Initial commit: LlamaLink Go rewrite

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.)

internal/api/handlers/usage.go

@@ -0,0 +1,126 @@
+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,
+		},
+	})
+}