fix: run CodeBoarding reviews without a synced baseline

[ivanmilevtues]

Configure CodeBoarding in review mode only, using the current v1 explicit OpenRouter inputs. Remove the sync workflow and generated committed baseline so a subsequent application PR can exercise review without a prepared base. Existing historical artifacts are left untouched. Validation: parsed the workflow YAML and checked the diff.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-08T17:20:45.880463Z	e27a7ab	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[github-actions]

CodeBoarding review - not configured

llm: openrouter needs openrouter_api_key, and none is set.

1. Add a repository secret named OPENROUTER_API_KEY, with your OpenRouter API key as the value.

2. In .github/workflows/codeboarding.yml, the CodeBoarding step's with: block needs to read:

        with:
          llm: openrouter
          openrouter_api_key: ${{ secrets.OPENROUTER_API_KEY }}

No analysis ran, and no CodeBoarding hosted usage was consumed.

_{run 34256096110 - attempt 1}