tools: persist spark_submit calls to SubmissionRepo

Co-Authored-By: Claude <noreply@anthropic.com>

internal/mcp/tools/spark_submit_path_test.go

@@ -10,11 +10,15 @@ import (
 
 	"github.com/mark3labs/mcp-go/mcp"
 
+	"spark-mcp-go/internal/audit"
 	"spark-mcp-go/internal/cluster"
+	"spark-mcp-go/internal/httpclient"
+	"spark-mcp-go/internal/storage"
+	"spark-mcp-go/internal/uploads"
 )
 
 func TestSparkSubmit_StructuredCommand(t *testing.T) {
-	deps, repo, _ := testDepsWithDataDir(t)
+	deps, repo, _, _ := testDepsWithDataDir(t)
 	deps.SparkSubmitTimeout = 5 * time.Second
 	store := deps.UploadStore
 
@@ -25,7 +29,7 @@ func TestSparkSubmit_StructuredCommand(t *testing.T) {
 
 	echoed := filepath.Join(t.TempDir(), "echoed")
 	echoScript := filepath.Join(t.TempDir(), "echo-args.sh")
-	if err := os.WriteFile(echoScript, []byte("#!/bin/sh\nfor arg do\n  echo \"$arg\" >> \"$ECHO_FILE\"\ndone\n"), 0o755); err != nil {
+	if err := os.WriteFile(echoScript, []byte("#!/bin/sh\nfor arg do\n  echo \"$arg\" >> \"$ECHO_FILE\"\ndone\necho 'Submitted application application_test_0001'\n"), 0o755); err != nil {
 		t.Fatalf("write echo script: %v", err)
 	}
 
@@ -97,8 +101,107 @@ func TestSparkSubmit_StructuredCommand(t *testing.T) {
 	}
 }
 
+func TestSparkSubmit_PersistsSubmission(t *testing.T) {
+	// Open a dedicated DB so we can insert upload_files metadata for the join.
+	db, err := storage.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open db: %v", err)
+	}
+	t.Cleanup(func() { _ = db.Close() })
+
+	dataDir := t.TempDir()
+	store, err := uploads.New(filepath.Join(dataDir, "uploads"))
+	if err != nil {
+		t.Fatalf("new upload store: %v", err)
+	}
+
+	deps := &Deps{
+		HTTPClient:         httpclient.New(httpclient.Config{Timeout: 5 * time.Second, MaxResponseBytes: 1 << 20}),
+		AuditRepo:          audit.NewRepo(db),
+		ClusterRepo:        db.Clusters(),
+		SubmissionRepo:     db.Submissions(),
+		MaxResponseBytes:   1 << 20,
+		DataDir:            dataDir,
+		UploadStore:        store,
+		SparkSubmitTimeout: 5 * time.Second,
+	}
+	repo := db.Clusters()
+	subRepo := db.Submissions()
+
+	fileID, _, _, _, absPath, err := store.Save([]byte("print('hi')\n"), "hello.py")
+	if err != nil {
+		t.Fatalf("save upload: %v", err)
+	}
+	if err := db.Uploads().Create(context.Background(), fileID, "hello.py", 14, "dummy-sha", time.Now()); err != nil {
+		t.Fatalf("create upload record: %v", err)
+	}
+
+	echoScript := filepath.Join(t.TempDir(), "echo-submit.sh")
+	if err := os.WriteFile(echoScript, []byte("#!/bin/sh\necho 'tracking URL: http://rm.example.com:8088/proxy/application_persist_0001/' >&2\necho 'Submitted application application_persist_0001'\n"), 0o755); err != nil {
+		t.Fatalf("write echo script: %v", err)
+	}
+
+	createCluster(t, repo, &cluster.Cluster{
+		ID:                    "cluster-persist",
+		Name:                  "Persist",
+		IsActive:              true,
+		AuthType:              cluster.AuthNone,
+		SparkSubmitExecuteBin: echoScript,
+	})
+
+	req := newToolRequest(SparkSubmitName, map[string]any{
+		"cluster_id":      "cluster-persist",
+		"master":          "yarn",
+		"deploy_mode":     "cluster",
+		"script_path":     absPath,
+		"queue":           "default",
+		"executor_memory": "2G",
+		"executor_cores":  1,
+		"num_executors":   4,
+	})
+	res, err := deps.SparkSubmitHandler(context.Background(), req)
+	if err != nil {
+		t.Fatalf("handler error: %v", err)
+	}
+	if res.IsError {
+		t.Fatalf("unexpected error result: %v", res.Content)
+	}
+
+	payload := resultJSON(t, res)
+	if payload["app_id"] != "application_persist_0001" {
+		t.Errorf("app_id=%v, want application_persist_0001", payload["app_id"])
+	}
+	if payload["tracking_url"] != "http://rm.example.com:8088/proxy/application_persist_0001/" {
+		t.Errorf("tracking_url=%v, want tracking URL", payload["tracking_url"])
+	}
+
+	subs, err := subRepo.List(context.Background(), storage.SubmissionFilter{Limit: 10})
+	if err != nil {
+		t.Fatalf("list submissions: %v", err)
+	}
+	if len(subs) != 1 {
+		t.Fatalf("got %d submissions, want 1", len(subs))
+	}
+	s := subs[0]
+	if s.FileID != fileID {
+		t.Errorf("file_id=%q, want %q", s.FileID, fileID)
+	}
+	if s.AppID != "application_persist_0001" {
+		t.Errorf("app_id=%q, want application_persist_0001", s.AppID)
+	}
+	if s.TrackingURL != "http://rm.example.com:8088/proxy/application_persist_0001/" {
+		t.Errorf("tracking_url=%q, want tracking URL", s.TrackingURL)
+	}
+	if s.ClusterID != "cluster-persist" {
+		t.Errorf("cluster_id=%q, want cluster-persist", s.ClusterID)
+	}
+	if s.FileName != "hello.py" {
+		t.Errorf("file_name=%q, want hello.py", s.FileName)
+	}
+}
+
 func TestSparkSubmit_MissingRequiredField(t *testing.T) {
-	deps, _, _ := testDepsWithDataDir(t)
+	deps, _, _, _ := testDepsWithDataDir(t)
 	store := deps.UploadStore
 	_, _, _, _, mintedPath, err := store.Save([]byte("# dummy\n"), "dummy.py")
 	if err != nil {
@@ -131,7 +234,7 @@ func TestSparkSubmit_MissingRequiredField(t *testing.T) {
 }
 
 func TestSparkSubmit_BadSparkConfValue(t *testing.T) {
-	deps, _, _ := testDepsWithDataDir(t)
+	deps, _, _, _ := testDepsWithDataDir(t)
 	store := deps.UploadStore
 	_, _, _, _, mintedPath, err := store.Save([]byte("# dummy\n"), "dummy.py")
 	if err != nil {
@@ -166,7 +269,7 @@ func TestSparkSubmit_BadSparkConfValue(t *testing.T) {
 }
 
 func TestSparkSubmit_RejectsNonMintedPath(t *testing.T) {
-	deps, _, _ := testDepsWithDataDir(t)
+	deps, _, _, _ := testDepsWithDataDir(t)
 
 	unminted := filepath.Join(t.TempDir(), "unminted.py")
 	if err := os.WriteFile(unminted, []byte("print('not from upload_file')\n"), 0o644); err != nil {
@@ -200,7 +303,7 @@ func TestSparkSubmit_RejectsNonMintedPath(t *testing.T) {
 }
 
 func TestSparkSubmit_EmptyMaster(t *testing.T) {
-	deps, _, _ := testDepsWithDataDir(t)
+	deps, _, _, _ := testDepsWithDataDir(t)
 	store := deps.UploadStore
 	_, _, _, _, mintedPath, err := store.Save([]byte("# dummy\n"), "dummy.py")
 	if err != nil {