iop/apps/node/internal/adapters/cli/persistent_execute_blackbox_test.go

537 lines
15 KiB
Go

package cli_test
import (
"context"
"strings"
"testing"
"time"
"go.uber.org/zap"
clipkg "iop/apps/node/internal/adapters/cli"
"iop/apps/node/internal/adapters/cli/internal/testutil"
noderuntime "iop/apps/node/internal/runtime"
"iop/packages/config"
)
func TestCLIExecutePersistentWaitsForSlowFirstOutput(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"slow-echo": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do sleep 0.2; printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 50,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
execCtx, cancel := context.WithTimeout(ctx, 1*time.Second)
defer cancel()
sink := &testutil.FakeSink{}
err := c.Execute(execCtx, noderuntime.ExecutionSpec{
RunID: "run-1",
Model: "slow-echo",
Input: map[string]any{"prompt": "hello"},
}, sink)
if err != nil {
t.Fatalf("execute: %v", err)
}
events := sink.Events()
if events[len(events)-1].Type != noderuntime.EventTypeComplete {
t.Fatalf("expected last event to be complete, got %q", events[len(events)-1].Type)
}
if combined := testutil.CollectDeltas(events); !strings.Contains(combined, "reply:hello") {
t.Fatalf("expected reply:hello in deltas, got %q", combined)
}
}
func TestCLIExecutePersistentProcessExitReturnsError(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"exit-on-input": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do printf "before-exit\n"; exit 2; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 500,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
sink := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-1",
Model: "exit-on-input",
Input: map[string]any{"prompt": "hello"},
}, sink)
if err == nil {
t.Fatal("expected non-nil error when persistent process exits")
}
events := sink.Events()
var hasError bool
for _, e := range events {
if e.Type == noderuntime.EventTypeError {
hasError = true
}
}
if !hasError {
t.Fatal("expected error event in emitted events")
}
if len(events) > 0 && events[len(events)-1].Type == noderuntime.EventTypeComplete {
t.Fatal("last event should not be complete when process exits unexpectedly")
}
}
func TestCLIStartPersistentTerminalAndExecuteWritesPrompt(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"echo-persistent": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 300,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
sink := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-1",
Model: "echo-persistent",
Input: map[string]any{"prompt": "hello"},
}, sink)
if err != nil {
t.Fatalf("execute: %v", err)
}
events := sink.Events()
var started, completed bool
for _, e := range events {
switch e.Type {
case noderuntime.EventTypeStart:
started = true
case noderuntime.EventTypeComplete:
completed = true
}
}
if !started {
t.Fatal("expected start event")
}
if !completed {
t.Fatal("expected complete event")
}
if combined := testutil.CollectDeltas(events); !strings.Contains(combined, "reply:hello") {
t.Fatalf("expected reply:hello in deltas, got %q", combined)
}
}
// TestCLIExecutePersistentCancelDoesNotTerminateSession verifies that a
// cancelled run leaves the session alive so subsequent runs can reuse it.
func TestCLIExecutePersistentCancelDoesNotTerminateSession(t *testing.T) {
testutil.RequirePTYSupport(t)
// ResponseIdleTimeoutMS is short so the cancel-drain exits quickly,
// allowing the second execute to acquire the session lock promptly.
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"slow-echo": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do sleep 0.05; printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 150,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
// First execute: cancel before idle timeout fires.
firstCtx, firstCancel := context.WithTimeout(ctx, 100*time.Millisecond)
defer firstCancel()
sink1 := &testutil.FakeSink{}
_ = c.Execute(firstCtx, noderuntime.ExecutionSpec{
RunID: "run-1",
Model: "slow-echo",
Input: map[string]any{"prompt": "first"},
}, sink1)
// Give time for cancel drain to finish (drain uses idleTimeout=150ms).
time.Sleep(400 * time.Millisecond)
// Second execute on same session — must succeed (session still alive).
execCtx, cancel := context.WithTimeout(ctx, 3*time.Second)
defer cancel()
sink2 := &testutil.FakeSink{}
err := c.Execute(execCtx, noderuntime.ExecutionSpec{
RunID: "run-2",
Model: "slow-echo",
Input: map[string]any{"prompt": "second"},
}, sink2)
if err != nil {
t.Fatalf("second execute after cancel must succeed (session should be alive): %v", err)
}
events2 := sink2.Events()
if len(events2) == 0 || events2[len(events2)-1].Type != noderuntime.EventTypeComplete {
t.Fatalf("expected complete event on second run, got %v", events2)
}
}
func TestCLIExecutePersistentConsecutiveExecutes(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"consecutive-echo": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 100,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
sink1 := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-1",
Model: "consecutive-echo",
Input: map[string]any{"prompt": "first"},
}, sink1)
if err != nil {
t.Fatalf("first execute: %v", err)
}
events1 := sink1.Events()
if events1[len(events1)-1].Type != noderuntime.EventTypeComplete {
t.Fatalf("first run: expected last event to be complete, got %q", events1[len(events1)-1].Type)
}
sink2 := &testutil.FakeSink{}
err = c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-2",
Model: "consecutive-echo",
Input: map[string]any{"prompt": "second"},
}, sink2)
if err != nil {
t.Fatalf("second execute: %v", err)
}
events2 := sink2.Events()
if events2[len(events2)-1].Type != noderuntime.EventTypeComplete {
t.Fatalf("second run: expected last event to be complete, got %q", events2[len(events2)-1].Type)
}
for _, e := range events2 {
if e.Type == noderuntime.EventTypeDelta && strings.Contains(e.Delta, "first") {
t.Fatalf("second run received first run's delta (session contamination): %q", e.Delta)
}
}
}
func TestCLIExecutePersistentCreatesIndependentSessionsForSameProfile(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"multi-echo": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 200,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
sinkA := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-a",
Model: "multi-echo",
SessionID: "session-a",
Input: map[string]any{"prompt": "alpha"},
}, sinkA)
if err != nil {
t.Fatalf("session-a execute: %v", err)
}
sinkB := &testutil.FakeSink{}
err = c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-b",
Model: "multi-echo",
SessionID: "session-b",
Input: map[string]any{"prompt": "beta"},
}, sinkB)
if err != nil {
t.Fatalf("session-b execute: %v", err)
}
if combined := testutil.CollectDeltas(sinkA.Events()); !strings.Contains(combined, "alpha") {
t.Fatalf("session-a: expected alpha in deltas, got %q", combined)
}
if combined := testutil.CollectDeltas(sinkB.Events()); !strings.Contains(combined, "beta") {
t.Fatalf("session-b: expected beta in deltas, got %q", combined)
}
if combined := testutil.CollectDeltas(sinkA.Events()); strings.Contains(combined, "beta") {
t.Fatalf("session-a contaminated with session-b output: %q", combined)
}
}
func TestCLIExecutePersistentRequireExistingSessionFailsWhenMissing(t *testing.T) {
testutil.RequireUnixShell(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"echo-req": {
Command: "sh",
Args: []string{"-c", `while IFS= read -r line; do printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: false,
ResponseIdleTimeoutMS: 200,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
sink := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-1",
Model: "echo-req",
SessionID: "nonexistent",
SessionMode: noderuntime.SessionModeRequireExisting,
Input: map[string]any{"prompt": "hello"},
}, sink)
if err == nil {
t.Fatal("expected error for require-existing with missing session")
}
if strings.Contains(err.Error(), "start") {
t.Fatalf("should not have started a new process, got: %v", err)
}
}
func TestCLIExecutePersistent_UserCancelEmitsUserCancelMessage(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"slow-echo": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do sleep 10; printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 500,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
execCtx, cancel := context.WithCancel(ctx)
sink := &testutil.FakeSink{}
go func() {
time.Sleep(100 * time.Millisecond)
cancel()
}()
err := c.Execute(execCtx, noderuntime.ExecutionSpec{
RunID: "run-usercancel",
Model: "slow-echo",
Input: map[string]any{"prompt": "hello"},
}, sink)
if err == nil {
t.Fatalf("expected error, got nil")
}
events := sink.Events()
var lastMsg string
var cancelEvent bool
for i := len(events) - 1; i >= 0; i-- {
if events[i].Type == noderuntime.EventTypeCancelled {
cancelEvent = true
lastMsg = events[i].Message
}
}
if !cancelEvent {
t.Fatal("expected cancelled event")
}
if lastMsg != "user-cancel" {
t.Fatalf("expected cancel Message 'user-cancel', got %q", lastMsg)
}
}
func TestCLIExecutePersistent_TimeoutEmitsTimeoutMessage(t *testing.T) {
testutil.RequirePTYSupport(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"slow-echo": {
Command: "sh",
Args: []string{"-c", `stty -echo; while IFS= read -r line; do sleep 10; printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: true,
ResponseIdleTimeoutMS: 500,
StartupIdleTimeoutMS: 50,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
if err := c.Start(ctx); err != nil {
t.Fatalf("start: %v", err)
}
defer func() { _ = c.Stop(ctx) }()
execCtx, cancel := context.WithTimeout(ctx, 100*time.Millisecond)
defer cancel()
sink := &testutil.FakeSink{}
executeErr := c.Execute(execCtx, noderuntime.ExecutionSpec{
RunID: "run-timeout",
Model: "slow-echo",
Input: map[string]any{"prompt": "hello"},
}, sink)
if executeErr == nil {
t.Fatalf("expected error, got nil")
}
events := sink.Events()
var lastMsg string
var cancelEvent bool
for i := len(events) - 1; i >= 0; i-- {
if events[i].Type == noderuntime.EventTypeCancelled {
cancelEvent = true
lastMsg = events[i].Message
}
}
if !cancelEvent {
t.Fatal("expected cancelled event")
}
if lastMsg != "timeout" {
t.Fatalf("expected cancel Message 'timeout', got %q", lastMsg)
}
}
func TestCLIExecutePersistentMaintainsHundredLogicalSessions(t *testing.T) {
if testing.Short() {
t.Skip("skipping heavy session test in short mode")
}
testutil.RequireUnixShell(t)
cfg := config.CLIConf{
Enabled: true,
Profiles: map[string]config.CLIProfileConf{
"hundred-echo": {
Command: "sh",
Args: []string{"-c", `while IFS= read -r line; do printf "reply:%s\n" "$line"; done`},
Persistent: true,
Terminal: false,
ResponseIdleTimeoutMS: 300,
},
},
}
c := clipkg.New(cfg, zap.NewNop())
ctx := context.Background()
const n = 100
for i := 0; i < n; i++ {
sessionID := "session-" + string(rune('a'+i%26)) + "-" + string(rune('0'+i/26))
sink := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-first-" + sessionID,
Model: "hundred-echo",
SessionID: sessionID,
Input: map[string]any{"prompt": "ping-" + sessionID},
}, sink)
if err != nil {
t.Fatalf("session %q first execute: %v", sessionID, err)
}
}
// Second round — all sessions must still be alive.
for i := 0; i < n; i++ {
sessionID := "session-" + string(rune('a'+i%26)) + "-" + string(rune('0'+i/26))
sink := &testutil.FakeSink{}
err := c.Execute(ctx, noderuntime.ExecutionSpec{
RunID: "run-second-" + sessionID,
Model: "hundred-echo",
SessionID: sessionID,
Input: map[string]any{"prompt": "pong-" + sessionID},
}, sink)
if err != nil {
t.Fatalf("session %q second execute: %v", sessionID, err)
}
}
_ = c.Stop(ctx)
}