feat: dump model (#776)

* feat: add model dump flag and multi-evaluator support

* tmp code

* refactor: update evaluator feedback and FBWorkspace types

* feat: add get_clear_ws_cmd and CPU count in Docker environment

* feat: Add model dump check level and enhance evaluator functionality

fix data type bug

* fix: Ensure required files exist before model dump evaluation

* refactor: streamline prompt and file checks in model dump evaluation

* fix: add assertions and reorder file reads in model dump evaluator

* feat: remove EDA part from evaluation output

* docs: update dump_model guidelines and eval prompt to include template

* style: reformat multiline dicts and lists in conf and eval files

* fix: add DOTALL flag to EDA removal regex

rdagent/components/coder/data_science/pipeline/eval.py

@@ -15,7 +15,7 @@ from rdagent.components.coder.CoSTEER.evaluators import (
 from rdagent.components.coder.CoSTEER.knowledge_management import (
     CoSTEERQueriedKnowledgeV2,
 )
-from rdagent.components.coder.data_science.conf import get_ds_env
+from rdagent.components.coder.data_science.conf import get_clear_ws_cmd, get_ds_env
 from rdagent.core.experiment import FBWorkspace, Task
 from rdagent.utils.agent.tpl import T
 from rdagent.utils.agent.workflow import build_cls_from_json_with_retry
@@ -55,7 +55,7 @@ class PipelineCoSTEEREvaluator(CoSTEEREvaluator):
         env.conf.extra_volumes = {f"{DS_RD_SETTING.local_data_path}/sample/{self.scen.competition}": "/kaggle/input"}
 
         # Clean the scores.csv & submission.csv.
-        implementation.execute(env=env, entry=f"rm submission.csv scores.csv")
+        implementation.execute(env=env, entry=get_clear_ws_cmd())
         stdout, execute_ret_code = implementation.execute_ret_code(env=env, entry=f"python main.py")
         stdout = re.sub(r"=== Start of EDA part ===(.*)=== End of EDA part ===", "", stdout)