cfc/cfc-langgraph/app/agents/report_parse_agent.py

"""
报告解析 Agent：算法解析 + LLM 兜底
"""
import json
import logging
from typing import Optional

from app.config import settings
from app.parsers.pdf_parser import parse_report_pdf_with_fallback

logger = logging.getLogger(__name__)

# 算法解析器使用中文键名（与 extract_full_report_v5.py 一致），
# Java 消费端期望英文键名；在此做双向映射，Java 读取英文键即可。
_CN_TO_EN_OVERVIEW: dict[str, str] = {
    '健康总分': 'overallScore',
    '菌群健康': 'gutHealthScore',
    '慢病控制': 'chronicDiseaseScore',
    '营养均衡': 'nutritionScore',
    '肠道菌群平衡': 'balanceScore',
    '菌群多样性': 'diversityScore',
    '有益菌': 'beneficialScore',
    '有害菌': 'harmfulScore',
    '核心菌属': 'coreGenusScore',
}


class ReportParseAgent:
    """报告解析 Agent"""

    def __init__(self):
        self.llm_api_key = getattr(settings, 'llm_api_key', '')

    @staticmethod
    def _normalize_overview_keys(result: dict) -> None:
        """将 overview 中的中文键名映射为英文键名（双向写入），兼容 Java 消费端。"""
        overview = result.get('overview')
        if not overview:
            return
        for _cn, _en in _CN_TO_EN_OVERVIEW.items():
            if _cn in overview and _en not in overview:
                overview[_en] = overview[_cn]

    async def parse(self, file_path: str) -> dict:
        """解析 PDF 报告，算法解析 + LLM 兜底"""
        # 1. 算法解析
        result = parse_report_pdf_with_fallback(file_path)
        logger.info("算法解析完成: format=%s, overview_keys=%d",
                     result.get('format'), len(result.get('overview', {})))

        # 1.5 归一化 overview 键名：中文 → 英文（Java 消费端兼容）
        self._normalize_overview_keys(result)

        # 2. 如果解析不完整，LLM 兜底
        if result.get('_parse_incomplete') or not result.get('disease_risks'):
            logger.info("算法解析不完整，尝试 LLM 兜底")
            llm_result = await self._parse_with_llm(file_path)
            if llm_result:
                # 合并 LLM 结果到算法结果上（LLM 覆盖缺失字段）
                for key in ['disease_risks', 'nutrition', 'amino_acids',
                            'vitamins', 'trace_elements', 'indicators']:
                    if key in llm_result and not result.get(key):
                        result[key] = llm_result[key]
                if llm_result.get('overview'):
                    for k, v in llm_result['overview'].items():
                        if k not in result.get('overview', {}):
                            result.setdefault('overview', {})[k] = v

        # 清理内部标记
        result.pop('_parse_incomplete', None)
        return result

    async def parse_generic(self, file_path: str, extra_context: Optional[dict] = None) -> dict:
        """通用报告 LLM 解析（不经过算法解析，直接走 LLM）"""
        try:
            from PyPDF2 import PdfReader
            reader = PdfReader(file_path)
            text = '\n'.join(page.extract_text() or '' for page in reader.pages)

            ctx_str = ""
            if extra_context:
                ctx_str = f"\n额外上下文：{json.dumps(extra_context, ensure_ascii=False)}"

            prompt = f"""你是一个通用报告解析专家。请从以下PDF文本中提取结构化数据，返回JSON格式。

报告文本内容：
{text[:12000]}{ctx_str}

请分析这份报告，推断它的类型和内容，然后按以下JSON Schema返回：
{{
    "reportType": "推断的报告类型名称",
    "reportTypeFamily": "报告家族分类（如: dan/cognitive/gut_flora/health_check/other）",
    "confidence": "high/medium/low",
    "summary": {{
        "personName": "姓名",
        "reportDate": "报告日期",
        "reportNumber": "报告编号",
        "overallScore": "总分（如果有）",
        "interpretation": "报告整体解读摘要"
    }},
    "indicators": [
        {{"name": "指标名称", "value": "数值", "category": "分类", "status": "状态"}}
    ],
    "sections": [
        {{"title": "段落标题", "content": "段落内容摘要", "items": [{{"name": "...", "value": "..."}}]}}
    ],
    "textFeatures": ["文本特征1", "文本特征2", ...]
}}

只返回JSON，不要其他文字。"""

            if self.llm_api_key:
                import httpx
                async with httpx.AsyncClient(timeout=120) as client:
                    resp = await client.post(
                        f"{settings.llm_base_url}/chat/completions",
                        json={
                            "model": settings.llm_model or "gpt-4o",
                            "messages": [{"role": "user", "content": prompt}],
                            "temperature": 0.1,
                        },
                        headers={"Authorization": f"Bearer {self.llm_api_key}"},
                    )
                    resp.raise_for_status()
                    data = resp.json()
                    content = data['choices'][0]['message']['content']
                    content = content.replace('```json', '').replace('```', '').strip()
                    return json.loads(content)
            else:
                logger.warning("LLM 未配置，返回空")
                return {"reportType": "unknown", "summary": {}, "indicators": [], "sections": []}
        except Exception as e:
            logger.error("通用LLM解析失败: %s", e)
            return {"reportType": "unknown", "error": str(e), "summary": {}, "indicators": [], "sections": []}

    async def _parse_with_llm(self, file_path: str) -> Optional[dict]:
        """LLM 兜底解析"""
        try:
            from PyPDF2 import PdfReader
            reader = PdfReader(file_path)
            text = '\n'.join(page.extract_text() or '' for page in reader.pages)

            # 构造 prompt
            prompt = f"""你是一个肠道菌群检测报告解析专家。请从以下PDF文本中提取结构化数据，返回JSON格式。

文本内容：
{text[:8000]}

请按以下JSON Schema返回：
{{
    "overview": {{ "person_name": "", "report_number": "", "age": 0, "gender": "male/female",
        "overallScore": 0, "gutHealthScore": 0, "chronicDiseaseScore": 0, "nutritionScore": 0,
        "gutAge": "", "gutType": "" }},
    "disease_risks": [{{"name": "", "value": "", "status": ""}}],
    "nutrition": [{{"name": "", "value": "", "status": ""}}],
    "amino_acids": [{{"name": "", "value": "", "status": ""}}],
    "vitamins": [{{"name": "", "value": "", "status": ""}}],
    "trace_elements": [{{"name": "", "value": "", "status": ""}}]
}}

只返回JSON，不要其他文字。"""

            if self.llm_api_key:
                # 调 OpenAI 兼容 API
                import httpx
                async with httpx.AsyncClient(timeout=60) as client:
                    resp = await client.post(
                        f"{settings.llm_base_url}/chat/completions",
                        json={
                            "model": settings.llm_model or "gpt-4o",
                            "messages": [{"role": "user", "content": prompt}],
                            "temperature": 0.1,
                        },
                        headers={"Authorization": f"Bearer {self.llm_api_key}"},
                    )
                    resp.raise_for_status()
                    data = resp.json()
                    content = data['choices'][0]['message']['content']
                    content = content.replace('```json', '').replace('```', '').strip()
                    return json.loads(content)
            else:
                logger.warning("LLM 未配置，跳过 LLM 兜底")
                return None
        except Exception as e:
            logger.warning("LLM 解析失败: %s", e)
            return None