uploads,tools,config,main: 将 upload_file 返回路径改为服务器端绝对路径并透传给 spark_submit

之前 upload_file 把文件写到 DataDir/uploads/<filename>，返回相对路径 uploads/hello.txt。MCP 服务器与 agent 不在同一台机器，agent 无法构造服务器本地路径，因此 spark_submit 无法定位脚本。改为由新的 internal/uploads 包 mint 一个 32 字符十六进制 file_id，文件落盘为 DataDir/uploads/<file_id>，元数据写入 <file_id>.meta.json（原始文件名只存在 sidecar 里）。upload_file 返回 {file_id, path, name, size, sha256}，其中 path 是绝对路径。spark_submit 的 description 明确要求 LLM 直接把 upload_file 返回的 path 放进 args，不要自己构造路径。为什么只在描述里约束而不在代码里拒绝非 mint 的绝对路径：集群本地已有路径（如 /opt/spark/examples/pi.py）是合法的 spark-submit 参数，代码不能替 LLM 拒绝。测试锁定： - internal/uploads: Save 往返、AbsPath/Validate 非法路径、Sweep 过期/未过期/ 孤立 sidecar - internal/mcp/tools: upload_file 新响应字段、spark_submit 透传 mint 路径与集群本地路径刻意未做：S3/HDFS 上传、给 spark_submit 新增 file_id 参数、在代码层面拒绝集群本地绝对路径。破坏性变更：upload_file 响应从相对 path 改为绝对 path，并新增 file_id/name/ sha256 字段。该工具尚无外部调用者。 Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-13 19:13:14 +08:00
parent 210aeb1315
commit f374ebfdb4
10 changed files with 748 additions and 22 deletions
@@ -0,0 +1,120 @@
+package tools
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"spark-mcp-go/internal/cluster"
+)
+
+func TestSparkSubmit_PathPassthrough(t *testing.T) {
+	deps, repo := testDepsWithDataDir(t)
+	deps.SparkSubmitTimeout = 5 * time.Second
+	store := deps.UploadStore
+
+	fileID, _, _, _, absPath, err := store.Save([]byte("print('hi')\n"), "hello.py")
+	if err != nil {
+		t.Fatalf("save upload: %v", err)
+	}
+
+	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 {
+		t.Fatalf("write echo script: %v", err)
+	}
+
+	t.Setenv("ECHO_FILE", echoed)
+
+	createCluster(t, repo, &cluster.Cluster{
+		ID:                    "cluster-echo",
+		Name:                  "Echo",
+		IsActive:              true,
+		AuthType:              cluster.AuthNone,
+		SparkSubmitExecuteBin: echoScript,
+	})
+
+	req := newToolRequest(SparkSubmitName, map[string]any{
+		"cluster_id": "cluster-echo",
+		"args":       []any{absPath, "--class", "Main"},
+	})
+	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)
+	}
+
+	got, err := os.ReadFile(echoed)
+	if err != nil {
+		t.Fatalf("read echoed args: %v", err)
+	}
+	lines := strings.Split(strings.TrimSpace(string(got)), "\n")
+	want := []string{absPath, "--class", "Main"}
+	if len(lines) != len(want) {
+		t.Fatalf("echoed lines=%v, want %v", lines, want)
+	}
+	for i, l := range lines {
+		if l != want[i] {
+			t.Errorf("line[%d]=%q, want %q", i, l, want[i])
+		}
+	}
+
+	// Sanity: the canonical path still contains the minted file ID.
+	if !strings.HasSuffix(absPath, "/"+fileID) {
+		t.Errorf("absPath=%q does not end with fileID %q", absPath, fileID)
+	}
+}
+
+func TestSparkSubmit_ClusterLocalPathPassthrough(t *testing.T) {
+	deps, repo := testDepsWithDataDir(t)
+	deps.SparkSubmitTimeout = 5 * time.Second
+
+	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 {
+		t.Fatalf("write echo script: %v", err)
+	}
+
+	t.Setenv("ECHO_FILE", echoed)
+
+	createCluster(t, repo, &cluster.Cluster{
+		ID:                    "cluster-echo",
+		Name:                  "Echo",
+		IsActive:              true,
+		AuthType:              cluster.AuthNone,
+		SparkSubmitExecuteBin: echoScript,
+	})
+
+	clusterLocalPath := "/usr/bin/env"
+	req := newToolRequest(SparkSubmitName, map[string]any{
+		"cluster_id": "cluster-echo",
+		"args":       []any{clusterLocalPath, "--class", "Main"},
+	})
+	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)
+	}
+
+	got, err := os.ReadFile(echoed)
+	if err != nil {
+		t.Fatalf("read echoed args: %v", err)
+	}
+	lines := strings.Split(strings.TrimSpace(string(got)), "\n")
+	want := []string{clusterLocalPath, "--class", "Main"}
+	if len(lines) != len(want) {
+		t.Fatalf("echoed lines=%v, want %v", lines, want)
+	}
+	for i, l := range lines {
+		if l != want[i] {
+			t.Errorf("line[%d]=%q, want %q", i, l, want[i])
+		}
+	}
+}