{"owner":"alibaba","repo":"spring-ai-alibaba","hasSkills":true,"hasMcp":false,"mcpConfig":null,"found":["AGENTS.md","CLAUDE.md"],"skills":{"AGENTS.md":"# AGENTS.md - AI Assistant Guide for Spring AI Alibaba\n\nThis file provides guidance for AI assistants working with the Spring AI Alibaba codebase.\n\n## Project Overview\n\nSpring AI Alibaba is a production-ready framework for building Agentic, Workflow, and Multi-agent applications. It is an implementation of the Spring AI framework tailored for Alibaba Cloud services and components. It provides a comprehensive ecosystem for developing AI-powered applications with built-in context engineering and human-in-the-loop support.\n\n**Key Features:**\n\n- Multi-Agent Orchestration with built-in patterns\n- Context Engineering with human-in-the-loop, context compaction, editing, model call limits\n- Graph-based workflow with conditional routing, nested graphs, parallel execution\n- A2A (Agent-to-Agent) support with Nacos integration\n- Rich model support (DashScope, OpenAI, DeepSeek) and MCP (Model Context Protocol)\n- One-stop visual agent platform\n\n## Repository Structure\n\n```\nspring-ai-alibaba/\n├── spring-ai-alibaba-agent-framework/ # Multi-agent framework (Sequential, Parallel, Routing, etc.)\n├── spring-ai-alibaba-graph-core/      # Runtime providing persistence, workflow orchestration, state mgmt\n├── spring-ai-alibaba-studio/          # Embedded UI for debugging agents visually\n├── spring-ai-alibaba-admin/           # One-stop Agent platform (visual dev, observability, MCP mgmt)\n├── spring-ai-alibaba-bom/             # Bill of Materials for dependency management\n├── spring-boot-starters/              # Spring Boot Starters\n│   ├── spring-ai-alibaba-starter-a2a-nacos/     # Nacos A2A communication\n│   ├── spring-ai-alibaba-starter-builtin-nodes/ # Built-in workflow nodes\n│   ├── spring-ai-alibaba-starter-config-nacos/  # Dynamic config with Nacos\n│   └── spring-ai-alibaba-starter-graph-observation/ # Observability\n├── examples/                          # Example applications\n│   ├── chatbot/                       # Chatbot example\n│   ├── deepresearch/                  # Deep research agent example\n│   └── documentation/                 # Documentation examples\n├── tools/                             # Build and linting tools\n└── docs/                              # Documentation\n```\n\n## Build System\n\n### Prerequisites\n\n- **JDK**: 17 (Required by `java.version` property)\n- **Maven**: 3.6+\n- **Git**\n\n### Common Build Commands\n\n```shell\n# Build the entire project (skip tests)\n./mvnw -B package -DskipTests=true\n\n# Build a specific module\n./mvnw -pl :spring-ai-alibaba-agent-framework -B package -DskipTests=true\n\n# Clean project\n./mvnw clean\n\n# Run tests\n./mvnw test\n\n# Run linting checks (using Makefile)\nmake lint\nmake licenses-check\n```\n\n## Architecture & Key Concepts\n\n### Core Components\n\n- **Agent Framework**: Built-in agents like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n- **Graph Core**: Underlying engine for stateful agents, supporting persistence (PostgreSQL, MySQL, Oracle, MongoDB, Redis, File).\n- **A2A (Agent-to-Agent)**: Enables agents to seek and communicate with each other using Nacos as a registry.\n- **Admin & Studio**: Provides visual tools for developing and debugging agent workflows.\n\n### Technology Stack\n\n- **Framework**: Spring Boot 3.5.x, Spring AI 1.1.x\n- **Cloud Integration**: Alibaba Cloud DashScope, Nacos (Service Discovery & Config)\n- **Observability**: Spring Cloud Observation (Micrometer/OpenTelemetry)\n\n## Code Style & Conventions\n\n### General Guidelines\n\n- Follow **Spring AI** standard code formatting.\n- Use **Apache 2.0** license headers for all Java files.\n- **Java 17** features are encouraged (records, switch expressions, text blocks).\n- Avoid `System.out.println` - use SLF4J logging.\n- Use `final` for local variables and parameters where appropriate.\n- Use Lombok annotations (`@Data`, `@Slf4j`, etc.) to reduce boilerplate.\n\n### Linting & Formatting\n\nThe project uses `make` for linting tasks:\n- `make codespell`: Checks for spelling errors.\n- `make yaml-lint`: Checks YAML file formatting.\n- `make licenses-check`: Verifies license headers.\n\n### License Header\n\n```java\n/*\n * Copyright 2025-2026 the original author or authors.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     https://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n```\n\n## Testing\n\n### Frameworks\n\n- **JUnit 5** (`org.junit.jupiter`)\n- **Mockito**\n\n### Running Tests\n\n```shell\n# Run all tests\n./mvnw test\n\n# Run a specific test class\n./mvnw -pl :<module-name> -Dtest=<TestClassName> test\n```\n\n## Tips for AI Assistants\n\n1.  **JDK Version**: Project targets JDK 17. Use appropriate language features.\n2.  **Spring Boot**: Uses Spring Boot 3.x. Be aware of `jakarta.*` namespace vs `javax.*`.\n3.  **Dependencies**: Check `spring-ai-alibaba-bom` or parent pom for version management.\n4.  **Makefile**: Use the Makefile in the root for project maintenance tasks (linting, license checks).\n5.  **Structure**: When adding new features, prefer creating or updating modules within `spring-ai-alibaba-agent-framework` or `spring-boot-starters` depending on the scope.\n\n## Important Links\n\n- **Issues**: [https://github.com/alibaba/spring-ai-alibaba/issues](https://github.com/alibaba/spring-ai-alibaba/issues)\n- **Source**: [https://github.com/alibaba/spring-ai-alibaba](https://github.com/alibaba/spring-ai-alibaba)\n- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)\n","CLAUDE.md":"# CLAUDE.md - AI Assistant Guide for Spring AI Alibaba\n\nThis file provides guidance for AI assistants working with the Spring AI Alibaba codebase.\n\n## Project Overview\n\nSpring AI Alibaba is a production-ready framework for building Agentic, Workflow, and Multi-agent applications. It is an implementation of the Spring AI framework tailored for Alibaba Cloud services and components. It provides a comprehensive ecosystem for developing AI-powered applications with built-in context engineering and human-in-the-loop support.\n\n**Key Features:**\n\n- Multi-Agent Orchestration with built-in patterns\n- Context Engineering with human-in-the-loop, context compaction, editing, model call limits\n- Graph-based workflow with conditional routing, nested graphs, parallel execution\n- A2A (Agent-to-Agent) support with Nacos integration\n- Rich model support (DashScope, OpenAI, DeepSeek) and MCP (Model Context Protocol)\n- One-stop visual agent platform\n\n## Repository Structure\n\n```\nspring-ai-alibaba/\n├── spring-ai-alibaba-agent-framework/ # Multi-agent framework (Sequential, Parallel, Routing, etc.)\n├── spring-ai-alibaba-graph-core/      # Runtime providing persistence, workflow orchestration, state mgmt\n├── spring-ai-alibaba-studio/          # Embedded UI for debugging agents visually\n├── spring-ai-alibaba-admin/           # One-stop Agent platform (visual dev, observability, MCP mgmt)\n├── spring-ai-alibaba-bom/             # Bill of Materials for dependency management\n├── spring-boot-starters/              # Spring Boot Starters\n│   ├── spring-ai-alibaba-starter-a2a-nacos/     # Nacos A2A communication\n│   ├── spring-ai-alibaba-starter-builtin-nodes/ # Built-in workflow nodes\n│   ├── spring-ai-alibaba-starter-config-nacos/  # Dynamic config with Nacos\n│   └── spring-ai-alibaba-starter-graph-observation/ # Observability\n├── examples/                          # Example applications\n│   ├── chatbot/                       # Chatbot example\n│   ├── deepresearch/                  # Deep research agent example\n│   └── documentation/                 # Documentation examples\n├── tools/                             # Build and linting tools\n└── docs/                              # Documentation\n```\n\n## Build System\n\n### Prerequisites\n\n- **JDK**: 17 (Required by `java.version` property)\n- **Maven**: 3.6+\n- **Git**\n\n### Common Build Commands\n\n```shell\n# Build the entire project (skip tests)\n./mvnw -B package -DskipTests=true\n\n# Build a specific module\n./mvnw -pl :spring-ai-alibaba-agent-framework -B package -DskipTests=true\n\n# Clean project\n./mvnw clean\n\n# Run tests\n./mvnw test\n\n# Run linting checks (using Makefile)\nmake lint\nmake licenses-check\n```\n\n## Architecture & Key Concepts\n\n### Core Components\n\n- **Agent Framework**: Built-in agents like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n- **Graph Core**: Underlying engine for stateful agents, supporting persistence (PostgreSQL, MySQL, Oracle, MongoDB, Redis, File).\n- **A2A (Agent-to-Agent)**: Enables agents to seek and communicate with each other using Nacos as a registry.\n- **Admin & Studio**: Provides visual tools for developing and debugging agent workflows.\n\n### Technology Stack\n\n- **Framework**: Spring Boot 3.5.x, Spring AI 1.1.x\n- **Cloud Integration**: Alibaba Cloud DashScope, Nacos (Service Discovery & Config)\n- **Observability**: Spring Cloud Observation (Micrometer/OpenTelemetry)\n\n## Code Style & Conventions\n\n### General Guidelines\n\n- Follow **Spring AI** standard code formatting.\n- Use **Apache 2.0** license headers for all Java files.\n- **Java 17** features are encouraged (records, switch expressions, text blocks).\n- Avoid `System.out.println` - use SLF4J logging.\n- Use `final` for local variables and parameters where appropriate.\n- Use Lombok annotations (`@Data`, `@Slf4j`, etc.) to reduce boilerplate.\n\n### Linting & Formatting\n\nThe project uses `make` for linting tasks:\n- `make codespell`: Checks for spelling errors.\n- `make yaml-lint`: Checks YAML file formatting.\n- `make licenses-check`: Verifies license headers.\n\n### License Header\n\n```java\n/*\n * Copyright 2025-2026 the original author or authors.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     https://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n```\n\n## Testing\n\n### Frameworks\n\n- **JUnit 5** (`org.junit.jupiter`)\n- **Mockito**\n\n### Running Tests\n\n```shell\n# Run all tests\n./mvnw test\n\n# Run a specific test class\n./mvnw -pl :<module-name> -Dtest=<TestClassName> test\n```\n\n## Tips for AI Assistants\n\n1.  **JDK Version**: Project targets JDK 17. Use appropriate language features.\n2.  **Spring Boot**: Uses Spring Boot 3.x. Be aware of `jakarta.*` namespace vs `javax.*`.\n3.  **Dependencies**: Check `spring-ai-alibaba-bom` or parent pom for version management.\n4.  **Makefile**: Use the Makefile in the root for project maintenance tasks (linting, license checks).\n5.  **Structure**: When adding new features, prefer creating or updating modules within `spring-ai-alibaba-agent-framework` or `spring-boot-starters` depending on the scope.\n\n## Important Links\n\n- **Issues**: [https://github.com/alibaba/spring-ai-alibaba/issues](https://github.com/alibaba/spring-ai-alibaba/issues)\n- **Source**: [https://github.com/alibaba/spring-ai-alibaba](https://github.com/alibaba/spring-ai-alibaba)\n- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)\n"},"files":{"AGENTS.md":"# AGENTS.md - AI Assistant Guide for Spring AI Alibaba\n\nThis file provides guidance for AI assistants working with the Spring AI Alibaba codebase.\n\n## Project Overview\n\nSpring AI Alibaba is a production-ready framework for building Agentic, Workflow, and Multi-agent applications. It is an implementation of the Spring AI framework tailored for Alibaba Cloud services and components. It provides a comprehensive ecosystem for developing AI-powered applications with built-in context engineering and human-in-the-loop support.\n\n**Key Features:**\n\n- Multi-Agent Orchestration with built-in patterns\n- Context Engineering with human-in-the-loop, context compaction, editing, model call limits\n- Graph-based workflow with conditional routing, nested graphs, parallel execution\n- A2A (Agent-to-Agent) support with Nacos integration\n- Rich model support (DashScope, OpenAI, DeepSeek) and MCP (Model Context Protocol)\n- One-stop visual agent platform\n\n## Repository Structure\n\n```\nspring-ai-alibaba/\n├── spring-ai-alibaba-agent-framework/ # Multi-agent framework (Sequential, Parallel, Routing, etc.)\n├── spring-ai-alibaba-graph-core/      # Runtime providing persistence, workflow orchestration, state mgmt\n├── spring-ai-alibaba-studio/          # Embedded UI for debugging agents visually\n├── spring-ai-alibaba-admin/           # One-stop Agent platform (visual dev, observability, MCP mgmt)\n├── spring-ai-alibaba-bom/             # Bill of Materials for dependency management\n├── spring-boot-starters/              # Spring Boot Starters\n│   ├── spring-ai-alibaba-starter-a2a-nacos/     # Nacos A2A communication\n│   ├── spring-ai-alibaba-starter-builtin-nodes/ # Built-in workflow nodes\n│   ├── spring-ai-alibaba-starter-config-nacos/  # Dynamic config with Nacos\n│   └── spring-ai-alibaba-starter-graph-observation/ # Observability\n├── examples/                          # Example applications\n│   ├── chatbot/                       # Chatbot example\n│   ├── deepresearch/                  # Deep research agent example\n│   └── documentation/                 # Documentation examples\n├── tools/                             # Build and linting tools\n└── docs/                              # Documentation\n```\n\n## Build System\n\n### Prerequisites\n\n- **JDK**: 17 (Required by `java.version` property)\n- **Maven**: 3.6+\n- **Git**\n\n### Common Build Commands\n\n```shell\n# Build the entire project (skip tests)\n./mvnw -B package -DskipTests=true\n\n# Build a specific module\n./mvnw -pl :spring-ai-alibaba-agent-framework -B package -DskipTests=true\n\n# Clean project\n./mvnw clean\n\n# Run tests\n./mvnw test\n\n# Run linting checks (using Makefile)\nmake lint\nmake licenses-check\n```\n\n## Architecture & Key Concepts\n\n### Core Components\n\n- **Agent Framework**: Built-in agents like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n- **Graph Core**: Underlying engine for stateful agents, supporting persistence (PostgreSQL, MySQL, Oracle, MongoDB, Redis, File).\n- **A2A (Agent-to-Agent)**: Enables agents to seek and communicate with each other using Nacos as a registry.\n- **Admin & Studio**: Provides visual tools for developing and debugging agent workflows.\n\n### Technology Stack\n\n- **Framework**: Spring Boot 3.5.x, Spring AI 1.1.x\n- **Cloud Integration**: Alibaba Cloud DashScope, Nacos (Service Discovery & Config)\n- **Observability**: Spring Cloud Observation (Micrometer/OpenTelemetry)\n\n## Code Style & Conventions\n\n### General Guidelines\n\n- Follow **Spring AI** standard code formatting.\n- Use **Apache 2.0** license headers for all Java files.\n- **Java 17** features are encouraged (records, switch expressions, text blocks).\n- Avoid `System.out.println` - use SLF4J logging.\n- Use `final` for local variables and parameters where appropriate.\n- Use Lombok annotations (`@Data`, `@Slf4j`, etc.) to reduce boilerplate.\n\n### Linting & Formatting\n\nThe project uses `make` for linting tasks:\n- `make codespell`: Checks for spelling errors.\n- `make yaml-lint`: Checks YAML file formatting.\n- `make licenses-check`: Verifies license headers.\n\n### License Header\n\n```java\n/*\n * Copyright 2025-2026 the original author or authors.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     https://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n```\n\n## Testing\n\n### Frameworks\n\n- **JUnit 5** (`org.junit.jupiter`)\n- **Mockito**\n\n### Running Tests\n\n```shell\n# Run all tests\n./mvnw test\n\n# Run a specific test class\n./mvnw -pl :<module-name> -Dtest=<TestClassName> test\n```\n\n## Tips for AI Assistants\n\n1.  **JDK Version**: Project targets JDK 17. Use appropriate language features.\n2.  **Spring Boot**: Uses Spring Boot 3.x. Be aware of `jakarta.*` namespace vs `javax.*`.\n3.  **Dependencies**: Check `spring-ai-alibaba-bom` or parent pom for version management.\n4.  **Makefile**: Use the Makefile in the root for project maintenance tasks (linting, license checks).\n5.  **Structure**: When adding new features, prefer creating or updating modules within `spring-ai-alibaba-agent-framework` or `spring-boot-starters` depending on the scope.\n\n## Important Links\n\n- **Issues**: [https://github.com/alibaba/spring-ai-alibaba/issues](https://github.com/alibaba/spring-ai-alibaba/issues)\n- **Source**: [https://github.com/alibaba/spring-ai-alibaba](https://github.com/alibaba/spring-ai-alibaba)\n- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)\n","CLAUDE.md":"# CLAUDE.md - AI Assistant Guide for Spring AI Alibaba\n\nThis file provides guidance for AI assistants working with the Spring AI Alibaba codebase.\n\n## Project Overview\n\nSpring AI Alibaba is a production-ready framework for building Agentic, Workflow, and Multi-agent applications. It is an implementation of the Spring AI framework tailored for Alibaba Cloud services and components. It provides a comprehensive ecosystem for developing AI-powered applications with built-in context engineering and human-in-the-loop support.\n\n**Key Features:**\n\n- Multi-Agent Orchestration with built-in patterns\n- Context Engineering with human-in-the-loop, context compaction, editing, model call limits\n- Graph-based workflow with conditional routing, nested graphs, parallel execution\n- A2A (Agent-to-Agent) support with Nacos integration\n- Rich model support (DashScope, OpenAI, DeepSeek) and MCP (Model Context Protocol)\n- One-stop visual agent platform\n\n## Repository Structure\n\n```\nspring-ai-alibaba/\n├── spring-ai-alibaba-agent-framework/ # Multi-agent framework (Sequential, Parallel, Routing, etc.)\n├── spring-ai-alibaba-graph-core/      # Runtime providing persistence, workflow orchestration, state mgmt\n├── spring-ai-alibaba-studio/          # Embedded UI for debugging agents visually\n├── spring-ai-alibaba-admin/           # One-stop Agent platform (visual dev, observability, MCP mgmt)\n├── spring-ai-alibaba-bom/             # Bill of Materials for dependency management\n├── spring-boot-starters/              # Spring Boot Starters\n│   ├── spring-ai-alibaba-starter-a2a-nacos/     # Nacos A2A communication\n│   ├── spring-ai-alibaba-starter-builtin-nodes/ # Built-in workflow nodes\n│   ├── spring-ai-alibaba-starter-config-nacos/  # Dynamic config with Nacos\n│   └── spring-ai-alibaba-starter-graph-observation/ # Observability\n├── examples/                          # Example applications\n│   ├── chatbot/                       # Chatbot example\n│   ├── deepresearch/                  # Deep research agent example\n│   └── documentation/                 # Documentation examples\n├── tools/                             # Build and linting tools\n└── docs/                              # Documentation\n```\n\n## Build System\n\n### Prerequisites\n\n- **JDK**: 17 (Required by `java.version` property)\n- **Maven**: 3.6+\n- **Git**\n\n### Common Build Commands\n\n```shell\n# Build the entire project (skip tests)\n./mvnw -B package -DskipTests=true\n\n# Build a specific module\n./mvnw -pl :spring-ai-alibaba-agent-framework -B package -DskipTests=true\n\n# Clean project\n./mvnw clean\n\n# Run tests\n./mvnw test\n\n# Run linting checks (using Makefile)\nmake lint\nmake licenses-check\n```\n\n## Architecture & Key Concepts\n\n### Core Components\n\n- **Agent Framework**: Built-in agents like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n- **Graph Core**: Underlying engine for stateful agents, supporting persistence (PostgreSQL, MySQL, Oracle, MongoDB, Redis, File).\n- **A2A (Agent-to-Agent)**: Enables agents to seek and communicate with each other using Nacos as a registry.\n- **Admin & Studio**: Provides visual tools for developing and debugging agent workflows.\n\n### Technology Stack\n\n- **Framework**: Spring Boot 3.5.x, Spring AI 1.1.x\n- **Cloud Integration**: Alibaba Cloud DashScope, Nacos (Service Discovery & Config)\n- **Observability**: Spring Cloud Observation (Micrometer/OpenTelemetry)\n\n## Code Style & Conventions\n\n### General Guidelines\n\n- Follow **Spring AI** standard code formatting.\n- Use **Apache 2.0** license headers for all Java files.\n- **Java 17** features are encouraged (records, switch expressions, text blocks).\n- Avoid `System.out.println` - use SLF4J logging.\n- Use `final` for local variables and parameters where appropriate.\n- Use Lombok annotations (`@Data`, `@Slf4j`, etc.) to reduce boilerplate.\n\n### Linting & Formatting\n\nThe project uses `make` for linting tasks:\n- `make codespell`: Checks for spelling errors.\n- `make yaml-lint`: Checks YAML file formatting.\n- `make licenses-check`: Verifies license headers.\n\n### License Header\n\n```java\n/*\n * Copyright 2025-2026 the original author or authors.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     https://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n```\n\n## Testing\n\n### Frameworks\n\n- **JUnit 5** (`org.junit.jupiter`)\n- **Mockito**\n\n### Running Tests\n\n```shell\n# Run all tests\n./mvnw test\n\n# Run a specific test class\n./mvnw -pl :<module-name> -Dtest=<TestClassName> test\n```\n\n## Tips for AI Assistants\n\n1.  **JDK Version**: Project targets JDK 17. Use appropriate language features.\n2.  **Spring Boot**: Uses Spring Boot 3.x. Be aware of `jakarta.*` namespace vs `javax.*`.\n3.  **Dependencies**: Check `spring-ai-alibaba-bom` or parent pom for version management.\n4.  **Makefile**: Use the Makefile in the root for project maintenance tasks (linting, license checks).\n5.  **Structure**: When adding new features, prefer creating or updating modules within `spring-ai-alibaba-agent-framework` or `spring-boot-starters` depending on the scope.\n\n## Important Links\n\n- **Issues**: [https://github.com/alibaba/spring-ai-alibaba/issues](https://github.com/alibaba/spring-ai-alibaba/issues)\n- **Source**: [https://github.com/alibaba/spring-ai-alibaba](https://github.com/alibaba/spring-ai-alibaba)\n- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)\n"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","title":"AGENTS.md","content":"# AGENTS.md - AI Assistant Guide for Spring AI Alibaba\n\nThis file provides guidance for AI assistants working with the Spring AI Alibaba codebase.\n\n## Project Overview\n\nSpring AI Alibaba is a production-ready framework for building Agentic, Workflow, and Multi-agent applications. It is an implementation of the Spring AI framework tailored for Alibaba Cloud services and components. It provides a comprehensive ecosystem for developing AI-powered applications with built-in context engineering and human-in-the-loop support.\n\n**Key Features:**\n\n- Multi-Agent Orchestration with built-in patterns\n- Context Engineering with human-in-the-loop, context compaction, editing, model call limits\n- Graph-based workflow with conditional routing, nested graphs, parallel execution\n- A2A (Agent-to-Agent) support with Nacos integration\n- Rich model support (DashScope, OpenAI, DeepSeek) and MCP (Model Context Protocol)\n- One-stop visual agent platform\n\n## Repository Structure\n\n```\nspring-ai-alibaba/\n├── spring-ai-alibaba-agent-framework/ # Multi-agent framework (Sequential, Parallel, Routing, etc.)\n├── spring-ai-alibaba-graph-core/      # Runtime providing persistence, workflow orchestration, state mgmt\n├── spring-ai-alibaba-studio/          # Embedded UI for debugging agents visually\n├── spring-ai-alibaba-admin/           # One-stop Agent platform (visual dev, observability, MCP mgmt)\n├── spring-ai-alibaba-bom/             # Bill of Materials for dependency management\n├── spring-boot-starters/              # Spring Boot Starters\n│   ├── spring-ai-alibaba-starter-a2a-nacos/     # Nacos A2A communication\n│   ├── spring-ai-alibaba-starter-builtin-nodes/ # Built-in workflow nodes\n│   ├── spring-ai-alibaba-starter-config-nacos/  # Dynamic config with Nacos\n│   └── spring-ai-alibaba-starter-graph-observation/ # Observability\n├── examples/                          # Example applications\n│   ├── chatbot/                       # Chatbot example\n│   ├── deepresearch/                  # Deep research agent example\n│   └── documentation/                 # Documentation examples\n├── tools/                             # Build and linting tools\n└── docs/                              # Documentation\n```\n\n## Build System\n\n### Prerequisites\n\n- **JDK**: 17 (Required by `java.version` property)\n- **Maven**: 3.6+\n- **Git**\n\n### Common Build Commands\n\n```shell\n# Build the entire project (skip tests)\n./mvnw -B package -DskipTests=true\n\n# Build a specific module\n./mvnw -pl :spring-ai-alibaba-agent-framework -B package -DskipTests=true\n\n# Clean project\n./mvnw clean\n\n# Run tests\n./mvnw test\n\n# Run linting checks (using Makefile)\nmake lint\nmake licenses-check\n```\n\n## Architecture & Key Concepts\n\n### Core Components\n\n- **Agent Framework**: Built-in agents like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n- **Graph Core**: Underlying engine for stateful agents, supporting persistence (PostgreSQL, MySQL, Oracle, MongoDB, Redis, File).\n- **A2A (Agent-to-Agent)**: Enables agents to seek and communicate with each other using Nacos as a registry.\n- **Admin & Studio**: Provides visual tools for developing and debugging agent workflows.\n\n### Technology Stack\n\n- **Framework**: Spring Boot 3.5.x, Spring AI 1.1.x\n- **Cloud Integration**: Alibaba Cloud DashScope, Nacos (Service Discovery & Config)\n- **Observability**: Spring Cloud Observation (Micrometer/OpenTelemetry)\n\n## Code Style & Conventions\n\n### General Guidelines\n\n- Follow **Spring AI** standard code formatting.\n- Use **Apache 2.0** license headers for all Java files.\n- **Java 17** features are encouraged (records, switch expressions, text blocks).\n- Avoid `System.out.println` - use SLF4J logging.\n- Use `final` for local variables and parameters where appropriate.\n- Use Lombok annotations (`@Data`, `@Slf4j`, etc.) to reduce boilerplate.\n\n### Linting & Formatting\n\nThe project uses `make` for linting tasks:\n- `make codespell`: Checks for spelling errors.\n- `make yaml-lint`: Checks YAML file formatting.\n- `make licenses-check`: Verifies license headers.\n\n### License Header\n\n```java\n/*\n * Copyright 2025-2026 the original author or authors.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     https://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n```\n\n## Testing\n\n### Frameworks\n\n- **JUnit 5** (`org.junit.jupiter`)\n- **Mockito**\n\n### Running Tests\n\n```shell\n# Run all tests\n./mvnw test\n\n# Run a specific test class\n./mvnw -pl :<module-name> -Dtest=<TestClassName> test\n```\n\n## Tips for AI Assistants\n\n1.  **JDK Version**: Project targets JDK 17. Use appropriate language features.\n2.  **Spring Boot**: Uses Spring Boot 3.x. Be aware of `jakarta.*` namespace vs `javax.*`.\n3.  **Dependencies**: Check `spring-ai-alibaba-bom` or parent pom for version management.\n4.  **Makefile**: Use the Makefile in the root for project maintenance tasks (linting, license checks).\n5.  **Structure**: When adding new features, prefer creating or updating modules within `spring-ai-alibaba-agent-framework` or `spring-boot-starters` depending on the scope.\n\n## Important Links\n\n- **Issues**: [https://github.com/alibaba/spring-ai-alibaba/issues](https://github.com/alibaba/spring-ai-alibaba/issues)\n- **Source**: [https://github.com/alibaba/spring-ai-alibaba](https://github.com/alibaba/spring-ai-alibaba)\n- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)\n","category":"root","tokens":1448},{"name":"CLAUDE.md","path":"CLAUDE.md","title":"CLAUDE.md","content":"# CLAUDE.md - AI Assistant Guide for Spring AI Alibaba\n\nThis file provides guidance for AI assistants working with the Spring AI Alibaba codebase.\n\n## Project Overview\n\nSpring AI Alibaba is a production-ready framework for building Agentic, Workflow, and Multi-agent applications. It is an implementation of the Spring AI framework tailored for Alibaba Cloud services and components. It provides a comprehensive ecosystem for developing AI-powered applications with built-in context engineering and human-in-the-loop support.\n\n**Key Features:**\n\n- Multi-Agent Orchestration with built-in patterns\n- Context Engineering with human-in-the-loop, context compaction, editing, model call limits\n- Graph-based workflow with conditional routing, nested graphs, parallel execution\n- A2A (Agent-to-Agent) support with Nacos integration\n- Rich model support (DashScope, OpenAI, DeepSeek) and MCP (Model Context Protocol)\n- One-stop visual agent platform\n\n## Repository Structure\n\n```\nspring-ai-alibaba/\n├── spring-ai-alibaba-agent-framework/ # Multi-agent framework (Sequential, Parallel, Routing, etc.)\n├── spring-ai-alibaba-graph-core/      # Runtime providing persistence, workflow orchestration, state mgmt\n├── spring-ai-alibaba-studio/          # Embedded UI for debugging agents visually\n├── spring-ai-alibaba-admin/           # One-stop Agent platform (visual dev, observability, MCP mgmt)\n├── spring-ai-alibaba-bom/             # Bill of Materials for dependency management\n├── spring-boot-starters/              # Spring Boot Starters\n│   ├── spring-ai-alibaba-starter-a2a-nacos/     # Nacos A2A communication\n│   ├── spring-ai-alibaba-starter-builtin-nodes/ # Built-in workflow nodes\n│   ├── spring-ai-alibaba-starter-config-nacos/  # Dynamic config with Nacos\n│   └── spring-ai-alibaba-starter-graph-observation/ # Observability\n├── examples/                          # Example applications\n│   ├── chatbot/                       # Chatbot example\n│   ├── deepresearch/                  # Deep research agent example\n│   └── documentation/                 # Documentation examples\n├── tools/                             # Build and linting tools\n└── docs/                              # Documentation\n```\n\n## Build System\n\n### Prerequisites\n\n- **JDK**: 17 (Required by `java.version` property)\n- **Maven**: 3.6+\n- **Git**\n\n### Common Build Commands\n\n```shell\n# Build the entire project (skip tests)\n./mvnw -B package -DskipTests=true\n\n# Build a specific module\n./mvnw -pl :spring-ai-alibaba-agent-framework -B package -DskipTests=true\n\n# Clean project\n./mvnw clean\n\n# Run tests\n./mvnw test\n\n# Run linting checks (using Makefile)\nmake lint\nmake licenses-check\n```\n\n## Architecture & Key Concepts\n\n### Core Components\n\n- **Agent Framework**: Built-in agents like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n- **Graph Core**: Underlying engine for stateful agents, supporting persistence (PostgreSQL, MySQL, Oracle, MongoDB, Redis, File).\n- **A2A (Agent-to-Agent)**: Enables agents to seek and communicate with each other using Nacos as a registry.\n- **Admin & Studio**: Provides visual tools for developing and debugging agent workflows.\n\n### Technology Stack\n\n- **Framework**: Spring Boot 3.5.x, Spring AI 1.1.x\n- **Cloud Integration**: Alibaba Cloud DashScope, Nacos (Service Discovery & Config)\n- **Observability**: Spring Cloud Observation (Micrometer/OpenTelemetry)\n\n## Code Style & Conventions\n\n### General Guidelines\n\n- Follow **Spring AI** standard code formatting.\n- Use **Apache 2.0** license headers for all Java files.\n- **Java 17** features are encouraged (records, switch expressions, text blocks).\n- Avoid `System.out.println` - use SLF4J logging.\n- Use `final` for local variables and parameters where appropriate.\n- Use Lombok annotations (`@Data`, `@Slf4j`, etc.) to reduce boilerplate.\n\n### Linting & Formatting\n\nThe project uses `make` for linting tasks:\n- `make codespell`: Checks for spelling errors.\n- `make yaml-lint`: Checks YAML file formatting.\n- `make licenses-check`: Verifies license headers.\n\n### License Header\n\n```java\n/*\n * Copyright 2025-2026 the original author or authors.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     https://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n```\n\n## Testing\n\n### Frameworks\n\n- **JUnit 5** (`org.junit.jupiter`)\n- **Mockito**\n\n### Running Tests\n\n```shell\n# Run all tests\n./mvnw test\n\n# Run a specific test class\n./mvnw -pl :<module-name> -Dtest=<TestClassName> test\n```\n\n## Tips for AI Assistants\n\n1.  **JDK Version**: Project targets JDK 17. Use appropriate language features.\n2.  **Spring Boot**: Uses Spring Boot 3.x. Be aware of `jakarta.*` namespace vs `javax.*`.\n3.  **Dependencies**: Check `spring-ai-alibaba-bom` or parent pom for version management.\n4.  **Makefile**: Use the Makefile in the root for project maintenance tasks (linting, license checks).\n5.  **Structure**: When adding new features, prefer creating or updating modules within `spring-ai-alibaba-agent-framework` or `spring-boot-starters` depending on the scope.\n\n## Important Links\n\n- **Issues**: [https://github.com/alibaba/spring-ai-alibaba/issues](https://github.com/alibaba/spring-ai-alibaba/issues)\n- **Source**: [https://github.com/alibaba/spring-ai-alibaba](https://github.com/alibaba/spring-ai-alibaba)\n- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)\n","category":"root","tokens":1448}]}