Add LLM anti-prompt injection system

Introduces a comprehensive anti-prompt injection system for LLMs, including rule-based and LLM-based detection, user ban/whitelist management, message shielding, and statistics tracking. Adds new modules under src/chat/antipromptinjector, integrates anti-injection checks into the message receive flow, updates configuration and database models, and provides test scripts. Also updates templates and logger aliases to support the new system.

template/model_config_template.toml

@@ -1,5 +1,5 @@
 [inner]
-version = "1.2.4"
+version = "1.2.5"
 
 # 配置文件版本号迭代规则同bot_config.toml
 
@@ -113,6 +113,12 @@ api_provider = "SiliconFlow"
 price_in = 0
 price_out = 0
 
+[[models]]
+model_identifier = "moonshotai/Kimi-K2-Instruct"
+name = "moonshotai-Kimi-K2-Instruct"
+api_provider = "SiliconFlow"
+price_in = 4.0
+price_out = 16.0
 
 [model_task_config.utils] # 在麦麦的一些组件中使用的模型，例如表情包模块，取名模块，关系模块，是麦麦必须的模型
 model_list = ["siliconflow-deepseek-v3"] # 使用的模型列表，每个子项对应上面的模型名称(name)
@@ -177,6 +183,11 @@ model_list = ["deepseek-v3"]
 temperature = 0.7
 max_tokens = 1000
 
+[model_task_config.anti_injection] # 反注入检测专用模型
+model_list = ["moonshotai-Kimi-K2-Instruct"]           # 使用快速的小模型进行检测
+temperature = 0.1                   # 低温度确保检测结果稳定
+max_tokens = 200                    # 检测结果不需要太长的输出
+
 #嵌入模型
 [model_task_config.embedding]
 model_list = ["bge-m3"]