4c9ed3c24b
Complete rewrite from Python/FastAPI to Go/Gin: - Go backend: auth (API keys + bcrypt), llama.cpp subprocess manager, hot-swap multi-model, rate limiting, quota system, webhooks - Vue 3 SPA admin panel (src/) with Tailwind CSS - Deployment: Docker multi-stage, docker-compose, nginx, systemd - GORM/SQLite models: ApiKey, Model, UsageLog, Quota, Webhook - REST API: /api/v1/admin/* (keys, models, chat, usage, health) - Embedded frontend via go:embed (build output at web/dist/) Removed legacy Python artifacts (app/, tests/, pyproject.toml, etc.)
127 lines
3.3 KiB
Go
127 lines
3.3 KiB
Go
package handlers
|
|
|
|
import (
|
|
"net/http"
|
|
"time"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/google/uuid"
|
|
"gorm.io/gorm"
|
|
|
|
"github.com/llamalink/llamalink/internal/api/middleware"
|
|
"github.com/llamalink/llamalink/internal/db"
|
|
"github.com/llamalink/llamalink/internal/quota"
|
|
)
|
|
|
|
type UsageHandler struct {
|
|
db *gorm.DB
|
|
quotaSvc *quota.Service
|
|
}
|
|
|
|
func NewUsageHandler(db *gorm.DB, quotaSvc *quota.Service) *UsageHandler {
|
|
return &UsageHandler{db: db, quotaSvc: quotaSvc}
|
|
}
|
|
|
|
func (h *UsageHandler) GetUsage(c *gin.Context) {
|
|
keyIDStr := c.Param("key_id")
|
|
keyID, err := uuid.Parse(keyIDStr)
|
|
if err != nil {
|
|
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid key id"})
|
|
return
|
|
}
|
|
|
|
// Only admins or key owner can view usage
|
|
currentKey := middleware.GetAPIKey(c)
|
|
if !currentKey.IsAdmin && currentKey.ID != keyID {
|
|
c.JSON(http.StatusForbidden, gin.H{"error": "access denied"})
|
|
return
|
|
}
|
|
|
|
period := c.DefaultQuery("period", "month")
|
|
now := time.Now().UTC()
|
|
|
|
var periodStart, periodEnd time.Time
|
|
switch period {
|
|
case "month":
|
|
periodStart = time.Date(now.Year(), now.Month(), 1, 0, 0, 0, 0, time.UTC)
|
|
periodEnd = periodStart.AddDate(0, 1, 0)
|
|
case "year":
|
|
periodStart = time.Date(now.Year(), 1, 1, 0, 0, 0, 0, time.UTC)
|
|
periodEnd = periodStart.AddDate(1, 0, 0)
|
|
default:
|
|
periodStart = now.AddDate(0, 0, -7)
|
|
periodEnd = now
|
|
}
|
|
|
|
// Get usage logs
|
|
var logs []db.UsageLog
|
|
h.db.Where("api_key_id = ? AND created_at >= ? AND created_at < ?", keyID, periodStart, periodEnd).
|
|
Order("created_at DESC").Limit(100).Find(&logs)
|
|
|
|
// Get aggregated stats
|
|
var stats struct {
|
|
TotalRequests int64
|
|
TotalTokens int64
|
|
AvgLatency float64
|
|
}
|
|
h.db.Model(&db.UsageLog{}).
|
|
Where("api_key_id = ? AND created_at >= ? AND created_at < ?", keyID, periodStart, periodEnd).
|
|
Select("COUNT(*) as total_requests, COALESCE(SUM(total_tokens), 0) as total_tokens, COALESCE(AVG(latency_ms), 0) as avg_latency").
|
|
Scan(&stats)
|
|
|
|
// Get quota info
|
|
used, limit, _ := h.quotaSvc.GetUsage(keyID, periodStart, periodEnd)
|
|
|
|
c.JSON(http.StatusOK, gin.H{
|
|
"period": gin.H{
|
|
"start": periodStart,
|
|
"end": periodEnd,
|
|
},
|
|
"usage": gin.H{
|
|
"total_requests": stats.TotalRequests,
|
|
"total_tokens": stats.TotalTokens,
|
|
"avg_latency_ms": stats.AvgLatency,
|
|
},
|
|
"quota": gin.H{
|
|
"tokens_used": used,
|
|
"tokens_limit": limit,
|
|
},
|
|
"logs": logs,
|
|
})
|
|
}
|
|
|
|
func (h *UsageHandler) GetCurrentKeyUsage(c *gin.Context) {
|
|
key := middleware.GetAPIKey(c)
|
|
now := time.Now().UTC()
|
|
periodStart := time.Date(now.Year(), now.Month(), 1, 0, 0, 0, 0, time.UTC)
|
|
periodEnd := periodStart.AddDate(0, 1, 0)
|
|
|
|
var stats struct {
|
|
TotalRequests int64
|
|
TotalTokens int64
|
|
AvgLatency float64
|
|
}
|
|
h.db.Model(&db.UsageLog{}).
|
|
Where("api_key_id = ? AND created_at >= ? AND created_at < ?", key.ID, periodStart, periodEnd).
|
|
Select("COUNT(*) as total_requests, COALESCE(SUM(total_tokens), 0) as total_tokens, COALESCE(AVG(latency_ms), 0) as avg_latency").
|
|
Scan(&stats)
|
|
|
|
used, limit, _ := h.quotaSvc.GetUsage(key.ID, periodStart, periodEnd)
|
|
|
|
c.JSON(http.StatusOK, gin.H{
|
|
"period": gin.H{
|
|
"start": periodStart,
|
|
"end": periodEnd,
|
|
},
|
|
"usage": gin.H{
|
|
"total_requests": stats.TotalRequests,
|
|
"total_tokens": stats.TotalTokens,
|
|
"avg_latency_ms": stats.AvgLatency,
|
|
},
|
|
"quota": gin.H{
|
|
"tokens_used": used,
|
|
"tokens_limit": limit,
|
|
},
|
|
})
|
|
}
|