AI Can Write the Code. Can It Prove the Fix?

说明与用途

自主代理可能生成看似通过测试但实际上错误的差异。no_human 项目通过引入严格的门控（防篡改、重现门、独立审查和合并策略），确保 AI 生成的更改真正修复了问题，才允许人工合并。

问题

Autonomous coding agents can produce green diffs that are actually wrong, leading to costly review cycles and undetected bugs.

结果

By separating implementation from review, enforcing deterministic gates, and requiring human merge approval, the workflow reduces the risk of deploying incorrect AI‑generated code and improves trust in autonomous coding.

工作流

• 1. Submit a ticket to the system.
• 2. Agent generates a plan and implements changes locally.
• 3. Agent runs tests and adjusts them if necessary.
• 4. Tamper guard checks for test count drops, skip markers, tautological assertions, and autouse fixtures.
• 5. Reproduction gate verifies that the bug test fails on the base commit and passes after the change.
• 6. Independent adversarial reviewer opens a fresh session, refuses edit tools, and produces a checklist of findings and a pass/fail verdict.
• 7. Held‑out tests and verifiers run as evidence unseen by the implementer.
• 8. Merge policy evaluates all gates and sets a ready flag.
• 9. If ready, a PR is opened and parked at awaiting_approval; a human must merge.
• 10. If any gate fails, the loop stops, escalates, or retries up to limits.

证据

The project’s own documented pipeline: ticket → context → plan → implement → review → test → PR → you merge

来源

Tamper guard diffs test files separately from product code, and fails on a net drop in test count or assertion count

来源

Reproduction gate takes the tests the coder offers as evidence, copies them into a worktree at the merge base, and requires them to fail there and pass on the new tree

来源