1 files changed, 353 insertions, 0 deletions
diff --git a/internal/executor/nativerunner_test.go b/internal/executor/nativerunner_test.go
new file mode 100644
index 0000000..f76b365
--- /dev/null
+++ b/internal/executor/nativerunner_test.go
@@ -0,0 +1,353 @@
+package executor
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/thepeterstone/claudomator/internal/llm"
+	"github.com/thepeterstone/claudomator/internal/provider/openaicompat"
+	"github.com/thepeterstone/claudomator/internal/storage"
+	"github.com/thepeterstone/claudomator/internal/task"
+)
+
+// TestNativeRunner_Run_ChangestatsParseable confirms that a git diff --stat
+// summary line embedded in the model's assistant text (the only way such a
+// line can reach stdout.log — tool results themselves are never logged) is
+// still recoverable by task.ParseChangestatFromFile via the new
+// NativeRunner/agentloop path, exactly as it was via the old LocalRunner
+// (neither runner logs raw tool output; both only log assistant text +
+// result lines, so this has always depended on the model itself echoing the
+// diff stat in its reply).
+func TestNativeRunner_Run_ChangestatsParseable(t *testing.T) {
+	srv := fakeChatServer(t, []fakeTurn{
+		{content: "## Summary\nCommitted the fix.\n2 files changed, 30 insertions(+), 4 deletions(-)", promptTok: 3, outTok: 7},
+	})
+	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)
+	}
+
+	stdoutPath := filepath.Join(r.ExecLogDir(exec.ID), "stdout.log")
+	cs := task.ParseChangestatFromFile(stdoutPath)
+	if cs == nil {
+		t.Fatalf("ParseChangestatFromFile found nothing in %s", stdoutPath)
+	}
+	if cs.FilesChanged != 2 || cs.LinesAdded != 30 || cs.LinesRemoved != 4 {
+		t.Errorf("changestats: got %+v, want {2 30 4}", cs)
+	}
+}
+
+// This file exercises NativeRunner — the provider.Provider/agentloop.Loop
+// based successor to the former LocalRunner — via a fake OpenAI-compatible
+// HTTP server, using the same fake-server test pattern LocalRunner's tests
+// used (fakeChatServer/fakeTurn/toolCall below), so it verifies behavioral
+// equivalence: same stdout.log stream-json shape, same summary/changestats
+// extraction, same tool-loop semantics.
+
+// 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) *NativeRunner {
+	t.Helper()
+	client := &llm.Client{Endpoint: srv.URL + "/v1", Model: "fake"}
+	return &NativeRunner{
+		Provider: openaicompat.New(client),
+		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 TestNativeRunner_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 native 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 TestNativeRunner_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 TestNativeRunner_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 TestNativeRunner_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 TestNativeRunner_Run_NoProvider_Errors(t *testing.T) {
+	r := &NativeRunner{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 provider configured") {
+		t.Errorf("expected 'no provider configured' error, got %v", err)
+	}
+}
+
+func TestNativeRunner_Run_EmptyInstructions_Errors(t *testing.T) {
+	r := &NativeRunner{
+		Provider: openaicompat.New(&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 TestNativeRunner_ExecLogDir(t *testing.T) {
+	r := &NativeRunner{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)
+	}
+}
+
+// TestNativeRunner_Run_ProjectDir_SandboxToolsAndPush drives a task with
+// Agent.ProjectDir set through write_file/read_file/glob/run_bash tool calls
+// against a real HostSandbox (git clone into a temp dir), confirming the
+// verbatim-ported sandbox.HostSandbox behavior end-to-end: tool dispatch
+// hits the real filesystem/shell, a commit made via run_bash is pushed back
+// to the origin repo on a clean finish, and the sandbox temp dir is removed
+// afterward — exactly the git-clone/push/cleanup sequence LocalRunner used
+// to run inline. No prior test (LocalRunner's included) exercised this path;
+// it's new coverage for logic that was previously only exercised manually.
+func TestNativeRunner_Run_ProjectDir_SandboxToolsAndPush(t *testing.T) {
+	if _, err := exec.LookPath("git"); err != nil {
+		t.Skip("git not available")
+	}
+
+	// Bare origin repo so `git push origin HEAD` from the sandbox clone
+	// doesn't hit receive.denyCurrentBranch.
+	origin := t.TempDir()
+	run := func(dir string, args ...string) {
+		t.Helper()
+		cmd := exec.Command("git", args...)
+		cmd.Dir = dir
+		cmd.Env = append(os.Environ(),
+			"GIT_AUTHOR_NAME=test", "GIT_AUTHOR_EMAIL=test@example.com",
+			"GIT_COMMITTER_NAME=test", "GIT_COMMITTER_EMAIL=test@example.com",
+		)
+		out, err := cmd.CombinedOutput()
+		if err != nil {
+			t.Fatalf("git %v: %v\n%s", args, err, out)
+		}
+	}
+	run(origin, "init", "--bare", "-b", "main")
+
+	// Seed the bare repo with an initial commit (an empty bare repo has no
+	// HEAD, so LocalRunner's plain `git clone <remote> <dir>` needs something
+	// to check out).
+	seed := t.TempDir()
+	run(seed, "init", "-b", "main")
+	run(seed, "remote", "add", "origin", origin)
+	if err := os.WriteFile(filepath.Join(seed, "README.md"), []byte("seed\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	run(seed, "add", "-A")
+	run(seed, "commit", "-m", "seed")
+	run(seed, "push", "origin", "main")
+
+	srv := fakeChatServer(t, []fakeTurn{
+		{toolCalls: []llm.ToolCall{toolCall("c1", "write_file", `{"path":"hello.txt","content":"hello world"}`)}},
+		{toolCalls: []llm.ToolCall{toolCall("c2", "read_file", `{"path":"hello.txt"}`)}},
+		{toolCalls: []llm.ToolCall{toolCall("c3", "glob", `{"pattern":"*.txt"}`)}},
+		{toolCalls: []llm.ToolCall{toolCall("c4", "run_bash", `{"command":"git add -A && git -c user.name=test -c user.email=test@example.com commit -m 'add hello'"}`)}},
+		{content: "## Summary\nAdded hello.txt and committed."},
+	})
+	defer srv.Close()
+
+	r := newLocalRunner(t, srv)
+	tt := localTask()
+	tt.Agent.ProjectDir = origin
+	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_.SandboxDir != "" {
+		t.Errorf("expected SandboxDir cleared after clean finish, got %q", exec_.SandboxDir)
+	}
+
+	// Verify the commit actually landed on origin.
+	logCmd := exec.Command("git", "-C", origin, "log", "--oneline", "main")
+	out, err := logCmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("git log on origin: %v\n%s", err, out)
+	}
+	if !strings.Contains(string(out), "add hello") {
+		t.Errorf("expected pushed commit 'add hello' in origin log, got:\n%s", out)
+	}
+}