Files
Agent-Squad/squad/backend_test.go
T
weichen aa15a5d164 Version resolver configs and invalidate executor caches
Why: F06 - the wrapped-executor cache keyed only backend/role/model, so
allow->deny permission tightening and factory replacement never took
effect on subsequent resolves.
Evidence: squad and adapters/native tests pass (verify-u4.json); config
identity helper covers permission/tool/limiter changes.
Impact: stale executors can no longer widen capabilities; in-flight
tasks are not rolled back (documented).
Refs: feature/agent-stack-audit-remediation-b1 U4
2026-10-21 15:51:53 +00:00

406 lines
10 KiB
Go

package squad
import (
"context"
"sync"
"sync/atomic"
"testing"
"time"
)
type labeledExec struct {
label string
perm string
tools string
delay time.Duration
enter func()
leave func()
}
func (e *labeledExec) Name() string { return e.label }
func (e *labeledExec) Execute(ctx context.Context, req ExecRequest) (*ExecResult, error) {
if e.enter != nil {
e.enter()
}
if e.leave != nil {
defer e.leave()
}
if e.delay > 0 {
select {
case <-ctx.Done():
return nil, ctx.Err()
case <-time.After(e.delay):
}
}
return &ExecResult{Success: true, Logs: e.label + "|" + e.perm + "|" + e.tools}, nil
}
func TestConfigIdentityChangesWithBashAndTools(t *testing.T) {
a := RoleSpec{Role: "r", Model: "m", BashPermission: BashPermissionAllow}
d := RoleSpec{Role: "r", Model: "m", BashPermission: BashPermissionDeny}
if ConfigIdentity(a) == ConfigIdentity(d) {
t.Fatal("allow and deny must differ")
}
t1 := RoleSpec{Role: "r", Model: "m", Tools: []string{"a", "b"}}
t2 := RoleSpec{Role: "r", Model: "m", Tools: []string{"b", "a"}}
if ConfigIdentity(t1) != ConfigIdentity(t2) {
t.Fatal("tool order must not change identity")
}
t3 := RoleSpec{Role: "r", Model: "m", Tools: []string{"a", "c"}}
if ConfigIdentity(t1) == ConfigIdentity(t3) {
t.Fatal("tool set change must change identity")
}
same := RoleSpec{Role: "r", Model: "m", BashPermission: BashPermissionAllow, MaxConcurrentTasks: 1}
bump := RoleSpec{Role: "r", Model: "m", BashPermission: BashPermissionAllow, MaxConcurrentTasks: 8}
if ConfigIdentity(same) != ConfigIdentity(bump) {
t.Fatal("MaxConcurrentTasks must not affect ConfigIdentity")
}
}
func TestResolveAllowDenyTighteningAndLoosening(t *testing.T) {
var builds atomic.Int32
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
builds.Add(1)
return &labeledExec{label: "cap", perm: role.BashPermission}, nil
})
allow := RoleSpec{Role: "writer", Backend: "cap", Model: "m1", BashPermission: BashPermissionAllow}
e1, _, err := r.Resolve(allow, "")
if err != nil {
t.Fatal(err)
}
res, _ := e1.Execute(context.Background(), ExecRequest{})
if res.Logs != "cap|allow|" {
t.Fatalf("want allow executor, got %q", res.Logs)
}
deny := RoleSpec{Role: "writer", Backend: "cap", Model: "m1", BashPermission: BashPermissionDeny}
e2, _, err := r.Resolve(deny, "")
if err != nil {
t.Fatal(err)
}
res, _ = e2.Execute(context.Background(), ExecRequest{})
if res.Logs != "cap|deny|" {
t.Fatalf("allow→deny must take effect on next Resolve, got %q", res.Logs)
}
if e1 == e2 {
t.Fatal("tightened config must not reuse cached allow executor")
}
e3, _, err := r.Resolve(allow, "")
if err != nil {
t.Fatal(err)
}
res, _ = e3.Execute(context.Background(), ExecRequest{})
if res.Logs != "cap|allow|" {
t.Fatalf("deny→allow must take effect, got %q", res.Logs)
}
if builds.Load() < 2 {
t.Fatalf("factory must rebuild on permission change, builds=%d", builds.Load())
}
}
func TestResolveFactoryReplacementTakesEffect(t *testing.T) {
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
return &labeledExec{label: "v1", perm: role.BashPermission}, nil
})
role := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionAllow}
e1, _, err := r.Resolve(role, "")
if err != nil {
t.Fatal(err)
}
res, _ := e1.Execute(context.Background(), ExecRequest{})
if res.Logs != "v1|allow|" {
t.Fatalf("got %q", res.Logs)
}
r.Register("cap", func(role RoleSpec) (Executor, error) {
return &labeledExec{label: "v2", perm: role.BashPermission}, nil
})
e2, _, err := r.Resolve(role, "")
if err != nil {
t.Fatal(err)
}
res, _ = e2.Execute(context.Background(), ExecRequest{})
if res.Logs != "v2|allow|" {
t.Fatalf("factory replacement must take effect, got %q", res.Logs)
}
}
func TestResolveToolConfigChangeTakesEffect(t *testing.T) {
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
tools := ""
if len(role.Tools) > 0 {
tools = role.Tools[0]
}
return &labeledExec{label: "cap", tools: tools}, nil
})
base := RoleSpec{Role: "writer", Backend: "cap", Model: "m", Tools: []string{"read"}}
e1, _, err := r.Resolve(base, "")
if err != nil {
t.Fatal(err)
}
res, _ := e1.Execute(context.Background(), ExecRequest{})
if res.Logs != "cap||read" {
t.Fatalf("got %q", res.Logs)
}
next := RoleSpec{Role: "writer", Backend: "cap", Model: "m", Tools: []string{"write"}}
e2, _, err := r.Resolve(next, "")
if err != nil {
t.Fatal(err)
}
res, _ = e2.Execute(context.Background(), ExecRequest{})
if res.Logs != "cap||write" {
t.Fatalf("tool-config change must take effect, got %q", res.Logs)
}
}
func TestResolveUnchangedConfigReusesCache(t *testing.T) {
var builds atomic.Int32
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
builds.Add(1)
return &labeledExec{label: "cap", perm: role.BashPermission}, nil
})
role := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionAsk}
e1, _, err := r.Resolve(role, "")
if err != nil {
t.Fatal(err)
}
e2, _, err := r.Resolve(role, "")
if err != nil {
t.Fatal(err)
}
if e1 != e2 {
t.Fatal("unchanged config must reuse cached executor")
}
if builds.Load() != 1 {
t.Fatalf("want 1 factory call, got %d", builds.Load())
}
}
func TestResolveParallelFirstDoesNotDuplicate(t *testing.T) {
var builds atomic.Int32
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
builds.Add(1)
time.Sleep(20 * time.Millisecond) // widen race window
return &labeledExec{label: "cap"}, nil
})
role := RoleSpec{Role: "writer", Backend: "cap", Model: "m", MaxConcurrentTasks: 2}
const n = 32
var wg sync.WaitGroup
got := make([]Executor, n)
errs := make([]error, n)
wg.Add(n)
for i := 0; i < n; i++ {
i := i
go func() {
defer wg.Done()
got[i], _, errs[i] = r.Resolve(role, "")
}()
}
wg.Wait()
for i, err := range errs {
if err != nil {
t.Fatalf("resolve %d: %v", i, err)
}
}
for i := 1; i < n; i++ {
if got[i] != got[0] {
t.Fatalf("parallel first Resolve must share one executor")
}
}
if builds.Load() != 1 {
t.Fatalf("want single factory construction, got %d", builds.Load())
}
}
func TestSharedGateAcrossVersionsAndLimiterChange(t *testing.T) {
var (
mu sync.Mutex
current int
peak int
)
hold := make(chan struct{})
entered := make(chan struct{}, 8)
trackEnter := func() {
mu.Lock()
current++
if current > peak {
peak = current
}
mu.Unlock()
entered <- struct{}{}
<-hold
}
trackLeave := func() {
mu.Lock()
current--
mu.Unlock()
}
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
return &labeledExec{
label: "cap",
perm: role.BashPermission,
enter: trackEnter,
leave: trackLeave,
}, nil
})
allow := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionAllow, MaxConcurrentTasks: 1}
eOld, _, err := r.Resolve(allow, "")
if err != nil {
t.Fatal(err)
}
errCh := make(chan error, 4)
go func() { _, err := eOld.Execute(context.Background(), ExecRequest{}); errCh <- err }()
<-entered // old holds the sole slot
deny := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionDeny, MaxConcurrentTasks: 1}
eNew, _, err := r.Resolve(deny, "")
if err != nil {
t.Fatal(err)
}
if eOld == eNew {
t.Fatal("version bump must produce a new executor")
}
secondDone := make(chan struct{})
go func() {
_, err := eNew.Execute(context.Background(), ExecRequest{})
errCh <- err
close(secondDone)
}()
select {
case <-secondDone:
t.Fatal("new-version execute must wait on shared role cap while old is in-flight")
case <-time.After(40 * time.Millisecond):
}
// Raising MaxConcurrentTasks must update the shared gate (not spawn a bypassing limiter).
deny2 := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionDeny, MaxConcurrentTasks: 2}
eLim, _, err := r.Resolve(deny2, "")
if err != nil {
t.Fatal(err)
}
go func() { _, err := eLim.Execute(context.Background(), ExecRequest{}); errCh <- err }()
// After setMax(2): waiting eNew can enter (active=2). eLim must still wait.
select {
case <-entered: // eNew
case <-time.After(time.Second):
t.Fatal("limiter raise must admit the waiting new-version task")
}
select {
case <-entered:
t.Fatal("third task must not bypass shared cap after limiter change")
case <-time.After(40 * time.Millisecond):
}
close(hold)
for i := 0; i < 3; i++ {
if err := <-errCh; err != nil {
t.Fatal(err)
}
}
mu.Lock()
p := peak
mu.Unlock()
if p > 2 {
t.Fatalf("shared gate must cap total in-flight across versions; peak=%d", p)
}
}
func TestInFlightOldVersionCannotExceedCap(t *testing.T) {
var (
mu sync.Mutex
current int
peak int
)
enter := func() {
mu.Lock()
current++
if current > peak {
peak = current
}
mu.Unlock()
}
leave := func() {
mu.Lock()
current--
mu.Unlock()
}
r := NewBackendResolver()
r.Register("cap", func(role RoleSpec) (Executor, error) {
return &labeledExec{
label: "cap",
perm: role.BashPermission,
delay: 80 * time.Millisecond,
enter: enter,
leave: leave,
}, nil
})
v1 := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionAllow, MaxConcurrentTasks: 2}
e1, _, err := r.Resolve(v1, "")
if err != nil {
t.Fatal(err)
}
v2 := RoleSpec{Role: "writer", Backend: "cap", Model: "m", BashPermission: BashPermissionDeny, MaxConcurrentTasks: 2}
e2, _, err := r.Resolve(v2, "")
if err != nil {
t.Fatal(err)
}
var wg sync.WaitGroup
// 2 from old version + 2 from new version; shared cap=2 ⇒ peak must stay ≤2.
for _, e := range []Executor{e1, e1, e2, e2} {
wg.Add(1)
e := e
go func() {
defer wg.Done()
_, _ = e.Execute(context.Background(), ExecRequest{})
}()
}
wg.Wait()
mu.Lock()
p := peak
mu.Unlock()
if p > 2 {
t.Fatalf("in-flight old+new must not exceed role cap; peak=%d", p)
}
}
func TestRegisterInstanceStubSemantics(t *testing.T) {
r := NewBackendResolver()
e, name, err := r.Resolve(RoleSpec{Role: "x"}, "")
if err != nil {
t.Fatal(err)
}
if name != "stub" {
t.Fatalf("want stub, got %s", name)
}
if e.Name() != "stub" {
t.Fatalf("want stub executor, got %s", e.Name())
}
custom := &labeledExec{label: "stub-custom"}
r.RegisterInstance("stub", custom)
e2, _, err := r.Resolve(RoleSpec{Role: "x"}, "")
if err != nil {
t.Fatal(err)
}
if e2.Name() != "stub-custom" {
t.Fatalf("RegisterInstance stub replace must take effect, got %s", e2.Name())
}
}