bailian-cli-core 2.0.0 → 2.0.1

package/dist/index.d.mts

@@ -1900,6 +1900,7 @@ export declare function speechVocabularyPath(): string;
 export declare function profileSchemaPath(): string;
 export declare function userProfilePath(schemaId: string): string;
 export declare function knowledgeRetrievePath(): string;
+export declare function workspaceMaaSBaseUrl(workspaceId: string): string;
 export declare function knowledgeSearchEndpoint(workspaceId: string): string;
 export declare function knowledgeChatEndpoint(workspaceId: string): string;
 /** Per-workspace AgentStudio host (same shape as {@link ragEndpoint}'s host). */
@@ -1909,6 +1910,18 @@ export declare function securityOverviewEndpoint(host: string): string;
 /** GET alert list (agent_logs); filters / pagination go in the query string. */
 export declare function securityAgentLogsEndpoint(host: string): string;
 export declare function mcpWebSearchPath(): string;
+/** GET /api/v1/deployments/{deployed_model}/capacity-instances */
+export declare function deploymentCapacityInstancesPath(code: string): string;
+/** GET /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id} */
+export declare function deploymentCapacityInstancePath(code: string, id: string): string;
+/** PUT /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}/scale */
+export declare function deploymentCapacityInstanceScalePath(code: string, id: string): string;
+/** PUT /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}/renew */
+export declare function deploymentCapacityInstanceRenewPath(code: string, id: string): string;
+/** PUT /api/v1/deployments/{deployed_model}/update-overflowstrategy */
+export declare function deploymentOverflowPath(code: string): string;
+/** GET /api/v1/deployments/{deployed_model}/capacity-operations/{operation_id} */
+export declare function deploymentCapacityOperationPath(code: string, id: string): string;
 export declare function ragEndpoint(workspaceId: string, path: string): string;
 /** AgentStudio workspace files; template uploads send source=sandbox_template. */
 export declare function agentStudioFilesPath(): string;
@@ -3237,6 +3250,18 @@ export interface Deployment {
   /** PTU-only token-rate limits. */
   input_tpm?: number;
   output_tpm?: number;
+  /** Aggregate effective reservation capacity, in kTPM. */
+  ptu_capacity?: ReservationCapacity;
+  /** ptu_fast | ptu_default | future service tiers. */
+  ptu_service_tier?: string;
+  pre_paid_info?: PrePaidInfo;
+  pre_paid_instance_id?: string;
+  pre_paid_gmt_expired?: string;
+  /** enable | disable | future overflow strategies. */
+  overflow_strategy?: string;
+  fail_reason?: string;
+  operation_id?: string;
+  instance_id?: string;
   enable_thinking?: boolean;
   max_context_length?: number;
   workspace_id?: string;
@@ -3247,6 +3272,71 @@ export interface Deployment {
   /** Free-form additional fields are preserved by callers. */
   [k: string]: unknown;
 }
+/** Reservation capacity returned by queries; separate from legacy PTU write input. */
+export interface ReservationCapacity {
+  /** Input capacity in kTPM (1 kTPM = 1000 tokens/minute); zero is valid. */
+  input_tpm?: number;
+  /** Output capacity in kTPM; zero is valid. */
+  output_tpm?: number;
+  [key: string]: unknown;
+}
+/** Prepaid purchase and renewal configuration returned by queries. */
+export interface PrePaidInfo {
+  /** Purchase / renewal duration in days. */
+  duration?: number;
+  auto_renewal?: boolean;
+  /** Automatic renewal duration in days. */
+  auto_renewal_duration?: number;
+  /** Renewal cycle unit, e.g. Day. */
+  auto_renewal_cycle?: string;
+  [key: string]: unknown;
+}
+/** A capacity instance returned by list/detail queries, including released instances. */
+export interface CapacityInstance {
+  /** The deployment's ModelCode. Identifiers are opaque strings. */
+  model_service_id?: string;
+  instance_id?: string;
+  /** pre_paid | post_paid | future charge types. */
+  charge_type?: string;
+  /** Instance lifecycle state; future states are preserved. */
+  status?: string;
+  deleted?: boolean;
+  /** Currently confirmed serving capacity. */
+  effective_capacity?: ReservationCapacity;
+  /** Configured / contracted capacity, which may remain while stopped or suspended. */
+  configured_capacity?: ReservationCapacity;
+  /** Pending target, not effective capacity; may be absent or null in a stable state. */
+  target_capacity?: ReservationCapacity | null;
+  pre_paid_info?: PrePaidInfo;
+  gmt_expired?: string;
+  can_scale?: boolean;
+  can_renew?: boolean;
+  can_delete?: boolean;
+  fail_reason?: string;
+  gmt_created?: string;
+  gmt_modified?: string;
+  gmt_deleted?: string;
+  [key: string]: unknown;
+}
+/** A capacity operation returned by a query; no state or identifier normalization. */
+export interface CapacityOperation {
+  operation_id?: string;
+  /** Original operation request ID, distinct from the query response's request_id. */
+  request_id?: string;
+  /** CREATE | SCALE | RENEW | DELETE | STOP | REFUND | future operation types. */
+  operation_type?: string;
+  /** PROCESSING | SUCCEEDED | FAILED | future operation states. */
+  operation_status?: string;
+  model_service_id?: string;
+  instance_id?: string;
+  from_status?: string;
+  current_status?: string;
+  error_code?: string;
+  error_message?: string;
+  gmt_created?: string;
+  gmt_finished?: string;
+  [key: string]: unknown;
+}
 /** A single deployable model record (GET /deployments/models). */
 export interface DeployableModel {
   model_name?: string;
@@ -3314,20 +3404,23 @@ export interface DeployableTemplate {
 export interface CreateDeploymentRequest {
   /** Required. The catalog or fine-tuned model identifier. */
   model_name: string;
-  /** Required. Display name shown in the console. */
-  name: string;
+  /** Optional display name; PTU creation generates one when omitted. */
+  name?: string;
   /** Required. Billing plan: mu | cu | ptu | lora. CLI defaults to "lora". */
   plan: string;
+  /** Required for PTU creation; distinct from instance billing_method. */
+  charge_type?: "pre_paid" | "post_paid";
+  /** PTU performance tier; the service defaults to ptu_fast. */
+  service_tier?: "ptu_fast" | "ptu_default";
+  /** Optional ModelCode suffix; generated by the service when omitted. */
+  suffix?: string;
+  /** Required for prepaid PTU creation; omitted for postpaid. */
+  pre_paid_info?: PrePaidInfo;
   /** Required by API even for token-billed (lora) plans where it is ignored — CLI injects 1. */
   capacity?: number;
   /** Deploy spec id (e.g. "MU1", "dps-..."), sent as `deploy_spec` in POST body. */
   deploy_spec?: string;
-  /**
-   * PTU capacity (provisioned throughput limits). Only effective when
-   * `plan === "ptu"`. The doc says this defaults to 10000/1000 when omitted,
-   * but the platform currently rejects creation without it ("Miss ptu capacity
-   * info"), so the CLI treats it as required for ptu.
-   */
+  /** Required PTU capacity in kTPM; values are forwarded without conversion. */
   ptu_capacity?: PtuCapacity;
   /**
    * AIGC generation config for fine-tuned Wan video (i2v/kf2v) LoRA deployments.
@@ -3350,13 +3443,13 @@ export interface AigcConfig {
   prompt?: string;
   lora_prompt_default?: string;
 }
-/** PTU throughput limits — only used when `plan === "ptu"`. */
+/** Legacy PTU input shape, retained for source compatibility. */
 export interface PtuCapacity {
-  /** Max input tokens per minute (all models). */
+  /** Input capacity in kTPM. */
   input_tpm?: number;
-  /** Max output tokens per minute (all models). */
+  /** Output capacity in kTPM. */
   output_tpm?: number;
-  /** Max thinking-output tokens per minute (some models only). */
+  /** @deprecated Current reservation models do not support separate thinking-output capacity. */
   thinking_output_tpm?: number;
 }
 /** POST /api/v1/deployments response. */
@@ -3389,18 +3482,69 @@ export interface GetDeploymentResponse {
   output?: Deployment;
   data?: Deployment;
 }
-/** DELETE /api/v1/deployments/{deployed_model} response. */
-export interface DeleteDeploymentResponse {
+/** GET /api/v1/deployments/{deployed_model}/capacity-instances response. */
+export interface ListCapacityInstancesResponse {
   request_id?: string;
   output?: {
+    records?: CapacityInstance[];
+    /** Total record count, not the current page's records. */
+    items?: number;
+    page?: number;
+    itemsPerPage?: number;
+    pageCount?: number;
+    [key: string]: unknown;
+  };
+  data?: ListCapacityInstancesResponse["output"];
+  [key: string]: unknown;
+}
+/** GET /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id} response. */
+export interface GetCapacityInstanceResponse {
+  request_id?: string;
+  output?: CapacityInstance;
+  data?: CapacityInstance;
+  [key: string]: unknown;
+}
+/** GET /api/v1/deployments/{deployed_model}/capacity-operations/{operation_id} response. */
+export interface GetCapacityOperationResponse {
+  request_id?: string;
+  output?: CapacityOperation;
+  data?: CapacityOperation;
+  [key: string]: unknown;
+}
+/** Instance writes return an operation, including HTTP 200 responses with status FAILED. */
+export type CapacityOperationResponse = GetCapacityOperationResponse;
+/** POST /api/v1/deployments/{deployed_model}/capacity-instances request body. */
+export interface CreateCapacityInstanceRequest {
+  billing_method: "PRE_PAY" | "POST_PAY";
+  ptu_capacity: ReservationCapacity;
+  /** Required for PRE_PAY; omitted for POST_PAY. */
+  pre_paid_info?: PrePaidInfo;
+}
+/** PUT /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}/scale body. */
+export interface ScaleCapacityInstanceRequest {
+  /** Absolute target capacity for this instance, not a delta or deployment total. */
+  ptu_capacity: ReservationCapacity;
+  /** Omit to reuse saved prepaid information; do not send for postpaid. */
+  pre_paid_info?: PrePaidInfo;
+  order_type?: "UPGRADE" | "DOWNGRADE";
+}
+/** PUT /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}/renew body. */
+export interface RenewCapacityInstanceRequest {
+  pre_paid_info: PrePaidInfo;
+  /** Required to be true when changing capacity; defaults to false on the service. */
+  is_change?: boolean;
+  ptu_capacity?: ReservationCapacity;
+}
+/** PUT /api/v1/deployments/{deployed_model}/update-overflowstrategy response. */
+export type UpdateDeploymentOverflowResponse = GetDeploymentResponse;
+/** DELETE /api/v1/deployments/{deployed_model} response, including legacy deleted flags. */
+export interface DeleteDeploymentResponse {
+  request_id?: string;
+  output?: Deployment & {
     deleted?: boolean;
-    deployed_model?: string;
-    [k: string]: unknown;
   };
-  data?: {
+  data?: Deployment & {
     deleted?: boolean;
-    deployed_model?: string;
-    [k: string]: unknown;
   };
 }
 /** GET /api/v1/deployments/models response. */
@@ -3423,9 +3567,15 @@ export interface ListDeployableModelsResponse {
 }
 /** PUT /api/v1/deployments/{deployed_model}/scale request body. */
 export interface ScaleDeploymentRequest {
-  /** New capacity in plan units. Server-side constraint: integer multiple of `base_capacity`, < 1000. */
+  /** New capacity in legacy MU plan units. */
   capacity?: number;
-  /** PTU-only token-rate adjustments. */
+  /** Required for PTU when more than one undeleted instance exists. */
+  instance_id?: string;
+  /** Absolute PTU target capacity for the selected instance, in kTPM. */
+  ptu_capacity?: ReservationCapacity;
+  pre_paid_info?: PrePaidInfo;
+  order_type?: "UPGRADE" | "DOWNGRADE";
+  /** Legacy top-level PTU fields retained for source compatibility. */
   input_tpm?: number;
   output_tpm?: number;
   [k: string]: unknown;
@@ -3456,18 +3606,52 @@ export interface UpdateDeploymentResponse {
 }
 //#endregion
 //#region src/deploy/api.d.ts
-/** POST /api/v1/deployments */
+/** Caller-owned idempotency key; wrappers never generate keys or retry writes. */
+export interface CapacityWriteOptions {
+  requestId?: string;
+  signal?: AbortSignal;
+}
+/** POST /api/v1/deployments; initial ModelCode creation has no instance-idempotency guarantee. */
 export declare function createDeployment(client: Client, body: CreateDeploymentRequest, signal?: AbortSignal): Promise<CreateDeploymentResponse>;
 export interface ListDeploymentsParams {
   pageNo?: number;
   pageSize?: number;
-  status?: string;
+  plan?: string;
   signal?: AbortSignal;
 }
 /** GET /api/v1/deployments */
 export declare function listDeployments(client: Client, params?: ListDeploymentsParams): Promise<ListDeploymentsResponse>;
 /** GET /api/v1/deployments/{deployed_model} */
 export declare function getDeployment(client: Client, deployedModel: string, signal?: AbortSignal): Promise<GetDeploymentResponse>;
+export interface ListCapacityInstancesParams {
+  pageNo?: number;
+  pageSize?: number;
+  includeDeleted?: boolean;
+  statuses?: string[];
+  chargeTypes?: string[];
+  signal?: AbortSignal;
+}
+/** GET /api/v1/deployments/{deployed_model}/capacity-instances */
+export declare function listCapacityInstances(client: Client, code: string, params?: ListCapacityInstancesParams): Promise<ListCapacityInstancesResponse>;
+/** GET /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id} */
+export declare function getCapacityInstance(client: Client, code: string, id: string, signal?: AbortSignal): Promise<GetCapacityInstanceResponse>;
+/** GET /api/v1/deployments/{deployed_model}/capacity-operations/{operation_id} */
+export declare function getCapacityOperation(client: Client, code: string, id: string, signal?: AbortSignal): Promise<GetCapacityOperationResponse>;
+/**
+ * POST /api/v1/deployments/{deployed_model}/capacity-instances
+ * All instance writes return operations verbatim; callers must check operation_status, even on HTTP 200.
+ */
+export declare function createCapacityInstance(client: Client, code: string, body: CreateCapacityInstanceRequest, options?: CapacityWriteOptions): Promise<CapacityOperationResponse>;
+/** PUT /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}/scale */
+export declare function scaleCapacityInstance(client: Client, code: string, id: string, body: ScaleCapacityInstanceRequest, options?: CapacityWriteOptions): Promise<CapacityOperationResponse>;
+/** PUT /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}/renew */
+export declare function renewCapacityInstance(client: Client, code: string, id: string, body: RenewCapacityInstanceRequest, options?: CapacityWriteOptions): Promise<CapacityOperationResponse>;
+/** DELETE /api/v1/deployments/{deployed_model}/capacity-instances/{instance_id}; no JSON body. */
+export declare function deleteCapacityInstance(client: Client, code: string, id: string, options?: CapacityWriteOptions & {
+  reason?: string;
+}): Promise<CapacityOperationResponse>;
+/** PUT /api/v1/deployments/{deployed_model}/update-overflowstrategy */
+export declare function updateDeploymentOverflow(client: Client, code: string, strategy: "enable" | "disable", signal?: AbortSignal): Promise<UpdateDeploymentOverflowResponse>;
 /** DELETE /api/v1/deployments/{deployed_model} */
 export declare function deleteDeployment(client: Client, deployedModel: string, signal?: AbortSignal): Promise<DeleteDeploymentResponse>;
 export interface ListDeployableModelsParams {
@@ -3482,7 +3666,7 @@ export interface ListDeployableModelsParams {
 /** GET /api/v1/deployments/models */
 export declare function listDeployableModels(client: Client, params?: ListDeployableModelsParams): Promise<ListDeployableModelsResponse>;
 /** PUT /api/v1/deployments/{deployed_model}/scale */
-export declare function scaleDeployment(client: Client, deployedModel: string, body: ScaleDeploymentRequest, signal?: AbortSignal): Promise<ScaleDeploymentResponse>;
+export declare function scaleDeployment(client: Client, deployedModel: string, body: ScaleDeploymentRequest, signal?: AbortSignal, requestId?: string): Promise<ScaleDeploymentResponse>;
 /**
  * PUT /api/v1/deployments/{deployed_model}/update
  *
@@ -3538,15 +3722,36 @@ export declare const CHARGE_TYPE: {
 };
 export type ChargeType = (typeof CHARGE_TYPE)[keyof typeof CHARGE_TYPE];
 //#endregion
+//#region src/deploy/reservation.d.ts
+/** Shared flags for reservation creation, scaling and renewal; capacity is in kTPM. */
+export interface ReservationFlags {
+  inputTpm?: number;
+  outputTpm?: number;
+  duration?: number;
+  autoRenewal?: boolean;
+  autoRenewalDuration?: number;
+  autoRenewalCycle?: string;
+}
+/** Validate paired capacity locally; model-specific steps and limits belong to the service. */
+export declare function validateReservationCapacity(flags: ReservationFlags, required: boolean): string | undefined;
+/** Build validated capacity without converting units or dropping zero. */
+export declare function buildReservationCapacity(flags: ReservationFlags): ReservationCapacity;
+export declare function hasPrepaidFlags(flags: ReservationFlags): boolean;
+/** Validate a complete prepaid block whenever any prepaid field is supplied. */
+export declare function validatePrepaidFlags(flags: ReservationFlags, required: boolean): string | undefined;
+/** Build validated prepaid information, preserving explicit false and omitting absent fields. */
+export declare function buildPrepaidInfo(flags: ReservationFlags): PrePaidInfo | undefined;
+//#endregion
 //#region src/deploy/plans.d.ts
 /** Plan-relevant subset of `deploy <modality> create` flags (parsed flags satisfy this shape). */
-export interface CreatePlanFlags {
+export interface CreatePlanFlags extends ReservationFlags {
   plan?: string;
   deploySpec?: string;
   capacity?: number;
   billingMethod?: string;
-  inputTpm?: number;
-  outputTpm?: number;
+  chargeType?: string;
+  serviceTier?: string;
+  suffix?: string;
   thinkingOutputTpm?: number;
 }
 export interface PlanContext {
@@ -3558,8 +3763,8 @@ export interface PlanContext {
   flags: CreatePlanFlags;
   /** Underlying model identifier (`--model`). */
   model: string;
-  /** Console display name (`--name`). */
-  name: string;
+  /** Optional console display name (`--name`); PTU can use the generated name. */
+  name?: string;
 }
 export interface PlanResolved {
   /**