from tools.base import Tool


from tools.utils import load_prompt, ToolExecutionError, logger
from typing import Any

class RecommendEmpiricTherapyTool(Tool):

    def openai_spec(self, legacy=False):
        return {
            "name": self.name,
            "description": self.description,
            "parameters": self.args_schema
        }
    """
    Tool to recommend empiric antibiotic therapy based on a patient's profile.

    This tool uses patient age, allergies, and laboratory results to generate a prompt
    for an LLM or rules engine to recommend empiric therapy.
    """
    def __init__(self) -> None:
        """
        Initialize the RecommendEmpiricTherapyTool with its name, description, and argument schema.
        """
        super().__init__()
        self.name = "recommend_empiric_therapy"
        self.description = (
            "Recommend empiric antibiotic therapy based on patient profile."
        )
        self.args_schema = {
            "type": "object",
            "properties": {
                "age": {"type": "string", "description": "Patient age or age bracket"},
                "allergies": {"type": "string", "description": "List of known drug allergies"},
                "labs": {"type": "string", "description": "Relevant laboratory results"},
                "culture": {"type": "string", "description": "Culture & sensitivity results"},
                "meds":    {"type": "string", "description": "Current antibiotic regimen"},
                "site_of_infection": {"type": "string", "description": "Site of infection (e.g., lung, urine, blood, etc.)"},
                "risk_of_biofilm": {"type": "string", "description": "Risk or presence of biofilm (e.g., prosthetic material, indwelling device, etc.)"},
                "current_response": {"type": "string", "description": "Current response to antibiotics (e.g., improving, stable, worsening)"},
                "creatinine_clearance": {"type": "string", "description": "Current creatinine clearance or renal function"},
                "severity_of_infection": {"type": "string", "description": "Severity of infection (e.g., mild, moderate, severe, septic shock)"},
            },
            "required": ["age", "allergies", "labs", "culture", "meds", "site_of_infection", "risk_of_biofilm", "current_response", "creatinine_clearance", "severity_of_infection"]
        }

    async def run(self, age: str, allergies: str, labs: str,
                  culture: str, meds: str, site_of_infection: str, risk_of_biofilm: str,
                  current_response: str, creatinine_clearance: str, severity_of_infection: str) -> str:
        """
        Generate an empiric therapy recommendation based on patient data.

        Args:
            age (str): Patient age or age bracket.
            allergies (str): List of known drug allergies.
            labs (str): Relevant laboratory results.

        Returns:
            str: The empiric therapy recommendation (placeholder).
        """
        try:
            prompt: str = load_prompt(
                "empiric_therapy.j2",
                age=age,
                allergies=allergies,
                labs=labs,
                culture=culture,
                meds=meds,
                site_of_infection=site_of_infection,
                risk_of_biofilm=risk_of_biofilm,
                current_response=current_response,
                creatinine_clearance=creatinine_clearance,
                severity_of_infection=severity_of_infection
            )
            # Placeholder for LLM call
            return f"Empiric therapy recommendation for: {age}, {allergies}, {labs}, {culture}, {meds}, {site_of_infection}, {risk_of_biofilm}, {current_response}, {creatinine_clearance}, {severity_of_infection}"
        except Exception as e:
            logger.error(f"EmpiricTherapyTool failed: {e}", exc_info=True)
            raise ToolExecutionError(
                message=f"EmpiricTherapyTool failed: {e}",
                code="EMPIRIC_THERAPY_ERROR",
                user_message="Unable to generate empiric therapy recommendation. Please try again or contact support.",
                original_exception=e
            )