ab1589921a
## 安全修复 (12项) - Webhook接口添加全局Token认证，过滤敏感请求头 - 修复JWT Base64 padding公式，防止签名验证绕过 - 数据库密码/飞书Token从源码移除，改为环境变量 - 工作流引擎添加路径遍历防护 (_resolve_safe_path) - eval()添加模板长度上限检查 - 审批API添加认证依赖 - 前端v-html增强XSS转义，console.log仅开发模式输出 - 500错误不再暴露内部异常详情 ## Agent运行时修复 (7项) - 删除_inject_knowledge_context中未定义db变量的finally块 - 工具执行添加try/except保护，异常不崩溃Agent - LLM重试计入budget计数器 - self_review异常时passed=False - max_iterations截断标记success=False - 工具参数JSON解析失败时记录警告日志 - run()开始时重置_llm_invocations计数器 ## 配置与基础设施 - DEBUG默认False，SQL_ECHO独立配置项 - init_db()补全13个缺失模型导入 - 新增WEBHOOK_AUTH_TOKEN/SQL_ECHO配置项 - 新增.env.example模板文件 ## 前端修复 (12项) - 登录改用URLSearchParams替代FormData - 401拦截器通过Pinia store统一清理状态 - SSE流超时从60s延长至300s - final/error事件时清除streamTimeout - localStorage聊天记录添加24h TTL - safeParseArgCount替代模板中裸JSON.parse - fetchUser 401时同时清除user对象 ## 新增模块 - 知识进化: knowledge_extractor/retriever/tasks - 数字孪生: shadow_executor/comparison模型 - 行为采集: behavior_middleware/collector/fingerprint_engine - 代码审查: code_review_agent/document_review_agent - 反馈学习: feedback_learner - 瓶颈检测/优化引擎/成本估算/需求估算 - 速率限制器 (rate_limiter) - Alembic迁移 015-020 ## 文档 - 商业化落地计划 - 8篇docs文档 (架构/API/部署/开发/贡献等) - Docker Compose生产配置 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
111 lines
5.1 KiB
Python
111 lines
5.1 KiB
Python
"""
|
||
Agent Runtime 配置与数据结构 Schema
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import logging
|
||
logger = logging.getLogger(__name__)
|
||
logger.warning("SCHEMAS_MODULE_LOADED_V3_FIELD_VALIDATOR")
|
||
|
||
from typing import Any, Dict, List, Optional
|
||
from pydantic import BaseModel, Field, field_validator
|
||
|
||
|
||
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")
|
||
require_approval: List[str] = Field(default_factory=list, description="需要人工审批的工具名列表")
|
||
|
||
@field_validator("include_tools", "exclude_tools", "require_approval", "cache_tool_whitelist", mode="before")
|
||
@classmethod
|
||
def coerce_none_to_empty(cls, v: Any) -> Any:
|
||
return v if v is not None else []
|
||
approval_timeout_ms: int = Field(default=60000, description="审批超时（毫秒），超时使用默认策略")
|
||
approval_default: str = Field(default="deny", description="超时默认策略: approve | deny | skip")
|
||
# 结果缓存
|
||
cache_enabled: bool = Field(default=True, description="是否启用工具结果缓存（确定性工具默认开启）")
|
||
cache_tool_whitelist: List[str] = Field(default_factory=list, description="启用缓存的工具名（空=确定性工具默认）")
|
||
cache_ttl_ms: int = Field(default=3600000, description="缓存 TTL（毫秒），默认 1 小时")
|
||
|
||
|
||
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
|
||
learning_enabled: bool = True # 是否启用自主学习（工具模式学习）
|
||
|
||
|
||
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
|
||
self_review_threshold: float = 0.6 # self-review 通过阈值（0-1）
|
||
cache_enabled: bool = False # LLM 响应缓存（默认关闭，语义缓存有风险）
|
||
cache_ttl_ms: int = 300000 # LLM 缓存 TTL，默认 5 分钟
|
||
fallback_llm: Optional[Dict[str, Any]] = None # 降级模型配置 {provider, model, api_key, base_url}
|
||
|
||
|
||
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
|
||
# 持久记忆 / 向量记忆的 scope_id；不设时沿用 user_id 或 name（易与其他 Agent 串记忆）
|
||
memory_scope_id: Optional[str] = None
|
||
# 是否开启输出质量自检（结束前用轻量 LLM 评审，不达标则追加修正）
|
||
self_review_enabled: bool = False
|
||
|
||
|
||
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")
|