jarvis-ai-assistant 0.1.224__tar.gz → 0.2.0__tar.gz

{jarvis_ai_assistant-0.1.224/src/jarvis_ai_assistant.egg-info → jarvis_ai_assistant-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jarvis-ai-assistant
-Version: 0.1.224
+Version: 0.2.0
 Summary: Jarvis: An AI assistant that uses tools to interact with the system
 Home-page: https://github.com/skyfireitdiy/Jarvis
 Author: skyfire
@@ -57,8 +57,8 @@ Requires-Dist: pyte==0.8.2
 Requires-Dist: httpx>=0.28.1
 Requires-Dist: pyyaml>=5.3.1
 Requires-Dist: ddgs==9.0.2
-Requires-Dist: beautifulsoup4==4.13.4
 Requires-Dist: lxml==6.0.0
+Requires-Dist: markdownify>=1.1.0
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: black; extra == "dev"
@@ -158,6 +158,7 @@ jarvis --llm_type thinking -t "初始任务"
 | `-t/--task` | 直接从命令行输入任务内容 |
 | `-f/--config` | 自定义配置文件的路径 |
 | `--restore-session` | 从 .jarvis/saved_session.json 恢复会话 |
+| `-e/--edit` | 编辑配置文件 |
 
 #### 4. 工作流程
 1. 初始化环境
@@ -507,9 +508,9 @@ ENV:
 #### Kimi
 ```yaml
 JARVIS_PLATFORM: kimi
-JARVIS_MODEL: kimi
+JARVIS_MODEL: k1.5
 JARVIS_THINKING_PLATFORM: kimi
-JARVIS_THINKING_MODEL: k1
+JARVIS_THINKING_MODEL: k1.5-thinking
 ENV:
   KIMI_API_KEY: <Kimi API KEY>
 ```
@@ -534,19 +535,55 @@ OPENAI_API_KEY: <OpenAI API Key>
 OPENAI_API_BASE: https://api.openai.com/v1
 ```
 
-### 2. 配置项说明
+### 2. 模型组配置 (高级)
+
+除了单独配置每个模型参数，您还可以定义和使用**模型组**来快速切换不同的模型组合。这对于需要在不同任务或平台间频繁切换的场景非常有用。
+
+**配置示例** (`~/.jarvis/config.yaml`):
+
+```yaml
+# 定义模型组
+JARVIS_MODEL_GROUPS:
+  - kimi:
+      JARVIS_PLATFORM: kimi
+      JARVIS_MODEL: k1.5
+      JARVIS_THINKING_PLATFORM: kimi
+      JARVIS_THINKING_MODEL: k1.5-thinking
+      JARVIS_MAX_TOKEN_COUNT: 8192
+  - ai8:
+      JARVIS_PLATFORM: ai8
+      JARVIS_MODEL: gemini-2.5-pro
+      # 如果不指定思考模型，将自动使用常规模型
+      # JARVIS_THINKING_PLATFORM: ai8
+      # JARVIS_THINKING_MODEL: gemini-2.5-pro
+
+# 选择要使用的模型组
+JARVIS_MODEL_GROUP: kimi
+```
+
+**配置优先级规则:**
+
+Jarvis 会按照以下顺序解析模型配置，序号越小优先级越高：
+
+1.  **独立配置**: 直接设置的 `JARVIS_PLATFORM`, `JARVIS_MODEL`, `JARVIS_THINKING_PLATFORM`, `JARVIS_THINKING_MODEL` 环境变量。这些配置会**覆盖**任何模型组中的设置。
+2.  **模型组配置**: 通过 `JARVIS_MODEL_GROUP` 选中的模型组配置。
+3.  **默认值**: 如果以上均未配置，则使用代码中定义的默认模型（如 `yuanbao` 和 `deep_seek_v3`）。
+
+### 3. 全部配置项说明
 | 变量名称 | 默认值 | 说明 |
 |----------|--------|------|
 | `ENV` | {} | 环境变量配置 |
-| `JARVIS_MAX_TOKEN_COUNT` | 960000 | 上下文窗口的最大token数量 |
-| `JARVIS_MAX_INPUT_TOKEN_COUNT` | 32000 | 输入的最大token数量 |
-| `JARVIS_PLATFORM` | yuanbao | 默认AI平台 |
-| `JARVIS_MODEL` | deep_seek_v3 | 默认模型 |
-| `JARVIS_THINKING_PLATFORM` | JARVIS_PLATFORM | 推理任务使用的平台 |
-| `JARVIS_THINKING_MODEL` | JARVIS_MODEL | 推理任务使用的模型 |
+| `JARVIS_MODEL_GROUPS` | `[]` | 预定义的模型配置组列表 |
+| `JARVIS_MODEL_GROUP` | `null` | 选择要激活的模型组名称 |
+| `JARVIS_MAX_TOKEN_COUNT` | 960000 | 上下文窗口的最大token数量 (可被模型组覆盖) |
+| `JARVIS_MAX_INPUT_TOKEN_COUNT` | 32000 | 输入的最大token数量 (可被模型组覆盖) |
+| `JARVIS_PLATFORM` | yuanbao | 默认AI平台 (可被模型组覆盖) |
+| `JARVIS_MODEL` | deep_seek_v3 | 默认模型 (可被模型组覆盖) |
+| `JARVIS_THINKING_PLATFORM` | JARVIS_PLATFORM | 推理任务使用的平台 (可被模型组覆盖) |
+| `JARVIS_THINKING_MODEL` | JARVIS_MODEL | 推理任务使用的模型 (可被模型组覆盖) |
 | `JARVIS_EXECUTE_TOOL_CONFIRM` | false | 执行工具前是否需要确认 |
 | `JARVIS_CONFIRM_BEFORE_APPLY_PATCH` | false | 应用补丁前是否需要确认 |
-| `JARVIS_MAX_BIG_CONTENT_SIZE` | 160000 | 最大大内容大小 |
+| `JARVIS_MAX_BIG_CONTENT_SIZE` | 160000 | 最大大内容大小 (可被模型组覆盖) |
 | `JARVIS_PRETTY_OUTPUT` | false | 是否启用PrettyOutput |
 | `JARVIS_GIT_COMMIT_PROMPT` | "" | 自定义git提交信息生成提示模板 |
 | `JARVIS_PRINT_PROMPT` | false | 是否打印提示 |

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/README.md

@@ -74,6 +74,7 @@ jarvis --llm_type thinking -t "初始任务"
 | `-t/--task` | 直接从命令行输入任务内容 |
 | `-f/--config` | 自定义配置文件的路径 |
 | `--restore-session` | 从 .jarvis/saved_session.json 恢复会话 |
+| `-e/--edit` | 编辑配置文件 |
 
 #### 4. 工作流程
 1. 初始化环境
@@ -423,9 +424,9 @@ ENV:
 #### Kimi
 ```yaml
 JARVIS_PLATFORM: kimi
-JARVIS_MODEL: kimi
+JARVIS_MODEL: k1.5
 JARVIS_THINKING_PLATFORM: kimi
-JARVIS_THINKING_MODEL: k1
+JARVIS_THINKING_MODEL: k1.5-thinking
 ENV:
   KIMI_API_KEY: <Kimi API KEY>
 ```
@@ -450,19 +451,55 @@ OPENAI_API_KEY: <OpenAI API Key>
 OPENAI_API_BASE: https://api.openai.com/v1
 ```
 
-### 2. 配置项说明
+### 2. 模型组配置 (高级)
+
+除了单独配置每个模型参数，您还可以定义和使用**模型组**来快速切换不同的模型组合。这对于需要在不同任务或平台间频繁切换的场景非常有用。
+
+**配置示例** (`~/.jarvis/config.yaml`):
+
+```yaml
+# 定义模型组
+JARVIS_MODEL_GROUPS:
+  - kimi:
+      JARVIS_PLATFORM: kimi
+      JARVIS_MODEL: k1.5
+      JARVIS_THINKING_PLATFORM: kimi
+      JARVIS_THINKING_MODEL: k1.5-thinking
+      JARVIS_MAX_TOKEN_COUNT: 8192
+  - ai8:
+      JARVIS_PLATFORM: ai8
+      JARVIS_MODEL: gemini-2.5-pro
+      # 如果不指定思考模型，将自动使用常规模型
+      # JARVIS_THINKING_PLATFORM: ai8
+      # JARVIS_THINKING_MODEL: gemini-2.5-pro
+
+# 选择要使用的模型组
+JARVIS_MODEL_GROUP: kimi
+```
+
+**配置优先级规则:**
+
+Jarvis 会按照以下顺序解析模型配置，序号越小优先级越高：
+
+1.  **独立配置**: 直接设置的 `JARVIS_PLATFORM`, `JARVIS_MODEL`, `JARVIS_THINKING_PLATFORM`, `JARVIS_THINKING_MODEL` 环境变量。这些配置会**覆盖**任何模型组中的设置。
+2.  **模型组配置**: 通过 `JARVIS_MODEL_GROUP` 选中的模型组配置。
+3.  **默认值**: 如果以上均未配置，则使用代码中定义的默认模型（如 `yuanbao` 和 `deep_seek_v3`）。
+
+### 3. 全部配置项说明
 | 变量名称 | 默认值 | 说明 |
 |----------|--------|------|
 | `ENV` | {} | 环境变量配置 |
-| `JARVIS_MAX_TOKEN_COUNT` | 960000 | 上下文窗口的最大token数量 |
-| `JARVIS_MAX_INPUT_TOKEN_COUNT` | 32000 | 输入的最大token数量 |
-| `JARVIS_PLATFORM` | yuanbao | 默认AI平台 |
-| `JARVIS_MODEL` | deep_seek_v3 | 默认模型 |
-| `JARVIS_THINKING_PLATFORM` | JARVIS_PLATFORM | 推理任务使用的平台 |
-| `JARVIS_THINKING_MODEL` | JARVIS_MODEL | 推理任务使用的模型 |
+| `JARVIS_MODEL_GROUPS` | `[]` | 预定义的模型配置组列表 |
+| `JARVIS_MODEL_GROUP` | `null` | 选择要激活的模型组名称 |
+| `JARVIS_MAX_TOKEN_COUNT` | 960000 | 上下文窗口的最大token数量 (可被模型组覆盖) |
+| `JARVIS_MAX_INPUT_TOKEN_COUNT` | 32000 | 输入的最大token数量 (可被模型组覆盖) |
+| `JARVIS_PLATFORM` | yuanbao | 默认AI平台 (可被模型组覆盖) |
+| `JARVIS_MODEL` | deep_seek_v3 | 默认模型 (可被模型组覆盖) |
+| `JARVIS_THINKING_PLATFORM` | JARVIS_PLATFORM | 推理任务使用的平台 (可被模型组覆盖) |
+| `JARVIS_THINKING_MODEL` | JARVIS_MODEL | 推理任务使用的模型 (可被模型组覆盖) |
 | `JARVIS_EXECUTE_TOOL_CONFIRM` | false | 执行工具前是否需要确认 |
 | `JARVIS_CONFIRM_BEFORE_APPLY_PATCH` | false | 应用补丁前是否需要确认 |
-| `JARVIS_MAX_BIG_CONTENT_SIZE` | 160000 | 最大大内容大小 |
+| `JARVIS_MAX_BIG_CONTENT_SIZE` | 160000 | 最大大内容大小 (可被模型组覆盖) |
 | `JARVIS_PRETTY_OUTPUT` | false | 是否启用PrettyOutput |
 | `JARVIS_GIT_COMMIT_PROMPT` | "" | 自定义git提交信息生成提示模板 |
 | `JARVIS_PRINT_PROMPT` | false | 是否打印提示 |

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jarvis-ai-assistant"
-version = "0.1.224"
+version = "0.2.0"
 description = "Jarvis: An AI assistant that uses tools to interact with the system"
 readme = "README.md"
 authors = [{ name = "skyfire", email = "skyfireitdiy@hotmail.com" }]
@@ -39,8 +39,8 @@ dependencies = [
     "httpx>=0.28.1",
     "pyyaml>=5.3.1",
     "ddgs==9.0.2",
-    "beautifulsoup4==4.13.4",
     "lxml==6.0.0",
+    "markdownify>=1.1.0",
 ]
 requires-python = ">=3.9"
 
@@ -89,3 +89,7 @@ jarvis-methodology = "jarvis.jarvis_methodology.main:main"
 jm = "jarvis.jarvis_methodology.main:main"
 jarvis-rag = "jarvis.jarvis_rag.cli:main"
 jrg = "jarvis.jarvis_rag.cli:main"
+
+[[tool.uv.index]]
+url = "https://artsz.zte.com.cn/artifactory/api/pypi/public-pypi-virtual/simple"
+default = true

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages  # type: ignore
 
 setup(
     name="jarvis-ai-assistant",
-    version="0.1.224",
+    version="0.2.0",
     author="skyfire",
     author_email="skyfireitdiy@hotmail.com",
     description="An AI assistant that uses various tools to interact with the system",
@@ -34,8 +34,8 @@ setup(
         "httpx>=0.28.1",
         "pyyaml>=5.3.1",
         "ddgs==9.0.2",
-        "beautifulsoup4==4.13.4",
         "lxml==6.0.0",
+        "markdownify>=1.1.0",
     ],
     extras_require={
         "dev": ["pytest", "black", "isort", "mypy", "build", "twine"],

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/src/jarvis/__init__.py

@@ -1,4 +1,4 @@
 # -*- coding: utf-8 -*-
 """Jarvis AI Assistant"""
 
-__version__ = "0.1.224"
+__version__ = "0.2.0"

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/src/jarvis/jarvis_agent/__init__.py

@@ -102,6 +102,7 @@ class Agent:
         name: str = "Jarvis",
         description: str = "",
         llm_type: str = "normal",
+        model_group: Optional[str] = None,
         summary_prompt: Optional[str] = None,
         auto_complete: bool = False,
         output_handler: List[OutputHandlerProtocol] = [],
@@ -137,11 +138,11 @@ class Agent:
         self.description = description
         # 初始化平台和模型
         if llm_type == "thinking":
-            platform_name = get_thinking_platform_name()
-            model_name = get_thinking_model_name()
+            platform_name = get_thinking_platform_name(model_group)
+            model_name = get_thinking_model_name(model_group)
         else:  # 默认为 normal
-            platform_name = get_normal_platform_name()
-            model_name = get_normal_model_name()
+            platform_name = get_normal_platform_name(model_group)
+            model_name = get_normal_model_name(model_group)
 
         self.model = PlatformRegistry().create_platform(platform_name)
         if self.model is None:
@@ -153,6 +154,8 @@ class Agent:
         if model_name:
             self.model.set_model_name(model_name)
 
+        self.model.set_model_group(model_group)
+
         self.user_data: Dict[str, Any] = {}
 
         self.model.set_suppress_output(False)
@@ -197,7 +200,7 @@ class Agent:
             summary_prompt if summary_prompt else DEFAULT_SUMMARY_PROMPT
         )
 
-        self.max_token_count = get_max_token_count()
+        self.max_token_count = get_max_token_count(model_group)
         self.auto_complete = auto_complete
         welcome_message = f"{name} 初始化完成 - 使用 {self.model.name()} 模型"
 
@@ -213,6 +216,7 @@ class Agent:
 """
         )
         self.first = True
+        self.run_input_handlers_next_turn = False
 
     def set_user_data(self, key: str, value: Any):
         """Sets user data in the session."""
@@ -236,6 +240,10 @@ class Agent:
         """Sets the addon prompt in the session."""
         self.session.set_addon_prompt(addon_prompt)
 
+    def set_run_input_handlers_next_turn(self, value: bool):
+        """Sets the flag to run input handlers on the next turn."""
+        self.run_input_handlers_next_turn = value
+
     def set_after_tool_call_cb(self, cb: Callable[[Any], None]):  # type: ignore
         """设置工具调用后回调函数。
 
@@ -264,7 +272,9 @@ class Agent:
                 return handler
         return None
 
-    def _call_model(self, message: str, need_complete: bool = False) -> str:
+    def _call_model(
+        self, message: str, need_complete: bool = False, run_input_handlers: bool = True
+    ) -> str:
         """调用AI模型并实现重试逻辑
 
         参数:
@@ -280,10 +290,11 @@ class Agent:
             3. 会自动添加附加提示
             4. 会检查并处理上下文长度限制
         """
-        for handler in self.input_handler:
-            message, need_return = handler(message, self)
-            if need_return:
-                return message
+        if run_input_handlers:
+            for handler in self.input_handler:
+                message, need_return = handler(message, self)
+                if need_return:
+                    return message
 
         if self.session.addon_prompt:
             message += f"\n\n{self.session.addon_prompt}"
@@ -478,12 +489,20 @@ class Agent:
         try:
             set_agent(self.name, self)
 
+            run_input_handlers = True
             while True:
+                if self.run_input_handlers_next_turn:
+                    run_input_handlers = True
+                    self.run_input_handlers_next_turn = False
+
                 if self.first:
                     self._first_run()
                 try:
-                    current_response = self._call_model(self.session.prompt, True)
+                    current_response = self._call_model(
+                        self.session.prompt, True, run_input_handlers
+                    )
                     self.session.prompt = ""
+                    run_input_handlers = False
 
                     if get_interrupt():
                         set_interrupt(False)
@@ -491,6 +510,7 @@ class Agent:
                             f"模型交互期间被中断，请输入用户干预信息："
                         )
                         if user_input:
+                            run_input_handlers = True
                             # 如果有工具调用且用户确认继续，则将干预信息和工具执行结果拼接为prompt
                             if any(
                                 handler.can_handle(current_response)
@@ -502,6 +522,7 @@ class Agent:
                                     self.session.prompt = (
                                         f"{user_input}\n\n{current_response}"
                                     )
+                                    run_input_handlers = False
                                     continue
                             self.session.prompt += f"{user_input}"
                             continue
@@ -529,6 +550,7 @@ class Agent:
 
                     if user_input:
                         self.session.prompt = user_input
+                        run_input_handlers = True
                         continue
 
                     if not user_input:

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/src/jarvis/jarvis_agent/jarvis.py

@@ -1,8 +1,11 @@
 # -*- coding: utf-8 -*-
 import argparse
 import os
+import shutil
+import subprocess
 import sys
-from typing import Dict
+from pathlib import Path
+from typing import Dict, Optional
 
 import yaml  # type: ignore
 from prompt_toolkit import prompt  # type: ignore
@@ -106,8 +109,8 @@ def _select_task(tasks: Dict[str, str]) -> str:
             PrettyOutput.print(f"选择任务失败: {str(val_err)}", OutputType.ERROR)
 
 
-def main() -> None:
-
+def _parse_args() -> argparse.Namespace:
+    """Parse command line arguments."""
     parser = argparse.ArgumentParser(description="Jarvis AI assistant")
     parser.add_argument(
         "--llm_type",
@@ -122,6 +125,11 @@ def main() -> None:
         type=str,
         help="Directly input task content from command line",
     )
+    parser.add_argument(
+        "--model_group",
+        type=str,
+        help="Model group to use, overriding config",
+    )
     parser.add_argument("-f", "--config", type=str, help="Path to custom config file")
     parser.add_argument(
         "--restore-session",
@@ -129,44 +137,91 @@ def main() -> None:
         help="Restore session from .jarvis/saved_session.json",
         default=False,
     )
-    args = parser.parse_args()
-    init_env(
-        "欢迎使用 Jarvis AI 助手，您的智能助理已准备就绪！", config_file=args.config
+    parser.add_argument(
+        "-e", "--edit", action="store_true", help="Edit the configuration file"
     )
+    return parser.parse_args()
 
-    try:
-        agent = Agent(
-            system_prompt=origin_agent_system_prompt,
-            llm_type=args.llm_type,
-            input_handler=[shell_input_handler, builtin_input_handler],
-            output_handler=[ToolRegistry()],
-            need_summary=False,
-        )
 
-        # 尝试恢复会话
-        if args.restore_session:
-            if agent.restore_session():
-                PrettyOutput.print("会话已成功恢复。", OutputType.SUCCESS)
-            else:
-                PrettyOutput.print("无法恢复会话。", OutputType.WARNING)
+def _handle_edit_mode(args: argparse.Namespace) -> None:
+    """If edit flag is set, open config file in editor and exit."""
+    if not args.edit:
+        return
+
+    config_file_path = (
+        Path(args.config)
+        if args.config
+        else Path(os.path.expanduser("~/.jarvis/config.yaml"))
+    )
+    editors = ["nvim", "vim", "vi"]
+    editor = next((e for e in editors if shutil.which(e)), None)
 
-        # 优先处理命令行直接传入的任务
-        if args.task:
-            agent.run(args.task)
+    if editor:
+        try:
+            subprocess.run([editor, str(config_file_path)], check=True)
             sys.exit(0)
+        except (subprocess.CalledProcessError, FileNotFoundError) as e:
+            PrettyOutput.print(f"Failed to open editor: {e}", OutputType.ERROR)
+            sys.exit(1)
+    else:
+        PrettyOutput.print(
+            "No suitable editor found (nvim, vim, vi).", OutputType.ERROR
+        )
+        sys.exit(1)
 
-        if agent.first:
-            tasks = _load_tasks()
-            if tasks and (selected_task := _select_task(tasks)):
-                PrettyOutput.print(f"开始执行任务: \n{selected_task}", OutputType.INFO)
-                agent.run(selected_task)
-                sys.exit(0)
 
-        user_input = get_multiline_input("请输入你的任务（输入空行退出）:")
-        if user_input:
-            agent.run(user_input)
+def _initialize_agent(args: argparse.Namespace) -> Agent:
+    """Initialize the agent and restore session if requested."""
+    agent = Agent(
+        system_prompt=origin_agent_system_prompt,
+        llm_type=args.llm_type,
+        model_group=args.model_group,
+        input_handler=[shell_input_handler, builtin_input_handler],
+        output_handler=[ToolRegistry()],  # type: ignore
+        need_summary=False,
+    )
+
+    # 尝试恢复会话
+    if args.restore_session:
+        if agent.restore_session():
+            PrettyOutput.print("会话已成功恢复。", OutputType.SUCCESS)
+        else:
+            PrettyOutput.print("无法恢复会话。", OutputType.WARNING)
+    return agent
+
+
+def _get_and_run_task(agent: Agent, task_content: Optional[str] = None) -> None:
+    """Get task from various sources and run it."""
+    # 优先处理命令行直接传入的任务
+    if task_content:
+        agent.run(task_content)
         sys.exit(0)
 
+    if agent.first:
+        tasks = _load_tasks()
+        if tasks and (selected_task := _select_task(tasks)):
+            PrettyOutput.print(f"开始执行任务: \n{selected_task}", OutputType.INFO)
+            agent.run(selected_task)
+            sys.exit(0)
+
+    user_input = get_multiline_input("请输入你的任务（输入空行退出）:")
+    if user_input:
+        agent.run(user_input)
+    sys.exit(0)
+
+
+def main() -> None:
+    """Main function for Jarvis AI assistant."""
+    args = _parse_args()
+    _handle_edit_mode(args)
+
+    init_env(
+        "欢迎使用 Jarvis AI 助手，您的智能助理已准备就绪！", config_file=args.config
+    )
+
+    try:
+        agent = _initialize_agent(args)
+        _get_and_run_task(agent, args.task)
     except Exception as err:  # pylint: disable=broad-except
         PrettyOutput.print(f"初始化错误: {str(err)}", OutputType.ERROR)
         sys.exit(1)

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/src/jarvis/jarvis_agent/main.py

@@ -20,7 +20,9 @@ def load_config(config_path: str) -> dict:
         dict: 配置字典
     """
     if not os.path.exists(config_path):
-        PrettyOutput.print(f"配置文件 {config_path} 不存在，使用默认配置", OutputType.WARNING)
+        PrettyOutput.print(
+            f"配置文件 {config_path} 不存在，使用默认配置", OutputType.WARNING
+        )
         return {}
 
     with open(config_path, "r", encoding="utf-8", errors="ignore") as f:
@@ -50,10 +52,17 @@ def main():
         choices=["normal", "thinking"],
         help="LLM type to use, overriding config",
     )
+    parser.add_argument(
+        "--model_group",
+        type=str,
+        help="Model group to use, overriding config",
+    )
     args = parser.parse_args()
 
     # Initialize environment
-    init_env("欢迎使用 Jarvis AI 助手，您的智能助理已准备就绪！", config_file=args.config)
+    init_env(
+        "欢迎使用 Jarvis AI 助手，您的智能助理已准备就绪！", config_file=args.config
+    )
 
     # Load configuration
     config = load_config(args.agent_definition) if args.agent_definition else {}
@@ -61,6 +70,8 @@ def main():
     # Override config with command-line arguments if provided
     if args.llm_type:
         config["llm_type"] = args.llm_type
+    if args.model_group:
+        config["model_group"] = args.model_group
 
     # Create and run agent
     try:

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/src/jarvis/jarvis_code_agent/code_agent.py

@@ -18,7 +18,10 @@ from jarvis.jarvis_code_agent.lint import get_lint_tools
 from jarvis.jarvis_git_utils.git_commiter import GitCommitTool
 from jarvis.jarvis_platform.registry import PlatformRegistry
 from jarvis.jarvis_tools.registry import ToolRegistry
-from jarvis.jarvis_utils.config import is_confirm_before_apply_patch, is_enable_static_analysis
+from jarvis.jarvis_utils.config import (
+    is_confirm_before_apply_patch,
+    is_enable_static_analysis,
+)
 from jarvis.jarvis_utils.git_utils import (
     confirm_add_new_files,
     find_git_root_and_cd,
@@ -44,6 +47,7 @@ class CodeAgent:
     def __init__(
         self,
         llm_type: str = "normal",
+        model_group: Optional[str] = None,
         need_summary: bool = True,
     ):
         self.root_dir = os.getcwd()
@@ -54,7 +58,6 @@ class CodeAgent:
                 "search_web",
                 "ask_user",
                 "read_code",
-                "methodology",
                 "rewrite_file",
             ]
         )
@@ -116,8 +119,9 @@ class CodeAgent:
             system_prompt=code_system_prompt,
             name="CodeAgent",
             auto_complete=False,
-            output_handler=[tool_registry, EditFileHandler()],
+            output_handler=[tool_registry, EditFileHandler()],  # type: ignore
             llm_type=llm_type,
+            model_group=model_group,
             input_handler=[shell_input_handler, builtin_input_handler],
             need_summary=need_summary,
             use_methodology=False,  # 禁用方法论
@@ -409,6 +413,11 @@ def main() -> None:
         choices=["normal", "thinking"],
         help="LLM type to use",
     )
+    parser.add_argument(
+        "--model_group",
+        type=str,
+        help="Model group to use, overriding config",
+    )
     parser.add_argument(
         "-r", "--requirement", type=str, help="Requirement to process", default=None
     )
@@ -425,7 +434,11 @@ def main() -> None:
     PrettyOutput.print(f"当前目录: {git_dir}", OutputType.INFO)
 
     try:
-        agent = CodeAgent(llm_type=args.llm_type, need_summary=False)
+        agent = CodeAgent(
+            llm_type=args.llm_type,
+            model_group=args.model_group,
+            need_summary=False,
+        )
 
         # 尝试恢复会话
         if args.restore_session:

{jarvis_ai_assistant-0.1.224 → jarvis_ai_assistant-0.2.0}/src/jarvis/jarvis_code_analysis/checklists/loader.py

@@ -5,12 +5,26 @@ Utility module for loading language-specific code review checklists.
 from typing import Dict, Optional
 
 # Import checklist modules
-from jarvis.jarvis_code_analysis.checklists import (c_cpp, csharp, data_format,
-                                                    devops, docs, go,
-                                                    infrastructure, java,
-                                                    javascript, kotlin, php,
-                                                    python, ruby, rust, shell,
-                                                    sql, swift, web)
+from jarvis.jarvis_code_analysis.checklists import (
+    c_cpp,
+    csharp,
+    data_format,
+    devops,
+    docs,
+    go,
+    infrastructure,
+    java,
+    javascript,
+    kotlin,
+    php,
+    python,
+    ruby,
+    rust,
+    shell,
+    sql,
+    swift,
+    web,
+)
 
 # Map of language identifiers to their checklist content
 CHECKLIST_MAP = {