fix: scale replicas in response, K8s metrics client, quota precheck, auth tests

- Add GetMetrics method to MetricsClient interface and implement cluster metrics API
- Add QuotaPrecheck service for validating resource quotas before deployment
- Add auth DTO with role/permission models and auth handler tests
- Add instance diagnostics: mounted NFS volumes, labels, annotations in pod diagnostics
- Update workspace handler with GetWorkspace endpoint and shared-user list
- Fix monitoring handler to use correct service method name
- Add tail_lines fallback in instance handler for snake_case query params
- Update nginx config for SSE log streaming support (no buffering)
- Add comprehensive test coverage: auth_service_test, auth_handler_test,
  auth_dto_test, metrics_client_test, quota_precheck_test
- Update error messages for quota validation and instance operations
- ModifyModal: fix YAML lineWidth:0, modified keys summary, delta-only submit
- InstanceCard: correctly disable scale-minus when replicas <= 0
- SidebarLayout: add hover transition for sidebar items
- Update todo.md and lessons.md with latest fixes

backend/internal/domain/entity/metrics.go

@@ -25,6 +25,18 @@ type ClusterMetrics struct {
 	MemoryUsage float64 `json:"memory_usage"` // 百分比
 	GPUUsage    float64 `json:"gpu_usage"`    // 百分比
 
+	CPURequests          string              `json:"cpu_requests,omitempty"`
+	CPULimits            string              `json:"cpu_limits,omitempty"`
+	MemoryRequests       string              `json:"memory_requests,omitempty"`
+	MemoryLimits         string              `json:"memory_limits,omitempty"`
+	GPURequests          int64               `json:"gpu_requests,omitempty"`
+	GPULimits            int64               `json:"gpu_limits,omitempty"`
+	GPUMemoryRequestsMB  int64               `json:"gpu_memory_requests_mb,omitempty"`
+	GPUMemoryLimitsMB    int64               `json:"gpu_memory_limits_mb,omitempty"`
+	AllocatedGPU         int64               `json:"allocated_gpu,omitempty"`
+	AllocatedGPUMemoryMB int64               `json:"allocated_gpu_memory_mb,omitempty"`
+	ResourceUsageByUser  []UserResourceUsage `json:"resource_usage_by_user,omitempty"`
+
 	// 单机资源最大值
 	MaxNodeCPU      string  `json:"max_node_cpu"`       // 单机最大CPU容量，如 "8 cores"
 	MaxNodeMemory   string  `json:"max_node_memory"`    // 单机最大内存容量，如 "32 GB"
@@ -37,6 +49,42 @@ type ClusterMetrics struct {
 	Nodes []NodeMetrics `json:"nodes,omitempty"`
 }
 
+// ResourceAllocation is derived from Kubernetes Pod resources requests/limits.
+type ResourceAllocation struct {
+	CPURequestsMilli    int64
+	CPULimitsMilli      int64
+	MemoryRequestsBytes int64
+	MemoryLimitsBytes   int64
+	GPURequests         int64
+	GPULimits           int64
+	GPUMemoryRequestsMB int64
+	GPUMemoryLimitsMB   int64
+}
+
+type PodResourceAllocation struct {
+	ClusterID    string
+	Namespace    string
+	PodName      string
+	InstanceName string
+	Allocation   ResourceAllocation
+}
+
+type UserResourceUsage struct {
+	UserID              string `json:"user_id"`
+	Username            string `json:"username"`
+	WorkspaceID         string `json:"workspace_id"`
+	InstanceCount       int    `json:"instance_count"`
+	PodCount            int    `json:"pod_count"`
+	CPURequests         string `json:"cpu_requests"`
+	CPULimits           string `json:"cpu_limits"`
+	MemoryRequests      string `json:"memory_requests"`
+	MemoryLimits        string `json:"memory_limits"`
+	GPURequests         int64  `json:"gpu_requests"`
+	GPULimits           int64  `json:"gpu_limits"`
+	GPUMemoryRequestsMB int64  `json:"gpu_memory_requests_mb"`
+	GPUMemoryLimitsMB   int64  `json:"gpu_memory_limits_mb"`
+}
+
 // NodeMetrics 节点监控指标
 type NodeMetrics struct {
 	NodeName string `json:"node_name"`