mesh-host/internal/link/rotate_test.go

package link

import (
	"context"
	"errors"
	"slices"
	"strings"
	"testing"
	"time"

	"git.novox.be/novox/mesh-sdk/go/delivery"
)

// rotRig is a Rotator over stand-ins: what the vault hands, what a test-dial answers, and what it was asked, in order.
type rotRig struct {
	r       *Rotator
	logins  *Logins
	states  []LoginsState
	steps   []string
	dialErr error
	said    []string
}

func newRotRig() *rotRig {
	g := &rotRig{}
	g.logins = NewLogins("ace", "first", LoginsState{}, func(s LoginsState) error {
		g.states = append(g.states, LoginsState{Current: s.Current, Values: map[string]string{}})
		for k, v := range s.Values {
			g.states[len(g.states)-1].Values[k] = v
		}
		return nil
	})
	g.r = &Rotator{Logins: g.logins,
		Fetch: func(_ context.Context, login string) (string, error) {
			g.steps = append(g.steps, "fetch "+login)
			return "secret-of-" + login, nil
		},
		TestDial: func(_ context.Context, login, _ string) error {
			g.steps = append(g.steps, "test-dial "+login)
			return g.dialErr
		},
		Confirm: func(context.Context) error {
			cur, _ := g.logins.Current()
			g.steps = append(g.steps, "confirm as "+cur)
			return nil
		},
		Say:       func(s string) { g.said = append(g.said, s) },
		Now:       func() time.Time { return time.Date(2026, 11, 2, 12, 5, 0, 0, time.UTC) },
		FailBound: 2}
	g.r.Watch()
	return g
}

func key(login, rotating, stage string) delivery.NodeLogin {
	return delivery.NodeLogin{Node: "ace", Login: login, Rotating: rotating, Stage: stage, Since: time.Date(2026, 11, 2, 12, 0, 0, 0, time.UTC)}
}

// 774/S62/AC1 and AC2 (ADR 0583 §3): at ready the engine fetches the new value and test-dials it; one that does not
// authenticate leaves it on the old login, saying why; one that does is switched to, confirmed over the new connection, and
// the old value is kept.
func TestTheEngineSwitchesOnlyAfterATestDialAndConfirmsAsTheNewLogin(t *testing.T) {
	g := newRotRig()
	ctx := context.Background()
	g.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationBegun))
	if len(g.steps) != 0 {
		t.Fatalf("before ready: %v", g.steps)
	}
	g.dialErr = errors.New("authorization violation")
	g.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationReady))
	if cur, _ := g.logins.Current(); cur != "node.ace" || !strings.Contains(strings.Join(g.said, "|"), "stays on node.ace") ||
		slices.Contains(g.steps, "confirm as node.ace--b") {
		t.Fatalf("a test-dial that failed: %s, said %v, steps %v", cur, g.said, g.steps)
	}
	g.dialErr = nil
	g.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationReady))
	cur, pw := g.logins.Current()
	if cur != "node.ace--b" || pw != "secret-of-node.ace--b" {
		t.Fatalf("after a good test-dial: %s %s", cur, pw)
	}
	if want := []string{"fetch node.ace--b", "test-dial node.ace--b", "test-dial node.ace--b", "confirm as node.ace--b"}; !slices.Equal(g.steps, want) {
		t.Errorf("steps %v, want %v", g.steps, want)
	}
	if v, ok := g.logins.Value("node.ace"); !ok || v != "first" {
		t.Error("the old value was not kept at the switch")
	}
	select {
	case <-g.logins.Changed():
	default:
		t.Error("the link was not told to open again as the new login")
	}
}

// 774/S63/AC1-AC3 (ADR 0583 §4-§6): the old value is dropped at rotation-done and not before; an abandon after the switch,
// before or after the confirmation, switches back before the new value is dropped; repeated failures with the new value before
// rotation-done bring the old one back, said as node-account-fallback, and that rotation is not tried again.
func TestTheOldValueGoesAtRotationDoneAbandonSwitchesBackAndFailuresFallBack(t *testing.T) {
	ctx := context.Background()
	for _, stage := range []string{"before confirming", "after confirming"} {
		g := newRotRig()
		g.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationReady))
		if stage == "after confirming" {
			g.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationConfirmed))
		}
		if _, held := g.logins.Value("node.ace"); !held {
			t.Fatalf("%s: the old value was dropped before rotation-done", stage)
		}
		g.states = nil
		g.r.Heard(ctx, key("node.ace", "", "")) // abandon: the vault keeps the old login in use, no rotation
		if cur, _ := g.logins.Current(); cur != "node.ace" {
			t.Fatalf("%s: after abandon the engine dials as %s", stage, cur)
		}
		for _, s := range g.states {
			if _, held := s.Values["node.ace--b"]; !held && s.Current != "node.ace" {
				t.Errorf("%s: the new value was dropped while %s was in use: %+v", stage, s.Current, s)
			}
		}
		if _, held := g.logins.Value("node.ace--b"); held {
			t.Errorf("%s: the abandoned value is kept", stage)
		}
	}
	g := newRotRig()
	g.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationReady))
	g.r.Heard(ctx, key("node.ace--b", "", "")) // rotation-done: the vault retired the old login
	if _, held := g.logins.Value("node.ace"); held {
		t.Error("the old value is kept after rotation-done")
	}
	if cur, _ := g.logins.Current(); cur != "node.ace--b" {
		t.Errorf("in use after done: %s", cur)
	}
	// Fallback: two failures with the new value (the bound) before rotation-done.
	f := newRotRig()
	f.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationReady))
	f.logins.dialed("node.ace--b", errors.New("nats: authorization violation"))
	if cur, _ := f.logins.Current(); cur != "node.ace--b" {
		t.Fatalf("fell back after one failure: %s", cur)
	}
	f.logins.dialed("node.ace--b", errors.New("nats: authorization violation"))
	fb := f.r.Fallback()
	if cur, _ := f.logins.Current(); cur != "node.ace" || fb == nil || fb.Node != "ace" || fb.From != "node.ace--b" || fb.Why == "" || fb.At.IsZero() {
		t.Fatalf("after the bound: %s, fall back %+v", cur, fb)
	}
	// The health report carries it, from which the watchman raises node-account-fallback.
	if _, err := delivery.EncodeNodeHealth(delivery.NodeHealth{Node: "ace", Fallback: fb}); err != nil {
		t.Errorf("the fall back is no health report's: %v", err)
	}
	steps := len(f.steps)
	f.r.Heard(ctx, key("node.ace", "node.ace--b", delivery.RotationReady))
	if len(f.steps) != steps {
		t.Errorf("the rotation fallen back from was tried again: %v", f.steps[steps:])
	}
	f.logins.dialed("node.ace", errors.New("dial tcp: connection refused")) // not a refusal of credentials: counts for nothing
	// The vault moves on (it abandons the rotation): the fall back is said no more.
	abandoned := key("node.ace", "", "")
	abandoned.Since = abandoned.Since.Add(time.Minute)
	f.r.Heard(ctx, abandoned)
	if f.r.Fallback() != nil {
		t.Error("the fall back is still said after the vault moved on")
	}
}