Let the code review run on pushes by Claude

[ddaspit]

Quick summary

The code review now runs when Claude pushes to a PR. It used to fail before reviewing. Only claude-code-review.yml changes, and only Claude is allowed, not every bot.

Where to look

A push by the @claude workflow makes claude[bot] the actor. claude-code-action rejects a bot actor unless it is listed in allowed_bots. The review of #390 failed with Workflow initiated by non-human actor: claude (type: Bot).

The review only posts comments and never pushes, so it cannot retrigger itself. The existing check that the PR head is in this repo still applies.

Validation

• Parsed .github/workflows/claude-code-review.yml with PyYAML. allowed_bots reads claude.
• git diff --check -- clean.
• I did not run ./local_check.sh. This PR only changes a workflow file.
• The fix can only be verified by running the workflow. The next push by Claude to Convert USFM versification before updating from rows #390 after this is merged will confirm it.

🤖 Generated with Claude Code

---

This change is 

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 92.07%. Comparing base (785fbcb) to head (dbbbe1e).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #392   +/-   ##
=======================================
  Coverage   92.07%   92.07%           
=======================================
  Files         394      394           
  Lines       24896    24896           
=======================================
  Hits        22922    22922           
  Misses       1974     1974           

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.