The real bottleneck for agent-driven coding is review and intent, not object…

The real bottleneck for agent-driven coding is review and intent, not object storage. Anthropic’s Scion shows that when agents produce tens of thousands of changes a day, you need change units that record what an agent did and why, plus provenance that review tools can reason about. You can keep Git as your backend, but start recording agent intent, a durable execution transcript, and framed diffs so reviewers see reviewable units instead of raw hunks. The practical move: add metadata hooks now so your code-review surface doesn’t break before your repo does.