mesh-controller/cmd/mesh-controller/doctor_test.go

package main

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

	"golang.org/x/net/dns/dnsmessage"

	"github.com/novox/mesh-controller/internal/broker"
	"github.com/novox/mesh-controller/internal/catalogue"
	"github.com/novox/mesh-controller/internal/conditions"
	"github.com/novox/mesh-controller/internal/link"
)

// The self-check (novox/hq to-be 45 §4): a probe that fails raises its condition, one that cannot run
// raises probe-failed for itself and is never a pass, and every run ends with its heartbeat.

// withProbes runs the test with a registry of its own.
func withProbes(t *testing.T, probes ...probe) {
	t.Helper()
	before := probeRegistry
	probeRegistry = probes
	t.Cleanup(func() { probeRegistry = before })
}

// **The registry says what each probe asserts**, and a probe not built says why and when.
func TestTheRegistryIsTheDesignsLiveForm(t *testing.T) {
	seen := map[string]bool{}
	for _, p := range probeRegistry {
		if seen[p.ID] {
			t.Errorf("%s twice", p.ID)
		}
		seen[p.ID] = true
		if p.Asserts == "" || p.From == "" || p.Kind == "" {
			t.Errorf("%s does not say what it asserts, where from, or what it raises", p.ID)
		}
		if (p.run == nil) != (p.Deferred != "") || (p.Deferred != "" && p.Phase <= 1) {
			t.Errorf("%s is run and deferred, or neither, or deferred out of Phase 1: %+v", p.ID, p)
		}
	}
	for _, id := range []string{"D1", "D2", "D3", "D4", "D5", "D6", "D7", "D8", "D9", "D10"} {
		if !seen[id] {
			t.Errorf("to-be 45 §4 has %s and the registry does not", id)
		}
	}
}

// **The doctor and the watchdogs watch each other**: watchdogs that stopped are DW; a self-check that
// stopped is S10 (signals_test.go).
func TestWatchdogsThatStoppedAreSaid(t *testing.T) {
	w := &watchdogs{started: time.Now().Add(-time.Hour)}
	d := &doctor{watchdogs: w, host: "anchor"}
	got, err := probeWatchdogs(t.Context(), d)
	if err != nil || len(got) != 1 || got[0].Severity != conditions.Urgent {
		t.Fatalf("%+v %v", got, err)
	}
	w.ticked = time.Now()
	if got, _ := probeWatchdogs(t.Context(), d); len(got) != 0 {
		t.Fatalf("%+v", got)
	}
}

// **D1 composes every machine of a healthy mesh and the host's own validator takes each.**

// **D1 names a machine nothing can be sent to**, and the network that cannot be computed for it.

// **D2: a resolver answering NXDOMAIN for IPv6 is wrong** — musl takes it as no such name (issue 262).
func TestAResolverAnsweringNoSuchNameForIPv6IsWrong(t *testing.T) {
	answerAs := func(rcode dnsmessage.RCode) string {
		conn, err := net.ListenPacket("udp", "127.0.0.1:0")
		if err != nil {
			t.Fatal(err)
		}
		t.Cleanup(func() { _ = conn.Close() })
		go func() {
			buf := make([]byte, 1500)
			for {
				n, from, err := conn.ReadFrom(buf)
				if err != nil {
					return
				}
				var q dnsmessage.Message
				if q.Unpack(buf[:n]) != nil {
					continue
				}
				reply := dnsmessage.Message{Header: dnsmessage.Header{ID: q.ID, Response: true}, Questions: q.Questions}
				if q.Questions[0].Type == dnsmessage.TypeA {
					reply.Answers = []dnsmessage.Resource{{Header: dnsmessage.ResourceHeader{Name: q.Questions[0].Name,
						Type: dnsmessage.TypeA, Class: dnsmessage.ClassINET}, Body: &dnsmessage.AResource{A: [4]byte{10, 77, 0, 1}}}}
				} else {
					reply.RCode = rcode
				}
				packed, _ := reply.Pack()
				_, _ = conn.WriteTo(packed, from)
			}
		}()
		_, port, _ := net.SplitHostPort(conn.LocalAddr().String())
		return port
	}
	before := resolverPort
	t.Cleanup(func() { resolverPort = before })

	resolverPort = answerAs(dnsmessage.RCodeSuccess)
	v4, rcode, err := askResolver(t.Context(), "127.0.0.1", "anchor.internal", dnsmessage.TypeA)
	if err != nil || rcode != dnsmessage.RCodeSuccess || !slices.Equal(v4, []string{"10.77.0.1"}) {
		t.Fatalf("%v %v %v", v4, rcode, err)
	}
	v6, rcode, err := askResolver(t.Context(), "127.0.0.1", "anchor.internal", dnsmessage.TypeAAAA)
	if err != nil || rcode != dnsmessage.RCodeSuccess || len(v6) != 0 {
		t.Fatalf("NODATA read as %v %v %v", v6, rcode, err)
	}
	resolverPort = answerAs(dnsmessage.RCodeNameError)
	if _, rcode, _ := askResolver(t.Context(), "127.0.0.1", "anchor.internal", dnsmessage.TypeAAAA); rcode != dnsmessage.RCodeNameError {
		t.Fatalf("NXDOMAIN read as %v", rcode)
	}
}

// **D6, D7: what the controller defines is what it finds**, and a consumer deleted or a stream
// redefined is said — against a real bus, raised by the same derivation the controller starts with.

// **S9 hears the bus**: a consumer that gives up on a message, and one deleted, as the server says.

// **D10 compares a node-engine with what it is delivered as, not with its commit** (2026-10-06: every
// machine read as behind right after a push sent it the current build — it says the digest-named
// directory it runs from, and the mesh holds a commit).
func TestANodeEngineIsJudgedByTheVersionItIsDeliveredAs(t *testing.T) {
	m := catalogue.Manifest{Module: "mesh-host", Resources: []map[string]any{
		{"id": "launcher", "type": "file", "path": "/usr/lib/nox-mesh-host/launch"},
		{"id": "host", "type": "archive", "path": "/usr/lib/nox-mesh-host/versions/31045596c83a"},
		{"id": "unfilled", "type": "archive", "path": "/usr/lib/x/versions/${version}"},
	}}
	delivered := deliveredVersions(m)
	if !slices.Equal(delivered, []string{"31045596c83a"}) {
		t.Fatalf("%v", delivered)
	}
	commit := "1545b00a9f0c"
	for _, c := range []struct {
		reported string
		behind   bool
	}{
		{"31045596c83a", false}, // the live case: current, and was called behind
		{"0123456789ab", true},  // another delivery
		{"1545b00a", false},     // placed by hand, stamped with the commit
		{"", false},             // not said
	} {
		if got := engineBehind(c.reported, delivered, commit); got != c.behind {
			t.Errorf("%q behind = %v, want %v", c.reported, got, c.behind)
		}
	}
	if engineBehind("31045596c83a", nil, commit) {
		t.Error("behind a mesh that holds no delivered build")
	}
}

// **Every seat verb a probe calls is one it declares, and one the controller is granted** — derived
// from the registry, so a probe added with a question the bus would refuse fails here, not live.
func TestEverySeatVerbAProbeAsksIsGranted(t *testing.T) {
	granted, err := broker.PermissionsFor(broker.Principal{Kind: broker.KindController, PasswordHash: "x"})
	if err != nil {
		t.Fatal(err)
	}
	asked := 0
	for _, p := range probeRegistry {
		for _, v := range p.Asks {
			asked++
			subject := link.NodeSeatToolSubject(v.Seat, v.Verb, "anchor")
			if !slices.ContainsFunc(granted.Publish, func(pattern string) bool { return subjectMatches(pattern, subject) }) {
				t.Errorf("%s asks %s.%s and the controller may not publish %s", p.ID, v.Seat, v.Verb, subject)
			}
			if !slices.Contains(broker.VerbsTheSelfCheckAsks, v) {
				t.Errorf("%s asks %s.%s, which broker.VerbsTheSelfCheckAsks does not name", p.ID, v.Seat, v.Verb)
			}
		}
	}
	if asked == 0 {
		t.Fatal("no probe asks a seat verb: D8 lost its declaration")
	}
	// And a probe asking what it did not declare is refused before anything is sent.
	ctx := context.WithValue(t.Context(), probeAsksKey{}, probe{ID: "DX"})
	if _, err := askSeatTool(ctx, nil, "node-intrusion-prevention", "banned", "anchor"); err == nil ||
		!strings.Contains(err.Error(), "does not declare") {
		t.Fatalf("an undeclared question was asked: %v", err)
	}
}

// subjectMatches is the bus's matching of a permission pattern against a subject.
func subjectMatches(pattern, subject string) bool {
	p, s := strings.Split(pattern, "."), strings.Split(subject, ".")
	for i, tok := range p {
		if tok == ">" {
			return len(s) > i
		}
		if i >= len(s) || (tok != "*" && tok != s[i]) {
			return false
		}
	}
	return len(p) == len(s)
}