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

168 lines
3.8 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
"""
Agent 工具集
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
提供 Agent 使用的各种工具，包括：
- 基础工具（文件操作、代码搜索）
- 分析工具（模式匹配、数据流分析）
- 外部安全工具（Semgrep、Bandit等）
- 协作工具（Think、Agent通信）
- 报告工具（漏洞报告）
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
- 🔥 智能扫描工具（批量扫描、快速审计）
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
"""
from .base import AgentTool, ToolResult
from .rag_tool import RAGQueryTool, SecurityCodeSearchTool, FunctionContextTool
from .pattern_tool import PatternMatchTool
from .code_analysis_tool import CodeAnalysisTool, DataFlowAnalysisTool, VulnerabilityValidationTool
from .file_tool import FileReadTool, FileSearchTool, ListFilesTool
feat(agent): 新增多语言代码测试和漏洞验证工具并增强错误处理 新增 PHP、Python、JavaScript 等多语言代码测试工具和命令注入、SQL 注入等专用漏洞验证工具 优化错误处理逻辑，提供更详细的错误信息和堆栈跟踪 增强 JSON 解析器，优先使用 json-repair 库处理复杂格式 改进 Agent 响应解析逻辑，更健壮地提取思考内容和操作指令 完善沙箱管理器的初始化和错误处理机制
2025-12-14 17:20:54 +08:00
from .sandbox_tool import (
SandboxTool,
SandboxHttpTool,
VulnerabilityVerifyTool,
SandboxManager,
)
# 🔥 多语言代码测试工具
from .sandbox_language import (
PhpTestTool,
PythonTestTool,
JavaScriptTestTool,
JavaTestTool,
GoTestTool,
RubyTestTool,
ShellTestTool,
UniversalCodeTestTool,
)
# 🔥 漏洞验证专用工具
from .sandbox_vuln import (
CommandInjectionTestTool,
SqlInjectionTestTool,
XssTestTool,
PathTraversalTestTool,
SstiTestTool,
DeserializationTestTool,
UniversalVulnTestTool,
)
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
# 外部安全工具
from .external_tools import (
SemgrepTool,
BanditTool,
GitleaksTool,
NpmAuditTool,
SafetyTool,
TruffleHogTool,
OSVScannerTool,
)
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：思考和推理工具
from .thinking_tool import ThinkTool, ReflectTool
# 🔥 新增：漏洞报告工具
from .reporting_tool import 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
# 🔥 新增：扫描完成工具
from .finish_tool import 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
# 🔥 新增：Agent协作工具
from .agent_tools import (
CreateSubAgentTool,
SendMessageTool,
ViewAgentGraphTool,
WaitForMessageTool,
AgentFinishTool,
RunSubAgentsTool,
CollectSubAgentResultsTool,
)
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：智能扫描工具
from .smart_scan_tool import SmartScanTool, QuickAuditTool
feat: Introduce Kunlun agent tool, add Docker and sandbox environment checks, and update agent services and frontend dialogs.
2025-12-15 02:00:34 +08:00
# 🔥 新增：Kunlun-M 静态代码分析工具 (MIT License)
from .kunlun_tool import KunlunMTool, KunlunRuleListTool, KunlunPluginTool
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__ = [
# 基础
"AgentTool",
"ToolResult",
# RAG 工具
"RAGQueryTool",
"SecurityCodeSearchTool",
"FunctionContextTool",
# 代码分析
"PatternMatchTool",
"CodeAnalysisTool",
"DataFlowAnalysisTool",
"VulnerabilityValidationTool",
# 文件操作
"FileReadTool",
"FileSearchTool",
"ListFilesTool",
# 沙箱
"SandboxTool",
"SandboxHttpTool",
"VulnerabilityVerifyTool",
"SandboxManager",
feat(agent): 新增多语言代码测试和漏洞验证工具并增强错误处理 新增 PHP、Python、JavaScript 等多语言代码测试工具和命令注入、SQL 注入等专用漏洞验证工具 优化错误处理逻辑，提供更详细的错误信息和堆栈跟踪 增强 JSON 解析器，优先使用 json-repair 库处理复杂格式 改进 Agent 响应解析逻辑，更健壮地提取思考内容和操作指令 完善沙箱管理器的初始化和错误处理机制
2025-12-14 17:20:54 +08:00
# 🔥 多语言代码测试工具
"PhpTestTool",
"PythonTestTool",
"JavaScriptTestTool",
"JavaTestTool",
"GoTestTool",
"RubyTestTool",
"ShellTestTool",
"UniversalCodeTestTool",
# 🔥 漏洞验证专用工具
"CommandInjectionTestTool",
"SqlInjectionTestTool",
"XssTestTool",
"PathTraversalTestTool",
"SstiTestTool",
"DeserializationTestTool",
"UniversalVulnTestTool",
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
# 外部安全工具
"SemgrepTool",
"BanditTool",
"GitleaksTool",
"NpmAuditTool",
"SafetyTool",
"TruffleHogTool",
"OSVScannerTool",
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
# 🔥 思考和推理工具
"ThinkTool",
"ReflectTool",
# 🔥 漏洞报告工具
"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
# 🔥 扫描完成工具
"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
# 🔥 Agent协作工具
"CreateSubAgentTool",
"SendMessageTool",
"ViewAgentGraphTool",
"WaitForMessageTool",
"AgentFinishTool",
"RunSubAgentsTool",
"CollectSubAgentResultsTool",
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
# 🔥 智能扫描工具
"SmartScanTool",
"QuickAuditTool",
feat: Introduce Kunlun agent tool, add Docker and sandbox environment checks, and update agent services and frontend dialogs.
2025-12-15 02:00:34 +08:00
# 🔥 Kunlun-M 工具 (MIT License - https://github.com/LoRexxar/Kunlun-M)
"KunlunMTool",
"KunlunRuleListTool",
"KunlunPluginTool",
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
]