Release Gates for Agent-Generated Code

PROJECT CONTEXT:
Agent-generated code flows toward production with less scrutiny than human code, despite being higher variance. PR-review agents and guardrail practice show the fix: a defined merge gate combining automated checks with risk-proportional human review.

GOAL:
Define and enforce a release gate for agent-generated changes: automated review + tests + security scans, plus human sign-off scaled to change risk.

REQUIREMENTS:
- A merge gate that agent-generated changes must pass before landing
- Automated layers: rule-file review, full tests, security/dependency scans, secret scan
- Risk classification of changes to set the required human-review depth
- Provenance labeling: agent-generated changes are marked as such
- A clear record of what passed and who approved, per change

CONSTRAINTS:
- Agent changes get at least the scrutiny human changes get - never less
- High-risk changes cannot merge on automated checks alone

DEFINITION OF DONE:
- An agent change failing tests, rules, or scans cannot merge
- A high-risk change (auth, payments, migrations) requires human sign-off
- Every change is labeled with its agent provenance
- The gate record shows checks passed and approver for each merge

COMMON FAILURES TO AVOID:
- Auto-merging agent PRs on green CI with no human ever looking at risky ones
- Applying weaker checks to agent code than to human code
- No risk tiering, so a typo fix and a payment change get identical review
- Unlabeled agent changes, so reviewers do not know to look harder