Implement structured issue templates and dynamic prompt injection

[thomas-vilte]

Description

I implemented structured template handling and dynamic prompt injection to improve the accuracy of AI-generated issues and PRs. This change replaces generic interfaces with strictly typed models for GitHub Issue Forms (YAML), allowing the AI to better understand specific field requirements like labels, descriptions, and placeholders. I also decoupled the default issue structure from the base prompt to allow for cleaner template overrides and added automated initialization for the project's PR template.

Type of Change

• Bug fix (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

How Has This Been Tested?

I updated the test suite to cover the new structured models and verified that the prompt generation logic correctly handles both custom YAML templates and the default fallback structure.

• Unit tests
• Integration tests
• Manual test: Verified template initialization via the CLI.

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• 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

🧪 Test Plan & Evidence

Suggested Manual Verification

• API/Backend: Attach JSON response or logs as evidence of correct behavior
• Performance: Ensure no significant latency increase
• Unit Tests: Run go test ./... and ensure all tests pass
• No Regressions: Verify that related features still work as expected