Add AI executor plugin for scheduled AI-powered tasks

[Copilot]

Proposed changes

New executor plugin enabling scheduled AI prompt execution against multiple model providers.

Supported providers:

• openai - GPT-4o, GPT-4o-mini, etc.
• anthropic - Claude 3 Opus, Sonnet, Haiku
• local - Any OpenAI-compatible API (Ollama, LM Studio, vLLM)

Configuration options:

• provider, apiKey, model, prompt (required based on provider)
• baseUrl, maxTokens, temperature, timeout, debug (optional)

Example usage:

{
  "executor": "ai",
  "executor_config": {
    "provider": "openai",
    "apiKey": "sk-...",
    "model": "gpt-4o-mini",
    "prompt": "Generate a daily status report",
    "maxTokens": "500"
  }
}

Security:

• API keys redacted from debug logs
• local provider requires explicit baseUrl to prevent accidental data leaks to external APIs
• Input validation for timeout, maxTokens, temperature ranges

Files added:

• builtin/bins/dkron-executor-ai/ - Executor implementation
• website/docs/usage/executors/ai.md - Documentation

21 unit tests covering validation, mock API responses, and error handling.

Types of changes

What types of changes does your code introduce?
Put an x in the boxes that apply

• Bugfix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation Update (if none of the other choices apply)

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.