#!/usr/bin/env python3
"""
调试脚本：使用真实数据验证 Prompt 构建
完整展示发送给 LLM 的文本
"""
import sys
import json
from pathlib import Path
from loguru import logger

# 添加 src 到路径
sys.path.insert(0, '.')

from src.manifest_manager import ManifestManager
from src.text_processor import TextProcessor
from src.llm_client import LLMClient
from src.utils import load_config

# 配置日志到文件，避免控制台刷屏
logger.remove()
logger.add("debug_prompt.log", level="DEBUG")
logger.add(sys.stdout, level="INFO")

def debug_prompt():
    print("=== 1. 加载配置 ===")
    try:
        config = load_config()
        # 确保 LLM 配置存在 (Mock if needed for init)
        if 'llm' not in config:
            if 'v3' in config['providers']:
                config['llm'] = config['providers']['v3']
            else:
                config['llm'] = {"api_key": "dummy", "models": {"fast": "dummy"}}
                
    except Exception as e:
        print(f"Config load failed: {e}")
        return

    print("=== 2. 加载真实 Manifest ===")
    # 查找 cache/manifests 下的 json 文件
    manifest_dir = Path("cache/manifests")
    if not manifest_dir.exists():
        print("Error: cache/manifests directory not found")
        return
        
    manifest_files = list(manifest_dir.glob("*_manifest.json"))
    if not manifest_files:
        print("Error: No manifest file found in cache/manifests")
        return
        
    manifest_path = manifest_files[0]
    print(f"Using manifest: {manifest_path}")
    
    manifest = ManifestManager(str(manifest_path))
    if not manifest.load():
        print("Failed to load manifest")
        return
        
    print(f"Loaded {len(manifest.get_items())} items")
    
    # 获取 Pending items (模拟真实流程)
    pending = manifest.get_items(status="pending")
    if not pending:
        print("No pending items found. Using ALL items for debug.")
        items_to_process = manifest.get_items()
    else:
        items_to_process = pending
        
    # 找到几个包含占位符的 item 用于验证
    target_items = []
    for item in items_to_process:
        if item.placeholder_map and len(item.placeholder_map) > 0:
            target_items.append(item)
            if len(target_items) >= 5: # 取前5个
                break
    
    if not target_items:
        print("No items with placeholders found!")
        return
        
    print(f"Selected {len(target_items)} items with placeholders for verification")
    for item in target_items:
        print(f"  - {item.global_id}: twp length={len(item.text_with_placeholders or '')}")

    print("\n=== 3. 生成 Prompt (Mode: Chinese) ===")
    client = LLMClient(config)
    
    # 只为这几个 item 生成 prompt
    prompt = client._build_prompt(target_items, mode="chinese")
    
    print("\n" + "="*40)
    print("FULL PROMPT CONTENT (Snippet):")
    print("="*40)
    print(prompt)
    print("="*40 + "\n")
    
    print("\n=== 4. 关键验证 ===")
    placeholders_found = prompt.count('φ')
    print(f"Total 'φ' symbols in prompt: {placeholders_found}")
    
    for item in target_items:
        if item.text_with_placeholders and 'φ' in item.text_with_placeholders:
            # 检查这个 item 的 ID 是否在 prompt 中
            in_prompt = item.global_id in prompt
            # 检查这个 item 的占位符是否在 prompt 中
            # 注意：如果占位符是 φ1φ，我们检查 'φ1φ' 是否在 prompt 中
            # 这里简单做，假设 text_with_placeholders 应该完整出现在 prompt 中 (忽略空白差异)
            import re
            normalized_twp = re.sub(r'\s+', '', item.text_with_placeholders)
            normalized_prompt = re.sub(r'\s+', '', prompt)
            
            content_in_prompt = normalized_twp in normalized_prompt
            
            print(f"Item {item.global_id}:")
            print(f"  In prompt ID: {in_prompt}")
            print(f"  Original twp: {repr(item.text_with_placeholders)}")
            print(f"  Content match (ignoring whitespace): {content_in_prompt}")

if __name__ == "__main__":
    debug_prompt()