import evoagentx.workflow.operators as operator
import examples.aflow.humanevalplus_renew.optimized.round_6.prompt as prompt_custom
from evoagentx.models.model_configs import LLMConfig
from evoagentx.benchmark.benchmark import Benchmark
from evoagentx.models.model_utils import create_llm_instance

class Workflow:
    
    def __init__(
        self,
        name: str,
        llm_config: LLMConfig,
        benchmark: Benchmark
    ):
        self.name = name
        self.llm = create_llm_instance(llm_config)
        self.benchmark = benchmark 
        self.custom = operator.Custom(self.llm)
        self.custom_code_generate = operator.CustomCodeGenerate(self.llm)
        self.test = operator.Test(self.llm)  # Initialize the Test operator
        self.sc_ensemble = operator.ScEnsemble(self.llm)  # Initialize the ScEnsemble operator
        self.log = []  # Initialize a log list to track results

    async def __call__(self, problem: str, entry_point: str):
        """
        Implementation of the workflow
        Custom operator to generate anything you want.
        But when you want to get standard code, you should use custom_code_generate operator.
        """
        solution = await self.custom_code_generate(problem=problem, entry_point=entry_point, instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT)
        
        # Log the generated solution
        self.log.append({'step': 'custom_code_generate', 'result': solution['response']})

        # Test the generated solution
        test_result = await self.test(problem=problem, solution=solution['response'], entry_point=entry_point, benchmark=self.benchmark)
        
        if not test_result['result']:
            # Log the failure of the initial solution
            self.log.append({'step': 'test', 'result': 'failed', 'solution': solution['response']})
            
            # If the solution fails, generate alternative solutions
            alternative_solutions = await self.custom(problem=problem, instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT)
            # Use ScEnsemble to select the best solution from alternatives
            ensemble_result = await self.sc_ensemble(solutions=[solution['response'], alternative_solutions['response']], problem=problem)
            # Log the ensemble result
            self.log.append({'step': 'ensemble', 'result': ensemble_result['response']})
            return ensemble_result['response']
        
        # Log the success of the initial solution
        self.log.append({'step': 'test', 'result': 'success', 'solution': solution['response']})
        return solution['response']