[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GPZM26P592GXSTQRWEFTJ":3,"skill-same:01M79GPZM26P592GXSTQRWEFTJ":91},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M79GPZM26P592GXSTQRWEFTJ","cloudbase-agent-python",null,"Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph\u002FCrewAI\u002FLlamaIndex, serve them via FastAPI with AG-UI protocol streaming + OpenAI-compatible endpoints, add tools (bash, filesystem, MCP, code execution), memory (in-memory, TDAI, MySQL, MongoDB), observability (OpenTelemetry\u002FLangfuse), and middleware (auth, logging). Use this skill when the user wants to create an AI agent server, build a chatbot backend, set up human-in-the-loop workflows, integrate MCP tools, add agent observability, or deploy an agent API — even if they don't explicitly mention 'CloudBase Agent.'","infometa\u002Fworkbuddyskills","infometa","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F109397516?v=4","01M79FS3XQK361MJFWQ2GFK95C","01M79FS3YPWKZYW9EPAAP2BFBJ",447,"MIT","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fskill.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cloudbase-agent-python\ndescription: \"Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph\u002FCrewAI\u002FLlamaIndex, serve them via FastAPI with AG-UI protocol streaming + OpenAI-compatible endpoints, add tools (bash, filesystem, MCP, code execution), memory (in-memory, TDAI, MySQL, MongoDB), observability (OpenTelemetry\u002FLangfuse), and middleware (auth, logging). Use this skill when the user wants to create an AI agent server, build a chatbot backend, set up human-in-the-loop workflows, integrate MCP tools, add agent observability, or deploy an agent API — even if they don't explicitly mention 'CloudBase Agent.'\"\nversion: 2.36.2\nlicense: MIT\nalwaysApply: true\n---\n\n# CloudBase Agent Python SDK\n\nBuild production-ready AI agent backends with multi-framework support, streaming\nprotocol, rich tools, persistent memory, and full observability.\n\n> **Note:** This skill is for **Python** projects only.\n\n## When to use this skill\n\nUse this skill for **AI agent development** when you need to:\n\n- Deploy AI agents as HTTP services with AG-UI protocol support\n- Build agent backends using LangGraph, CrewAI, or LlamaIndex frameworks\n- Create custom agent adapters implementing the AbstractAgent interface\n- Understand AG-UI protocol events and message streaming\n- Build production-ready agent servers with FastAPI\n\n**Do NOT use for:**\n- Simple AI model calling without agent capabilities (use `ai-model-*` skills)\n- CloudBase cloud functions (use `cloud-functions` skill)\n- CloudRun backend services without agent features (use `cloudrun-development` skill)\n- TypeScript\u002FJavaScript agent projects (use `cloudbase-agent` skill, refer to the `ts\u002F` sub-directory)\n\n## How to use this skill (for a coding agent)\n\n1. **Choose the right adapter**\n   - Use LangGraph adapter for stateful, graph-based workflows\n   - Use CrewAI adapter for multi-agent collaboration patterns\n   - Build custom adapter for specialized agent logic\n\n2. **Write agent code** — follow the adapter-specific doc from the Routing table\n\n3. **Deploy the agent server** — follow the **blocking deployment pipeline** in [agent-deployment](agent-deployment.md)\n\n## Routing (Execution Order)\n\n> ⚠️ **Deployment is a BLOCKING 4-step pipeline.** Steps marked ✅ BLOCKING\n> must be completed AND verified before proceeding to the next step.\n> Do NOT call `manageAgent` until all blocking steps pass.\n\n| Step | Task | Document | Blocking? |\n|------|------|----------|-----------|\n| 0 | **Choose adapter & write agent code** | See \"Adapter Selection\" below | — |\n| 1 | **Ensure Python 3.10** | [agent-deployment](agent-deployment.md) § Step 1 | ✅ BLOCKING |\n| 2 | **Build env\u002F (one-shot)** | [agent-deployment](agent-deployment.md) § Step 2 | ✅ BLOCKING |\n| 3 | **Verify env\u002F integrity** | [agent-deployment](agent-deployment.md) § Step 3 | ✅ BLOCKING |\n| 4 | **Deploy with manageAgent** | [agent-deployment](agent-deployment.md) § Step 4 | — |\n\n### Adapter Selection (Step 0)\n\n| Framework | Read | Install |\n|-----------|------|---------|\n| LangGraph (stateful graphs) | [adapter-langgraph](adapter-langgraph.md) | `cloudbase-agent-langgraph` |\n| CrewAI (multi-agent crews) | [adapter-development](adapter-development.md) | `cloudbase-agent-crewai` |\n| Coze platform | [adapter-coze](adapter-coze.md) | `cloudbase-agent-coze` |\n| Custom \u002F raw FastAPI | [server-quickstart](server-quickstart.md) + [adapter-development](adapter-development.md) | `cloudbase-agent-server` |\n\n### Additional References (read on demand, NOT required for deployment)\n\n| Task | Read |\n|------|------|\n| Server setup, middleware, multi-agent, CORS | [server-quickstart](server-quickstart.md) |\n| Authentication and user context | [authentication](authentication.md) |\n\n## Quick Start (Framework-Agnostic)\n\n**Prerequisites:** Python >= 3.10 is required.\n\n**1. Install dependencies (pick ONE adapter):**\n\n```bash\n# Option A: LangGraph-based agent\npip install cloudbase-agent-langgraph\n\n# Option B: CrewAI-based agent\npip install cloudbase-agent-crewai\n\n# Option C: Custom \u002F minimal\npip install cloudbase-agent-server\n```\n\n**2. Create server entry point:**\n\n```python\n# server.py — this pattern works with ANY adapter\nimport os\nfrom dotenv import load_dotenv\nload_dotenv()\n\nfrom cloudbase_agent.server import AgentServiceApp, AgentCreatorResult\n\n# Import your agent (framework-specific, see adapter docs)\n# from agents.chat.agent import create_my_agent\n\ndef create_agent() -> AgentCreatorResult:\n    agent = create_my_agent()  # Your agent factory\n    return {\"agent\": agent}\n\napp = AgentServiceApp()\napp.set_cors_config(allow_origins=[\"*\"])\n\nif __name__ == \"__main__\":\n    port = int(os.environ.get(\"SCF_RUNTIME_PORT\", \"9000\"))\n    app.run(create_agent, port=port, host=\"0.0.0.0\")\n```\n\n**3. Deploy to CloudBase:**\n\nFollow the **4-step deployment pipeline** in [agent-deployment](agent-deployment.md).\n\n---\n\n## Architecture\n\n```\nClient (React \u002F MiniProgram \u002F curl)\n   │  HTTP POST + SSE streaming\n   ▼\n┌─────────────────────────────────────────────┐\n│  AgentServiceApp (FastAPI)                   │\n│  ├─ \u002Fsend-message      ← AG-UI SSE         │\n│  ├─ \u002Fchat\u002Fcompletions  ← OpenAI-compat      │\n│  └─ Middleware chain (onion model)           │\n├─────────────────────────────────────────────┤\n│  Agent Layer                                 │\n│  ├─ LangGraphAgent  ├─ CrewAIAgent          │\n│  ├─ LlamaIndexAgent ├─ CozeAgent\u002FDifyAgent  │\n│  └─ BaseAgent (extend for custom)           │\n├──────────────────┬──────────────────────────┤\n│  Tools           │  Storage                  │\n│  Bash\u002FFS\u002FCode\u002FMCP│  Memory + LongTermMemory  │\n├─────────────────────────────────────────────┤\n│  Observability (OpenTelemetry + Langfuse)    │\n└─────────────────────────────────────────────┘\n```\n\n## Installation\n\nCloudBase Agent Python SDK is published to PyPI as separate packages. **Note: PyPI package names use hyphens (`cloudbase-agent-*`), and Python imports use the same namespace (`cloudbase_agent.*`)**.\n\n```bash\n# Core + Server + LangGraph (most common)\npip install cloudbase-agent-langgraph\n\n# Individual packages\npip install cloudbase-agent-core        # Core framework\npip install cloudbase-agent-server      # FastAPI server\npip install cloudbase-agent-langgraph   # LangGraph integration\npip install cloudbase-agent-tools       # Tool system\npip install cloudbase-agent-storage     # Memory\u002FStorage\npip install cloudbase-agent-observability  # OpenTelemetry\u002FLangfuse\npip install cloudbase-agent-coze        # Coze platform\npip install cloudbase-agent-crewai      # CrewAI integration\n```\n\n**Import Note**: All packages share the `cloudbase_agent` namespace:\n```python\n# After installing cloudbase-agent-langgraph, import from cloudbase_agent\nfrom cloudbase_agent.langgraph import LangGraphAgent\nfrom cloudbase_agent.server import AgentServiceApp\nfrom cloudbase_agent.tools import create_bash_tool\n```\n\n## Reference Documents\n\nBased on what the user needs, read the corresponding reference document.\n**Only read the relevant reference — don't load all of them.**\n\n| User Need | Reference | What It Covers |\n|-----------|-----------|---------------|\n| **Deploying agent to CloudBase** | Read [agent-deployment](agent-deployment.md) | **manageAgent MCP tool (MUST USE)**, 4-step blocking pipeline, Python 3.10, env\u002F build, verification |\n| Server setup, deployment, middleware, multi-agent, CORS | Read `references\u002Fserver.md` | AgentServiceApp 3 deployment methods, middleware (generator\u002Fyield\u002Fonion model), multi-agent server, Agent Creator pattern, health checks |\n| LangGraph agent, callbacks, tool proxy, HITL, checkpoints | Read [adapter-langgraph](adapter-langgraph.md) | LangGraphAgent constructor, AgentCallback protocol, ToolProxy, human-in-the-loop with interrupt(), TDAICheckpointSaver, client-defined tools |\n| Tools: bash, filesystem, code execution, MCP, custom tools | Read `references\u002Ftools.md` | create_bash_tool, 8 file tools, code executors, MCPToolkit\u002FCloudBaseMCPServer, @tool decorator, BaseTool, framework adapters |\n| Memory, persistence, short\u002Flong-term, MySQL, MongoDB | Read `references\u002Fstorage.md` | InMemoryMemory, TDAIMemory, MySQLMemory, MongoDBMemory, TDAILongTermMemory, Mem0LongTermMemory, LangGraph checkpoint |\n| Tracing, monitoring, Langfuse, OpenTelemetry | Read `references\u002Fobservability.md` | ConsoleTraceConfig, OTLPTraceConfig, setup_observability, env vars, manual observation spans |\n| Common patterns, JWT auth, MCP integration, production | Read `references\u002Frecipes.md` | JWT middleware, MCP + LangGraph, production deployment, adding tools to agents, client-defined tools |\n\n## Key Imports Quick Reference\n\n```python\n# Server\nfrom cloudbase_agent.server import AgentServiceApp, AgentCreatorResult\nfrom cloudbase_agent.server import create_send_message_adapter, create_openai_adapter\nfrom cloudbase_agent.server import RunAgentInput, OpenAIChatCompletionRequest\n\n# Agents\nfrom cloudbase_agent.langgraph import LangGraphAgent\nfrom cloudbase_agent.crewai import CrewAIAgent\n\n# Tools\nfrom cloudbase_agent.tools import create_bash_tool, create_read_tool, create_write_tool\nfrom cloudbase_agent.tools import MCPToolkit, CloudBaseMCPServer, CloudBaseTool\nfrom cloudbase_agent.tools import tool, BaseTool  # custom tools\n\n# Storage\nfrom cloudbase_agent.storage import InMemoryMemory, TDAIMemory\nfrom cloudbase_agent.storage import TDAILongTermMemory, Mem0LongTermMemory\nfrom cloudbase_agent.langgraph import TDAICheckpointSaver, TDAIStore\n\n# Observability\nfrom cloudbase_agent.observability import ConsoleTraceConfig, OTLPTraceConfig, setup_observability\n\n# Schemas\nfrom cloudbase_agent.schemas import Message, MessageRole, StreamEvent, EventType\n```\n\n## Project Structure Convention\n\n```\nmy-agent-project\u002F\n├── agents\u002F\n│   ├── agentic_chat\u002Fagent.py      # build_workflow() → agent instance\n│   ├── human_in_the_loop\u002Fagent.py\n│   └── __init__.py\n├── server.py                       # Main entry: AgentServiceApp().run(...)\n├── scf_bootstrap                   # CloudBase startup script (required for deployment)\n├── .env                            # OPENAI_API_KEY, etc.\n└── requirements.txt\n```\n\n## Environment Variables\n\n| Variable | Purpose |\n|----------|---------|\n| `OPENAI_API_KEY` | OpenAI API key |\n| `AUTO_TRACES_STDOUT` | Enable console tracing (`true`) |\n| `LANGFUSE_PUBLIC_KEY` \u002F `LANGFUSE_SECRET_KEY` | Langfuse keys |\n| `TDAI_ENDPOINT` \u002F `TDAI_API_KEY` | TDAI memory\u002Fcheckpoint endpoint |\n| `SCF_RUNTIME_PORT` | CloudBase runtime port (set automatically during deployment) |\n\n## Key Design Decisions\n\n1. **Agent Creator Pattern**: Every request creates a fresh agent via factory function. Supports cleanup callbacks for resource release.\n2. **Dual Protocol**: Every agent supports both AG-UI native (SSE + rich events) and OpenAI-compatible (`\u002Fchat\u002Fcompletions`).\n3. **Middleware = Generator**: Use `yield` — pre-yield = pre-processing, post-yield = post-processing (onion model).\n4. **Namespace Package**: `cloudbase_agent` spans multiple PyPI packages (cloudbase-agent-core, cloudbase-agent-server, cloudbase-agent-langgraph, etc.). PyPI names use hyphens, but all imports use `from cloudbase_agent.xxx import ...`.\n5. **Observability Auto-Integration**: Install `cloudbase-agent-observability` and tracing works automatically — zero config needed.\n6. **Deploy with manageAgent**: Always use the `manageAgent` MCP tool for CloudBase deployment. Follow the **4-step blocking pipeline** in [agent-deployment](agent-deployment.md).\n","# CloudBase Agent Python SDK\n\nBuild production-ready AI agent backends with multi-framework support, streaming\nprotocol, rich tools, persistent memory, and full observability.\n\n> **Note:** This skill is for **Python** projects only.\n\n## When to use this skill\n\nUse this skill for **AI agent development** when you need to:\n\n- Deploy AI agents as HTTP services with AG-UI protocol support\n- Build agent backends using LangGraph, CrewAI, or LlamaIndex frameworks\n- Create custom agent adapters implementing the AbstractAgent interface\n- Understand AG-UI protocol events and message streaming\n- Build production-ready agent servers with FastAPI\n\n**Do NOT use for:**\n- Simple AI model calling without agent capabilities (use `ai-model-*` skills)\n- CloudBase cloud functions (use `cloud-functions` skill)\n- CloudRun backend services without agent features (use `cloudrun-development` skill)\n- TypeScript\u002FJavaScript agent projects (use `cloudbase-agent` skill, refer to the `ts\u002F` sub-directory)\n\n## How to use this skill (for a coding agent)\n\n1. **Choose the right adapter**\n   - Use LangGraph adapter for stateful, graph-based workflows\n   - Use CrewAI adapter for multi-agent collaboration patterns\n   - Build custom adapter for specialized agent logic\n\n2. **Write agent code** — follow the adapter-specific doc from the Routing table\n\n3. **Deploy the agent server** — follow the **blocking deployment pipeline** in [agent-deployment](agent-deployment.md)\n\n## Routing (Execution Order)\n\n> ⚠️ **Deployment is a BLOCKING 4-step pipeline.** Steps marked ✅ BLOCKING\n> must be completed AND verified before proceeding to the next step.\n> Do NOT call `manageAgent` until all blocking steps pass.\n\n| Step | Task | Document | Blocking? |\n|------|------|----------|-----------|\n| 0 | **Choose adapter & write agent code** | See \"Adapter Selection\" below | — |\n| 1 | **Ensure Python 3.10** | [agent-deployment](agent-deployment.md) § Step 1 | ✅ BLOCKING |\n| 2 | **Build env\u002F (one-shot)** | [agent-deployment](agent-deployment.md) § Step 2 | ✅ BLOCKING |\n| 3 | **Verify env\u002F integrity** | [agent-deployment](agent-deployment.md) § Step 3 | ✅ BLOCKING |\n| 4 | **Deploy with manageAgent** | [agent-deployment](agent-deployment.md) § Step 4 | — |\n\n### Adapter Selection (Step 0)\n\n| Framework | Read | Install |\n|-----------|------|---------|\n| LangGraph (stateful graphs) | [adapter-langgraph](adapter-langgraph.md) | `cloudbase-agent-langgraph` |\n| CrewAI (multi-agent crews) | [adapter-development](adapter-development.md) | `cloudbase-agent-crewai` |\n| Coze platform | [adapter-coze](adapter-coze.md) | `cloudbase-agent-coze` |\n| Custom \u002F raw FastAPI | [server-quickstart](server-quickstart.md) + [adapter-development](adapter-development.md) | `cloudbase-agent-server` |\n\n### Additional References (read on demand, NOT required for deployment)\n\n| Task | Read |\n|------|------|\n| Server setup, middleware, multi-agent, CORS | [server-quickstart](server-quickstart.md) |\n| Authentication and user context | [authentication](authentication.md) |\n\n## Quick Start (Framework-Agnostic)\n\n**Prerequisites:** Python >= 3.10 is required.\n\n**1. Install dependencies (pick ONE adapter):**\n\n```bash\n# Option A: LangGraph-based agent\npip install cloudbase-agent-langgraph\n\n# Option B: CrewAI-based agent\npip install cloudbase-agent-crewai\n\n# Option C: Custom \u002F minimal\npip install cloudbase-agent-server\n```\n\n**2. Create server entry point:**\n\n```python\n# server.py — this pattern works with ANY adapter\nimport os\nfrom dotenv import load_dotenv\nload_dotenv()\n\nfrom cloudbase_agent.server import AgentServiceApp, AgentCreatorResult\n\n# Import your agent (framework-specific, see adapter docs)\n# from agents.chat.agent import create_my_agent\n\ndef create_agent() -> AgentCreatorResult:\n    agent = create_my_agent()  # Your agent factory\n    return {\"agent\": agent}\n\napp = AgentServiceApp()\napp.set_cors_config(allow_origins=[\"*\"])\n\nif __name__ == \"__main__\":\n    port = int(os.environ.get(\"SCF_RUNTIME_PORT\", \"9000\"))\n    app.run(create_agent, port=port, host=\"0.0.0.0\")\n```\n\n**3. Deploy to CloudBase:**\n\nFollow the **4-step deployment pipeline** in [agent-deployment](agent-deployment.md).\n\n---\n\n## Architecture\n\n```\nClient (React \u002F MiniProgram \u002F curl)\n   │  HTTP POST + SSE streaming\n   ▼\n┌─────────────────────────────────────────────┐\n│  AgentServiceApp (FastAPI)                   │\n│  ├─ \u002Fsend-message      ← AG-UI SSE         │\n│  ├─ \u002Fchat\u002Fcompletions  ← OpenAI-compat      │\n│  └─ Middleware chain (onion model)           │\n├─────────────────────────────────────────────┤\n│  Agent Layer                                 │\n│  ├─ LangGraphAgent  ├─ CrewAIAgent          │\n│  ├─ LlamaIndexAgent ├─ CozeAgent\u002FDifyAgent  │\n│  └─ BaseAgent (extend for custom)           │\n├──────────────────┬──────────────────────────┤\n│  Tools           │  Storage                  │\n│  Bash\u002FFS\u002FCode\u002FMCP│  Memory + LongTermMemory  │\n├─────────────────────────────────────────────┤\n│  Observability (OpenTelemetry + Langfuse)    │\n└─────────────────────────────────────────────┘\n```\n\n## Installation\n\nCloudBase Agent Python SDK is published to PyPI as separate packages. **Note: PyPI package names use hyphens (`cloudbase-agent-*`), and Python imports use the same namespace (`cloudbase_agent.*`)**.\n\n```bash\n# Core + Server + LangGraph (most common)\npip install cloudbase-agent-langgraph\n\n# Individual packages\npip install cloudbase-agent-core        # Core framework\npip install cloudbase-agent-server      # FastAPI server\npip install cloudbase-agent-langgraph   # LangGraph integration\npip install cloudbase-agent-tools       # Tool system\npip install cloudbase-agent-storage     # Memory\u002FStorage\npip install cloudbase-agent-observability  # OpenTelemetry\u002FLangfuse\npip install cloudbase-agent-coze        # Coze platform\npip install cloudbase-agent-crewai      # CrewAI integration\n```\n\n**Import Note**: All packages share the `cloudbase_agent` namespace:\n```python\n# After installing cloudbase-agent-langgraph, import from cloudbase_agent\nfrom cloudbase_agent.langgraph import LangGraphAgent\nfrom cloudbase_agent.server import AgentServiceApp\nfrom cloudbase_agent.tools import create_bash_tool\n```\n\n## Reference Documents\n\nBased on what the user needs, read the corresponding reference document.\n**Only read the relevant reference — don't load all of them.**\n\n| User Need | Reference | What It Covers |\n|-----------|-----------|---------------|\n| **Deploying agent to CloudBase** | Read [agent-deployment](agent-deployment.md) | **manageAgent MCP tool (MUST USE)**, 4-step blocking pipeline, Python 3.10, env\u002F build, verification |\n| Server setup, deployment, middleware, multi-agent, CORS | Read `references\u002Fserver.md` | AgentServiceApp 3 deployment methods, middleware (generator\u002Fyield\u002Fonion model), multi-agent server, Agent Creator pattern, health checks |\n| LangGraph agent, callbacks, tool proxy, HITL, checkpoints | Read [adapter-langgraph](adapter-langgraph.md) | LangGraphAgent constructor, AgentCallback protocol, ToolProxy, human-in-the-loop with interrupt(), TDAICheckpointSaver, client-defined tools |\n| Tools: bash, filesystem, code execution, MCP, custom tools | Read `references\u002Ftools.md` | create_bash_tool, 8 file tools, code executors, MCPToolkit\u002FCloudBaseMCPServer, @tool decorator, BaseTool, framework adapters |\n| Memory, persistence, short\u002Flong-term, MySQL, MongoDB | Read `references\u002Fstorage.md` | InMemoryMemory, TDAIMemory, MySQLMemory, MongoDBMemory, TDAILongTermMemory, Mem0LongTermMemory, LangGraph checkpoint |\n| Tracing, monitoring, Langfuse, OpenTelemetry | Read `references\u002Fobservability.md` | ConsoleTraceConfig, OTLPTraceConfig, setup_observability, env vars, manual observation spans |\n| Common patterns, JWT auth, MCP integration, production | Read `references\u002Frecipes.md` | JWT middleware, MCP + LangGraph, production deployment, adding tools to agents, client-defined tools |\n\n## Key Imports Quick Reference\n\n```python\n# Server\nfrom cloudbase_agent.server import AgentServiceApp, AgentCreatorResult\nfrom cloudbase_agent.server import create_send_message_adapter, create_openai_adapter\nfrom cloudbase_agent.server import RunAgentInput, OpenAIChatCompletionRequest\n\n# Agents\nfrom cloudbase_agent.langgraph import LangGraphAgent\nfrom cloudbase_agent.crewai import CrewAIAgent\n\n# Tools\nfrom cloudbase_agent.tools import create_bash_tool, create_read_tool, create_write_tool\nfrom cloudbase_agent.tools import MCPToolkit, CloudBaseMCPServer, CloudBaseTool\nfrom cloudbase_agent.tools import tool, BaseTool  # custom tools\n\n# Storage\nfrom cloudbase_agent.storage import InMemoryMemory, TDAIMemory\nfrom cloudbase_agent.storage import TDAILongTermMemory, Mem0LongTermMemory\nfrom cloudbase_agent.langgraph import TDAICheckpointSaver, TDAIStore\n\n# Observability\nfrom cloudbase_agent.observability import ConsoleTraceConfig, OTLPTraceConfig, setup_observability\n\n# Schemas\nfrom cloudbase_agent.schemas import Message, MessageRole, StreamEvent, EventType\n```\n\n## Project Structure Convention\n\n```\nmy-agent-project\u002F\n├── agents\u002F\n│   ├── agentic_chat\u002Fagent.py      # build_workflow() → agent instance\n│   ├── human_in_the_loop\u002Fagent.py\n│   └── __init__.py\n├── server.py                       # Main entry: AgentServiceApp().run(...)\n├── scf_bootstrap                   # CloudBase startup script (required for deployment)\n├── .env                            # OPENAI_API_KEY, etc.\n└── requirements.txt\n```\n\n## Environment Variables\n\n| Variable | Purpose |\n|----------|---------|\n| `OPENAI_API_KEY` | OpenAI API key |\n| `AUTO_TRACES_STDOUT` | Enable console tracing (`true`) |\n| `LANGFUSE_PUBLIC_KEY` \u002F `LANGFUSE_SECRET_KEY` | Langfuse keys |\n| `TDAI_ENDPOINT` \u002F `TDAI_API_KEY` | TDAI memory\u002Fcheckpoint endpoint |\n| `SCF_RUNTIME_PORT` | CloudBase runtime port (set automatically during deployment) |\n\n## Key Design Decisions\n\n1. **Agent Creator Pattern**: Every request creates a fresh agent via factory function. Supports cleanup callbacks for resource release.\n2. **Dual Protocol**: Every agent supports both AG-UI native (SSE + rich events) and OpenAI-compatible (`\u002Fchat\u002Fcompletions`).\n3. **Middleware = Generator**: Use `yield` — pre-yield = pre-processing, post-yield = post-processing (onion model).\n4. **Namespace Package**: `cloudbase_agent` spans multiple PyPI packages (cloudbase-agent-core, cloudbase-agent-server, cloudbase-agent-langgraph, etc.). PyPI names use hyphens, but all imports use `from cloudbase_agent.xxx import ...`.\n5. **Observability Auto-Integration**: Install `cloudbase-agent-observability` and tracing works automatically — zero config needed.\n6. **Deploy with manageAgent**: Always use the `manageAgent` MCP tool for CloudBase deployment. Follow the **4-step blocking pipeline** in [agent-deployment](agent-deployment.md).\n",{"name":5,"license":14,"version":23,"alwaysApply":24,"description":7},"2.36.2",true,"main","33b6151ccee9aa0816c6f32d021be77d82772755","connectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy",138,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills","https:\u002F\u002Fgithub.com\u002Finfometa","2026-11-11 03:15:35",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add infometa\u002Fworkbuddyskills --skill cloudbase-agent-python",{"tool":38,"command":39},"bunx","bunx skills add infometa\u002Fworkbuddyskills --skill cloudbase-agent-python",{"tool":41,"command":42},"pnpm","pnpm dlx skills add infometa\u002Fworkbuddyskills --skill cloudbase-agent-python","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fskill.md",[45,51,55,59,63,67,71,75,79,83,87],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"adapter-coze.md","REFERENCE","参考文档",9666,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fadapter-coze.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"adapter-development.md",17170,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fadapter-development.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"adapter-langgraph.md",14678,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fadapter-langgraph.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"agent-deployment.md",14285,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fagent-deployment.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"authentication.md",14607,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fauthentication.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fobservability.md",8796,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Freferences\u002Fobservability.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Frecipes.md",9126,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Freferences\u002Frecipes.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fserver.md",4858,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Freferences\u002Fserver.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fstorage.md",6843,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Freferences\u002Fstorage.md",{"path":84,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Ftools.md",4832,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Freferences\u002Ftools.md",{"path":88,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":89,"sourceHtmlUrl":90},"server-quickstart.md",11359,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fcloudbase\u002Fskills\u002Freferences\u002Fcloudbase-agent\u002Fpy\u002Fserver-quickstart.md",[92,99,106,113,120,129],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7A1EC013S1PBBTSH2PA2S7D","yingmi-skill","当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fyingmi-skill\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M7A194T67P6NRVYK8KCTH3CH","web-access","所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-access\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":18},"01M7A14FATMDD6FK8QAGXY5GVR","tencentmap-map-assistant","腾讯位置服务·地图助手 Skill，一句自然语言调用腾讯地图全套能力，无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索（含评分\u002F人均\u002F营业时间）、关键词提示、路线规划（驾车\u002F步行\u002F公交\u002F骑行）、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询，并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Ftencentmap-map-assistant\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":18},"01M7A0SX4XW5053MZ2S921EDH2","skill-scanner","Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-scanner\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":124,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":18},"01M7A0SQC2CZB3450G8471673M","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":18},"01M7A0RHV7BKS7DFQF9X9QCCNN","shader-dev","Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fshader-dev\u002FSKILL.md",[],[]]