feat: 补齐上游细节、渠道观测与模型定价元数据
- 上游 429 的 Retry-After 转成渠道冷却时长（夹在 10 分钟内；比默认值短则不缩短， 否则 1s 就把坏渠道放回轮转）。失败计数改由 proxyOne 就地报——只有它读得到响应头。 - 故障转移时间预算 OT_PROXY_FAILOVER_BUDGET（默认 30s）：只约束第二个及以后的渠道， 首个不受限（长回答本就要跑几分钟），但坏渠道不再把客户端拖到 N×timeout。 - 流式空闲心跳 OT_PROXY_STREAM_HEARTBEAT（默认 15s）：补一行 SSE 注释 `: ping`， 防止 nginx/Cloudflare 的空闲超时掐掉长思考。心跳与正文共用一把写的锁， gin 的 ResponseWriter 不是并发安全的；注释行不进转换也不计费。 - 渠道观测：GET /api/v1/admin/channels/stats?window=5m|1h|6h|24h|7d 聚合请求量、 成功率、P50/P95/max 延迟、成本与 top_errors；分位只取成功样本，canceled（客户端 主动断开）不计入渠道错误率。渠道页桌面表格加「近N小时」列、移动端加同内容条， 顶部可切窗口。 - 修一个让统计瞎掉的归因问题：全部渠道失败时 recordError 传的是 nil， usage_logs 里 channel_id=0，这类失败在渠道维度完全看不见。改为归到最后一个 真正试过的渠道。 - 模型定价与元数据：Model 新增 cache_write_price（0 则回退输入价×1.25，可显式配 Anthropic 1h 的 ×2）、context_length 与 supports_tools/vision/reasoning； finishUsage 走 CacheWritePriceOr()。/v1/models 叠加用户与密钥白名单过滤 （原来会把限制外的模型名直接泄漏在列表里）并返回元数据，价格不外泄。 - /v1/models 的 Anthropic 分支原是死代码：协议只按路径判，而两种客户端共用这个路径。 改为按 x-api-key / anthropic-version 头判，OpenAI SDK 从不发这两个头，互不影响。 - NewGateway 的十个位置参数换成 Options 结构体（三个 Duration 两个 int，传错编译期发现不了）。 新增 6 个用例：Retry-After 两种写法与夹顶、重试预算截止、空闲心跳出帧、 /v1/models 过滤与双形状、缓存写价两条路径、失败归因。
This commit is contained in:
Sakurasan committed
1 parent
ad10bdc400
commit
c39c3e7da4
16 files changed
+984
-125
No files matched your search
@@ -1,6 +1,8 @@
|
||||
package api
|
||||
|
||||
import (
|
||||
"math"
|
||||
"sort"
|
||||
"strconv"
|
||||
"time"
|
||||
|
||||
@@ -53,12 +55,150 @@ func (h *Handler) AdminStatsOverview(c *gin.Context) {
|
||||
resp.OK(c, gin.H{
|
||||
"total_users": totalUsers, "total_keys": totalKeys,
|
||||
"total_channels": totalChannels, "total_models": totalModels,
|
||||
"today": gin.H{"requests": todayReq, "cost": todayCost, "tokens": todayTokens},
|
||||
"month": gin.H{"requests": monthReq, "cost": monthCost, "tokens": monthTokens},
|
||||
"today": gin.H{"requests": todayReq, "cost": todayCost, "tokens": todayTokens},
|
||||
"month": gin.H{"requests": monthReq, "cost": monthCost, "tokens": monthTokens},
|
||||
"trend_14d": trend,
|
||||
})
|
||||
}
|
||||
|
||||
// AdminChannelStats GET /api/v1/admin/channels/stats?window=1h — 按渠道聚合近一段的
|
||||
// 请求量、成功率、错误码分布与延迟分位。定位"哪条渠道在掉"不该靠翻日志。
|
||||
func (h *Handler) AdminChannelStats(c *gin.Context) {
|
||||
win := c.DefaultQuery("window", "1h")
|
||||
d, ok := statWindows[win]
|
||||
if !ok {
|
||||
win, d = "1h", statWindows["1h"]
|
||||
}
|
||||
since := time.Now().UTC().Add(-d)
|
||||
|
||||
// 只取窗口内最近这么多行，避免大窗口把内存吃光（超出部分不参与分位计算）
|
||||
const maxRows = 50000
|
||||
var rows []channelStatRow
|
||||
h.a.DB.Model(&store.UsageLog{}).
|
||||
Select("channel_id, status, latency_ms, cost, "+
|
||||
"(input_tokens + output_tokens + cache_read_tokens) AS tokens, error_code, created_at").
|
||||
Where("created_at >= ? AND channel_id > 0", since).
|
||||
Order("id DESC").Limit(maxRows).Scan(&rows)
|
||||
|
||||
agg := map[uint64]*chanAgg{}
|
||||
for _, r := range rows {
|
||||
a := agg[r.ChannelID]
|
||||
if a == nil {
|
||||
a = &chanAgg{lat: make([]int, 0, 64), errs: map[string]int{}}
|
||||
agg[r.ChannelID] = a
|
||||
}
|
||||
a.requests++
|
||||
a.cost += r.Cost
|
||||
a.tokens += r.Tokens
|
||||
switch r.Status {
|
||||
case store.UsageStatusSuccess:
|
||||
a.success++
|
||||
a.lat = append(a.lat, r.LatencyMS) // 分位只按正常完成的请求算，中断/失败的延迟不代表体感
|
||||
case store.UsageStatusCanceled:
|
||||
a.canceled++
|
||||
default:
|
||||
a.err++
|
||||
if r.ErrorCode != nil && *r.ErrorCode != "" {
|
||||
a.errs[*r.ErrorCode]++
|
||||
}
|
||||
}
|
||||
if r.CreatedAt.After(a.lastAt) {
|
||||
a.lastAt = r.CreatedAt
|
||||
}
|
||||
}
|
||||
|
||||
var chans []store.Channel
|
||||
h.a.DB.Find(&chans)
|
||||
names := make(map[uint64]string, len(chans))
|
||||
for _, ch := range chans {
|
||||
names[ch.ID] = ch.Name
|
||||
}
|
||||
|
||||
out := make([]gin.H, 0, len(agg))
|
||||
for id, a := range agg {
|
||||
out = append(out, gin.H{
|
||||
"channel_id": id, "channel_name": names[id],
|
||||
"requests": a.requests, "success": a.success,
|
||||
"error": a.err, "canceled": a.canceled,
|
||||
"err_rate": rate(a.err, a.requests), // canceled 是客户端主动断开，不算渠道的错
|
||||
"p50_ms": percentile(a.lat, 0.50),
|
||||
"p95_ms": percentile(a.lat, 0.95),
|
||||
"max_ms": percentile(a.lat, 1.0),
|
||||
"tokens": a.tokens,
|
||||
"cost": a.cost,
|
||||
"top_errors": topErrors(a.errs, 3),
|
||||
"last_at": a.lastAt,
|
||||
})
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool {
|
||||
return out[i]["requests"].(int64) > out[j]["requests"].(int64)
|
||||
})
|
||||
resp.OK(c, gin.H{"window": win, "since": since, "items": out})
|
||||
}
|
||||
|
||||
// statWindows 支持的统计窗口。
|
||||
var statWindows = map[string]time.Duration{
|
||||
"5m": 5 * time.Minute,
|
||||
"1h": time.Hour,
|
||||
"6h": 6 * time.Hour,
|
||||
"24h": 24 * time.Hour,
|
||||
"7d": 7 * 24 * time.Hour,
|
||||
}
|
||||
|
||||
type channelStatRow struct {
|
||||
ChannelID uint64
|
||||
Status string
|
||||
LatencyMS int
|
||||
Cost float64
|
||||
Tokens int64
|
||||
ErrorCode *string
|
||||
CreatedAt time.Time
|
||||
}
|
||||
|
||||
type chanAgg struct {
|
||||
requests, success, err, canceled int64
|
||||
cost float64
|
||||
tokens int64
|
||||
lat []int
|
||||
errs map[string]int
|
||||
lastAt time.Time
|
||||
}
|
||||
|
||||
func rate(part, total int64) float64 {
|
||||
if total <= 0 {
|
||||
return 0
|
||||
}
|
||||
return float64(part) / float64(total)
|
||||
}
|
||||
|
||||
// percentile 最近秩法取分位（q=1 为最大值）；空样本返回 0。
|
||||
func percentile(xs []int, q float64) int {
|
||||
if len(xs) == 0 {
|
||||
return 0
|
||||
}
|
||||
sort.Ints(xs)
|
||||
idx := int(math.Ceil(q*float64(len(xs)))) - 1
|
||||
if idx < 0 {
|
||||
idx = 0
|
||||
}
|
||||
if idx >= len(xs) {
|
||||
idx = len(xs) - 1
|
||||
}
|
||||
return xs[idx]
|
||||
}
|
||||
|
||||
func topErrors(m map[string]int, n int) []gin.H {
|
||||
list := make([]gin.H, 0, len(m))
|
||||
for code, cnt := range m {
|
||||
list = append(list, gin.H{"code": code, "count": cnt})
|
||||
}
|
||||
sort.Slice(list, func(i, j int) bool { return list[i]["count"].(int) > list[j]["count"].(int) })
|
||||
if len(list) > n {
|
||||
list = list[:n]
|
||||
}
|
||||
return list
|
||||
}
|
||||
|
||||
// AdminUsage GET /api/v1/admin/usage — 全局用量日志（分页 + 过滤）。
|
||||
func (h *Handler) AdminUsage(c *gin.Context) {
|
||||
page, _ := strconv.Atoi(c.DefaultQuery("page", "1"))
|
||||
|
||||
Reference in new issue
Block a user