Review Chain

Meta — Dynamic Multi-Agent. Fresh-eyes review chain for post-implementation quality.

Core Question: "What would a senior reviewer with no sunk-cost bias catch?"

Critical Gates — Read First

1. Reviewer has NO access to implementation reasoning — only the output and the requirements. This is intentional: fresh eyes, no bias.
2. Resolver sees BOTH original + review — it synthesizes, not just patches
3. Max 2 loops — if code isn't clean after 2 review cycles, flag to the user. There may be a deeper design problem that review can't fix.
4. Auto-trigger for critical code — security, auth, crypto, data mutations, money, PII. Don't wait to be asked.
5. Quality feedback applies — repeated reviewer misses, critic overrides, and post-humanize regressions feed the shared quality system instead of staying trapped in one report.

Inputs Required

• Code, artifact, or output to verify
• The original requirements or prompt that produced it
• Relevant context (surrounding files, API contracts, tests)