feat(sense): add reconciliation safety controls [T-012]

2026-08-07 23:00:03 +08:00
parent 677ed732f7
commit 12857fdf32
35 changed files with 2817 additions and 124 deletions
@@ -0,0 +1,272 @@
+package orphan
+
+import (
+	"context"
+	"errors"
+	"sort"
+	"sync"
+	"testing"
+	"time"
+
+	"yovision/sense/internal/store"
+)
+
+type fakeLease struct {
+	owner, token string
+	expires      time.Time
+}
+
+type fakeRepository struct {
+	mu        sync.Mutex
+	leases    map[string]fakeLease
+	ownership []store.MediaPathOwnership
+	scans     map[string]store.OrphanScan
+	deleted   map[string]map[string]bool
+}
+
+func newFakeRepository() *fakeRepository {
+	return &fakeRepository{
+		leases: make(map[string]fakeLease), scans: make(map[string]store.OrphanScan),
+		deleted: make(map[string]map[string]bool),
+	}
+}
+
+func (f *fakeRepository) AcquireOperationalLease(
+	_ context.Context,
+	name, owner, token string,
+	now time.Time,
+	duration time.Duration,
+) (bool, error) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	current, exists := f.leases[name]
+	if exists && current.expires.After(now) && (current.owner != owner || current.token != token) {
+		return false, nil
+	}
+	f.leases[name] = fakeLease{owner: owner, token: token, expires: now.Add(duration)}
+	return true, nil
+}
+
+func (f *fakeRepository) ReleaseOperationalLease(
+	_ context.Context,
+	name, owner, token string,
+	now time.Time,
+) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	current := f.leases[name]
+	if current.owner == owner && current.token == token {
+		current.expires = now
+		f.leases[name] = current
+	}
+	return nil
+}
+
+func (f *fakeRepository) ListMediaPathOwnership(context.Context) ([]store.MediaPathOwnership, error) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return append([]store.MediaPathOwnership(nil), f.ownership...), nil
+}
+
+func (f *fakeRepository) SaveOrphanScan(
+	_ context.Context,
+	scan store.OrphanScan,
+	owner, token string,
+) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	lease := f.leases[store.OperationalLeaseOrphanScan]
+	if lease.owner != owner || lease.token != token || !lease.expires.After(scan.CompletedAt) {
+		return store.ErrOperationalLeaseLost
+	}
+	f.scans[scan.ID] = cloneScan(scan)
+	lease.expires = scan.CompletedAt
+	f.leases[store.OperationalLeaseOrphanScan] = lease
+	return nil
+}
+
+func (f *fakeRepository) GetOrphanScan(_ context.Context, id string) (store.OrphanScan, error) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	scan, exists := f.scans[id]
+	if !exists {
+		return store.OrphanScan{}, store.ErrOrphanScanNotFound
+	}
+	result := cloneScan(scan)
+	for index := range result.Findings {
+		result.Findings[index].Deleted = f.deleted[id][result.Findings[index].PathName]
+	}
+	return result, nil
+}
+
+func (f *fakeRepository) RecordOrphanCleanup(
+	_ context.Context,
+	scanID, pathName, _, status, _ string,
+	_ time.Time,
+) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	if f.deleted[scanID] == nil {
+		f.deleted[scanID] = make(map[string]bool)
+	}
+	if status == "deleted" {
+		f.deleted[scanID][pathName] = true
+	}
+	return nil
+}
+
+func cloneScan(value store.OrphanScan) store.OrphanScan {
+	value.Findings = append([]store.OrphanFinding(nil), value.Findings...)
+	return value
+}
+
+type fakeRuntime struct {
+	paths   map[string]bool
+	fail    map[string]bool
+	deleted []string
+}
+
+func (f *fakeRuntime) ListPathNames(context.Context) ([]string, error) {
+	values := make([]string, 0, len(f.paths))
+	for path, present := range f.paths {
+		if present {
+			values = append(values, path)
+		}
+	}
+	sort.Strings(values)
+	return values, nil
+}
+
+func (f *fakeRuntime) DeletePath(_ context.Context, path string) error {
+	if f.fail[path] {
+		return errors.New("redacted media failure")
+	}
+	delete(f.paths, path)
+	f.deleted = append(f.deleted, path)
+	return nil
+}
+
+func TestSafetyGateUsesExactTenPercentBoundary(t *testing.T) {
+	t.Parallel()
+	if allowed, reason := safetyGate(1, 10); !allowed || reason != "allowed" {
+		t.Fatalf("exact 10%% boundary was rejected: %v %s", allowed, reason)
+	}
+	if allowed, reason := safetyGate(1, 9); allowed || reason != "ratio_exceeded" {
+		t.Fatalf("more than 10%% was accepted: %v %s", allowed, reason)
+	}
+	if allowed, reason := safetyGate(129, 2000); allowed || reason != "scope_exceeded" {
+		t.Fatalf("129-item scope was accepted: %v %s", allowed, reason)
+	}
+}
+
+func TestReportClassifiesOwnershipAndApplyNeverDeletesUnowned(t *testing.T) {
+	repository := newFakeRepository()
+	repository.ownership = []store.MediaPathOwnership{
+		{PathName: "owned-stale", DeviceID: "old-device"},
+		{PathName: "owned-current", DeviceID: "live-device", CurrentClaim: true},
+	}
+	runtime := &fakeRuntime{paths: map[string]bool{
+		"owned-stale": true, "owned-current": true,
+		"unowned-1": true, "unowned-2": true, "unowned-3": true, "unowned-4": true,
+		"unowned-5": true, "unowned-6": true, "unowned-7": true, "unowned-8": true,
+	}, fail: make(map[string]bool)}
+	now := time.Date(2026, 8, 7, 0, 0, 0, 0, time.UTC)
+	manager := New(repository, runtime, "ins_test", nil)
+	manager.now = func() time.Time { return now }
+	scan, err := manager.Report(context.Background())
+	if err != nil {
+		t.Fatal(err)
+	}
+	if scan.ObservedCount != 10 || scan.OwnedStaleCount != 1 || scan.UnownedCount != 8 || !scan.SafetyAllowed {
+		t.Fatalf("unexpected report: %+v", scan)
+	}
+	result, err := manager.Apply(
+		context.Background(), scan.ID, "operator-1", Confirmation(scan.ID),
+	)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if result.Deleted != 1 || len(runtime.deleted) != 1 || runtime.deleted[0] != "owned-stale" {
+		t.Fatalf("cleanup escaped owned stale set: result=%+v deleted=%v", result, runtime.deleted)
+	}
+	for _, path := range []string{"owned-current", "unowned-1", "unowned-8"} {
+		if !runtime.paths[path] {
+			t.Fatalf("cleanup deleted protected path %q", path)
+		}
+	}
+}
+
+func TestApplyBlocksExpiredOrOversizedSnapshotBeforeDelete(t *testing.T) {
+	repository := newFakeRepository()
+	repository.ownership = []store.MediaPathOwnership{{PathName: "stale", DeviceID: "old"}}
+	runtime := &fakeRuntime{paths: map[string]bool{"stale": true}, fail: make(map[string]bool)}
+	now := time.Date(2026, 8, 7, 0, 0, 0, 0, time.UTC)
+	manager := New(repository, runtime, "ins_test", nil)
+	manager.now = func() time.Time { return now }
+	scan, err := manager.Report(context.Background())
+	if err != nil {
+		t.Fatal(err)
+	}
+	if scan.SafetyAllowed || scan.SafetyReason != "ratio_exceeded" {
+		t.Fatalf("single-path 100%% cleanup was not blocked: %+v", scan)
+	}
+	if _, err := manager.Apply(context.Background(), scan.ID, "operator", Confirmation(scan.ID)); !errors.Is(err, ErrSafetyBlocked) {
+		t.Fatalf("expected ratio gate, got %v", err)
+	}
+	if len(runtime.deleted) != 0 {
+		t.Fatal("ratio-blocked cleanup mutated MediaMTX")
+	}
+
+	for index := 0; index < 9; index++ {
+		runtime.paths[string(rune('a'+index))] = true
+	}
+	scan, err = manager.Report(context.Background())
+	if err != nil || !scan.SafetyAllowed {
+		t.Fatalf("expected a fresh 1/10 executable report: %+v %v", scan, err)
+	}
+	now = now.Add(reportTTL)
+	if _, err := manager.Apply(context.Background(), scan.ID, "operator", Confirmation(scan.ID)); !errors.Is(err, ErrSnapshotExpired) {
+		t.Fatalf("expected expired snapshot, got %v", err)
+	}
+	if len(runtime.deleted) != 0 {
+		t.Fatal("expired cleanup mutated MediaMTX")
+	}
+}
+
+func TestApplyIsRetryableAndCannotExpandBeyondSnapshot(t *testing.T) {
+	repository := newFakeRepository()
+	repository.ownership = []store.MediaPathOwnership{
+		{PathName: "stale-a", DeviceID: "old-a"},
+		{PathName: "stale-b", DeviceID: "old-b"},
+	}
+	runtime := &fakeRuntime{paths: make(map[string]bool), fail: map[string]bool{"stale-b": true}}
+	runtime.paths["stale-a"], runtime.paths["stale-b"] = true, true
+	for index := 0; index < 18; index++ {
+		runtime.paths[string(rune(0x100+index))] = true
+	}
+	now := time.Date(2026, 8, 7, 0, 0, 0, 0, time.UTC)
+	manager := New(repository, runtime, "ins_test", nil)
+	manager.now = func() time.Time { return now }
+	scan, err := manager.Report(context.Background())
+	if err != nil || !scan.SafetyAllowed {
+		t.Fatalf("expected 2/20 report: %+v %v", scan, err)
+	}
+	repository.ownership = append(repository.ownership,
+		store.MediaPathOwnership{PathName: "new-stale", DeviceID: "new-old"})
+	runtime.paths["new-stale"] = true
+	result, err := manager.Apply(context.Background(), scan.ID, "operator", Confirmation(scan.ID))
+	if err == nil || result.Deleted != 1 || result.Failed != 1 {
+		t.Fatalf("expected one partial failure: %+v %v", result, err)
+	}
+	if !runtime.paths["new-stale"] {
+		t.Fatal("cleanup expanded beyond the approved snapshot")
+	}
+	runtime.fail["stale-b"] = false
+	result, err = manager.Apply(context.Background(), scan.ID, "operator", Confirmation(scan.ID))
+	if err != nil || result.Deleted != 1 || result.Failed != 0 {
+		t.Fatalf("failed item was not retryable: %+v %v", result, err)
+	}
+	if !runtime.paths["new-stale"] {
+		t.Fatal("retry expanded beyond the approved snapshot")
+	}
+}