1 files changed, 137 insertions, 56 deletions
diff --git a/internal/executor/local_test.go b/internal/executor/local_test.go
index ffe87f9..2ae8380 100644
--- a/internal/executor/local_test.go
+++ b/internal/executor/local_test.go
@@ -3,7 +3,7 @@ package executor
 import (
 	"context"
 	"encoding/json"
-	"fmt"
+	"errors"
 	"io"
 	"log/slog"
 	"net/http"
@@ -11,6 +11,7 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
 	"testing"
 
 	"github.com/google/uuid"
@@ -19,60 +20,77 @@ import (
 	"github.com/thepeterstone/claudomator/internal/task"
 )
 
-// fakeOpenAIServer returns an httptest.Server that replies with a streaming
-// chat completion containing the supplied content (split into chunks) plus a
-// usage record.
-func fakeOpenAIServer(t *testing.T, chunks []string, promptTok, outTok int) *httptest.Server {
+// 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()
-	return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		w.Header().Set("Content-Type", "text/event-stream")
-		flusher, _ := w.(http.Flusher)
-		for _, c := range chunks {
-			payload := map[string]any{
-				"model":   "fake",
-				"choices": []map[string]any{{"delta": map[string]string{"content": c}}},
-			}
-			b, _ := json.Marshal(payload)
-			fmt.Fprintf(w, "data: %s\n\n", b)
-			if flusher != nil {
-				flusher.Flush()
-			}
+	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
 		}
-		final := map[string]any{
+		resp := map[string]any{
 			"model":   "fake",
-			"choices": []map[string]any{{"delta": map[string]string{}, "finish_reason": "stop"}},
-			"usage":   map[string]int{"prompt_tokens": promptTok, "completion_tokens": outTok},
+			"choices": []map[string]any{{"message": msg, "finish_reason": "stop"}},
+			"usage":   map[string]int{"prompt_tokens": turn.promptTok, "completion_tokens": turn.outTok},
 		}
-		fb, _ := json.Marshal(final)
-		fmt.Fprintf(w, "data: %s\n\ndata: [DONE]\n\n", fb)
+		_ = json.NewEncoder(w).Encode(resp)
 	}))
 }
 
-func TestLocalRunner_Run_WritesStreamJSON(t *testing.T) {
-	srv := fakeOpenAIServer(t,
-		[]string{"## Summary\n", "All ", "good."},
-		11, 22,
-	)
-	defer srv.Close()
+func toolCall(id, name, args string) llm.ToolCall {
+	return llm.ToolCall{ID: id, Type: "function", Function: llm.ToolCallFunction{Name: name, Arguments: args}}
+}
 
-	logRoot := t.TempDir()
-	r := &LocalRunner{
+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: logRoot,
+		LogDir: t.TempDir(),
 	}
-	tt := &task.Task{
+}
+
+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(nil, tt.ID)); err != nil {
+	if err := r.Run(context.Background(), tt, exec, newStoreChannel(&fakeChannelStore{}, tt.ID)); err != nil {
 		t.Fatalf("Run: %v", err)
 	}
 
@@ -83,40 +101,103 @@ func TestLocalRunner_Run_WritesStreamJSON(t *testing.T) {
 		t.Errorf("tokens: want 11/22 got %d/%d", exec.TokensIn, exec.TokensOut)
 	}
 
-	// Verify stdout.log contains stream-json envelopes that extractSummary can parse.
 	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")
-	if len(lines) < 4 {
-		t.Fatalf("expected at least 4 lines (3 deltas + 1 result), got %d:\n%s", len(lines), data)
-	}
-	for i, line := range lines[:3] {
-		var env struct {
-			Type    string `json:"type"`
-			Message struct {
-				Content []struct {
-					Type string `json:"type"`
-					Text string `json:"text"`
-				}
-			}
-		}
-		if err := json.Unmarshal([]byte(line), &env); err != nil {
-			t.Fatalf("line %d not JSON: %v: %s", i, err, line)
-		}
-		if env.Type != "assistant" {
-			t.Errorf("line %d: want type=assistant, got %q", i, env.Type)
-		}
+	// 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])
 	}
 
-	summary := extractSummary(stdoutPath)
-	if !strings.Contains(summary, "All good.") {
+	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"}}