refactor: 后端代码质量优化 - 复用公共库、使用标准库、类型安全错误判断

## 高优先级修复
- stats_service_impl: 使用 strings.SplitN 替代错误的索引分割
- provider_handler: 使用 errors.Is(err, gorm.ErrDuplicatedKey) 替代字符串匹配
- client: 重写 isNetworkError 使用 errors.As/Is 类型安全判断
- proxy_handler: 使用 encoding/json 标准库解析 JSON（extractModelName、isStreamRequest）

## 中优先级修复
- stats_handler: 添加 parseDateParam 辅助函数消除重复日期解析
- pkg/errors: 新增 ErrRequestCreate/Send/ResponseRead 错误类型和 WithCause 方法
- client: 使用结构化错误替代 fmt.Errorf
- ConversionEngine: logger 依赖注入，替换所有 zap.L() 调用

## 低优先级修复
- encoder: 删除 joinStrings，使用 strings.Join
- adapter: 删除 modelInfoRegex 正则，使用 isModelInfoPath 字符串函数

## 文档更新
- README.md: 添加公共库使用指南和编码规范章节
- specs: 同步 delta specs 到 main specs（error-handling、structured-logging、request-validation）

## 归档
- openspec/changes/archive/2026-04-20-refactor-backend-code-quality/

backend/internal/service/service_supplemental_test.go

@@ -104,26 +104,6 @@ func TestModelService_Delete_NotFound(t *testing.T) {
 	assert.Error(t, err)
 }
 
-func TestStatsService_Aggregate_ByModel(t *testing.T) {
-	statsRepo := repository.NewStatsRepository(nil)
-	svc := NewStatsService(statsRepo)
-
-	stats := []domain.UsageStats{
-		{ProviderID: "p1", ModelName: "gpt-4", RequestCount: 10},
-		{ProviderID: "p1", ModelName: "gpt-4", RequestCount: 5},
-		{ProviderID: "p2", ModelName: "gpt-4", RequestCount: 8},
-	}
-
-	result := svc.Aggregate(stats, "model")
-	assert.True(t, len(result) >= 1)
-
-	totalCount := 0
-	for _, r := range result {
-		totalCount += r["request_count"].(int)
-	}
-	assert.Equal(t, 23, totalCount)
-}
-
 func TestStatsService_Aggregate_Default(t *testing.T) {
 	statsRepo := repository.NewStatsRepository(nil)
 	svc := NewStatsService(statsRepo)

backend/internal/service/service_test.go

@@ -243,3 +243,28 @@ func TestStatsService_Aggregate_ByDate(t *testing.T) {
 	assert.Len(t, result, 1)
 	assert.Equal(t, 15, result[0]["request_count"])
 }
+
+func TestStatsService_Aggregate_ByModel(t *testing.T) {
+	statsRepo := repository.NewStatsRepository(nil)
+	svc := NewStatsService(statsRepo)
+
+	stats := []domain.UsageStats{
+		{ProviderID: "openai", ModelName: "gpt-4", RequestCount: 10},
+		{ProviderID: "openai", ModelName: "gpt-3.5", RequestCount: 5},
+		{ProviderID: "anthropic", ModelName: "claude-3", RequestCount: 8},
+		{ProviderID: "openai", ModelName: "gpt-4", RequestCount: 3},
+	}
+
+	result := svc.Aggregate(stats, "model")
+	assert.Len(t, result, 3)
+
+	// 验证每个 provider/model 组合的计数
+	counts := make(map[string]int)
+	for _, r := range result {
+		key := r["provider_id"].(string) + "/" + r["model_name"].(string)
+		counts[key] = r["request_count"].(int)
+	}
+	assert.Equal(t, 13, counts["openai/gpt-4"])
+	assert.Equal(t, 5, counts["openai/gpt-3.5"])
+	assert.Equal(t, 8, counts["anthropic/claude-3"])
+}

backend/internal/service/stats_service_impl.go

@@ -1,6 +1,7 @@
 package service
 
 import (
+	"strings"
 	"time"
 
 	"nex/backend/internal/domain"
@@ -59,9 +60,10 @@ func (s *statsService) aggregateByModel(stats []domain.UsageStats) []map[string]
 	}
 	result := make([]map[string]interface{}, 0, len(aggregated))
 	for key, count := range aggregated {
+		parts := strings.SplitN(key, "/", 2)
 		result = append(result, map[string]interface{}{
-			"provider_id":   key[:len(key)/2],
-			"model_name":    key[len(key)/2+1:],
+			"provider_id":   parts[0],
+			"model_name":    parts[1],
 			"request_count": count,
 		})
 	}