iop/apps/node/internal/node/node_test.go
toki 137b3a5301 feat(node): runtime concurrency support and task module cleanup
- Add node concurrency integration test
- Update bootstrap module for runtime concurrency
- Refactor node.go with concurrency improvements
- Update run_manager for concurrent task handling
- Archive completed subtask documents (07+02_runtime_concurrency)
- Remove obsolete code review and plan files
2026-06-12 06:07:03 +09:00

1304 lines
42 KiB
Go

package node_test
import (
"context"
"errors"
"fmt"
"io"
"strings"
"sync/atomic"
"testing"
"time"
"go.uber.org/zap"
"iop/apps/node/internal/node"
"iop/apps/node/internal/runtime"
"iop/apps/node/internal/store"
"iop/apps/node/internal/transport"
iop "iop/proto/gen/iop"
)
// --- test doubles ---
type countingAdapter struct {
executeCalls int32
}
func (a *countingAdapter) Name() string { return "test" }
func (a *countingAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "test", Targets: []string{"v1"}, MaxConcurrency: 1}, nil
}
func (a *countingAdapter) Execute(_ context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
atomic.AddInt32(&a.executeCalls, 1)
return nil
}
// failingAdapter returns a fixed error from Execute.
type failingAdapter struct{ err error }
func (a *failingAdapter) Name() string { return "failing" }
func (a *failingAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "failing"}, nil
}
func (a *failingAdapter) Execute(_ context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
return a.err
}
// blockingAdapter blocks until its context is cancelled, then returns ErrRunCancelled.
type blockingAdapter struct {
started chan struct{}
done chan struct{}
}
func newBlockingAdapter() *blockingAdapter {
return &blockingAdapter{started: make(chan struct{}), done: make(chan struct{})}
}
func (a *blockingAdapter) Name() string { return "blocking" }
func (a *blockingAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "blocking"}, nil
}
func (a *blockingAdapter) Execute(ctx context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
close(a.started)
<-ctx.Done()
close(a.done)
return runtime.ErrRunCancelled
}
// terminatingAdapter implements SessionTerminator.
type terminatingAdapter struct {
terminateCalls int32
lastTarget string
lastSessionID string
}
func (a *terminatingAdapter) Name() string { return "terminating" }
func (a *terminatingAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "terminating"}, nil
}
func (a *terminatingAdapter) Execute(_ context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
return nil
}
func (a *terminatingAdapter) TerminateSession(_ context.Context, target, sessionID string) error {
atomic.AddInt32(&a.terminateCalls, 1)
a.lastTarget = target
a.lastSessionID = sessionID
return nil
}
type instanceKeyAdapter struct {
instanceKey string
}
func (a *instanceKeyAdapter) Name() string { return "ollama" }
func (a *instanceKeyAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{
AdapterName: "ollama",
InstanceKey: a.instanceKey,
Targets: []string{"llama3"},
MaxConcurrency: 4,
}, nil
}
func (a *instanceKeyAdapter) Execute(_ context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
return nil
}
type commandAdapter struct {
lastReq runtime.CommandRequest
}
func (a *commandAdapter) Name() string { return "command" }
func (a *commandAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "command", Targets: []string{"v2", "v1"}, MaxConcurrency: 3}, nil
}
func (a *commandAdapter) Execute(_ context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
return nil
}
func (a *commandAdapter) HandleCommand(ctx context.Context, req runtime.CommandRequest) (runtime.CommandResponse, error) {
a.lastReq = req
switch req.Type {
case runtime.CommandTypeUsageStatus:
return runtime.CommandResponse{
RequestID: req.RequestID,
Type: req.Type,
Adapter: req.Adapter,
Target: req.Target,
SessionID: req.SessionID,
UsageStatus: &runtime.AgentUsageStatus{
RawOutput: "success",
},
}, nil
default:
return runtime.CommandResponse{}, errors.New("command not supported by adapter")
}
}
type fixedRouter struct {
adapterName string
adapter runtime.Adapter
adapters map[string]runtime.Adapter
lookupErrors map[string]error // optional per-adapter errors for LookupAdapter
}
func (r *fixedRouter) Resolve(_ context.Context, req runtime.RunRequest) (runtime.ExecutionSpec, error) {
return runtime.ExecutionSpec{
RunID: req.RunID,
Adapter: r.adapterName,
Target: req.Target,
SessionID: req.SessionID,
SessionMode: req.SessionMode,
Background: req.Background,
Workspace: req.Workspace,
Policy: req.Policy,
Input: req.Input,
TimeoutSec: req.TimeoutSec,
Metadata: req.Metadata,
}, nil
}
func (r *fixedRouter) ResolveAdapter(ctx context.Context, req runtime.RunRequest) (runtime.ExecutionSpec, runtime.Adapter, error) {
spec, err := r.Resolve(ctx, req)
if err != nil {
return runtime.ExecutionSpec{}, nil, err
}
a, ok := r.adapters[spec.Adapter]
if !ok {
return runtime.ExecutionSpec{}, nil, fmt.Errorf("router: adapter %q not found", spec.Adapter)
}
return spec, a, nil
}
func (r *fixedRouter) LookupAdapter(adapterName string) (runtime.Adapter, error) {
if r.lookupErrors != nil {
if err, ok := r.lookupErrors[adapterName]; ok {
return nil, err
}
}
a, ok := r.adapters[adapterName]
if !ok {
return nil, fmt.Errorf("adapter %q not found", adapterName)
}
return a, nil
}
func (r *fixedRouter) GetAdapter(adapterName string) (runtime.Adapter, bool) {
a, ok := r.adapters[adapterName]
return a, ok
}
type errorRouter struct{ err error }
func (r *errorRouter) Resolve(_ context.Context, _ runtime.RunRequest) (runtime.ExecutionSpec, error) {
return runtime.ExecutionSpec{}, r.err
}
func (r *errorRouter) ResolveAdapter(_ context.Context, _ runtime.RunRequest) (runtime.ExecutionSpec, runtime.Adapter, error) {
return runtime.ExecutionSpec{}, nil, r.err
}
func (r *errorRouter) LookupAdapter(_ string) (runtime.Adapter, error) {
return nil, r.err
}
func (r *errorRouter) GetAdapter(_ string) (runtime.Adapter, bool) {
return nil, false
}
func makeNode(t *testing.T, rtr runtime.Router) (*node.Node, *store.Store) {
t.Helper()
return makeNodeWithConcurrency(t, rtr, 0)
}
func makeNodeWithConcurrency(t *testing.T, rtr runtime.Router, concurrency int) (*node.Node, *store.Store) {
t.Helper()
st, err := store.New(":memory:", zap.NewNop())
if err != nil {
t.Fatalf("store: %v", err)
}
t.Cleanup(func() { _ = st.Close() })
return node.New("test-node", rtr, st, concurrency, io.Discard, zap.NewNop()), st
}
// --- existing tests (updated) ---
func TestOnRunRequest_RouterError(t *testing.T) {
n, _ := makeNode(t, &errorRouter{err: errors.New("boom")})
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{RunId: "run-1"})
if err == nil {
t.Fatal("expected error")
}
if !strings.Contains(err.Error(), "node: resolve:") {
t.Fatalf("expected resolve prefix, got %v", err)
}
}
func TestOnRunRequest_AdapterNotFound(t *testing.T) {
router := &fixedRouter{adapterName: "missing", adapters: make(map[string]runtime.Adapter)}
n, _ := makeNode(t, router)
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{RunId: "run-1"})
if err == nil {
t.Fatal("expected error")
}
if !strings.Contains(err.Error(), "not found") {
t.Fatalf("expected adapter lookup error, got %v", err)
}
}
func TestOnRunRequest_Success(t *testing.T) {
adapter := &countingAdapter{}
router := &fixedRouter{adapterName: "test", adapters: make(map[string]runtime.Adapter)}
router.adapters["test"] = adapter
n, st := makeNode(t, router)
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-1",
Adapter: "test",
Target: "v1",
})
if err != nil {
t.Fatalf("run request: %v", err)
}
if got := atomic.LoadInt32(&adapter.executeCalls); got != 1 {
t.Fatalf("expected 1 execute call, got %d", got)
}
run, err := st.GetRun(context.Background(), "run-1")
if err != nil {
t.Fatalf("get run: %v", err)
}
if run == nil {
t.Fatal("expected persisted run record")
}
if run.Status != "completed" {
t.Fatalf("expected completed status, got %q", run.Status)
}
}
// --- new tests ---
func TestOnRunRequest_ForegroundAdapterErrorReturned(t *testing.T) {
adapter := &failingAdapter{err: errors.New("adapter boom")}
router := &fixedRouter{adapterName: "failing", adapters: make(map[string]runtime.Adapter)}
router.adapters["failing"] = adapter
n, st := makeNode(t, router)
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-fail",
Adapter: "failing",
Target: "v1",
})
if err == nil {
t.Fatal("expected error from OnRunRequest")
}
if !strings.Contains(err.Error(), "adapter boom") {
t.Fatalf("expected adapter boom in error, got %v", err)
}
run, err := st.GetRun(context.Background(), "run-fail")
if err != nil {
t.Fatalf("get run: %v", err)
}
if run == nil {
t.Fatal("expected persisted run record")
}
if run.Status != "failed" {
t.Fatalf("expected failed status, got %q", run.Status)
}
if !strings.Contains(run.Error, "adapter boom") {
t.Fatalf("expected adapter boom in stored error, got %q", run.Error)
}
}
func TestOnRunRequest_ForegroundCancelReturnedAndStored(t *testing.T) {
adapter := &failingAdapter{err: runtime.ErrRunCancelled}
router := &fixedRouter{adapterName: "failing", adapters: make(map[string]runtime.Adapter)}
router.adapters["failing"] = adapter
n, st := makeNode(t, router)
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-cancel-fg",
Adapter: "failing",
Target: "v1",
})
if !errors.Is(err, runtime.ErrRunCancelled) {
t.Fatalf("expected ErrRunCancelled, got %v", err)
}
run, err := st.GetRun(context.Background(), "run-cancel-fg")
if err != nil {
t.Fatalf("get run: %v", err)
}
if run == nil || run.Status != "cancelled" {
t.Fatalf("expected cancelled status, got %+v", run)
}
}
func TestOnRunRequest_BackgroundReturnsBeforeAdapterCompletes(t *testing.T) {
ba := newBlockingAdapter()
router := &fixedRouter{adapterName: "blocking", adapters: make(map[string]runtime.Adapter)}
router.adapters["blocking"] = ba
n, st := makeNode(t, router)
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-bg",
Adapter: "blocking",
Target: "v1",
Background: true,
})
if err != nil {
t.Fatalf("OnRunRequest: %v", err)
}
// OnRunRequest should return before adapter finishes.
select {
case <-ba.started:
case <-time.After(2 * time.Second):
t.Fatal("adapter never started")
}
// Cancel via OnCancel so the blocking adapter finishes.
if err := n.OnCancel(context.Background(), &transport.Session{}, &iop.CancelRequest{RunId: "run-bg"}); err != nil {
t.Fatalf("OnCancel: %v", err)
}
select {
case <-ba.done:
case <-time.After(2 * time.Second):
t.Fatal("adapter did not finish after cancel")
}
// Wait briefly for completeRun goroutine to update the store.
deadline := time.Now().Add(2 * time.Second)
for time.Now().Before(deadline) {
run, err := st.GetRun(context.Background(), "run-bg")
if err != nil {
t.Fatalf("get run: %v", err)
}
if run != nil && run.Status == "cancelled" {
return
}
time.Sleep(10 * time.Millisecond)
}
run, _ := st.GetRun(context.Background(), "run-bg")
t.Fatalf("expected cancelled status, got %q", run.Status)
}
func TestOnCancel_CancelsRunViaRunManager(t *testing.T) {
ba := newBlockingAdapter()
router := &fixedRouter{adapterName: "blocking", adapters: make(map[string]runtime.Adapter)}
router.adapters["blocking"] = ba
n, _ := makeNode(t, router)
go func() {
_ = n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-cancel",
Adapter: "blocking",
Target: "v1",
})
}()
<-ba.started
if err := n.OnCancel(context.Background(), &transport.Session{}, &iop.CancelRequest{RunId: "run-cancel"}); err != nil {
t.Fatalf("OnCancel: %v", err)
}
select {
case <-ba.done:
case <-time.After(2 * time.Second):
t.Fatal("adapter did not finish after cancel")
}
}
func TestOnCancel_TerminatesAdapterSession(t *testing.T) {
ta := &terminatingAdapter{}
router := &fixedRouter{adapterName: "terminating", adapters: make(map[string]runtime.Adapter)}
router.adapters["terminating"] = ta
n, _ := makeNode(t, router)
err := n.OnCancel(context.Background(), &transport.Session{}, &iop.CancelRequest{
RunId: "",
Adapter: "terminating",
Target: "codex",
SessionId: "session-a",
Action: iop.CancelAction_CANCEL_ACTION_TERMINATE_SESSION,
})
if err != nil {
t.Fatalf("OnCancel terminate: %v", err)
}
if atomic.LoadInt32(&ta.terminateCalls) != 1 {
t.Fatal("expected TerminateSession to be called once")
}
if ta.lastTarget != "codex" || ta.lastSessionID != "session-a" {
t.Fatalf("unexpected terminate args: target=%q session=%q", ta.lastTarget, ta.lastSessionID)
}
}
func TestOnCommandRequest_Success(t *testing.T) {
ca := &commandAdapter{}
router := &fixedRouter{adapterName: "command", adapters: make(map[string]runtime.Adapter)}
router.adapters["command"] = ca
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-1",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_USAGE_STATUS,
Adapter: "command",
Target: "codex",
SessionId: "default",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if resp.GetError() != "" {
t.Fatalf("expected no error, got %q", resp.GetError())
}
if resp.GetUsageStatus().GetRawOutput() != "success" {
t.Fatalf("expected success raw output, got %q", resp.GetUsageStatus().GetRawOutput())
}
if ca.lastReq.Type != runtime.CommandTypeUsageStatus || ca.lastReq.Target != "codex" {
t.Fatalf("unexpected last req: %+v", ca.lastReq)
}
}
func TestOnCommandRequest_MissingAdapter(t *testing.T) {
router := &fixedRouter{adapterName: "missing", adapters: make(map[string]runtime.Adapter)}
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-1",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_USAGE_STATUS,
Adapter: "missing",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), "not found") {
t.Fatalf("expected not found error, got %q", resp.GetError())
}
}
func TestOnCommandRequest_NotSupported(t *testing.T) {
ta := &terminatingAdapter{}
router := &fixedRouter{adapterName: "terminating", adapters: make(map[string]runtime.Adapter)}
router.adapters["terminating"] = ta
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-1",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_USAGE_STATUS,
Adapter: "terminating",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), "does not support commands") {
t.Fatalf("expected not supported error, got %q", resp.GetError())
}
}
func TestOnCommandRequest_UnspecifiedRejected(t *testing.T) {
ca := &commandAdapter{}
router := &fixedRouter{adapterName: "command", adapters: make(map[string]runtime.Adapter)}
router.adapters["command"] = ca
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-1",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_UNSPECIFIED,
Adapter: "command",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), "unsupported command type") {
t.Fatalf("expected unsupported command type error, got %q", resp.GetError())
}
// Adapter must not be invoked for unsupported command types.
if ca.lastReq.RequestID != "" {
t.Fatalf("expected adapter to be skipped, got lastReq %+v", ca.lastReq)
}
}
func TestOnCommandRequest_Capabilities(t *testing.T) {
ca := &commandAdapter{}
router := &fixedRouter{adapterName: "command", adapters: make(map[string]runtime.Adapter)}
router.adapters["command"] = ca
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-cap",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_CAPABILITIES,
Adapter: "command",
Target: "codex",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if resp.GetError() != "" {
t.Fatalf("expected no error, got %q", resp.GetError())
}
if resp.GetType() != iop.NodeCommandType_NODE_COMMAND_TYPE_CAPABILITIES {
t.Fatalf("type: got %v want CAPABILITIES", resp.GetType())
}
if got := resp.GetResult()["targets"]; got != "v1,v2" {
t.Fatalf("result[targets]: got %q want %q", got, "v1,v2")
}
if got := resp.GetResult()["adapter"]; got != "command" {
t.Fatalf("result[adapter]: got %q want %q", got, "command")
}
if got := resp.GetResult()["max_concurrency"]; got != "3" {
t.Fatalf("result[max_concurrency]: got %q want %q", got, "3")
}
// Capabilities must not go through the adapter CommandHandler.
if ca.lastReq.RequestID != "" {
t.Fatalf("expected CommandHandler to be skipped, got %+v", ca.lastReq)
}
}
// TestOnCommandRequest_CapabilitiesWithoutCommandHandler verifies CAPABILITIES
// succeeds for an adapter that does not implement runtime.CommandHandler.
func TestOnCommandRequest_CapabilitiesWithoutCommandHandler(t *testing.T) {
ta := &terminatingAdapter{} // no CommandHandler
router := &fixedRouter{adapterName: "terminating", adapters: make(map[string]runtime.Adapter)}
router.adapters["terminating"] = ta
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-cap",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_CAPABILITIES,
Adapter: "terminating",
Target: "codex",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if resp.GetError() != "" {
t.Fatalf("expected no error, got %q", resp.GetError())
}
if got := resp.GetResult()["adapter"]; got != "terminating" {
t.Fatalf("result[adapter]: got %q want %q", got, "terminating")
}
}
func TestOnCommandRequest_TransportStatus(t *testing.T) {
ta := &terminatingAdapter{} // adapter not required for transport_status
router := &fixedRouter{adapterName: "terminating", adapters: make(map[string]runtime.Adapter)}
router.adapters["terminating"] = ta
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-tx",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_TRANSPORT_STATUS,
Adapter: "terminating",
Target: "codex",
SessionId: "sess-a",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if resp.GetError() != "" {
t.Fatalf("expected no error, got %q", resp.GetError())
}
if got := resp.GetResult()["node_id"]; got != "test-node" {
t.Fatalf("result[node_id]: got %q want %q", got, "test-node")
}
if got := resp.GetResult()["adapter"]; got != "terminating" {
t.Fatalf("result[adapter]: got %q want %q", got, "terminating")
}
if got := resp.GetResult()["session_id"]; got != "sess-a" {
t.Fatalf("result[session_id]: got %q want %q", got, "sess-a")
}
if _, ok := resp.GetResult()["connected"]; !ok {
t.Fatalf("result missing connected key: %+v", resp.GetResult())
}
if got, ok := resp.GetResult()["state"]; !ok || (got != "connected" && got != "disconnected") {
t.Fatalf("result[state]: got %q, want \"connected\" or \"disconnected\"", got)
}
}
func TestOnCommandRequest_AdapterError(t *testing.T) {
ca := &commandAdapter{}
router := &fixedRouter{adapterName: "command", adapters: make(map[string]runtime.Adapter)}
router.adapters["command"] = ca
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-1",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_SESSION_LIST,
Adapter: "command",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), "command not supported by adapter") {
t.Fatalf("expected adapter unsupported error, got %q", resp.GetError())
}
}
func TestOnCommandRequest_TransportStatusDefaultsSessionID(t *testing.T) {
ta := &terminatingAdapter{}
router := &fixedRouter{adapterName: "terminating", adapters: make(map[string]runtime.Adapter)}
router.adapters["terminating"] = ta
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-ts-default",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_TRANSPORT_STATUS,
Adapter: "terminating",
Target: "codex",
SessionId: "",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if resp.GetError() != "" {
t.Fatalf("expected no error, got %q", resp.GetError())
}
if got := resp.GetSessionId(); got != "default" {
t.Fatalf("response SessionId: got %q want %q", got, "default")
}
if got := resp.GetResult()["session_id"]; got != "default" {
t.Fatalf("result[session_id]: got %q want %q", got, "default")
}
if got, ok := resp.GetResult()["state"]; !ok || (got != "connected" && got != "disconnected") {
t.Fatalf("result[state]: got %q, want \"connected\" or \"disconnected\"", got)
}
}
func TestOnCommandRequest_ErrorResponsesPreserveEnvelope(t *testing.T) {
cases := []struct {
name string
req *iop.NodeCommandRequest
adapter runtime.Adapter
wantErr string
}{
{
name: "missing adapter",
req: &iop.NodeCommandRequest{
RequestId: "req-missing",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_USAGE_STATUS,
Adapter: "missing",
Target: "tgt",
SessionId: "sess-x",
},
adapter: nil,
wantErr: "not found",
},
{
name: "unsupported command type",
req: &iop.NodeCommandRequest{
RequestId: "req-unspec",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_UNSPECIFIED,
Adapter: "terminating",
Target: "tgt",
SessionId: "sess-y",
},
adapter: &terminatingAdapter{},
wantErr: "unsupported command type",
},
{
name: "adapter does not support commands",
req: &iop.NodeCommandRequest{
RequestId: "req-nosupport",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_USAGE_STATUS,
Adapter: "terminating",
Target: "tgt",
SessionId: "sess-z",
},
adapter: &terminatingAdapter{},
wantErr: "does not support commands",
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
adapters := make(map[string]runtime.Adapter)
if tc.adapter != nil {
adapters[tc.req.Adapter] = tc.adapter
}
router := &fixedRouter{adapterName: tc.req.Adapter, adapters: adapters}
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, tc.req)
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), tc.wantErr) {
t.Fatalf("error: got %q want contains %q", resp.GetError(), tc.wantErr)
}
if got := resp.GetRequestId(); got != tc.req.RequestId {
t.Fatalf("RequestId: got %q want %q", got, tc.req.RequestId)
}
if got := resp.GetType(); got != tc.req.Type {
t.Fatalf("Type: got %v want %v", got, tc.req.Type)
}
if got := resp.GetAdapter(); got != tc.req.Adapter {
t.Fatalf("Adapter: got %q want %q", got, tc.req.Adapter)
}
if got := resp.GetTarget(); got != tc.req.Target {
t.Fatalf("Target: got %q want %q", got, tc.req.Target)
}
if got := resp.GetSessionId(); got != tc.req.SessionId {
t.Fatalf("SessionId: got %q want %q", got, tc.req.SessionId)
}
})
}
}
// --- LookupAdapter / ambiguous error propagation tests ---
func TestOnCancel_TerminateSession_AmbiguousAdapterError(t *testing.T) {
ambigErr := fmt.Errorf("adapter \"ollama\" is ambiguous: matches instance keys [ollama@local ollama@dgx]; use an instance key")
router := &fixedRouter{
adapterName: "ollama",
adapters: make(map[string]runtime.Adapter),
lookupErrors: map[string]error{"ollama": ambigErr},
}
n, _ := makeNode(t, router)
err := n.OnCancel(context.Background(), &transport.Session{}, &iop.CancelRequest{
Adapter: "ollama",
Target: "llama3",
SessionId: "sess-1",
Action: iop.CancelAction_CANCEL_ACTION_TERMINATE_SESSION,
})
if err == nil {
t.Fatal("expected error for ambiguous adapter lookup")
}
if !strings.Contains(err.Error(), "ambiguous") {
t.Errorf("expected 'ambiguous' in error, got %v", err)
}
if !strings.Contains(err.Error(), "instance key") {
t.Errorf("expected 'instance key' guidance in error, got %v", err)
}
}
func TestOnCancel_TerminateSession_ExactInstanceKey(t *testing.T) {
ta := &terminatingAdapter{}
router := &fixedRouter{
adapterName: "ollama@local",
adapters: map[string]runtime.Adapter{"ollama@local": ta},
}
n, _ := makeNode(t, router)
err := n.OnCancel(context.Background(), &transport.Session{}, &iop.CancelRequest{
Adapter: "ollama@local",
Target: "llama3",
SessionId: "sess-a",
Action: iop.CancelAction_CANCEL_ACTION_TERMINATE_SESSION,
})
if err != nil {
t.Fatalf("OnCancel with exact instance key: %v", err)
}
if atomic.LoadInt32(&ta.terminateCalls) != 1 {
t.Fatal("expected TerminateSession to be called once")
}
if ta.lastTarget != "llama3" || ta.lastSessionID != "sess-a" {
t.Errorf("terminate args: target=%q session=%q", ta.lastTarget, ta.lastSessionID)
}
}
func TestOnCommandRequest_Capabilities_AmbiguousAdapter(t *testing.T) {
ambigErr := fmt.Errorf("adapter \"cli\" is ambiguous: matches instance keys [cli@claude cli@codex]; use an instance key")
router := &fixedRouter{
adapterName: "cli",
adapters: make(map[string]runtime.Adapter),
lookupErrors: map[string]error{"cli": ambigErr},
}
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-ambig-cap",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_CAPABILITIES,
Adapter: "cli",
Target: "codex",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), "ambiguous") {
t.Errorf("expected 'ambiguous' in response error, got %q", resp.GetError())
}
if !strings.Contains(resp.GetError(), "instance key") {
t.Errorf("expected 'instance key' guidance in response error, got %q", resp.GetError())
}
}
func TestOnCommandRequest_AdapterDispatch_AmbiguousAdapter(t *testing.T) {
ambigErr := fmt.Errorf("adapter \"cli\" is ambiguous: matches instance keys [cli@claude cli@codex]; use an instance key")
router := &fixedRouter{
adapterName: "cli",
adapters: make(map[string]runtime.Adapter),
lookupErrors: map[string]error{"cli": ambigErr},
}
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-ambig-cmd",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_USAGE_STATUS,
Adapter: "cli",
Target: "codex",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if !strings.Contains(resp.GetError(), "ambiguous") {
t.Errorf("expected 'ambiguous' in response error, got %q", resp.GetError())
}
}
func TestOnCommandRequest_MultiAdapterCapabilities(t *testing.T) {
ika1 := &instanceKeyAdapter{instanceKey: "ollama@local"}
ika2 := &instanceKeyAdapter{instanceKey: "ollama@dgx"}
router := &fixedRouter{
adapters: map[string]runtime.Adapter{
"ollama@local": ika1,
"ollama@dgx": ika2,
},
}
n, _ := makeNode(t, router)
cases := []struct {
adapter string
wantInstKey string
}{
{"ollama@local", "ollama@local"},
{"ollama@dgx", "ollama@dgx"},
}
instKeys := make([]string, 0, len(cases))
for _, tc := range cases {
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-multi-" + tc.adapter,
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_CAPABILITIES,
Adapter: tc.adapter,
Target: "llama3",
})
if err != nil {
t.Fatalf("CAPABILITIES %s: %v", tc.adapter, err)
}
if resp.GetError() != "" {
t.Fatalf("CAPABILITIES %s: unexpected error %q", tc.adapter, resp.GetError())
}
if got := resp.GetResult()["instance_key"]; got != tc.wantInstKey {
t.Errorf("CAPABILITIES %s: instance_key got %q want %q", tc.adapter, got, tc.wantInstKey)
}
if resp.GetAdapter() != tc.adapter {
t.Errorf("CAPABILITIES %s: response adapter got %q want %q", tc.adapter, resp.GetAdapter(), tc.adapter)
}
instKeys = append(instKeys, resp.GetResult()["instance_key"])
}
if instKeys[0] == instKeys[1] {
t.Errorf("expected distinct instance_key for distinct adapters, both got %q", instKeys[0])
}
}
func TestOnCommandRequest_Capabilities_ExactInstanceKey(t *testing.T) {
ika := &instanceKeyAdapter{instanceKey: "ollama@local"}
router := &fixedRouter{
adapterName: "ollama@local",
adapters: map[string]runtime.Adapter{"ollama@local": ika},
}
n, _ := makeNode(t, router)
resp, err := n.OnCommandRequest(context.Background(), &transport.Session{}, &iop.NodeCommandRequest{
RequestId: "req-exact-cap",
Type: iop.NodeCommandType_NODE_COMMAND_TYPE_CAPABILITIES,
Adapter: "ollama@local",
Target: "llama3",
})
if err != nil {
t.Fatalf("OnCommandRequest: %v", err)
}
if resp.GetError() != "" {
t.Fatalf("expected no error for exact instance key, got %q", resp.GetError())
}
if got := resp.GetResult()["adapter"]; got != "ollama" {
t.Errorf("result[adapter]: got %q want ollama", got)
}
if got := resp.GetResult()["instance_key"]; got != "ollama@local" {
t.Errorf("result[instance_key]: got %q want ollama@local", got)
}
}
// --- concurrency gate tests ---
// slowAdapter blocks until released, exposing a start channel so tests can
// synchronize. Execute returns nil on normal completion.
type slowAdapter struct {
started chan struct{}
release chan struct{}
}
func newSlowAdapter() *slowAdapter {
return &slowAdapter{started: make(chan struct{}, 1), release: make(chan struct{})}
}
func (a *slowAdapter) Name() string { return "slow" }
func (a *slowAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "slow", MaxConcurrency: 1}, nil
}
// slowAdapterUnlimited is like slowAdapter but reports MaxConcurrency=0 (unlimited).
type slowAdapterUnlimited struct {
started chan struct{}
release chan struct{}
}
func newSlowAdapterUnlimited() *slowAdapterUnlimited {
return &slowAdapterUnlimited{started: make(chan struct{}, 1), release: make(chan struct{})}
}
func (a *slowAdapterUnlimited) Name() string { return "slow" }
func (a *slowAdapterUnlimited) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "slow", MaxConcurrency: 0}, nil
}
func (a *slowAdapterUnlimited) Execute(ctx context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
select {
case a.started <- struct{}{}:
default:
}
select {
case <-a.release:
case <-ctx.Done():
return runtime.ErrRunCancelled
}
return nil
}
// slowHighCapAdapter is like slowAdapter but reports MaxConcurrency=4,
// used to verify that the global limit overrides a looser adapter cap.
type slowHighCapAdapter struct {
started chan struct{}
release chan struct{}
}
func newSlowHighCapAdapter() *slowHighCapAdapter {
return &slowHighCapAdapter{started: make(chan struct{}, 1), release: make(chan struct{})}
}
func (a *slowHighCapAdapter) Name() string { return "slow-hicap" }
func (a *slowHighCapAdapter) Capabilities(_ context.Context) (runtime.Capabilities, error) {
return runtime.Capabilities{AdapterName: "slow-hicap", MaxConcurrency: 4}, nil
}
func (a *slowHighCapAdapter) Execute(ctx context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
select {
case a.started <- struct{}{}:
default:
}
select {
case <-a.release:
case <-ctx.Done():
return runtime.ErrRunCancelled
}
return nil
}
func (a *slowAdapter) Execute(ctx context.Context, _ runtime.ExecutionSpec, _ runtime.EventSink) error {
select {
case a.started <- struct{}{}:
default:
}
select {
case <-a.release:
case <-ctx.Done():
return runtime.ErrRunCancelled
}
return nil
}
// TestConcurrencyLimit_RejectSecondForeground verifies that a second foreground
// run is rejected immediately when the global limit is 1 and one run is active.
func TestConcurrencyLimit_RejectSecondForeground(t *testing.T) {
sa := newSlowAdapter()
router := &fixedRouter{adapterName: "slow", adapters: map[string]runtime.Adapter{"slow": sa}}
n, _ := makeNodeWithConcurrency(t, router, 1)
errc := make(chan error, 1)
go func() {
errc <- n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-fg-1", Adapter: "slow", Target: "v1",
})
}()
// Wait until the first run has started executing.
select {
case <-sa.started:
case <-time.After(2 * time.Second):
t.Fatal("first run never started")
}
// Second run must be rejected.
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-fg-2", Adapter: "slow", Target: "v1",
})
if !errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("expected ErrConcurrencyLimitExceeded, got %v", err)
}
// Release the first run and drain it.
close(sa.release)
if err := <-errc; err != nil {
t.Fatalf("first run: %v", err)
}
}
// TestConcurrencyLimit_RejectBackgroundRun verifies that a background run is
// also subject to the global concurrency gate.
func TestConcurrencyLimit_RejectBackgroundRun(t *testing.T) {
sa := newSlowAdapter()
router := &fixedRouter{adapterName: "slow", adapters: map[string]runtime.Adapter{"slow": sa}}
n, _ := makeNodeWithConcurrency(t, router, 1)
errc := make(chan error, 1)
go func() {
errc <- n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-bg-hold", Adapter: "slow", Target: "v1",
})
}()
select {
case <-sa.started:
case <-time.After(2 * time.Second):
t.Fatal("hold run never started")
}
// Background run must also be rejected.
err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-bg-2", Adapter: "slow", Target: "v1", Background: true,
})
if !errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("expected ErrConcurrencyLimitExceeded for background run, got %v", err)
}
close(sa.release)
if err := <-errc; err != nil {
t.Fatalf("hold run: %v", err)
}
}
// TestConcurrencyLimit_PermitReleasedAfterCompletion verifies that after the
// first run completes, a subsequent run can acquire the permit.
func TestConcurrencyLimit_PermitReleasedAfterCompletion(t *testing.T) {
sa := newSlowAdapter()
router := &fixedRouter{adapterName: "slow", adapters: map[string]runtime.Adapter{"slow": sa}}
n, _ := makeNodeWithConcurrency(t, router, 1)
// First run: start, wait, release.
errc := make(chan error, 1)
go func() {
errc <- n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-seq-1", Adapter: "slow", Target: "v1",
})
}()
select {
case <-sa.started:
case <-time.After(2 * time.Second):
t.Fatal("seq-1 never started")
}
close(sa.release)
if err := <-errc; err != nil {
t.Fatalf("seq-1: %v", err)
}
// Second run must succeed now that the permit is free.
sa2 := newSlowAdapter()
router.adapters["slow"] = sa2
close(sa2.release) // let it complete immediately
if err := n.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-seq-2", Adapter: "slow", Target: "v1",
}); err != nil {
t.Fatalf("seq-2 should succeed after permit released, got %v", err)
}
}
// TestConcurrencyLimit_Unlimited verifies that global=0 + adapter cap=0 imposes no cap.
func TestConcurrencyLimit_Unlimited(t *testing.T) {
const count = 5
shared := newSlowAdapterUnlimited() // MaxConcurrency=0 (unlimited)
router := &fixedRouter{adapterName: "slow", adapters: map[string]runtime.Adapter{"slow": shared}}
nd, _ := makeNodeWithConcurrency(t, router, 0) // global unlimited
errs := make(chan error, count)
for i := 0; i < count; i++ {
runID := fmt.Sprintf("run-unlimited-%d", i)
go func(id string) {
errs <- nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: id, Adapter: "slow", Target: "v1",
})
}(runID)
}
// Release all.
close(shared.release)
// All must complete without ErrConcurrencyLimitExceeded.
for i := 0; i < count; i++ {
if err := <-errs; errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("unexpected concurrency rejection with limit=0: %v", err)
}
}
}
// TestConcurrencyLimit_AdapterCapFallback verifies that when global=0 and adapter
// cap=1, the adapter cap is used as the effective limit.
func TestConcurrencyLimit_AdapterCapFallback(t *testing.T) {
sa := newSlowAdapter() // MaxConcurrency=1
router := &fixedRouter{adapterName: "slow", adapters: map[string]runtime.Adapter{"slow": sa}}
nd, _ := makeNodeWithConcurrency(t, router, 0) // global=0 → use adapter cap
errc := make(chan error, 1)
go func() {
errc <- nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-cap-1", Adapter: "slow", Target: "v1",
})
}()
select {
case <-sa.started:
case <-time.After(2 * time.Second):
t.Fatal("run-cap-1 never started")
}
// Second run must be rejected by adapter cap.
err := nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-cap-2", Adapter: "slow", Target: "v1",
})
if !errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("expected ErrConcurrencyLimitExceeded from adapter cap, got %v", err)
}
close(sa.release)
if err := <-errc; err != nil {
t.Fatalf("run-cap-1: %v", err)
}
}
// TestConcurrencyLimit_GlobalBeatsAdapterCap verifies that when both global and
// adapter cap are > 0 and global < adapter cap, the global (stricter) limit applies.
func TestConcurrencyLimit_GlobalBeatsAdapterCap(t *testing.T) {
// slowHighCapAdapter reports MaxConcurrency=4; global=1 → effective=1.
sa := newSlowHighCapAdapter()
router := &fixedRouter{adapterName: "slow-hicap", adapters: map[string]runtime.Adapter{"slow-hicap": sa}}
nd, _ := makeNodeWithConcurrency(t, router, 1) // global=1, adapter cap=4 → effective=1
errc := make(chan error, 1)
go func() {
errc <- nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-g1-1", Adapter: "slow-hicap", Target: "v1",
})
}()
select {
case <-sa.started:
case <-time.After(2 * time.Second):
t.Fatal("run-g1-1 never started")
}
// Second run must be rejected by global limit=1 even though adapter cap=4.
err := nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-g1-2", Adapter: "slow-hicap", Target: "v1",
})
if !errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("expected ErrConcurrencyLimitExceeded (global=1 beats adapter cap=4), got %v", err)
}
close(sa.release)
if err := <-errc; err != nil {
t.Fatalf("run-g1-1: %v", err)
}
}
// TestConcurrencyLimit_GlobalBeatsAdapterCap_DifferentAdapters verifies that
// global=1 rejects a run on adapter B when adapter A already holds the global
// permit, even though both adapter caps are > 1.
func TestConcurrencyLimit_GlobalBeatsAdapterCap_DifferentAdapters(t *testing.T) {
saA := newSlowHighCapAdapter() // adapter "slow-hicap-a", MaxConcurrency=4
saB := newSlowHighCapAdapter() // adapter "slow-hicap-b", MaxConcurrency=4
router := &fixedRouter{
adapterName: "slow-hicap-a",
adapters: map[string]runtime.Adapter{
"slow-hicap-a": saA,
"slow-hicap-b": saB,
},
}
nd, _ := makeNodeWithConcurrency(t, router, 1) // global=1
// First run on adapter A: hold the global permit.
errc := make(chan error, 1)
go func() {
errc <- nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-xa-1", Adapter: "slow-hicap-a", Target: "v1",
})
}()
select {
case <-saA.started:
case <-time.After(2 * time.Second):
t.Fatal("run-xa-1 never started")
}
// Second run on adapter B must be rejected because global permit is taken.
router.adapterName = "slow-hicap-b"
err := nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-xb-1", Adapter: "slow-hicap-b", Target: "v1",
})
if !errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("expected ErrConcurrencyLimitExceeded for cross-adapter second run, got %v", err)
}
close(saA.release)
if err := <-errc; err != nil {
t.Fatalf("run-xa-1: %v", err)
}
}
// TestConcurrencyLimit_RejectStoreAndEvent verifies that a rejected run is stored
// with terminal status "rejected" and an error message is recorded.
func TestConcurrencyLimit_RejectStoreAndEvent(t *testing.T) {
sa := newSlowAdapter()
router := &fixedRouter{adapterName: "slow", adapters: map[string]runtime.Adapter{"slow": sa}}
nd, st := makeNodeWithConcurrency(t, router, 1)
errc := make(chan error, 1)
go func() {
errc <- nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-hold", Adapter: "slow", Target: "v1",
})
}()
select {
case <-sa.started:
case <-time.After(2 * time.Second):
t.Fatal("run-hold never started")
}
// Second run must be rejected.
err := nd.OnRunRequest(context.Background(), &transport.Session{}, &iop.RunRequest{
RunId: "run-rejected", Adapter: "slow", Target: "v1",
})
if !errors.Is(err, node.ErrConcurrencyLimitExceeded) {
t.Fatalf("expected ErrConcurrencyLimitExceeded, got %v", err)
}
// Rejected run must be stored with status "rejected".
run, err := st.GetRun(context.Background(), "run-rejected")
if err != nil {
t.Fatalf("GetRun: %v", err)
}
if run == nil {
t.Fatal("expected rejected run to be stored")
}
if run.Status != "rejected" {
t.Fatalf("expected status %q, got %q", "rejected", run.Status)
}
if run.Error == "" {
t.Fatal("expected non-empty error message for rejected run")
}
close(sa.release)
if err := <-errc; err != nil {
t.Fatalf("run-hold: %v", err)
}
}