✨ feat: add order-attachment LLM classifier

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-24 13:35:28 +08:00
commit 2110e6f38c
12 changed files with 1745 additions and 0 deletions
--- a/config_loader.py
+++ b/config_loader.py
@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+"""配置文件加载与校验。"""
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+from typing import Any
+
+import yaml
+
+_REQUIRED_KEYS = {
+    "database": [
+        "driver", "server", "port", "database", "schema", "username", "password",
+        "table", "id_column", "param_column", "connect_timeout", "query_timeout",
+    ],
+    "llm": [
+        "base_url", "api_key", "model", "temperature", "max_tokens",
+        "disable_thinking", "timeout", "max_retry", "retry_backoff_seconds",
+    ],
+    "business": ["max_workers", "log_level", "default_mode", "log_dir", "format_retry"],
+}
+_VALID_MODES = {"coarse", "fine"}
+
+
+class ConfigError(Exception):
+    """配置文件缺失或格式错误。"""
+
+
+def load_config(path: str | Path = "config.yaml") -> dict[str, Any]:
+    """读取 YAML 配置文件并做基础字段校验。
+
+    校验失败会抛出 ConfigError 并说明缺哪个字段，避免程序运行到一半才因为
+    配置缺失而报出难以理解的异常。
+    """
+    p = Path(path)
+    if not p.exists():
+        raise ConfigError(f"配置文件不存在: {p.resolve()}")
+
+    with p.open("r", encoding="utf-8") as f:
+        try:
+            cfg = yaml.safe_load(f)
+        except yaml.YAMLError as e:
+            raise ConfigError(f"配置文件 YAML 解析失败: {e}") from e
+
+    if not isinstance(cfg, dict):
+        raise ConfigError("配置文件顶层必须是一个字典 (database/llm/business)")
+
+    missing_sections = [s for s in _REQUIRED_KEYS if s not in cfg]
+    if missing_sections:
+        raise ConfigError(f"配置文件缺少顶层配置块: {missing_sections}")
+
+    for section, keys in _REQUIRED_KEYS.items():
+        section_cfg = cfg[section]
+        if not isinstance(section_cfg, dict):
+            raise ConfigError(f"配置块 '{section}' 必须是字典")
+        missing = [k for k in keys if k not in section_cfg]
+        if missing:
+            raise ConfigError(f"配置块 '{section}' 缺少字段: {missing}")
+
+    default_mode = cfg["business"]["default_mode"]
+    if default_mode not in _VALID_MODES:
+        raise ConfigError(
+            f"business.default_mode 必须是 {_VALID_MODES} 之一，实际为: {default_mode!r}"
+        )
+
+    # enable_other_category 是后加的可选字段，不放进 _REQUIRED_KEYS——避免
+    # 旧配置文件因为没有这个字段就直接报"缺字段"。不写就按 False（关闭）处理；
+    # 一旦写了就必须是布尔值，防止 "false"(字符串) 这类误写被当成真值静默生效。
+    if "enable_other_category" in cfg["business"]:
+        other_flag = cfg["business"]["enable_other_category"]
+        if not isinstance(other_flag, bool):
+            raise ConfigError(
+                f"business.enable_other_category 必须是布尔值 true/false，实际为: {other_flag!r}"
+            )
+
+    # 简单的占位符提醒，防止用户忘记改配置直接运行
+    placeholders = []
+    if cfg["database"]["password"] == "CHANGE_ME":
+        placeholders.append("database.password")
+    if cfg["llm"]["api_key"] == "CHANGE_ME":
+        placeholders.append("llm.api_key")
+    if placeholders:
+        print(
+            f"[警告] 以下配置项仍是占位符，请修改 config.yaml: {placeholders}",
+            file=sys.stderr,
+        )
+
+    return cfg