felhom-controller/controller/internal/bootstrap/drift_test.go

package bootstrap

import (
	"bytes"
	"encoding/json"
	"io"
	"log"
	"os"
	"path/filepath"
	"strings"
	"testing"

	"gitea.dooplex.hu/admin/felhom-controller/internal/config"
)

// R-77 endpoint-drift detection. The outage this guards is DIAG-agent-channel-2026-07-26: the island
// migration rewrote bootstrap.json, controller.yaml kept the pre-island LAN address, and the fleet's
// controllers dialled the wrong host for 17.5 h while alerting only "agent unreachable".

const driftYAML = `customer:
    id: demo-hp
local_api:
    endpoint: %ENDPOINT%
    fingerprint: aaaa1111
    token: tok-secret
`

// writeDriftFixture lays out a controller.yaml + bootstrap.json pair and points Path() at the latter.
func writeDriftFixture(t *testing.T, cfgEndpoint, bsEndpoint, bsFingerprint, bsToken string) (cfgPath string, cfg *config.Config) {
	t.Helper()
	dir := t.TempDir()
	cfgPath = filepath.Join(dir, "controller.yaml")
	if err := os.WriteFile(cfgPath, []byte(strings.ReplaceAll(driftYAML, "%ENDPOINT%", cfgEndpoint)), 0o600); err != nil {
		t.Fatal(err)
	}
	bsPath := filepath.Join(dir, "bootstrap.json")
	b := Bootstrap{}
	b.LocalAPI = BootstrapLocalAPI{Endpoint: bsEndpoint, Fingerprint: bsFingerprint, Token: bsToken}
	raw, _ := json.Marshal(b)
	if err := os.WriteFile(bsPath, raw, 0o600); err != nil {
		t.Fatal(err)
	}
	t.Setenv("FELHOM_BOOTSTRAP_PATH", bsPath)

	var err error
	cfg, err = config.LoadPermissive(cfgPath)
	if err != nil {
		t.Fatal(err)
	}
	return cfgPath, cfg
}

func sha(t *testing.T, p string) []byte {
	t.Helper()
	b, err := os.ReadFile(p)
	if err != nil {
		t.Fatal(err)
	}
	return b
}

// Scenario A — drift is DETECTED, NAMED, and nothing is written.
//
// The "nothing is written" half is the load-bearing assertion: auto-reconcile is R-78 and would
// clobber a working channel on any guest whose controller.yaml is the correct one. "An error was
// logged" alone would be a hollow test.
func TestScenarioA_DriftDetectedAndNamed_NoWrite(t *testing.T) {
	cfgPath, cfg := writeDriftFixture(t,
		"192.168.0.87:8443",  // the live demo-hp value
		"169.254.253.1:8443", // the island value the migration wrote
		"aaaa1111", "tok-secret")
	before := sha(t, cfgPath)

	var buf bytes.Buffer
	d := DetectEndpointDrift(cfgPath, cfg, log.New(&buf, "", 0))

	if d == nil {
		t.Fatal("drift must be DETECTED — this is the exact live shape from the 2026-07-25 outage")
	}
	if d.ConfigEndpoint != "192.168.0.87:8443" || d.BootstrapEndpoint != "169.254.253.1:8443" {
		t.Errorf("wrong values captured: %+v", d)
	}
	if !d.FingerprintAgrees {
		t.Error("fingerprints are identical in this fixture — must report agreement")
	}

	// The log line alone must diagnose it: BOTH values AND BOTH paths.
	logged := buf.String()
	for _, want := range []string{"192.168.0.87:8443", "169.254.253.1:8443", cfgPath, "bootstrap.json", "ERROR"} {
		if !strings.Contains(logged, want) {
			t.Errorf("the ERROR line must contain %q; got:\n%s", want, logged)
		}
	}
	// Never log a secret.
	if strings.Contains(logged, "tok-secret") {
		t.Error("the token must NEVER be logged")
	}

	// THE assertion: controller.yaml is byte-identical.
	if after := sha(t, cfgPath); !bytes.Equal(before, after) {
		t.Errorf("controller.yaml was MODIFIED — detection must never write (that is R-78)\nbefore:\n%s\nafter:\n%s", before, after)
	}
}

// Scenario B — agreement is silent. A spurious alert on every healthy boot would be worse than the
// bug: it trains the operator to ignore the banner.
func TestScenarioB_AgreementIsSilent(t *testing.T) {
	cfgPath, cfg := writeDriftFixture(t, "169.254.253.1:8443", "169.254.253.1:8443", "aaaa1111", "tok-secret")
	before := sha(t, cfgPath)
	var buf bytes.Buffer
	if d := DetectEndpointDrift(cfgPath, cfg, log.New(&buf, "", 0)); d != nil {
		t.Errorf("matching endpoints must not report drift: %+v", d)
	}
	if strings.Contains(buf.String(), "ERROR") {
		t.Errorf("no ERROR on agreement; got: %s", buf.String())
	}
	if after := sha(t, cfgPath); !bytes.Equal(before, after) {
		t.Error("controller.yaml must not be touched")
	}
}

// Scenario D — an absent / unparseable / incomplete bootstrap is NOT drift. An unprovisioned or
// legacy guest must stay silent, not alarm.
func TestScenarioD_IncompleteBootstrapIsFailSafe(t *testing.T) {
	t.Run("bootstrap absent", func(t *testing.T) {
		cfgPath, cfg := writeDriftFixture(t, "192.168.0.87:8443", "169.254.253.1:8443", "aaaa1111", "tok")
		os.Remove(os.Getenv("FELHOM_BOOTSTRAP_PATH"))
		if d := DetectEndpointDrift(cfgPath, cfg, log.New(io.Discard, "", 0)); d != nil {
			t.Errorf("a missing bootstrap is not drift: %+v", d)
		}
	})
	t.Run("bootstrap unparseable", func(t *testing.T) {
		cfgPath, cfg := writeDriftFixture(t, "192.168.0.87:8443", "169.254.253.1:8443", "aaaa1111", "tok")
		os.WriteFile(os.Getenv("FELHOM_BOOTSTRAP_PATH"), []byte("{not json"), 0o600)
		if d := DetectEndpointDrift(cfgPath, cfg, log.New(io.Discard, "", 0)); d != nil {
			t.Errorf("an unparseable bootstrap is not drift: %+v", d)
		}
	})
	// Incomplete = any of endpoint/fingerprint/token empty — the same completeness bar ensureLocalAPI
	// applies before it will merge.
	for _, tc := range []struct{ name, ep, fp, tok string }{
		{"no endpoint", "", "aaaa1111", "tok"},
		{"no fingerprint", "169.254.253.1:8443", "", "tok"},
		{"no token", "169.254.253.1:8443", "aaaa1111", ""},
	} {
		t.Run(tc.name, func(t *testing.T) {
			cfgPath, cfg := writeDriftFixture(t, "192.168.0.87:8443", tc.ep, tc.fp, tc.tok)
			if d := DetectEndpointDrift(cfgPath, cfg, log.New(io.Discard, "", 0)); d != nil {
				t.Errorf("an incomplete bootstrap is not drift: %+v", d)
			}
		})
	}
	t.Run("controller.yaml has no endpoint — that is the fill-if-missing path, not drift", func(t *testing.T) {
		cfgPath, cfg := writeDriftFixture(t, `""`, "169.254.253.1:8443", "aaaa1111", "tok")
		if cfg.LocalAPI.Endpoint != "" {
			t.Skipf("fixture did not produce an empty endpoint (got %q)", cfg.LocalAPI.Endpoint)
		}
		if d := DetectEndpointDrift(cfgPath, cfg, log.New(io.Discard, "", 0)); d != nil {
			t.Errorf("an absent local_api endpoint is ensureLocalAPI's job, not drift: %+v", d)
		}
	})
	t.Run("nil cfg", func(t *testing.T) {
		if d := DetectEndpointDrift("/nonexistent", nil, log.New(io.Discard, "", 0)); d != nil {
			t.Error("nil cfg must be silent")
		}
	})
}

// A moved PIN alongside a moved address is a materially different failure — fixing the endpoint
// alone would then fail closed on the pin. It must be surfaced, as a boolean, never as a value.
func TestDrift_FingerprintDisagreementIsSurfacedNotLeaked(t *testing.T) {
	cfgPath, cfg := writeDriftFixture(t, "192.168.0.87:8443", "169.254.253.1:8443", "bbbb2222", "tok-secret")
	var buf bytes.Buffer
	d := DetectEndpointDrift(cfgPath, cfg, log.New(&buf, "", 0))
	if d == nil {
		t.Fatal("drift expected")
	}
	if d.FingerprintAgrees {
		t.Error("fingerprints differ in this fixture — must report DISagreement")
	}
	for _, secret := range []string{"aaaa1111", "bbbb2222", "tok-secret"} {
		if strings.Contains(buf.String(), secret) {
			t.Errorf("a fingerprint/token value leaked into the log: %q", secret)
		}
		if strings.Contains(d.EnglishMessage(), secret) {
			t.Errorf("a fingerprint/token value leaked into the operator message: %q", secret)
		}
	}
	if !strings.Contains(d.EnglishMessage(), "false") {
		t.Errorf("the operator message must carry the pin-agreement boolean: %q", d.EnglishMessage())
	}
}

// Scenario C — the fill-if-missing path is untouched by any of this (it is the ONLY writer).
func TestScenarioC_AbsentBlockStillMerges(t *testing.T) {
	dir := t.TempDir()
	cfgPath := filepath.Join(dir, "controller.yaml")
	if err := os.WriteFile(cfgPath, []byte("customer:\n    id: demo-hp\n"), 0o600); err != nil {
		t.Fatal(err)
	}
	bsPath := filepath.Join(dir, "bootstrap.json")
	b := Bootstrap{}
	b.LocalAPI = BootstrapLocalAPI{Endpoint: "169.254.253.1:8443", Fingerprint: "aaaa1111", Token: "tok"}
	raw, _ := json.Marshal(b)
	os.WriteFile(bsPath, raw, 0o600)
	t.Setenv("FELHOM_BOOTSTRAP_PATH", bsPath)

	cfg, err := config.LoadPermissive(cfgPath)
	if err != nil {
		t.Fatal(err)
	}
	if cfg.LocalAPI.Endpoint != "" {
		t.Fatalf("precondition: fixture should have no local_api, got %q", cfg.LocalAPI.Endpoint)
	}
	got := ensureLocalAPI(cfgPath, cfg, log.New(io.Discard, "", 0))
	if got == nil || got.LocalAPI.Endpoint != "169.254.253.1:8443" {
		t.Fatalf("the fill-if-missing merge must still work; got %+v", got)
	}
	// And the drift check stays silent on the now-merged config.
	if d := DetectEndpointDrift(cfgPath, got, log.New(io.Discard, "", 0)); d != nil {
		t.Errorf("after a successful merge the two files agree — no drift: %+v", d)
	}
}