WuYanBo
/
CodeReview
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
CodeReview/backend/app/services/agent/__init__.py

124 lines
2.7 KiB
Python
Raw Normal View History

feat(agent): implement Agent audit module with LangGraph integration - Introduce new Agent audit functionality for autonomous code security analysis and vulnerability verification. - Add API endpoints for managing Agent tasks and configurations. - Implement UI components for Agent mode selection and embedding model configuration. - Enhance the overall architecture with a focus on RAG (Retrieval-Augmented Generation) for improved code semantic search. - Create a sandbox environment for secure execution of vulnerability tests. - Update documentation to include details on the new Agent audit features and usage instructions.
2025-12-11 19:09:10 +08:00
"""
DeepAudit Agent 服务模块
基于 LangGraph 的 AI Agent 代码安全审计
feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence
2025-12-12 15:27:12 +08:00
架构升级版本 - 支持：
- 动态Agent树结构
- 专业知识模块系统
- Agent间通信机制
- 完整状态管理
- Think工具和漏洞报告工具
工作流:
feat(agent): implement Agent audit module with LangGraph integration - Introduce new Agent audit functionality for autonomous code security analysis and vulnerability verification. - Add API endpoints for managing Agent tasks and configurations. - Implement UI components for Agent mode selection and embedding model configuration. - Enhance the overall architecture with a focus on RAG (Retrieval-Augmented Generation) for improved code semantic search. - Create a sandbox environment for secure execution of vulnerability tests. - Update documentation to include details on the new Agent audit features and usage instructions.
2025-12-11 19:09:10 +08:00
START → Recon → Analysis ⟲ → Verification → Report → END
feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence
2025-12-12 15:27:12 +08:00
支持动态创建子Agent进行专业化分析
feat(agent): implement Agent audit module with LangGraph integration - Introduce new Agent audit functionality for autonomous code security analysis and vulnerability verification. - Add API endpoints for managing Agent tasks and configurations. - Implement UI components for Agent mode selection and embedding model configuration. - Enhance the overall architecture with a focus on RAG (Retrieval-Augmented Generation) for improved code semantic search. - Create a sandbox environment for secure execution of vulnerability tests. - Update documentation to include details on the new Agent audit features and usage instructions.
2025-12-11 19:09:10 +08:00
"""
# 从 graph 模块导入主要组件
from .graph import (
AgentRunner,
run_agent_task,
LLMService,
AuditState,
create_audit_graph,
)
# 事件管理
from .event_manager import EventManager, AgentEventEmitter
# Agent 类
from .agents import (
BaseAgent, AgentConfig, AgentResult,
OrchestratorAgent, ReconAgent, AnalysisAgent, VerificationAgent,
)
feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence
2025-12-12 15:27:12 +08:00
# 🔥 新增：核心模块（状态管理、注册表、消息）
from .core import (
AgentState, AgentStatus,
AgentRegistry, agent_registry,
AgentMessage, MessageType, MessagePriority, MessageBus,
)
# 🔥 新增：知识模块系统（基于RAG）
from .knowledge import (
KnowledgeLoader, knowledge_loader,
get_available_modules, get_module_content,
SecurityKnowledgeRAG, security_knowledge_rag,
SecurityKnowledgeQueryTool, GetVulnerabilityKnowledgeTool,
)
# 🔥 新增：协作工具
from .tools import (
ThinkTool, ReflectTool,
CreateVulnerabilityReportTool,
feat: 新增安全工具集成和漏洞知识库扩展 - 添加 Bandit 和 Safety 安全工具到依赖项 - 新增 CSRF、业务逻辑和开放重定向漏洞知识文档 - 实现安全工具一键安装脚本和文档 - 改进模式匹配工具支持直接文件扫描 - 增强遥测模块和 Agent 审计功能 - 修复验证节点中 findings 合并逻辑 - 优化前端 Agent 审计界面和状态展示
2025-12-13 12:35:03 +08:00
FinishScanTool,
feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence
2025-12-12 15:27:12 +08:00
CreateSubAgentTool, SendMessageTool, ViewAgentGraphTool,
WaitForMessageTool, AgentFinishTool,
)
feat: 新增安全工具集成和漏洞知识库扩展 - 添加 Bandit 和 Safety 安全工具到依赖项 - 新增 CSRF、业务逻辑和开放重定向漏洞知识文档 - 实现安全工具一键安装脚本和文档 - 改进模式匹配工具支持直接文件扫描 - 增强遥测模块和 Agent 审计功能 - 修复验证节点中 findings 合并逻辑 - 优化前端 Agent 审计界面和状态展示
2025-12-13 12:35:03 +08:00
# 🔥 新增：遥测模块
from .telemetry import Tracer, get_global_tracer, set_global_tracer
feat(agent): implement Agent audit module with LangGraph integration - Introduce new Agent audit functionality for autonomous code security analysis and vulnerability verification. - Add API endpoints for managing Agent tasks and configurations. - Implement UI components for Agent mode selection and embedding model configuration. - Enhance the overall architecture with a focus on RAG (Retrieval-Augmented Generation) for improved code semantic search. - Create a sandbox environment for secure execution of vulnerability tests. - Update documentation to include details on the new Agent audit features and usage instructions.
2025-12-11 19:09:10 +08:00
__all__ = [
# 核心 Runner
"AgentRunner",
"run_agent_task",
"LLMService",
# LangGraph
"AuditState",
"create_audit_graph",
# 事件管理
"EventManager",
"AgentEventEmitter",
# Agent 类
"BaseAgent",
"AgentConfig",
"AgentResult",
"OrchestratorAgent",
"ReconAgent",
"AnalysisAgent",
"VerificationAgent",
feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence
2025-12-12 15:27:12 +08:00
# 🔥 核心模块
"AgentState",
"AgentStatus",
"AgentRegistry",
"agent_registry",
"AgentMessage",
"MessageType",
"MessagePriority",
"MessageBus",
# 🔥 知识模块（基于RAG）
"KnowledgeLoader",
"knowledge_loader",
"get_available_modules",
"get_module_content",
"SecurityKnowledgeRAG",
"security_knowledge_rag",
"SecurityKnowledgeQueryTool",
"GetVulnerabilityKnowledgeTool",
# 🔥 协作工具
"ThinkTool",
"ReflectTool",
"CreateVulnerabilityReportTool",
feat: 新增安全工具集成和漏洞知识库扩展 - 添加 Bandit 和 Safety 安全工具到依赖项 - 新增 CSRF、业务逻辑和开放重定向漏洞知识文档 - 实现安全工具一键安装脚本和文档 - 改进模式匹配工具支持直接文件扫描 - 增强遥测模块和 Agent 审计功能 - 修复验证节点中 findings 合并逻辑 - 优化前端 Agent 审计界面和状态展示
2025-12-13 12:35:03 +08:00
"FinishScanTool",
feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence
2025-12-12 15:27:12 +08:00
"CreateSubAgentTool",
"SendMessageTool",
"ViewAgentGraphTool",
"WaitForMessageTool",
"AgentFinishTool",
feat: 新增安全工具集成和漏洞知识库扩展 - 添加 Bandit 和 Safety 安全工具到依赖项 - 新增 CSRF、业务逻辑和开放重定向漏洞知识文档 - 实现安全工具一键安装脚本和文档 - 改进模式匹配工具支持直接文件扫描 - 增强遥测模块和 Agent 审计功能 - 修复验证节点中 findings 合并逻辑 - 优化前端 Agent 审计界面和状态展示
2025-12-13 12:35:03 +08:00
# 🔥 遥测模块
"Tracer",
"get_global_tracer",
"set_global_tracer",
feat(agent): implement Agent audit module with LangGraph integration - Introduce new Agent audit functionality for autonomous code security analysis and vulnerability verification. - Add API endpoints for managing Agent tasks and configurations. - Implement UI components for Agent mode selection and embedding model configuration. - Enhance the overall architecture with a focus on RAG (Retrieval-Augmented Generation) for improved code semantic search. - Create a sandbox environment for secure execution of vulnerability tests. - Update documentation to include details on the new Agent audit features and usage instructions.
2025-12-11 19:09:10 +08:00
]