v1alpha1

type BackendConfig struct {
	// Name represents the inference backend under the hood, e.g. vLLM.
	// +kubebuilder:validation:Enum={vllm,sglang,llamacpp}
	// +kubebuilder:default=vllm
	// +optional
	Name *BackendName `json:"name,omitempty"`
	// Version represents the backend version if you want a different one
	// from the default version.
	// +optional
	Version *string `json:"version,omitempty"`
	// Args represents the arguments passed to the backend.
	// +optional
	Args []string `json:"args,omitempty"`
	// Envs represents the environments set to the container.
	// +optional
	Envs []corev1.EnvVar `json:"envs,omitempty"`
	// Resources represents the resource requirements for backend, like cpu/mem,
	// accelerators like GPU should not be defined here, but at the Model flavors,
	// or the same accelerator requirements defined there will be covered and
	// the workload will lose the fungibility capacity.
	Resources *ResourceRequirements `json:"resources,omitempty"`
}

type BackendName string

type ElasticConfig struct {
	// MinReplicas indicates the minimum number of inference workloads based on the traffic.
	// Default to nil means we can scale down the instances to 1.
	// If minReplicas set to 0, it requires to install serverless component at first.
	// +kubebuilder:default=1
	// +optional
	MinReplicas *int32 `json:"minReplicas,omitempty"`
	// MaxReplicas indicates the maximum number of inference workloads based on the traffic.
	// Default to nil means there's no limit for the instance number.
	// +optional
	MaxReplicas *int32 `json:"maxReplicas,omitempty"`
}

type Playground struct {
	metav1.TypeMeta   `json:",inline"`
	metav1.ObjectMeta `json:"metadata,omitempty"`

	Spec   PlaygroundSpec   `json:"spec,omitempty"`
	Status PlaygroundStatus `json:"status,omitempty"`
}

type PlaygroundList struct {
	metav1.TypeMeta `json:",inline"`
	metav1.ListMeta `json:"metadata,omitempty"`
	Items           []Playground `json:"items"`
}

type PlaygroundSpec struct {
	// Replicas represents the replica number of inference workloads.
	// +kubebuilder:default=1
	// +optional
	Replicas *int32 `json:"replicas,omitempty"`
	// ModelClaim represents one modelClaim, it's a simple configuration
	// compared to multiModelsClaims only work for one model and one claim.
	// ModelClaim and multiModelsClaims are exclusive configured.
	// Note: properties (nodeSelectors, resources, e.g.) of the model flavors
	// will be applied to the workload if not exist.
	// +optional
	ModelClaim *coreapi.ModelClaim `json:"modelClaim,omitempty"`
	// MultiModelsClaims represents multiple modelClaim, which is useful when different
	// sub-workload has different accelerator requirements, like the state-of-the-art
	// technology called splitwise, the workload template is shared by both.
	// ModelClaim and multiModelsClaims are exclusive configured.
	// +optional
	MultiModelsClaims []coreapi.MultiModelsClaim `json:"multiModelsClaims,omitempty"`
	// BackendConfig represents the inference backend configuration
	// under the hood, e.g. vLLM, which is the default backend.
	// +optional
	BackendConfig *BackendConfig `json:"backendConfig,omitempty"`
}

type PlaygroundStatus struct {
	// Conditions represents the Inference condition.
	Conditions []metav1.Condition `json:"conditions,omitempty"`
}

type ResourceRequirements struct {
	// Limits describes the maximum amount of compute resources allowed.
	// More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/
	// +optional
	Limits corev1.ResourceList `json:"limits,omitempty"`
	// Requests describes the minimum amount of compute resources required.
	// If Requests is omitted for a container, it defaults to Limits if that is explicitly specified,
	// otherwise to an implementation-defined value. Requests cannot exceed Limits.
	// More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/
	// +optional
	Requests corev1.ResourceList `json:"requests,omitempty"`
}

type Service struct {
	metav1.TypeMeta   `json:",inline"`
	metav1.ObjectMeta `json:"metadata,omitempty"`

	Spec   ServiceSpec   `json:"spec,omitempty"`
	Status ServiceStatus `json:"status,omitempty"`
}

type ServiceList struct {
	metav1.TypeMeta `json:",inline"`
	metav1.ListMeta `json:"metadata,omitempty"`
	Items           []Service `json:"items"`
}

type ServiceSpec struct {
	// MultiModelsClaims represents multiple modelClaim, which is useful when different
	// sub-workload has different accelerator requirements, like the state-of-the-art
	// technology called splitwise, the workload template is shared by both.
	// Most of the time, one modelClaim is enough.
	// Note: properties (nodeSelectors, resources, e.g.) of the model flavors
	// will be applied to the workload if not exist.
	// +kubebuilder:validation:MinItems=1
	MultiModelsClaims []coreapi.MultiModelsClaim `json:"multiModelsClaims,omitempty"`
	// WorkloadTemplate defines the underlying workload layout and configuration.
	// Note: the LWS spec might be twisted with various LWS instances to support
	// accelerator fungibility or other cutting-edge researches.
	// LWS supports both single-host and multi-host scenarios, for single host
	// cases, only need to care about replicas, rolloutStrategy and workerTemplate.
	WorkloadTemplate lws.LeaderWorkerSetSpec `json:"workloadTemplate"`
	// ElasticConfig defines the configuration for elastic usage,
	// e.g. the max/min replicas. Default to 0 ~ Inf+.
	// This requires to install the HPA first or will not work.
	// +optional
	ElasticConfig *ElasticConfig `json:"elasticConfig,omitempty"`
}

type ServiceStatus struct {
	// Conditions represents the Inference condition.
	Conditions []metav1.Condition `json:"conditions,omitempty"`
}