1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
|
package executor
import (
"context"
"encoding/json"
"errors"
"io"
"log/slog"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"strings"
"sync"
"testing"
"github.com/google/uuid"
"github.com/thepeterstone/claudomator/internal/llm"
"github.com/thepeterstone/claudomator/internal/storage"
"github.com/thepeterstone/claudomator/internal/task"
)
// fakeTurn is one canned chat-completion response the fake server returns.
type fakeTurn struct {
content string
toolCalls []llm.ToolCall
promptTok int
outTok int
}
// fakeChatServer replies to /chat/completions with the supplied turns in order,
// one per request (non-streaming JSON), so a tool-use loop can be driven
// deterministically. Requests beyond the list repeat the final turn.
func fakeChatServer(t *testing.T, turns []fakeTurn) *httptest.Server {
t.Helper()
var mu sync.Mutex
idx := 0
return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
mu.Lock()
turn := turns[idx]
if idx < len(turns)-1 {
idx++
}
mu.Unlock()
msg := map[string]any{"role": "assistant", "content": turn.content}
if len(turn.toolCalls) > 0 {
msg["tool_calls"] = turn.toolCalls
}
resp := map[string]any{
"model": "fake",
"choices": []map[string]any{{"message": msg, "finish_reason": "stop"}},
"usage": map[string]int{"prompt_tokens": turn.promptTok, "completion_tokens": turn.outTok},
}
_ = json.NewEncoder(w).Encode(resp)
}))
}
func toolCall(id, name, args string) llm.ToolCall {
return llm.ToolCall{ID: id, Type: "function", Function: llm.ToolCallFunction{Name: name, Arguments: args}}
}
func newLocalRunner(t *testing.T, srv *httptest.Server) *LocalRunner {
t.Helper()
return &LocalRunner{
Client: &llm.Client{Endpoint: srv.URL + "/v1", Model: "fake"},
Logger: slog.New(slog.NewTextHandler(io.Discard, nil)),
LogDir: t.TempDir(),
}
}
func localTask() *task.Task {
return &task.Task{
ID: "task-1",
Name: "test",
Agent: task.AgentConfig{
Type: "local",
Model: "fake",
Instructions: "Do a thing.",
SkipPlanning: true, // keep the preamble out of these assertions
},
}
}
func TestLocalRunner_Run_WritesStreamJSON(t *testing.T) {
srv := fakeChatServer(t, []fakeTurn{{content: "## Summary\nAll good.", promptTok: 11, outTok: 22}})
defer srv.Close()
r := newLocalRunner(t, srv)
tt := localTask()
exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
if err := r.Run(context.Background(), tt, exec, newStoreChannel(&fakeChannelStore{}, tt.ID)); err != nil {
t.Fatalf("Run: %v", err)
}
if exec.CostUSD != 0 {
t.Errorf("CostUSD should be 0 for local runner, got %v", exec.CostUSD)
}
if exec.TokensIn != 11 || exec.TokensOut != 22 {
t.Errorf("tokens: want 11/22 got %d/%d", exec.TokensIn, exec.TokensOut)
}
stdoutPath := filepath.Join(r.ExecLogDir(exec.ID), "stdout.log")
data, err := os.ReadFile(stdoutPath)
if err != nil {
t.Fatalf("read stdout: %v", err)
}
lines := strings.Split(strings.TrimSpace(string(data)), "\n")
// One assistant envelope + one result line.
if len(lines) != 2 {
t.Fatalf("expected 2 lines (assistant + result), got %d:\n%s", len(lines), data)
}
var env struct {
Type string `json:"type"`
}
if err := json.Unmarshal([]byte(lines[0]), &env); err != nil || env.Type != "assistant" {
t.Fatalf("line 0 should be an assistant envelope: %v: %s", err, lines[0])
}
if summary := extractSummary(stdoutPath); !strings.Contains(summary, "All good.") {
t.Errorf("extractSummary should find 'All good.', got %q", summary)
}
}
func TestLocalRunner_Run_ToolLoop_ReportSummaryAndSpawn(t *testing.T) {
// Turn 1: model spawns a subtask. Turn 2: reports summary. Turn 3: finishes.
srv := fakeChatServer(t, []fakeTurn{
{toolCalls: []llm.ToolCall{toolCall("c1", "spawn_subtask", `{"name":"sub A","instructions":"do sub"}`)}, promptTok: 5, outTok: 3},
{toolCalls: []llm.ToolCall{toolCall("c2", "report_summary", `{"summary":"all done"}`)}, promptTok: 4, outTok: 2},
{content: "finished", promptTok: 2, outTok: 1},
})
defer srv.Close()
r := newLocalRunner(t, srv)
tt := localTask()
store := &fakeChannelStore{}
ch := newStoreChannel(store, tt.ID)
exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
if err := r.Run(context.Background(), tt, exec, ch); err != nil {
t.Fatalf("Run: %v", err)
}
if len(store.createdTasks) != 1 || store.createdTasks[0].Name != "sub A" {
t.Errorf("expected one spawned subtask 'sub A', got %+v", store.createdTasks)
}
if store.createdTasks[0].ParentTaskID != tt.ID {
t.Errorf("subtask parent: want %q, got %q", tt.ID, store.createdTasks[0].ParentTaskID)
}
if sum, ok := ch.ReportedSummary(); !ok || sum != "all done" {
t.Errorf("expected reported summary 'all done', got %q (set=%v)", sum, ok)
}
// Tokens accumulate across all three turns.
if exec.TokensIn != 11 || exec.TokensOut != 6 {
t.Errorf("tokens should accumulate: want 11/6, got %d/%d", exec.TokensIn, exec.TokensOut)
}
}
func TestLocalRunner_Run_RecordProgress(t *testing.T) {
srv := fakeChatServer(t, []fakeTurn{
{toolCalls: []llm.ToolCall{toolCall("c1", "record_progress", `{"message":"halfway there"}`)}},
{content: "done"},
})
defer srv.Close()
store := &fakeChannelStore{}
tt := localTask()
exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
if err := newLocalRunner(t, srv).Run(context.Background(), tt, exec, newStoreChannel(store, tt.ID)); err != nil {
t.Fatalf("Run: %v", err)
}
if len(store.createdEvents) != 1 {
t.Fatalf("expected 1 progress event, got %d", len(store.createdEvents))
}
if !strings.Contains(string(store.createdEvents[0].Payload), "halfway there") {
t.Errorf("progress event payload: %s", store.createdEvents[0].Payload)
}
}
func TestLocalRunner_Run_AskUser_Blocks(t *testing.T) {
srv := fakeChatServer(t, []fakeTurn{
{toolCalls: []llm.ToolCall{toolCall("c1", "ask_user", `{"question":"which branch?"}`)}},
{content: "should not be reached"},
})
defer srv.Close()
tt := localTask()
exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
err := newLocalRunner(t, srv).Run(context.Background(), tt, exec, newStoreChannel(&fakeChannelStore{}, tt.ID))
var be *BlockedError
if !errors.As(err, &be) {
t.Fatalf("expected *BlockedError, got %v", err)
}
if !strings.Contains(be.QuestionJSON, "which branch?") {
t.Errorf("BlockedError question: %q", be.QuestionJSON)
}
}
func TestLocalRunner_Run_NoClient_Errors(t *testing.T) {
r := &LocalRunner{LogDir: t.TempDir()}
tt := &task.Task{ID: "x", Agent: task.AgentConfig{Instructions: "hi"}}
exec := &storage.Execution{ID: "exec-x"}
err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID))
if err == nil || !strings.Contains(err.Error(), "no LLM client") {
t.Errorf("expected 'no LLM client' error, got %v", err)
}
}
func TestLocalRunner_Run_EmptyInstructions_Errors(t *testing.T) {
r := &LocalRunner{
Client: &llm.Client{Endpoint: "http://unused", Model: "x"},
LogDir: t.TempDir(),
}
tt := &task.Task{ID: "x", Agent: task.AgentConfig{}}
exec := &storage.Execution{ID: "exec-x"}
err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID))
if err == nil || !strings.Contains(err.Error(), "empty instructions") {
t.Errorf("expected empty-instructions error, got %v", err)
}
}
func TestLocalRunner_ExecLogDir(t *testing.T) {
r := &LocalRunner{LogDir: "/tmp/logs"}
if got := r.ExecLogDir("abc"); got != "/tmp/logs/abc" {
t.Errorf("ExecLogDir: got %q", got)
}
r.LogDir = ""
if got := r.ExecLogDir("abc"); got != "" {
t.Errorf("ExecLogDir empty LogDir: got %q", got)
}
}
|
