openteam/server/internal/api/admin_stats.go

package api

import (
	"math"
	"net/http"
	"sort"
	"strconv"
	"time"

	"github.com/gin-gonic/gin"
	"github.com/openteam/server/internal/pkg/resp"
	"github.com/openteam/server/internal/store"
)

// AdminStatsOverview GET /api/v1/admin/stats/overview — 运营总览。
func (h *Handler) AdminStatsOverview(c *gin.Context) {
	now := time.Now().UTC()
	today := now.Format("2006-01-02")
	month := now.Format("2006-01")

	var totalUsers int64
	h.a.DB.Model(&store.User{}).Count(&totalUsers)
	var totalKeys int64
	h.a.DB.Model(&store.APIKey{}).Count(&totalKeys)
	var totalChannels int64
	h.a.DB.Model(&store.Channel{}).Count(&totalChannels)
	var totalModels int64
	h.a.DB.Model(&store.Model{}).Count(&totalModels)

	// 全局今日/本月汇总（跨用户）
	var todayReq, monthReq int64
	var todayCost, monthCost float64
	var todayTokens, monthTokens int64
	h.a.DB.Model(&store.UsageDaily{}).Where("date = ?", today).
		Select("COALESCE(SUM(requests),0), COALESCE(SUM(cost),0), COALESCE(SUM(input_tokens+output_tokens+cache_read_tokens),0)").
		Row().Scan(&todayReq, &todayCost, &todayTokens)
	h.a.DB.Model(&store.UsageDaily{}).Where("date LIKE ?", month+"%").
		Select("COALESCE(SUM(requests),0), COALESCE(SUM(cost),0), COALESCE(SUM(input_tokens+output_tokens+cache_read_tokens),0)").
		Row().Scan(&monthReq, &monthCost, &monthTokens)

	// 近 14 天趋势（日粒度）
	var days []struct {
		Date string
		Req  int64
		Cost float64
	}
	h.a.DB.Model(&store.UsageDaily{}).
		Select("date, SUM(requests) req, SUM(cost) cost").
		Where("date >= ?", now.AddDate(0, 0, -13).Format("2006-01-02")).
		Group("date").Order("date").Scan(&days)
	trend := make([]gin.H, 0, len(days))
	for _, d := range days {
		trend = append(trend, gin.H{"date": d.Date, "requests": d.Req, "cost": d.Cost})
	}

	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},
		"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"))
	size, _ := strconv.Atoi(c.DefaultQuery("page_size", "20"))
	if page < 1 {
		page = 1
	}
	if size < 1 || size > 100 {
		size = 20
	}
	q := h.a.DB.Model(&store.UsageLog{})
	if from := c.Query("from"); from != "" {
		q = q.Where("created_at >= ?", from+" 00:00:00")
	}
	if to := c.Query("to"); to != "" {
		q = q.Where("created_at <= ?", to+" 23:59:59")
	}
	if model := c.Query("model"); model != "" {
		q = q.Where("model_name = ?", model)
	}
	if user := c.Query("user_id"); user != "" {
		q = q.Where("user_id = ?", user)
	}
	var total int64
	q.Count(&total)
	var logs []store.UsageLog
	q.Order("id DESC").Offset((page - 1) * size).Limit(size).Find(&logs)
	// 批量预取用户名与渠道名：每行两次查询在 100 行分页下是 200 次额外查询
	userNames := map[uint64]string{}
	chNames := map[uint64]string{}
	userIDs := make([]uint64, 0, len(logs))
	chIDs := make([]uint64, 0, len(logs))
	for _, l := range logs {
		userIDs = append(userIDs, l.UserID)
		if l.ChannelID > 0 {
			chIDs = append(chIDs, l.ChannelID)
		}
	}
	if len(userIDs) > 0 {
		var us []store.User
		h.a.DB.Select("id, username").Where("id IN ?", userIDs).Find(&us)
		for _, u := range us {
			userNames[u.ID] = u.Username
		}
	}
	if len(chIDs) > 0 {
		var cs []store.Channel
		h.a.DB.Select("id, name").Where("id IN ?", chIDs).Find(&cs)
		for _, ch := range cs {
			chNames[ch.ID] = ch.Name
		}
	}
	out := make([]gin.H, 0, len(logs))
	for _, l := range logs {
		out = append(out, gin.H{
			"id": l.ID, "user": userNames[l.UserID], "user_id": l.UserID, "model": l.ModelName, "protocol": l.Protocol,
			"channel_id": l.ChannelID, "channel": chNames[l.ChannelID],
			"input_tokens": l.InputTokens, "output_tokens": l.OutputTokens,
			"cache_read_tokens": l.CacheReadTokens, "cache_creation_tokens": l.CacheCreationTokens,
			"reasoning_tokens": l.ReasoningTokens, "cache_write_1h_tokens": l.CacheWrite1hTokens,
			"served_model": l.ServedModel, "cost": l.Cost,
			"latency_ms": l.LatencyMS, "status": l.Status, "error_code": l.ErrorCode,
			// 原始体（可能是整段 SSE，百 KB～MB 级）不进列表：15 行一页就能到几十 MB。
			// 只给一个标记，需要时走 /admin/usage/:id 单独取。
			"has_raw":    l.RawRequest != "" || l.RawResponse != "",
			"created_at": l.CreatedAt,
		})
	}
	resp.OK(c, gin.H{"items": out, "total": total, "page": page, "page_size": size})
}

// AdminUsageDetail 单条用量的完整明细（含原始请求/响应体）。
// 列表接口刻意不返回原始体：它们可能是整段 SSE，把列表响应撑到几十 MB 没有意义。
func (h *Handler) AdminUsageDetail(c *gin.Context) {
	id, err := strconv.ParseUint(c.Param("id"), 10, 64)
	if err != nil {
		resp.Fail(c, http.StatusBadRequest, "invalid usage id")
		return
	}
	var l store.UsageLog
	if err := h.a.DB.First(&l, id).Error; err != nil {
		resp.Fail(c, http.StatusNotFound, "usage log not found")
		return
	}
	var u store.User
	h.a.DB.Select("id, username").First(&u, l.UserID)
	var ch store.Channel
	if l.ChannelID > 0 {
		h.a.DB.Select("id, name").First(&ch, l.ChannelID)
	}
	resp.OK(c, gin.H{
		"id": l.ID, "user": u.Username, "user_id": l.UserID, "model": l.ModelName, "protocol": l.Protocol,
		"channel_id": l.ChannelID, "channel": ch.Name,
		"input_tokens": l.InputTokens, "output_tokens": l.OutputTokens,
		"cache_read_tokens": l.CacheReadTokens, "cache_creation_tokens": l.CacheCreationTokens,
		"reasoning_tokens": l.ReasoningTokens, "cache_write_1h_tokens": l.CacheWrite1hTokens,
		"served_model": l.ServedModel, "cost": l.Cost,
		"latency_ms": l.LatencyMS, "status": l.Status, "error_code": l.ErrorCode,
		"raw_request": l.RawRequest, "raw_response": l.RawResponse,
		"has_raw":    l.RawRequest != "" || l.RawResponse != "",
		"created_at": l.CreatedAt,
	})
}