v — a transient 502 must not be fatal", err)
	}
	if got != "ready" {
		t.Errorf("got %q, want %q", got, "ready")
	}
	if calls != 4 {
		t.Errorf("calls = %d, want 4", calls)
	}
}

func TestDo_GivesUpAfterTheAttemptBudgetAndReportsTheLastError(t *testing.T) {
	// A genuinely broken issuer must still fail — retrying forever would turn
	// a config error into a silent hang, which is worse than crash-looping.
	last := errors.New("oidc discovery: status 404")
	calls := 0

	_, err := Do(context.Background(), fastPolicy(3), func(context.Context) (string, error) {
		calls++
		return "", last
	})

	if !errors.Is(err, last) {
		t.Fatalf("err = %v, want it to wrap the last failure", err)
	}
	if calls != 3 {
		t.Errorf("calls = %d, want 3 (the attempt budget)", calls)
	}
}

func TestDo_StopsPromptlyWhenTheContextIsCancelled(t *testing.T) {
	ctx, cancel := context.WithCancel(context.Background())
	calls := 0

	done := make(chan struct{})
	var err error
	go func() {
		defer close(done)
		_, err = Do(ctx, Policy{Attempts: 100, Base: 50 * time.Millisecond, Max: time.Second},
			func(context.Context) (string, error) {
				calls++
				if calls == 1 {
					cancel()
				}
				return "", errors.New("still down")
			})
	}()

	select {
	case <-done:
	case <-time.After(2 * time.Second):
		t.Fatal("Do did not return after context cancellation")
	}
	if !errors.Is(err, context.Canceled) {
		t.Errorf("err = %v, want context.Canceled", err)
	}
}

func TestDo_BacksOffAndIsCappedByMax(t *testing.T) {
	var delays []time.Duration
	p := Policy{Attempts: 5, Base: 10 * time.Millisecond, Max: 25 * time.Millisecond}

	last := time.Now()
	_, _ = Do(context.Background(), p, func(context.Context) (string, error) {
		now := time.Now()
		delays = append(delays, now.Sub(last))
		last = now
		return "", errors.New("down")
	})

	// delays[0] is the first call (no wait); the rest are the sleeps.
	if len(delays) != 5 {
		t.Fatalf("attempts = %d, want 5", len(delays))
	}
	if delays[1] >= delays[2] {
		t.Errorf("backoff is not growing: %v then %v", delays[1], delays[2])
	}
	for i, d := range delays[1:] {
		if d > 2*p.Max {
			t.Errorf("delay %d = %v, exceeds the Max cap %v with slack", i+1, d, p.Max)
		}
	}
}

func TestPolicy_ZeroValueStillMakesOneAttempt(t *testing.T) {
	// A caller that forgets to configure the policy must not silently get a
	// no-op that returns a nil validator and a nil error.
	calls := 0
	_, err := Do(context.Background(), Policy{}, func(context.Context) (string, error) {
		calls++
		return "", errors.New("down")
	})

	if calls != 1 {
		t.Errorf("calls = %d, want 1", calls)
	}
	if err == nil {
		t.Error("err = nil, want the failure surfaced")
	}
}