drive: cloud run fb9fce40

[kjgbot]

Automated drive work from cloud run fb9fce40-204e-4f36-9a73-70c753463cea.

The sandbox cannot open PRs (no remote, no GitHub token), so this was delivered
from a host that can. Verification and adversarial review ran in-run — see
ops/reviews/ in the diff. A human merges.

[coderabbitai]

Warning

Review limit reached

Next included review available in 28 minutes.

Check out review usage here.

View limit details

Limit details: You’ve used the included review currently available.

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

Learn how review limits work.

Review configuration:

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Free

Run ID: 289bafdd-6899-4de5-9527-a845bfd5e0df

📥 Commits

Reviewing files that changed from the base of the PR and between 066ef24 and 736747b.

📒 Files selected for processing (8)

• .github/workflows/review-swarm.yml
• .github/workflows/scripts/swarm-post.sh
• .github/workflows/scripts/swarm-prepare.sh
• .github/workflows/scripts/swarm-verdict.sh
• .gitignore
• README.md
• ops/NEXT.md
• workflows/review-swarm.yaml

---

Note

🎁 Summarized by CodeRabbit Free

Your organization is on the Free plan. CodeRabbit will generate a high-level summary and a walkthrough for each pull request. For a comprehensive line-by-line review, please upgrade your subscription to CodeRabbit Essentials by visiting https://app.coderabbit.ai/settings/billing.

_{Comment @coderabbitai help to get the list of available commands.}

[kjgbot]

Merging as the consolidated version of the review-swarm work; #161 and #162 closed as superseded (this is a superset — it also adds workflows/review-swarm.yaml).

Merging with a known red check, deliberately. The review check fails because RELAY_WORKSPACE_KEY does not exist — the repo has no Actions secrets at all — so this workflow fails on its own PR and will show red on every PR until that secret is added.

Flagging that cost explicitly since it is the exact shape of the hole #153 dug (a gate turned on before it could pass, which took #154/#158/#159 to climb out of). The difference is that this one fails fast and closed with a clear message rather than hanging, and it is one gh secret set from working.

The design itself I have no findings against: pull_request rather than pull_request_target (no fork-secret exposure), and the gate is checked out from main separately from the PR head, so a PR cannot edit the gate that judges it.

One caveat worth knowing before relying on it: the swarm runs on the cloud launch queue, which was wedged for ~12 hours today with six runs created and never placed. When the queue is in that state this workflow launches, polls for 65 minutes, and reports timed_out.

Revertable in one command if the red is worse than the wait.