fastcheck_api fix

fastcheck_api/app/api/v1/routers/rut.py

@@ -1,38 +1,174 @@
 from __future__ import annotations
 
+import logging
 import datetime as dt
 import time
+import re
 from typing import Annotated, Any
 
 from fastapi import APIRouter, Depends, HTTPException, Request, status
-from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
 from motor.motor_asyncio import AsyncIOMotorDatabase
 from pymongo import ReturnDocument
 from pydantic import BaseModel, Field
 
 from fastcheck_api.app.api.dependencies import CurrentUser, require_permission
 from fastcheck_api.app.core.mongodb import get_db
+from fastcheck_api.app.services.dequienes_native_service import dequienes_native_service
 from fastcheck_api.app.services.audit_service import AuditService
-from fastcheck_api.app.services.legacy_service import legacy_service
-from fastcheck_api.app.utils.mongo import sanitize_rut, to_object_id
+from fastcheck_api.app.services.risk_calculation_service import RiskCalculationService
+from fastcheck_api.app.services.sheriff_v2_native_service import sheriff_v2_native_service
+from fastcheck_api.app.utils.mongo import jsonable, sanitize_rut, to_object_id
 
 
 router = APIRouter(prefix="/rut", tags=["rut"])
-
-_bearer = HTTPBearer(auto_error=False)
+logger = logging.getLogger("fastcheck.rut")
 
 
 class RutLookupRequest(BaseModel):
     rut: str = Field(examples=["12345678-9"])
-    isMonitoring: bool = Field(default=False, description="Compatibility flag with legacy backend.")
+    isMonitoring: bool = Field(default=False)
+    isRefreshing: bool = Field(default=False)
+    isPep: bool = Field(default=False)
+    type: str = Field(default="individual")
+
+
+def _as_list(value: Any) -> list[Any]:
+    return value if isinstance(value, list) else []
+
+
+def _safe_get(dct: Any, *path: str, default: Any = None) -> Any:
+    cur = dct
+    for key in path:
+        if not isinstance(cur, dict):
+            return default
+        cur = cur.get(key)
+    return default if cur is None else cur
+
+
+def _extract_socios_from_diario_oficial(rut: str, diario_oficial: Any, limit: int = 200) -> list[dict[str, Any]]:
+    out: list[dict[str, Any]] = []
+    seen: set[str] = set()
+    for item in _as_list(diario_oficial):
+        for socio in _as_list(_safe_get(item, "socios", default=[])):
+            socio_rut = sanitize_rut(str(_safe_get(socio, "rut", default="") or ""))
+            if not socio_rut or socio_rut == rut:
+                continue
+            if socio_rut in seen:
+                continue
+            seen.add(socio_rut)
+            name = str(_safe_get(socio, "nombre", default="") or _safe_get(socio, "name", default="") or "").strip()
+            out.append({"name": name or "N/A", "rut": socio_rut, "personType": None, "isNaturalPerson": None})
+            if len(out) >= limit:
+                return out
+    return out
+
+
+def _compute_is_pep_from_compliance(compliance: Any) -> bool:
+    pep = _as_list(_safe_get(compliance, "pepChile", "coincidencias", default=[]))
+    fam = _as_list(_safe_get(compliance, "familiaresPep", "coincidencias", default=[]))
+    pub = _as_list(_safe_get(compliance, "funcionariosPublicos", "coincidencias", default=[]))
+    return bool(pep or fam or pub)
+
+
+def _simple_risk_assessment(filtered_details: dict[str, Any]) -> dict[str, Any]:
+    compliance = filtered_details.get("compliance") or {}
+    is_pep = _compute_is_pep_from_compliance(compliance)
+    has_judicial = bool(filtered_details.get("civilCasesData") or filtered_details.get("laboralCasesData") or filtered_details.get("cobranzaCasesData"))
+    has_labor_collection = bool(filtered_details.get("moraPrevisionalCasesData") or filtered_details.get("multaLaboralCasesData"))
+    semaphore = "bajo"
+    if is_pep:
+        semaphore = "critico"
+    elif has_judicial or has_labor_collection:
+        semaphore = "alto"
+    return {
+        "riskSummary": {"semaphore": semaphore},
+        "allRules": {
+            "complianceRules": [],
+            "legalRules": [],
+            "capitalHumanoRules": [],
+            "financieroTributarioRules": [],
+        },
+        "summaryDocumentMD": "",
+    }
+
+
+def _compute_is_pep_from_risk(risk_assessment: dict[str, Any] | None) -> bool:
+    if not isinstance(risk_assessment, dict):
+        return False
+    rules = _safe_get(risk_assessment, "allRules", "complianceRules", default=[])
+    for r in _as_list(rules):
+        label = str(_safe_get(r, "label", default="") or "")
+        if label in {"PEP Chile", "Familiares PEP"} and bool(_safe_get(r, "detected", default=False)):
+            return True
+    return False
+
+
+_PROV_REPLACEMENTS: dict[str, str] = {
+    "sheriff": "sProv",
+    "dequienes": "dProv",
+}
+_PROV_PATTERN = re.compile("|".join(re.escape(k) for k in _PROV_REPLACEMENTS), re.IGNORECASE)
+
+
+def _mask_providers_text(value: str) -> str:
+    return _PROV_PATTERN.sub(lambda m: _PROV_REPLACEMENTS[m.group(0).lower()], value)
+
+
+def _mask_providers_json(value: Any) -> Any:
+    if isinstance(value, str):
+        return _mask_providers_text(value)
+    if isinstance(value, list):
+        return [_mask_providers_json(v) for v in value]
+    if isinstance(value, dict):
+        out: dict[Any, Any] = {}
+        for k, v in value.items():
+            masked_key = _mask_providers_text(k) if isinstance(k, str) else k
+            out[masked_key] = _mask_providers_json(v)
+        return out
+    return value
+
+
+def _normalize_date(value: str | None) -> str | None:
+    if not value:
+        return None
+    raw = str(value).strip()
+    if not raw:
+        return None
+    if re.match(r"^\d{4}-\d{2}-\d{2}$", raw):
+        return raw
+    m = re.match(r"^(\d{2})-(\d{2})-(\d{4})$", raw)
+    if m:
+        dd, mm, yyyy = m.group(1), m.group(2), m.group(3)
+        return f"{yyyy}-{mm}-{dd}"
+    m = re.match(r"^(\d{2})/(\d{2})/(\d{4})$", raw)
+    if m:
+        dd, mm, yyyy = m.group(1), m.group(2), m.group(3)
+        return f"{yyyy}-{mm}-{dd}"
+    return None
+
+
+def _strip_cache_info_json(value: Any) -> Any:
+    if isinstance(value, list):
+        return [_strip_cache_info_json(v) for v in value]
+    if isinstance(value, dict):
+        out: dict[Any, Any] = {}
+        for k, v in value.items():
+            if k == "_cache_info":
+                continue
+            out[k] = _strip_cache_info_json(v)
+        return out
+    return value
+
+
+def _sanitize_result_payload(payload: Any) -> Any:
+    return _mask_providers_json(_strip_cache_info_json(payload))
 
 
 @router.post(
     "/lookup",
-    summary="Lookup RUT (single evaluation)",
+    summary="Lookup RUT",
     description=(
-        "Runs a single evaluation for a RUT using the legacy backend and persists the result in MongoDB.\n\n"
-        "If a successful result for the same RUT already exists for the tenant, returns it without consuming credits."
+        "Runs a native RUT lookup using Sheriff V2 APIs and persists the result in MongoDB (same persistence model as the legacy Node implementation)."
     ),
 )
 async def lookup_rut(
@@ -40,32 +176,33 @@ async def lookup_rut(
     payload: RutLookupRequest,
     user: Annotated[CurrentUser, Depends(require_permission("rut:lookup"))],
     db: Annotated[AsyncIOMotorDatabase, Depends(get_db)],
-    credentials: Annotated[HTTPAuthorizationCredentials | None, Depends(_bearer)] = None,
 ):
     start = time.perf_counter()
     rut = sanitize_rut(payload.rut)
 
-    token = credentials.credentials if credentials else None
-    if not token:
-        raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="No token provided")
+    refresh = bool(payload.isMonitoring or payload.isRefreshing)
+    now = dt.datetime.now(dt.timezone.utc)
 
-    cached = (
-        await db["evaluationresults"]
-        .find({"tenantId": user.tenant, "rut": rut, "status": "success"})
-        .sort([("createdAt", -1)])
-        .limit(1)
-        .to_list(length=1)
+    if refresh:
+        await db["results"].update_many(
+            {"rut": rut, "tenantId": user.tenant, "archived": {"$ne": True}},
+            {"$set": {"archived": True, "archivedAt": now, "updatedAt": now}},
+        )
+
+    existing = await db["results"].find_one(
+        {"rut": rut, "tenantId": user.tenant, "archived": {"$ne": True}},
+        sort=[("createdAt", -1)],
     )
-    if cached and isinstance(cached[0], dict) and isinstance(cached[0].get("data"), dict):
+    if existing and not refresh:
         await AuditService.log_consulta(
             db=db,
             tenant_id=user.tenant,
             user_id=user.id,
             consulta_type="individual",
             rut=rut,
-            endpoint="/api/v1/rut/lookup",
+            endpoint="/client-api-v1/rut/lookup",
             response_status=status.HTTP_200_OK,
-            request_data={"rut": rut, "isMonitoring": payload.isMonitoring},
+            request_data=jsonable(payload.model_dump()),
             response_data={"source": "cache"},
             processing_time_ms=int((time.perf_counter() - start) * 1000),
             credits_used=0,
@@ -73,147 +210,231 @@ async def lookup_rut(
             user_agent=request.headers.get("user-agent"),
             metadata={"source": "cache"},
         )
-        return {**cached[0]["data"], "isFromCache": True}
+        return _sanitize_result_payload(jsonable(existing))
 
-    tenant_oid = to_object_id(user.tenant)
-    now = dt.datetime.now(dt.timezone.utc)
-
-    tenant_after = await db["tenants"].find_one_and_update(
-        {"_id": tenant_oid, "creditBalance.availableCredits": {"$gte": 1}},
-        {
-            "$inc": {
-                "creditBalance.availableCredits": -1,
-                "creditBalance.totalCreditsUsed": 1,
+    should_deduct = (not payload.isPep) and (payload.isRefreshing or not refresh)
+    if should_deduct:
+        tenant_oid = to_object_id(user.tenant)
+        tenant_after = await db["tenants"].find_one_and_update(
+            {"_id": tenant_oid, "creditBalance.availableCredits": {"$gte": 1}},
+            {
+                "$inc": {
+                    "creditBalance.availableCredits": -1,
+                    "creditBalance.totalCreditsUsed": 1,
+                },
+                "$set": {
+                    "creditBalance.lastCreditOperation": now,
+                    "updatedAt": now,
+                },
             },
-            "$set": {
-                "creditBalance.lastCreditOperation": now,
-                "updatedAt": now,
-            },
-        },
-        return_document=ReturnDocument.AFTER,
-    )
-    if not tenant_after:
-        await AuditService.log_consulta(
-            db=db,
-            tenant_id=user.tenant,
-            user_id=user.id,
-            consulta_type="individual",
-            rut=rut,
-            endpoint="/api/v1/rut/lookup",
-            response_status=status.HTTP_402_PAYMENT_REQUIRED,
-            request_data={"rut": rut, "isMonitoring": payload.isMonitoring},
-            processing_time_ms=int((time.perf_counter() - start) * 1000),
-            credits_used=0,
-            ip_address=request.client.host if request.client else None,
-            user_agent=request.headers.get("user-agent"),
-            metadata={"reason": "insufficient_credits"},
+            return_document=ReturnDocument.AFTER,
         )
-        raise HTTPException(status_code=status.HTTP_402_PAYMENT_REQUIRED, detail="Insufficient credits")
+        if not tenant_after:
+            await AuditService.log_consulta(
+                db=db,
+                tenant_id=user.tenant,
+                user_id=user.id,
+                consulta_type="individual",
+                rut=rut,
+                endpoint="/client-api-v1/rut/lookup",
+                response_status=status.HTTP_402_PAYMENT_REQUIRED,
+                request_data=jsonable(payload.model_dump()),
+                processing_time_ms=int((time.perf_counter() - start) * 1000),
+                credits_used=0,
+                ip_address=request.client.host if request.client else None,
+                user_agent=request.headers.get("user-agent"),
+                metadata={"reason": "insufficient_credits"},
+            )
+            raise HTTPException(
+                status_code=status.HTTP_402_PAYMENT_REQUIRED,
+                detail={"message": "Insufficient credits", "availableCredits": int((tenant_after or {}).get("creditBalance", {}).get("availableCredits", 0))},
+            )
 
-    new_balance = int((tenant_after.get("creditBalance") or {}).get("availableCredits") or 0)
-    await db["creditoperations"].insert_one(
-        {
-            "tenantId": tenant_oid,
-            "userId": to_object_id(user.id),
-            "operationType": "evaluation",
-            "creditsChanged": -1,
-            "balanceAfter": new_balance,
-            "description": f"Valutazione singola per {rut}",
-            "metadata": {"evaluationType": "single", "supplierRut": rut},
-            "createdAt": now,
-        }
-    )
-
-    job_doc: dict[str, Any] = {
-        "tenantId": user.tenant,
-        "status": "processing",
-        "type": "single",
-        "createdBy": user.id,
-        "totalEvaluations": 1,
-        "completedEvaluations": 0,
-        "failedEvaluations": 0,
-        "supplierData": {"rut": rut, "name": "N/A"},
-        "createdAt": now,
-        "updatedAt": now,
-    }
-    job_insert = await db["evaluationjobs"].insert_one(job_doc)
-    job_id = str(job_insert.inserted_id)
+        new_balance = int((tenant_after.get("creditBalance") or {}).get("availableCredits") or 0)
+        await db["creditoperations"].insert_one(
+            {
+                "tenantId": tenant_oid,
+                "userId": to_object_id(user.id),
+                "operationType": "evaluation",
+                "creditsChanged": -1,
+                "balanceAfter": new_balance,
+                "description": f"Valutazione singola per {rut}",
+                "metadata": {"evaluationType": "single", "supplierRut": rut, "source": "fastcheck_api"},
+                "createdAt": now,
+            }
+        )
 
     response_status = status.HTTP_200_OK
     error_message: str | None = None
-    result_data: dict[str, Any] | None = None
     try:
-        result_data = await legacy_service.lookup_rut(
-            rut=rut,
-            token=token,
-            is_monitoring=payload.isMonitoring,
-            evaluation_type="individual",
-        )
-        ai_summary = result_data.get("aiAnalysis")
-        if isinstance(ai_summary, str) and ai_summary.strip():
-            try:
-                await legacy_service.save_fastcheck_summary(rut=rut, summary=ai_summary, token=token)
-            except Exception:
-                pass
+        sheriff_payload = await sheriff_v2_native_service.query_rut(rut=rut, is_monitoring=payload.isMonitoring)
+        masked_sheriff_payload = _mask_providers_json(sheriff_payload)
 
-        await db["evaluationresults"].insert_one(
-            {
-                "jobId": job_insert.inserted_id,
-                "tenantId": user.tenant,
-                "rut": rut,
-                "name": None,
-                "status": "success",
-                "data": result_data,
-                "createdAt": now,
-                "updatedAt": now,
-            }
+        resumen_data = _safe_get(masked_sheriff_payload, "resumen", "data", default={})
+        data_sii = _safe_get(resumen_data, "identificacion", default={})
+        credit_scoring = _safe_get(masked_sheriff_payload, "creditScore", "data", default={})
+        compliance = _safe_get(masked_sheriff_payload, "compliance", "data", default={})
+
+        filtered_details: dict[str, Any] = {
+            "rut": _safe_get(resumen_data, "rut", default=rut),
+            "razonSocial": _safe_get(data_sii, "razonSocial", default=None),
+            "presentaActividades": _safe_get(data_sii, "presentaActividades", default=None),
+            "inicioActividades": _safe_get(data_sii, "inicioActividades", default=None),
+            "autorizadoMonedaExtranjera": _safe_get(data_sii, "autorizadoMonedaExtranjera", default=None),
+            "empresaMenor": _safe_get(data_sii, "empresaMenor", default=None),
+            "observaciones": _safe_get(data_sii, "observaciones", default=None),
+            "notas": _safe_get(data_sii, "notas", default=None),
+            "situacionActual": _safe_get(data_sii, "situacionActual", default=None),
+            "fetchedAt": now.date().isoformat(),
+            "creditScoringData": credit_scoring,
+            "compliance": compliance,
+            "boletinComercialSummary": _safe_get(masked_sheriff_payload, "resumen", "boletinComercial", default={}),
+            "boletinLaboralSummary": _safe_get(resumen_data, "boletinLaboral", default={}),
+            "boletinLaboralLastUpdate": _safe_get(resumen_data, "boletinLaboral", "ultimaActualizacion", default=None),
+            "vehiclesSummary": _safe_get(resumen_data, "bienes", "vehiculos", default={}),
+            "propertiesSummary": _safe_get(resumen_data, "bienes", "propiedades", default={}),
+            "deudaBancariaSummary": _safe_get(masked_sheriff_payload, "resumen", "deudaBancaria", default={}),
+            "mallaSocietariaData": _safe_get(masked_sheriff_payload, "legal", "mallaSocietaria", "data", default={}),
+            "officialDiaryData": _safe_get(masked_sheriff_payload, "legal", "mallaSocietaria", "data", "diarioOficial", default=[]),
+            "civilCasesData": _safe_get(masked_sheriff_payload, "judicial", "civil", "data", default={}),
+            "laboralCasesData": _safe_get(masked_sheriff_payload, "judicial", "laboral", "data", default={}),
+            "cobranzaCasesData": _safe_get(masked_sheriff_payload, "judicial", "cobranza", "data", default={}),
+            "moraPrevisionalCasesData": _safe_get(masked_sheriff_payload, "cobranzaLaboral", "moraPrevisional", "data", default={}),
+            "multaLaboralCasesData": _safe_get(masked_sheriff_payload, "cobranzaLaboral", "multaLaboral", "data", default={}),
+        }
+
+        compliance_person_type = "juridical" if bool(_safe_get(resumen_data, "esPersonaJuridica", default=False)) else "natural"
+        filtered_details["compliancePersonType"] = compliance_person_type
+        filtered_details["complianceSelectedRowsPepChile"] = _as_list(_safe_get(compliance, "pepChile", "coincidencias", default=[]))
+        filtered_details["complianceSelectedRowsPublicOfficial"] = _as_list(
+            _safe_get(compliance, "funcionariosPublicos", "coincidencias", default=[])
         )
-        await db["evaluationjobs"].update_one(
-            {"_id": job_insert.inserted_id, "tenantId": user.tenant},
-            {"$set": {"status": "completed", "completedEvaluations": 1, "updatedAt": now}},
+        filtered_details["complianceSelectedRowsPepChileFamily"] = _as_list(_safe_get(compliance, "familiaresPep", "coincidencias", default=[]))
+        filtered_details["complianceSelectedRowsPenal"] = _as_list(_safe_get(compliance, "penal", "coincidencias", default=[]))
+        filtered_details["complianceSelectedlistasInternacionales"] = _as_list(
+            _safe_get(compliance, "listasInternacionales", "coincidencias", default=[])
         )
-        return {**result_data, "jobId": job_id, "isFromCache": False}
-    except HTTPException as e:
-        raise e
-    except Exception as e:
-        response_status = status.HTTP_502_BAD_GATEWAY
-        error_message = str(e)
-        await db["evaluationresults"].insert_one(
-            {
-                "jobId": job_insert.inserted_id,
-                "tenantId": user.tenant,
-                "rut": rut,
-                "name": None,
-                "status": "failed",
-                "error": error_message,
-                "createdAt": now,
-                "updatedAt": now,
-            }
+
+        company_general_info: dict[str, Any] = {
+            "rapresentanteLegal": "N/D",
+            "rapresentanteLegalRut": "N/D",
+            "inicioActividades": filtered_details.get("inicioActividades") or "",
+            "fechaDeConstitucion": "",
+            "empresaMenor": filtered_details.get("empresaMenor") or "",
+            "razonSocial": filtered_details.get("razonSocial") or "",
+            "socios": [],
+            "administradores": [],
+            "rangoVentas": None,
+            "tamanoEmpresa": None,
+            "iconImpresa": None,
+            "cantidadTrabajadores": None,
+        }
+
+        diario = filtered_details.get("officialDiaryData")
+        company_general_info["socios"] = _extract_socios_from_diario_oficial(rut, diario)
+
+        if not payload.isPep:
+            try:
+                deq_relationships = await dequienes_native_service.relationships(
+                    rut=rut,
+                    distance=2,
+                    relationship_direction="BOTH",
+                    one_path_per_node=False,
+                )
+                filtered_details["dequienesRelationships"] = _mask_providers_json(_strip_cache_info_json(deq_relationships))
+            except Exception:
+                logger.exception("Dequienes relationships failed")
+            try:
+                deq_legal = await dequienes_native_service.legal_events(rut=rut)
+                filtered_details["dequienesLegalEvents"] = _mask_providers_json(_strip_cache_info_json(deq_legal))
+                raw_date = deq_legal.get("constitution_date") if isinstance(deq_legal, dict) else None
+                normalized = _normalize_date(raw_date if isinstance(raw_date, str) else None)
+                if normalized and not company_general_info.get("fechaDeConstitucion"):
+                    company_general_info["fechaDeConstitucion"] = normalized
+            except Exception:
+                logger.exception("Dequienes legal events failed")
+
+        if not company_general_info.get("fechaDeConstitucion"):
+            company_general_info["fechaDeConstitucion"] = "No hay informacion"
+
+        risk_assessment = await RiskCalculationService.calculate_risk(
+            db,
+            tenant_id=user.tenant,
+            rut=rut,
+            sheriff_v2_data=masked_sheriff_payload,
+            filtered_details=filtered_details,
+            company_general_info=company_general_info,
+            is_pep_only=payload.isPep,
         )
-        await db["evaluationjobs"].update_one(
-            {"_id": job_insert.inserted_id, "tenantId": user.tenant},
-            {"$set": {"status": "completed", "failedEvaluations": 1, "updatedAt": now}},
-        )
-        raise HTTPException(status_code=response_status, detail="Legacy lookup failed")
-    finally:
+        is_pep = _compute_is_pep_from_risk(risk_assessment) or _compute_is_pep_from_compliance(compliance)
+
         processing_ms = int((time.perf_counter() - start) * 1000)
-        audit_response: dict[str, Any] | None = None
-        if result_data is not None:
-            audit_response = {"jobId": job_id}
+        result_doc: dict[str, Any] = {
+            "rut": rut,
+            "tenantId": user.tenant,
+            "queryType": "derived_socio_pep" if payload.isPep else "primary",
+            "sheriffLogData": {
+                "rut": rut,
+                "tenantId": user.tenant,
+                "fetchedAt": now,
+                "companyGeneralInfo": company_general_info if not payload.isPep else None,
+                "filteredDetails": filtered_details,
+                "rawSheriffV2": masked_sheriff_payload,
+            },
+            "details": filtered_details,
+            "companyGeneralInfo": None if payload.isPep else company_general_info,
+            "riskAssessment": risk_assessment,
+            "isPep": bool(is_pep),
+            "userEmail": user.email,
+            "status": 200,
+            "type": payload.type,
+            "processingTime": f"{processing_ms}ms",
+            "creditsConsumed": 1 if should_deduct else 0,
+            "archived": False,
+            "createdAt": now,
+            "updatedAt": now,
+        }
+
+        insert = await db["results"].insert_one(result_doc)
+        stored = await db["results"].find_one({"_id": insert.inserted_id})
+        response_payload = jsonable(stored) if stored else jsonable({**result_doc, "_id": str(insert.inserted_id)})
+        response_payload = _sanitize_result_payload(response_payload)
+
         await AuditService.log_consulta(
             db=db,
             tenant_id=user.tenant,
             user_id=user.id,
             consulta_type="individual",
             rut=rut,
-            endpoint="/api/v1/rut/lookup",
+            endpoint="/client-api-v1/rut/lookup",
             response_status=response_status,
-            request_data={"rut": rut, "isMonitoring": payload.isMonitoring},
-            response_data=audit_response,
-            error_message=error_message,
+            request_data=jsonable(payload.model_dump()),
+            response_data={"resultId": response_payload.get("_id")},
             processing_time_ms=processing_ms,
-            credits_used=1,
+            credits_used=1 if should_deduct else 0,
             ip_address=request.client.host if request.client else None,
             user_agent=request.headers.get("user-agent"),
-            metadata={"evaluationType": "single", "jobId": job_id},
+            metadata={"evaluationType": "single", "source": "fastcheck_api"},
         )
+        return response_payload
+    except Exception as e:
+        response_status = status.HTTP_502_BAD_GATEWAY
+        error_message = str(e)
+        logger.exception(f"Native lookup failed error={error_message[:500]}")
+        await AuditService.log_consulta(
+            db=db,
+            tenant_id=user.tenant,
+            user_id=user.id,
+            consulta_type="individual",
+            rut=rut,
+            endpoint="/client-api-v1/rut/lookup",
+            response_status=response_status,
+            request_data=jsonable(payload.model_dump()),
+            error_message=error_message[:2000],
+            processing_time_ms=int((time.perf_counter() - start) * 1000),
+            credits_used=1 if should_deduct else 0,
+            ip_address=request.client.host if request.client else None,
+            user_agent=request.headers.get("user-agent"),
+            metadata={"evaluationType": "single", "source": "fastcheck_api"},
+        )
+        raise HTTPException(status_code=response_status, detail={"message": "Native lookup failed", "error": error_message[:2000]})

fastcheck_api/app/core/config.py

@@ -29,6 +29,19 @@ class Settings(BaseSettings):
     legacy_base_url: str = Field(default="http://localhost:4040/api", validation_alias="LEGACY_BASE_URL")
     legacy_http_timeout_seconds: int = Field(default=30, validation_alias="LEGACY_HTTP_TIMEOUT_SECONDS")
 
+    sheriff_v2_base_url: str | None = Field(default=None, validation_alias="SHERIFF_V2_BASE_URL")
+    sheriff_v2_access_key: str | None = Field(default=None, validation_alias="SHERIFF_V2_ACCESS_KEY")
+    sheriff_v2_access_secret: str | None = Field(default=None, validation_alias="SHERIFF_V2_ACCESS_SECRET")
+    sheriff_v2_client_identifier: str = Field(
+        default="SheriffSecureClient-v1",
+        validation_alias="SHERIFF_V2_CLIENT_IDENTIFIER",
+    )
+    sheriff_v2_token_ttl_seconds: int = Field(default=600, validation_alias="SHERIFF_V2_TOKEN_TTL_SECONDS")
+
+    dequienes_base_url: str = Field(default="http://127.0.0.1:8023", validation_alias="DEQUIENES_BASE_URL")
+    dequienes_api_key: str | None = Field(default=None, validation_alias="DEQUIENES_API_KEY")
+    dequienes_http_timeout_seconds: int = Field(default=30, validation_alias="DEQUIENES_HTTP_TIMEOUT_SECONDS")
+
     rabbitmq_enabled: bool = Field(default=True, validation_alias="RABBITMQ_ENABLED")
     rabbitmq_queue: str = Field(default="evaluation_queue", validation_alias="RABBITMQ_QUEUE")
     rabbitmq_url: str | None = Field(default=None, validation_alias="RABBITMQ_URL")

fastcheck_api/app/main.py

@@ -8,10 +8,13 @@ from fastapi import APIRouter
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import HTMLResponse, JSONResponse
 
-from fastcheck_api.app.api.v1.routers import auth, checks, reports, rut, usage
+#from fastcheck_api.app.api.v1.routers import auth, checks, reports, rut, usage
+from fastcheck_api.app.api.v1.routers import auth, checks, rut, usage
 from fastcheck_api.app.core.logging import configure_logging
 from fastcheck_api.app.core.mongodb import lifespan_db
 from fastcheck_api.app.services.legacy_service import legacy_service
+from fastcheck_api.app.services.dequienes_native_service import dequienes_native_service
+from fastcheck_api.app.services.sheriff_v2_native_service import sheriff_v2_native_service
 from fastcheck_api.app.services.rabbitmq_service import rabbitmq_service
 from fastcheck_api.app.middleware.request_logging import RequestLoggingMiddleware
 from fastcheck_api.app.middleware.tenant_context import TenantContextMiddleware
@@ -46,6 +49,8 @@ async def lifespan(app: FastAPI):
             except Exception:
                 logger.exception("RabbitMQ shutdown failed")
             await legacy_service.close()
+            await sheriff_v2_native_service.close()
+            await dequienes_native_service.aclose()
 
 
 app = FastAPI(
@@ -156,7 +161,7 @@ async def prefixed_openapi():
 
 api_v1.include_router(auth.router)
 api_v1.include_router(checks.router)
-api_v1.include_router(reports.router)
+#api_v1.include_router(reports.router)
 api_v1.include_router(rut.router)
 api_v1.include_router(usage.router)
 app.include_router(api_v1)

fastcheck_api/app/services/dequienes_native_service.py

@@ -0,0 +1,76 @@
+from __future__ import annotations
+
+import re
+from typing import Any
+
+import httpx
+
+from fastcheck_api.app.core.config import settings
+
+
+def _sanitize_rut_for_dequienes(rut: str) -> str:
+    rut_no_dots = (rut or "").replace(".", "").strip()
+    parts = rut_no_dots.split("-", 1)
+    numeric = re.sub(r"\D+", "", parts[0])
+    numeric = re.sub(r"^0+", "", numeric) or "0"
+    return numeric
+
+
+class DequienesNativeService:
+    def __init__(self) -> None:
+        self._client: httpx.AsyncClient | None = None
+
+    def _get_client(self) -> httpx.AsyncClient:
+        if self._client is None:
+            self._client = httpx.AsyncClient(
+                base_url=settings.dequienes_base_url.rstrip("/"),
+                timeout=httpx.Timeout(settings.dequienes_http_timeout_seconds),
+            )
+        return self._client
+
+    async def aclose(self) -> None:
+        if self._client is not None:
+            await self._client.aclose()
+            self._client = None
+
+    def _headers(self) -> dict[str, str]:
+        headers: dict[str, str] = {"accept": "application/json"}
+        api_key = (settings.dequienes_api_key or "").strip()
+        if api_key:
+            headers["x-api-key"] = api_key
+        return headers
+
+    async def relationships(
+        self,
+        *,
+        rut: str,
+        distance: int = 2,
+        relationship_direction: str = "BOTH",
+        one_path_per_node: bool = False,
+    ) -> dict[str, Any]:
+        rut_sanitized = _sanitize_rut_for_dequienes(rut)
+        client = self._get_client()
+        resp = await client.get(
+            f"/relationships/{rut_sanitized}",
+            params={
+                "distance": int(distance),
+                "relationship_direction": relationship_direction,
+                "one_path_per_node": "true" if one_path_per_node else "false",
+            },
+            headers=self._headers(),
+        )
+        resp.raise_for_status()
+        data = resp.json()
+        return data if isinstance(data, dict) else {"raw": data}
+
+    async def legal_events(self, *, rut: str) -> dict[str, Any]:
+        rut_sanitized = _sanitize_rut_for_dequienes(rut)
+        client = self._get_client()
+        resp = await client.get(f"/api/legal-events/{rut_sanitized}", headers=self._headers())
+        resp.raise_for_status()
+        data = resp.json()
+        return data if isinstance(data, dict) else {"raw": data}
+
+
+dequienes_native_service = DequienesNativeService()
+

fastcheck_api/app/services/risk_calculation_service.py

@@ -0,0 +1,697 @@
+from __future__ import annotations
+
+import datetime as dt
+import re
+from typing import Any
+
+from motor.motor_asyncio import AsyncIOMotorDatabase
+
+from fastcheck_api.app.utils.mongo import sanitize_rut
+
+
+def _as_dict(value: Any) -> dict[str, Any]:
+    return value if isinstance(value, dict) else {}
+
+
+def _as_list(value: Any) -> list[Any]:
+    return value if isinstance(value, list) else []
+
+
+def _safe_get(value: Any, *path: str, default: Any = None) -> Any:
+    cur = value
+    for key in path:
+        if not isinstance(cur, dict):
+            return default
+        cur = cur.get(key)
+    return default if cur is None else cur
+
+
+def _risk_from_impact(detected: bool, impacto: str) -> str:
+    if not detected:
+        return "bajo"
+    if impacto == "severo":
+        return "critico"
+    if impacto == "significativo":
+        return "alto"
+    return "bajo"
+
+
+def _normalize_text(value: str) -> str:
+    value = (value or "").strip()
+    value = value.replace("Á", "A").replace("É", "E").replace("Í", "I").replace("Ó", "O").replace("Ú", "U")
+    value = value.replace("á", "a").replace("é", "e").replace("í", "i").replace("ó", "o").replace("ú", "u")
+    value = re.sub(r"[^\w\s]", " ", value, flags=re.UNICODE)
+    value = re.sub(r"\s+", " ", value, flags=re.UNICODE).strip()
+    return value
+
+
+def _rut_variants(rut: str) -> list[str]:
+    rut = sanitize_rut(rut)
+    clean = rut.replace(".", "").replace("-", "").upper()
+    if len(clean) < 2:
+        return [rut]
+    dotted = f"{clean[:-1]:0>9}"
+    dotted = re.sub(r"^(\d{2})(\d{3})(\d{3})$", r"\1.\2.\3", dotted[:-1]) + "-" + clean[-1]
+    with_dash = f"{clean[:-1]}-{clean[-1]}"
+    return list(dict.fromkeys([rut, with_dash, clean, dotted]))
+
+
+class RiskCalculationService:
+    @staticmethod
+    async def _load_equifax_normalized(
+        db: AsyncIOMotorDatabase, *, tenant_id: str, rut: str
+    ) -> dict[str, Any] | None:
+        rut = sanitize_rut(rut)
+        base = rut.replace(".", "").replace("-", "").upper()
+        rut_with_dash = f"{base[:-1]}-{base[-1]}" if len(base) > 1 else rut
+        rut_without_dash = base
+        query: dict[str, Any] = {"tenantId": tenant_id, "$or": [{"rut": rut}, {"rut": rut_with_dash}, {"rut": rut_without_dash}]}
+        doc = await db["equifax-responses"].find_one(query, sort=[("createdAt", -1)])
+        if not doc or not isinstance(doc, dict):
+            return None
+        normalized = doc.get("normalizedData")
+        return normalized if isinstance(normalized, dict) else None
+
+    @staticmethod
+    async def _load_antiunion_cases(db: AsyncIOMotorDatabase, *, rut: str) -> list[dict[str, Any]]:
+        variants = _rut_variants(rut)
+        ors: list[dict[str, Any]] = []
+        for v in variants:
+            ors.append({"rut": {"$regex": f"^{re.escape(v)}$", "$options": "i"}})
+        cursor = db["antiunioncases"].find({"$or": ors}).sort([("createdAt", -1)]).limit(200)
+        out: list[dict[str, Any]] = []
+        async for doc in cursor:
+            if isinstance(doc, dict):
+                out.append(doc)
+        return out
+
+    @staticmethod
+    async def _load_ley_records(db: AsyncIOMotorDatabase, *, collection: str, rut: str) -> list[dict[str, Any]]:
+        clean = rut.replace(".", "").upper()
+        cursor = db[collection].find({"rut": clean}).sort([("createdAt", -1)]).limit(200)
+        out: list[dict[str, Any]] = []
+        async for doc in cursor:
+            if isinstance(doc, dict):
+                out.append(doc)
+        return out
+
+    @staticmethod
+    async def _load_listas_propias(db: AsyncIOMotorDatabase, *, collection: str, tenant_id: str, rut: str) -> list[dict[str, Any]]:
+        clean = rut.replace(".", "").upper()
+        cursor = db[collection].find({"rut": clean, "tenant": tenant_id}).sort([("createdAt", -1)]).limit(200)
+        out: list[dict[str, Any]] = []
+        async for doc in cursor:
+            if isinstance(doc, dict):
+                out.append(doc)
+        return out
+
+    @staticmethod
+    async def _find_snifa_by_company_name(
+        db: AsyncIOMotorDatabase,
+        *,
+        razon_social: str,
+        field_flag: str,
+    ) -> list[dict[str, Any]]:
+        name = _normalize_text(razon_social)
+        if not name:
+            return []
+        tokens = [t for t in name.split(" ") if len(t) >= 3]
+        tokens = tokens[:6]
+        if not tokens:
+            return []
+        regex = ".*".join(re.escape(t) for t in tokens)
+        query = {
+            field_flag: {"$regex": r"^SI$", "$options": "i"},
+            "razonSocial": {"$regex": regex, "$options": "i"},
+        }
+        cursor = db["snifasancionatorios"].find(query).sort([("createdAt", -1)]).limit(200)
+        out: list[dict[str, Any]] = []
+        async for doc in cursor:
+            if isinstance(doc, dict):
+                out.append(doc)
+        return out
+
+    @staticmethod
+    def _evaluate_compliance_rules(log_entry: dict[str, Any]) -> list[dict[str, Any]]:
+        compliance_rules: list[dict[str, Any]] = []
+        summary = _as_dict(_safe_get(log_entry, "summaryData", "data", default={}))
+        v2 = _as_dict(_safe_get(log_entry, "filteredDetails", "sheriffV2Data", default={}))
+        compliance_data = _as_dict(_safe_get(v2, "compliance", "data", default={}))
+        compliance_local = _as_dict(_safe_get(log_entry, "filteredDetails", "compliance", default={}))
+
+        ley21121_records = _as_list(summary.get("ley21121Records") or [])
+        ley21121_detected = bool(summary.get("ley21121Detected"))
+        compliance_rules.append(
+            {
+                "label": "Condenas Ley 21.121",
+                "impacto": "severo",
+                "detected": ley21121_detected,
+                "risk": _risk_from_impact(ley21121_detected, "severo"),
+                "score": len(ley21121_records),
+                "details": ley21121_records,
+            }
+        )
+
+        ley20393_records = _as_list(summary.get("ley20393Records") or [])
+        ley20393_detected = bool(summary.get("ley20393Detected"))
+        compliance_rules.append(
+            {
+                "label": "Condenas Ley 20.393",
+                "impacto": "severo",
+                "detected": ley20393_detected,
+                "risk": _risk_from_impact(ley20393_detected, "severo"),
+                "score": len(ley20393_records),
+                "details": ley20393_records,
+            }
+        )
+
+        listas_int = _as_list(_safe_get(compliance_data, "listasInternacionales", "coincidencias", default=[]))
+        detected = len(listas_int) > 0
+        compliance_rules.append(
+            {
+                "label": "Listas Internacionales",
+                "impacto": "severo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "severo"),
+                "score": len(listas_int),
+                "details": listas_int,
+            }
+        )
+
+        sanciones = _as_list(_safe_get(summary, "snifaSancionesRecords", default=[]))
+        detected = len(sanciones) > 0
+        compliance_rules.append(
+            {
+                "label": "Sanciones Medioambientales",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(sanciones),
+                "details": sanciones,
+            }
+        )
+
+        procesos = _as_list(_safe_get(summary, "snifaProcesoRecords", default=[]))
+        detected = len(procesos) > 0
+        compliance_rules.append(
+            {
+                "label": "Proceso Sanciones Medioambientales",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(procesos),
+                "details": procesos,
+            }
+        )
+
+        lpaltos = _as_list(summary.get("lpaltosRecords") or [])
+        lpaltos_detected = bool(summary.get("lpaltosDetected"))
+        compliance_rules.append(
+            {
+                "label": "Listas Propias Alto Impacto",
+                "impacto": "severo",
+                "detected": lpaltos_detected,
+                "risk": _risk_from_impact(lpaltos_detected, "severo"),
+                "score": len(lpaltos),
+                "details": lpaltos,
+            }
+        )
+
+        lpmedios = _as_list(summary.get("lpmediosRecords") or [])
+        lpmedios_detected = bool(summary.get("lpmediosDetected"))
+        compliance_rules.append(
+            {
+                "label": "Listas Propias Mediano Impacto",
+                "impacto": "significativo",
+                "detected": lpmedios_detected,
+                "risk": _risk_from_impact(lpmedios_detected, "significativo"),
+                "score": len(lpmedios),
+                "details": lpmedios,
+            }
+        )
+
+        noticias = _as_list(_safe_get(compliance_local, "noticias", "coincidencias", default=[]))
+        detected = len(noticias) > 0
+        compliance_rules.append(
+            {
+                "label": "Reputación Pública y Mediática",
+                "impacto": "severo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "severo"),
+                "score": len(noticias),
+                "details": noticias,
+            }
+        )
+
+        pep = _as_list(_safe_get(compliance_data, "pepChile", "coincidencias", default=[]))
+        detected = len(pep) > 0
+        compliance_rules.append(
+            {
+                "label": "PEP Chile",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(pep),
+                "details": pep,
+            }
+        )
+
+        penales = _as_list(_safe_get(compliance_data, "penal", "coincidencias", default=[]))
+        filtered_penales: list[Any] = []
+        for d in penales:
+            posture = str(_safe_get(d, "postura", default="") or "").lower()
+            if posture and posture not in {"denunciante", "querellante"}:
+                filtered_penales.append(d)
+        detected = len(filtered_penales) > 0
+        compliance_rules.append(
+            {
+                "label": "Causas Penales",
+                "impacto": "severo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "severo"),
+                "score": len(filtered_penales),
+                "details": filtered_penales,
+            }
+        )
+
+        familiares = _as_list(_safe_get(compliance_data, "familiaresPep", "coincidencias", default=[]))
+        detected = len(familiares) > 0
+        compliance_rules.append(
+            {
+                "label": "Familiares PEP",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(familiares),
+                "details": familiares,
+            }
+        )
+
+        return compliance_rules
+
+    @staticmethod
+    def _evaluate_capital_humano_rules(log_entry: dict[str, Any]) -> list[dict[str, Any]]:
+        out: list[dict[str, Any]] = []
+        antiunion = _as_list(_safe_get(log_entry, "antiunionCases", default=[]))
+        detected = len(antiunion) > 0
+        out.append(
+            {
+                "label": "Condenas por Prácticas Antisindicales",
+                "impacto": "severo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "severo"),
+                "score": len(antiunion),
+                "details": antiunion,
+            }
+        )
+
+        compliance_person_type = str(_safe_get(log_entry, "filteredDetails", "compliancePersonType", default="") or "").lower()
+        equifax = _as_dict(_safe_get(log_entry, "equifaxData", default={}))
+        bolab = _as_list(_safe_get(equifax, "allData", "commercialData", "credit", "debtsSummary", "bolab", "commercialBolab", default=[]))
+        deuda_previsional = []
+        if compliance_person_type == "juridical":
+            for entry in bolab:
+                it = str(_safe_get(entry, "injuryType", default="") or _safe_get(entry, "injurytype", default="") or "").upper()
+                if it != "M":
+                    deuda_previsional.append(entry)
+        detected = len(deuda_previsional) > 0
+        out.append(
+            {
+                "label": "Deuda Previsional Publicada",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(deuda_previsional),
+                "details": deuda_previsional,
+            }
+        )
+
+        bolab_j = _as_list(_safe_get(log_entry, "filteredDetails", "bolabTypePersonaJuridica", default=[]))
+        bolab_n = _as_list(_safe_get(log_entry, "filteredDetails", "bolabTypePersonaNatural", default=[]))
+        multas = []
+        for entry in [*bolab_j, *bolab_n]:
+            it = str(_safe_get(entry, "injuryType", default="") or _safe_get(entry, "injurytype", default="") or "").upper()
+            if it == "M":
+                multas.append(entry)
+        detected = len(multas) > 0
+        out.append(
+            {
+                "label": "Multas Laborales",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(multas),
+                "details": multas,
+            }
+        )
+
+        v2 = _as_dict(_safe_get(log_entry, "filteredDetails", "sheriffV2Data", default={}))
+        mora_casos = _as_list(_safe_get(v2, "cobranzaLaboral", "moraPrevisional", "data", "casos", default=[]))
+        detected = len(mora_casos) > 0
+        out.append(
+            {
+                "label": "Deuda Previsional Presunta",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(mora_casos),
+                "details": mora_casos,
+            }
+        )
+
+        return out
+
+    @staticmethod
+    def _extract_cases(value: Any) -> list[Any]:
+        if isinstance(value, list):
+            return value
+        if isinstance(value, dict):
+            data = value.get("data")
+            if isinstance(data, dict):
+                cases = data.get("casos")
+                if isinstance(cases, list):
+                    return cases
+            if isinstance(data, list):
+                return data
+        return []
+
+    @staticmethod
+    def _evaluate_legal_rules(log_entry: dict[str, Any]) -> list[dict[str, Any]]:
+        v2 = _as_dict(_safe_get(log_entry, "filteredDetails", "sheriffV2Data", default={}))
+        out: list[dict[str, Any]] = []
+
+        casos_quiebra = int(_safe_get(v2, "resumen", "data", "judicial", "casosQuiebra", default=0) or 0)
+        detected = casos_quiebra > 0
+        out.append(
+            {
+                "label": "Quiebra Judicial",
+                "impacto": "severo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "severo"),
+                "score": casos_quiebra,
+                "details": ["Existe quiebra judicial"] if detected else [],
+            }
+        )
+
+        equifax = _as_dict(_safe_get(log_entry, "equifaxData", default={}))
+        boletin_concursal = _as_list(
+            _safe_get(
+                equifax,
+                "allData",
+                "commercialData",
+                "credit",
+                "boletinConcursal",
+                "detailBoletinConcursal",
+                "commercialDetailBoletinConcursal",
+                default=[],
+            )
+        )
+        detected = len(boletin_concursal) > 0
+        out.append(
+            {
+                "label": "Boletin Concursal",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(boletin_concursal),
+                "details": boletin_concursal,
+            }
+        )
+
+        civil_cases = RiskCalculationService._extract_cases(_safe_get(v2, "judicial", "civil", default={}))
+        detected = len(civil_cases) > 0
+        out.append(
+            {
+                "label": "Causas Civiles",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(civil_cases),
+                "details": civil_cases,
+            }
+        )
+
+        laboral_cases = RiskCalculationService._extract_cases(_safe_get(v2, "judicial", "laboral", default={}))
+        detected = len(laboral_cases) > 0
+        out.append(
+            {
+                "label": "Causas Laborales",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(laboral_cases),
+                "details": laboral_cases,
+            }
+        )
+
+        cobranza_cases = RiskCalculationService._extract_cases(_safe_get(v2, "judicial", "cobranza", default={}))
+        detected = len(cobranza_cases) > 0
+        out.append(
+            {
+                "label": "Causas de Cobranza Laboral",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(cobranza_cases),
+                "details": cobranza_cases,
+            }
+        )
+
+        return out
+
+    @staticmethod
+    def _evaluate_financiero_tributario_rules(log_entry: dict[str, Any]) -> list[dict[str, Any]]:
+        v2 = _as_dict(_safe_get(log_entry, "filteredDetails", "sheriffV2Data", default={}))
+        ident = _as_dict(_safe_get(v2, "resumen", "data", "identificacion", default={}))
+        out: list[dict[str, Any]] = []
+
+        observaciones = str(_safe_get(ident, "observaciones", default="") or "")
+        termino = "término de giro" in observaciones.lower()
+        out.append(
+            {
+                "label": "Término de Giro",
+                "impacto": "severo",
+                "detected": termino,
+                "risk": _risk_from_impact(termino, "severo"),
+                "score": 1 if termino else 0,
+                "details": observaciones if termino else [],
+            }
+        )
+
+        equifax = _as_dict(_safe_get(log_entry, "filteredDetails", "equifaxData", default={}))
+        icom = _as_list(_safe_get(equifax, "allData", "commercialData", "credit", "debtsSummary", "icom", "commercialIcom", default=[]))
+        if not icom:
+            icom = _as_list(_safe_get(equifax, "protestosMorosidadesPersonaNaturalList", default=[]))
+        detected = len(icom) > 0
+        out.append(
+            {
+                "label": "Protestos y Morosidades",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": len(icom),
+                "details": icom,
+            }
+        )
+
+        inicio_actividades = _safe_get(ident, "inicioActividades", default=None)
+        actividad = _as_list(_safe_get(ident, "actividadEconomicaVigente", default=[]))
+        missing_inicio = inicio_actividades is None
+        out.append(
+            {
+                "label": "Inicio de Actividades",
+                "impacto": "significativo",
+                "detected": missing_inicio,
+                "risk": _risk_from_impact(missing_inicio, "significativo"),
+                "score": 1 if missing_inicio else 0,
+                "details": actividad if not missing_inicio else [],
+            }
+        )
+
+        situacion = str(_safe_get(ident, "situacionActual", default="") or "")
+        detected = bool(situacion) and not re.search(r"No se encuentra", situacion, flags=re.IGNORECASE)
+        out.append(
+            {
+                "label": "Contribuyente de difícil fiscalización",
+                "impacto": "significativo",
+                "detected": detected,
+                "risk": _risk_from_impact(detected, "significativo"),
+                "score": 1 if detected else 0,
+                "details": [{"situacionActual": situacion}] if detected else [],
+            }
+        )
+
+        return out
+
+    @staticmethod
+    def _risk_summary(
+        compliance_rules: list[dict[str, Any]],
+        legal_rules: list[dict[str, Any]],
+        capital_humano_rules: list[dict[str, Any]],
+        financiero_tributario_rules: list[dict[str, Any]],
+    ) -> dict[str, Any]:
+        def _count_detected(rules: list[dict[str, Any]], impacto: str) -> int:
+            return sum(1 for r in rules if r.get("impacto") == impacto and bool(r.get("detected")))
+
+        total_severo = _count_detected(compliance_rules, "severo") + _count_detected(legal_rules, "severo") + _count_detected(capital_humano_rules, "severo") + _count_detected(financiero_tributario_rules, "severo")
+        total_significativo = _count_detected(compliance_rules, "significativo") + _count_detected(legal_rules, "significativo") + _count_detected(capital_humano_rules, "significativo") + _count_detected(financiero_tributario_rules, "significativo")
+        total_detected = (
+            sum(1 for r in compliance_rules if r.get("detected"))
+            + sum(1 for r in legal_rules if r.get("detected"))
+            + sum(1 for r in capital_humano_rules if r.get("detected"))
+            + sum(1 for r in financiero_tributario_rules if r.get("detected"))
+        )
+        total_parameters = len(compliance_rules) + len(legal_rules) + len(capital_humano_rules) + len(financiero_tributario_rules)
+
+        semaphore = "green"
+        if total_severo > 0:
+            semaphore = "red"
+        elif total_significativo > 0.7 * total_parameters:
+            semaphore = "red"
+        elif total_significativo > 0.5 * total_parameters:
+            semaphore = "orange"
+        elif total_significativo > 0:
+            semaphore = "yellow"
+
+        icon = "🟢"
+        desc = "Riego Bajo"
+        if semaphore == "red":
+            icon = "🔴"
+            desc = "Riesgo Crítico"
+        elif semaphore == "orange":
+            icon = "🟠"
+            desc = "Riesgo Alto"
+        elif semaphore == "yellow":
+            icon = "🟡"
+            desc = "Riesgo Medio"
+
+        return {
+            "totalSevero": total_severo,
+            "totalSignificativo": total_significativo,
+            "totalDetected": total_detected,
+            "totalParameters": total_parameters,
+            "semaphore": semaphore,
+            "semaphoreIcon": icon,
+            "riskLevelDescription": desc,
+        }
+
+    @staticmethod
+    def _build_doc_markdown(rut: str, razon_social: str | None, risk_summary: dict[str, Any], all_rules: dict[str, Any]) -> str:
+        company = razon_social or "N/A"
+        lines = [
+            f"# Evaluación de Riesgo\n",
+            f"**RUT**: {rut}\n",
+            f"**Razón Social**: {company}\n",
+            f"**Semáforo**: {risk_summary.get('semaphoreIcon')} ({risk_summary.get('riskLevelDescription')})\n",
+            "\n",
+            "## Resumen\n",
+            f"- Total parámetros: {risk_summary.get('totalParameters')}\n",
+            f"- Detectados: {risk_summary.get('totalDetected')}\n",
+            f"- Severos detectados: {risk_summary.get('totalSevero')}\n",
+            f"- Significativos detectados: {risk_summary.get('totalSignificativo')}\n",
+            "\n",
+            "## Detalle de Reglas\n",
+        ]
+        for section_key, title in [
+            ("complianceRules", "Compliance"),
+            ("legalRules", "Legal"),
+            ("capitalHumanoRules", "Capital Humano"),
+            ("financieroTributarioRules", "Financiero / Tributario"),
+        ]:
+            rules = _as_list(_safe_get(all_rules, section_key, default=[]))
+            lines.append(f"### {title}\n")
+            lines.append("| Parámetro | Impacto | Riesgo | Detectado |\n")
+            lines.append("|---|---|---|---|\n")
+            for r in rules:
+                label = str(_safe_get(r, "label", default="") or "")
+                impacto = str(_safe_get(r, "impacto", default="") or "")
+                risk = str(_safe_get(r, "risk", default="") or "")
+                detected = "SI" if bool(_safe_get(r, "detected", default=False)) else "NO"
+                lines.append(f"| {label} | {impacto} | {risk} | {detected} |\n")
+            lines.append("\n")
+        return "".join(lines)
+
+    @staticmethod
+    async def calculate_risk(
+        db: AsyncIOMotorDatabase,
+        *,
+        tenant_id: str,
+        rut: str,
+        sheriff_v2_data: dict[str, Any],
+        filtered_details: dict[str, Any],
+        company_general_info: dict[str, Any] | None,
+        is_pep_only: bool,
+    ) -> dict[str, Any] | None:
+        if is_pep_only:
+            return None
+
+        clean_rut = sanitize_rut(rut)
+
+        ley21121 = await RiskCalculationService._load_ley_records(db, collection="ley21121s", rut=clean_rut)
+        ley20393 = await RiskCalculationService._load_ley_records(db, collection="ley20393s", rut=clean_rut)
+        lpaltos = await RiskCalculationService._load_listas_propias(db, collection="lpaltos", tenant_id=tenant_id, rut=clean_rut)
+        lpmedios = await RiskCalculationService._load_listas_propias(db, collection="lpmedios", tenant_id=tenant_id, rut=clean_rut)
+        antiunion = await RiskCalculationService._load_antiunion_cases(db, rut=clean_rut)
+        equifax = await RiskCalculationService._load_equifax_normalized(db, tenant_id=tenant_id, rut=clean_rut)
+
+        razon_social = str(filtered_details.get("razonSocial") or "")
+        snifa_sanciones = await RiskCalculationService._find_snifa_by_company_name(
+            db, razon_social=razon_social, field_flag="fastCheckSanciones"
+        )
+        snifa_procesos = await RiskCalculationService._find_snifa_by_company_name(
+            db, razon_social=razon_social, field_flag="fastCheckProcesoSancionatorio"
+        )
+
+        summary_data = {
+            "ley21121Detected": len(ley21121) > 0,
+            "ley21121Records": ley21121,
+            "ley20393Detected": len(ley20393) > 0,
+            "ley20393Records": ley20393,
+            "lpaltosDetected": len(lpaltos) > 0,
+            "lpaltosRecords": lpaltos,
+            "lpmediosDetected": len(lpmedios) > 0,
+            "lpmediosRecords": lpmedios,
+            "snifaSancionesRecords": snifa_sanciones,
+            "snifaProcesoRecords": snifa_procesos,
+        }
+
+        log_entry: dict[str, Any] = {
+            "rut": clean_rut,
+            "tenantId": tenant_id,
+            "summaryData": {"data": summary_data},
+            "filteredDetails": {**filtered_details, "sheriffV2Data": sheriff_v2_data},
+            "companyGeneralInfo": company_general_info or {},
+            "antiunionCases": antiunion,
+            "equifaxData": equifax or {},
+        }
+
+        if equifax:
+            log_entry["filteredDetails"]["equifaxData"] = equifax
+            if "bolabTypePersonaJuridica" in equifax:
+                log_entry["filteredDetails"]["bolabTypePersonaJuridica"] = _as_list(equifax.get("bolabTypePersonaJuridica"))
+            if "bolabTypePersonaNatural" in equifax:
+                log_entry["filteredDetails"]["bolabTypePersonaNatural"] = _as_list(equifax.get("bolabTypePersonaNatural"))
+            if "protestosMorosidadesPersonaNaturalList" in equifax:
+                log_entry["filteredDetails"]["protestosMorosidadesPersonaNaturalList"] = _as_list(equifax.get("protestosMorosidadesPersonaNaturalList"))
+
+        compliance_rules = RiskCalculationService._evaluate_compliance_rules(log_entry)
+        legal_rules = RiskCalculationService._evaluate_legal_rules(log_entry)
+        capital_rules = RiskCalculationService._evaluate_capital_humano_rules(log_entry)
+        financiero_rules = RiskCalculationService._evaluate_financiero_tributario_rules(log_entry)
+
+        all_rules = {
+            "complianceRules": compliance_rules,
+            "legalRules": legal_rules,
+            "capitalHumanoRules": capital_rules,
+            "financieroTributarioRules": financiero_rules,
+        }
+        risk_summary = RiskCalculationService._risk_summary(compliance_rules, legal_rules, capital_rules, financiero_rules)
+        summary_md = RiskCalculationService._build_doc_markdown(clean_rut, razon_social or None, risk_summary, all_rules)
+
+        return {
+            "riskSummary": risk_summary,
+            "allRules": all_rules,
+            "summaryDocumentMD": summary_md,
+            "financialRisk": None,
+        }
+

fastcheck_api/app/services/sheriff_v2_native_service.py

@@ -0,0 +1,144 @@
+from __future__ import annotations
+
+import asyncio
+import time
+from typing import Any
+
+import httpx
+
+from fastcheck_api.app.core.config import settings
+
+
+class SheriffV2NativeService:
+    def __init__(self) -> None:
+        self._client = httpx.AsyncClient(timeout=60)
+        self._token: str | None = None
+        self._token_expires_at: float = 0.0
+
+    async def close(self) -> None:
+        await self._client.aclose()
+
+    def _base_url(self) -> str:
+        base_url = (settings.sheriff_v2_base_url or "").strip()
+        if not base_url:
+            raise RuntimeError("Missing SHERIFF_V2_BASE_URL")
+        return base_url.rstrip("/")
+
+    def _client_identifier(self) -> str:
+        return (settings.sheriff_v2_client_identifier or "SheriffSecureClient-v1").strip()
+
+    def _credentials(self) -> tuple[str, str]:
+        access_key = (settings.sheriff_v2_access_key or "").strip()
+        access_secret = (settings.sheriff_v2_access_secret or "").strip()
+        if not access_key or not access_secret:
+            raise RuntimeError("Missing shf V2 access credentials")
+        return access_key, access_secret
+
+    async def _get_token(self) -> str:
+        now = time.time()
+        if self._token and now < (self._token_expires_at - 30):
+            return self._token
+
+        base_url = self._base_url()
+        access_key, access_secret = self._credentials()
+        url = f"{base_url}/api/clients/v2/apiCredentials/getToken"
+        headers = {
+            "Content-Type": "application/json",
+            "accept": "application/json",
+            "x-client-identifier": self._client_identifier(),
+        }
+        resp = await self._client.post(url, headers=headers, json={"accessKey": access_key, "accessSecret": access_secret})
+        resp.raise_for_status()
+        payload = resp.json()
+        token: str | None = None
+        if isinstance(payload, dict):
+            raw = payload.get("data") or payload.get("token") or payload.get("access_token") or payload.get("accessToken")
+            if isinstance(raw, str):
+                token = raw
+            elif isinstance(raw, dict):
+                inner = raw.get("token") or raw.get("access_token") or raw.get("accessToken")
+                if isinstance(inner, str):
+                    token = inner
+        token = (token or "").strip()
+        if not token:
+            raise RuntimeError("shf token response invalid")
+
+        ttl = int(settings.sheriff_v2_token_ttl_seconds or 600)
+        self._token = token
+        self._token_expires_at = now + ttl
+        return token
+
+    async def _request(self, method: str, path: str, *, params: dict[str, Any] | None = None, json: dict[str, Any] | None = None) -> dict[str, Any]:
+        base_url = self._base_url()
+        url = f"{base_url}{path}"
+        token = await self._get_token()
+        headers = {
+            "accept": "application/json",
+            "Authorization": f"Bearer {token}",
+            "x-client-identifier": self._client_identifier(),
+        }
+        resp = await self._client.request(method, url, headers=headers, params=params, json=json)
+        if resp.status_code == 401:
+            self._token = None
+            token = await self._get_token()
+            headers["Authorization"] = f"Bearer {token}"
+            resp = await self._client.request(method, url, headers=headers, params=params, json=json)
+        if resp.status_code >= 400:
+            body = (resp.text or "")[:2000]
+            raise RuntimeError(f"shf {resp.status_code} for {method} {path}: {body}")
+        data = resp.json()
+        if not isinstance(data, dict):
+            raise RuntimeError("Unexpected shf response")
+        return data
+
+    async def query_rut(self, *, rut: str, is_monitoring: bool = False) -> dict[str, Any]:
+        rut = (rut or "").strip()
+        if not rut:
+            raise ValueError("Missing rut")
+
+        cargar = await self._request(
+            "POST",
+            "/api/clients/v2/helper/cargarRut",
+            json={"rut": rut, "isMonitoring": bool(is_monitoring), "includeEquifax": False},
+        )
+        await asyncio.sleep(2)
+
+        resumen = await self._request(
+            "GET",
+            "/api/clients/v2/helper/resumen",
+            params={"rut": rut, "complete": "True"},
+        )
+
+        result: dict[str, Any] = {"success": True, "cargarRut": cargar, "resumen": resumen}
+
+        ok = True
+        if isinstance(cargar, dict) and ("success" in cargar) and (not bool(cargar.get("success"))):
+            ok = False
+        if isinstance(resumen, dict) and ("success" in resumen) and (not bool(resumen.get("success"))):
+            ok = False
+
+        if ok:
+            judicial_civil, judicial_cobranza, judicial_laboral, multa_laboral, mora_previsional, compliance, malla_societaria, credit_score = await asyncio.gather(
+                self._request("GET", f"/api/clients/v2/helper/judicial/{rut}/civil"),
+                self._request("GET", f"/api/clients/v2/helper/judicial/{rut}/cobranza"),
+                self._request("GET", f"/api/clients/v2/helper/judicial/{rut}/laboral"),
+                self._request("GET", f"/api/clients/v2/helper/cobranzaLaboral/{rut}/multaLaboral"),
+                self._request("GET", f"/api/clients/v2/helper/cobranzaLaboral/{rut}/moraPrevisional"),
+                self._request("GET", f"/api/clients/v2/helper/compliance/{rut}"),
+                self._request("GET", f"/api/clients/v2/helper/legal/{rut}/mallaSocietaria"),
+                self._request("GET", f"/api/clients/v2/creditScore/{rut}"),
+            )
+            result.update(
+                {
+                    "judicial": {"civil": judicial_civil, "cobranza": judicial_cobranza, "laboral": judicial_laboral},
+                    "cobranzaLaboral": {"multaLaboral": multa_laboral, "moraPrevisional": mora_previsional},
+                    "compliance": compliance,
+                    "legal": {"mallaSocietaria": malla_societaria},
+                    "creditScore": credit_score,
+                }
+            )
+
+        return result
+
+
+sheriff_v2_native_service = SheriffV2NativeService()

fastcheck_api/app/utils/mongo.py

@@ -25,7 +25,23 @@ def jsonable(value: Any) -> Any:
 
 
 def sanitize_rut(value: str) -> str:
-    digits = "".join(re.findall(r"\d", value or ""))
-    if len(digits) <= 1:
-        return digits
-    return f"{digits[:-1]}-{digits[-1]}"
+    raw = (value or "").strip().replace(".", "").replace(" ", "").upper()
+    if not raw:
+        return ""
+
+    if "-" in raw:
+        base, dv = raw.split("-", 1)
+        base_digits = "".join(re.findall(r"\d", base))
+        dv_clean = "".join(re.findall(r"[0-9K]", dv))[:1]
+        if not base_digits:
+            return raw
+        base_digits = base_digits.lstrip("0") or "0"
+        return f"{base_digits}-{dv_clean}" if dv_clean else base_digits
+
+    cleaned = "".join(re.findall(r"[0-9K]", raw))
+    if len(cleaned) <= 1:
+        return cleaned
+    base_digits = "".join(re.findall(r"\d", cleaned[:-1]))
+    dv = cleaned[-1]
+    base_digits = base_digits.lstrip("0") or "0"
+    return f"{base_digits}-{dv}"