refactor: refactor core framework to better propogate feedbacks (#599)

* refactor: Update type annotations and remove unused class in evolving modules

* refactor: Simplify evolving agent and feedback handling in CoSTEER module

* lint & CI

* mypy

* ruff for core

* mypy

* refactor: remove unnecessary comments and update feedback handling logic

* refactor: Add prev_task_feedback parameter to evolving strategies

* feat: Clear folder before extracting zip file in DockerEnv

* fix: Correct retrieval of last experiment from history

rdagent/components/coder/factor_coder/__init__.py

@@ -5,6 +5,7 @@ from rdagent.components.coder.factor_coder.evaluators import FactorEvaluatorForC
 from rdagent.components.coder.factor_coder.evolving_strategy import (
     FactorMultiProcessEvolvingStrategy,
 )
+from rdagent.core.experiment import Experiment
 from rdagent.core.scenario import Scenario
 
 
@@ -20,3 +21,11 @@ class FactorCoSTEER(CoSTEER):
         es = FactorMultiProcessEvolvingStrategy(scen=scen, settings=FACTOR_COSTEER_SETTINGS)
 
         super().__init__(*args, settings=setting, eva=eva, es=es, evolving_version=2, scen=scen, **kwargs)
+
+    def develop(self, exp: Experiment) -> Experiment:
+        try:
+            exp = super().develop(exp)
+        finally:
+            es = self.evolve_agent.evolving_trace[-1]
+            exp.prop_dev_feedback = es.feedback
+        return exp

rdagent/components/coder/factor_coder/evolving_strategy.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 from jinja2 import Environment, StrictUndefined
 
+from rdagent.components.coder.CoSTEER.evaluators import CoSTEERSingleFeedback
 from rdagent.components.coder.CoSTEER.evolving_strategy import (
     MultiProcessEvolvingStrategy,
 )
@@ -74,6 +75,7 @@ class FactorMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
         target_task: FactorTask,
         queried_knowledge: CoSTEERQueriedKnowledge,
         workspace: FBWorkspace | None = None,
+        prev_task_feedback: CoSTEERSingleFeedback | None = None,
     ) -> str:
         target_factor_task_information = target_task.get_task_information()