ArtiAgent - DefectDiffu/src/batch_agent_orchestrator.py

"""
Batch Agent Orchestrator — DefectDiffu Edition

Usage:
    # Scenario B: Global description for entire folder
    python batch_agent_orchestrator.py \
        --input-dir "C:/TestingImage/vcsel_batch" \
        --product-desc "VCSEL laser diode with emission aperture and surrounding mesa" \
        --output-dir "C:/AgentOutput" \
        --defectdiffu-ckpt "./defectdiffu_ckpt.pt" \
        --vae-path "./sd-vae-ft-mse" \
        --device cuda

    # Scenario A: CSV manifest
    python batch_agent_orchestrator.py \\
        --input-dir "C:/TestingImage" \\
        --manifest "C:/products.csv" \\
        --output-dir "C:/AgentOutput" \\
        --defectdiffu-ckpt "./defectdiffu_ckpt.pt" \\
        --vae-path "./sd-vae-ft-mse"

    # Mode 3: Infer from folder names
    python batch_agent_orchestrator.py \\
        --input-dir "C:/TestingImage" \\
        --output-dir "C:/AgentOutput" \\
        --defectdiffu-ckpt "./defectdiffu_ckpt.pt" \\
        --vae-path "./sd-vae-ft-mse"
"""

import os
import sys
import csv
import json
import argparse
import traceback
from pathlib import Path
from datetime import datetime
from typing import Dict, List, Optional
from tqdm import tqdm

import numpy as np
from PIL import Image

SCRIPT_DIR = Path(__file__).parent
if str(SCRIPT_DIR) not in sys.path:
    sys.path.insert(0, str(SCRIPT_DIR))

from artiagent_orchestrator import ArtiAgentOrchestrator


def infer_product_from_path(image_path: Path) -> str:
    """Infer product description from folder structure or filename."""
    parent = image_path.parent.name.lower()
    if parent and parent not in ['.', '', 'images', 'imgs', 'data', 'input']:
        return parent.replace('_', ' ').replace('-', ' ')
    stem = image_path.stem.lower()
    for keyword in ['vcsel', 'lens', 'die', 'photodiode', 'sensor', 'chip', 'led', 'laser', 'optical']:
        if keyword in stem:
            return keyword
    return "electronic component"


def load_manifest(manifest_path: str) -> Dict[str, str]:
    """Load CSV manifest mapping image paths to product descriptions."""
    manifest = {}
    with open(manifest_path, 'r', encoding='utf-8') as f:
        reader = csv.DictReader(f)
        for row in reader:
            img_path = row.get('image_path', row.get('path', row.get('image', ''))).strip()
            desc = row.get('product_description', row.get('description', row.get('product', ''))).strip()
            if img_path and desc:
                manifest[Path(img_path).resolve()] = desc
    print(f"[Batch] Loaded manifest with {len(manifest)} entries")
    return manifest


def discover_images(input_dir: str, extensions=('.png', '.jpg', '.jpeg', '.bmp', '.tif', '.tiff')) -> List[Path]:
    """Recursively discover all images in input directory."""
    input_path = Path(input_dir)
    images = []
    for ext in extensions:
        images.extend(input_path.rglob(f"*{ext}"))
        images.extend(input_path.rglob(f"*{ext.upper()}"))
    unique = sorted(set(images))
    print(f"[Batch] Discovered {len(unique)} images in {input_dir}")
    return unique


def run_batch(
    input_dir: str,
    output_dir: str,
    defectdiffu_ckpt: str,
    vae_path: str,
    product_desc: Optional[str] = None,
    manifest_path: Optional[str] = None,
    defect_type: Optional[str] = None,
    max_defects_per_image: int = 3,
    device: str = 'cuda',
    vlm_model: str = 'gemma3:12b',
    image_size: int = 512,
    num_steps: int = 50,
    resume: bool = False,
    save_failed: bool = True
):
    """Run agent orchestrator over all images in input directory."""

    timestamp = datetime.now().strftime("%Y%m%d_%H%M")
    output_path = Path(output_dir) / timestamp
    output_path.mkdir(parents=True, exist_ok=True)
    print(f"[Batch] Output folder: {output_path}")

    manifest = {}
    if product_desc and not manifest_path:
        print(f"[Batch] Scenario B Active: Global Description = '{product_desc}'")
    elif manifest_path and os.path.exists(manifest_path):
        manifest = load_manifest(manifest_path)
        print(f"[Batch] Scenario A Active: CSV Manifest ({len(manifest)} entries)")
    elif product_desc:
        print(f"[Batch] Scenario B Active (Fallback): Global Description = '{product_desc}'")
    else:
        print("[Batch] Scenario C Active: Folder Name Inference (no description provided)")

    images = discover_images(input_dir)
    if not images:
        print("[Batch] No images found. Exiting.")
        return

    progress_file = output_path / "batch_progress.json"
    processed_ids = set()
    if resume and progress_file.exists():
        with open(progress_file, 'r') as f:
            progress = json.load(f)
            processed_ids = set(progress.get('processed_paths', []))
        print(f"[Batch] Resuming: {len(processed_ids)} images already processed")

    orchestrator = ArtiAgentOrchestrator(
        device=device,
        output_dir=str(output_path),
        vlm_model=vlm_model,
        defectdiffu_ckpt=defectdiffu_ckpt,
        vae_path=vae_path,
        image_size=image_size,
        num_steps=num_steps
    )

    stats = {
        'total': len(images),
        'processed': 0,
        'successful': 0,
        'failed': 0,
        'defects_generated': 0,
        'start_time': datetime.now().isoformat(),
        'processed_paths': [],
        'failed_images': []
    }

    if resume:
        images = [img for img in images if str(img.resolve()) not in processed_ids]

    print(f"[Batch] Processing {len(images)} images...")
    print(f"[Batch] Max defects per image: {max_defects_per_image}")
    print("=" * 70)

    for img_path in tqdm(images, desc="Agent Batch Processing"):
        img_key = str(img_path.resolve())

        try:
            if img_key in manifest:
                desc = manifest[img_key]
                source = "manifest"
            elif product_desc:
                desc = product_desc
                source = "global"
            else:
                desc = infer_product_from_path(img_path)
                source = "inferred"

            print(f"\\n[Batch] Processing: {img_path.name} | desc source: {source}")
            if source in ['inferred', 'global']:
                print(f"[Batch] Using description: '{desc}'")

            result = orchestrator.run(
                product_description=desc,
                image_path=str(img_path),
                max_defects=max_defects_per_image,
                defect_type=defect_type
            )

            successful_defects = sum(1 for r in result['results'] if r['success'])

            stats['processed'] += 1
            stats['successful'] += 1 if successful_defects > 0 else 0
            stats['defects_generated'] += successful_defects
            stats['processed_paths'].append(img_key)

            if successful_defects == 0:
                stats['failed'] += 1
                stats['failed_images'].append({'path': img_key, 'reason': 'no_defects_generated'})

            if stats['processed'] % 5 == 0:
                with open(progress_file, 'w') as f:
                    json.dump(stats, f, indent=2)

        except Exception as e:
            stats['failed'] += 1
            stats['failed_images'].append({'path': img_key, 'reason': str(e)})
            print(f"[Batch] FAILED: {img_path.name} -> {str(e)}")
            if save_failed:
                fail_dir = output_path / "_failed" / img_path.stem
                fail_dir.mkdir(parents=True, exist_ok=True)
                with open(fail_dir / "error.txt", 'w') as f:
                    f.write(traceback.format_exc())

    with open(progress_file, 'w') as f:
        json.dump(stats, f, indent=2)

    orchestrator.cleanup()

    elapsed = (datetime.now() - datetime.fromisoformat(stats['start_time'])).total_seconds()
    hours = int(elapsed // 3600)
    minutes = int((elapsed % 3600) // 60)
    seconds = int(elapsed % 60)

    print("\\n" + "=" * 70)
    print("BATCH ORCHESTRATION COMPLETE")
    print("=" * 70)
    print(f"Total images:      {stats['total']}")
    print(f"Processed:         {stats['processed']}")
    print(f"Successful:        {stats['successful']}")
    print(f"Failed:            {stats['failed']}")
    print(f"Defects generated: {stats['defects_generated']}")
    print(f"Total time:        {hours}h {minutes}m {seconds}s")
    print(f"Output directory:  {output_path}")
    print("=" * 70)


def main():
    parser = argparse.ArgumentParser(description='Batch Agent-Driven Defect Generation (DefectDiffu)')

    # Input / Output
    parser.add_argument('--input-dir', required=True, help='Directory containing clean product images')
    parser.add_argument('--output-dir', required=True, help='Output directory for all defect images')

    # DefectDiffu model paths (REQUIRED)
    parser.add_argument('--defectdiffu-ckpt', required=True,
                        help='Path to trained DefectDiffu checkpoint')
    parser.add_argument('--vae-path', required=True,
                        help='Path to Stable Diffusion VAE (e.g. stabilityai/sd-vae-ft-mse)')

    # Description sources
    parser.add_argument('--product-desc', default=None,
                        help='[Scenario B] ONE global description applied to ALL images in the folder')
    parser.add_argument('--manifest', default=None,
                        help='[Scenario A] CSV manifest with columns: image_path,product_description')

    # Defect control
    parser.add_argument('--defect-type', default=None,
                        help='Specify defect type for batch generation (e.g., bubble, scratch)')
    parser.add_argument('--max-defects-per-image', type=int, default=3,
                        help='Maximum defects to generate per image (default: 3)')

    # Generation control
    parser.add_argument('--device', default='cuda', help='Device (cuda/cpu)')
    parser.add_argument('--vlm-model', default='gemma3:12b', help='Local VLM model')
    parser.add_argument('--image-size', type=int, default=512,
                        help='DefectDiffu generation resolution (default: 512)')
    parser.add_argument('--num-steps', type=int, default=50,
                        help='Denoising steps for DefectDiffu (default: 50)')
    parser.add_argument('--resume', action='store_true', help='Resume from previous batch run')
    parser.add_argument('--no-save-failed', action='store_true', help='Do not save failed case logs')

    args = parser.parse_args()

    run_batch(
        input_dir=args.input_dir,
        output_dir=args.output_dir,
        defectdiffu_ckpt=args.defectdiffu_ckpt,
        vae_path=args.vae_path,
        product_desc=args.product_desc,
        manifest_path=args.manifest,
        defect_type=args.defect_type,
        max_defects_per_image=args.max_defects_per_image,
        device=args.device,
        vlm_model=args.vlm_model,
        image_size=args.image_size,
        num_steps=args.num_steps,
        resume=args.resume,
        save_failed=not args.no_save_failed
    )


if __name__ == "__main__":
    main()