add feedback to workspace and ds runner base on costeer

This commit is contained in:
Xu Yang
2025-02-11 20:50:19 +08:00
committed by GitHub
parent 18de5eea43
commit c1085921b5
25 changed files with 383 additions and 231 deletions
@@ -97,21 +97,21 @@ class WorkflowGeneralCaseSpecEvaluator(CoSTEEREvaluator):
if not submission_fp.exists():
stdout += "\nSubmission file (submission.csv) is not generated."
else:
base_check_code = (DIRNAME / "eval_tests" / "submission_check.txt").read_text()
implementation.inject_files(**{"submission_check.py": base_check_code})
base_check_code = (DIRNAME / "eval_tests" / "submission_format_test.txt").read_text()
implementation.inject_files(**{"submission_format_test.py": base_check_code})
# stdout += "----Submission Check 1-----\n"
stdout += implementation.execute(env=de, entry="python submission_check.py")
stdout += implementation.execute(env=de, entry="python submission_format_test.py")
# MLEBench Check
# !!! Since we are running on a sampled dataset, mlebench check is not required.
# mle_check_code = (
# (DIRNAME / "eval_tests" / "mle_submission_check.txt")
# (DIRNAME / "eval_tests" / "mle_submission_format_test.txt")
# .read_text()
# .replace("<competition_id>", self.scen.competition)
# )
# implementation.inject_files(**{"mle_submission_check.py": mle_check_code})
# implementation.inject_files(**{"mle_submission_format_test.py": mle_check_code})
# stdout += "----Submission Check 2-----\n"
# stdout += implementation.execute(env=mde, entry=f"python mle_submission_check.py")
# stdout += implementation.execute(env=mde, entry=f"python mle_submission_format_test.py")
system_prompt = T(".prompts:workflow_eval.system").r(
scenario=self.scen.get_scenario_all_desc(),