Implement model wrapper for AI content generation

[httpdss]

Issue

Description

This PR introduces the new ModelWrapper feature, which encapsulates model logic using the pydantic-ai Agent. The ModelWrapper enables flexible integration with multiple LLM providers and centralizes AI-powered content generation. Key changes include:

• Addition of the ModelWrapper class in struct_module/model_wrapper.py
• Integration of ModelWrapper into FileItem and related modules
• Improved test and workflow configuration to support AI model usage
• Ensured environment variable handling for API keys in CI and local development

These changes improve modularity, testability, and future extensibility for AI-powered features.

Checklist

• I have read the contributing guidelines.
• My code follows the code style of this project.
• I have performed a self-review of my own code.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have updated the documentation accordingly.

Screenshots (if applicable)

Additional Comments

• The main feature is the ModelWrapper, which standardizes model usage across the codebase.
• The test workflow now sets a dummy OPENAI_API_KEY for CI compatibility.