feat: use unified pickle cacher & move llm config into a isolated config (#424)

* simplify RDAgent conf

* add unified cacher(untested)

* fix small bugs

* fix a bug

* fix a small bug in runner

* use hash_key = None to skip cache

* fix CI

* in factor execution, ignore cache when raise exception

* add file locker to avoid mp calling

* fix CI

* use function __module__ name as folder in cache

rdagent/components/coder/model_coder/conf.py

@@ -10,10 +10,6 @@ class ModelImplSettings(BaseSettings):
 
     coder_use_cache: bool = False
 
-    cache_location: str = str(
-        (Path().cwd() / "git_ignore_folder" / "model_implementation_execution_cache").absolute(),
-    )
-
     knowledge_base_path: Union[str, None] = None
     new_knowledge_base_path: Union[str, None] = None
 
@@ -23,7 +19,5 @@ class ModelImplSettings(BaseSettings):
     query_similar_success_limit: int = 5
     fail_task_trial_limit: int = 20
 
-    enable_execution_cache: bool = True  # whether to enable the execution cache
-
 
 MODEL_IMPL_SETTINGS = ModelImplSettings()