feat: 优化集群部署与堡垒机接入 (#106)

支持受限网络、正向代理、私有 CA 与 SSH 堡垒机部署 Agent。加固 Docker、systemd、Nginx、安装器、Release 校验与可信代理边界，并完善命令队列索引、前端安装向导及中英文运维文档。
2026-08-22 00:32:40 +08:00 · 2026-08-09 02:45:17 +08:00
parent 00151e466c
commit 5827074334
86 changed files with 4668 additions and 3082 deletions
--- a/server/internal/agent/agent.go
+++ b/server/internal/agent/agent.go
@@ -28,10 +28,16 @@ type Agent struct {

 // New 构造 Agent。
 func New(cfg *Config, version string) (*Agent, error) {
+	if err := cfg.ResolveToken(); err != nil {
+		return nil, err
+	}
 	if err := cfg.Validate(); err != nil {
 		return nil, err
 	}
 	client := NewMasterClient(cfg.Master, cfg.Token, cfg.InsecureSkipTLSVerify)
+	if err := client.ConfigureTransport(cfg.ProxyURL, cfg.CACertFile); err != nil {
+		return nil, fmt.Errorf("configure master connection: %w", err)
+	}
 	executor := NewExecutor(client, cfg.TempDir)
 	return &Agent{
 		cfg:      cfg,
@@ -93,7 +99,6 @@ func (a *Agent) heartbeatLoop(ctx context.Context, interval time.Duration) {
 func (a *Agent) heartbeatOnce(ctx context.Context) error {
 	hostname, _ := os.Hostname()
 	req := HeartbeatRequest{
-		Token:        a.cfg.Token,
 		Hostname:     hostname,
 		IPAddress:    detectLocalIP(),
 		AgentVersion: a.version,
--- a/server/internal/agent/client.go
+++ b/server/internal/agent/client.go
@@ -4,11 +4,14 @@ import (
 	"bytes"
 	"context"
 	"crypto/tls"
+	"crypto/x509"
 	"encoding/json"
 	"errors"
 	"fmt"
 	"io"
 	"net/http"
+	"net/url"
+	"os"
 	"strings"
 	"time"
 )
@@ -22,23 +25,64 @@ type MasterClient struct {

 // NewMasterClient 构造 Master 客户端。
 func NewMasterClient(baseURL, token string, insecureTLS bool) *MasterClient {
-	transport := &http.Transport{}
-	if insecureTLS {
-		transport.TLSClientConfig = &tls.Config{InsecureSkipVerify: true}
+	transport := http.DefaultTransport.(*http.Transport).Clone()
+	tlsConfig := &tls.Config{MinVersion: tls.VersionTLS12}
+	if transport.TLSClientConfig != nil {
+		tlsConfig = transport.TLSClientConfig.Clone()
+		tlsConfig.MinVersion = tls.VersionTLS12
 	}
+	// 仅用于用户显式开启的测试模式。生产环境应配置受信 CA。
+	tlsConfig.InsecureSkipVerify = insecureTLS // #nosec G402
+	transport.TLSClientConfig = tlsConfig
 	return &MasterClient{
 		baseURL: strings.TrimRight(baseURL, "/"),
 		token:   token,
 		httpClient: &http.Client{
 			Timeout:   120 * time.Second,
 			Transport: transport,
+			// Agent Token 是自定义认证头。禁止自动重定向，避免代理或错误
+			// 配置把它转发到另一个主机；Master URL 必须直接指向 API。
+			CheckRedirect: func(_ *http.Request, _ []*http.Request) error {
+				return http.ErrUseLastResponse
+			},
 		},
 	}
 }

+// ConfigureTransport 应用显式代理和私有 CA。默认 Transport 已保留
+// ProxyFromEnvironment，因此 ProxyURL 留空时 HTTP_PROXY/HTTPS_PROXY/NO_PROXY 生效。
+func (c *MasterClient) ConfigureTransport(proxyURL, caCertFile string) error {
+	transport, ok := c.httpClient.Transport.(*http.Transport)
+	if !ok {
+		return errors.New("agent http transport has unexpected type")
+	}
+	if strings.TrimSpace(proxyURL) != "" {
+		parsedProxy, err := url.Parse(strings.TrimSpace(proxyURL))
+		if err != nil {
+			return fmt.Errorf("parse proxy URL: %w", err)
+		}
+		transport.Proxy = http.ProxyURL(parsedProxy)
+	}
+	if strings.TrimSpace(caCertFile) == "" {
+		return nil
+	}
+	pemData, err := os.ReadFile(strings.TrimSpace(caCertFile))
+	if err != nil {
+		return fmt.Errorf("read CA certificate: %w", err)
+	}
+	roots, err := x509.SystemCertPool()
+	if err != nil || roots == nil {
+		roots = x509.NewCertPool()
+	}
+	if !roots.AppendCertsFromPEM(pemData) {
+		return errors.New("CA certificate file does not contain a valid PEM certificate")
+	}
+	transport.TLSClientConfig.RootCAs = roots
+	return nil
+}
+
 // HeartbeatRequest Agent 上报心跳的请求
 type HeartbeatRequest struct {
-	Token        string `json:"token"`
 	Hostname     string `json:"hostname,omitempty"`
 	IPAddress    string `json:"ipAddress,omitempty"`
 	AgentVersion string `json:"agentVersion,omitempty"`
--- a/server/internal/agent/client_test.go
+++ b/server/internal/agent/client_test.go
@@ -0,0 +1,93 @@
+package agent
+
+import (
+	"context"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestMasterClientKeepsEnvironmentProxySupport(t *testing.T) {
+	client := NewMasterClient("https://master.example.com", "token", false)
+	transport := client.httpClient.Transport.(*http.Transport)
+	if transport.Proxy == nil {
+		t.Fatal("default transport proxy function must be preserved")
+	}
+}
+
+func TestMasterClientConfiguresExplicitProxy(t *testing.T) {
+	client := NewMasterClient("https://master.example.com", "token", false)
+	if err := client.ConfigureTransport("socks5h://127.0.0.1:1080", ""); err != nil {
+		t.Fatal(err)
+	}
+	transport := client.httpClient.Transport.(*http.Transport)
+	requestURL, _ := url.Parse("https://master.example.com")
+	proxyURL, err := transport.Proxy(&http.Request{URL: requestURL})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if proxyURL == nil || proxyURL.String() != "socks5h://127.0.0.1:1080" {
+		t.Fatalf("proxy URL = %v", proxyURL)
+	}
+}
+
+func TestMasterClientRejectsInvalidCACertificate(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "invalid.pem")
+	if err := os.WriteFile(path, []byte("not a certificate"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	client := NewMasterClient("https://master.example.com", "token", false)
+	if err := client.ConfigureTransport("", path); err == nil {
+		t.Fatal("expected invalid CA certificate error")
+	}
+}
+
+func TestMasterClientDoesNotForwardTokenThroughRedirects(t *testing.T) {
+	receivedToken := ""
+	target := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedToken = r.Header.Get("X-Agent-Token")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer target.Close()
+	redirector := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		http.Redirect(w, r, target.URL, http.StatusTemporaryRedirect)
+	}))
+	defer redirector.Close()
+
+	client := NewMasterClient(redirector.URL, "secret-agent-token", false)
+	if _, err := client.Heartbeat(context.Background(), HeartbeatRequest{}); err == nil {
+		t.Fatal("redirect response should not be accepted as a Master API response")
+	}
+	if receivedToken != "" {
+		t.Fatalf("Agent token leaked through redirect: %q", receivedToken)
+	}
+}
+
+func TestHeartbeatSendsTokenOnlyInAuthenticationHeader(t *testing.T) {
+	requestBody := ""
+	receivedHeader := ""
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		body, _ := io.ReadAll(r.Body)
+		requestBody = string(body)
+		receivedHeader = r.Header.Get("X-Agent-Token")
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"data":{"status":"ok","nodeId":1,"name":"node"}}`))
+	}))
+	defer server.Close()
+
+	client := NewMasterClient(server.URL, "secret-agent-token", false)
+	if _, err := client.Heartbeat(context.Background(), HeartbeatRequest{Hostname: "node"}); err != nil {
+		t.Fatal(err)
+	}
+	if receivedHeader != "secret-agent-token" {
+		t.Fatalf("authentication header = %q", receivedHeader)
+	}
+	if strings.Contains(requestBody, "secret-agent-token") || strings.Contains(requestBody, `"token"`) {
+		t.Fatalf("heartbeat body exposed the Agent token: %s", requestBody)
+	}
+}
--- a/server/internal/agent/config.go
+++ b/server/internal/agent/config.go
@@ -10,8 +10,10 @@ package agent
 import (
 	"errors"
 	"fmt"
+	"net/url"
 	"os"
 	"strings"
+	"time"

 	"gopkg.in/yaml.v3"
 )
@@ -22,16 +24,34 @@ type Config struct {
 	Master string `yaml:"master"`
 	// Token 节点认证令牌（在 Master 创建节点时生成）
 	Token string `yaml:"token"`
+	// TokenFile 从文件读取节点认证令牌；适合 systemd 凭据和容器 secret。
+	// Token 与 TokenFile 同时设置时优先使用 Token。
+	TokenFile string `yaml:"tokenFile"`
 	// HeartbeatInterval 心跳间隔，默认 15s
 	HeartbeatInterval string `yaml:"heartbeatInterval"`
 	// PollInterval 命令轮询间隔，默认 5s
 	PollInterval string `yaml:"pollInterval"`
 	// TempDir 备份临时目录，默认 /var/lib/backupx-agent/tmp
 	TempDir string `yaml:"tempDir"`
+	// ProxyURL Agent 访问 Master 使用的显式代理。留空时遵循
+	// HTTP_PROXY、HTTPS_PROXY 与 NO_PROXY；支持 http(s) 和 socks5(h)。
+	ProxyURL string `yaml:"proxyUrl"`
+	// CACertFile 私有 CA 的 PEM 文件路径，用于安全连接内网 HTTPS Master。
+	CACertFile string `yaml:"caCertFile"`
 	// InsecureSkipTLSVerify 测试环境允许跳过 TLS 证书校验
 	InsecureSkipTLSVerify bool `yaml:"insecureSkipTlsVerify"`
 }

+// Overrides 表示命令行显式提供的 Agent 配置覆盖项。
+type Overrides struct {
+	Master     string
+	Token      string
+	TokenFile  string
+	TempDir    string
+	ProxyURL   string
+	CACertFile string
+}
+
 // LoadConfigFile 从 YAML 文件加载 Agent 配置。
 func LoadConfigFile(path string) (*Config, error) {
 	data, err := os.ReadFile(path)
@@ -50,42 +70,109 @@ func LoadConfigFile(path string) (*Config, error) {
 // 支持的环境变量：
 //   - BACKUPX_AGENT_MASTER            Master URL
 //   - BACKUPX_AGENT_TOKEN             节点认证令牌
+//   - BACKUPX_AGENT_TOKEN_FILE        节点认证令牌文件
 //   - BACKUPX_AGENT_HEARTBEAT         心跳间隔（如 15s）
 //   - BACKUPX_AGENT_POLL              命令轮询间隔（如 5s）
 //   - BACKUPX_AGENT_TEMP_DIR          临时目录
+//   - BACKUPX_AGENT_PROXY_URL         显式 HTTP(S)/SOCKS5 代理
+//   - BACKUPX_AGENT_CA_CERT_FILE      私有 CA PEM 文件
 //   - BACKUPX_AGENT_INSECURE_TLS      true / 1 跳过 TLS 校验
 func LoadConfigFromEnv() (*Config, error) {
 	cfg := &Config{
 		Master:                strings.TrimSpace(os.Getenv("BACKUPX_AGENT_MASTER")),
 		Token:                 strings.TrimSpace(os.Getenv("BACKUPX_AGENT_TOKEN")),
+		TokenFile:             strings.TrimSpace(os.Getenv("BACKUPX_AGENT_TOKEN_FILE")),
 		HeartbeatInterval:     strings.TrimSpace(os.Getenv("BACKUPX_AGENT_HEARTBEAT")),
 		PollInterval:          strings.TrimSpace(os.Getenv("BACKUPX_AGENT_POLL")),
 		TempDir:               strings.TrimSpace(os.Getenv("BACKUPX_AGENT_TEMP_DIR")),
+		ProxyURL:              strings.TrimSpace(os.Getenv("BACKUPX_AGENT_PROXY_URL")),
+		CACertFile:            strings.TrimSpace(os.Getenv("BACKUPX_AGENT_CA_CERT_FILE")),
 		InsecureSkipTLSVerify: strings.EqualFold(os.Getenv("BACKUPX_AGENT_INSECURE_TLS"), "true") || os.Getenv("BACKUPX_AGENT_INSECURE_TLS") == "1",
 	}
 	return applyConfigDefaults(cfg)
 }

-// MergeWithFlags 把命令行覆盖值合并入配置（非空覆盖）。
-func (c *Config) MergeWithFlags(master, token, tempDir string) {
-	if strings.TrimSpace(master) != "" {
-		c.Master = master
+// ApplyOverrides 把命令行覆盖值合并入配置（非空覆盖）。
+func (c *Config) ApplyOverrides(overrides Overrides) {
+	if strings.TrimSpace(overrides.Master) != "" {
+		c.Master = strings.TrimSpace(overrides.Master)
 	}
-	if strings.TrimSpace(token) != "" {
-		c.Token = token
+	tokenProvided := strings.TrimSpace(overrides.Token) != ""
+	if strings.TrimSpace(overrides.TokenFile) != "" {
+		c.TokenFile = strings.TrimSpace(overrides.TokenFile)
+		if !tokenProvided {
+			// An explicit --token-file must override a token inherited from YAML.
+			c.Token = ""
+		}
 	}
-	if strings.TrimSpace(tempDir) != "" {
-		c.TempDir = tempDir
+	if tokenProvided {
+		c.Token = strings.TrimSpace(overrides.Token)
 	}
+	if strings.TrimSpace(overrides.TempDir) != "" {
+		c.TempDir = strings.TrimSpace(overrides.TempDir)
+	}
+	if strings.TrimSpace(overrides.ProxyURL) != "" {
+		c.ProxyURL = strings.TrimSpace(overrides.ProxyURL)
+	}
+	if strings.TrimSpace(overrides.CACertFile) != "" {
+		c.CACertFile = strings.TrimSpace(overrides.CACertFile)
+	}
+}
+
+// ResolveToken 在所有配置源合并完成后读取 token 文件。
+func (c *Config) ResolveToken() error {
+	if strings.TrimSpace(c.Token) != "" || strings.TrimSpace(c.TokenFile) == "" {
+		c.Token = strings.TrimSpace(c.Token)
+		return nil
+	}
+	data, err := os.ReadFile(strings.TrimSpace(c.TokenFile))
+	if err != nil {
+		return fmt.Errorf("read agent token file: %w", err)
+	}
+	c.Token = strings.TrimSpace(string(data))
+	if c.Token == "" {
+		return errors.New("agent token file is empty")
+	}
+	return nil
 }

 // Validate 校验必填字段。
 func (c *Config) Validate() error {
+	masterURL, err := url.Parse(strings.TrimSpace(c.Master))
 	if strings.TrimSpace(c.Master) == "" {
 		return errors.New("master url is required (set via --master, BACKUPX_AGENT_MASTER or config file)")
 	}
+	if err != nil || (masterURL.Scheme != "http" && masterURL.Scheme != "https") || masterURL.Host == "" || masterURL.User != nil || masterURL.RawQuery != "" || masterURL.Fragment != "" {
+		return errors.New("master url must be an absolute http(s) URL without credentials, query or fragment")
+	}
 	if strings.TrimSpace(c.Token) == "" {
-		return errors.New("token is required (set via --token, BACKUPX_AGENT_TOKEN or config file)")
+		return errors.New("token is required (set via --token, --token-file, environment or config file)")
+	}
+	if c.ProxyURL != "" {
+		proxyURL, proxyErr := url.Parse(c.ProxyURL)
+		if proxyErr != nil || proxyURL.Host == "" {
+			return errors.New("proxy url must be an absolute URL")
+		}
+		switch proxyURL.Scheme {
+		case "http", "https", "socks5", "socks5h":
+		default:
+			return errors.New("proxy url scheme must be http, https, socks5 or socks5h")
+		}
+		if proxyURL.RawQuery != "" || proxyURL.Fragment != "" || (proxyURL.Path != "" && proxyURL.Path != "/") {
+			return errors.New("proxy url must not contain a path, query or fragment")
+		}
+	}
+	if c.CACertFile != "" && c.InsecureSkipTLSVerify {
+		return errors.New("ca cert file and insecure TLS cannot be enabled together")
+	}
+	for name, value := range map[string]string{
+		"heartbeat interval": c.HeartbeatInterval,
+		"poll interval":      c.PollInterval,
+	} {
+		duration, durationErr := time.ParseDuration(value)
+		if durationErr != nil || duration <= 0 {
+			return fmt.Errorf("%s must be a positive duration", name)
+		}
 	}
 	return nil
 }
@@ -101,5 +188,9 @@ func applyConfigDefaults(cfg *Config) (*Config, error) {
 		cfg.TempDir = "/var/lib/backupx-agent/tmp"
 	}
 	cfg.Master = strings.TrimRight(strings.TrimSpace(cfg.Master), "/")
+	cfg.Token = strings.TrimSpace(cfg.Token)
+	cfg.TokenFile = strings.TrimSpace(cfg.TokenFile)
+	cfg.ProxyURL = strings.TrimSpace(cfg.ProxyURL)
+	cfg.CACertFile = strings.TrimSpace(cfg.CACertFile)
 	return cfg, nil
 }
--- a/server/internal/agent/config_test.go
+++ b/server/internal/agent/config_test.go
@@ -11,9 +11,12 @@ func TestLoadConfigFile(t *testing.T) {
 	path := filepath.Join(dir, "agent.yaml")
 	content := `master: http://master.example.com:8340/
 token: abc123
+tokenFile: /run/secrets/backupx_agent_token
 heartbeatInterval: 20s
 pollInterval: 3s
 tempDir: /var/backupx-agent
+proxyUrl: socks5h://127.0.0.1:1080
+caCertFile: /etc/backupx-agent/ca.pem
 insecureSkipTlsVerify: true
 `
 	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
@@ -35,6 +38,9 @@ insecureSkipTlsVerify: true
 	if !cfg.InsecureSkipTLSVerify {
 		t.Errorf("insecure should be true")
 	}
+	if cfg.ProxyURL != "socks5h://127.0.0.1:1080" || cfg.CACertFile != "/etc/backupx-agent/ca.pem" {
+		t.Errorf("connection options not loaded: %+v", cfg)
+	}
 }

 func TestLoadConfigDefaults(t *testing.T) {
@@ -64,8 +70,15 @@ func TestConfigValidate(t *testing.T) {
 		{"valid", Config{Master: "http://m", Token: "t"}, false},
 		{"missing master", Config{Token: "t"}, true},
 		{"missing token", Config{Master: "http://m"}, true},
+		{"invalid master scheme", Config{Master: "ssh://m", Token: "t"}, true},
+		{"master credentials rejected", Config{Master: "https://user:pass@m", Token: "t"}, true},
+		{"valid socks proxy", Config{Master: "https://m", Token: "t", ProxyURL: "socks5h://127.0.0.1:1080"}, false},
+		{"invalid proxy", Config{Master: "https://m", Token: "t", ProxyURL: "ftp://proxy"}, true},
+		{"proxy path rejected", Config{Master: "https://m", Token: "t", ProxyURL: "http://proxy/connect"}, true},
+		{"invalid heartbeat", Config{Master: "https://m", Token: "t", HeartbeatInterval: "never"}, true},
 	}
 	for _, c := range cases {
+		_, _ = applyConfigDefaults(&c.cfg)
 		err := c.cfg.Validate()
 		if (err != nil) != c.wantErr {
 			t.Errorf("%s: err=%v wantErr=%v", c.name, err, c.wantErr)
@@ -75,7 +88,7 @@ func TestConfigValidate(t *testing.T) {

 func TestMergeWithFlags(t *testing.T) {
 	cfg := &Config{Master: "http://old", Token: "old"}
-	cfg.MergeWithFlags("http://new", "", "/tmp/x")
+	cfg.ApplyOverrides(Overrides{Master: "http://new", TempDir: "/tmp/x", ProxyURL: "http://proxy:3128"})
 	if cfg.Master != "http://new" {
 		t.Errorf("master not overridden: %q", cfg.Master)
 	}
@@ -85,17 +98,50 @@ func TestMergeWithFlags(t *testing.T) {
 	if cfg.TempDir != "/tmp/x" {
 		t.Errorf("tempDir: %q", cfg.TempDir)
 	}
+	if cfg.ProxyURL != "http://proxy:3128" {
+		t.Errorf("proxyUrl: %q", cfg.ProxyURL)
+	}
+}
+
+func TestTokenFileOverrideReplacesConfiguredToken(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "agent.token")
+	if err := os.WriteFile(path, []byte("file-token\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg := &Config{Token: "yaml-token", TokenFile: "/old/token"}
+	cfg.ApplyOverrides(Overrides{TokenFile: "  " + path + "  "})
+	if err := cfg.ResolveToken(); err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Token != "file-token" || cfg.TokenFile != path {
+		t.Fatalf("token file override was not applied: %+v", cfg)
+	}
 }

 func TestLoadConfigFromEnv(t *testing.T) {
 	t.Setenv("BACKUPX_AGENT_MASTER", "http://env-master")
 	t.Setenv("BACKUPX_AGENT_TOKEN", "env-token")
+	t.Setenv("BACKUPX_AGENT_PROXY_URL", "http://env-proxy:8080")
 	t.Setenv("BACKUPX_AGENT_INSECURE_TLS", "true")
 	cfg, err := LoadConfigFromEnv()
 	if err != nil {
 		t.Fatal(err)
 	}
-	if cfg.Master != "http://env-master" || cfg.Token != "env-token" || !cfg.InsecureSkipTLSVerify {
+	if cfg.Master != "http://env-master" || cfg.Token != "env-token" || cfg.ProxyURL != "http://env-proxy:8080" || !cfg.InsecureSkipTLSVerify {
 		t.Errorf("env not picked up: %+v", cfg)
 	}
 }
+
+func TestResolveTokenFile(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "agent.token")
+	if err := os.WriteFile(path, []byte(" file-token\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg := &Config{TokenFile: path}
+	if err := cfg.ResolveToken(); err != nil {
+		t.Fatal(err)
+	}
+	if cfg.Token != "file-token" {
+		t.Fatalf("token = %q", cfg.Token)
+	}
+}