feat(server): API relay gateway backend M0-M4

Gin + GORM + pure-Go SQLite. Users/auth (JWT), API key management with
quotas, proxy gateway with weighted channel failover and health checks,
usage/billing ledger, cross-protocol conversion (Anthropic Messages /
OpenAI Chat Completions / OpenAI Responses), and channel/model admin API.
Channels declare native API formats and auto-convert the rest.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

server/internal/proxy/models.go

@@ -0,0 +1,34 @@
+package proxy
+
+import (
+	"github.com/gin-gonic/gin"
+	"gorm.io/gorm"
+)
+
+// ModelsHandler serves GET /v1/models (OpenAI-style list).
+type ModelsHandler struct {
+	db  *gorm.DB
+	gw  *Gateway
+}
+
+func NewModelsHandler(db *gorm.DB, gw *Gateway) *ModelsHandler {
+	return &ModelsHandler{db: db, gw: gw}
+}
+
+func (h *ModelsHandler) List(c *gin.Context) {
+	models, err := h.gw.channel.ListEnabledModels()
+	if err != nil {
+		c.JSON(502, gin.H{"error": gin.H{"message": "list models failed", "type": "api_error"}})
+		return
+	}
+	data := make([]gin.H, 0, len(models))
+	for _, m := range models {
+		data = append(data, gin.H{
+			"id":       m.Name,
+			"object":   "model",
+			"created":  m.CreatedAt.Unix(),
+			"owned_by": "openteam",
+		})
+	}
+	c.JSON(200, gin.H{"object": "list", "data": data})
+}