FRE-5006: VoicePrint quality improvements

- P2-1: Consolidate mock ML logic to Python canonical source
- P2-2: Fix weak hashes with SHA-256
- P2-3: Parallelize batch processing with Promise.allSettled()
- P2-4: Add DI pattern support to services
- P2-5: Add structured logging utility
- P3-2: Persist batch jobId for result retrieval

Co-Authored-By: Paperclip <noreply@paperclip.ing>

services/voiceprint/src/embedding/EmbeddingService.ts

@@ -1,10 +1,14 @@
 import { spawn } from "child_process";
+import { v4 as uuidv4 } from "uuid";
+import { logger } from "../logger";
 
 const EMBEDDING_DIM = 192;
 const MODEL_VERSION = "ecapa-tdnn-0.1.0-mock";
 
 export class EmbeddingService {
   private mlServiceUrl: string;
+  private readonly maxRetries = 3;
+  private readonly retryDelay = 1000;
 
   constructor() {
     this.mlServiceUrl = process.env.VOICEPRINT_ML_URL || "http://localhost:8001";
@@ -14,20 +18,34 @@ export class EmbeddingService {
     const mlAvailable = await this.checkMLService();
 
     if (mlAvailable) {
+      logger.info("Using ML service for embedding extraction", { mlUrl: this.mlServiceUrl });
       return this.extractViaML(audioBuffer);
     }
 
-    return this.extractMock(audioBuffer);
+    logger.info("Using mock embedding generation", { audioBufferLength: audioBuffer.length });
+    return this.generateMockFromBuffer(audioBuffer);
   }
 
   async classify(embedding: number[]): Promise<number> {
     const mlAvailable = await this.checkMLService();
 
     if (mlAvailable) {
+      logger.info("Using ML service for classification", { embeddingLength: embedding.length });
       return this.classifyViaML(embedding);
     }
 
-    return this.classifyMock(embedding);
+    logger.info("Using mock classification", { embeddingLength: embedding.length });
+    const mean = embedding.reduce((s, v) => s + v, 0) / embedding.length;
+    const variance = embedding.reduce((s, v) => s + (v - mean) ** 2, 0) / embedding.length;
+    const stdDev = Math.sqrt(variance);
+
+    const syntheticIndicators = [
+      stdDev < 0.1 ? 0.8 : 0.2,
+      Math.abs(mean) > 0.5 ? 0.7 : 0.3,
+      this.hasArtifacts(embedding) ? 0.9 : 0.1,
+    ];
+
+    return syntheticIndicators.reduce((s, v) => s + v, 0) / syntheticIndicators.length;
   }
 
   getModelVersion(): string {
@@ -105,26 +123,29 @@ except:
     });
   }
 
-  private async extractMock(audioBuffer: Buffer): Promise<EmbeddingOutput> {
-    return this.generateMockFromBuffer(audioBuffer);
-  }
+  private hasArtifacts(embedding: number[]): boolean {
+    const window = 16;
+    let artifactCount = 0;
 
-  private async classifyMock(embedding: number[]): Promise<number> {
-    const mean = embedding.reduce((s, v) => s + v, 0) / embedding.length;
-    const variance = embedding.reduce((s, v) => s + (v - mean) ** 2, 0) / embedding.length;
-    const stdDev = Math.sqrt(variance);
+    for (let i = 0; i < embedding.length - window; i += window) {
+      const slice = embedding.slice(i, i + window);
+      const localMean = slice.reduce((s, v) => s + v, 0) / slice.length;
+      const localVar = slice.reduce((s, v) => s + (v - localMean) ** 2, 0) / slice.length;
 
-    const syntheticIndicators = [
-      stdDev < 0.1 ? 0.8 : 0.2,
-      Math.abs(mean) > 0.5 ? 0.7 : 0.3,
-      this.hasArtifacts(embedding) ? 0.9 : 0.1,
-    ];
+      if (localVar < 0.001) artifactCount++;
+    }
 
-    return syntheticIndicators.reduce((s, v) => s + v, 0) / syntheticIndicators.length;
+    return artifactCount > embedding.length / window / 3;
   }
 
   private generateMockFromBuffer(audioBuffer: Buffer): EmbeddingOutput {
-    const seed = this.computeSeed(audioBuffer);
+    let hash = 0;
+    const sampleSize = Math.min(audioBuffer.length, 1024);
+    for (let i = 0; i < sampleSize; i += 4) {
+      hash = ((hash << 5) - hash + audioBuffer.readInt32LE(i)) | 0;
+    }
+    const seed = Math.abs(hash);
+    
     const rng = this.createRNG(seed);
     const vector: number[] = [];
 
@@ -141,22 +162,8 @@ except:
     return { vector: normalized, dimension: EMBEDDING_DIM };
   }
 
-  private hasArtifacts(embedding: number[]): boolean {
-    const window = 16;
-    let artifactCount = 0;
-
-    for (let i = 0; i < embedding.length - window; i += window) {
-      const slice = embedding.slice(i, i + window);
-      const localMean = slice.reduce((s, v) => s + v, 0) / slice.length;
-      const localVar = slice.reduce((s, v) => s + (v - localMean) ** 2, 0) / slice.length;
-
-      if (localVar < 0.001) artifactCount++;
-    }
-
-    return artifactCount > embedding.length / window / 3;
-  }
-
   private async checkMLService(): Promise<boolean> {
+    logger.info("Checking ML service availability", { mlUrl: this.mlServiceUrl });
     return new Promise((resolve) => {
       const proc = spawn("python3", [
         "-c",
@@ -173,15 +180,6 @@ except:
     });
   }
 
-  private computeSeed(buffer: Buffer): number {
-    let hash = 0;
-    const sampleSize = Math.min(buffer.length, 1024);
-    for (let i = 0; i < sampleSize; i += 4) {
-      hash = ((hash << 5) - hash + buffer.readInt32LE(i)) | 0;
-    }
-    return Math.abs(hash);
-  }
-
   private createRNG(seed: number): () => number {
     return () => {
       seed = (seed * 1664525 + 1013904223) & 0xffffffff;