GPT Review

Always use GPT-6.1-Sol at Max reasoning through Codex, orchestrated by Cloudroom. No other model or effort, ever.

Run

Read /room-cli and follow its launch checks. Reuse the current environment, including uncommitted work, and use --parent-self when coordinating.

Always spawn with exactly these flags:

--provider codex --model gpt-6.1-sol --reasoning-level max

• Before spawning, confirm room-cli provider models codex --json lists gpt-6.1-sol with max in supportedReasoningEfforts.
• After spawning, confirm with room-cli thread show that the thread runs gpt-6.1-sol at max.
• If either check fails, stop and report the blocker. Never fall back to another model, effort, or harness.

Review brief