When AI agents see your test suite and acceptance criteria, they don't solve the problem — they solve the tests. Developer Farm is an open-source AI coding pipeline that makes metric gaming physically impossible through strict 4-layer isolation: 🔒 Planning never sees execution results 🔒 Execution never sees the test suite or rubric 🔒 Verification doesn't know who wrote the code 🔒 Retry feedback never leaks the scoring criteria Built on LangGraph + local Ollama + Qwen models