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/data_science/feature/__init__.py

@@ -2,7 +2,10 @@ import json
 
 from rdagent.components.coder.CoSTEER import CoSTEER
 from rdagent.components.coder.CoSTEER.config import CoSTEER_SETTINGS
-from rdagent.components.coder.CoSTEER.evaluators import CoSTEERMultiEvaluator
+from rdagent.components.coder.CoSTEER.evaluators import (
+    CoSTEERMultiEvaluator,
+    CoSTEERSingleFeedback,
+)
 from rdagent.components.coder.CoSTEER.evolving_strategy import (
     MultiProcessEvolvingStrategy,
 )
@@ -24,6 +27,7 @@ class FeatureMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
         target_task: FeatureTask,
         queried_knowledge: CoSTEERQueriedKnowledge | None = None,
         workspace: FBWorkspace | None = None,
+        prev_task_feedback: CoSTEERSingleFeedback | None = None,
     ) -> dict[str, str]:
         # return a workspace with "load_data.py", "spec/load_data.md" inside
         # assign the implemented code to the new workspace.
@@ -59,7 +63,7 @@ class FeatureMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
         user_prompt = T(".prompts:feature_coder.user").r(
             feature_spec=workspace.file_dict["spec/feature.md"],
             latest_code=workspace.file_dict.get("feature.py"),
-            latest_code_feedback=workspace.feedback,
+            latest_code_feedback=prev_task_feedback,
         )
 
         for _ in range(5):