felhom-controller/controller/internal/stacks/installed_test.go

package stacks

import (
	"context"
	"fmt"
	"go/ast"
	"go/parser"
	"go/token"
	"io"
	"log"
	"os"
	"path/filepath"
	"runtime"
	"strings"
	"testing"
	"time"

	"gitea.dooplex.hu/admin/felhom-controller/internal/config"
	"gopkg.in/yaml.v3"
)

// Slice 1 (v0.233.0) — the box writes down what it ACTUALLY installed.
//
// Every assertion here reads app.yaml BACK OFF DISK and checks the entries, their count and their
// digests. "recordInstalledImages returned" proves nothing: the whole feature is a durable record.

// --- the docker seam ---

// fakeContainer is one scripted container: what `docker inspect` will say about it.
type fakeContainer struct {
	id      string
	ref     string
	imageID string
}

// scriptedInstalledDocker returns an execRunner that answers the recorder's three reads from canned data and
// never touches a daemon. It fails the test on an argv it does not recognise, so a change to the
// commands the recorder issues cannot pass silently.
func scriptedInstalledDocker(t *testing.T, psOut string, containers []fakeContainer, digests map[string]string) execRunner {
	t.Helper()
	return func(_ context.Context, _ string, _ []string, name string, args ...string) (string, error) {
		// Accept BOTH compose spellings — composeArgv emits `docker compose ps` or `docker-compose
		// ps` depending on the configured command, and the wiring tests use the latter.
		if name == "docker" && len(args) >= 1 && args[0] == "compose" {
			args = args[1:]
			name = "docker-compose"
		}
		switch {
		case name == "docker-compose" && len(args) >= 1 && args[0] == "ps":
			return psOut, nil
		case name == "docker" && len(args) >= 1 && args[0] == "inspect":
			var b strings.Builder
			for _, want := range args {
				for _, c := range containers {
					if c.id == want {
						fmt.Fprintf(&b, "%s%s%s%s%s\n", c.id, inspectSep, c.ref, inspectSep, c.imageID)
					}
				}
			}
			return b.String(), nil
		case name == "docker" && len(args) >= 2 && args[0] == "image" && args[1] == "inspect":
			var b strings.Builder
			for _, want := range args {
				if d, ok := digests[want]; ok {
					fmt.Fprintf(&b, "%s%s%s\n", want, inspectSep, d)
				}
			}
			return b.String(), nil
		}
		t.Fatalf("unexpected command in test: %s %v", name, args)
		return "", nil
	}
}

const threeServiceCompose = `services:
  web:
    image: lscr.io/linuxserver/bookstack:26.05.2
  db:
    image: mariadb:12.3
  cache:
    image: redis:7-alpine
volumes:
  bookstack_config:
`

// newInstalledManager builds a Manager over one real stack directory. Real FS, because the thing
// under test is a file write.
func newInstalledManager(t *testing.T, compose, appYAML string) (*Manager, string) {
	t.Helper()
	root := t.TempDir()
	dir := filepath.Join(root, "bookstack")
	if err := os.MkdirAll(dir, 0o755); err != nil {
		t.Fatal(err)
	}
	if err := os.WriteFile(filepath.Join(dir, "docker-compose.yml"), []byte(compose), 0o644); err != nil {
		t.Fatal(err)
	}
	if appYAML != "" {
		if err := os.WriteFile(filepath.Join(dir, "app.yaml"), []byte(appYAML), 0o600); err != nil {
			t.Fatal(err)
		}
	}
	cfg := &config.Config{}
	cfg.Paths.StacksDir = root
	m := &Manager{
		cfg:        cfg,
		logger:     log.New(io.Discard, "", 0),
		composeCmd: "docker compose",
		encKey:     []byte("0123456789abcdef0123456789abcdef"),
		stacks: map[string]*Stack{
			"bookstack": {Name: "bookstack", ComposePath: filepath.Join(dir, "docker-compose.yml"), Deployed: true},
		},
	}
	// Mirror ScanStacks: the in-memory stack carries the loaded app.yaml and the template's pins.
	m.stacks["bookstack"].AppConfig = LoadAppConfig(dir)
	if imgs, err := ParseComposeImages(filepath.Join(dir, "docker-compose.yml")); err == nil {
		m.stacks["bookstack"].TemplateImages = imgs
	}
	return m, dir
}

func readInstalled(t *testing.T, dir string) *AppConfig {
	t.Helper()
	b, err := os.ReadFile(filepath.Join(dir, "app.yaml"))
	if err != nil {
		t.Fatal(err)
	}
	cfg := &AppConfig{}
	if err := yaml.Unmarshal(b, cfg); err != nil {
		t.Fatal(err)
	}
	return cfg
}

const ndjsonPS = `{"ID":"aaa111","Name":"bookstack","Service":"web"}
{"ID":"bbb222","Name":"bookstack-db","Service":"db"}
{"ID":"ccc333","Name":"bookstack-cache","Service":"cache"}`

func threeContainers() ([]fakeContainer, map[string]string) {
	return []fakeContainer{
			{id: "aaa111", ref: "lscr.io/linuxserver/bookstack:26.05.2", imageID: "sha256:img-web"},
			{id: "bbb222", ref: "mariadb:12.3", imageID: "sha256:img-db"},
			{id: "ccc333", ref: "redis:7-alpine", imageID: "sha256:img-cache"},
		}, map[string]string{
			"sha256:img-web":   "lscr.io/linuxserver/bookstack@sha256:aaaaaaaa",
			"sha256:img-db":    "mariadb@sha256:bbbbbbbb",
			"sha256:img-cache": "redis@sha256:cccccccc",
		}
}

// --- GROUP A: one entry PER COMPOSE SERVICE, with digests ---

// TestGroupA_RecordsOneEntryPerService is the case that matters: a MULTI-container app. The wrong
// implementation records one entry for the whole stack, and it would pass any single-service test.
func TestGroupA_RecordsOneEntryPerService(t *testing.T) {
	m, dir := newInstalledManager(t, threeServiceCompose, "deployed: true\nenv: {}\n")
	cs, digs := threeContainers()
	m.installedExecFn = scriptedInstalledDocker(t, ndjsonPS, cs, digs)

	before := time.Now().UTC().Add(-time.Second)
	m.recordInstalledImages("bookstack", dir, nil)

	got := readInstalled(t, dir).InstalledImages
	if len(got) != 3 {
		t.Fatalf("recorded %d entries, want ONE PER COMPOSE SERVICE (3): %+v", len(got), got)
	}
	want := map[string][2]string{
		"web":   {"lscr.io/linuxserver/bookstack:26.05.2", "sha256:aaaaaaaa"},
		"db":    {"mariadb:12.3", "sha256:bbbbbbbb"},
		"cache": {"redis:7-alpine", "sha256:cccccccc"},
	}
	for svc, w := range want {
		e, ok := got[svc]
		if !ok {
			t.Fatalf("service %q missing — entries must be keyed by COMPOSE SERVICE NAME, got %+v", svc, got)
		}
		if e.Ref != w[0] {
			t.Errorf("%s ref = %q, want %q", svc, e.Ref, w[0])
		}
		if e.Digest != w[1] {
			t.Errorf("%s digest = %q, want %q — the digest is the only identifier that cannot lie", svc, e.Digest, w[1])
		}
		ts, err := time.Parse(time.RFC3339, e.At)
		if err != nil {
			t.Errorf("%s at = %q, not RFC3339: %v", svc, e.At, err)
		} else if ts.Before(before) {
			t.Errorf("%s at = %v, older than the run that produced it", svc, ts)
		}
	}
	// The record must NOT have been assembled from the compose file: prove it by checking the
	// deployed marker survived the copy-and-overlay save.
	if !readInstalled(t, dir).Deployed {
		t.Error("the save dropped deployed=true — SaveAppConfig must stay copy-and-overlay")
	}
}

// TestGroupA_ImageWithNoRepoDigestRecordsAnEmptyDigest — a locally built or imported image has no
// RepoDigests. The entry is still recorded, with an empty digest: skipping it would silently lose a
// service from the record.
func TestGroupA_ImageWithNoRepoDigestRecordsAnEmptyDigest(t *testing.T) {
	m, dir := newInstalledManager(t, "services:\n  web:\n    image: local/built:dev\n", "deployed: true\nenv: {}\n")
	m.installedExecFn = scriptedInstalledDocker(t,
		`{"ID":"aaa111","Name":"w","Service":"web"}`,
		[]fakeContainer{{id: "aaa111", ref: "local/built:dev", imageID: "sha256:local"}},
		map[string]string{"sha256:local": ""})

	m.recordInstalledImages("app", dir, nil)
	got := readInstalled(t, dir).InstalledImages
	if len(got) != 1 {
		t.Fatalf("an image with no repo digest must still be RECORDED, got %+v", got)
	}
	if got["web"].Ref != "local/built:dev" || got["web"].Digest != "" {
		t.Fatalf("want ref recorded and digest empty, got %+v", got["web"])
	}
}

// TestGroupA_MissingContainerRecordsWhatExists — the edge-case table: record what is there, and say
// the count out loud. A partial record written silently would read as a complete answer.
func TestGroupA_MissingContainerRecordsWhatExists(t *testing.T) {
	var logs strings.Builder
	m, dir := newInstalledManager(t, threeServiceCompose, "deployed: true\nenv: {}\n")
	m.logger = log.New(&logs, "", 0)
	cs, digs := threeContainers()
	m.installedExecFn = scriptedInstalledDocker(t,
		`{"ID":"aaa111","Name":"bookstack","Service":"web"}
{"ID":"bbb222","Name":"bookstack-db","Service":"db"}`, cs, digs)

	m.recordInstalledImages("bookstack", dir, nil)
	got := readInstalled(t, dir).InstalledImages
	if len(got) != 2 {
		t.Fatalf("want the 2 observed services recorded, got %+v", got)
	}
	if !strings.Contains(logs.String(), "recorded 2 of 3") || !strings.Contains(logs.String(), "cache") {
		t.Fatalf("a partial read must be said out loud, naming what is missing. Log was:\n%s", logs.String())
	}
}

// --- GROUP B: the record follows the CONTAINER, not the file ---

// TestGroupB_RecordFollowsTheContainerNotTheFile is the reason this feature exists. The compose file
// and the running container can disagree indefinitely (measured: SPIKE §3 — 25 minutes). Here the
// FILE says one thing and the CONTAINER another; the record must carry the container's answer.
//
// It also pins the re-record half of Scenario B: an existing record for the OLD image is replaced,
// not left standing. A record that goes stale is worse than none, because it will be trusted.
func TestGroupB_RecordFollowsTheContainerNotTheFile(t *testing.T) {
	const old = `deployed: true
env: {}
installed_images:
  web:
    ref: ghcr.io/alam00000/bentopdf:v2.8.5
    digest: sha256:oldoldold
    at: "2026-09-01T17:36:35Z"
`
	// The FILE pins v2.8.5 — exactly the post-sync state the spike measured.
	m, dir := newInstalledManager(t, "services:\n  web:\n    image: ghcr.io/alam00000/bentopdf:v2.8.5\n", old)
	// The CONTAINER runs v2.8.6.
	m.installedExecFn = scriptedInstalledDocker(t,
		`{"ID":"aaa111","Name":"bentopdf","Service":"web"}`,
		[]fakeContainer{{id: "aaa111", ref: "ghcr.io/alam00000/bentopdf:v2.8.6", imageID: "sha256:new"}},
		map[string]string{"sha256:new": "ghcr.io/alam00000/bentopdf@sha256:newnewnew"})

	m.recordInstalledImages("bentopdf", dir, nil)

	got := readInstalled(t, dir).InstalledImages["web"]
	if got.Ref != "ghcr.io/alam00000/bentopdf:v2.8.6" {
		t.Fatalf("ref = %q — the record must read the CONTAINER; the file is the value that has already moved", got.Ref)
	}
	if got.Digest != "sha256:newnewnew" {
		t.Fatalf("digest = %q, want the new one — a record that goes stale is worse than none", got.Digest)
	}
	if got.At == "2026-09-01T17:36:35Z" {
		t.Fatal("`at` must be re-stamped when the image CHANGES")
	}
}

// TestGroupB_UnchangedObservationDoesNotRewriteAppYAML — the SetDesiredState rule. app.yaml holds
// encrypted secrets; rewriting it on every restart for no new information is pure risk. `at` is
// therefore also carried forward, so it answers "running since" and not "last looked at".
func TestGroupB_UnchangedObservationDoesNotRewriteAppYAML(t *testing.T) {
	const same = `deployed: true
env: {}
installed_images:
  web:
    ref: nginx:1.27
    digest: sha256:keepme
    at: "2026-08-01T00:00:00Z"
`
	m, dir := newInstalledManager(t, "services:\n  web:\n    image: nginx:1.27\n", same)
	m.installedExecFn = scriptedInstalledDocker(t,
		`{"ID":"aaa111","Name":"n","Service":"web"}`,
		[]fakeContainer{{id: "aaa111", ref: "nginx:1.27", imageID: "sha256:i"}},
		map[string]string{"sha256:i": "nginx@sha256:keepme"})

	path := filepath.Join(dir, "app.yaml")
	st0, err := os.Stat(path)
	if err != nil {
		t.Fatal(err)
	}
	m.recordInstalledImages("app", dir, nil)
	st1, err := os.Stat(path)
	if err != nil {
		t.Fatal(err)
	}
	if !st0.ModTime().Equal(st1.ModTime()) || st0.Size() != st1.Size() {
		t.Error("an unchanged observation must not rewrite app.yaml")
	}
	if got := readInstalled(t, dir).InstalledImages["web"].At; got != "2026-08-01T00:00:00Z" {
		t.Errorf("at = %q — the first-seen timestamp must be carried forward, not re-stamped", got)
	}
}

// --- GROUP C: recording fails, the ACTION still succeeds ---

// TestGroupC_UnwritableAppYAMLDoesNotFailTheAction is the deliberate opposite of SetDesiredState.
// `desired_state` is INTENT and a failed write correctly refuses the act. `installed_images` is an
// OBSERVATION: refusing to restart a customer's app because we could not write down which version it
// is would trade a real outage for a bookkeeping gap.
//
// COMPANION RED-PROOF (run 2026-09-02): give recordInstalledImages an `error` return and make
// RestartStack `return` it on failure. This test then fails with "restart must SUCCEED" — i.e. the
// customer's app refuses to start because a note could not be written. Reverted.
func TestGroupC_UnwritableAppYAMLDoesNotFailTheAction(t *testing.T) {
	if os.Getuid() == 0 {
		t.Skip("root ignores directory permissions — this test cannot make a write fail")
	}
	var logs strings.Builder
	m, dir := newInstalledManager(t, "services:\n  web:\n    image: nginx:1.27\n", "deployed: true\nenv: {}\n")
	m.logger = log.New(&logs, "", 0)
	m.installedExecFn = scriptedInstalledDocker(t,
		`{"ID":"aaa111","Name":"n","Service":"web"}`,
		[]fakeContainer{{id: "aaa111", ref: "nginx:1.27", imageID: "sha256:i"}},
		map[string]string{"sha256:i": "nginx@sha256:d"})
	withFakeCompose(t, m)

	// Read-only stack dir: SaveAppConfig's tmp+rename cannot create its temp file.
	if err := os.Chmod(dir, 0o555); err != nil {
		t.Fatal(err)
	}
	t.Cleanup(func() { _ = os.Chmod(dir, 0o755) })

	if err := m.RestartStack("bookstack"); err != nil {
		t.Fatalf("restart must SUCCEED even when the record cannot be written: %v", err)
	}
	out := logs.String()
	if !strings.Contains(out, "[ERROR]") || !strings.Contains(out, "installed-images bookstack") {
		t.Fatalf("the failure must be logged at ERROR, naming the app. Log was:\n%s", out)
	}
	if !strings.Contains(out, "unaffected") {
		t.Errorf("the ERROR line should say the app is unaffected, so it is not read as an outage. Log was:\n%s", out)
	}
}

// --- GROUP E: the WIRING — reached through the REAL caller ---

// withFakeCompose puts a stub `docker-compose` on PATH and points the manager at it, so a REAL
// RestartStack can run to completion without a docker daemon. It is the compose process boundary
// that is faked, not the recorder — the recorder is reached exactly as production reaches it.
func withFakeCompose(t *testing.T, m *Manager) {
	t.Helper()
	if runtime.GOOS != "linux" {
		t.Skip("the stub compose binary is a shell script")
	}
	bin := t.TempDir()
	script := "#!/bin/sh\nexit 0\n"
	if err := os.WriteFile(filepath.Join(bin, "docker-compose"), []byte(script), 0o755); err != nil {
		t.Fatal(err)
	}
	t.Setenv("PATH", bin+string(os.PathListSeparator)+os.Getenv("PATH"))
	m.composeCmd = "docker-compose"
	// refreshStatusLocked's `docker ps` — the OTHER, pre-existing seam.
	m.execFn = func(string, ...string) (string, error) { return "", nil }
}

// TestGroupE_RestartStackReachesTheRecorder is the seam-discipline test. Three shipped defects in
// three days were injected-seam tests that proved a component whose caller never invoked it, so at
// least one test must reach recordInstalledImages through a REAL production caller. RestartStack is
// invoked here in full; only the compose and `docker ps` process boundaries are stubbed.
func TestGroupE_RestartStackReachesTheRecorder(t *testing.T) {
	m, dir := newInstalledManager(t, "services:\n  web:\n    image: nginx:1.27\n", "deployed: true\nenv: {}\n")
	m.installedExecFn = scriptedInstalledDocker(t,
		`{"ID":"aaa111","Name":"n","Service":"web"}`,
		[]fakeContainer{{id: "aaa111", ref: "nginx:1.27", imageID: "sha256:i"}},
		map[string]string{"sha256:i": "nginx@sha256:wired"})
	withFakeCompose(t, m)

	if err := m.RestartStack("bookstack"); err != nil {
		t.Fatalf("restart: %v", err)
	}
	got := readInstalled(t, dir).InstalledImages
	if len(got) != 1 || got["web"].Digest != "sha256:wired" {
		t.Fatalf("RestartStack did not reach the recorder — app.yaml holds %+v", got)
	}
	// And the in-memory view is in step, so the badge does not lag a ScanStacks behind the file.
	if s, ok := m.GetStack("bookstack"); !ok || s.AppConfig == nil || s.AppConfig.InstalledImages["web"].Digest != "sha256:wired" {
		t.Error("the in-memory AppConfig must be updated too")
	}
}

// TestGroupE_EveryBringUpPathCallsTheRecorder walks the AST of the production sources for the four
// paths that cannot each be driven to completion from a unit test.
//
// An AST walk, NOT a strings.Contains: a commented-out call still contains the string, and that is
// exactly the shape a "seam built but never wired" defect takes. It also asserts the NEGATIVE —
// StartStackServices must NOT call it, because that path starts only the database service for the
// R-47 window and would overwrite a complete record with an incomplete one.
func TestGroupE_EveryBringUpPathCallsTheRecorder(t *testing.T) {
	callers := map[string]bool{} // enclosing func name -> calls recordInstalledImages
	fset := token.NewFileSet()
	for _, src := range []string{"manager.go", "deploy.go"} {
		f, err := parser.ParseFile(fset, src, nil, 0)
		if err != nil {
			t.Fatal(err)
		}
		for _, d := range f.Decls {
			fn, ok := d.(*ast.FuncDecl)
			if !ok {
				continue
			}
			found := false
			ast.Inspect(fn.Body, func(n ast.Node) bool {
				call, ok := n.(*ast.CallExpr)
				if !ok {
					return true
				}
				if sel, ok := call.Fun.(*ast.SelectorExpr); ok && sel.Sel.Name == "recordInstalledImages" {
					found = true
				}
				return true
			})
			if found {
				callers[fn.Name.Name] = true
			}
		}
	}
	for _, want := range []string{"StartStack", "RestartStack", "UpdateStack", "runComposeDeploy"} {
		if !callers[want] {
			t.Errorf("%s does not call recordInstalledImages — a bring-up path that records nothing leaves a stale record standing", want)
		}
	}
	if callers["StartStackServices"] {
		t.Error("StartStackServices must NOT record: it starts only the DB service for the R-47 window, and a partial record would overwrite a complete one")
	}
}

// --- parsing units ---

func TestParseComposePS_BothShapes(t *testing.T) {
	arr := `[{"ID":"a","Name":"n1","Service":"web"},{"ID":"b","Name":"n2","Service":"db"}]`
	for name, in := range map[string]string{"ndjson": ndjsonPS, "array": arr} {
		got, err := parseComposePS(in)
		if err != nil {
			t.Fatalf("%s: %v", name, err)
		}
		if len(got) < 2 || got[0].Service == "" {
			t.Fatalf("%s: parsed %+v", name, got)
		}
	}
	if got, err := parseComposePS("   "); err != nil || got != nil {
		t.Errorf("empty output must be an empty list, not an error: %v %v", got, err)
	}
	if _, err := parseComposePS("not json"); err == nil {
		t.Error("unparseable output must be an ERROR — cannot-tell must never read as no-containers")
	}
}

func TestPickDigestAndRefRepository(t *testing.T) {
	cases := []struct{ ref, digests, want string }{
		{"mariadb:12.3", "mariadb@sha256:aaa", "sha256:aaa"},
		{"mariadb:12.3", "", ""},
		// Two repos, same bytes: pick the one this app's ref names, never the other.
		{"mariadb:12.3", "mirror.example/mariadb@sha256:zzz mariadb@sha256:aaa", "sha256:aaa"},
		// A registry PORT is not a tag.
		{"registry:5000/app:1.2", "registry:5000/app@sha256:bbb", "sha256:bbb"},
		// Sole entry, repo does not match: fall back rather than lose the digest.
		{"weird:1", "other@sha256:ccc", "sha256:ccc"},
		// Several unrelated entries and none matches: give up rather than guess.
		{"weird:1", "a@sha256:1 b@sha256:2", ""},
	}
	for _, c := range cases {
		if got := pickDigest(c.ref, c.digests); got != c.want {
			t.Errorf("pickDigest(%q, %q) = %q, want %q", c.ref, c.digests, got, c.want)
		}
	}
	if got := refRepository("registry:5000/app:1.2"); got != "registry:5000/app" {
		t.Errorf("refRepository dropped a registry port: %q", got)
	}
}

// TestParseComposeImages_RealYAMLParse pins the reason this is not a line scan: immich's top-level
// volume keys have exactly the shape a naive scan misreads as a service.
func TestParseComposeImages_RealYAMLParse(t *testing.T) {
	dir := t.TempDir()
	p := filepath.Join(dir, "docker-compose.yml")
	body := `services:
  immich-server:
    image: ghcr.io/immich-app/immich-server:v2.0.1
  immich-db:
    image: ghcr.io/immich-app/postgres:16
volumes:
  immich_ml_cache:
  immich_postgres_data:
`
	if err := os.WriteFile(p, []byte(body), 0o644); err != nil {
		t.Fatal(err)
	}
	got, err := ParseComposeImages(p)
	if err != nil {
		t.Fatal(err)
	}
	if len(got) != 2 {
		t.Fatalf("parsed %d services, want 2 — a top-level volume key is NOT a service: %+v", len(got), got)
	}
	if _, err := ParseComposeImages(filepath.Join(dir, "nope.yml")); err == nil {
		t.Error("an unreadable file must be an ERROR — cannot-tell must never read as no-images")
	}
}