feat: add agent options to model config

[mudler]

Description

This pull request introduces a new agent configuration section for the Model Context Protocol (MCP) feature, allowing fine-grained control over agent behavior and tool execution. It adds support for advanced reasoning, re-evaluation, and customizable limits on execution attempts and iterations. The changes span configuration structures, endpoint logic, and documentation.

The most important changes are:

Agent configuration support:

• Added an AgentConfig struct to ModelConfig, with fields for max_attempts, max_iterations, enable_reasoning, and enable_re_evaluation to control agent behavior and reasoning capabilities.
• Updated the MCP completion endpoint to use the new agent config values for tool execution, reasoning, and re-evaluation, falling back to sensible defaults if not set.

Documentation updates:

• Updated the MCP feature documentation to highlight advanced reasoning, re-evaluation, and flexible agent control as new features.
• Added detailed documentation and YAML examples for the new agent configuration section, including descriptions of each field and recommended settings for different use cases. [1] [2] [3]

Notes for Reviewers

Signed commits

• Yes, I signed my commits.

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	e6f55e3
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/68e2c1b08dcb2e0008776a4e
😎 Deploy Preview	https://deploy-preview-6383--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.