auto-stock/backend/app/api/endpoints/mcp.py

"""
MCP 프록시 엔드포인트 + 공통 리스크 평가 유틸리티

이슈 4 - request_mcp_risk_assessment():
    auto/day 스케줄러 양쪽에서 재사용 가능한 공통 RISK_ASSESSMENT 함수.
    호출부는 trade_plan / portfolio / signals 세 dict를 넘긴다.

이슈 6 - httpx.AsyncClient 싱글톤:
    요청마다 클라이언트를 생성/소멸하지 않는다.
    lifespan에서 init_http_client() → 사용 → close_http_client() 순서로 호출.
"""
from fastapi import APIRouter, HTTPException
from typing import Dict, Any, Optional, Tuple
from pydantic import BaseModel
import httpx
import logging
import time

from app.core.config import settings

logger = logging.getLogger(__name__)
router = APIRouter()


# ─── httpx 싱글톤 클라이언트 ──────────────────────────────────────────
_http_client: Optional[httpx.AsyncClient] = None


def _mcp_default_headers() -> dict:
    """MCP 서버 인증용 기본 헤더. MCP_API_KEY가 설정되어 있으면 X-API-Key 포함."""
    headers: dict = {}
    if settings.MCP_API_KEY:
        headers["X-API-Key"] = settings.MCP_API_KEY
    return headers


async def init_http_client() -> None:
    """lifespan 시작 시 한 번만 호출. keepalive 연결 풀 설정."""
    global _http_client
    _http_client = httpx.AsyncClient(
        timeout=httpx.Timeout(connect=5.0, read=60.0, write=10.0, pool=5.0),
        limits=httpx.Limits(max_keepalive_connections=5, max_connections=10),
        headers=_mcp_default_headers(),
    )
    logger.info("MCP httpx.AsyncClient initialized (api_key=%s)", "set" if settings.MCP_API_KEY else "none")


async def close_http_client() -> None:
    """lifespan 종료 시 한 번만 호출."""
    global _http_client
    if _http_client is not None:
        await _http_client.aclose()
        _http_client = None
        logger.info("🔒 MCP httpx.AsyncClient closed")


def get_http_client() -> httpx.AsyncClient:
    """공유 클라이언트 반환. 초기화 전 접근 시 RuntimeError."""
    if _http_client is None:
        raise RuntimeError(
            "http_client not initialized — call init_http_client() in lifespan"
        )
    return _http_client


# ─── fail-open 카운터 ─────────────────────────────────────────────────
_fail_open_count: int = 0
_FAIL_OPEN_WARN_THRESHOLD: int = 5  # 연속 N회 초과 시 경고 로그

# ─── RISK_ASSESSMENT 결과 캐시 (MCP_RISK_CACHE_TTL>0 일 때만) ────────────
# 스케줄러가 매 사이클(60s/30s) 같은 종목셋으로 재요청하는 AI 호출을 줄인다.
_risk_cache: Dict[str, Tuple[float, bool, str]] = {}  # key → (expires_at, approve, reason)


def _risk_cache_key(trade_plan: Dict[str, Any]) -> str:
    stocks = trade_plan.get("top_stocks") or []
    codes = sorted(
        str(s.get("stock_code", s) if isinstance(s, dict) else s) for s in stocks
    )
    if not codes and trade_plan.get("stock_code"):
        codes = [str(trade_plan["stock_code"])]
    return f"{trade_plan.get('strategy', '')}:{trade_plan.get('action', '')}:{','.join(codes)}"


# ─── 공통 리스크 평가 함수 ────────────────────────────────────────────
async def request_mcp_risk_assessment(
    trade_plan: Dict[str, Any],
    portfolio: Dict[str, Any],
    signals: Dict[str, Any],
) -> Tuple[bool, str]:
    """MCP RISK_ASSESSMENT 호출 — auto/day 스케줄러 공통 진입점.

    Args:
        trade_plan:  주문 계획 (action, strategy, stock_code, quantity, price 등)
        portfolio:   현재 포트폴리오 요약 (보유 종목 목록, 총 평가금액 등)
        signals:     진입 신호 정보 (strategy, rules, indicators 등)

    Returns:
        (approve: bool, reason: str)
        - approve=True  → 주문 실행
        - approve=False → 주문 스킵
        - MCP 장애 / 타임아웃 → fail-open (approve=True, 매매 중단 방지)
    """
    global _fail_open_count

    if not settings.MCP_VALIDATION_ENABLED:
        return True, "mcp_disabled"

    _ttl = settings.MCP_RISK_CACHE_TTL
    _ckey = _risk_cache_key(trade_plan) if _ttl > 0 else None
    if _ckey:
        _hit = _risk_cache.get(_ckey)
        if _hit and _hit[0] > time.monotonic():
            return _hit[1], f"{_hit[2]} (cached)"

    try:
        client = get_http_client()
    except RuntimeError:
        _fail_open_count += 1
        logger.warning(
            "MCP http_client 미초기화 — fail-open (누적 %d회)", _fail_open_count
        )
        if _fail_open_count > _FAIL_OPEN_WARN_THRESHOLD:
            logger.error(
                "MCP fail-open 연속 %d회 초과: MCP 서버 연결 상태를 점검하세요",
                _fail_open_count,
            )
        return True, "client_not_initialized_fail_open"

    try:
        resp = await client.post(
            f"{settings.MCP_SERVER_URL}/analyze",
            json={
                "analysis_type": "RISK_ASSESSMENT",
                "data": {
                    "trade_plan": trade_plan,
                    "portfolio": portfolio,
                    "signals": signals,
                },
            },
            timeout=settings.MCP_REQUEST_TIMEOUT,
        )
        if resp.status_code == 200:
            result = resp.json()
            # 응답: {"result": {"decision": "approve"|"deny", "reason": "..."}}
            payload = result.get("result", result)
            decision = str(payload.get("decision", "approve")).lower()
            reason = str(payload.get("reason", ""))
            _fail_open_count = 0  # 정상 응답 수신 시 카운터 리셋
            approve = not ("deny" in decision or "reject" in decision)
            if _ckey:
                _risk_cache[_ckey] = (time.monotonic() + _ttl, approve, reason)
            return approve, reason
        else:
            _fail_open_count += 1
            logger.warning(
                "MCP RISK_ASSESSMENT HTTP %d — fail-open (누적 %d회)",
                resp.status_code, _fail_open_count,
            )
            if _fail_open_count > _FAIL_OPEN_WARN_THRESHOLD:
                logger.error(
                    "MCP fail-open 연속 %d회 초과: MCP 서버 응답 오류가 지속됩니다",
                    _fail_open_count,
                )
            return True, f"mcp_http_{resp.status_code}_fail_open"
    except httpx.TimeoutException:
        _fail_open_count += 1
        logger.warning(
            "MCP RISK_ASSESSMENT 타임아웃 — fail-open (누적 %d회)", _fail_open_count
        )
        if _fail_open_count > _FAIL_OPEN_WARN_THRESHOLD:
            logger.error(
                "MCP fail-open 연속 %d회 초과: MCP 서버 타임아웃이 지속됩니다",
                _fail_open_count,
            )
        return True, "mcp_timeout_fail_open"
    except Exception as e:
        _fail_open_count += 1
        logger.warning(
            "MCP RISK_ASSESSMENT 오류: %s — fail-open (누적 %d회)", e, _fail_open_count
        )
        if _fail_open_count > _FAIL_OPEN_WARN_THRESHOLD:
            logger.error(
                "MCP fail-open 연속 %d회 초과: 오류=%s", _fail_open_count, e
            )
        return True, f"mcp_error_fail_open: {e}"


# ─── 모델 ──────────────────────────────────────────────────────────────
class MCPToolRequest(BaseModel):
    tool_name: str
    parameters: Dict[str, Any]


class MCPAnalysisRequest(BaseModel):
    analysis_type: str  # "RULE_VALIDATION", "MARKET_ANALYSIS", "RISK_ASSESSMENT"
    data: Dict[str, Any]


# ─── 엔드포인트 ────────────────────────────────────────────────────────
@router.get("/status")
async def get_mcp_status():
    """MCP 서버 상태 확인"""
    try:
        client = get_http_client()
    except RuntimeError:
        return {"status": "disconnected", "message": "http_client not initialized"}
    try:
        response = await client.get(f"{settings.MCP_SERVER_URL}/health", timeout=2.0)
        if response.status_code == 200:
            health_data = response.json()
            return {
                "status": "connected",
                "mcp_server_url": settings.MCP_SERVER_URL,
                "claude_configured": health_data.get("claude_configured", False),
                "ai_provider": health_data.get("ai_provider", "unknown"),
                "details": health_data,
            }
        return {"status": "error", "message": "MCP server responded with error"}
    except Exception as e:
        return {"status": "disconnected", "message": str(e)}


@router.post("/tools/call")
async def call_mcp_tool(request: MCPToolRequest):
    """MCP 도구 호출"""
    try:
        client = get_http_client()
    except RuntimeError as e:
        raise HTTPException(status_code=503, detail=str(e))
    try:
        response = await client.post(
            f"{settings.MCP_SERVER_URL}/tools/call",
            json={"tool_name": request.tool_name, "parameters": request.parameters},
            timeout=30.0,
        )
        if response.status_code == 200:
            return response.json()
        raise HTTPException(
            status_code=response.status_code,
            detail=f"MCP tool call failed: {response.text}",
        )
    except httpx.TimeoutException:
        raise HTTPException(status_code=504, detail="MCP server timeout")
    except HTTPException:
        raise
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Failed to call MCP tool: {str(e)}")


@router.post("/analyze")
async def analyze_with_claude(request: MCPAnalysisRequest):
    """Claude AI를 통한 분석 요청"""
    try:
        client = get_http_client()
    except RuntimeError as e:
        raise HTTPException(status_code=503, detail=str(e))
    try:
        response = await client.post(
            f"{settings.MCP_SERVER_URL}/analyze",
            json={"analysis_type": request.analysis_type, "data": request.data},
            timeout=60.0,
        )
        if response.status_code == 200:
            return response.json()
        raise HTTPException(
            status_code=response.status_code,
            detail=f"Claude analysis failed: {response.text}",
        )
    except httpx.TimeoutException:
        raise HTTPException(status_code=504, detail="Analysis timeout")
    except HTTPException:
        raise
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Failed to analyze: {str(e)}")


@router.get("/tools")
async def list_mcp_tools():
    """사용 가능한 MCP 도구 목록"""
    try:
        client = get_http_client()
    except RuntimeError as e:
        raise HTTPException(status_code=503, detail=str(e))
    try:
        response = await client.get(f"{settings.MCP_SERVER_URL}/tools", timeout=10.0)
        if response.status_code == 200:
            return response.json()
        raise HTTPException(
            status_code=response.status_code, detail="Failed to fetch tools list"
        )
    except HTTPException:
        raise
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Failed to list tools: {str(e)}")