fix: main bug (#938)

* feat: parameterize cache paths with USER to avoid conflicts

* guide for missing training_hyperparameters

* guidance for  KeyError: 'concise_reason'

* fixed three bugs in the test

* fix general_model task bug

* fixed some bugs in the med_model scenario

* delete comments

* format with black

* fix mypy error

* fix ruff error

* fix isort error

* sync code

* revert cache_path code

* revert cache_path code

* delete data mining scenario

* fix factor report loop

* fix LiteLLMAPIBackend log_llm_chat_content setting

* refine fin factor report scenario

* remove unused LogColors

* fix UI

* remove medical scenario docs

* change **kaggle** to **data_science**

* remove default dataset_path in create_debug_data

* remove KAGGLE_SETTINGS in kaggle_crawler

* limit litellm versions

* reformat with black

* change README

* fix_data_science_docs

* make hypothesis observations string

* Hiding old versions of kaggle docs

* hidding kaggle agent docs

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: Bowen Xian <xianbowen@outlook.com>
Co-authored-by: yuanteli <1957922024@qq.com>

rdagent/components/coder/model_coder/task_loader.py

@@ -3,6 +3,8 @@ from __future__ import annotations
 import json
 import re
 
+from pydantic import BaseModel, Field
+
 from rdagent.components.coder.model_coder.model import ModelTask
 from rdagent.components.document_reader.document_reader import (
     load_and_process_pdfs_by_langchain,
@@ -12,6 +14,7 @@ from rdagent.log import rdagent_logger as logger
 from rdagent.oai.llm_utils import APIBackend
 from rdagent.scenarios.qlib.experiment.model_experiment import QlibModelExperiment
 from rdagent.utils.agent.tpl import T
+from rdagent.utils.workflow import wait_retry
 
 
 def extract_model_from_doc(doc_content: str) -> dict:
@@ -105,6 +108,7 @@ class ModelExperimentLoaderFromDict(ModelTaskLoader):
                 architecture=model_data["architecture"],
                 variables=model_data["variables"],
                 hyperparameters=model_data["hyperparameters"],
+                training_hyperparameters=model_data["training_hyperparameters"],
                 model_type=model_data["model_type"],
             )
             task_l.append(task)
@@ -112,6 +116,7 @@ class ModelExperimentLoaderFromDict(ModelTaskLoader):
 
 
 class ModelExperimentLoaderFromPDFfiles(ModelTaskLoader):
+    @wait_retry(retry_n=5)
     def load(self, file_or_folder_path: str) -> dict:
         docs_dict = load_and_process_pdfs_by_langchain(file_or_folder_path)  # dict{file_path:content}
         model_dict = extract_model_from_docs(