Pydantic AI Expert Skill

This skill provides patterns for defining agents, dependencies, and tools using Pydantic AI.

🤖 Agent Definition

• State Management: Use StateDeps[T] to pass dependencies (DB clients, settings) to agents.
• System Prompts: Define complex prompts in src/prompts.py. Use @agent.instructions for dynamic context.
• Model Choice: Use OpenAIModel as a base for OpenAI-compatible providers (OpenRouter, Ollama) via OpenAIProvider.

🛠️ Tool Patterns

• Return Strings: Agents work best with text. Tools should return formatted strings, not Pydantic objects.
• Resource Management: Initialize and cleanup DB connections properly within the tool or via injected deps.
• Error Handling: Tools should catch exceptions and return helpful error messages to the agent rather than crashing.

📺 CLI & Streaming

• Rich Integration: Use Rich to display real-time streaming of agent output and tool call details.
• Node Handling: Implement logic for userprompt, modelrequest, call_tools, and end nodes in the CLI.
• Transparency: Always show the user which tool is being called and with what parameters.