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 := newFakeResponses(t) server.reply = func(w http.ResponseWriter, call fakeCall) { if call.number == 0 { writeEvents(w, completedEvent([]any{ reasoningItem("rs_1", "opaque thought"), functionCallItem("fc_1", "call_1", "shell", `{"command":"echo hi"}`), }, 100, 0, 5)) return } writeEvents(w, completedEvent([]any{messageItem("It said hi.")}, 120, 100, 5)) } test := newTestLoop(t, server) _, err := test.loop.Submit("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()) } func TestFirstRequestHoldsTheViewTheStateAndTheMessage(t *testing.T) { server := newFakeResponses(t) test := newTestLoop(t, server) _, err := test.memory.Append("user", "an earlier message") require.NoError(t, err) _, err = test.loop.Submit("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.", }, inputTexts(t, server.Call(0))) } func TestMessageDuringATurnJoinsTheNextRequest(t *testing.T) { server := newFakeResponses(t) arrived := make(chan struct{}) release := make(chan struct{}) server.reply = func(w http.ResponseWriter, call fakeCall) { if call.number == 0 { close(arrived) <-release writeEvents(w, completedEvent([]any{functionCallItem("fc_1", "call_1", "date", `{"id":0}`)}, 100, 0, 5)) return } writeEvents(w, completedEvent([]any{messageItem("done")}, 100, 0, 5)) } test := newTestLoop(t, server) _, err := test.loop.Submit("first") require.NoError(t, err) <-arrived _, err = test.loop.Submit("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 := newFakeResponses(t) arrived := make(chan struct{}) release := make(chan struct{}) server.reply = func(w http.ResponseWriter, call fakeCall) { if call.number == 0 { close(arrived) <-release } writeEvents(w, completedEvent([]any{messageItem("answer")}, 100, 0, 5)) } test := newTestLoop(t, server) _, err := test.loop.Submit("first") require.NoError(t, err) <-arrived _, err = test.loop.Submit("second") require.NoError(t, err) close(release) test.events.WaitFor(t, "idle", 2) require.Equal(t, 2, server.Calls()) texts := inputTexts(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 := newFakeResponses(t) summarizer := newFakeSummarizer() summarizer.gate = make(chan struct{}) test := newTestLoopWith(t, server, summarizer, false) _, err := test.memory.Append("echo", strings.Repeat("long output ", 100)) require.NoError(t, err) _, err = test.loop.Submit("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, inputTexts(t, server.Call(0))[0], pending) } func TestInterruptEndsTheTurn(t *testing.T) { server := newFakeResponses(t) arrived := make(chan struct{}) release := make(chan struct{}) server.reply = func(w http.ResponseWriter, call fakeCall) { if call.number == 0 { close(arrived) <-release } writeEvents(w, completedEvent([]any{messageItem("answer")}, 100, 0, 5)) } test := newTestLoop(t, server) _, err := test.loop.Submit("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("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 := newFakeResponses(t) server.reply = func(w http.ResponseWriter, call fakeCall) { http.Error(w, "busy", http.StatusServiceUnavailable) } test := newTestLoop(t, server) _, err := test.loop.Submit("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 := newFakeResponses(t) test := newTestLoop(t, server) for n, text := range []string{"one", "two", "three"} { _, err := test.loop.Submit(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", }, inputTexts(t, server.Call(2))) } func TestWarmUpEndsWhereTheNextTurnReadsTheCache(t *testing.T) { server := newFakeResponses(t) server.reply = func(w http.ResponseWriter, call fakeCall) { if call.number == 1 { writeEvents(w, map[string]any{"type": "response.output_item.added", "item": reasoningItem("rs_1", "")}) return } writeEvents(w, completedEvent([]any{messageItem("answer")}, 100, 0, 5)) } test := newTestLoopWith(t, server, newFakeSummarizer(), true) _, err := test.loop.Submit("one") require.NoError(t, err) require.Eventually(t, func() bool { return server.Calls() == 2 }, 10*time.Second, time.Millisecond) _, err = test.loop.Submit("two") require.NoError(t, err) test.events.WaitFor(t, "idle", 2) require.Eventually(t, func() bool { return server.Calls() == 4 }, 10*time.Second, time.Millisecond) warmUp := server.Call(1).body require.Equal(t, server.Call(0).body["instructions"], warmUp["instructions"]) require.Equal(t, server.Call(0).body["tools"], warmUp["tools"]) require.Equal(t, []string{"\n", "0+1|user: one\n1+1|reply: answer\n"}, inputTexts(t, server.Call(1))) // The next turn begins with the whole warm-up, so its message end after // the view is the end of the warm-up entry. warmInput := warmUp["input"].([]any) turnInput := server.Call(2).body["input"].([]any) require.Equal(t, warmInput, turnInput[:len(warmInput)]) require.Equal(t, "\n\nNow: Thursday 2026-01-01 12:00 +00:00", inputTexts(t, server.Call(2))[len(warmInput)]) turns := []string{} for _, record := range readUsage(t, test.usagePath) { turns = append(turns, record.Turn) } require.Equal(t, []string{"first", "warmup", "first", "warmup"}, turns) require.Equal(t, []string{"user: one", "reply: answer", "user: two", "reply: answer"}, test.Log(t)) } // testLoop is a loop that runs in the background of a test, with its parts. type testLoop struct { agent *Agent memory *Memory loop *loop events *eventRecorder usagePath string } // Log returns the logged messages as "kind: text". func (l *testLoop) 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 } // eventRecorder keeps the events of a loop. type eventRecorder struct { mutex sync.Mutex events []Event } func (r *eventRecorder) Add(event Event) { r.mutex.Lock() defer r.mutex.Unlock() r.events = append(r.events, event) } func (r *eventRecorder) 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 *eventRecorder) 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 *eventRecorder) 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 "" } // WaitFor waits until count events of kind came. func (r *eventRecorder) 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 newTestLoop(t *testing.T, server *fakeResponses) *testLoop { t.Helper() return newTestLoopWith(t, server, newFakeSummarizer(), false) } // newTestLoopWith returns a running loop on a new agent whose builds use // summarizer and whose commands run in a temporary directory. warmUp turns the // warm-up on. func newTestLoopWith(t *testing.T, server *fakeResponses, summarizer Summarizer, warmUp bool) *testLoop { 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 := &testLoop{ agent: agent, memory: memory, events: &eventRecorder{}, usagePath: filepath.Join(t.TempDir(), "usage.jsonl"), } client := newClient(server.URL, apiKey(testKey), agent.CacheKey(), test.usagePath) test.loop, err = newLoop(agent, memory, client, clock.Now, test.events.Add) require.NoError(t, err) test.loop.warmUp = warmUp 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 } // inputTexts returns the text of each user message of the input of call. func inputTexts(t *testing.T, call fakeCall) []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 } func reasoningItem(id, encrypted string) map[string]any { return map[string]any{ "type": "reasoning", "id": id, "encrypted_content": encrypted, "summary": []any{}, } } func functionCallItem(id, callID, name, arguments string) map[string]any { return map[string]any{ "type": "function_call", "id": id, "call_id": callID, "name": name, "arguments": arguments, } }