fix(tests): stabilize OCR extraction tests and manage GPU containers

test/helpers/docker.ts

@@ -2,10 +2,6 @@ import { execSync } from 'child_process';
 
 // Project container names (only manage these)
 const PROJECT_CONTAINERS = [
-  'paddleocr-vl-test',
-  'paddleocr-vl-gpu-test',
-  'paddleocr-vl-cpu-test',
-  'paddleocr-vl-full-test',
   'minicpm-test',
   'nanonets-test',
 ];
@@ -24,30 +20,6 @@ export interface IImageConfig {
 }
 
 export const IMAGES = {
-  paddleocrVlGpu: {
-    name: 'paddleocr-vl-gpu',
-    dockerfile: 'Dockerfile_paddleocr_vl_gpu',
-    buildContext: '.',
-    containerName: 'paddleocr-vl-test',
-    ports: ['8000:8000'],
-    volumes: ['ht-huggingface-cache:/root/.cache/huggingface'],
-    gpus: true,
-    healthEndpoint: 'http://localhost:8000/health',
-    healthTimeout: 300000, // 5 minutes for model loading
-  } as IImageConfig,
-
-  paddleocrVlCpu: {
-    name: 'paddleocr-vl-cpu',
-    dockerfile: 'Dockerfile_paddleocr_vl_cpu',
-    buildContext: '.',
-    containerName: 'paddleocr-vl-test',
-    ports: ['8000:8000'],
-    volumes: ['ht-huggingface-cache:/root/.cache/huggingface'],
-    gpus: false,
-    healthEndpoint: 'http://localhost:8000/health',
-    healthTimeout: 300000,
-  } as IImageConfig,
-
   minicpm: {
     name: 'minicpm45v',
     dockerfile: 'Dockerfile_minicpm45v_gpu',
@@ -60,22 +32,6 @@ export const IMAGES = {
     healthTimeout: 120000,
   } as IImageConfig,
 
-  // Full PaddleOCR-VL pipeline with PP-DocLayoutV2 + structured JSON output
-  paddleocrVlFull: {
-    name: 'paddleocr-vl-full',
-    dockerfile: 'Dockerfile_paddleocr_vl_full',
-    buildContext: '.',
-    containerName: 'paddleocr-vl-full-test',
-    ports: ['8000:8000'],
-    volumes: [
-      'ht-huggingface-cache:/root/.cache/huggingface',
-      'ht-paddleocr-cache:/root/.paddleocr',
-    ],
-    gpus: true,
-    healthEndpoint: 'http://localhost:8000/health',
-    healthTimeout: 600000, // 10 minutes for model loading (vLLM + PP-DocLayoutV2)
-  } as IImageConfig,
-
   // Nanonets-OCR-s - Document OCR optimized VLM (Qwen2.5-VL-3B fine-tuned)
   nanonetsOcr: {
     name: 'nanonets-ocr',
@@ -140,7 +96,7 @@ export function removeContainer(containerName: string): void {
 }
 
 /**
- * Stop all project containers that conflict with the required one
+ * Stop all project containers that conflict with the required one (port-based)
  */
 export function stopConflictingContainers(requiredContainer: string, requiredPort: string): void {
   // Stop project containers using the same port
@@ -158,6 +114,24 @@ export function stopConflictingContainers(requiredContainer: string, requiredPor
   }
 }
 
+/**
+ * Stop all GPU-consuming project containers (for GPU memory management)
+ * This ensures GPU memory is freed before starting a new GPU service
+ */
+export function stopAllGpuContainers(exceptContainer?: string): void {
+  for (const container of PROJECT_CONTAINERS) {
+    if (container === exceptContainer) continue;
+
+    if (isContainerRunning(container)) {
+      console.log(`[Docker] Stopping GPU container: ${container}`);
+      exec(`docker stop ${container}`, true);
+      // Give the GPU a moment to free memory
+    }
+  }
+  // Brief pause to allow GPU memory to be released
+  execSync('sleep 2');
+}
+
 /**
  * Build a Docker image
  */
@@ -234,6 +208,11 @@ export async function ensureService(config: IImageConfig): Promise<boolean> {
     buildImage(config);
   }
 
+  // For GPU services, stop ALL other GPU containers to free GPU memory
+  if (config.gpus) {
+    stopAllGpuContainers(config.containerName);
+  }
+
   // Stop conflicting containers on the same port
   const mainPort = config.ports[0];
   stopConflictingContainers(config.containerName, mainPort);
@@ -254,21 +233,7 @@ export async function ensureService(config: IImageConfig): Promise<boolean> {
 }
 
 /**
- * Ensure PaddleOCR-VL GPU service is running
- */
-export async function ensurePaddleOcrVlGpu(): Promise<boolean> {
-  return ensureService(IMAGES.paddleocrVlGpu);
-}
-
-/**
- * Ensure PaddleOCR-VL CPU service is running
- */
-export async function ensurePaddleOcrVlCpu(): Promise<boolean> {
-  return ensureService(IMAGES.paddleocrVlCpu);
-}
-
-/**
- * Ensure MiniCPM service is running
+ * Ensure MiniCPM service is running (Ollama with GPU)
  */
 export async function ensureMiniCpm(): Promise<boolean> {
   return ensureService(IMAGES.minicpm);
@@ -286,30 +251,6 @@ export function isGpuAvailable(): boolean {
   }
 }
 
-/**
- * Ensure PaddleOCR-VL service (auto-detect GPU/CPU)
- */
-export async function ensurePaddleOcrVl(): Promise<boolean> {
-  if (isGpuAvailable()) {
-    console.log('[Docker] GPU detected, using GPU image');
-    return ensurePaddleOcrVlGpu();
-  } else {
-    console.log('[Docker] No GPU detected, using CPU image');
-    return ensurePaddleOcrVlCpu();
-  }
-}
-
-/**
- * Ensure PaddleOCR-VL Full Pipeline service (PP-DocLayoutV2 + structured output)
- * This is the recommended service for production use - outputs structured JSON/Markdown
- */
-export async function ensurePaddleOcrVlFull(): Promise<boolean> {
-  if (!isGpuAvailable()) {
-    console.log('[Docker] WARNING: Full pipeline requires GPU, but none detected');
-  }
-  return ensureService(IMAGES.paddleocrVlFull);
-}
-
 /**
  * Ensure an Ollama model is pulled and available
  * Uses the MiniCPM container (which runs Ollama) to pull the model