autocoder-nano 0.1.30__py3-none-any.whl → 0.1.33__py3-none-any.whl

autocoder_nano/llm_types.py

@@ -18,6 +18,7 @@ class AutoCoderArgs(BaseModel):
     index_filter_level: Optional[int] = 0  # 用于查找相关文件的过滤级别
     index_filter_file_num: Optional[int] = -1  #
     index_filter_workers: Optional[int] = 1  # 过滤文件的线程数量
+    index_model_max_input_length: Optional[int] = 6000  # 模型最大输入长度
     filter_batch_size: Optional[int] = 5  #
     anti_quota_limit: Optional[int] = 1  # 请求模型时的间隔时间(s)
     skip_build_index: Optional[bool] = False  # 是否跳过索引构建(索引可以帮助您通过查询找到相关文件)
@@ -46,7 +47,7 @@ class AutoCoderArgs(BaseModel):
     full_text_ratio: Optional[float] = 0.7
     segment_ratio: Optional[float] = 0.2
     buff_ratio: Optional[float] = 0.1
-    required_exts: Optional[str] = None    # 指定处理的文件后缀,例如.pdf,.doc
+    required_exts: Optional[str] = None  # 指定处理的文件后缀,例如.pdf,.doc
     monitor_mode: bool = False  # 监控模式,会监控doc_dir目录中的文件变化
     enable_hybrid_index: bool = False  # 开启混合索引
     disable_auto_window: bool = False
@@ -57,26 +58,32 @@ class AutoCoderArgs(BaseModel):
     enable_rag_context: Optional[Union[bool, str]] = False
     disable_segment_reorder: bool = False
     disable_inference_enhance: bool = False
-    duckdb_vector_dim: Optional[int] = 1024    # DuckDB 向量化存储的维度
+    duckdb_vector_dim: Optional[int] = 1024  # DuckDB 向量化存储的维度
     duckdb_query_similarity: Optional[float] = 0.7  # DuckDB 向量化检索 相似度 阈值
-    duckdb_query_top_k: Optional[int] = 50    # DuckDB 向量化检索 返回 TopK个结果(且大于相似度)
+    duckdb_query_top_k: Optional[int] = 50  # DuckDB 向量化检索 返回 TopK个结果(且大于相似度)
 
     # Git 相关参数
     skip_commit: Optional[bool] = False
 
+    # Rules 相关参数
+    enable_rules: Optional[bool] = False
+
+    # Agent 相关参数
+    generate_max_rounds: Optional[int] = 5
+
     # 模型相关参数
     current_chat_model: Optional[str] = ""
     current_code_model: Optional[str] = ""
-    model: Optional[str] = ""    # 默认模型
-    chat_model: Optional[str] = ""    # AI Chat交互模型
-    index_model: Optional[str] = ""    # 代码索引生成模型
-    code_model: Optional[str] = ""    # 编码模型
-    commit_model: Optional[str] = ""    # Git Commit 模型
-    emb_model: Optional[str] = ""    # RAG Emb 模型
-    recall_model: Optional[str] = ""    # RAG 召回阶段模型
-    chunk_model: Optional[str] = ""    # 段落重排序模型
-    qa_model: Optional[str] = ""    # RAG 提问模型
-    vl_model: Optional[str] = ""    # 多模态模型
+    model: Optional[str] = ""  # 默认模型
+    chat_model: Optional[str] = ""  # AI Chat交互模型
+    index_model: Optional[str] = ""  # 代码索引生成模型
+    code_model: Optional[str] = ""  # 编码模型
+    commit_model: Optional[str] = ""  # Git Commit 模型
+    emb_model: Optional[str] = ""  # RAG Emb 模型
+    recall_model: Optional[str] = ""  # RAG 召回阶段模型
+    chunk_model: Optional[str] = ""  # 段落重排序模型
+    qa_model: Optional[str] = ""  # RAG 提问模型
+    vl_model: Optional[str] = ""  # 多模态模型
 
     class Config:
         protected_namespaces = ()
@@ -117,6 +124,14 @@ class SourceCode(BaseModel):
     metadata: Dict[str, Any] = Field(default_factory=dict)
 
 
+class SourceCodeList:
+    def __init__(self, sources: List[SourceCode]):
+        self.sources = sources
+
+    def to_str(self):
+        return "\n".join([f"##File: {source.module_name}\n{source.source_code}\n" for source in self.sources])
+
+
 class LLMRequest(BaseModel):
     model: str  # 指定使用的语言模型名称
     messages: List[Dict[str, str]]  # 包含对话消息的列表，每个消息是一个字典，包含 "role"（角色）和 "content"（内容）
@@ -138,6 +153,21 @@ class LLMResponse(BaseModel):
     )
 
 
+class SingleOutputMeta:
+    def __init__(self, input_tokens_count: int = 0,
+                 generated_tokens_count: int = 0,
+                 reasoning_content: str = "",
+                 finish_reason: str = "",
+                 first_token_time: float = 0.0,
+                 extra_info: Dict[str, Any] = {}):
+        self.input_tokens_count = input_tokens_count
+        self.generated_tokens_count = generated_tokens_count
+        self.reasoning_content = reasoning_content
+        self.finish_reason = finish_reason
+        self.first_token_time = first_token_time
+        self.extra_info = extra_info
+
+
 class IndexItem(BaseModel):
     module_name: str
     symbols: str
@@ -269,4 +299,13 @@ class FileInfo(BaseModel):
     file_path: str
     relative_path: str
     modify_time: float
-    file_md5: str
+    file_md5: str
+
+
+class RuleFile(BaseModel):
+    """规则文件的Pydantic模型"""
+    description: str = Field(default="", description="规则的描述")
+    globs: List[str] = Field(default_factory=list, description="文件匹配模式列表")
+    always_apply: bool = Field(default=False, description="是否总是应用规则")
+    content: str = Field(default="", description="规则文件的正文内容")
+    file_path: str = Field(default="", description="规则文件的路径")

autocoder_nano/rules/rules_learn.py

@@ -0,0 +1,221 @@
+import os
+from typing import List, Tuple, Dict, Optional, Generator
+
+from autocoder_nano.git_utils import get_commit_changes
+from autocoder_nano.llm_client import AutoLLM
+from autocoder_nano.llm_prompt import prompt
+from autocoder_nano.llm_types import AutoCoderArgs, SourceCodeList
+from autocoder_nano.utils.printer_utils import Printer
+
+
+printer = Printer()
+
+
+class AutoRulesLearn:
+
+    def __init__(self, args: AutoCoderArgs, llm: AutoLLM):
+        self.args = args
+        self.llm = llm
+
+    @prompt()
+    def _analyze_commit_changes(
+        self, querie_with_urls_and_changes: List[Tuple[str, List[str], Dict[str, Tuple[str, str]]]]
+    ):
+        """
+        下面是用户一次提交的代码变更：
+        <changes>
+        {% for query,urls,changes in querie_with_urls_and_changes %}
+        ## 原始的任务需求
+        {{ query }}
+
+        修改的文件:
+        {% for url in urls %}
+        - {{ url }}
+        {% endfor %}
+
+        代码变更:
+        {% for file_path, (before, after) in changes.items() %}
+        ##File: {{ file_path }}
+        ##修改前:
+
+        {{ before or "New file" }}
+
+        ##File: {{ file_path }}
+        ##修改后:
+
+        {{ after or "File deleted" }}
+
+        {% endfor %}
+        {% endfor %}
+        </changes>
+
+        请对根据上面的代码变更进行深入分析，提取具有通用价值的功能模式和设计模式，转化为可在其他项目中复用的代码规则（rules）。
+
+        - 识别代码变更中具有普遍应用价值的功能点和模式
+        - 将这些功能点提炼为结构化规则，便于在其他项目中快速复用
+        - 生成清晰的使用示例，包含完整依赖和调用方式
+
+        最后，新生成的文件格式要是这种形态的：
+
+        <example_rules>
+        ---
+        description: [简明描述规则的功能，20字以内]
+        globs: [匹配应用此规则的文件路径，如"src/services/*.py"]
+        alwaysApply: [是否总是应用，通常为false]
+        ---
+
+        # [规则主标题]
+
+        ## 简要说明
+        [该规则的功能、适用场景和价值，100字以内]
+
+        ## 典型用法
+        ```python
+        # 完整的代码示例，包含:
+        # 1. 必要的import语句
+        # 2. 类/函数定义
+        # 3. 参数说明
+        # 4. 调用方式
+        # 5. 关键注释
+        ```
+
+        ## 依赖说明
+        - [必要的依赖库及版本]
+        - [环境要求]
+        - [初始化流程(如有)]
+
+        ## 学习来源
+        [从哪个提交变更的哪部分代码中提取的该功能点]
+        </example_rules>
+        """
+
+    @prompt()
+    def _analyze_modules(self, sources: SourceCodeList):
+        """
+        下面是用户提供的需要抽取规则的代码：
+        <files>
+        {% for source in sources.sources %}
+        ##File: {{ source.module_name }}
+        {{ source.source_code }}
+        {% endfor %}
+        </files>
+
+        请对对上面的代码进行深入分析，提取具有通用价值的功能模式和设计模式，转化为可在其他项目中复用的代码规则（rules）。
+
+        - 识别代码变更中具有普遍应用价值的功能点和模式
+        - 将这些功能点提炼为结构化规则，便于在其他项目中快速复用
+        - 生成清晰的使用示例，包含完整依赖和调用方式
+
+        最后，新生成的文件格式要是这种形态的：
+
+        <example_rules>
+        ---
+        description: [简明描述规则的功能，20字以内]
+        globs: [匹配应用此规则的文件路径，如"src/services/*.py"]
+        alwaysApply: [是否总是应用，通常为false]
+        ---
+
+        # [规则主标题]
+
+        ## 简要说明
+        [该规则的功能、适用场景和价值，100字以内]
+
+        ## 典型用法
+        ```python
+        # 完整的代码示例，包含:
+        # 1. 必要的import语句
+        # 2. 类/函数定义
+        # 3. 参数说明
+        # 4. 调用方式
+        # 5. 关键注释
+        ```
+
+        ## 依赖说明
+        - [必要的依赖库及版本]
+        - [环境要求]
+        - [初始化流程(如有)]
+
+        ## 学习来源
+        [从哪个提交变更的哪部分代码中提取的该功能点]
+        </example_rules>
+        """
+
+    def analyze_commit_changes(
+        self, commit_id: str, conversations=None
+    ) -> str:
+        """ 分析指定commit的代码变更 """
+        if conversations is None:
+            conversations = []
+
+        changes, _ = get_commit_changes(self.args.source_dir, commit_id)
+
+        if not changes:
+            printer.print_text("未发现代码变更(Commit)", style="yellow")
+            return ""
+
+        try:
+            # 获取prompt内容
+            prompt_content = self._analyze_commit_changes.prompt(
+                querie_with_urls_and_changes=changes
+            )
+
+            # 准备对话历史
+            if conversations:
+                new_conversations = conversations[:-1]
+            else:
+                new_conversations = []
+            new_conversations.append({"role": "user", "content": prompt_content})
+
+            self.llm.setup_default_model_name(self.args.chat_model)
+            v = self.llm.chat_ai(new_conversations, self.args.chat_model)
+            return v.output
+        except Exception as e:
+            printer.print_text(f"代码变更分析失败: {e}", style="red")
+            return ""
+
+    def analyze_modules(
+        self, sources: SourceCodeList, conversations=None
+    ) -> str:
+        """ 分析给定的模块文件，根据用户需求生成可复用功能点的总结。 """
+
+        if conversations is None:
+            conversations = []
+
+        if not sources or not sources.sources:
+            printer.print_text("没有提供有效的模块文件进行分析.", style="red")
+            return ""
+
+        try:
+            # 准备 Prompt
+            prompt_content = self._analyze_modules.prompt(
+                sources=sources
+            )
+
+            # 准备对话历史
+            # 如果提供了 conversations，我们假设最后一个是用户的原始查询，替换它
+            if conversations:
+                new_conversations = conversations[:-1]
+            else:
+                new_conversations = []
+            new_conversations.append({"role": "user", "content": prompt_content})
+
+            self.llm.setup_default_model_name(self.args.chat_model)
+            v = self.llm.chat_ai(new_conversations, self.args.chat_model)
+            return v.output
+        except Exception as e:
+            printer.print_text(f"代码模块分析失败: {e}", style="red")
+            return ""
+
+    def _get_index_file_content(self) -> str:
+        """获取索引文件内容"""
+        index_file_path = os.path.join(os.path.abspath(self.args.source_dir), ".autocoderrules", "index.md")
+        index_file_content = ""
+
+        try:
+            if os.path.exists(index_file_path):
+                with open(index_file_path, 'r', encoding='utf-8') as f:
+                    index_file_content = f.read()
+        except Exception as e:
+            printer.print_text(f"读取索引文件时出错: {str(e)}", style="yellow")
+
+        return index_file_content

autocoder_nano/templates.py

@@ -99,7 +99,7 @@ def init_command_template(source_dir: str):
     ## 2. 查找0和1中的文件引用的相关文件
     ## 第一次建议使用0
     index_filter_level: 0
-    index_model_max_input_length: 30000
+    index_model_max_input_length: 100000
 
     ## 过滤文件的线程数量
     ## 如果您有一个大项目，可以增加这个数字

autocoder_nano/utils/formatted_log_utils.py

@@ -0,0 +1,128 @@
+import os
+import json
+import uuid
+from datetime import datetime
+
+
+# New helper function for cleaning up logs
+def _cleanup_logs(logs_dir: str, max_files: int = 100):
+    """
+    Cleans up old log files in the specified directory, keeping only the most recent ones.
+    Log files are expected to follow the naming convention: <YYYYmmdd_HHMMSS>_<uuid>_<suffix>.md
+    """
+    # logger.debug(f"开始清理日志目录: {logs_dir}，最大保留文件数: {max_files}")
+    if not os.path.isdir(logs_dir):
+        # logger.debug(f"日志目录 {logs_dir} 不存在，无需清理。")
+        return
+
+    log_files = []
+    for filename in os.listdir(logs_dir):
+        if filename.endswith(".md"):
+            parts = filename.split('_')
+            # Expected format: <YYYYmmdd_HHMMSS>_<uuid>_<suffix>.md
+            # parts[0] should be the full timestamp string "YYYYmmdd_HHMMSS"
+            if len(parts) >= 2:  # At least timestamp and uuid part (suffix might be empty or complex)
+                timestamp_str = parts[0]
+                try:
+                    # Validate the timestamp format
+                    datetime.strptime(timestamp_str, "%Y%m%d_%H%M%S")
+                    log_files.append((timestamp_str, os.path.join(logs_dir, filename)))
+                except ValueError:
+                    # logger.debug(f"文件名 {filename} 的时间戳部分 ({timestamp_str}) 格式不正确，跳过。")
+                    continue
+            else:
+                pass
+                # Log the parts for better debugging if needed
+                # logger.debug(f"文件名 {filename} (分割后: {parts}) 不符合预期的下划线分割数量 (至少需要 <timestamp>_<uuid>_...)，跳过。")
+
+    # Sort by timestamp (oldest first)
+    log_files.sort(key=lambda x: x[0])
+
+    if len(log_files) > max_files:
+        files_to_delete_count = len(log_files) - max_files
+        # logger.info(f"日志文件数量 ({len(log_files)}) 超过限制 ({max_files})，将删除 {files_to_delete_count} 个最旧的文件。")
+        for i in range(files_to_delete_count):
+            file_to_delete_timestamp, file_to_delete_path = log_files[i]
+            try:
+                os.remove(file_to_delete_path)
+                # logger.info(f"已删除旧日志文件: {file_to_delete_path} (时间戳: {file_to_delete_timestamp})")
+            except OSError as e:
+                pass
+                # logger.warning(f"删除日志文件 {file_to_delete_path} 失败: {str(e)}")
+                # logger.exception(e)  # Log stack trace
+    else:
+        pass
+        # logger.debug(f"日志文件数量 ({len(log_files)}) 未超过限制 ({max_files})，无需删除。")
+
+
+def save_formatted_log(project_root, json_text, suffix):
+    """
+    Save a JSON log as a formatted markdown file under project_root/.auto-coder/logs/agentic.
+    Filename: <YYYYmmdd_HHMMSS>_<uuid>_<suffix>.md
+    Also cleans up old logs in the directory, keeping the latest 100.
+    Args:
+        project_root (str): The root directory of the project.
+        json_text (str): The JSON string to be formatted and saved.
+        suffix (str): The suffix for the filename.
+    """
+    # Prepare directory (logs_dir is needed for cleanup first)
+    logs_dir = os.path.join(project_root, ".auto-coder", "logs", "agentic")
+
+    # Cleanup old logs BEFORE saving the new one
+    try:
+        _cleanup_logs(logs_dir)  # Default to keep 100 files
+    except Exception as e:
+        pass
+        # logger.warning(f"日志清理过程中发生错误: {str(e)}")
+        # logger.exception(e)
+        # Log cleanup failure should not prevent the main functionality
+
+    # Parse JSON
+    try:
+        data = json.loads(json_text)
+    except Exception as e:
+        # logger.error(f"无效的 JSON 格式: {str(e)}") # Log error before raising
+        # logger.exception(e) # Log stack trace
+        raise ValueError(f"Invalid JSON provided: {e}")
+
+    # Format as markdown with recursive depth
+    def to_markdown(obj, level=1):
+        lines = []
+        if isinstance(obj, dict):
+            for key, value in obj.items():
+                lines.append(f"{'#' * (level + 1)} {key}\n")
+                lines.extend(to_markdown(value, level + 1))
+        elif isinstance(obj, list):
+            for idx, item in enumerate(obj, 1):
+                lines.append(f"{'#' * (level + 1)} Item {idx}\n")
+                lines.extend(to_markdown(item, level + 1))
+        else:
+            lines.append(str(obj) + "\n")
+        return lines
+
+    md_lines = ["# Log Entry\n"]
+    md_lines.extend(to_markdown(data, 1))
+    md_content = "\n".join(md_lines)
+
+    # Ensure directory exists
+    # _cleanup_logs checks if dir exists but does not create it.
+    # os.makedirs needs to be called to ensure the directory for the new log file.
+    os.makedirs(logs_dir, exist_ok=True)
+
+    # Prepare filename
+    now = datetime.now().strftime("%Y%m%d_%H%M%S")
+    unique_id = str(uuid.uuid4())
+    filename = f"{now}_{unique_id}_{suffix}.md"
+    filepath = os.path.join(logs_dir, filename)
+
+    # Save file
+    try:
+        with open(filepath, "w", encoding="utf-8") as f:
+            f.write(md_content)
+        # logger.info(f"日志已保存至: {filepath}")
+    except IOError as e:
+        # logger.error(f"保存日志文件 {filepath} 失败: {str(e)}")
+        # logger.exception(e) # Log stack trace
+        raise  # Re-throw the exception so the caller knows saving failed
+
+    return filepath

autocoder_nano/utils/printer_utils.py

@@ -294,7 +294,7 @@ class Printer:
 
     def print_key_value(
         self, items: Dict[str, Any], key_style: str = "bold cyan",
-        value_style: str = "green", separator: str = ": ", panel: bool = True
+        value_style: str = "green", separator: str = ": ", panel: bool = True, title: Optional[str] = None
     ) -> None:
         """
         键值对格式化输出
@@ -303,6 +303,7 @@ class Printer:
         :param value_style: 值的样式
         :param separator: 键值分隔符
         :param panel: 是否用面板包裹
+        :param title: 面板标题
         """
         content = Group(*[
             Text.assemble(
@@ -310,7 +311,7 @@ class Printer:
                 (str(v), value_style)
             ) for k, v in items.items()
         ])
-        self._print_with_panel(content, panel)
+        self._print_with_panel(content, panel, title)
 
     def context_aware_help(
         self, help_content: Dict[str, str], current_context: str, width: int = 40
@@ -336,10 +337,10 @@ class Printer:
             width=width
         )
 
-    def _print_with_panel(self, content: Any, use_panel: bool) -> None:
+    def _print_with_panel(self, content: Any, use_panel: bool, title: Optional[str] = None) -> None:
         """内部方法：根据参数决定是否使用面板包装"""
         if use_panel:
-            self.print_panel(content)
+            self.print_panel(content, title)
         else:
             self.console.print(content)
 

autocoder_nano/utils/shell_utils.py

@@ -0,0 +1,85 @@
+import os
+import platform
+import subprocess
+import sys
+
+import psutil
+
+
+def get_windows_parent_process_name():
+    """
+    获取当前进程的父进程名（仅在Windows系统下有意义）。
+
+    适用场景：
+    - 判断命令是否由PowerShell或cmd.exe启动，以便调整命令格式。
+    - 在Windows平台上进行父进程分析。
+
+    参数：
+    - 无
+
+    返回：
+    - str|None: 父进程名（小写字符串，如"powershell.exe"或"cmd.exe"），如果无法获取则为None。
+
+    异常：
+    - 捕获所有异常，返回None。
+    """
+    try:
+        current_process = psutil.Process()
+        while True:
+            parent = current_process.parent()
+            if parent is None:
+                break
+            parent_name = parent.name().lower()
+            if parent_name in ["powershell.exe", "cmd.exe"]:
+                return parent_name
+            current_process = parent
+        return None
+    except Exception:
+        return None
+
+
+def run_cmd_subprocess(command, verbose=False, cwd=None, encoding=sys.stdout.encoding):
+    if verbose:
+        print("Using run_cmd_subprocess:", command)
+
+    try:
+        shell = os.environ.get("SHELL", "/bin/sh")
+        parent_process = None
+
+        # Determine the appropriate shell
+        if platform.system() == "Windows":
+            parent_process = get_windows_parent_process_name()
+            if parent_process == "powershell.exe":
+                command = f"powershell -Command {command}"
+
+        if verbose:
+            print("Running command:", command)
+            print("SHELL:", shell)
+            if platform.system() == "Windows":
+                print("Parent process:", parent_process)
+
+        process = subprocess.Popen(
+            command,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,
+            text=True,
+            shell=True,
+            encoding=encoding,
+            errors="replace",
+            bufsize=0,  # Set bufsize to 0 for unbuffered output
+            universal_newlines=True,
+            cwd=cwd,
+        )
+
+        output = []
+        while True:
+            chunk = process.stdout.read(1)
+            if not chunk:
+                break
+            print(chunk, end="", flush=True)  # Print the chunk in real-time
+            output.append(chunk)  # Store the chunk for later use
+
+        process.wait()
+        return process.returncode, "".join(output)
+    except Exception as e:
+        return 1, str(e)

autocoder_nano/version.py

@@ -1,3 +1,3 @@
-__version__ = "0.1.30"
+__version__ = "0.1.33"
 __author__ = "moofs"
 __license__ = "Apache License 2.0"

{autocoder_nano-0.1.30.dist-info → autocoder_nano-0.1.33.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: autocoder_nano
-Version: 0.1.30
+Version: 0.1.33
 Summary: AutoCoder Nano
 Author: moofs
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
@@ -24,10 +24,11 @@ Requires-Dist: uvicorn
 Requires-Dist: pathspec
 Requires-Dist: fastapi
 Requires-Dist: tokenizers
-Requires-Dist: duckdb==1.2.0
+Requires-Dist: duckdb
 Requires-Dist: numpy
 Requires-Dist: requests
 Requires-Dist: beautifulsoup4
+Requires-Dist: psutil
 Dynamic: author
 Dynamic: classifier
 Dynamic: description