runbios-sdk 0.2.1-dev.97 → 0.2.1-rc.118

package/README.md

@@ -239,17 +239,47 @@ const preview = await client.datasets.preview('ds_abc123', { pageSize: 5 });
 
 // Import from HuggingFace
 const imported = await client.datasets.importFromHuggingFace({
-  repoId: 'databricks/dolly-15k',
+  repoId: 'HuggingFaceH4/ultrachat_200k',
   integrationId: 'int_abc123',
-  name: 'Dolly 15k',
+  name: 'Ultrachat SFT',
+  subset: 'default',
+  split: 'train_sft',
 });
 
 // Validate before upload
 const validation = await client.datasets.validate('./data.jsonl');
 ```
 
+#### Connected Hub search and exact source selection
+
+Use `client.integrations.list()` to discover connected accounts, then select the
+returned ID explicitly. `client.integrations.browse(integrationId, { query,
+page, limit })` searches with that account's access. Discovery returns account
+metadata, never stored credentials.
+
+Pass the same `integrationId` to `datasets.previewHub` and
+`datasets.importFromHuggingFace`. Preview returns `available_configs` and
+`available_splits`; choose the actual subset/split rather than assuming `train`.
+A missing or unauthorized integration is an error, not anonymous fallback.
+Public imports without an integration use `datasets.registerHuggingFace` and
+require `workspaceId` on the client or method call.
+
+Both import methods accept `revision`, `maxSamples`, `sampleStrategy` and
+`importMode`. The service records immutable source metadata for resume. A Hub
+preview does not prove readiness or preview an arbitrary older revision: inspect
+the registered dataset when importing an explicit revision. Poll
+`datasets.getStatus(id)` until `ready` before selecting it for training; a client
+polling timeout does not cancel the background import.
+
 ### Training
 
+`datasetIds` preserves source order. Pass the same `mixing` object to preflight
+and create: `{ mode: 'interleave', weights: [3, 1], seed: 42 }`. Weights match the
+ordered IDs. Modes are `sequential`, `shuffle`, `interleave`, and `phased`; phased
+plans contain ordered `phases` with `name`, `portion`, optional `weights`, and
+`shuffle`. The default composition seed is 42. Resume reconstructs data from
+source pins and the stored plan and verifies the checksum.
+
 ```typescript
 const request = {
   idempotencyKey: 'training-create-20260711-0001',

package/dist/client.js

@@ -276,7 +276,7 @@ export class HttpClient {
     constructor(config) {
         // Default host stays api.runbios.ai for now; cutover to api.runbios.ai is
         // planned once its DNS exists.
-        this.baseUrl = (config.baseUrl || envBaseUrl() || 'https://api-dev.runbios.ai').replace(/\/+$/, '');
+        this.baseUrl = (config.baseUrl || envBaseUrl() || 'https://api-staging.runbios.ai').replace(/\/+$/, '');
         this.apiKey = config.apiKey ?? envApiKey();
         this.accessToken = config.accessToken;
         this.orgId = config.orgId;

package/dist/index.d.ts

@@ -26,20 +26,23 @@
 import type { BiOSConfig, ApiKeyIntrospection } from './types.js';
 import { Models } from './resources/models.js';
 import { Datasets } from './resources/datasets.js';
+import { Integrations } from './resources/integrations.js';
 import { Training } from './resources/training.js';
 import { Wallet } from './resources/wallet.js';
 import { GPU } from './resources/gpu.js';
 import { Inference } from './resources/inference.js';
+import { Loop } from './resources/loop.js';
 /**
  * SDK version. Sent as part of the User-Agent header.
  * Must match package.json "version" -- enforced by a contract test.
  */
-export declare const VERSION = "0.2.1-dev.97";
+export declare const VERSION = "0.2.1-rc.118";
 export declare class RunBiOS {
     /** Search models, fetch configs, check adapter compatibility. */
     readonly models: Models;
     /** Upload, import, preview, and manage training datasets. */
     readonly datasets: Datasets;
+    readonly integrations: Integrations;
     /** Create, monitor, stop, and resume fine-tuning jobs. */
     readonly training: Training;
     /** Check wallet balance. */
@@ -51,6 +54,12 @@ export declare class RunBiOS {
      * serving deployments, plus OpenAI-compatible non-streaming and SSE calls.
      */
     readonly inference: Inference;
+    /**
+     * The Conscious Loop. Capture what your model was asked and answered, record
+     * whether it was right, and turn those judgements into training data for
+     * SFT, DPO or GRPO. Nothing is captured until you turn it on for a source.
+     */
+    readonly loop: Loop;
     /** @internal */
     private readonly _http;
     constructor(config: BiOSConfig);
@@ -61,8 +70,9 @@ export { RunBiOS as BiOS };
 export { ApiError, GpuRejectionError, CapacityUnavailableError, ComingSoonError, CAPACITY_UNAVAILABLE_CODE, COMING_SOON_CODES, PERMANENT_GPU_CODES, isPermanentGpuCode, gpuRejectionCodeForReason, } from './client.js';
 export { Models } from './resources/models.js';
 export { Datasets } from './resources/datasets.js';
+export { Integrations, type HuggingFaceIntegration, type IntegrationBrowseParams } from './resources/integrations.js';
 export { Training } from './resources/training.js';
 export { Wallet } from './resources/wallet.js';
 export { GPU, type GPURecommendation } from './resources/gpu.js';
 export { Inference, validateChatRequest, parseSSE, buildInferenceRequest, contextSizingBasis, type ContextSizingBasis, CONTEXT_DEFAULT_CEILING, CONTEXT_EDITABLE_FLOOR, type ChatMessage, type FunctionTool, type ChatCompletionParams, type ChatCompletionResponse, type ChatCompletionChunk, } from './resources/inference.js';
-export type { BiOSConfig, PaginatedResponse, ApiErrorBody, AvailableGpuAlternative, CapacityMinimumRequirement, InferenceBookingAccepted, Model, ModelSearchParams, ModelSearchResponse, ModelDetailResponse, ModelConfig, Dataset, DatasetListParams, DatasetListResponse, DatasetUploadParams, DatasetPreview, DatasetPreviewParams, DatasetImportHFParams, DatasetRegisterHFParams, DatasetHubSearchParams, DatasetHubPreviewParams, DatasetValidation, DatasetFormatVariant, DatasetFormatSpec, DatasetFormatSpecs, DatasetStorageUsage, TrainingMethod, RLHFAlgorithm, AdapterType, TrainingJobStatus, TrainingStatusFilter, TrainingCreateParams, TrainingListParams, TrainingListResponse, TrainingJob, TrainingMetrics, MetricPoint, MetricGraphConfig, TrainingCheckpoint, TrainingLogs, TrainingLogEntry, TrainingStopResponse, TrainingResumeResponse, CanonicalTrainingRequest, TrainingPreflightDataset, TrainingPreflightWarning, TrainingPreflightResponse, TrainingCapabilityChoice, TrainingConfigFieldCapability, TrainingCapabilities, GPUChoice, WalletBalance, Transaction, TransactionListResponse, TransactionListParams, GPUInfo, GPUPricingResponse, GPUOptionsParams, GPUOption, GPUOptionSuggestion, GPUOptionsResponse, InferenceStatus, InferenceCreateParams, InferenceUpdateParams, InferenceDeployment, InferenceDeploymentSummary, InferenceCreateResponse, InferenceListResponse, InferenceUpdateResponse, InferenceLifecycleResponse, InferenceDeleteResponse, InferenceGPUOptionMarket, InferenceGPUOption, InferenceGPUAlternative, InferenceGPUOptionsParams, InferenceGPUOptionsResponse, InferenceCanonicalRequest, InferencePreflightWarning, InferencePreflightResponse, AdapterCompatibility, AdapterCompatibilityResponse, AdapterCompatibilityParams, SupportedArchitecture, ArchitectureScope, SupportedArchitecturesResponse, ApiKey, ApiKeyScope, ApiKeyIntrospection, Organization, OrgMember, OrgInvite, Workspace, Integration, IntegrationCreateParams, StorageUsage, StorageObject, PromptTokensDetails, ChatCompletionUsage, } from './types.js';
+export type { BiOSConfig, PaginatedResponse, ApiErrorBody, AvailableGpuAlternative, CapacityMinimumRequirement, InferenceBookingAccepted, Model, ModelSearchParams, ModelSearchResponse, ModelDetailResponse, ModelConfig, Dataset, DatasetListParams, DatasetListResponse, DatasetUploadParams, DatasetPreview, DatasetPreviewParams, DatasetImportHFParams, DatasetRegisterHFParams, DatasetHubSearchParams, DatasetHubPreviewParams, DatasetValidation, DatasetFormatVariant, DatasetFormatSpec, DatasetFormatSpecs, DatasetStorageUsage, TrainingMethod, RLHFAlgorithm, AdapterType, TrainingJobStatus, TrainingStatusFilter, TrainingCreateParams, TrainingListParams, TrainingListResponse, TrainingJob, TrainingMetrics, TrainingResourceMetrics, TrainingDeviceMetrics, MetricPoint, MetricGraphConfig, TrainingCheckpoint, TrainingLogs, TrainingLogEntry, TrainingStopResponse, TrainingResumeResponse, CanonicalTrainingRequest, TrainingPreflightDataset, TrainingPreflightWarning, TrainingPreflightResponse, TrainingCapabilityChoice, TrainingConfigFieldCapability, TrainingCapabilities, GPUChoice, WalletBalance, Transaction, TransactionListResponse, TransactionListParams, GPUInfo, GPUPricingResponse, GPUOptionsParams, TrainingRecommendParams, TrainingAdvisorVerdict, TrainingAdvisorRecommendation, TrainingAdvisorUserShape, TrainingAdvisorJustification, TrainingAdvisorBasis, GPUOption, GPUOptionSuggestion, GPUOptionsResponse, InferenceStatus, InferenceCreateParams, InferenceUpdateParams, InferenceDeployment, InferenceDeploymentSummary, InferenceCreateResponse, InferenceListResponse, InferenceUpdateResponse, InferenceLifecycleResponse, InferenceDeleteResponse, InferenceGPUOptionMarket, InferenceGPUOption, InferenceGPUAlternative, InferenceGPUOptionsParams, InferenceGPUOptionsResponse, InferenceCanonicalRequest, InferencePreflightWarning, InferencePreflightResponse, AdapterCompatibility, AdapterCompatibilityResponse, AdapterCompatibilityParams, SupportedArchitecture, ArchitectureScope, SupportedArchitecturesResponse, ApiKey, ApiKeyScope, ApiKeyIntrospection, Organization, OrgMember, OrgInvite, Workspace, Integration, IntegrationCreateParams, StorageUsage, StorageObject, PromptTokensDetails, ChatCompletionUsage, } from './types.js';

package/dist/index.js

@@ -26,20 +26,23 @@
 import { HttpClient, envInferenceKey } from './client.js';
 import { Models } from './resources/models.js';
 import { Datasets } from './resources/datasets.js';
+import { Integrations } from './resources/integrations.js';
 import { Training } from './resources/training.js';
 import { Wallet } from './resources/wallet.js';
 import { GPU } from './resources/gpu.js';
 import { Inference } from './resources/inference.js';
+import { Loop } from './resources/loop.js';
 /**
  * SDK version. Sent as part of the User-Agent header.
  * Must match package.json "version" -- enforced by a contract test.
  */
-export const VERSION = '0.2.1-dev.97';
+export const VERSION = '0.2.1-rc.118';
 export class RunBiOS {
     /** Search models, fetch configs, check adapter compatibility. */
     models;
     /** Upload, import, preview, and manage training datasets. */
     datasets;
+    integrations;
     /** Create, monitor, stop, and resume fine-tuning jobs. */
     training;
     /** Check wallet balance. */
@@ -51,6 +54,12 @@ export class RunBiOS {
      * serving deployments, plus OpenAI-compatible non-streaming and SSE calls.
      */
     inference;
+    /**
+     * The Conscious Loop. Capture what your model was asked and answered, record
+     * whether it was right, and turn those judgements into training data for
+     * SFT, DPO or GRPO. Nothing is captured until you turn it on for a source.
+     */
+    loop;
     /** @internal */
     _http;
     constructor(config) {
@@ -58,9 +67,11 @@ export class RunBiOS {
         this._http = http;
         this.models = new Models(http);
         this.datasets = new Datasets(http);
+        this.integrations = new Integrations(http);
         this.training = new Training(http);
         this.wallet = new Wallet(http);
         this.gpu = new GPU(http);
+        this.loop = new Loop(http);
         // Inference-key resolution, most specific first:
         //   1. an explicit inferenceKey (a per-deployment sk-bios-... key)
         //   2. RUNBIOS_INFERENCE_KEY from the environment (legacy: BIOS_INFERENCE_KEY)
@@ -87,6 +98,7 @@ export { RunBiOS as BiOS };
 export { ApiError, GpuRejectionError, CapacityUnavailableError, ComingSoonError, CAPACITY_UNAVAILABLE_CODE, COMING_SOON_CODES, PERMANENT_GPU_CODES, isPermanentGpuCode, gpuRejectionCodeForReason, } from './client.js';
 export { Models } from './resources/models.js';
 export { Datasets } from './resources/datasets.js';
+export { Integrations } from './resources/integrations.js';
 export { Training } from './resources/training.js';
 export { Wallet } from './resources/wallet.js';
 export { GPU } from './resources/gpu.js';

package/dist/resources/datasets.d.ts

@@ -84,10 +84,14 @@ export declare class Datasets {
      *
      * @example
      * ```ts
+     * The selected split must already expose canonical rows: a `messages` array
+     * for SFT or a `text` field for CPT. Legacy layouts are rejected with
+     * conversion guidance rather than remapped silently.
+     *
      * const imported = await client.datasets.importFromHuggingFace({
-     *   repoId: 'databricks/dolly-15k',
+     *   repoId: 'your-org/dataset-with-messages',
      *   integrationId: 'int_abc123',
-     *   name: 'Dolly 15k',
+     *   name: 'Canonical SFT data',
      * });
      * console.log(`Imported: ${imported.id}`);
      * ```
@@ -99,8 +103,8 @@ export declare class Datasets {
      * @example
      * ```ts
      * const ds = await client.datasets.registerHuggingFace({
-     *   repo_id: 'databricks/dolly-15k',
-     *   name: 'Dolly 15k',
+     *   repo_id: 'your-org/dataset-with-text',
+     *   name: 'Canonical CPT corpus',
      *   split: 'train',
      * });
      * ```

package/dist/resources/datasets.js

@@ -114,6 +114,9 @@ export class Datasets {
             const message = err instanceof Error ? err.message : String(err);
             throw new Error(`Failed to read file at "${params.filePath}": ${message}`);
         }
+        if (!fileName.toLowerCase().endsWith('.jsonl')) {
+            throw new Error('RunBiOS: dataset uploads accept .jsonl only — one JSON object per line, with "messages" for SFT or "text" for CPT');
+        }
         const blob = new Blob([fileData]);
         const formData = new FormData();
         formData.append('file', blob, fileName);
@@ -181,10 +184,14 @@ export class Datasets {
      *
      * @example
      * ```ts
+     * The selected split must already expose canonical rows: a `messages` array
+     * for SFT or a `text` field for CPT. Legacy layouts are rejected with
+     * conversion guidance rather than remapped silently.
+     *
      * const imported = await client.datasets.importFromHuggingFace({
-     *   repoId: 'databricks/dolly-15k',
+     *   repoId: 'your-org/dataset-with-messages',
      *   integrationId: 'int_abc123',
-     *   name: 'Dolly 15k',
+     *   name: 'Canonical SFT data',
      * });
      * console.log(`Imported: ${imported.id}`);
      * ```
@@ -196,6 +203,7 @@ export class Datasets {
         return normalizeDataset(await this._http.fetchPost(`/api/datasets/integrations/${encodeURIComponent(params.integrationId)}/import`, {
             dataset_id: params.repoId,
             name: params.name || params.repoId.split('/').pop() || params.repoId,
+            revision: params.revision,
             subset: params.subset,
             split: params.split,
             max_samples: params.maxSamples,
@@ -210,8 +218,8 @@ export class Datasets {
      * @example
      * ```ts
      * const ds = await client.datasets.registerHuggingFace({
-     *   repo_id: 'databricks/dolly-15k',
-     *   name: 'Dolly 15k',
+     *   repo_id: 'your-org/dataset-with-text',
+     *   name: 'Canonical CPT corpus',
      *   split: 'train',
      * });
      * ```
@@ -232,6 +240,7 @@ export class Datasets {
             description: raw.description,
             hf_subset: raw.subset ?? raw.hf_subset,
             hf_split: raw.split ?? raw.hf_split,
+            hf_revision: raw.revision ?? raw.hf_revision,
             max_samples: raw.maxSamples ?? raw.max_samples,
             sample_strategy: raw.sampleStrategy ?? raw.sample_strategy,
             column_mapping: raw.columnMapping ?? raw.column_mapping,
@@ -341,6 +350,8 @@ export class Datasets {
             q.set('subset', params.subset);
         if (params.limit !== undefined)
             q.set('limit', String(params.limit));
+        if (params.integrationId)
+            q.set('integration_id', params.integrationId);
         return this._http.fetchGet(`/api/datasets/hub-preview?${q}`);
     }
     /**

package/dist/resources/inference.d.ts

@@ -62,7 +62,13 @@ export interface ChatCompletionParams extends Record<string, unknown> {
     /**
      * Standardized reasoning effort. Forwarded to `/v1/chat/completions` as
      * `reasoning_effort`. Use `'none'` to disable reasoning where the model
-     * allows it.
+     * allows it — with reasoning off, no thinking tokens are generated or billed.
+     *
+     * `'low'` and `'medium'` minimise or skip thinking. `'high'`, `'xhigh'` and
+     * `'max'` think, and thinking tokens are billed as output tokens AND count
+     * against `max_tokens` — so a small `max_tokens` at those levels can be spent
+     * entirely on thinking and return an empty `content` with
+     * `finish_reason: "length"`. Budget generously at `'xhigh'`/`'max'`.
      */
     reasoningEffort?: 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max';
     inferenceKey?: string;

package/dist/resources/inference.js

@@ -326,7 +326,7 @@ export class Inference {
         this.key = config.inferenceKey || envInferenceKey() || envApiKey();
         // Same default host as HttpClient (api.runbios.ai); api.runbios.ai cutover
         // is planned once its DNS exists — update both call sites together.
-        this.baseUrl = (config.baseUrl || envBaseUrl() || 'https://api-dev.runbios.ai').replace(/\/+$/, '');
+        this.baseUrl = (config.baseUrl || envBaseUrl() || 'https://api-staging.runbios.ai').replace(/\/+$/, '');
         this.timeout = config.timeout ?? 900_000;
         this._http = http;
     }

package/dist/resources/integrations.d.ts

@@ -0,0 +1,21 @@
+import type { HttpClient } from '../client.js';
+export interface HuggingFaceIntegration {
+    id: string;
+    label: string;
+    provider: string;
+    status: string;
+    hf_username?: string;
+    scope?: string;
+}
+export interface IntegrationBrowseParams {
+    query?: string;
+    page?: number;
+    limit?: number;
+    sort?: 'downloads' | 'likes' | 'modified';
+}
+export declare class Integrations {
+    private readonly _http;
+    constructor(_http: HttpClient);
+    list(): Promise<HuggingFaceIntegration[]>;
+    browse(id: string, params?: IntegrationBrowseParams): Promise<Record<string, unknown>>;
+}

package/dist/resources/integrations.js

@@ -0,0 +1,20 @@
+export class Integrations {
+    _http;
+    constructor(_http) {
+        this._http = _http;
+    }
+    async list() {
+        const result = await this._http.fetchGet('/api/datasets/integrations');
+        if (!Array.isArray(result.integrations))
+            throw new Error('The integration service did not return an account list');
+        return result.integrations;
+    }
+    async browse(id, params = {}) {
+        const query = new URLSearchParams({ page: String(params.page ?? 1), limit: String(params.limit ?? 20) });
+        if (params.query !== undefined)
+            query.set('search', params.query);
+        if (params.sort !== undefined)
+            query.set('sort', params.sort);
+        return this._http.fetchGet(`/api/datasets/integrations/${encodeURIComponent(id)}/browse?${query}`);
+    }
+}