"""
app/services/llm_service.py — LLM Client (Ollama)
Version: 0.3.0 (Fix: JSON Format Enforcement)
"""

import httpx
import yaml
import logging
import os
from pathlib import Path
# ANNAHME: app.config ist verfügbar
# from app.config import get_settings 

logger = logging.getLogger(__name__)

# --- Mock get_settings für die Vollständigkeit ---
class Settings:
    OLLAMA_URL = os.getenv("MINDNET_OLLAMA_URL", "http://127.0.0.1:11434")
    LLM_TIMEOUT = float(os.getenv("MINDNET_LLM_TIMEOUT", 300.0))
    LLM_MODEL = os.getenv("MINDNET_LLM_MODEL", "phi3:mini")
    PROMPTS_PATH = os.getenv("MINDNET_PROMPTS_PATH", "./config/prompts.yaml")
    
def get_settings():
    return Settings()
# -----------------------------------------------

class LLMService:
    def __init__(self):
        self.settings = get_settings()
        self.prompts = self._load_prompts()
        
        self.client = httpx.AsyncClient(
            base_url=self.settings.OLLAMA_URL, 
            timeout=self.settings.LLM_TIMEOUT
        )

    def _load_prompts(self) -> dict:
        path = Path(self.settings.PROMPTS_PATH)
        if not path.exists():
            return {}
        try:
            with open(path, "r", encoding="utf-8") as f:
                return yaml.safe_load(f)
        except Exception as e:
            logger.error(f"Failed to load prompts: {e}")
            return {}

    async def generate_raw_response(self, prompt: str, system: str = None, force_json: bool = False) -> str:
        """
        Führt einen LLM Call aus. 
        force_json: NEUER OPTIONALER PARAMETER zur Erzwingung des Ollama JSON-Modus.
        """
        payload = {
            "model": self.settings.LLM_MODEL,
            "prompt": prompt,
            "stream": False,
            "options": {
                "temperature": 0.7, 
                "num_ctx": 2048
            }
        }

        # NEU: Ollama Format Erzwingung (wichtig für Semantic Chunking)
        if force_json:
             payload["format"] = "json"

        # WICHTIG: System-Prompt separat übergeben
        if system:
            payload["system"] = system

        try:
            response = await self.client.post("/api/generate", json=payload)
            if response.status_code != 200:
                logger.error(f"Ollama Error ({response.status_code}): {response.text}")
                return "Fehler bei der Generierung."
            
            data = response.json()
            return data.get("response", "").strip()
            
        except Exception as e:
            logger.error(f"LLM Raw Gen Error: {e}")
            return "Interner LLM Fehler."

    async def generate_rag_response(self, query: str, context_str: str) -> str:
        """
        Legacy Support: Wird vom Chat und Intent Router genutzt.
        Ruft generate_raw_response OHNE force_json auf.
        """
        system_prompt = self.prompts.get("system_prompt", "")
        rag_template = self.prompts.get("rag_template", "{context_str}\n\n{query}")
        final_prompt = rag_template.format(context_str=context_str, query=query)
        
        # Aufruf bleibt im Standard-Modus (force_json=False Default)
        return await self.generate_raw_response(final_prompt, system=system_prompt)

    async def close(self):
        await self.client.aclose()