flexorch-sdk 0.3.0 → 0.3.2

package/dist/{chunk-4KCMMRD7.js → chunk-U2CE5GVG.js}

@@ -16,6 +16,9 @@ var Dataset = class _Dataset {
   slug;
   status;
   rowCount;
+  piiMasked;
+  piiFindingsCount;
+  piiTypeSummary;
   createdAt;
   availableFormats;
   _transport;
@@ -25,6 +28,9 @@ var Dataset = class _Dataset {
     this.slug = data.slug;
     this.status = data.status;
     this.rowCount = data.rowCount;
+    this.piiMasked = data.piiMasked;
+    this.piiFindingsCount = data.piiFindingsCount;
+    this.piiTypeSummary = data.piiTypeSummary;
     this.createdAt = data.createdAt;
     this.availableFormats = data.availableFormats;
     this._transport = data._transport;
@@ -32,12 +38,19 @@ var Dataset = class _Dataset {
   static fromDict(data, transport) {
     const fmt = data["format_summary"] ?? {};
     const files = fmt["files"] ?? {};
+    const privacy = data["privacy"];
+    const piiMasked = privacy ? Boolean(privacy["privacy_applied"] ?? false) : Boolean(data["privacy_applied"] ?? false);
+    const piiFindingsCount = privacy ? Number(privacy["pii_findings_count"] ?? 0) : Number(data["pii_findings_count"] ?? 0);
+    const piiTypeSummary = privacy ? privacy["pii_type_summary"] ?? {} : {};
     return new _Dataset({
       id: String(data["id"] ?? ""),
       name: String(data["name"] ?? ""),
       slug: String(data["slug"] ?? ""),
       status: String(data["status"] ?? ""),
       rowCount: Number(data["row_count"] ?? 0),
+      piiMasked,
+      piiFindingsCount,
+      piiTypeSummary,
       createdAt: String(data["created_at"] ?? ""),
       availableFormats: Object.keys(files),
       _transport: transport

package/dist/{dataset-E7EXJETI.js → dataset-UGUUKKH3.js}

@@ -1,6 +1,6 @@
 import {
   Dataset
-} from "./chunk-4KCMMRD7.js";
+} from "./chunk-U2CE5GVG.js";
 export {
   Dataset
 };

package/dist/index.cjs

@@ -56,6 +56,9 @@ var init_dataset = __esm({
       slug;
       status;
       rowCount;
+      piiMasked;
+      piiFindingsCount;
+      piiTypeSummary;
       createdAt;
       availableFormats;
       _transport;
@@ -65,6 +68,9 @@ var init_dataset = __esm({
         this.slug = data.slug;
         this.status = data.status;
         this.rowCount = data.rowCount;
+        this.piiMasked = data.piiMasked;
+        this.piiFindingsCount = data.piiFindingsCount;
+        this.piiTypeSummary = data.piiTypeSummary;
         this.createdAt = data.createdAt;
         this.availableFormats = data.availableFormats;
         this._transport = data._transport;
@@ -72,12 +78,19 @@ var init_dataset = __esm({
       static fromDict(data, transport) {
         const fmt = data["format_summary"] ?? {};
         const files = fmt["files"] ?? {};
+        const privacy = data["privacy"];
+        const piiMasked = privacy ? Boolean(privacy["privacy_applied"] ?? false) : Boolean(data["privacy_applied"] ?? false);
+        const piiFindingsCount = privacy ? Number(privacy["pii_findings_count"] ?? 0) : Number(data["pii_findings_count"] ?? 0);
+        const piiTypeSummary = privacy ? privacy["pii_type_summary"] ?? {} : {};
         return new _Dataset({
           id: String(data["id"] ?? ""),
           name: String(data["name"] ?? ""),
           slug: String(data["slug"] ?? ""),
           status: String(data["status"] ?? ""),
           rowCount: Number(data["row_count"] ?? 0),
+          piiMasked,
+          piiFindingsCount,
+          piiTypeSummary,
           createdAt: String(data["created_at"] ?? ""),
           availableFormats: Object.keys(files),
           _transport: transport
@@ -312,7 +325,7 @@ var Transport = class {
     this.fetchFn = fetchFn ?? globalThis.fetch.bind(globalThis);
     this.defaultHeaders = {
       "X-API-KEY": apiKey,
-      "User-Agent": "flexorch-sdk-js/0.3.0"
+      "User-Agent": "flexorch-sdk-js/0.3.2"
     };
   }
   url(path, params) {
@@ -405,6 +418,8 @@ var Job = class _Job {
   /** Needed by buildDataset() — POST /datasets/build-from-execution/{executionId}. */
   executionId;
   hasDataset;
+  /** Set from `dataset_summary.dataset_id` on a completed dataset_build job's response. */
+  datasetId;
   /**
    * True when the underlying pipeline execution completed but one or more
    * non-critical steps failed (e.g. structured extraction couldn't find a
@@ -416,6 +431,9 @@ var Job = class _Job {
    */
   degraded;
   failureReason;
+  piiMasked;
+  piiFindingsCount;
+  piiTypeSummary;
   _transport;
   constructor(data) {
     this.id = data.id;
@@ -425,13 +443,19 @@ var Job = class _Job {
     this.documentId = data.documentId;
     this.executionId = data.executionId;
     this.hasDataset = data.hasDataset;
+    this.datasetId = data.datasetId;
     this.degraded = data.degraded;
     this.failureReason = data.failureReason;
+    this.piiMasked = data.piiMasked;
+    this.piiFindingsCount = data.piiFindingsCount;
+    this.piiTypeSummary = data.piiTypeSummary;
     this._transport = data._transport;
   }
   static fromDict(data, transport) {
     const executionSummary = data["execution_summary"];
     const processingSummary = data["processing_summary"];
+    const datasetSummary = data["dataset_summary"];
+    const privacy = executionSummary?.["privacy"];
     let quality = data["quality"];
     if (!quality && processingSummary) {
       quality = processingSummary["quality"];
@@ -445,9 +469,22 @@ var Job = class _Job {
       qualityScore: quality["score"] ?? null,
       documentId: data["document_id"] ?? null,
       executionId,
-      hasDataset: Boolean(data["has_dataset"] ?? processingSummary?.["has_dataset"] ?? false),
+      // dataset_summary is only present on a completed dataset_build job's
+      // response — neither has_dataset nor processing_summary is ever set
+      // for that job type, so without this .dataset() always returned null
+      // for the job.buildDataset().wait().dataset() chain even though the
+      // dataset had been built successfully.
+      hasDataset: Boolean(data["has_dataset"] ?? processingSummary?.["has_dataset"] ?? Boolean(datasetSummary) ?? false),
+      datasetId: datasetSummary?.["dataset_id"] ?? null,
       degraded: Boolean(executionSummary?.["degraded"] ?? false),
       failureReason: data["failure_reason"] ?? null,
+      // execution_summary.privacy — computed fresh on every GET /jobs/{id}
+      // read, not frozen at job-completion time, so this works even for
+      // jobs older than this field. Defaults for jobs with no execution
+      // (e.g. dataset_build) or against an older API version.
+      piiMasked: Boolean(privacy?.["privacy_applied"] ?? false),
+      piiFindingsCount: Number(privacy?.["pii_findings_count"] ?? 0),
+      piiTypeSummary: privacy?.["pii_type_summary"] ?? {},
       _transport: transport
     });
   }
@@ -473,13 +510,17 @@ var Job = class _Job {
     throw new JobTimeoutError(this.id, timeout);
   }
   async dataset() {
+    const { Dataset: Dataset2 } = await Promise.resolve().then(() => (init_dataset(), dataset_exports));
+    if (this.datasetId !== null) {
+      const data2 = await this._transport.get(`/datasets/${this.datasetId}`);
+      return Dataset2.fromDict(data2, this._transport);
+    }
     if (!this.hasDataset) return null;
     const data = await this._transport.get("/datasets", {
       job_id: this.id
     });
     const items = data["items"] ?? [];
     if (items.length === 0) return null;
-    const { Dataset: Dataset2 } = await Promise.resolve().then(() => (init_dataset(), dataset_exports));
     return Dataset2.fromDict(items[0], this._transport);
   }
   /**
@@ -1261,7 +1302,7 @@ var FlexOrchReader = class {
 };
 
 // src/index.ts
-var version = "0.3.0";
+var version = "0.3.2";
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
   AuthError,

package/dist/index.d.cts

@@ -22,6 +22,9 @@ declare class Dataset {
     readonly slug: string;
     readonly status: string;
     readonly rowCount: number;
+    readonly piiMasked: boolean;
+    readonly piiFindingsCount: number;
+    readonly piiTypeSummary: Record<string, number>;
     readonly createdAt: string;
     readonly availableFormats: string[];
     private readonly _transport;
@@ -31,6 +34,9 @@ declare class Dataset {
         slug: string;
         status: string;
         rowCount: number;
+        piiMasked: boolean;
+        piiFindingsCount: number;
+        piiTypeSummary: Record<string, number>;
         createdAt: string;
         availableFormats: string[];
         _transport: Transport;
@@ -99,6 +105,8 @@ declare class Job {
     /** Needed by buildDataset() — POST /datasets/build-from-execution/{executionId}. */
     readonly executionId: number | null;
     readonly hasDataset: boolean;
+    /** Set from `dataset_summary.dataset_id` on a completed dataset_build job's response. */
+    readonly datasetId: number | null;
     /**
      * True when the underlying pipeline execution completed but one or more
      * non-critical steps failed (e.g. structured extraction couldn't find a
@@ -110,6 +118,9 @@ declare class Job {
      */
     readonly degraded: boolean;
     readonly failureReason: string | null;
+    readonly piiMasked: boolean;
+    readonly piiFindingsCount: number;
+    readonly piiTypeSummary: Record<string, number>;
     private readonly _transport;
     constructor(data: {
         id: string;
@@ -119,8 +130,12 @@ declare class Job {
         documentId: string | null;
         executionId: number | null;
         hasDataset: boolean;
+        datasetId: number | null;
         degraded: boolean;
         failureReason: string | null;
+        piiMasked: boolean;
+        piiFindingsCount: number;
+        piiTypeSummary: Record<string, number>;
         _transport: Transport;
     });
     static fromDict(data: Record<string, unknown>, transport: Transport): Job;
@@ -603,6 +618,6 @@ declare class FlexOrchReader {
     toString(): string;
 }
 
-declare const version = "0.3.0";
+declare const version = "0.3.2";
 
 export { AuthError, Connector, type ConnectorTestResult, type ConnectorType, Dataset, Document, type ExportFormat, FlexOrchClient, type FlexOrchClientOptions, FlexOrchError, FlexOrchReader, FlexOrchRetriever, Job, JobFailedError, type JobFeedback, JobTimeoutError, NotFoundError, type QualityTrendItem, QuotaError, RAGDocument, RateLimitError, type RateLimitStatus, type ReaderLoadOptions, type RetrieverOptions, type S3ConnectorConfig, type SearchFilters, SearchResult, ServerError, type SyncLog, type SyncSchedule, type UsageHistoryItem, type UsageSnapshot, ValidationError, type Webhook, type WebhookEvent, version };

package/dist/index.d.ts

@@ -22,6 +22,9 @@ declare class Dataset {
     readonly slug: string;
     readonly status: string;
     readonly rowCount: number;
+    readonly piiMasked: boolean;
+    readonly piiFindingsCount: number;
+    readonly piiTypeSummary: Record<string, number>;
     readonly createdAt: string;
     readonly availableFormats: string[];
     private readonly _transport;
@@ -31,6 +34,9 @@ declare class Dataset {
         slug: string;
         status: string;
         rowCount: number;
+        piiMasked: boolean;
+        piiFindingsCount: number;
+        piiTypeSummary: Record<string, number>;
         createdAt: string;
         availableFormats: string[];
         _transport: Transport;
@@ -99,6 +105,8 @@ declare class Job {
     /** Needed by buildDataset() — POST /datasets/build-from-execution/{executionId}. */
     readonly executionId: number | null;
     readonly hasDataset: boolean;
+    /** Set from `dataset_summary.dataset_id` on a completed dataset_build job's response. */
+    readonly datasetId: number | null;
     /**
      * True when the underlying pipeline execution completed but one or more
      * non-critical steps failed (e.g. structured extraction couldn't find a
@@ -110,6 +118,9 @@ declare class Job {
      */
     readonly degraded: boolean;
     readonly failureReason: string | null;
+    readonly piiMasked: boolean;
+    readonly piiFindingsCount: number;
+    readonly piiTypeSummary: Record<string, number>;
     private readonly _transport;
     constructor(data: {
         id: string;
@@ -119,8 +130,12 @@ declare class Job {
         documentId: string | null;
         executionId: number | null;
         hasDataset: boolean;
+        datasetId: number | null;
         degraded: boolean;
         failureReason: string | null;
+        piiMasked: boolean;
+        piiFindingsCount: number;
+        piiTypeSummary: Record<string, number>;
         _transport: Transport;
     });
     static fromDict(data: Record<string, unknown>, transport: Transport): Job;
@@ -603,6 +618,6 @@ declare class FlexOrchReader {
     toString(): string;
 }
 
-declare const version = "0.3.0";
+declare const version = "0.3.2";
 
 export { AuthError, Connector, type ConnectorTestResult, type ConnectorType, Dataset, Document, type ExportFormat, FlexOrchClient, type FlexOrchClientOptions, FlexOrchError, FlexOrchReader, FlexOrchRetriever, Job, JobFailedError, type JobFeedback, JobTimeoutError, NotFoundError, type QualityTrendItem, QuotaError, RAGDocument, RateLimitError, type RateLimitStatus, type ReaderLoadOptions, type RetrieverOptions, type S3ConnectorConfig, type SearchFilters, SearchResult, ServerError, type SyncLog, type SyncSchedule, type UsageHistoryItem, type UsageSnapshot, ValidationError, type Webhook, type WebhookEvent, version };

package/dist/index.js

@@ -1,6 +1,6 @@
 import {
   Dataset
-} from "./chunk-4KCMMRD7.js";
+} from "./chunk-U2CE5GVG.js";
 
 // src/errors.ts
 var FlexOrchError = class extends Error {
@@ -123,7 +123,7 @@ var Transport = class {
     this.fetchFn = fetchFn ?? globalThis.fetch.bind(globalThis);
     this.defaultHeaders = {
       "X-API-KEY": apiKey,
-      "User-Agent": "flexorch-sdk-js/0.3.0"
+      "User-Agent": "flexorch-sdk-js/0.3.2"
     };
   }
   url(path, params) {
@@ -216,6 +216,8 @@ var Job = class _Job {
   /** Needed by buildDataset() — POST /datasets/build-from-execution/{executionId}. */
   executionId;
   hasDataset;
+  /** Set from `dataset_summary.dataset_id` on a completed dataset_build job's response. */
+  datasetId;
   /**
    * True when the underlying pipeline execution completed but one or more
    * non-critical steps failed (e.g. structured extraction couldn't find a
@@ -227,6 +229,9 @@ var Job = class _Job {
    */
   degraded;
   failureReason;
+  piiMasked;
+  piiFindingsCount;
+  piiTypeSummary;
   _transport;
   constructor(data) {
     this.id = data.id;
@@ -236,13 +241,19 @@ var Job = class _Job {
     this.documentId = data.documentId;
     this.executionId = data.executionId;
     this.hasDataset = data.hasDataset;
+    this.datasetId = data.datasetId;
     this.degraded = data.degraded;
     this.failureReason = data.failureReason;
+    this.piiMasked = data.piiMasked;
+    this.piiFindingsCount = data.piiFindingsCount;
+    this.piiTypeSummary = data.piiTypeSummary;
     this._transport = data._transport;
   }
   static fromDict(data, transport) {
     const executionSummary = data["execution_summary"];
     const processingSummary = data["processing_summary"];
+    const datasetSummary = data["dataset_summary"];
+    const privacy = executionSummary?.["privacy"];
     let quality = data["quality"];
     if (!quality && processingSummary) {
       quality = processingSummary["quality"];
@@ -256,9 +267,22 @@ var Job = class _Job {
       qualityScore: quality["score"] ?? null,
       documentId: data["document_id"] ?? null,
       executionId,
-      hasDataset: Boolean(data["has_dataset"] ?? processingSummary?.["has_dataset"] ?? false),
+      // dataset_summary is only present on a completed dataset_build job's
+      // response — neither has_dataset nor processing_summary is ever set
+      // for that job type, so without this .dataset() always returned null
+      // for the job.buildDataset().wait().dataset() chain even though the
+      // dataset had been built successfully.
+      hasDataset: Boolean(data["has_dataset"] ?? processingSummary?.["has_dataset"] ?? Boolean(datasetSummary) ?? false),
+      datasetId: datasetSummary?.["dataset_id"] ?? null,
       degraded: Boolean(executionSummary?.["degraded"] ?? false),
       failureReason: data["failure_reason"] ?? null,
+      // execution_summary.privacy — computed fresh on every GET /jobs/{id}
+      // read, not frozen at job-completion time, so this works even for
+      // jobs older than this field. Defaults for jobs with no execution
+      // (e.g. dataset_build) or against an older API version.
+      piiMasked: Boolean(privacy?.["privacy_applied"] ?? false),
+      piiFindingsCount: Number(privacy?.["pii_findings_count"] ?? 0),
+      piiTypeSummary: privacy?.["pii_type_summary"] ?? {},
       _transport: transport
     });
   }
@@ -284,13 +308,17 @@ var Job = class _Job {
     throw new JobTimeoutError(this.id, timeout);
   }
   async dataset() {
+    const { Dataset: Dataset2 } = await import("./dataset-UGUUKKH3.js");
+    if (this.datasetId !== null) {
+      const data2 = await this._transport.get(`/datasets/${this.datasetId}`);
+      return Dataset2.fromDict(data2, this._transport);
+    }
     if (!this.hasDataset) return null;
     const data = await this._transport.get("/datasets", {
       job_id: this.id
     });
     const items = data["items"] ?? [];
     if (items.length === 0) return null;
-    const { Dataset: Dataset2 } = await import("./dataset-E7EXJETI.js");
     return Dataset2.fromDict(items[0], this._transport);
   }
   /**
@@ -1068,7 +1096,7 @@ var FlexOrchReader = class {
 };
 
 // src/index.ts
-var version = "0.3.0";
+var version = "0.3.2";
 export {
   AuthError,
   Connector,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "flexorch-sdk",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "TypeScript/JavaScript SDK for the FlexOrch API — process documents, build LLM-ready datasets",
   "type": "module",
   "main": "./dist/index.cjs",