chore(master): release 1.4.0 (#46)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "1.3.9"
+  ".": "1.4.0"
 }

CHANGELOG.md

@@ -1,5 +1,26 @@
 # Changelog
 
+## [1.4.0](https://github.com/TPTBusiness/Predix/compare/v1.3.11...v1.4.0) (2026-05-01)
+
+
+### Features
+
+* **optimizer:** add max_positions parameter to Optuna search space ([fdb4be3](https://github.com/TPTBusiness/Predix/commit/fdb4be3b3ebd93325e7821f4251148424184a40d))
+
+## [1.3.11](https://github.com/TPTBusiness/Predix/compare/v1.3.10...v1.3.11) (2026-05-01)
+
+
+### Bug Fixes
+
+* **ci:** lazy import logger in predix.py and cli.py to avoid ImportError in test env ([60763e8](https://github.com/TPTBusiness/Predix/commit/60763e8eae34f41865ba8e5e65bdfde13b564b4b))
+
+## [1.3.10](https://github.com/TPTBusiness/Predix/compare/v1.3.9...v1.3.10) (2026-05-01)
+
+
+### Bug Fixes
+
+* **security:** replace remaining assert statements with proper error handling ([928533d](https://github.com/TPTBusiness/Predix/commit/928533d9a81bd5062f07458fbf94d3c7fe347775))
+
 ## [1.3.9](https://github.com/TPTBusiness/Predix/compare/v1.3.8...v1.3.9) (2026-05-01)
 
 

predix.py

@@ -18,7 +18,12 @@ load_dotenv(Path(__file__).parent / ".env")
 import typer
 from rich.console import Console
 
-from rdagent.utils.env import logger
+try:
+    from rdagent.utils.env import logger
+except ImportError:
+    import logging
+
+    logger = logging.getLogger(__name__)
 
 app = typer.Typer(help="Predix - AI Quantitative Trading Agent")
 console = Console()

rdagent/app/cli.py

@@ -27,7 +27,12 @@ import typer
 from rich.console import Console
 from typing_extensions import Annotated
 
-from rdagent.utils.env import logger
+try:
+    from rdagent.utils.env import logger
+except ImportError:
+    import logging
+
+    logger = logging.getLogger(__name__)
 
 from rdagent.app.data_science.loop import main as data_science
 from rdagent.app.finetune.llm.loop import main as llm_finetune

rdagent/app/data_science/conf.py

@@ -201,6 +201,5 @@ class DataScienceBasePropSetting(KaggleBasePropSetting):
 DS_RD_SETTING = DataScienceBasePropSetting()
 
 # enable_cross_trace_diversity and llm_select_hypothesis should not be true at the same time
-assert not (
+if DS_RD_SETTING.enable_cross_trace_diversity and DS_RD_SETTING.llm_select_hypothesis:
-    DS_RD_SETTING.enable_cross_trace_diversity and DS_RD_SETTING.llm_select_hypothesis
+    raise ValueError("enable_cross_trace_diversity and llm_select_hypothesis cannot be true at the same time")
-), "enable_cross_trace_diversity and llm_select_hypothesis cannot be true at the same time"

rdagent/app/finetune/llm/loop.py

@@ -58,18 +58,18 @@ def main(
 
     if user_target_scenario:
         FT_RD_SETTING.user_target_scenario = user_target_scenario
-    assert (
+    if FT_RD_SETTING.user_target_scenario is not None:
-        FT_RD_SETTING.user_target_scenario is None
+        raise ValueError("user_target_scenario is not yet supported, please specify via benchmark and benchmark_description")
-    ), "user_target_scenario is not yet supported, please specify via benchmark and benchmark_description"
     if upper_data_size_limit:
         FT_RD_SETTING.upper_data_size_limit = upper_data_size_limit
         logger.info(f"Set upper_data_size_limit to {FT_RD_SETTING.upper_data_size_limit}")
     if benchmark and benchmark_description:
         FT_RD_SETTING.target_benchmark = benchmark
         FT_RD_SETTING.benchmark_description = benchmark_description
-    assert FT_RD_SETTING.user_target_scenario or (
+    if not (
-        FT_RD_SETTING.target_benchmark and FT_RD_SETTING.benchmark_description
+        FT_RD_SETTING.user_target_scenario or (FT_RD_SETTING.target_benchmark and FT_RD_SETTING.benchmark_description)
-    ), "Either user_target_scenario or target_benchmark must be specified for LLM fine-tuning."
+    ):
+        raise ValueError("Either user_target_scenario or target_benchmark must be specified for LLM fine-tuning.")
 
     # Update configuration with provided parameters
     if dataset:
@@ -82,9 +82,8 @@ def main(
     model_target = FT_RD_SETTING.base_model if FT_RD_SETTING.base_model else "auto selected model"
 
     # Temporary assertion until auto-selection is implemented
-    assert (
+    if FT_RD_SETTING.base_model is None:
-        FT_RD_SETTING.base_model is not None
+        raise ValueError("Base model auto selection not yet supported, please specify via --base-model")
-    ), "Base model auto selection not yet supported, please specify via --base-model"
 
     logger.info(f"Starting LLM fine-tuning on dataset='{data_set_target}' with model='{model_target}'")
 

rdagent/app/qlib_rd_loop/quant.py

@@ -78,7 +78,8 @@ class QuantRDLoop(RDLoop):
         while True:
             if self.get_unfinished_loop_cnt(self.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel():
                 hypo = self._propose()
-                assert hypo.action in ["factor", "model"]
+                if hypo.action not in ["factor", "model"]:
+                    raise ValueError(f"hypo.action must be 'factor' or 'model', got {hypo.action!r}")
                 if hypo.action == "factor":
                     exp = self.factor_hypothesis2experiment.convert(hypo, self.trace)
                 else:

rdagent/components/coder/CoSTEER/__init__.py

@@ -75,8 +75,10 @@ class CoSTEER(Developer[Experiment]):
 
     def _get_last_fb(self) -> CoSTEERMultiFeedback:
         fb = self.evolve_agent.evolving_trace[-1].feedback
-        assert fb is not None, "feedback is None"
+        if fb is None:
-        assert isinstance(fb, CoSTEERMultiFeedback), "feedback must be of type CoSTEERMultiFeedback"
+            raise AssertionError("feedback is None")
+        if not isinstance(fb, CoSTEERMultiFeedback):
+            raise TypeError("feedback must be of type CoSTEERMultiFeedback")
         return fb
 
     def should_use_new_evo(self, base_fb: CoSTEERMultiFeedback | None, new_fb: CoSTEERMultiFeedback) -> bool:
@@ -121,7 +123,8 @@ class CoSTEER(Developer[Experiment]):
 
         for evo_exp in self.evolve_agent.multistep_evolve(evo_exp, self.evaluator):
             iteration_count += 1
-            assert isinstance(evo_exp, Experiment)  # multiple inheritance
+            if not isinstance(evo_exp, Experiment):
+                raise TypeError("evo_exp must be an instance of Experiment")
             evo_fb = self._get_last_fb()
             update_fallback = self.should_use_new_evo(
                 base_fb=fallback_evo_fb,
@@ -154,7 +157,8 @@ class CoSTEER(Developer[Experiment]):
                 evo_exp = fallback_evo_exp
                 evo_exp.recover_ws_ckp()
                 evo_fb = fallback_evo_fb
-            assert evo_fb is not None  # multistep_evolve should run at least once
+            if evo_fb is None:
+                raise AssertionError("multistep_evolve should run at least once")
             evo_exp = self._exp_postprocess_by_feedback(evo_exp, evo_fb)
         except CoderError as e:
             e.caused_by_timeout = reached_max_seconds
@@ -264,9 +268,12 @@ class CoSTEER(Developer[Experiment]):
         - Raise Error if it failed to handle the develop task
         -
         """
-        assert isinstance(evo, Experiment)
+        if not isinstance(evo, Experiment):
-        assert isinstance(feedback, CoSTEERMultiFeedback)
+            raise TypeError("evo must be an instance of Experiment")
-        assert len(evo.sub_workspace_list) == len(feedback)
+        if not isinstance(feedback, CoSTEERMultiFeedback):
+            raise TypeError("feedback must be an instance of CoSTEERMultiFeedback")
+        if len(evo.sub_workspace_list) != len(feedback):
+            raise ValueError("Length of sub_workspace_list must match length of feedback")
 
         # FIXME: when whould the feedback be None?
         failed_feedbacks = [

rdagent/components/coder/CoSTEER/evolving_strategy.py

@@ -122,7 +122,8 @@ class MultiProcessEvolvingStrategy(EvolvingStrategy):
         last_feedback = None
         if len(evolving_trace) > 0:
             last_feedback = evolving_trace[-1].feedback
-            assert isinstance(last_feedback, CoSTEERMultiFeedback)
+            if not isinstance(last_feedback, CoSTEERMultiFeedback):
+                raise TypeError("last_feedback must be of type CoSTEERMultiFeedback")
 
         # 1.找出需要evolve的task
         to_be_finished_task_index: list[int] = []

rdagent/components/coder/CoSTEER/knowledge_management.py

@@ -1028,7 +1028,8 @@ class CoSTEERKnowledgeBaseV2(EvolvingKnowledgeBase):
 
         """
         node_count = len(nodes)
-        assert node_count >= 2, "nodes length must >=2"
+        if node_count < 2:
+            raise ValueError("nodes length must >=2")
         intersection_node_list = []
         if output_intersection_origin:
             origin_list = []

rdagent/components/coder/model_coder/eva_utils.py

@@ -58,10 +58,12 @@ class ModelCodeEvaluator(CoSTEEREvaluator):
         model_execution_feedback: str = "",
         model_value_feedback: str = "",
     ):
-        assert isinstance(target_task, ModelTask)
+        if not isinstance(target_task, ModelTask):
-        assert isinstance(implementation, ModelFBWorkspace)
+            raise TypeError("target_task must be of type ModelTask")
-        if gt_implementation is not None:
+        if not isinstance(implementation, ModelFBWorkspace):
-            assert isinstance(gt_implementation, ModelFBWorkspace)
+            raise TypeError("implementation must be of type ModelFBWorkspace")
+        if gt_implementation is not None and not isinstance(gt_implementation, ModelFBWorkspace):
+            raise TypeError("gt_implementation must be of type ModelFBWorkspace")
 
         model_task_information = target_task.get_task_information()
         code = implementation.all_codes
@@ -113,10 +115,12 @@ class ModelFinalEvaluator(CoSTEEREvaluator):
         model_value_feedback: str,
         model_code_feedback: str,
     ):
-        assert isinstance(target_task, ModelTask)
+        if not isinstance(target_task, ModelTask):
-        assert isinstance(implementation, ModelFBWorkspace)
+            raise TypeError("target_task must be of type ModelTask")
-        if gt_implementation is not None:
+        if not isinstance(implementation, ModelFBWorkspace):
-            assert isinstance(gt_implementation, ModelFBWorkspace)
+            raise TypeError("implementation must be of type ModelFBWorkspace")
+        if gt_implementation is not None and not isinstance(gt_implementation, ModelFBWorkspace):
+            raise TypeError("gt_implementation must be of type ModelFBWorkspace")
 
         system_prompt = T(".prompts:evaluator_final_feedback.system").r(
             scenario=(

rdagent/components/coder/optuna_optimizer.py

@@ -292,6 +292,7 @@ class OptunaOptimizer:
             "volatility_lookback": trial.suggest_int("volatility_lookback", 5, 500, step=5),
             "signal_bias": trial.suggest_float("signal_bias", -1.0, 1.0, step=0.05),
             "max_hold_bars": trial.suggest_int("max_hold_bars", 5, 1000, step=5),
+            "max_positions": trial.suggest_int("max_positions", 1, 5, step=1),
         }
 
     # Parameters that are allowed to be negative (not clamped to 0).
@@ -308,6 +309,7 @@ class OptunaOptimizer:
         "volatility_lookback": 1.0,
         "signal_bias": -1.0,
         "max_hold_bars": 1.0,
+        "max_positions": 1.0,
     }
 
     def _suggest_bounded(
@@ -357,6 +359,7 @@ class OptunaOptimizer:
             "volatility_lookback": (center.get("volatility_lookback", 100), 30),
             "signal_bias": (center.get("signal_bias", 0.0), 0.2),
             "max_hold_bars": (center.get("max_hold_bars", 100), 50),
+            "max_positions": (center.get("max_positions", 1), 2),
         }
         return {key: self._suggest_bounded(trial, key, c, hw) for key, (c, hw) in ranges.items()}
 
@@ -388,6 +391,7 @@ class OptunaOptimizer:
             "volatility_lookback": (center.get("volatility_lookback", 100), 10),
             "signal_bias": (center.get("signal_bias", 0.0), 0.07),
             "max_hold_bars": (center.get("max_hold_bars", 100), 17),
+            "max_positions": (center.get("max_positions", 1), 1),
         }
         return {key: self._suggest_bounded(trial, key, c, hw) for key, (c, hw) in ranges.items()}
 
@@ -467,6 +471,9 @@ class OptunaOptimizer:
 
             # Max holding periods (in bars)
             "max_hold_bars": trial.suggest_int("max_hold_bars", 10, 500, step=10),
+
+            # Max concurrent positions (1 = no pyramiding, 2-5 = scale-in)
+            "max_positions": trial.suggest_int("max_positions", 1, 5, step=1),
         }
 
         return params
@@ -597,6 +604,13 @@ class OptunaOptimizer:
             if signal_bias != 0.0:
                 signal = (signal.astype(float) + signal_bias).round().astype(int).clip(-1, 1)
 
+            # Apply max_positions: scale signal by position_size_pct and cap exposure
+            max_positions   = int(params.get("max_positions", 1))
+            position_size_pct = float(params.get("position_size_pct", 1.0))
+            # Each "position" is position_size_pct of equity; total exposure capped at max_positions × size
+            effective_size  = min(position_size_pct * max_positions, 1.0)
+            signal = (signal.astype(float) * effective_size).clip(-1.0, 1.0)
+
             # Build a synthetic close from the factor-mean so we can route
             # through the same unified engine as every other backtest path.
             # Backtest formulas must match the orchestrator's real-OHLCV path.

rdagent/components/document_reader/document_reader.py

@@ -85,13 +85,16 @@ def load_and_process_one_pdf_by_azure_document_intelligence(
 
 
 def load_and_process_pdfs_by_azure_document_intelligence(path: Path) -> dict[str, str]:
-    assert RD_AGENT_SETTINGS.azure_document_intelligence_key is not None
+    if RD_AGENT_SETTINGS.azure_document_intelligence_key is None:
-    assert RD_AGENT_SETTINGS.azure_document_intelligence_endpoint is not None
+        raise AssertionError("azure_document_intelligence_key must be set")
+    if RD_AGENT_SETTINGS.azure_document_intelligence_endpoint is None:
+        raise AssertionError("azure_document_intelligence_endpoint must be set")
 
     content_dict = {}
     ab_path = path.resolve()
     if ab_path.is_file():
-        assert ".pdf" in ab_path.suffixes, "The file must be a PDF file."
+        if ".pdf" not in ab_path.suffixes:
+            raise ValueError("The file must be a PDF file.")
         proc = load_and_process_one_pdf_by_azure_document_intelligence
         content_dict[str(ab_path)] = proc(
             ab_path,

rdagent/components/loader/task_loader.py

@@ -87,7 +87,8 @@ class ModelWsLoader(WsLoader[ModelTask, ModelFBWorkspace]):
         self.path = Path(path)
 
     def load(self, task: ModelTask) -> ModelFBWorkspace:
-        assert task.name is not None
+        if task.name is None:
+            raise AssertionError("task.name should not be None")
         mti = ModelFBWorkspace(task)
         mti.prepare()
         with open(self.path / f"{task.name}.py", "r") as f:

rdagent/oai/backend/base.py

@@ -541,7 +541,8 @@ class APIBackend(ABC):
         **kwargs,
     ) -> str | list[list[float]]:
         """This function to share operation between embedding and chat completion"""
-        assert not (chat_completion and embedding), "chat_completion and embedding cannot be True at the same time"
+        if chat_completion and embedding:
+            raise ValueError("chat_completion and embedding cannot be True at the same time")
         max_retry = LLM_SETTINGS.max_retry if LLM_SETTINGS.max_retry is not None else max_retry
         timeout_count = 0
         violation_count = 0

rdagent/scenarios/data_science/debug/data.py

@@ -268,7 +268,8 @@ class JsonReducer(DataReducer):
                 parent[key] = sampled  # type: ignore  # parent 是 list，key 是 index, list.__setitem__(key, sampled)
             self.sampled_files.extend([self.extract_filename(i) for i in sampled])
             break
-        assert len(self.sampled_files) > 0
+        if len(self.sampled_files) <= 0:
+            raise AssertionError("sampled_files must contain at least one file")
         return data
 
     def _find_all_lists(

rdagent/scenarios/data_science/example/source_data/arf-12-hours-prediction-task/prepare.py

@@ -56,14 +56,17 @@ sparse.save_npz(public / "test" / "X.npz", X_test)
 sparse.save_npz(public / "train" / "X.npz", X_train)
 df_train.to_csv(public / "train" / "ARF_12h.csv", index=False)
 
-assert (
+if X_train.shape[0] != df_train.shape[0]:
-    X_train.shape[0] == df_train.shape[0]
+    raise ValueError(
-), f"Mismatch: X_train rows ({X_train.shape[0]}) != df_train rows ({df_train.shape[0]})"
+        f"Mismatch: X_train rows ({X_train.shape[0]}) != df_train rows ({df_train.shape[0]})"
-assert (
+    )
-    X_test.shape[0] == df_test.shape[0]
+if X_test.shape[0] != df_test.shape[0]:
-), f"Mismatch: X_test rows ({X_test.shape[0]}) != df_test rows ({df_test.shape[0]})"
+    raise ValueError(
-assert df_test.shape[1] == 2, "Public test set should have 2 columns"
+        f"Mismatch: X_test rows ({X_test.shape[0]}) != df_test rows ({df_test.shape[0]})"
-assert df_train.shape[1] == 3, "Public train set should have 3 columns"
+    )
-assert len(df_train) + len(df_test) == len(
+if df_test.shape[1] != 2:
-    df_label
+    raise ValueError("Public test set should have 2 columns")
-), "Length of new_train and new_test should equal length of old_train"
+if df_train.shape[1] != 3:
+    raise ValueError("Public train set should have 3 columns")
+if len(df_train) + len(df_test) != len(df_label):
+    raise ValueError("Length of new_train and new_test should equal length of old_train")

rdagent/scenarios/data_science/loop.py

@@ -320,7 +320,8 @@ class DataScienceRDLoop(RDLoop):
             # only clean current workspace without affecting other loops.
             for k in "direct_exp_gen", "coding", "running":
                 if k in prev_out and prev_out[k] is not None:
-                    assert isinstance(prev_out[k], DSExperiment)
+                    if not isinstance(prev_out[k], DSExperiment):
+                        raise TypeError(f"prev_out[{k!r}] must be an instance of DSExperiment")
                     clean_workspace(prev_out[k].experiment_workspace.workspace_path)
 
             # Backup the workspace (only necessary files are included)

rdagent/scenarios/data_science/proposal/exp_gen/base.py

@@ -213,7 +213,8 @@ class DSTrace(Trace[DataScienceScen, KnowledgeBase]):
         self, component: COMPONENT, search_list: list[tuple[DSExperiment, ExperimentFeedback]] = []
     ) -> bool:
         for exp, fb in search_list:
-            assert isinstance(exp.hypothesis, DSHypothesis), "Hypothesis should be DSHypothesis (and not None)"
+            if not isinstance(exp.hypothesis, DSHypothesis):
+                raise TypeError("Hypothesis should be DSHypothesis (and not None)")
             if exp.hypothesis.component == component and fb:
                 return True
         return False

rdagent/scenarios/data_science/proposal/exp_gen/merge.py

@@ -377,7 +377,8 @@ class ExpGen2TraceAndMergeV2(ExpGen):
             if DS_RD_SETTING.enable_multi_version_exp_gen:
                 exp_gen_version_list = DS_RD_SETTING.exp_gen_version_list.split(",")
                 for version in exp_gen_version_list:
-                    assert version in ["v3", "v2", "v1"]
+                    if version not in ["v3", "v2", "v1"]:
+                        raise ValueError(f"version must be 'v1', 'v2', or 'v3', got {version!r}")
 
                 if len(trace.hist) == 0:
                     # set the proposal version for the first sub-trace

rdagent/scenarios/data_science/proposal/exp_gen/proposal.py

@@ -339,7 +339,8 @@ class DSProposalV1ExpGen(ExpGen):
             eda_output = sota_exp.experiment_workspace.file_dict.get("EDA.md", None)
         scenario_desc = trace.scen.get_scenario_all_desc(eda_output=eda_output)
 
-        assert sota_exp is not None, "SOTA experiment is not provided."
+        if sota_exp is None:
+            raise ValueError("SOTA experiment is not provided.")
         last_exp = trace.last_exp()
         # exp_and_feedback = trace.hist[-1]
         # last_exp = exp_and_feedback[0]
@@ -445,8 +446,10 @@ class DSProposalV1ExpGen(ExpGen):
                         json_target_type=dict[str, dict[str, str | dict] | str],
                     )
                 )
-                assert "hypothesis_proposal" in resp_dict, "Hypothesis proposal not provided."
+                if "hypothesis_proposal" not in resp_dict:
-                assert "task_design" in resp_dict, "Task design not provided."
+                    raise ValueError("Hypothesis proposal not provided.")
+                if "task_design" not in resp_dict:
+                    raise ValueError("Task design not provided.")
                 task_class = component_info["task_class"]
                 hypothesis_proposal = resp_dict.get("hypothesis_proposal", {})
                 hypothesis = DSHypothesis(
@@ -1149,8 +1152,10 @@ You help users retrieve relevant knowledge from community discussions and public
         )
 
         response_dict = json.loads(response)
-        assert response_dict.get("component") in HypothesisComponent.__members__, f"Invalid component"
+        if response_dict.get("component") not in HypothesisComponent.__members__:
-        assert response_dict.get("hypothesis") is not None, f"Invalid hypothesis"
+            raise ValueError(f"Invalid component: {response_dict.get('component')}")
+        if response_dict.get("hypothesis") is None:
+            raise ValueError("Invalid hypothesis")
         return response_dict
 
     # END: for support llm-based hypothesis selection  -----
@@ -1253,7 +1258,8 @@ You help users retrieve relevant knowledge from community discussions and public
             description=task_desc,
         )
 
-        assert isinstance(task, PipelineTask), f"Task {task_name} is not a PipelineTask, got {type(task)}"
+        if not isinstance(task, PipelineTask):
+            raise TypeError(f"Task {task_name} is not a PipelineTask, got {type(task)}")
         # only for llm with response schema.(TODO: support for non-schema llm?)
         # If the LLM provides a "packages" field (list[str]), compute runtime environment now and cache it for subsequent prompts in later loops.
         if isinstance(task_dict, dict) and "packages" in task_dict and isinstance(task_dict["packages"], list):

rdagent/scenarios/kaggle/experiment/scenario.py

@@ -165,7 +165,8 @@ class KGScenario(Scenario):
         return data_info
 
     def output_format(self, tag=None) -> str:
-        assert tag in [None, "feature", "model"]
+        if tag not in [None, "feature", "model"]:
+            raise ValueError(f"tag must be None, 'feature', or 'model', got {tag!r}")
         feature_output_format = f"""The feature code should output following the format:
 {T(".prompts:kg_feature_output_format").r()}"""
         model_output_format = f"""The model code should output following the format:\n""" + T(
@@ -180,7 +181,8 @@ class KGScenario(Scenario):
             return model_output_format
 
     def interface(self, tag=None) -> str:
-        assert tag in [None, "feature", "XGBoost", "RandomForest", "LightGBM", "NN"]
+        if tag not in [None, "feature", "XGBoost", "RandomForest", "LightGBM", "NN"]:
+            raise ValueError(f"tag must be None, 'feature', 'XGBoost', 'RandomForest', 'LightGBM', or 'NN', got {tag!r}")
         feature_interface = f"""The feature code should follow the interface:
 {T(".prompts:kg_feature_interface").r()}"""
         if tag == "feature":
@@ -195,7 +197,8 @@ class KGScenario(Scenario):
             return model_interface
 
     def simulator(self, tag=None) -> str:
-        assert tag in [None, "feature", "model"]
+        if tag not in [None, "feature", "model"]:
+            raise ValueError(f"tag must be None, 'feature', or 'model', got {tag!r}")
 
         kg_feature_simulator = (
             "The feature code will be sent to the simulator:\n" + T(".prompts:kg_feature_simulator").r()

rdagent/scenarios/kaggle/kaggle_crawler.py

@@ -87,7 +87,12 @@ def crawl_descriptions(
         content = e.get_attribute("innerHTML")
         contents.append(content)
 
-    assert len(subtitles) == len(contents) + 1 and subtitles[-1] == "Citation"
+    if not (len(subtitles) == len(contents) + 1 and subtitles[-1] == "Citation"):
+        raise AssertionError(
+            f"Expected len(contents)+1 == len(subtitles) and last subtitle == 'Citation', "
+            f"got len(subtitles)={len(subtitles)}, len(contents)={len(contents)}, "
+            f"last subtitle={subtitles[-1]!r}"
+        )
     for i in range(len(subtitles) - 1):
         descriptions[subtitles[i]] = contents[i]
 

rdagent/scenarios/kaggle/proposal/proposal.py

@@ -307,7 +307,8 @@ class KGHypothesisGen(FactorAndModelHypothesisGen):
 class KGHypothesis2Experiment(FactorAndModelHypothesis2Experiment):
     def prepare_context(self, hypothesis: Hypothesis, trace: Trace) -> Tuple[dict, bool]:
         scenario = trace.scen.get_scenario_all_desc(filtered_tag="hypothesis_and_experiment")
-        assert isinstance(hypothesis, KGHypothesis)
+        if not isinstance(hypothesis, KGHypothesis):
+            raise TypeError("hypothesis must be an instance of KGHypothesis")
         experiment_output_format = (
             T("scenarios.kaggle.prompts:feature_experiment_output_format").r()
             if hypothesis.action in [KG_ACTION_FEATURE_ENGINEERING, KG_ACTION_FEATURE_PROCESSING]

rdagent/scenarios/qlib/experiment/quant_experiment.py

@@ -56,7 +56,8 @@ class QlibQuantScenario(Scenario):
         )
 
     def background(self, tag=None) -> str:
-        assert tag in [None, "factor", "model"]
+        if tag not in [None, "factor", "model"]:
+            raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}")
         quant_background = "The background of the scenario is as follows:\n" + T(".prompts:qlib_quant_background").r(
             runtime_environment=self.get_runtime_environment(),
         )
@@ -83,7 +84,8 @@ class QlibQuantScenario(Scenario):
         return self._source_data
 
     def output_format(self, tag=None) -> str:
-        assert tag in [None, "factor", "model"]
+        if tag not in [None, "factor", "model"]:
+            raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}")
         factor_output_format = (
             "The factor code should output the following format:\n" + T(".prompts:qlib_factor_output_format").r()
         )
@@ -99,7 +101,8 @@ class QlibQuantScenario(Scenario):
             return model_output_format
 
     def interface(self, tag=None) -> str:
-        assert tag in [None, "factor", "model"]
+        if tag not in [None, "factor", "model"]:
+            raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}")
         factor_interface = (
             "The factor code should be written in the following interface:\n" + T(".prompts:qlib_factor_interface").r()
         )
@@ -115,7 +118,8 @@ class QlibQuantScenario(Scenario):
             return model_interface
 
     def simulator(self, tag=None) -> str:
-        assert tag in [None, "factor", "model"]
+        if tag not in [None, "factor", "model"]:
+            raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}")
         factor_simulator = "The factor code will be sent to the simulator:\n" + T(".prompts:qlib_factor_simulator").r()
         model_simulator = "The model code will be sent to the simulator:\n" + T(".prompts:qlib_model_simulator").r()
 
@@ -185,7 +189,8 @@ class QlibQuantScenario(Scenario):
             return common_description(action) + interface(action) + output(action) + simulator(action)
 
     def get_runtime_environment(self, tag: str = None) -> str:
-        assert tag in [None, "factor", "model"]
+        if tag not in [None, "factor", "model"]:
+            raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}")
 
         if tag is None or tag == "factor":
             # Use factor env to get the runtime environment

rdagent/utils/env.py

@@ -620,7 +620,8 @@ class LocalEnv(Env[ASpecificLocalConf]):
         for lp, rp in running_extra_volume.items():
             volumes[lp] = rp
 
-        assert local_path is not None, "local_path should not be None"
+        if local_path is None:
+            raise ValueError("local_path should not be None")
         volumes = normalize_volumes(volumes, local_path)
 
         @contextlib.contextmanager
@@ -1472,7 +1473,8 @@ class DockerEnv(Env[DockerConf]):
                 cpu_count=self.conf.cpu_count,  # Set CPU limit
                 **self._gpu_kwargs(client),
             )
-            assert container is not None  # Ensure container was created successfully
+            if container is None:
+                raise AssertionError("Docker container was not created successfully")
             logs = container.logs(stream=True)
             print(Rule("[bold green]Docker Logs Begin[/bold green]", style="dark_orange"))
             table = Table(title="Run Info", show_header=False)

rdagent/utils/workflow/tracking.py

@@ -84,7 +84,8 @@ class WorkflowTracker:
             # Log timer status if timer is started
             if self.loop_base.timer.started:
                 remain_time = self.loop_base.timer.remain_time()
-                assert remain_time is not None
+                if remain_time is None:
+                    raise AssertionError("remain_time should not be None")
                 mlflow.log_metric("remain_time", remain_time.total_seconds())
                 mlflow.log_metric(
                     "remain_percent",