feat: Semantic release notes and robust AI token counting

[thomas-vilte]

Description

This Pull Request introduces a major enhancement to the release notes generation process by implementing semantic sections. This moves away from a flat list of highlights to a more structured and categorized format, significantly improving readability and organization for end-users.

Additionally, this PR improves the robustness of AI token counting within the cost_wrapper by adding comprehensive error handling. If the AI provider's token counting API fails or does not support a specific model, the system will now gracefully fall back to a local estimation, preventing failures and ensuring continuous operation.

Fixes #

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?

The changes have been verified through:

• Unit tests: New unit tests were added for the release_generator to specifically validate the parsing and handling of the new semantic sections from the AI model's JSON output. Existing tests for cost_wrapper and commit_summarizer_service ensure no regressions.
• Integration tests
• Manual test:
  • Generated release notes using the updated AI prompts to confirm that the output correctly includes semantic sections (e.g., "🎨 UI Improvements", "🐛 Fixes") instead of the old flat highlights.
  • Simulated AI token counting failures (e.g., by using an unsupported model or network issues) to verify that the cost_wrapper correctly falls back to local estimation and logs appropriate warnings.

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