7b9e0826de
- 新增 embedding_service（语义检索）、knowledge_service（RAG）、text_chunker、document_parser - 新增 tool_registry（自定义工具注册表）并完善工具市场 API（CRUD + code/http 执行） - 新增 agent_vector_memory / knowledge_base 模型及对应数据库表 - 实现 SSE 流式响应与 Agent 预算控制 - AgentChat.vue 集成 MainLayout 导航布局 - 完善测试体系：7 个新测试文件共 110 个测试覆盖 - 修复 conftest.py SQLite 内存数据库连接隔离问题 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
86 lines
3.3 KiB
Python
86 lines
3.3 KiB
Python
"""
|
||
Agent Runtime 配置与数据结构 Schema
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
from typing import Any, Dict, List, Optional
|
||
from pydantic import BaseModel, Field
|
||
|
||
|
||
class AgentToolConfig(BaseModel):
|
||
"""Agent 可用工具配置"""
|
||
# 若为空列表则使用全部已注册工具
|
||
include_tools: List[str] = Field(default_factory=list, description="允许的工具名称白名单")
|
||
exclude_tools: List[str] = Field(default_factory=list, description="排除的工具名称黑名单")
|
||
|
||
|
||
class AgentMemoryConfig(BaseModel):
|
||
"""Agent 记忆配置"""
|
||
enabled: bool = True
|
||
max_history_messages: int = 20 # 注入 LLM 的上文最大消息数
|
||
session_key: Optional[str] = None # 会话标识，默认自动生成
|
||
persist_to_db: bool = True # 是否写入 MySQL 长期记忆
|
||
vector_memory_enabled: bool = True # 是否启用向量记忆（语义检索）
|
||
vector_memory_top_k: int = 5 # 向量检索 Top-K
|
||
|
||
|
||
class AgentLLMConfig(BaseModel):
|
||
"""Agent 模型配置"""
|
||
provider: str = "openai" # openai / deepseek
|
||
model: str = "gpt-4o-mini"
|
||
temperature: float = 0.7
|
||
max_tokens: Optional[int] = None
|
||
api_key: Optional[str] = None
|
||
base_url: Optional[str] = None
|
||
max_iterations: int = 10 # ReAct 循环最大步数
|
||
request_timeout: float = 120.0
|
||
extra_body: Optional[Dict[str, Any]] = None
|
||
|
||
|
||
class AgentBudgetConfig(BaseModel):
|
||
"""Agent 执行预算配置"""
|
||
max_llm_invocations: int = 200 # LLM 调用次数上限
|
||
max_tool_calls: int = 500 # 工具调用次数上限
|
||
|
||
|
||
class AgentConfig(BaseModel):
|
||
"""Agent 完整配置"""
|
||
name: str = "default_agent"
|
||
system_prompt: str = "你是一个有用的AI助手。请使用可用工具来帮助用户完成任务。"
|
||
llm: AgentLLMConfig = Field(default_factory=AgentLLMConfig)
|
||
tools: AgentToolConfig = Field(default_factory=AgentToolConfig)
|
||
memory: AgentMemoryConfig = Field(default_factory=AgentMemoryConfig)
|
||
budget: AgentBudgetConfig = Field(default_factory=AgentBudgetConfig)
|
||
user_id: Optional[str] = None
|
||
|
||
|
||
class AgentMessage(BaseModel):
|
||
"""Agent 对话消息"""
|
||
role: str # user / assistant / tool
|
||
content: str
|
||
tool_calls: Optional[List[Dict[str, Any]]] = None
|
||
tool_call_id: Optional[str] = None
|
||
name: Optional[str] = None
|
||
|
||
|
||
class AgentStep(BaseModel):
|
||
"""Agent 单步执行记录（用于执行追踪）"""
|
||
iteration: int = Field(..., description="第几步")
|
||
type: str = Field(..., description="步骤类型: think / tool_call / tool_result / final")
|
||
content: str = Field(default="", description="步骤内容")
|
||
tool_name: Optional[str] = Field(default=None, description="工具名称（tool_call/tool_result 类型时）")
|
||
tool_input: Optional[Dict[str, Any]] = Field(default=None, description="工具输入参数")
|
||
tool_result: Optional[str] = Field(default=None, description="工具执行结果")
|
||
reasoning: Optional[str] = Field(default=None, description="思考过程")
|
||
|
||
|
||
class AgentResult(BaseModel):
|
||
"""Agent 执行结果"""
|
||
success: bool = True
|
||
content: str = ""
|
||
truncated: bool = False
|
||
iterations_used: int = 0
|
||
tool_calls_made: int = 0
|
||
error: Optional[str] = None
|
||
steps: List[AgentStep] = Field(default_factory=list, description="执行追踪步骤详情")
|