fix(agent): 手机已经放弃的请求不再执行
中继答 504 并说"可能已经执行了，重试前请先确认"——这句话诚实的前提是它保持为真。 批次是串行处理的，所以满邮箱里第八个信封可以在它被签名之后 8 个上游超时才轮到； 那时手机早已被告知失败、用户可能已经重试。再执行它，就把一次诚实的"未知"变成了 一条重复发出的短信。 现在 agent 在动任何东西之前先比对自己的截止时间（策略里的 requestTtlSeconds）， 超龄一律以 expired 拒绝并落审计。判定放在新鲜度检查之后、策略判定之前：它比签名 更便宜，而且一个过期请求无论路径是否在白名单里都不该执行。 为了让这条规则**可达**，策略新增一条断言：TTL 不得大于时钟偏移窗口。否则新鲜度 检查会先触发，这条规则永远不会被执行——而"永不触发的规则"是出事时才会被发现坏了 的那种东西。 单个上游调用的超时也移进了策略（agentUpstreamTimeoutSeconds）。"中继期限必须长于 一次上游调用"这个比较，与二进制里的常量是比不了的；现在两侧从同一个文件读，策略 加载时就能拒绝一组自相矛盾的数值。原来那个 20s 常量保留为默认值的来源，不再硬编码。 测试两项：一个请求在期限内被转发、一个超龄请求被拒且**没有被转发**（计数按路径， 否则首次转发前的 /api/auth/status 探测会让断言以错误的理由通过）；另一项断言策略 本身满足上述两个关系。变异验证：关掉判定，第一项失败。 Go 全包、Node 119 项、Swift 101 项通过。
This commit is contained in:
chick
@@ -31,6 +31,7 @@
|
||||
"dangerous": ["/api/sms/send", "/api/sms/batch-delete"],
|
||||
"limits": {
|
||||
"dangerousWritesPerMinute": 6,
|
||||
"agentUpstreamTimeoutSeconds": 20,
|
||||
"maxRequestBytes": 262144,
|
||||
"maxResponseBytes": 262144,
|
||||
"requestTtlSeconds": 30,
|
||||
|
||||
+32
-14
@@ -39,12 +39,17 @@ type AuthPaths struct {
|
||||
|
||||
type Limits struct {
|
||||
DangerousWritesPerMinute int `json:"dangerousWritesPerMinute"`
|
||||
MaxRequestBytes int `json:"maxRequestBytes"`
|
||||
MaxResponseBytes int `json:"maxResponseBytes"`
|
||||
RequestTTLSeconds int `json:"requestTtlSeconds"`
|
||||
ClockSkewSeconds int `json:"clockSkewSeconds"`
|
||||
ReplayCacheSize int `json:"replayCacheSize"`
|
||||
MailboxDepth int `json:"mailboxDepth"`
|
||||
// AgentUpstreamTimeoutSeconds is how long one loopback call to SimAdmin may take. It lives in the
|
||||
// policy rather than only in the agent's code because the relay's deadline has to be compared
|
||||
// against it, and a comparison between a policy file and a constant in a binary is not one
|
||||
// anything can check.
|
||||
AgentUpstreamTimeoutSeconds int `json:"agentUpstreamTimeoutSeconds"`
|
||||
MaxRequestBytes int `json:"maxRequestBytes"`
|
||||
MaxResponseBytes int `json:"maxResponseBytes"`
|
||||
RequestTTLSeconds int `json:"requestTtlSeconds"`
|
||||
ClockSkewSeconds int `json:"clockSkewSeconds"`
|
||||
ReplayCacheSize int `json:"replayCacheSize"`
|
||||
MailboxDepth int `json:"mailboxDepth"`
|
||||
}
|
||||
|
||||
type Policy struct {
|
||||
@@ -148,13 +153,14 @@ func Parse(raw []byte) (*Policy, error) {
|
||||
}
|
||||
|
||||
for name, value := range map[string]int{
|
||||
"dangerousWritesPerMinute": p.Limits.DangerousWritesPerMinute,
|
||||
"maxRequestBytes": p.Limits.MaxRequestBytes,
|
||||
"maxResponseBytes": p.Limits.MaxResponseBytes,
|
||||
"requestTtlSeconds": p.Limits.RequestTTLSeconds,
|
||||
"clockSkewSeconds": p.Limits.ClockSkewSeconds,
|
||||
"replayCacheSize": p.Limits.ReplayCacheSize,
|
||||
"mailboxDepth": p.Limits.MailboxDepth,
|
||||
"dangerousWritesPerMinute": p.Limits.DangerousWritesPerMinute,
|
||||
"maxRequestBytes": p.Limits.MaxRequestBytes,
|
||||
"maxResponseBytes": p.Limits.MaxResponseBytes,
|
||||
"requestTtlSeconds": p.Limits.RequestTTLSeconds,
|
||||
"agentUpstreamTimeoutSeconds": p.Limits.AgentUpstreamTimeoutSeconds,
|
||||
"clockSkewSeconds": p.Limits.ClockSkewSeconds,
|
||||
"replayCacheSize": p.Limits.ReplayCacheSize,
|
||||
"mailboxDepth": p.Limits.MailboxDepth,
|
||||
} {
|
||||
if value <= 0 {
|
||||
return nil, fmt.Errorf("policy: limits.%s must be positive, got %d", name, value)
|
||||
@@ -163,8 +169,20 @@ func Parse(raw []byte) (*Policy, error) {
|
||||
if p.Limits.ClockSkewSeconds > 300 {
|
||||
return nil, errors.New("policy: clockSkewSeconds is too wide to bound replay")
|
||||
}
|
||||
// The relay's deadline has to sit inside the clock-skew window, and the reason is not tidiness.
|
||||
//
|
||||
// The freshness check above rejects an envelope whose timestamp is further from now than
|
||||
// clockSkewSeconds. The agent's own deadline check rejects one older than requestTtlSeconds. If the
|
||||
// TTL were the larger of the two, the freshness check would fire first and the deadline check would
|
||||
// be unreachable — a rule that can never fire, which is the kind of thing that gets discovered
|
||||
// during an incident by someone who assumed it was working.
|
||||
if p.Limits.RequestTTLSeconds > p.Limits.ClockSkewSeconds {
|
||||
return nil, errors.New("policy: requestTtlSeconds exceeds clockSkewSeconds and would never be enforced")
|
||||
return nil, errors.New("policy: requestTtlSeconds exceeds clockSkewSeconds, so the agent's deadline check would never be reached")
|
||||
}
|
||||
// And the node must not be told to wait longer than the phone is willing to. The two are one
|
||||
// decision — how long a request may take end to end — stated in the file that both sides read.
|
||||
if p.Limits.RequestTTLSeconds*1000 <= p.Limits.AgentUpstreamTimeoutSeconds*1000 {
|
||||
return nil, errors.New("policy: requestTtlSeconds must exceed the per-request upstream timeout, or the relay deadline is not the longer bound")
|
||||
}
|
||||
if p.Limits.ReplayCacheSize < p.Limits.MailboxDepth {
|
||||
return nil, errors.New("policy: replayCacheSize is smaller than mailboxDepth, so entries can be evicted while still queued")
|
||||
|
||||
@@ -91,7 +91,10 @@ func NewExecutor(pol *policy.Policy, cfg Config) (*Executor, error) {
|
||||
}
|
||||
timeout := cfg.Timeout
|
||||
if timeout <= 0 {
|
||||
timeout = 20 * time.Second
|
||||
// From the policy, not a constant here. The relay's deadline is compared against this number
|
||||
// when the policy is validated, and a comparison against a constant inside a binary is not one
|
||||
// anything can check.
|
||||
timeout = time.Duration(pol.Limits.AgentUpstreamTimeoutSeconds) * time.Second
|
||||
}
|
||||
client, err := egress.NewClient(target, timeout)
|
||||
if err != nil {
|
||||
@@ -145,6 +148,21 @@ func (e *Executor) Execute(ctx context.Context, envelope wire.Envelope, inner wi
|
||||
if err := Freshness(envelope.TS, uint64(now.Unix()), e.pol.Limits.ClockSkewSeconds); err != nil {
|
||||
return Result{}, e.refuse(envelope, inner, ClassExpired, err)
|
||||
}
|
||||
// The phone's own deadline, checked before anything is executed.
|
||||
//
|
||||
// The relay answers 504 with "it may or may not have executed it; check the node before retrying",
|
||||
// which is honest — but it is only honest while it stays true. A batch is processed serially, so
|
||||
// the eighth envelope of a full mailbox can begin up to eight upstream timeouts after it was
|
||||
// signed; by then the phone has been told the request failed and the user may already have retried.
|
||||
// Executing it at that point turns an honest "unknown" into a duplicate SMS.
|
||||
//
|
||||
// The relay's deadline is the authority on when that happened, because the relay is the party that
|
||||
// starts the clock. Its value is therefore carried in the policy and asserted to be no larger than
|
||||
// the clock-skew window, which is what makes the freshness check above unable to mask this one.
|
||||
if age := int64(now.Unix()) - int64(envelope.TS); age > int64(e.pol.Limits.RequestTTLSeconds) {
|
||||
return Result{}, e.refuse(envelope, inner, ClassExpired,
|
||||
fmt.Errorf("%w: signed %ds ago, deadline is %ds", ErrExpired, age, e.pol.Limits.RequestTTLSeconds))
|
||||
}
|
||||
if e.replay.Seen(envelope.Req, now) {
|
||||
return Result{}, e.refuse(envelope, inner, ClassReplay, fmt.Errorf("%w: %s", ErrReplay, envelope.Req))
|
||||
}
|
||||
|
||||
@@ -594,3 +594,68 @@ func TestAFailedAuditWriteIsReported(t *testing.T) {
|
||||
t.Fatalf("a failed audit write was not reported; log was: %s", captured.String())
|
||||
}
|
||||
}
|
||||
|
||||
// A request whose phone has already given up must not be executed.
|
||||
//
|
||||
// The relay answers 504 with "it may or may not have executed it; check the node before retrying",
|
||||
// which is honest — but only while it stays true. A batch is processed serially, so the eighth
|
||||
// envelope of a full mailbox can begin up to eight upstream timeouts after it was signed. By then the
|
||||
// phone has been told the request failed and the user may have retried; executing it turns an honest
|
||||
// "unknown" into a duplicate SMS.
|
||||
func TestARequestPastItsDeadlineIsNotExecuted(t *testing.T) {
|
||||
// Counted by path: the agent probes /api/auth/status before its first forward, and counting every
|
||||
// request would make the first assertion pass for the wrong reason.
|
||||
executed := 0
|
||||
f := newFixture(t, http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.URL.Path == "/api/sms/send" {
|
||||
executed++
|
||||
}
|
||||
w.WriteHeader(200)
|
||||
}))
|
||||
pol := testPolicy(t)
|
||||
body := []byte(`{"phone_number":"+8613800000000","content":"hello"}`)
|
||||
intent, err := wire.IntentDigest("POST", "/api/sms/send", body)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
inner := wire.InnerRequest{Method: "POST", Path: "/api/sms/send", Body: body, Intent: intent}
|
||||
|
||||
// One second inside the deadline: executed, because the phone is still waiting.
|
||||
envelope := envelopeAt("nd_test0001", newReqID(1), uint64(f.now.Unix()))
|
||||
if _, refusal := f.executor.Execute(context.Background(), envelope, inner); refusal != nil {
|
||||
t.Fatalf("a request inside its deadline was refused: %v", refusal)
|
||||
}
|
||||
if executed != 1 {
|
||||
t.Fatalf("expected one execution, got %d", executed)
|
||||
}
|
||||
|
||||
// One second past it: refused, and nothing is forwarded.
|
||||
f.advance(time.Duration(pol.Limits.RequestTTLSeconds+1) * time.Second)
|
||||
late := envelopeAt("nd_test0001", newReqID(2), uint64(f.now.Unix()-int64(pol.Limits.RequestTTLSeconds)-1))
|
||||
_, refusal := f.executor.Execute(context.Background(), late, inner)
|
||||
if refusal == nil {
|
||||
t.Fatal("a request past its deadline was executed; the phone was told it had failed")
|
||||
}
|
||||
if refusal.Class != ClassExpired {
|
||||
t.Fatalf("refused as %s, want %s", refusal.Class, ClassExpired)
|
||||
}
|
||||
if executed != 1 {
|
||||
t.Fatalf("the late request was forwarded anyway (%d executions)", executed)
|
||||
}
|
||||
}
|
||||
|
||||
// The deadline check is only reachable because the policy keeps the TTL inside the clock-skew window.
|
||||
// If it were not, the freshness check would fire first and the deadline rule could never be reached —
|
||||
// a rule that never fires is one nobody discovers is broken until an incident.
|
||||
func TestThePolicyKeepsTheDeadlineInsideTheFreshnessWindow(t *testing.T) {
|
||||
pol := testPolicy(t)
|
||||
if pol.Limits.RequestTTLSeconds > pol.Limits.ClockSkewSeconds {
|
||||
t.Fatalf("requestTtlSeconds (%d) exceeds clockSkewSeconds (%d); the deadline check is unreachable",
|
||||
pol.Limits.RequestTTLSeconds, pol.Limits.ClockSkewSeconds)
|
||||
}
|
||||
// And the relay's deadline is the longer bound, or the phone gives up before the node does.
|
||||
if pol.Limits.RequestTTLSeconds <= pol.Limits.AgentUpstreamTimeoutSeconds {
|
||||
t.Fatalf("the relay deadline (%ds) is not longer than one upstream call (%ds)",
|
||||
pol.Limits.RequestTTLSeconds, pol.Limits.AgentUpstreamTimeoutSeconds)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user