Files
chick 20070b90f7 fix: enroll 写出守护进程会拒绝的配置,install 写出与自身路径不符的单元
四处"校验在错误的层"的缺陷,都属于同一类:每个组件单独看都对,接缝错了。

1. `msa-agent enroll --relay http://relay.example` / `relay.example` /
   `https://relay.example/v1` 都会写出配置文件,install 报成功,守护进程在**下一次启动**才
   拒绝,日志里只有一行 "msa-agent exiting"。规则原本散在三处(config 只查非空、transport
   查真实规则、enroll 的注册客户端另有一份),现在收进 `internal/relayurl` 一份,三处都调它。
   `config.File.Validate` 因此也补上了 https/host/无路径/无 query 的检查。

2. `enroll` 不再自己手写字段检查,改为构造真正的 `config.File` 并调用真正的 `Validate`——
   一份"什么是可用配置"的定义,结构上无法再漂移。`config.Marshal` 让 enroll 与 Save 用同一个
   编码器。

3. `install --config /srv/msa/config.json` 会给该文件改属主、交给服务用户,然后写一个
   ExecStart 指向 `/etc/msa-agent/config.json` 的单元——服务起来找不到配置就退出,而它需要的
   文件就在别处、属主正确、从未被读。`enroll --audit /srv/audit/audit.log` 同理:单元的
   `ReadWritePaths` 只覆盖 `/var/log/msa-agent`,在 `ProtectSystem=strict` 下 agent 的
   `MkdirAll` 报 EROFS,进程启动即退出,报错既不提那个 flag 也不提那条指令。现在单元是模板,
   `RenderedUnit` 按实际布局渲染,`--print-unit` 打印的就是会被写入的那一份;默认布局渲染结果
   与仓库里被 review 过的文件逐字节相同,所以 vendored 副本的漂移检查仍然有意义。

测试:新增 `internal/relayurl`,`config`/`enroll`/`install` 各补回归测试。每条都做了变异验证
(把修复回退,对应测试必须失败)。
2026-09-18 12:38:56 +08:00

188 lines
7.1 KiB
Go

package enroll
import (
"crypto/ed25519"
"encoding/base64"
"encoding/json"
"strings"
"testing"
)
// The two artefacts have to agree, and that agreement is the whole reason this is a package rather
// than two commands: the config carries the private signing key, the registration carries the public
// one, and a node whose relay entry was minted from a different key pair authenticates nowhere.
func TestTheConfigAndTheRegistrationDescribeTheSameNode(t *testing.T) {
result, err := Generate(Options{
RelayURL: "https://relay.example",
LocalPort: 3000,
AuditPath: "/var/log/msa-agent/audit.log",
})
if err != nil {
t.Fatalf("Generate: %v", err)
}
var cfg struct {
NodeID string `json:"nodeId"`
RelayURL string `json:"relayUrl"`
AgentToken string `json:"agentToken"`
LocalPort int `json:"localPort"`
SignKey string `json:"signKey"`
KxKey string `json:"kxKey"`
AuditPath string `json:"auditPath"`
Devices []any `json:"devices"`
}
if err := json.Unmarshal(result.Config, &cfg); err != nil {
t.Fatalf("the config is not valid JSON: %v", err)
}
var reg Registration
if err := json.Unmarshal(result.Registration, &reg); err != nil {
t.Fatalf("the registration is not valid JSON: %v", err)
}
if cfg.NodeID != reg.NodeID || cfg.NodeID != result.NodeID {
t.Fatalf("node ids disagree: config=%q registration=%q result=%q", cfg.NodeID, reg.NodeID, result.NodeID)
}
if cfg.AgentToken != reg.Token {
t.Fatal("the config's bearer and the registration's token differ; the agent would 401")
}
if cfg.RelayURL != "https://relay.example" || cfg.LocalPort != 3000 {
t.Fatalf("relay or port lost: %+v", cfg)
}
if cfg.Devices == nil || len(cfg.Devices) != 0 {
t.Fatalf("devices must start empty, got %v", cfg.Devices)
}
// The private key is 64 bytes; its last 32 are the public key, which is what the relay verifies.
private, err := base64.StdEncoding.DecodeString(cfg.SignKey)
if err != nil || len(private) != ed25519.PrivateKeySize {
t.Fatalf("signKey is not a base64 ed25519 private key: %v (%d bytes)", err, len(private))
}
public, err := base64.StdEncoding.DecodeString(reg.SignKey)
if err != nil || len(public) != ed25519.PublicKeySize {
t.Fatalf("the registration's signKey is not a base64 ed25519 public key: %v (%d bytes)", err, len(public))
}
if string(private[ed25519.PrivateKeySize-ed25519.PublicKeySize:]) != string(public) {
t.Fatal("the relay's registration carries a key that does not belong to the config's private key")
}
}
// The node password is the one secret this tool must not invent. An unprotected node needs no value;
// a protected one needs the real one, or every command fails with node_auth_failed and the cause is
// not obvious from the phone.
func TestTheNodePasswordIsOnlyWrittenWhenGiven(t *testing.T) {
without, err := Generate(Options{RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a"})
if err != nil {
t.Fatal(err)
}
if strings.Contains(string(without.Config), "nodePassword") {
t.Fatal("a config with no password claims one")
}
with, err := Generate(Options{
RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a", NodePassword: "hunter2",
})
if err != nil {
t.Fatal(err)
}
if !strings.Contains(string(with.Config), `"nodePassword": "hunter2"`) {
t.Fatal("the given password was not written")
}
}
// Re-enrolling a node has to be able to keep the identifiers the relay already knows, or the operator
// has two edits to make instead of one.
func TestGivenIdentifiersAreKept(t *testing.T) {
result, err := Generate(Options{
RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a",
NodeID: "nd_keepme0001", AgentToken: strings.Repeat("a", 64), ProvisionSecret: "kept-secret",
})
if err != nil {
t.Fatal(err)
}
var reg Registration
if err := json.Unmarshal(result.Registration, &reg); err != nil {
t.Fatal(err)
}
if reg.NodeID != "nd_keepme0001" || reg.Token != strings.Repeat("a", 64) {
t.Fatalf("identifiers were regenerated: %+v", reg)
}
if result.ProvisionSecret != "kept-secret" {
t.Fatal("the pairing secret was regenerated")
}
}
// Two enrollments must not produce the same keys or ids. A generator that repeated a key would make
// two nodes able to impersonate each other, and it is the kind of bug a seeded RNG introduces once.
func TestTwoEnrollmentsDiffer(t *testing.T) {
first, err := Generate(Options{RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a"})
if err != nil {
t.Fatal(err)
}
second, err := Generate(Options{RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a"})
if err != nil {
t.Fatal(err)
}
if first.NodeID == second.NodeID {
t.Fatal("two enrollments produced the same node id")
}
if string(first.Config) == string(second.Config) {
t.Fatal("two enrollments produced the same config, so the same keys")
}
}
// Enrollment is where a bad relay URL is cheapest to catch and where it used to be missed entirely.
// It built a map[string]any with a handful of hand-written checks, so `--relay relay.example` and
// `--relay https://relay.example/v1` both produced a config file, the install reported success, and
// the daemon refused the file at the next startup. The values below are the ones that were measured
// being written.
func TestARelayURLTheDaemonWouldRefuseIsNeverWritten(t *testing.T) {
for _, raw := range []string{
"relay.example",
"http://relay.example",
"https://relay.example/v1",
"https://relay.example?x=1",
"https://",
} {
if _, err := Generate(Options{RelayURL: raw, LocalPort: 3000, AuditPath: "/a"}); err == nil {
t.Errorf("wrote a config for relay %q", raw)
}
}
}
func TestMissingInputIsRefused(t *testing.T) {
cases := map[string]Options{
"no relay": {LocalPort: 3000, AuditPath: "/a"},
"bad port": {RelayURL: "https://relay.example", LocalPort: 0, AuditPath: "/a"},
"huge port": {RelayURL: "https://relay.example", LocalPort: 70000, AuditPath: "/a"},
"no audit": {RelayURL: "https://relay.example", LocalPort: 3000},
}
for name, opts := range cases {
if _, err := Generate(opts); err == nil {
t.Fatalf("%s was accepted", name)
}
}
}
// The node records how it got into the relay, because `uninstall` cannot work it out any other way: the
// agent holds no admin token, so it cannot remove its own entry, and the operator has to be told which
// of the relay's two records mentions this node.
func TestEnrollmentRecordsItsOwnProvenance(t *testing.T) {
withCode, err := Generate(Options{
RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a", SelfEnrolled: true,
})
if err != nil {
t.Fatal(err)
}
if !strings.Contains(string(withCode.Config), `"selfEnrolled": true`) {
t.Fatal("a self-enrolled node does not say so")
}
// And a node an operator wrote into agents.json does not claim to have enrolled itself, or the
// uninstall would send the operator to the app to remove an entry that is not there.
manual, err := Generate(Options{RelayURL: "https://relay.example", LocalPort: 3000, AuditPath: "/a"})
if err != nil {
t.Fatal(err)
}
if strings.Contains(string(manual.Config), "selfEnrolled") {
t.Fatal("a manually registered node claims to be self-enrolled")
}
}