Remove dead code and obsolete modules

Author: LIHUA919

README.md

@@ -269,7 +269,7 @@ pytest -q
 Current local baseline:
 
 - 490 tests passing
-- 46 dynamically registered tools
+- 45 dynamically registered tools
 - 5 dynamically registered agents
 
 Some dependency deprecation warnings remain and are tracked separately from

benchmark/process/dataset_candidate/reasoning/math_reasoning/constant.py

@@ -1,13 +1,9 @@
 from pathlib import Path
 from tqdm import tqdm
-import multiprocessing
-from copy import deepcopy
 import re
 from lm_eval.tasks.minerva_math.utils import (
-    last_boxed_only_string,
     normalize_final_answer,
     get_unnormalized_answer,
-    remove_boxed,
     is_equiv,
 )
 
@@ -92,22 +88,6 @@ def is_correct(sample: str, gt_answer: str, dset: str):
 
 
 
-def get_tasks(config):
-    sample_paths = Path(config.samples_dir).glob("*.yaml")
-
-    tasks = []
-    for sample_path in tqdm(sample_paths, desc="Loading generations"):
-        save_path = config.save_dir / sample_path.name
-
-        task_config = deepcopy(config)
-        task_config.sample_path = sample_path
-        task_config.save_path = save_path
-
-        tasks.append(task_config)
-
-    return tasks
-
-
 def main(args):
     save_dir = Path(args.save_dir).absolute()
 

benchmark/process/dataset_candidate/reasoning/math_reasoning/get_score.py

@@ -1,21 +1,18 @@
-import torch
 from datasets import load_dataset
 from tqdm import tqdm
-import multiprocessing
 import random
-import requests
-from functools import partial
 import argparse
 from pathlib import Path    
 import yaml
-import importlib
 import os
 import asyncio
+from dotenv import load_dotenv
 from prompts import MATH_COT_PROMPT
-from constant import *
 
 import openai
 
+load_dotenv()
+
 def save_yaml(path: Path, data, sort_keys=True):
     with open(path, "w") as f:
         yaml.dump(data, f, sort_keys=sort_keys)
@@ -92,9 +89,8 @@ async def main(args):
     save_dir = Path(save_dir)
     save_dir.mkdir(parents=True, exist_ok=True)
 
-    predictions = []
     for item in tqdm(test_dataset):
-        predictions.append(await run_inference(item, save_dir, args.model, args.base_url))
+        await run_inference(item, save_dir, args.model, args.base_url)
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()

benchmark/process/dataset_candidate/reasoning/math_reasoning/run_infer.py

@@ -72,14 +72,6 @@ def get_args_research():
     return args
 
 
-def get_args_paper():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--research_field", type=str, default="vq")
-    parser.add_argument("--instance_id", type=str, default="rotation_vq")
-    args = parser.parse_args()
-    return args
-
-
 def _prepare_research_args(config):
     """Build a research args namespace from the validated config dict.
 

main_ai_researcher.py

@@ -32,9 +32,6 @@ def find_task1_content(self, benchmark_path: str, target_paper: str) -> str:
             #     if paper['target'].lower() == target_paper_lower:
             #         return paper.get('task1', '')
             return benchmark_data['task1']
-            
-            logging.warning(f"No matching paper found for: {target_paper}")
-            return ""
         except Exception as e:
             logging.error(f"Error reading benchmark file: {str(e)}")
             return ""
@@ -259,4 +256,4 @@ async def introduction_composing(research_field: str, instance_id: str):
         raise
 
 if __name__ == "__main__":
-    asyncio.run(introduction_composing())
+    asyncio.run(introduction_composing())

paper_agent/introduction_composing.py

@@ -5,16 +5,6 @@
 logger = logging.getLogger(__name__)
 
 
-def run_and_print(args):
-    result = subprocess.run(args, capture_output=True, text=True)
-    logger.info("[CMD] %s", " ".join(args))
-    if result.stdout:
-        logger.debug(result.stdout)
-    if result.stderr:
-        logger.debug(result.stderr)
-    return result
-
-
 def compile_latex_project(project_dir, main_tex_file):
     """Compile a LaTeX project with bibtex support.
 

paper_agent/tex_writer.py

@@ -21,7 +21,6 @@
 from .logger import MetaChainLogger, LoggerManager
 from httpx import RemoteProtocolError, ConnectError, TimeoutException
 from litellm.exceptions import APIError
-from tenacity import RetryCallState
 from research_agent.constant import  API_BASE_URL, CHEEP_MODEL, COMPLETION_MODEL, NOT_SUPPORT_SENDER, MUST_ADD_USER, NOT_SUPPORT_FN_CALL, NOT_USE_FN_CALL
 from research_agent.inno.fn_call_converter import convert_tools_to_description, convert_non_fncall_messages_to_fncall_messages, SYSTEM_PROMPT_SUFFIX_TEMPLATE, convert_fn_messages_to_non_fn_messages, interleave_user_into_messages
 from research_agent.inno.memory.utils import encode_string_by_tiktoken, decode_tokens_by_tiktoken
@@ -33,44 +32,6 @@
 LLM_RETRY_ATTEMPTS = int(os.getenv("LLM_RETRY_ATTEMPTS", "3"))
 LLM_RETRY_BACKOFF_SECONDS = int(os.getenv("LLM_RETRY_BACKOFF_SECONDS", "5"))
 
-def should_retry_error(retry_state: RetryCallState):
-    """检查是否应该重试错误
-    
-    Args:
-        retry_state: RetryCallState对象，包含重试状态信息
-        
-    Returns:
-        bool: 是否应该重试
-    """
-    if retry_state.outcome is None:
-        return False
-        
-    exception = retry_state.outcome.exception()
-    if exception is None:
-        return False
-        
-    print(f"Caught exception: {type(exception).__name__} - {str(exception)}")
-    
-    # 匹配更多错误类型
-    if isinstance(exception, (APIError, RemoteProtocolError, ConnectError, TimeoutException, TimeoutError)):
-        return True
-    
-    # 通过错误消息匹配
-    error_msg = str(exception).lower()
-    return any([
-        "connection error" in error_msg,
-        "server disconnected" in error_msg,
-        "eof occurred" in error_msg,
-        "timeout" in error_msg,
-        "rate limit" in error_msg,  # 添加 rate limit 错误检查
-        "rate_limit_error" in error_msg,  # Anthropic 的错误类型
-        "too many requests" in error_msg,  # HTTP 429 错误
-        "overloaded" in error_msg,  # 添加 Anthropic overloaded 错误
-        "overloaded_error" in error_msg,  # 添加 Anthropic overloaded 错误的另一种形式
-        "负载已饱和" in error_msg,  # 添加中文错误消息匹配
-        "error code: 429" in error_msg,  # 添加 HTTP 429 状态码匹配
-        "context_length_exceeded" in error_msg  # 添加上下文长度超限错误匹配
-    ])
 __CTX_VARS_NAME__ = "context_variables"
 logger = LoggerManager.get_logger()
 

paper_agent/tex_writer_ori.py

@@ -45,16 +45,5 @@ def convert_cookies_to_python():
         f.write(output_str)
     return output_str
 
-def get_all_cookies():
-    all_cookies = []
-    json_dir = wd / "cookie_json"
-    cookie_files = glob.glob(str(json_dir / "*.json"))
-    
-    for cookie_file in cookie_files:
-        json_path = wd / "cookie_json" / cookie_file
-        cookies = load_cookies_from_json(json_path)
-        all_cookies.extend(cookies)
-    return all_cookies
-
 if __name__ == "__main__":
-    print(convert_cookies_to_python())
+    print(convert_cookies_to_python())