apt: fix some 2

Author: zhansheng.lzs

dashscope/finetune/agentic_rl.py

@@ -103,7 +103,7 @@ async def register_functions(
                 reward_instance_ids,
                 group_reward_instance_ids,
             ) = await self.tuning.register_functions(
-                lazy_load=lazy_load or True,
+                lazy_load=lazy_load,
             )
             logger.info("Function components registered")
         except Exception as e:

dashscope/finetune/reinforcement/common/cli.py

@@ -23,6 +23,8 @@
     FunctionType,
 )
 from dashscope.finetune.reinforcement.common.errors import OutputError
+from dashscope.finetune.customize_types import FineTune
+
 
 app = typer.Typer(
     name="agentic-rl",

dashscope/finetune/reinforcement/common/model.py

@@ -1038,7 +1038,7 @@ class TuningModel(Models, BaseModel):
 
     async def register_functions(
         self,
-        lazy_load: bool = True,
+        lazy_load: Optional[bool] = True,
     ) -> tuple[
         List[str], List[str], List[str], List[str], List[str], List[str]
     ]:

dashscope/finetune/reinforcement/common/utils.py

@@ -6,7 +6,7 @@
 import os
 import uuid
 import zipfile
-from typing import Optional, List, Any, Dict, Union, Tuple
+from typing import Optional, List, Any, Dict, Union, Tuple, Literal
 
 import aiohttp
 import requests
@@ -20,6 +20,18 @@
     RetryError,
 )
 
+from dashscope.finetune.reinforcement import logger
+from dashscope.finetune.reinforcement.common.errors import (
+    InputError, OutputError, BaseConnectionError, ConfigurationError, BasePermissionError, RuntimeErrorWithCode, OSSUploadError
+)
+from dashscope.finetune.reinforcement import (LOG_LEVEL, DASHSCOPE_HTTP_BASE_URL,
+                                                   DASHSCOPE_API_KEY, BAILIAN_FILE_API,
+                                                   BAILIAN_FILE_TIMEOUT, HTTP_REQUEST_TIMEOUT,
+                                                   FC_API_KEY, FC_FILES_START, FC_PYPI_LIB, FC_PYPI_REPO, FC_LAYER_USED,
+                                                   FC_SERVER_CLASSPATH, FC_ZIP_EXCLUDE_PATTERNS, FC_OSS_FILE_SIZE_WARNING,
+                                                   LOGGER_FILTER_FIELDS, FC_WORKERS_COUNT)
+from dashscope.finetune.reinforcement.common.model_types import FileSpec, FunctionType
+
 
 def generate_random_id(prefix: str = "") -> str:
     """Generate a unique identifier with optional prefix."""
@@ -436,7 +448,10 @@ def _should_exclude(path: str, patterns: List[str]) -> Optional[str]:
                         matched = _should_exclude(
                             normalized_path, all_excludes
                         )
-                        if matched:
+
+                        if not matched:
+                            the_dirs.append(d)
+                        else:
                             logger.debug(
                                 f"Excluding directory: {normalized_path} (matched pattern: '{matched}')"
                             )
@@ -499,7 +514,7 @@ def _sync_upload_to_oss(signed_url: str, zip_path: str) -> int:
                 f"Uploading file: {zip_path} ({size_mb:.2f}MB) to OSS"
             )
 
-        with open(zip_path, "rb", encoding="utf-8") as file:
+        with open(zip_path, "rb") as file:
             response = requests.put(
                 signed_url, data=file, headers={}, timeout=BAILIAN_FILE_TIMEOUT
             )
@@ -578,7 +593,7 @@ async def to_bailian_data(files: List[FileSpec]) -> List[str]:
                 continue
 
             # Add file to form data
-            with open(file_path, "rb", encoding="utf-8") as f:
+            with open(file_path, "rb") as f:
                 form_data.add_field(
                     name="files",
                     value=f.read(),

dashscope/finetune/reinforcement/component/demo/group_reward_processor_demo.py

@@ -9,8 +9,10 @@
 from dashscope.finetune.reinforcement.component.data.base_data_model import (
     TaskStatus,
 )
-from dashscope.finetune.reinforcement.component.data.group_reward_output import (
+from dashscope.finetune.reinforcement.component.data.group_reward_input import (
     GroupRewardInput,
+)
+from dashscope.finetune.reinforcement.component.data.group_reward_output import (
     GroupRewardOutput,
     GroupReward,
 )

dashscope/finetune/reinforcement/component/func_decorator.py

@@ -139,7 +139,7 @@ async def process(self, input_data: RewardInput) -> RewardOutput:
                     )
 
             # If no aggregate function, use default weighted sum
-            total = self.get_total()
+            total = self.get_total(sub_rewards)
 
             # Return RewardOutput with calculated total
             return RewardOutput(

dashscope/finetune/reinforcement/component/processor/abstract_group_reward_processor.py

@@ -6,6 +6,7 @@
 """
 
 from abc import abstractmethod
+import asyncio
 
 from dashscope.finetune.reinforcement.component.data.group_reward_input import (
     GroupRewardInput,

dashscope/finetune/reinforcement/component/processor/abstract_processor.py

@@ -6,6 +6,7 @@
 
 from abc import ABC, abstractmethod
 from typing import Any
+import asyncio
 
 from dashscope.finetune.reinforcement.component.data.base_data_model import (
     BaseDataModel,

dashscope/finetune/reinforcement/component/processor/abstract_reward_processor.py

@@ -68,7 +68,7 @@ def __init__(self, executor: Optional[Executor] = None):
         # IMPORTANT: Subclasses MUST call super().__init__() to ensure function collection
         self._collect_functions()
 
-    async def _collect_functions(self):
+    def _collect_functions(self):
         """Collect marked sub-functions and aggregate functions in the class"""
         # Prevent duplicate collection
         if self.functions_collected:

dashscope/finetune/reinforcement/component/processor/abstract_rollout_processor.py

@@ -6,6 +6,7 @@
 """
 
 from abc import abstractmethod
+import asyncio
 
 from dashscope.finetune.reinforcement.component.data.rollout_input import (
     RolloutInput,