felhom-controller/controller/internal/web/intermediary_test.go

package web

import (
	"testing"
	"time"

	"gitea.dooplex.hu/admin/felhom-controller/internal/agentapi"
	"gitea.dooplex.hu/admin/felhom-controller/internal/settings"

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

func TestAgentWhere(t *testing.T) {
	cases := map[string]string{
		"/mnt/felhom-drives/felhom-usb": "/mnt/felhom-usb", // stable → raw
		"/mnt/felhom-usb":               "/mnt/felhom-usb", // legacy raw → raw (idempotent)
		"/mnt/felhom-drives/x":          "/mnt/x",
	}
	for in, want := range cases {
		if got := agentWhere(in); got != want {
			t.Errorf("agentWhere(%q) = %q, want %q", in, got, want)
		}
	}
}

// TestShouldRecreateOnBoot pins the boot-id recreate decision on BOTH axes it must get right at once:
// recreate every deployed drive-backed present app that still HAS containers, independent of what
// STATE those containers are in.
//
// COMPANION GUARD 1 (state must NOT filter): the pre-fix logic (the old `stackStartedRecently`, and
// even a `State!=stopped` filter) MISSED an app that was Stopped/Exited at the one-shot instant —
// docker hadn't auto-restarted it yet after the boot. The exited/stopped cases below are `true`: a
// state-filtered impl returns false for them and the app stays down (exactly what happened live: 5
// apps exited after a host reboot).
//
// COMPANION GUARD 2 (R-55: containers MUST filter): an impl that ignores `hasContainers` resurrects
// an app the customer deliberately stopped, on every guest reboot. The zero-container cases below are
// `false`; the pre-R-55 impl returns true for them (proven live: immich, stopped from the UI seconds
// earlier, came back running).
//
// The two guards pull in opposite directions on purpose — that is the whole difficulty of this gate.
// `state` and `hasContainers` are DIFFERENT questions: "is it up right now" vs "does docker still
// have records of it", and only the second survives a reboot as a statement of intent.
func TestShouldRecreateOnBoot(t *testing.T) {
	const flash = "/mnt/felhom-drives/felhom-flash"
	present := map[string]bool{flash: true}
	cases := []struct {
		name          string
		deployed      bool
		hdd           string
		hasContainers bool
		want          bool
	}{
		// --- has containers: recreate regardless of what state they are in (guard 1) ---
		{"deployed+present+containers (running)", true, flash, true, true},
		{"deployed+present+containers (exited after boot)", true, flash, true, true},
		{"deployed+present+containers (stuck create-time failure)", true, flash, true, true},

		// --- R-55: zero containers == `compose down` == the customer's Stop (guard 2) ---
		{"R-55 customer-stopped drive app (zero containers)", true, flash, false, false},
		{"R-55 gate-stopped app (zero containers; Return branch owns it)", true, flash, false, false},

		// --- the pre-existing axes, unchanged ---
		{"drive absent (gate handles)", true, "/mnt/felhom-drives/felhom-usb", true, false},
		{"SSD path never", true, "/mnt/sys_drive/felhom-data", true, false},
		{"app.yaml not deployed", false, flash, true, false},
		{"no HDD_PATH (SSD-resident)", true, "", true, false},
	}
	for _, c := range cases {
		if got := shouldRecreateOnBoot(c.deployed, c.hdd, present, c.hasContainers, stacks.DesiredStateUnknown); got != c.want {
			t.Errorf("%s: shouldRecreateOnBoot = %v, want %v", c.name, got, c.want)
		}
	}
}

// TestRecreateDriveBackedApps_HonoursCustomerStop is the R-55 regression at the driver level, and it
// separates the two reasons an app is not recreated — a conflated counter would fire a WARN about a
// missing drive bind for an app that is stopped exactly as the customer asked.
//
// COMPANION GUARD: drop `hasContainers` from the predicate and `immich` is recreated — the exact live
// defect (REPORT §4b). Drop the counter split and `leftStopped` reads 0 while `skipped` reads 2.
func TestRecreateDriveBackedApps_HonoursCustomerStop(t *testing.T) {
	const flash = "/mnt/felhom-drives/felhom-flash"
	present := map[string]bool{flash: true}
	stacks := []bootStack{
		// boot orphan: containers exist but are down → MUST be recreated.
		{name: "romm", deployed: true, hdd: flash, state: "exited", hasContainers: true},
		// customer pressed Stop → compose down → zero containers → MUST be left alone.
		{name: "immich", deployed: true, hdd: flash, state: "stopped", hasContainers: false},
		// drive-backed but the bind never went live → the drive gate's job, counted separately.
		{name: "stranded", deployed: true, hdd: "/mnt/felhom-drives/felhom-usb", hasContainers: true},
	}
	var recreated []string
	n, skipped, leftStopped := recreateDriveBackedApps(stacks, present,
		func(bs bootStack) { recreated = append(recreated, bs.name) }, func() {})

	if len(recreated) != 1 || recreated[0] != "romm" {
		t.Fatalf("recreated=%v, want exactly [romm] — a customer-stopped app must never be restarted", recreated)
	}
	for _, name := range recreated {
		if name == "immich" {
			t.Fatal("immich was stopped from the UI and was recreated anyway — R-55 regression")
		}
	}
	if n != 1 || skipped != 1 || leftStopped != 1 {
		t.Fatalf("recreated=%d skipped=%d leftStopped=%d, want 1/1/1 "+
			"(skipped = no live bind; leftStopped = honoured customer Stop — these must not be conflated)",
			n, skipped, leftStopped)
	}
}

// TestDefaultPromotionTarget pins M1 (never leave zero default).
//
// COMPANION GUARD: the pre-fix decommission blanked the default and promoted nothing — equivalent to this
// always returning ("", false). The "promote another" + "block when only drive" cases below fail that.
func TestDefaultPromotionTarget(t *testing.T) {
	flash := "/mnt/felhom-drives/felhom-flash"
	usb := "/mnt/felhom-drives/felhom-usb"
	// decommissioning a NON-default → no action.
	paths := []settings.StoragePath{{Path: flash, IsDefault: true, Schedulable: true}, {Path: usb, Schedulable: true}}
	if tgt, blk := defaultPromotionTarget(paths, usb, ""); tgt != "" || blk {
		t.Fatalf("non-default decommission: got (%q,%v), want (\"\",false)", tgt, blk)
	}
	// decommissioning the DEFAULT with another usable → promote it.
	if tgt, blk := defaultPromotionTarget(paths, flash, ""); tgt != usb || blk {
		t.Fatalf("default decommission: got (%q,%v), want (%q,false)", tgt, blk, usb)
	}
	// prefer the migrate target when valid.
	if tgt, _ := defaultPromotionTarget(paths, flash, usb); tgt != usb {
		t.Fatalf("should prefer migrate target %q, got %q", usb, tgt)
	}
	// the ONLY usable drive (other is decommissioned) → BLOCK.
	only := []settings.StoragePath{{Path: flash, IsDefault: true, Schedulable: true}, {Path: usb, Decommissioned: true}}
	if tgt, blk := defaultPromotionTarget(only, flash, ""); tgt != "" || !blk {
		t.Fatalf("only-drive decommission: got (%q,%v), want (\"\",true)", tgt, blk)
	}
}

// TestPollLiveBinds_WaitsForLateBind is the boot-race fix's core: the readiness gate must WAIT for the
// drive bind to actually go live (the agent re-binds it ~18s post-boot) and only THEN report it present,
// so shouldRecreateOnBoot fires and the create-time-failed app is recreated.
//
// COMPANION (must fail pre-fix): the old readiness was a SINGLE early sample of the agent's
// BoundUnderParent — taken before the ~18s rebind, so it read the bind ABSENT, recreated nothing, and
// burned the boot-id one-shot. TestSingleEarlySample_MissesLateBind_Companion pins that broken outcome;
// and if pollLiveBinds is reverted to a no-wait single check, this test fails its "did it wait" assertion.
func TestPollLiveBinds_WaitsForLateBind(t *testing.T) {
	flash := "/mnt/felhom-drives/felhom-flash"
	var nowT time.Duration // fake monotonic clock since boot
	now := func() time.Time { return time.Unix(0, 0).Add(nowT) }
	sleep := func(d time.Duration) { nowT += d }
	const goLive = 18 * time.Second // the real agent rebind lag
	bindLive := func(string) bool { return nowT >= goLive }

	live := pollLiveBinds([]string{flash}, bindLive, sleep, now, bootBindWait, bootBindPoll)

	if !live[flash] {
		t.Fatalf("poll must detect the bind once live; got %v", live)
	}
	if nowT < goLive { // proves it WAITED through the rebind window (a single sample would return at t=0)
		t.Fatalf("poll returned at t=%s before the bind went live at %s — it did not wait (regression)", nowT, goLive)
	}
	if !shouldRecreateOnBoot(true, flash, live, true, stacks.DesiredStateUnknown) {
		t.Fatalf("with the live bind present, the drive-backed app MUST be recreated")
	}
}

// TestSingleEarlySample_MissesLateBind_Companion is the explicit pre-fix companion: a single sample of
// the bind at boot (t=0), before the ~18s rebind, reads it ABSENT → the app is NOT recreated and stays
// Exited. This is exactly what stranded paperless-webserver et al. live.
func TestSingleEarlySample_MissesLateBind_Companion(t *testing.T) {
	flash := "/mnt/felhom-drives/felhom-flash"
	bindLiveAtBoot := func(string) bool { return false } // not yet live at the boot instant
	oldPresent := map[string]bool{flash: bindLiveAtBoot(flash)}
	if shouldRecreateOnBoot(true, flash, oldPresent, true, stacks.DesiredStateUnknown) {
		t.Fatalf("companion: a single early sample reads the not-yet-live bind as absent and must MISS it")
	}
}

// TestPollLiveBinds_TimeoutLeavesAbsent: a drive that never comes live within the window stays absent,
// so its apps are NOT recreated here (left to the normal drive gate) — no spurious recreate/loop.
func TestPollLiveBinds_TimeoutLeavesAbsent(t *testing.T) {
	usb := "/mnt/felhom-drives/felhom-usb"
	var nowT time.Duration
	now := func() time.Time { return time.Unix(0, 0).Add(nowT) }
	sleep := func(d time.Duration) { nowT += d }
	bindLive := func(string) bool { return false } // never live

	live := pollLiveBinds([]string{usb}, bindLive, sleep, now, bootBindWait, bootBindPoll)

	if live[usb] {
		t.Fatalf("a never-live bind must remain absent after the bounded wait")
	}
	if nowT < bootBindWait {
		t.Fatalf("poll must run to the deadline for an absent drive, t=%s", nowT)
	}
	if shouldRecreateOnBoot(true, usb, live, true, stacks.DesiredStateUnknown) {
		t.Fatalf("an absent drive's app must NOT be recreated here (the gate owns drive-absent)")
	}
}

// TestRecreateDriveBackedApps_SyncsFileBrowserAfterRecreate (Task B): FileBrowser must be re-synced
// AFTER the drive-backed apps are recreated (so it syncs against live binds). COMPANION: the pre-fix
// boot-recreate path never synced FileBrowser — red-proofed by dropping the syncFB() call.
func TestRecreateDriveBackedApps_SyncsFileBrowserAfterRecreate(t *testing.T) {
	flash := "/mnt/felhom-drives/felhom-flash"
	present := map[string]bool{flash: true}
	stacks := []bootStack{
		{name: "romm", deployed: true, hdd: flash, hasContainers: true},                                // drive-backed, live → recreate
		{name: "actualbudget", deployed: true, hdd: "/mnt/sys_drive/felhom-data", hasContainers: true}, // SSD → not recreated
		{name: "stranded", deployed: true, hdd: "/mnt/felhom-drives/felhom-usb", hasContainers: true},  // drive-backed, bind NOT live → skipped
	}
	var seq []string
	recreate := func(bs bootStack) { seq = append(seq, "recreate:"+bs.name) }
	syncFB := func() { seq = append(seq, "syncFB") }

	recreated, skipped, leftStopped := recreateDriveBackedApps(stacks, present, recreate, syncFB)

	if recreated != 1 || skipped != 1 || leftStopped != 0 {
		t.Fatalf("recreated=%d skipped=%d leftStopped=%d, want 1/1/0", recreated, skipped, leftStopped)
	}
	// FileBrowser sync MUST be invoked, and AFTER every recreate.
	if len(seq) != 2 || seq[0] != "recreate:romm" || seq[len(seq)-1] != "syncFB" {
		t.Fatalf("FileBrowser sync must run once, AFTER the recreate; seq=%v", seq)
	}
}

// TestRecreateDriveBackedApps_SyncsEvenWithNoRecreate: FileBrowser is re-synced to reflect the live
// binds even when no app needed recreating (so its mounts never go stale).
func TestRecreateDriveBackedApps_SyncsEvenWithNoRecreate(t *testing.T) {
	stacks := []bootStack{{name: "x", deployed: true, hdd: "/mnt/sys_drive/felhom-data"}} // SSD only
	synced := false
	recreateDriveBackedApps(stacks, map[string]bool{}, func(bootStack) { t.Fatal("should not recreate") }, func() { synced = true })
	if !synced {
		t.Fatal("FileBrowser sync must run even when nothing was recreated")
	}
}

func TestStablePathForName(t *testing.T) {
	if got := stablePathForName("felhom-usb"); got != "/mnt/felhom-drives/felhom-usb" {
		t.Errorf("stablePathForName = %q", got)
	}
}

// TestPlanDriveGates pins the gate's pure decision across the four meaningful states.
//
// COMPANION GUARD: a trivial impl that gates every absent path regardless of the disconnected flag would
// re-stop an already-disconnected drive (and never return it); one that ignores presence would never
// gate. Both fail here.
func TestPlanDriveGates(t *testing.T) {
	paths := []settings.StoragePath{
		{Path: "/mnt/felhom-drives/usb"},                        // present + connected → no action
		{Path: "/mnt/felhom-drives/flash"},                      // ABSENT + connected → STOP
		{Path: "/mnt/felhom-drives/back", Disconnected: true},   // present + disconnected → RETURN
		{Path: "/mnt/felhom-drives/gone", Disconnected: true},   // ABSENT + disconnected → no action (steady)
		{Path: "/mnt/felhom-drives/dead", Decommissioned: true}, // decommissioned → never touched
		{Path: "/mnt/sys_drive/felhom-data"},                    // INTERNAL SSD (absent from agent) → never gated
	}
	disks := []agentapi.DiskInfo{
		// present = BoundUnderParent (the usable-in-guest signal), not merely State==attached.
		{MountPath: "/mnt/usb", GuestPath: "/mnt/felhom-drives/usb", State: "attached", BoundUnderParent: true},
		{MountPath: "/mnt/back", GuestPath: "/mnt/felhom-drives/back", State: "attached", BoundUnderParent: true},
		// flash reports State=attached but NOT bound under parent yet → still treated ABSENT (the
		// reboot-ordering case: raw drive mounted, agent hasn't bound it under the parent yet).
		{MountPath: "/mnt/flash", GuestPath: "/mnt/felhom-drives/flash", State: "attached", BoundUnderParent: false},
		// gone + dead report NO present disk
	}
	actions := map[string]gateAction{}
	for _, a := range planDriveGates(paths, disks) {
		actions[a.Path] = a
	}
	if len(actions) != 2 {
		t.Fatalf("expected exactly 2 actions (stop flash, return back), got %d: %+v", len(actions), actions)
	}
	if a, ok := actions["/mnt/felhom-drives/flash"]; !ok || !a.Stop || a.Return {
		t.Errorf("flash should STOP (absent+connected): %+v", a)
	}
	if a, ok := actions["/mnt/felhom-drives/back"]; !ok || !a.Return || a.Stop || a.Raw != "/mnt/back" {
		t.Errorf("back should RETURN with raw /mnt/back (present+disconnected): %+v", a)
	}
	if _, gated := actions["/mnt/felhom-drives/usb"]; gated {
		t.Errorf("usb (present+connected) must not be gated")
	}
	if _, acted := actions["/mnt/felhom-drives/gone"]; acted {
		t.Errorf("gone (absent+already-disconnected) is steady — no action")
	}
	if _, acted := actions["/mnt/felhom-drives/dead"]; acted {
		t.Errorf("decommissioned drive must never be gated")
	}
	if _, acted := actions["/mnt/sys_drive/felhom-data"]; acted {
		t.Errorf("internal SSD/system path must NEVER be gated (only /mnt/felhom-drives/ externals)")
	}
}