Files
pipelines/internal/pipeline/resources_test.go
T
alan 27ad7daecd test: cover inspected resource recovery boundaries
Add executable regressions for a forged forwarded loopback claim over a real WebSocket transport and for replaying an old recovery after FIFO successor handoff.\n\nChecked packaged templates and packaged authoring skill references; neither needs updating. The existing per-item documentation note records shared documentation that the manual docs-fold process must update.
2026-10-18 19:18:03 +01:00

531 lines
17 KiB
Go

package pipeline
import (
"context"
"encoding/json"
"fmt"
"path/filepath"
"strings"
"sync"
"testing"
"time"
"git.a-wan.net/alan/pipelines/internal/protocol"
)
func TestResourceDeclaration(t *testing.T) {
base := Template([]string{"work"}, true)
for _, value := range []string{`{"exclusive":"phone-X"}`, `{ "exclusive" : "A_1" }`} {
graph, err := Parse(base + "```resources\n" + value + "\n```\n")
if err != nil || graph.Stages[0].Resources == nil {
t.Fatalf("%s: %v", value, err)
}
if _, ok := StageDefinition(graph.Stages[0]).Blocks["resources"]; ok {
t.Fatal("runner control reached executor")
}
encoded, _ := json.Marshal(graph)
if !strings.Contains(string(encoded), `"resources"`) {
t.Fatal("resource lost in persisted graph")
}
}
for _, value := range []string{`{}`, `null`, `[]`, `{"exclusive":""}`, `{"exclusive":"a b"}`, `{"exclusive":"a","exclusive":"b"}`, `{"exclusive":"a","extra":1}`, `{"exclusive":["a","b"]}`, fmt.Sprintf(`{"exclusive":%q}`, strings.Repeat("a", 129))} {
if _, err := Parse(base + "```resources\n" + value + "\n```\n"); err == nil {
t.Fatalf("accepted %s", value)
}
}
human := "# stage gate\n```prompt\nChoose\n```\n```configs\ntype=human\n```\n```edges\ngo -> #success\n```\n```resources\n{\"exclusive\":\"phone\"}\n```\n"
if _, err := Parse(human); err == nil {
t.Fatal("human acquired a resource")
}
}
func resourceStore(t *testing.T) (*Store, func(string) ResourceVisit) {
t.Helper()
ctx := context.Background()
s, err := Open(filepath.Join(t.TempDir(), "resources.db"))
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { s.Close() })
if _, err := s.Submit(ctx, "resource", Template([]string{"work"}, true)); err != nil {
t.Fatal(err)
}
items, _ := s.List(ctx)
d, _ := s.Get(ctx, items[0].ID, 1)
count := 0
return s, func(resource string) ResourceVisit {
count++
id, _, err := s.CreateRun(ctx, d, fmt.Sprint(count), "workspace", false, nil, nil)
if err != nil {
t.Fatal(err)
}
return ResourceVisit{Resource: resource, RunID: id, Stage: "work", Sequence: 1}
}
}
func acquireTestResource(t *testing.T, s *Store, visit ResourceVisit) ResourceLease {
t.Helper()
l, ch, _, err := s.RequestResource(context.Background(), visit)
if err != nil || ch != nil {
t.Fatalf("acquire: %v %v", ch, err)
}
return l
}
func releaseTestResource(t *testing.T, s *Store, lease ResourceLease) {
t.Helper()
if err := s.SetResourceCleanup(context.Background(), lease, true); err != nil {
t.Fatal(err)
}
if err := s.ReleaseResource(context.Background(), lease); err != nil {
t.Fatal(err)
}
}
func TestResourceFIFOOwnershipCancellationAndRegistry(t *testing.T) {
s, create := resourceStore(t)
ctx := context.Background()
a := acquireTestResource(t, s, create("X"))
duplicate := acquireTestResource(t, s, a.ResourceVisit)
if duplicate != a {
t.Fatal("duplicate acquisition changed capability")
}
var visits []ResourceVisit
var channels []<-chan ResourceLease
for i := 0; i < 4; i++ {
v := create("X")
_, ch, wait, err := s.RequestResource(ctx, v)
if err != nil || ch == nil || wait == nil {
t.Fatal("missing waiter", err)
}
_, again, _, err := s.RequestResource(ctx, v)
if err != nil || again != ch {
t.Fatal("duplicate waiter registered", err)
}
visits = append(visits, v)
channels = append(channels, ch)
}
if err := s.ReleaseResource(ctx, a); err != nil {
t.Fatal(err)
} // no cleanup receipt
for _, ch := range channels {
select {
case <-ch:
t.Fatal("unconfirmed release granted")
default:
}
}
if err := s.SetResourceCleanup(ctx, a, true); err != nil {
t.Fatal(err)
}
for _, corrupt := range []func(*ResourceLease){func(l *ResourceLease) { l.RunID++ }, func(l *ResourceLease) { l.Stage = "other" }, func(l *ResourceLease) { l.Sequence++ }, func(l *ResourceLease) { l.token = "wrong" }} {
bad := a
corrupt(&bad)
if err := s.ReleaseResource(ctx, bad); err != nil {
t.Fatal(err)
}
}
for _, ch := range channels {
select {
case <-ch:
t.Fatal("unconfirmed/mismatched release granted")
default:
}
}
if err := s.CancelResource(ctx, visits[1]); err != nil {
t.Fatal(err)
}
releaseTestResource(t, s, a)
for _, i := range []int{0, 2, 3} {
var grant ResourceLease
select {
case grant = <-channels[i]:
case <-time.After(time.Second):
t.Fatal("FIFO grant not delivered")
}
s.AcceptResource(grant)
if grant.ResourceVisit != visits[i] {
t.Fatal("wrong FIFO owner")
}
// An old owner's repeated release cannot release the next owner.
if err := s.ReleaseResource(ctx, a); err != nil {
t.Fatal(err)
}
for _, j := range []int{2, 3} {
if j > i {
select {
case <-channels[j]:
t.Fatal("multiple grants")
default:
}
}
}
releaseTestResource(t, s, grant)
}
if len(s.resourceWaiters) != 0 {
t.Fatal("channel registry leaked")
}
for i := 0; i < 30; i++ {
owner := acquireTestResource(t, s, create("X"))
v := create("X")
_, _, _, err := s.RequestResource(ctx, v)
if err != nil {
t.Fatal(err)
}
releaseTestResource(t, s, owner) // race window: granted but not accepted
if err := s.CancelResource(ctx, v); err != nil {
t.Fatal(err)
}
if len(s.resourceWaiters) != 0 {
t.Fatal("grant/cancel leaked channel")
}
}
for i := 0; i < 30; i++ {
owner := acquireTestResource(t, s, create("X"))
v := create("X")
if _, _, _, err := s.RequestResource(ctx, v); err != nil {
t.Fatal(err)
}
if err := s.SetResourceCleanup(ctx, owner, true); err != nil {
t.Fatal(err)
}
var wg sync.WaitGroup
wg.Add(2)
go func() {
defer wg.Done()
if err := s.ReleaseResource(ctx, owner); err != nil {
t.Error(err)
}
}()
go func() {
defer wg.Done()
if err := s.CancelResource(ctx, v); err != nil {
t.Error(err)
}
}()
wg.Wait()
if len(s.resourceWaiters) != 0 {
t.Fatal("concurrent grant/cancel leaked channel")
}
}
var owners, waiters int
s.db.QueryRow("SELECT COUNT(*) FROM resource_owners").Scan(&owners)
s.db.QueryRow("SELECT COUNT(*) FROM resource_waiters").Scan(&waiters)
if owners != 0 || waiters != 0 {
t.Fatalf("stranded owners/waiters: %d/%d", owners, waiters)
}
}
func TestResourceCancellationPersistenceFailureRemovesChannel(t *testing.T) {
s, create := resourceStore(t)
acquireTestResource(t, s, create("X"))
v := create("X")
if _, _, _, err := s.RequestResource(context.Background(), v); err != nil {
t.Fatal(err)
}
if err := s.Close(); err != nil {
t.Fatal(err)
}
if err := s.CancelResource(context.Background(), v); err == nil {
t.Fatal("closed DB cancellation claimed success")
}
if len(s.resourceWaiters) != 0 {
t.Fatal("persistence failure leaked channel")
}
}
func TestResourceRestartQuarantineAndRetention(t *testing.T) {
for _, confirmed := range []bool{false, true} {
t.Run(fmt.Sprint(confirmed), func(t *testing.T) {
s, create := resourceStore(t)
ctx := context.Background()
a := acquireTestResource(t, s, create("X"))
b := create("X")
if _, _, _, err := s.RequestResource(ctx, b); err != nil {
t.Fatal(err)
}
if confirmed {
if err := s.SetResourceCleanup(ctx, a, true); err != nil {
t.Fatal(err)
}
}
path := s.path
if err := s.Close(); err != nil {
t.Fatal(err)
}
reopened, err := Open(path)
if err != nil {
t.Fatal(err)
}
defer reopened.Close()
if err := reopened.RecoverRuns(ctx); err != nil {
t.Fatal(err)
}
if err := reopened.RecoverRuns(ctx); err != nil {
t.Fatal(err)
}
detail, err := reopened.GetRun(ctx, b.RunID)
if err != nil || detail.Status != "interrupted" || detail.ResourceWait != nil || len(detail.Steps) != 0 || !strings.Contains(detail.Diagnostic, "resource") {
t.Fatal("queued visit replayed/lost diagnostic", detail, err)
}
exists, err := reopened.HasResourceOwner(ctx, a.RunID)
if err != nil || exists == confirmed {
t.Fatal("incorrect recovery disposition", exists, err)
}
report, err := reopened.RetentionReport(ctx, RetentionPolicy{Keep: 0}, "", time.Now())
if err != nil {
t.Fatal(err)
}
protected := false
for _, p := range report.Protected {
if p.ID == a.RunID {
protected = true
}
}
if protected == confirmed {
t.Fatal("quarantined evidence not protected")
}
})
}
}
func TestResourceReconcileMissingWaiterPreservesQuarantine(t *testing.T) {
s, create := resourceStore(t)
ctx := context.Background()
owner := acquireTestResource(t, s, create("X"))
if _, err := s.db.ExecContext(ctx, "UPDATE pipeline_runs SET status='interrupted' WHERE id=?", owner.RunID); err != nil {
t.Fatal(err)
}
waiter := create("X")
if _, ch, _, err := s.RequestResource(ctx, waiter); err != nil || ch == nil {
t.Fatalf("register waiter: %v", err)
}
// Simulate a runner disappearing while its durable waiter remains. The
// authoritative operation must reject the handoff before audit or cleanup.
delete(s.resourceWaiters, waiter)
err := s.ReconcileResource(ctx, protocol.ResourceRecoveryRequest{
Resource: owner.Resource,
RunID: owner.RunID,
Stage: owner.Stage,
Sequence: owner.Sequence,
Actor: "operator",
Evidence: &protocol.ResourceRecoveryEvidence{CleanupConfirmed: true, NoMutatingAction: true, Summary: "inspection confirmed no mutating action occurred"},
})
if err == nil {
t.Fatal("reconciled without a live waiter channel")
}
var cleanup, audits, owners int
if err := s.db.QueryRow("SELECT cleanup_confirmed FROM resource_owners WHERE resource_key=?", owner.Resource).Scan(&cleanup); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_recovery_audit WHERE resource_key=?", owner.Resource).Scan(&audits); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_owners WHERE resource_key=?", owner.Resource).Scan(&owners); err != nil {
t.Fatal(err)
}
if cleanup != 0 || audits != 0 || owners != 1 {
t.Fatalf("failed recovery changed state: cleanup=%d audits=%d owners=%d", cleanup, audits, owners)
}
}
func TestResourceReconcileTransfersAndAudits(t *testing.T) {
s, create := resourceStore(t)
ctx := context.Background()
owner := acquireTestResource(t, s, create("X"))
if _, err := s.db.ExecContext(ctx, "UPDATE pipeline_runs SET status='interrupted' WHERE id=?", owner.RunID); err != nil {
t.Fatal(err)
}
waiter := create("X")
_, ch, _, err := s.RequestResource(ctx, waiter)
if err != nil || ch == nil {
t.Fatalf("register waiter: %v", err)
}
if err := s.ReconcileResource(ctx, protocol.ResourceRecoveryRequest{
Resource: owner.Resource,
RunID: owner.RunID,
Stage: owner.Stage,
Sequence: owner.Sequence,
Actor: "operator",
Evidence: &protocol.ResourceRecoveryEvidence{CleanupConfirmed: true, NoMutatingAction: true, Summary: "inspection confirmed no mutating action occurred"},
}); err != nil {
t.Fatal(err)
}
select {
case next := <-ch:
s.AcceptResource(next)
if next.ResourceVisit != waiter {
t.Fatalf("wrong handoff: %#v", next.ResourceVisit)
}
case <-time.After(time.Second):
t.Fatal("reconciliation did not wake waiter")
}
var audits int
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_recovery_audit WHERE resource_key=? AND result='reconciled'", owner.Resource).Scan(&audits); err != nil {
t.Fatal(err)
}
if audits != 1 {
t.Fatalf("recovery audit count=%d", audits)
}
}
func TestResourceReconcileReplayAfterSuccessorHandoff(t *testing.T) {
s, create := resourceStore(t)
ctx := context.Background()
owner := acquireTestResource(t, s, create("X"))
if _, err := s.db.ExecContext(ctx, "UPDATE pipeline_runs SET status='interrupted' WHERE id=?", owner.RunID); err != nil {
t.Fatal(err)
}
successor := create("X")
_, ch, _, err := s.RequestResource(ctx, successor)
if err != nil || ch == nil {
t.Fatalf("register successor: %v", err)
}
request := protocol.ResourceRecoveryRequest{
Resource: owner.Resource,
RunID: owner.RunID,
Stage: owner.Stage,
Sequence: owner.Sequence,
Actor: "operator",
Evidence: &protocol.ResourceRecoveryEvidence{
CleanupConfirmed: true,
NoMutatingAction: true,
Summary: "inspection confirmed no mutating action occurred",
},
}
if err := s.ReconcileResource(ctx, request); err != nil {
t.Fatal(err)
}
var successorLease ResourceLease
select {
case successorLease = <-ch:
case <-time.After(time.Second):
t.Fatal("reconciliation did not hand off to successor")
}
if successorLease.ResourceVisit != successor {
t.Fatalf("wrong successor visit: %#v", successorLease.ResourceVisit)
}
if successorLease.token == "" {
t.Fatal("successor capability was empty")
}
s.AcceptResource(successorLease)
// The old request is an idempotent replay after the handoff. It must not
// match or release the successor's private capability.
if err := s.ReconcileResource(ctx, request); err == nil {
t.Fatal("old recovery replay was accepted against successor owner")
}
inspection, err := s.InspectResource(ctx, owner.Resource)
if err != nil {
t.Fatal(err)
}
if inspection.Owner == nil || inspection.Owner.RunID != successor.RunID || inspection.Owner.Stage != successor.Stage || inspection.Owner.Sequence != successor.Sequence {
t.Fatalf("successor was not preserved: %#v", inspection.Owner)
}
if len(inspection.Waiters) != 0 || len(inspection.Audits) != 1 || inspection.Audits[0].RunID != owner.RunID {
t.Fatalf("replay changed handoff state: waiters=%d audits=%#v", len(inspection.Waiters), inspection.Audits)
}
if len(s.resourceWaiters) != 0 {
t.Fatal("successor channel registry leaked")
}
var owners, waiters, audits int
if err := s.db.QueryRowContext(ctx, "SELECT COUNT(*) FROM resource_owners WHERE resource_key=?", owner.Resource).Scan(&owners); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRowContext(ctx, "SELECT COUNT(*) FROM resource_waiters WHERE resource_key=?", owner.Resource).Scan(&waiters); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRowContext(ctx, "SELECT COUNT(*) FROM resource_recovery_audit WHERE resource_key=?", owner.Resource).Scan(&audits); err != nil {
t.Fatal(err)
}
if owners != 1 || waiters != 0 || audits != 1 {
t.Fatalf("unexpected post-replay counts: owners=%d waiters=%d audits=%d", owners, waiters, audits)
}
}
func TestResourceReconcileRequiresQuarantinedInactiveOwner(t *testing.T) {
ctx := context.Background()
test := func(t *testing.T, setup func(*Store, ResourceLease) int) {
s, create := resourceStore(t)
owner := acquireTestResource(t, s, create("X"))
expectedCleanup := setup(s, owner)
err := s.ReconcileResource(ctx, protocol.ResourceRecoveryRequest{
Resource: owner.Resource, RunID: owner.RunID, Stage: owner.Stage, Sequence: owner.Sequence,
Actor: "operator", Evidence: &protocol.ResourceRecoveryEvidence{CleanupConfirmed: true, Summary: "verified"},
})
if err == nil {
t.Fatal("reconciled unsafe owner")
}
var owners, audits, cleanup int
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_owners").Scan(&owners); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_recovery_audit").Scan(&audits); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRow("SELECT cleanup_confirmed FROM resource_owners WHERE resource_key=?", owner.Resource).Scan(&cleanup); err != nil {
t.Fatal(err)
}
if owners != 1 || audits != 0 || cleanup != expectedCleanup {
t.Fatalf("unsafe recovery changed state: owners=%d audits=%d cleanup=%d", owners, audits, cleanup)
}
}
t.Run("active run", func(t *testing.T) {
test(t, func(s *Store, owner ResourceLease) int {
if _, err := s.db.Exec("UPDATE pipeline_runs SET status=? WHERE id=?", protocol.RunStatusWaiting, owner.RunID); err != nil {
t.Fatal(err)
}
return 0
})
})
t.Run("active agent", func(t *testing.T) {
test(t, func(s *Store, owner ResourceLease) int {
if _, err := s.db.Exec("UPDATE pipeline_runs SET status='interrupted' WHERE id=?", owner.RunID); err != nil {
t.Fatal(err)
}
if _, err := s.db.Exec("INSERT INTO run_steps(run_id,sequence,stage_key,status,agent_active,input_json) VALUES(?,?,?,?,?, '{}')", owner.RunID, owner.Sequence, owner.Stage, "running", 1); err != nil {
t.Fatal(err)
}
return 0
})
})
t.Run("already confirmed", func(t *testing.T) {
test(t, func(s *Store, owner ResourceLease) int {
if err := s.SetResourceCleanup(ctx, owner, true); err != nil {
t.Fatal(err)
}
return 1
})
})
}
func TestResourceReconcileRejectsMalformedEvidenceBeforeMutation(t *testing.T) {
ctx := context.Background()
for _, summary := range []string{"", "true", "FALSE", "null", "verified\x00cleanup", strings.Repeat("x", maxRecoveryText+1)} {
t.Run(fmt.Sprintf("%q", summary), func(t *testing.T) {
s, create := resourceStore(t)
owner := acquireTestResource(t, s, create("X"))
err := s.ReconcileResource(ctx, protocol.ResourceRecoveryRequest{
Resource: owner.Resource, RunID: owner.RunID, Stage: owner.Stage, Sequence: owner.Sequence,
Actor: "operator", Evidence: &protocol.ResourceRecoveryEvidence{CleanupConfirmed: true, Summary: summary},
})
if err == nil {
t.Fatal("accepted malformed evidence")
}
var owners, audits, cleanup int
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_owners").Scan(&owners); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRow("SELECT COUNT(*) FROM resource_recovery_audit").Scan(&audits); err != nil {
t.Fatal(err)
}
if err := s.db.QueryRow("SELECT cleanup_confirmed FROM resource_owners WHERE resource_key=?", owner.Resource).Scan(&cleanup); err != nil {
t.Fatal(err)
}
if owners != 1 || audits != 0 || cleanup != 0 {
t.Fatalf("invalid evidence changed state: owners=%d audits=%d cleanup=%d", owners, audits, cleanup)
}
})
}
}