package main
import (
"context"
"encoding/json"
"errors"
"net/http"
"path/filepath"
"strings"
"sync"
"testing"
"time"
"github.com/stretchr/testify/require"
)
func TestTurnRunsToolsUntilTheFinalAnswer(t *testing.T) {
server := newModelFake(t)
server.reply = func(w http.ResponseWriter, call ModelFakeCall) {
if call.number == 0 {
modelWriteEvents(w, modelCompletedEvent([]any{
modelReasoningItem("rs_1", "opaque thought"),
modelFunctionCallItem("fc_1", "call_1", "shell", `{"command":"echo hi"}`),
}, 100, 0, 5))
return
}
modelWriteEvents(w, modelCompletedEvent([]any{modelMessageItem("It said hi.")}, 120, 100, 5))
}
test := newTestTurnLoop(t, server)
_, err := test.loop.Submit(terminalSource, "Run echo hi.")
require.NoError(t, err)
test.events.WaitFor(t, "idle", 1)
require.Equal(t, 2, server.Calls())
first := server.Call(0).body
second := server.Call(1).body
instructions, err := test.agent.Prompt()
require.NoError(t, err)
require.Equal(t, instructions, first["instructions"])
require.Equal(t, test.agent.config.Model, first["model"])
// The second request begins with the whole first one.
firstInput := first["input"].([]any)
secondInput := second["input"].([]any)
require.Equal(t, firstInput, secondInput[:len(firstInput)])
require.Equal(t, []any{
map[string]any{"type": "reasoning", "encrypted_content": "opaque thought", "summary": []any{}},
map[string]any{"type": "function_call", "call_id": "call_1", "name": "shell", "arguments": `{"command":"echo hi"}`},
map[string]any{"type": "function_call_output", "call_id": "call_1", "output": "hi\n"},
}, secondInput[len(firstInput):])
require.Equal(t, []string{
"user: Run echo hi.",
`tool: shell {"command":"echo hi"}`,
"echo: hi\n",
"reply: It said hi.",
}, test.Log(t))
require.Equal(t, []string{"user", "busy", "tool", "echo", "reply", "idle"}, test.events.Kinds())
var turns []string
for _, record := range modelReadUsage(t, test.usagePath) {
turns = append(turns, record.Turn)
}
require.Equal(t, []string{"first", "next"}, turns)
}
func TestFirstRequestHoldsTheViewTheStateAndTheMessage(t *testing.T) {
server := newModelFake(t)
test := newTestTurnLoop(t, server)
_, err := test.memory.Append("user", "an earlier message")
require.NoError(t, err)
_, err = test.loop.Submit(terminalSource, "The new message.")
require.NoError(t, err)
test.events.WaitFor(t, "idle", 1)
require.Equal(t, []string{
"\n0+1|user: an earlier message\n",
"\n\nNow: Thursday 2026-01-01 12:00 +00:00",
"The new message.",
}, turnInputTexts(t, server.Call(0)))
}
func TestMessageDuringATurnJoinsTheNextRequest(t *testing.T) {
server := newModelFake(t)
arrived := make(chan struct{})
release := make(chan struct{})
server.reply = func(w http.ResponseWriter, call ModelFakeCall) {
if call.number == 0 {
close(arrived)
<-release
modelWriteEvents(w, modelCompletedEvent([]any{modelFunctionCallItem("fc_1", "call_1", "date", `{"id":0}`)}, 100, 0, 5))
return
}
modelWriteEvents(w, modelCompletedEvent([]any{modelMessageItem("done")}, 100, 0, 5))
}
test := newTestTurnLoop(t, server)
_, err := test.loop.Submit(terminalSource, "first")
require.NoError(t, err)
<-arrived
_, err = test.loop.Submit(terminalSource, "second, during the turn")
require.NoError(t, err)
close(release)
test.events.WaitFor(t, "idle", 1)
input := server.Call(1).body["input"].([]any)
require.Equal(t, map[string]any{
"role": "user",
"content": []any{map[string]any{"type": "input_text", "text": "second, during the turn"}},
}, input[len(input)-1])
time.Sleep(50 * time.Millisecond)
require.Equal(t, 2, server.Calls())
require.Equal(t, 1, test.events.Count("busy"))
}
func TestMessageDuringTheFinalRequestStartsANewTurn(t *testing.T) {
server := newModelFake(t)
arrived := make(chan struct{})
release := make(chan struct{})
server.reply = func(w http.ResponseWriter, call ModelFakeCall) {
if call.number == 0 {
close(arrived)
<-release
}
modelWriteEvents(w, modelCompletedEvent([]any{modelMessageItem("answer")}, 100, 0, 5))
}
test := newTestTurnLoop(t, server)
_, err := test.loop.Submit(terminalSource, "first")
require.NoError(t, err)
<-arrived
_, err = test.loop.Submit(terminalSource, "second")
require.NoError(t, err)
close(release)
test.events.WaitFor(t, "idle", 2)
require.Equal(t, 2, server.Calls())
texts := turnInputTexts(t, server.Call(1))
require.Equal(t, "second", texts[len(texts)-1])
require.Contains(t, strings.Join(texts, ""), "|reply: answer\n")
}
func TestTurnWaitsForTheSummaries(t *testing.T) {
server := newModelFake(t)
summarizer := newFakeSummarizer()
summarizer.gate = make(chan struct{})
test := newTestTurnLoopWith(t, server, summarizer)
_, err := test.memory.Append("echo", strings.Repeat("long output ", 100))
require.NoError(t, err)
_, err = test.loop.Submit(terminalSource, "go on")
require.NoError(t, err)
time.Sleep(50 * time.Millisecond)
require.Equal(t, 0, server.Calls())
close(summarizer.gate)
test.events.WaitFor(t, "idle", 1)
require.Equal(t, 1, server.Calls())
require.NotContains(t, turnInputTexts(t, server.Call(0))[0], viewPending)
}
func TestInterruptEndsTheTurn(t *testing.T) {
server := newModelFake(t)
arrived := make(chan struct{})
release := make(chan struct{})
server.reply = func(w http.ResponseWriter, call ModelFakeCall) {
if call.number == 0 {
close(arrived)
<-release
}
modelWriteEvents(w, modelCompletedEvent([]any{modelMessageItem("answer")}, 100, 0, 5))
}
test := newTestTurnLoop(t, server)
_, err := test.loop.Submit(terminalSource, "a long task")
require.NoError(t, err)
<-arrived
require.True(t, test.loop.Interrupt())
test.events.WaitFor(t, "idle", 1)
close(release)
require.Equal(t, "interrupted", test.events.Last("error"))
require.Equal(t, []string{"user: a long task"}, test.Log(t))
require.False(t, test.loop.Interrupt())
_, err = test.loop.Submit(terminalSource, "again")
require.NoError(t, err)
test.events.WaitFor(t, "idle", 2)
require.Equal(t, "reply: answer", test.Log(t)[2])
}
func TestFailedCallEndsTheTurnWithoutARetry(t *testing.T) {
server := newModelFake(t)
server.reply = func(w http.ResponseWriter, call ModelFakeCall) {
http.Error(w, "busy", http.StatusServiceUnavailable)
}
test := newTestTurnLoop(t, server)
_, err := test.loop.Submit(terminalSource, "hello")
require.NoError(t, err)
test.events.WaitFor(t, "idle", 1)
time.Sleep(50 * time.Millisecond)
require.Equal(t, 1, server.Calls())
require.Contains(t, test.events.Last("error"), "HTTP 503")
}
func TestViewMessagesOnlyGrowBetweenTurns(t *testing.T) {
server := newModelFake(t)
test := newTestTurnLoop(t, server)
for n, text := range []string{"one", "two", "three"} {
_, err := test.loop.Submit(terminalSource, text)
require.NoError(t, err)
test.events.WaitFor(t, "idle", n+1)
}
first := server.Call(1).body["input"].([]any)
second := server.Call(2).body["input"].([]any)
require.Len(t, first, 4)
require.Len(t, second, 5)
require.Equal(t, first[:2], second[:2])
require.Equal(t, []string{
"\n",
"0+1|user: one\n1+1|reply: a line\n",
"2+1|user: two\n3+1|reply: a line\n",
"\n\nNow: Thursday 2026-01-01 12:00 +00:00",
"three",
}, turnInputTexts(t, server.Call(2)))
}
// TurnTestLoop is a loop that runs in the background of a test, with its parts.
type TurnTestLoop struct {
agent *Agent
memory *Memory
loop *TurnLoop
events *TurnEventRecorder
usagePath string
}
// Log returns the logged messages as "kind: text".
func (l *TurnTestLoop) Log(t *testing.T) []string {
t.Helper()
var lines []string
for id := range l.memory.Len() {
message, err := l.memory.Message(id)
require.NoError(t, err)
lines = append(lines, message.Kind+": "+message.Text)
}
return lines
}
// TurnEventRecorder keeps the events of a loop.
type TurnEventRecorder struct {
mutex sync.Mutex
events []Event
}
// WaitFor waits until count events of kind came.
func (r *TurnEventRecorder) WaitFor(t *testing.T, kind string, count int) {
t.Helper()
require.Eventually(t, func() bool {
return r.Count(kind) >= count
}, 10*time.Second, time.Millisecond)
}
func (r *TurnEventRecorder) Kinds() []string {
r.mutex.Lock()
defer r.mutex.Unlock()
kinds := make([]string, len(r.events))
for n, event := range r.events {
kinds[n] = event.Kind
}
return kinds
}
func (r *TurnEventRecorder) Count(kind string) int {
count := 0
for _, each := range r.Kinds() {
if each == kind {
count++
}
}
return count
}
// Last returns the text of the last event of kind.
func (r *TurnEventRecorder) Last(kind string) string {
r.mutex.Lock()
defer r.mutex.Unlock()
for n := len(r.events) - 1; n >= 0; n-- {
if r.events[n].Kind == kind {
return r.events[n].Text
}
}
return ""
}
func (r *TurnEventRecorder) Add(event Event) {
r.mutex.Lock()
defer r.mutex.Unlock()
r.events = append(r.events, event)
}
func newTestTurnLoop(t *testing.T, server *ModelFake) *TurnTestLoop {
t.Helper()
return newTestTurnLoopWith(t, server, newFakeSummarizer())
}
// turnInputTexts returns the text of each user message of the input of call.
func turnInputTexts(t *testing.T, call ModelFakeCall) []string {
t.Helper()
var body struct {
Input []struct {
Role string `json:"role"`
Content []struct {
Text string `json:"text"`
} `json:"content"`
} `json:"input"`
}
require.NoError(t, json.Unmarshal(call.raw, &body))
var texts []string
for _, item := range body.Input {
if item.Role != "user" {
continue
}
var text strings.Builder
for _, part := range item.Content {
text.WriteString(part.Text)
}
texts = append(texts, text.String())
}
return texts
}
// newTestTurnLoopWith returns a running loop on a new agent whose builds use
// summarizer and whose commands run in a temporary directory.
func newTestTurnLoopWith(t *testing.T, server *ModelFake, summarizer Summarizer) *TurnTestLoop {
t.Helper()
agent, err := openAgent(t.TempDir())
require.NoError(t, err)
agent.config.Workdir = t.TempDir()
clock := newTestClock()
memory, err := openMemory(t.Context(), t.TempDir(), clock.Now, summarizer)
require.NoError(t, err)
test := &TurnTestLoop{
agent: agent,
memory: memory,
events: &TurnEventRecorder{},
usagePath: filepath.Join(t.TempDir(), "usage.jsonl"),
}
client := newModelClient(server.URL, ModelAPIKey(modelTestKey), agent.CacheKey(), test.usagePath)
test.loop, err = newTurnLoop(agent, memory, newTestSubagents(t), client, clock.Now, test.events.Add)
require.NoError(t, err)
ctx, cancel := context.WithCancel(t.Context())
done := make(chan error)
go func() {
done <- test.loop.Run(ctx)
}()
t.Cleanup(func() {
cancel()
require.True(t, errors.Is(<-done, context.Canceled))
require.NoError(t, memory.Close())
})
return test
}