Merge pull request #4 from thepeterstone/claude/gemini-sandbox

Gemini runner: full sandbox-flow parity with Claude

1 files changed, 268 insertions, 0 deletions

diff --git a/internal/executor/gemini_test.go b/internal/executor/gemini_test.go
index 4b0339e..cd11ebc 100644
--- a/internal/executor/gemini_test.go
+++ b/internal/executor/gemini_test.go
@@ -3,8 +3,11 @@ package executor
 import (
 	"bytes"
 	"context"
+	"errors"
 	"io"
 	"log/slog"
+	"os"
+	"path/filepath"
 	"strings"
 	"testing"
 
@@ -177,3 +180,268 @@ func TestParseGeminiStream_ParsesStructuredOutput(t *testing.T) {
 		t.Errorf("writer content mismatch:\nwant:\n%s\ngot:\n%s", expectedWriterContent, writer.String())
 	}
 }
+
+// TestGeminiRunner_Run_ProjectDir_RunsInSandbox verifies that when project_dir
+// is set, the gemini subprocess runs inside a sandbox clone — not in
+// project_dir itself.
+func TestGeminiRunner_Run_ProjectDir_RunsInSandbox(t *testing.T) {
+	projectDir := t.TempDir()
+	initGitRepo(t, projectDir)
+
+	logDir := t.TempDir()
+	cwdFile := filepath.Join(logDir, "gemini-cwd.txt")
+
+	// Fake gemini binary that records its $PWD then exits 0.
+	scriptPath := filepath.Join(t.TempDir(), "fake-gemini.sh")
+	script := "#!/bin/sh\nprintf '%s' \"$PWD\" > " + cwdFile + "\n"
+	if err := os.WriteFile(scriptPath, []byte(script), 0755); err != nil {
+		t.Fatalf("write script: %v", err)
+	}
+
+	r := &GeminiRunner{
+		BinaryPath: scriptPath,
+		Logger:     slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir:     logDir,
+	}
+	tk := &task.Task{
+		Agent: task.AgentConfig{
+			Type:         "gemini",
+			Instructions: "do work",
+			ProjectDir:   projectDir,
+			SkipPlanning: true,
+		},
+	}
+	e := &storage.Execution{ID: "sandbox-exec", TaskID: "task-1"}
+
+	if err := r.Run(context.Background(), tk, e); err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+
+	got, err := os.ReadFile(cwdFile)
+	if err != nil {
+		t.Fatalf("cwd file not written: %v", err)
+	}
+	cwd := string(got)
+	if cwd == projectDir {
+		t.Errorf("ran directly in project_dir; expected sandbox clone (cwd=%q)", cwd)
+	}
+	// Sandbox should be removed after successful teardown (no edits → nothing to push).
+	// We can't assert the exact dir, but it should not be projectDir.
+}
+
+// TestGeminiRunner_Run_BlockedError_IncludesSandboxDir verifies that when the
+// agent writes a question file before exiting, the BlockedError carries the
+// sandbox path so resume runs in the same dir.
+func TestGeminiRunner_Run_BlockedError_IncludesSandboxDir(t *testing.T) {
+	src := t.TempDir()
+	initGitRepo(t, src)
+	logDir := t.TempDir()
+
+	scriptPath := filepath.Join(t.TempDir(), "fake-gemini.sh")
+	if err := os.WriteFile(scriptPath, []byte(`#!/bin/sh
+if [ -n "$CLAUDOMATOR_QUESTION_FILE" ]; then
+  printf '{"text":"Should I continue?"}' > "$CLAUDOMATOR_QUESTION_FILE"
+fi
+`), 0755); err != nil {
+		t.Fatalf("write script: %v", err)
+	}
+
+	r := &GeminiRunner{
+		BinaryPath: scriptPath,
+		Logger:     slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir:     logDir,
+	}
+	tk := &task.Task{
+		Agent: task.AgentConfig{
+			Type:         "gemini",
+			Instructions: "do something",
+			ProjectDir:   src,
+			SkipPlanning: true,
+		},
+	}
+	e := &storage.Execution{ID: "blocked-gemini-exec", TaskID: "task-1"}
+
+	err := r.Run(context.Background(), tk, e)
+
+	var blocked *BlockedError
+	if !errors.As(err, &blocked) {
+		t.Fatalf("expected BlockedError, got: %v", err)
+	}
+	if blocked.SandboxDir == "" {
+		t.Error("BlockedError.SandboxDir should be set when gemini task runs in a sandbox")
+	}
+	if _, statErr := os.Stat(blocked.SandboxDir); os.IsNotExist(statErr) {
+		t.Error("sandbox directory should be preserved when blocked")
+	} else {
+		os.RemoveAll(blocked.SandboxDir)
+	}
+}
+
+// TestGeminiRunner_Run_ExecError_PreservesSandbox verifies that when gemini
+// exits non-zero, the sandbox path is included in the wrapped error so the
+// user can inspect partial work.
+func TestGeminiRunner_Run_ExecError_PreservesSandbox(t *testing.T) {
+	src := t.TempDir()
+	initGitRepo(t, src)
+	logDir := t.TempDir()
+
+	// "false" exits 1, no output.
+	r := &GeminiRunner{
+		BinaryPath: "false",
+		Logger:     slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir:     logDir,
+	}
+	tk := &task.Task{
+		Agent: task.AgentConfig{
+			Type:         "gemini",
+			Instructions: "do something",
+			ProjectDir:   src,
+			SkipPlanning: true,
+		},
+	}
+	e := &storage.Execution{ID: "err-gemini-exec", TaskID: "task-1"}
+
+	err := r.Run(context.Background(), tk, e)
+	if err == nil {
+		t.Fatal("expected error from failing gemini exit")
+	}
+	if !strings.Contains(err.Error(), "sandbox preserved at ") {
+		t.Errorf("expected error to include sandbox path; got: %v", err)
+	}
+	// Extract path and verify it exists.
+	idx := strings.Index(err.Error(), "sandbox preserved at ")
+	rest := err.Error()[idx+len("sandbox preserved at "):]
+	rest = strings.TrimSuffix(rest, ")")
+	rest = strings.TrimSpace(rest)
+	if _, statErr := os.Stat(rest); os.IsNotExist(statErr) {
+		t.Errorf("sandbox path from error should exist on disk: %q", rest)
+	} else {
+		os.RemoveAll(rest)
+	}
+}
+
+// TestGeminiRunner_Run_ResumeUsesStoredSandboxDir verifies that a resume
+// execution runs in the preserved SandboxDir rather than cloning fresh.
+func TestGeminiRunner_Run_ResumeUsesStoredSandboxDir(t *testing.T) {
+	logDir := t.TempDir()
+	sandboxDir := t.TempDir()
+	initGitRepo(t, sandboxDir)
+	cwdFile := filepath.Join(logDir, "cwd.txt")
+
+	scriptPath := filepath.Join(t.TempDir(), "fake-gemini.sh")
+	script := "#!/bin/sh\nprintf '%s' \"$PWD\" > " + cwdFile + "\n"
+	if err := os.WriteFile(scriptPath, []byte(script), 0755); err != nil {
+		t.Fatalf("write script: %v", err)
+	}
+
+	r := &GeminiRunner{
+		BinaryPath: scriptPath,
+		Logger:     slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir:     logDir,
+	}
+	tk := &task.Task{
+		Agent: task.AgentConfig{
+			Type:         "gemini",
+			SkipPlanning: true,
+		},
+	}
+	e := &storage.Execution{
+		ID:              "resume-gemini-1",
+		TaskID:          "task-resume",
+		ResumeSessionID: "session-abc",
+		SandboxDir:      sandboxDir,
+	}
+
+	if err := r.Run(context.Background(), tk, e); err != nil {
+		t.Fatalf("Run with preserved sandbox: %v", err)
+	}
+
+	got, err := os.ReadFile(cwdFile)
+	if err != nil {
+		t.Fatalf("cwd file not written: %v", err)
+	}
+	if string(got) != sandboxDir {
+		t.Errorf("resume should run in preserved sandbox; got cwd=%q want %q", got, sandboxDir)
+	}
+}
+
+// TestGeminiRunner_Run_StaleSandboxDir_ClonesAfresh verifies that a resume
+// pointing at a missing sandbox falls back to cloning a fresh sandbox from
+// project_dir rather than failing outright.
+func TestGeminiRunner_Run_StaleSandboxDir_ClonesAfresh(t *testing.T) {
+	logDir := t.TempDir()
+	projectDir := t.TempDir()
+	initGitRepo(t, projectDir)
+
+	cwdFile := filepath.Join(logDir, "cwd.txt")
+	scriptPath := filepath.Join(t.TempDir(), "fake-gemini.sh")
+	script := "#!/bin/sh\nprintf '%s' \"$PWD\" > " + cwdFile + "\n"
+	if err := os.WriteFile(scriptPath, []byte(script), 0755); err != nil {
+		t.Fatalf("write script: %v", err)
+	}
+
+	r := &GeminiRunner{
+		BinaryPath: scriptPath,
+		Logger:     slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir:     logDir,
+	}
+	tk := &task.Task{
+		Agent: task.AgentConfig{
+			Type:         "gemini",
+			ProjectDir:   projectDir,
+			SkipPlanning: true,
+		},
+	}
+	staleSandbox := filepath.Join(t.TempDir(), "gone")
+	e := &storage.Execution{
+		ID:              "resume-gemini-2",
+		TaskID:          "task-stale",
+		ResumeSessionID: "session-xyz",
+		SandboxDir:      staleSandbox,
+	}
+
+	if err := r.Run(context.Background(), tk, e); err != nil {
+		t.Fatalf("Run with stale sandbox: %v", err)
+	}
+
+	got, err := os.ReadFile(cwdFile)
+	if err != nil {
+		t.Fatalf("cwd file not written: %v", err)
+	}
+	cwd := string(got)
+	if cwd == staleSandbox {
+		t.Error("ran in stale (nonexistent) sandbox dir")
+	}
+	if cwd == projectDir {
+		t.Error("ran directly in project_dir; expected a fresh sandbox clone")
+	}
+}
+
+// TestGeminiRunner_Run_NoProjectDir_SkipsSandbox verifies that a task with no
+// project_dir doesn't trigger sandbox setup (matches LocalRunner/non-coding
+// task semantics).
+func TestGeminiRunner_Run_NoProjectDir_SkipsSandbox(t *testing.T) {
+	logDir := t.TempDir()
+
+	r := &GeminiRunner{
+		BinaryPath: "true", // exits 0, no output
+		Logger:     slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir:     logDir,
+	}
+	tk := &task.Task{
+		Agent: task.AgentConfig{
+			Type:         "gemini",
+			Instructions: "summarize: 2+2",
+			SkipPlanning: true,
+			// No ProjectDir
+		},
+	}
+	e := &storage.Execution{ID: "no-pd-gemini", TaskID: "task-nopd"}
+
+	if err := r.Run(context.Background(), tk, e); err != nil {
+		t.Fatalf("Run without project_dir: %v", err)
+	}
+	if e.SandboxDir != "" {
+		t.Errorf("SandboxDir should be empty for tasks without project_dir, got %q", e.SandboxDir)
+	}
+}