You reset the coder's context each chunk but leave the reviewer long-running — over a 549-commit migration doesn't the reviewer accumulate enough drift that its adversarial value degrades on the later chunks?
The migration was not a single, long run of neal (because I was developing/tweaking neal along the way). However I have used it for large-ish implementations and haven't noticed any issues with the reviewer drifting. It is re-prompted each review turn with its adversarial review instructions plus a summary of the run state (completed scopes, open findings, etc). Also, the final review is executed with a fresh context.