@gpuai/sdk 0.3.0 → 0.3.2

package/README.md

@@ -1,4 +1,4 @@
-# @gpuai/sdk@0.3.0
+# @gpuai/sdk@0.3.2
 
 A TypeScript SDK client for the api.gpu.ai API.
 
@@ -196,7 +196,7 @@ and is automatically generated by the
 [OpenAPI Generator](https://openapi-generator.tech) project:
 
 - API version: `1.0.0`
-- Package version: `0.3.0`
+- Package version: `0.3.2`
 - Generator version: `7.24.0`
 - Build package: `org.openapitools.codegen.languages.TypeScriptFetchClientCodegen`
 

package/dist/esm/models/CreateInstanceRequest.d.ts

@@ -57,6 +57,12 @@ export interface CreateInstanceRequest {
      * @memberof CreateInstanceRequest
      */
     maxPricePerHour?: number;
+    /**
+     * The retail $/hr the caller displayed to the user before launch. A catalog row is a quote, not a booking, and pinning an offering fixes which machine is placed but not its rate. If the launch-time price exceeds this by more than $0.01 the launch fails with `price_changed` carrying the new price instead of proceeding at the higher price; omit to accept the launch-time price (previous behavior). Refusal only — it is never read as consent, so it can neither raise what you are charged nor widen what may be bought on your behalf. Use max_price_per_hour to bound spend.
+     * @type {number}
+     * @memberof CreateInstanceRequest
+     */
+    viewedPricePerHour?: number;
     /**
      * Deploy a curated application template (e.g. comfyui, vllm). When set, gpu_type may be omitted — the cheapest eligible GPU is auto-selected. For templates serving a Hugging Face model via env.MODEL (vllm, sglang), the model's published weights size is checked against the GPU's VRAM at submit time: an oversized model on an explicit gpu_type returns 422 `model_too_large` (auto-select instead raises its VRAM floor to the estimate, and 422s only when no available GPU fits). Gated/private/unknown repos are never blocked — the deploy proceeds and the 202 carries a `warnings` entry.
      * @type {string}

package/dist/esm/models/CreateInstanceRequest.js

@@ -45,6 +45,7 @@ export function CreateInstanceRequestFromJSONTyped(json, ignoreDiscriminator) {
         'sshKeyIds': json['ssh_key_ids'] == null ? undefined : json['ssh_key_ids'],
         'name': json['name'] == null ? undefined : json['name'],
         'maxPricePerHour': json['max_price_per_hour'] == null ? undefined : json['max_price_per_hour'],
+        'viewedPricePerHour': json['viewed_price_per_hour'] == null ? undefined : json['viewed_price_per_hour'],
         'templateId': json['template_id'] == null ? undefined : json['template_id'],
         'environment': json['environment'] == null ? undefined : json['environment'],
         'offeringId': json['offering_id'] == null ? undefined : json['offering_id'],
@@ -67,6 +68,7 @@ export function CreateInstanceRequestToJSONTyped(value, ignoreDiscriminator = fa
         'ssh_key_ids': value['sshKeyIds'],
         'name': value['name'],
         'max_price_per_hour': value['maxPricePerHour'],
+        'viewed_price_per_hour': value['viewedPricePerHour'],
         'template_id': value['templateId'],
         'environment': value['environment'],
         'offering_id': value['offeringId'],

package/dist/esm/models/Instance.d.ts

@@ -29,7 +29,7 @@ export interface Instance {
      */
     name?: string;
     /**
-     * Customer-facing lifecycle status. "allocating" = the GPU is still being acquired from the provider (slow-boot capacity such as baremetal can take ~15 min); "starting" = the node exists and is booting; "running" = ready to use.
+     * Customer-facing lifecycle status. "allocating" = the GPU is still being acquired from the provider (slow-boot capacity such as baremetal can take ~15 min); "starting" = the node exists and is booting; "running" = ready to use. "unreachable" = the platform's tunnel probe has confirmed the SSH path is down while the machine may still be up: the instance is NOT usable right now, billing for the confirmed-dead window is auto-credited back, and the instance either recovers to "running" on its own or is failed after a grace window. It is a degraded reading of a running instance, not a separate lifecycle state — see unreachable_since.
      * @type {InstanceStatusEnum}
      * @memberof Instance
      */
@@ -106,6 +106,12 @@ export interface Instance {
      * @memberof Instance
      */
     lastReachableAt?: Date;
+    /**
+     * Start of the confirmed tunnel outage the instance is currently in. Present exactly when status is "unreachable", absent otherwise. It is the timestamp the auto-credit for the dead window is computed from, so a ledger credit can be reconciled against it.
+     * @type {Date}
+     * @memberof Instance
+     */
+    unreachableSince?: Date;
 }
 /**
  * @export
@@ -117,6 +123,7 @@ export declare const InstanceStatusEnum: {
     readonly Stopping: "stopping";
     readonly Stopped: "stopped";
     readonly Terminated: "terminated";
+    readonly Unreachable: "unreachable";
     readonly Error: "error";
 };
 export type InstanceStatusEnum = typeof InstanceStatusEnum[keyof typeof InstanceStatusEnum];

package/dist/esm/models/Instance.js

@@ -22,6 +22,7 @@ export const InstanceStatusEnum = {
     Stopping: 'stopping',
     Stopped: 'stopped',
     Terminated: 'terminated',
+    Unreachable: 'unreachable',
     Error: 'error'
 };
 /**
@@ -76,6 +77,7 @@ export function InstanceFromJSONTyped(json, ignoreDiscriminator) {
         'readyAt': json['ready_at'] == null ? undefined : (new Date(json['ready_at'])),
         'terminatedAt': json['terminated_at'] == null ? undefined : (new Date(json['terminated_at'])),
         'lastReachableAt': json['last_reachable_at'] == null ? undefined : (new Date(json['last_reachable_at'])),
+        'unreachableSince': json['unreachable_since'] == null ? undefined : (new Date(json['unreachable_since'])),
     };
 }
 export function InstanceToJSON(json) {
@@ -101,5 +103,6 @@ export function InstanceToJSONTyped(value, ignoreDiscriminator = false) {
         'ready_at': value['readyAt'] == null ? value['readyAt'] : value['readyAt'].toISOString(),
         'terminated_at': value['terminatedAt'] == null ? value['terminatedAt'] : value['terminatedAt'].toISOString(),
         'last_reachable_at': value['lastReachableAt'] == null ? value['lastReachableAt'] : value['lastReachableAt'].toISOString(),
+        'unreachable_since': value['unreachableSince'] == null ? value['unreachableSince'] : value['unreachableSince'].toISOString(),
     };
 }

package/dist/models/CreateInstanceRequest.d.ts

@@ -57,6 +57,12 @@ export interface CreateInstanceRequest {
      * @memberof CreateInstanceRequest
      */
     maxPricePerHour?: number;
+    /**
+     * The retail $/hr the caller displayed to the user before launch. A catalog row is a quote, not a booking, and pinning an offering fixes which machine is placed but not its rate. If the launch-time price exceeds this by more than $0.01 the launch fails with `price_changed` carrying the new price instead of proceeding at the higher price; omit to accept the launch-time price (previous behavior). Refusal only — it is never read as consent, so it can neither raise what you are charged nor widen what may be bought on your behalf. Use max_price_per_hour to bound spend.
+     * @type {number}
+     * @memberof CreateInstanceRequest
+     */
+    viewedPricePerHour?: number;
     /**
      * Deploy a curated application template (e.g. comfyui, vllm). When set, gpu_type may be omitted — the cheapest eligible GPU is auto-selected. For templates serving a Hugging Face model via env.MODEL (vllm, sglang), the model's published weights size is checked against the GPU's VRAM at submit time: an oversized model on an explicit gpu_type returns 422 `model_too_large` (auto-select instead raises its VRAM floor to the estimate, and 422s only when no available GPU fits). Gated/private/unknown repos are never blocked — the deploy proceeds and the 202 carries a `warnings` entry.
      * @type {string}

package/dist/models/CreateInstanceRequest.js

@@ -53,6 +53,7 @@ function CreateInstanceRequestFromJSONTyped(json, ignoreDiscriminator) {
         'sshKeyIds': json['ssh_key_ids'] == null ? undefined : json['ssh_key_ids'],
         'name': json['name'] == null ? undefined : json['name'],
         'maxPricePerHour': json['max_price_per_hour'] == null ? undefined : json['max_price_per_hour'],
+        'viewedPricePerHour': json['viewed_price_per_hour'] == null ? undefined : json['viewed_price_per_hour'],
         'templateId': json['template_id'] == null ? undefined : json['template_id'],
         'environment': json['environment'] == null ? undefined : json['environment'],
         'offeringId': json['offering_id'] == null ? undefined : json['offering_id'],
@@ -75,6 +76,7 @@ function CreateInstanceRequestToJSONTyped(value, ignoreDiscriminator = false) {
         'ssh_key_ids': value['sshKeyIds'],
         'name': value['name'],
         'max_price_per_hour': value['maxPricePerHour'],
+        'viewed_price_per_hour': value['viewedPricePerHour'],
         'template_id': value['templateId'],
         'environment': value['environment'],
         'offering_id': value['offeringId'],

package/dist/models/Instance.d.ts

@@ -29,7 +29,7 @@ export interface Instance {
      */
     name?: string;
     /**
-     * Customer-facing lifecycle status. "allocating" = the GPU is still being acquired from the provider (slow-boot capacity such as baremetal can take ~15 min); "starting" = the node exists and is booting; "running" = ready to use.
+     * Customer-facing lifecycle status. "allocating" = the GPU is still being acquired from the provider (slow-boot capacity such as baremetal can take ~15 min); "starting" = the node exists and is booting; "running" = ready to use. "unreachable" = the platform's tunnel probe has confirmed the SSH path is down while the machine may still be up: the instance is NOT usable right now, billing for the confirmed-dead window is auto-credited back, and the instance either recovers to "running" on its own or is failed after a grace window. It is a degraded reading of a running instance, not a separate lifecycle state — see unreachable_since.
      * @type {InstanceStatusEnum}
      * @memberof Instance
      */
@@ -106,6 +106,12 @@ export interface Instance {
      * @memberof Instance
      */
     lastReachableAt?: Date;
+    /**
+     * Start of the confirmed tunnel outage the instance is currently in. Present exactly when status is "unreachable", absent otherwise. It is the timestamp the auto-credit for the dead window is computed from, so a ledger credit can be reconciled against it.
+     * @type {Date}
+     * @memberof Instance
+     */
+    unreachableSince?: Date;
 }
 /**
  * @export
@@ -117,6 +123,7 @@ export declare const InstanceStatusEnum: {
     readonly Stopping: "stopping";
     readonly Stopped: "stopped";
     readonly Terminated: "terminated";
+    readonly Unreachable: "unreachable";
     readonly Error: "error";
 };
 export type InstanceStatusEnum = typeof InstanceStatusEnum[keyof typeof InstanceStatusEnum];

package/dist/models/Instance.js

@@ -30,6 +30,7 @@ exports.InstanceStatusEnum = {
     Stopping: 'stopping',
     Stopped: 'stopped',
     Terminated: 'terminated',
+    Unreachable: 'unreachable',
     Error: 'error'
 };
 /**
@@ -84,6 +85,7 @@ function InstanceFromJSONTyped(json, ignoreDiscriminator) {
         'readyAt': json['ready_at'] == null ? undefined : (new Date(json['ready_at'])),
         'terminatedAt': json['terminated_at'] == null ? undefined : (new Date(json['terminated_at'])),
         'lastReachableAt': json['last_reachable_at'] == null ? undefined : (new Date(json['last_reachable_at'])),
+        'unreachableSince': json['unreachable_since'] == null ? undefined : (new Date(json['unreachable_since'])),
     };
 }
 function InstanceToJSON(json) {
@@ -109,5 +111,6 @@ function InstanceToJSONTyped(value, ignoreDiscriminator = false) {
         'ready_at': value['readyAt'] == null ? value['readyAt'] : value['readyAt'].toISOString(),
         'terminated_at': value['terminatedAt'] == null ? value['terminatedAt'] : value['terminatedAt'].toISOString(),
         'last_reachable_at': value['lastReachableAt'] == null ? value['lastReachableAt'] : value['lastReachableAt'].toISOString(),
+        'unreachable_since': value['unreachableSince'] == null ? value['unreachableSince'] : value['unreachableSince'].toISOString(),
     };
 }

package/docs/CreateInstanceRequest.md

@@ -13,6 +13,7 @@ Name | Type
 `sshKeyIds` | Array<string>
 `name` | string
 `maxPricePerHour` | number
+`viewedPricePerHour` | number
 `templateId` | string
 `environment` | string
 `offeringId` | string
@@ -33,6 +34,7 @@ const example = {
   "sshKeyIds": null,
   "name": null,
   "maxPricePerHour": null,
+  "viewedPricePerHour": null,
   "templateId": null,
   "environment": certified:pytorch@2.13,
   "offeringId": null,

package/docs/Instance.md

@@ -21,6 +21,7 @@ Name | Type
 `readyAt` | Date
 `terminatedAt` | Date
 `lastReachableAt` | Date
+`unreachableSince` | Date
 
 ## Example
 
@@ -44,6 +45,7 @@ const example = {
   "readyAt": null,
   "terminatedAt": null,
   "lastReachableAt": null,
+  "unreachableSince": null,
 } satisfies Instance
 
 console.log(example)

package/docs/InstancesApi.md

@@ -268,7 +268,7 @@ async function example() {
     cursor: cursor_example,
     // number (optional)
     limit: 56,
-    // 'allocating' | 'starting' | 'running' | 'stopping' | 'stopped' | 'terminated' | 'error' | 'all' | Filter by customer-facing status (default = all non-terminated) (optional)
+    // 'allocating' | 'starting' | 'running' | 'stopping' | 'stopped' | 'terminated' | 'error' | 'all' | Filter by customer-facing status (default = all non-terminated). There is no \"unreachable\" filter value: an unreachable instance is a running instance with a dead tunnel, so it is listed under status=running and reads \"unreachable\" in the response body. (optional)
     status: status_example,
   } satisfies ListInstancesRequest;
 
@@ -291,7 +291,7 @@ example().catch(console.error);
 |------------- | ------------- | ------------- | -------------|
 | **cursor** | `string` |  | [Optional] [Defaults to `undefined`] |
 | **limit** | `number` |  | [Optional] [Defaults to `50`] |
-| **status** | `allocating`, `starting`, `running`, `stopping`, `stopped`, `terminated`, `error`, `all` | Filter by customer-facing status (default = all non-terminated) | [Optional] [Defaults to `undefined`] [Enum: allocating, starting, running, stopping, stopped, terminated, error, all] |
+| **status** | `allocating`, `starting`, `running`, `stopping`, `stopped`, `terminated`, `error`, `all` | Filter by customer-facing status (default = all non-terminated). There is no \"unreachable\" filter value: an unreachable instance is a running instance with a dead tunnel, so it is listed under status=running and reads \"unreachable\" in the response body. | [Optional] [Defaults to `undefined`] [Enum: allocating, starting, running, stopping, stopped, terminated, error, all] |
 
 ### Return type
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gpuai/sdk",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "TypeScript SDK for the GPU.ai Public Developer API",
   "author": "GPU.ai Support <support@gpu.ai>",
   "repository": {

package/src/models/CreateInstanceRequest.ts

@@ -61,6 +61,12 @@ export interface CreateInstanceRequest {
      * @memberof CreateInstanceRequest
      */
     maxPricePerHour?: number;
+    /**
+     * The retail $/hr the caller displayed to the user before launch. A catalog row is a quote, not a booking, and pinning an offering fixes which machine is placed but not its rate. If the launch-time price exceeds this by more than $0.01 the launch fails with `price_changed` carrying the new price instead of proceeding at the higher price; omit to accept the launch-time price (previous behavior). Refusal only — it is never read as consent, so it can neither raise what you are charged nor widen what may be bought on your behalf. Use max_price_per_hour to bound spend.
+     * @type {number}
+     * @memberof CreateInstanceRequest
+     */
+    viewedPricePerHour?: number;
     /**
      * Deploy a curated application template (e.g. comfyui, vllm). When set, gpu_type may be omitted — the cheapest eligible GPU is auto-selected. For templates serving a Hugging Face model via env.MODEL (vllm, sglang), the model's published weights size is checked against the GPU's VRAM at submit time: an oversized model on an explicit gpu_type returns 422 `model_too_large` (auto-select instead raises its VRAM floor to the estimate, and 422s only when no available GPU fits). Gated/private/unknown repos are never blocked — the deploy proceeds and the 202 carries a `warnings` entry.
      * @type {string}
@@ -131,6 +137,7 @@ export function CreateInstanceRequestFromJSONTyped(json: any, ignoreDiscriminato
         'sshKeyIds': json['ssh_key_ids'] == null ? undefined : json['ssh_key_ids'],
         'name': json['name'] == null ? undefined : json['name'],
         'maxPricePerHour': json['max_price_per_hour'] == null ? undefined : json['max_price_per_hour'],
+        'viewedPricePerHour': json['viewed_price_per_hour'] == null ? undefined : json['viewed_price_per_hour'],
         'templateId': json['template_id'] == null ? undefined : json['template_id'],
         'environment': json['environment'] == null ? undefined : json['environment'],
         'offeringId': json['offering_id'] == null ? undefined : json['offering_id'],
@@ -157,6 +164,7 @@ export function CreateInstanceRequestToJSONTyped(value?: CreateInstanceRequest |
         'ssh_key_ids': value['sshKeyIds'],
         'name': value['name'],
         'max_price_per_hour': value['maxPricePerHour'],
+        'viewed_price_per_hour': value['viewedPricePerHour'],
         'template_id': value['templateId'],
         'environment': value['environment'],
         'offering_id': value['offeringId'],

package/src/models/Instance.ts

@@ -40,7 +40,7 @@ export interface Instance {
      */
     name?: string;
     /**
-     * Customer-facing lifecycle status. "allocating" = the GPU is still being acquired from the provider (slow-boot capacity such as baremetal can take ~15 min); "starting" = the node exists and is booting; "running" = ready to use.
+     * Customer-facing lifecycle status. "allocating" = the GPU is still being acquired from the provider (slow-boot capacity such as baremetal can take ~15 min); "starting" = the node exists and is booting; "running" = ready to use. "unreachable" = the platform's tunnel probe has confirmed the SSH path is down while the machine may still be up: the instance is NOT usable right now, billing for the confirmed-dead window is auto-credited back, and the instance either recovers to "running" on its own or is failed after a grace window. It is a degraded reading of a running instance, not a separate lifecycle state — see unreachable_since.
      * @type {InstanceStatusEnum}
      * @memberof Instance
      */
@@ -117,6 +117,12 @@ export interface Instance {
      * @memberof Instance
      */
     lastReachableAt?: Date;
+    /**
+     * Start of the confirmed tunnel outage the instance is currently in. Present exactly when status is "unreachable", absent otherwise. It is the timestamp the auto-credit for the dead window is computed from, so a ledger credit can be reconciled against it.
+     * @type {Date}
+     * @memberof Instance
+     */
+    unreachableSince?: Date;
 }
 
 
@@ -130,6 +136,7 @@ export const InstanceStatusEnum = {
     Stopping: 'stopping',
     Stopped: 'stopped',
     Terminated: 'terminated',
+    Unreachable: 'unreachable',
     Error: 'error'
 } as const;
 export type InstanceStatusEnum = typeof InstanceStatusEnum[keyof typeof InstanceStatusEnum];
@@ -184,6 +191,7 @@ export function InstanceFromJSONTyped(json: any, ignoreDiscriminator: boolean):
         'readyAt': json['ready_at'] == null ? undefined : (new Date(json['ready_at'])),
         'terminatedAt': json['terminated_at'] == null ? undefined : (new Date(json['terminated_at'])),
         'lastReachableAt': json['last_reachable_at'] == null ? undefined : (new Date(json['last_reachable_at'])),
+        'unreachableSince': json['unreachable_since'] == null ? undefined : (new Date(json['unreachable_since'])),
     };
 }
 
@@ -213,6 +221,7 @@ export function InstanceToJSONTyped(value?: Instance | null, ignoreDiscriminator
         'ready_at': value['readyAt'] == null ? value['readyAt'] : value['readyAt'].toISOString(),
         'terminated_at': value['terminatedAt'] == null ? value['terminatedAt'] : value['terminatedAt'].toISOString(),
         'last_reachable_at': value['lastReachableAt'] == null ? value['lastReachableAt'] : value['lastReachableAt'].toISOString(),
+        'unreachable_since': value['unreachableSince'] == null ? value['unreachableSince'] : value['unreachableSince'].toISOString(),
     };
 }