docs: update changelog for v0.1.8

[github-actions]

Release v0.1.8

Warning

All other pull requests are blocked until merged or closed

This pull request is for the v0.1.8 release.

Checklist (in order)

1. Mark the pull request "Ready for review" and label with "codebuild" to trigger required workflows
2. Inspect the CHANGELOG.md and "Approve" or "Reject" the pending CodeBuild GitHub Action
3. Evaluate the artifacts
4. Review the pull request (if approved set the "Merge when ready")

Post Merge

• Verify v0.1.8 tag
• Approve "Approve" or "Reject" the pending CodeBuild GitHub Action
• Review the drafted release artifacts for completion
• Publish the release

Caution

Simply closing this will block a subsequent v0.1.8 release, so delete the branch or reopen the pull request if necessary

When merged, the merge commit will be automatically tagged as v0.1.8, which triggers:

• release.yml — creates a draft GitHub Release with the rules zip
• codebuild.yml — runs CodeBuild and attaches build artifacts to the draft

After both workflows complete, review and publish the draft release.

[scottschreckengaust]

LGTM

[github-actions]

A. Executive Summary

Latest release: PR #196

High-level snapshot comparing the latest release against the golden baseline (the reference evaluation used as the quality target).

Metric	What it measures
Unit tests passed	Number of generated unit tests that pass. Higher means the rules produce broader, more complete test suites.
Contract tests	API compliance checks against the OpenAPI spec (passed/total). 88/88 = full compliance.
Lint findings	Static analysis warnings in generated code. Lower is better — 0 means clean code.
Qualitative score	AI-graded quality of generated documentation on a 0–1 scale (higher is better).
Execution time	Wall-clock time for the full evaluation run. Lower means faster generation.
Total tokens	Total LLM tokens consumed (input + output). Lower means more cost-efficient.

Metric	Golden	Latest (PR #196)	vs Golden	Trend
Unit tests passed	180	204	+24	█▄▄▁▂▃▃▁▅ ↓
Contract tests	88/88	87/88	-1	███▁████▅ ↘
Lint findings	0	0	—	▅▅▅▅▅▅▅▅▅ →
Qualitative score	0.854	0.802	-0.053	▅▇▇▆▇█▁▁▂ ↓
Execution time	23.8m	18.4m	-5.4m	▁▅▁▅▂▄█▆▅ ↑
Total tokens	18.39M	6.22M	-12.17M	▃▇▃▆▆█▃▁▁ ↓

---

Full trend report available in the workflow artifacts.