Integrate wuying-agentbay-sdk with crewAI

crews/agentbay_sdk/.gitignore

@@ -0,0 +1,26 @@
+.env
+.cursorrules
+agentbay-sdk-api.md
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+pipeline_outputs/

crews/agentbay_sdk/README.md

@@ -0,0 +1,81 @@
+# AI Crew for AgentBay SDK Integration
+
+## Introduction
+
+This project demonstrates the use of the CrewAI framework integrated with `wuying-agentbay-sdk` to automate cloud code execution and full development workflows. CrewAI orchestrates autonomous AI agents, enabling them to collaborate and execute complex tasks efficiently in secure cloud environments.
+
+- [CrewAI Framework](#crewai-framework)
+- [Running the Script](#running-the-script)
+- [Details & Explanation](#details--explanation)
+- [Configuration](#configuration)
+- [Contributing](#contributing)
+- [Support and Contact](#support-and-contact)
+- [License](#license)
+
+## CrewAI Framework
+
+CrewAI is designed to facilitate the collaboration of role-playing AI agents. In this example, these agents work together to:
+- Execute code in secure cloud environments
+- Design and implement complete projects
+- Deploy and run services in the cloud
+- Analyze execution results
+
+## Running the Script
+
+It uses GPT-4o by default so you should have access to that to run it.
+
+***Disclaimer:** This will use gpt-4o unless you change it to use a different model, and by doing so it may incur in different costs.*
+
+- **Configure Environment**: Copy `.env.example` to `.env` and set up the environment variables:
+  - `AGENTBAY_API_KEY`: Your AgentBay cloud execution API key
+  - `OPENAI_API_KEY`: Your LLM API key
+  - `OPENAI_API_BASE`: (Optional) LLM API endpoint for custom providers
+  - `OPENAI_MODEL_NAME`: (Optional) LLM model name, default is `gpt-4o-mini`
+- **Install Dependencies**: Run `poetry lock && poetry install` (or use `uv`/`pip`).
+- **Customize**: Modify `main.py` to add custom inputs for your agents and tasks.
+- **Customize Further**: Check `config/agents.yaml` to update your agents and `config/tasks.yaml` to update your tasks.
+- **Execute the Script**: Run `python main.py` and follow the prompts.
+
+## Details & Explanation
+
+- **Running the Script**: Execute `python main.py`. The script provides two modes:
+  1. Simple code execution task - Execute a single code snippet in the cloud
+  2. Full development pipeline - Complete workflow from design to deployment and analysis
+- **Key Components**:
+  - `crew.py`: Main crew file where agents and tasks come together, and the main logic is executed.
+  - `main.py`: Main script file with example usage.
+  - `pipeline.py`: Pipeline orchestation utilities.
+  - `config/agents.yaml`: Configuration file for defining agents.
+  - `config/tasks.yaml`: Configuration file for defining tasks.
+  - `tools/`: Contains tool classes used by the agents:
+    - `agentbay_tools.py`: AgentBay SDK integration tools
+    - `local_tools.py`: Local file system and HTTP verification tools
+  - `api/agentbay_temporary_session.py`: Temporary session operations (each call creates/deletes session automatically)
+  - `api/agentbay_persistent_session.py`: Persistent session operations (reusable sessions with manual lifecycle management)
+  - `tests/`: Test cases for the integration
+
+## Configuration
+
+### Required Environment Variables
+
+- `AGENTBAY_API_KEY`: Your AgentBay cloud execution API key
+- `OPENAI_API_KEY`: Your LLM API key
+
+### Optional Environment Variables
+
+- `OPENAI_API_BASE`: Custom LLM API endpoint (e.g., for Alibaba Cloud Bailian: `https://dashscope.aliyuncs.com/compatible-mode/v1`)
+- `OPENAI_MODEL_NAME`: LLM model name (default: `gpt-4o-mini`)
+  - For Bailian: Use `openai/qwen-plus` (with `openai/` prefix for LiteLLM compatibility)
+
+### Example Configuration
+
+See `.env.example` for detailed configuration examples for different LLM providers:
+- OpenAI (default)
+- Alibaba Cloud Bailian
+- Azure OpenAI
+- Custom endpoints
+
+## License
+
+This project is released under the MIT License.
+

crews/agentbay_sdk/env.example

@@ -0,0 +1,38 @@
+# AgentBay SDK Integration - Environment Variables Configuration
+# Copy this file to .env and fill in your actual API keys
+
+# =============================================================================
+# Required: AgentBay API Key
+# =============================================================================
+# Get your API key from: https://agentbay.ai (or your AgentBay provider)
+AGENTBAY_API_KEY=your_agentbay_api_key_here
+
+# =============================================================================
+# Required: LLM API Key
+# =============================================================================
+# Choose one of the following options based on your LLM provider
+
+# Option A: Using OpenAI (Default)
+OPENAI_API_KEY=your_openai_api_key_here
+# OPENAI_MODEL_NAME=gpt-4o-mini  # Optional, default is gpt-4o-mini
+
+# Option B: Using Alibaba Cloud Bailian
+# OPENAI_API_KEY=your_dashscope_api_key_here
+# OPENAI_API_BASE=https://dashscope.aliyuncs.com/compatible-mode/v1
+# OPENAI_MODEL_NAME=openai/qwen-plus  # Note: openai/ prefix is required for LiteLLM
+
+# Option C: Using Azure OpenAI
+# AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
+# AZURE_OPENAI_API_KEY=your_azure_key_here
+# AZURE_OPENAI_DEPLOYMENT=your_deployment_name
+
+# Option D: Using Custom Endpoint
+# OPENAI_API_KEY=your_api_key_here
+# OPENAI_API_BASE=https://your-custom-endpoint.com/v1
+# OPENAI_MODEL_NAME=your-model-name
+
+# =============================================================================
+# Optional: Advanced Configuration
+# =============================================================================
+# OPENAI_MODEL_NAME=gpt-4o-mini  # Override default model
+# OPENAI_API_BASE=  # Override default API base URL