feat(gateway): per-key 用量配额(token + 请求数)与重置周期

问题:密钥控制只能限制模型范围。实测发现三个缺陷,其中前两个让
per-model token_quota 在真实链路上从未生效:

1. 桶键不含 key。scopeTokens 调 WindowTokens(model, source, win),
   桶键是 model / source::model,与调用方无关。实测两把 key 各用
   1000 token,窗口报 2000 —— A key 的额度被 B key 消耗。
2. 无 source pin 的桶永远是空的。真实记录 Source 总被填上,桶键存成
   "deepseek::m1",而无 pin 的查询找 "m1" —— 读到 0,永远 < quota,
   配额形同虚设。实测 WindowTokens("m1","",1h)=0 而 pinned=2000。
3. AUTO scope 走 KeyTokens(key),是全时段累计、永不重置。实测 30 天
   前的 200 token 仍计入 1 小时配额(报 210 而非 10)。配了
   period: hour 也不会每小时归零。

生产 5 把 user key 全是 token_quota: 0,所以前两条一直没暴露。

改动:
- Stats 新增 per-key 小时桶 keyModelHour(key → model → hour)与
  keyHour(key 总量)、keyReqHour(请求数),retention 40 天,与既有
  modelHour 对齐以覆盖最长的 month 窗口;LoadAudit 走 aggregateLocked,
  所以窗口用量跨重启存活。modelHour 保持 key-blind:它服务的是 AUTO
  槽位配额(限制整个网关对某槽位的消耗),语义不同,不应被 per-key
  改造污染。
- 每个请求写两份模型桶:裸 model 与 source::model。无 pin 的 scope
  条目读前者,有 pin 的读后者。
- GWKey 新增 TokenQuota / ReqQuota / Period / Hours:整钥配额,
  跨该 key 所有模型共享一份预算;ReqQuota 覆盖持续请求量(源上的
  RPM 只管突发)。
- 配额耗尽返回 429 + Retry-After(rate_limit_exceeded),而不是 403:
  403 让客户端以为这把 key 永远不能用该模型,直接放弃;429 + 等待
  才能在窗口重置后自动恢复。模型越权仍是 403。
- admin key 永不受配额限制 —— 否则操作者会把自己锁在门外。
- 周期词表在写入时校验,拼错的 period 被拒绝而不是静默当成永不过期
  (那与操作者输入的意图正好相反)。
- PUT /api/keys 的配额字段是指针:省略=保留原值,显式 0=解除限制。
  否则只改模型范围就会悄悄清空预算。

判据 3 个文件 24 例,9 个变异全部被抓:key 隔离、pin 桶缺失、
AUTO 周期、key-blind 退化、429→403、admin 被限、PUT 清空配额、
Validate 失效、pinned 桶缺失。前三个变异最初漏网 —— 判据只测了
Stats 层没测接线,补了走真实 HTTP 的接线层与 API 层判据后抓住。
端到端验证:真实进程 + 加密配置往返,配额字段与 enc:v1 密钥均正常。

(cherry picked from commit 5306251840)
This commit is contained in:
JianFeeeee
2026-09-27 17:23:36 +08:00
parent a7355debed
commit 9c3aabb7f9
9 changed files with 1151 additions and 41 deletions

View File

@ -375,6 +375,82 @@ type GWKey struct {
Note string `yaml:"note,omitempty" json:"note,omitempty"`
CreatedAt int64 `yaml:"created_at,omitempty" json:"created_at,omitempty"`
Seed bool `yaml:"seed,omitempty" json:"seed,omitempty"` // true if migrated from config gateway_keys
// TokenQuota caps this key's TOTAL tokens across every model it may use.
// 0 = unlimited. Period/Hours define the reset window, exactly like
// ModelScope: "" never resets, "hour"/"week"/"month" fixed windows,
// "nhour" uses Hours.
TokenQuota int64 `yaml:"token_quota,omitempty" json:"token_quota,omitempty"`
Period string `yaml:"period,omitempty" json:"period,omitempty"`
Hours int64 `yaml:"hours,omitempty" json:"hours,omitempty"`
// ReqQuota caps the number of requests per reset window; 0 = unlimited.
// RPM covers short bursts; this covers sustained volume.
ReqQuota int64 `yaml:"req_quota,omitempty" json:"req_quota,omitempty"`
}
// KeyQuota is the set of key-wide caps accepted by the admin API. It is a
// separate struct so a partial update can be expressed as a pointer (nil =
// "leave the stored caps alone") instead of zero values meaning "clear".
type KeyQuota struct {
TokenQuota int64 `json:"token_quota"`
ReqQuota int64 `json:"req_quota"`
Period string `json:"period"`
Hours int64 `json:"hours"`
}
// ApplyQuota writes the caps onto a key record.
func (k *GWKey) ApplyQuota(q KeyQuota) {
k.TokenQuota = q.TokenQuota
k.ReqQuota = q.ReqQuota
k.Period = q.Period
k.Hours = q.Hours
}
// NormalizeRole defaults an empty role to "user", so a key can never end up in
// a state where no role means "neither admin nor user".
func NormalizeRole(role string) string {
if role == "admin" {
return "admin"
}
return "user"
}
// Validate rejects a quota configuration that could not work as written. A
// period is only meaningful when at least one cap is set, and a cap of zero
// means "unlimited" rather than "deny everything", so those are the only two
// things worth rejecting.
func (q KeyQuota) Validate() error {
if q.TokenQuota < 0 {
return fmt.Errorf("token_quota must be >= 0 (0 = unlimited)")
}
if q.ReqQuota < 0 {
return fmt.Errorf("req_quota must be >= 0 (0 = unlimited)")
}
if q.Hours < 0 {
return fmt.Errorf("hours must be >= 0")
}
if q.TokenQuota > 0 || q.ReqQuota > 0 {
if err := ValidatePeriod(q.Period, q.Hours); err != nil {
return err
}
}
return nil
}
// ValidatePeriod accepts the quota period vocabulary: "" (never resets),
// "hour", "week", "month", or "nhour" with hours >= 1. An unknown period is
// rejected rather than silently treated as "never resets", which would turn a
// typo into an all-time quota — the opposite of what the operator typed.
func ValidatePeriod(period string, hours int64) error {
switch period {
case "", "hour", "week", "month":
return nil
case "nhour":
if hours < 1 {
return fmt.Errorf("period %q needs hours >= 1", period)
}
return nil
}
return fmt.Errorf("period must be one of \"\", hour, week, month, nhour (got %q)", period)
}
// ModelScope is one allowed model for a key, or one AUTO scheduling slot,