The Agent Patch Test Budget: Spend CI Minutes Where They Catch Faults

说明与用途

AI 生成的补丁生产成本低，但验证成本高。通过按风险分类并限制每个风险级别的 CI 测试时间，流水线可以处理更多补丁，同时仍能捕获错误。

问题

Agent-generated patches are cheap to produce but expensive to validate; running the same full test gauntlet on every patch throttles CI throughput.

结果

By allocating CI minutes based on patch risk, the pipeline processes more patches per hour, reducing bottlenecks while still catching faults where they matter.

工作流

• 1. Agent generates patch and pushes to CI
• 2. CI runs gate_budget.sh to classify patch risk and output gate plan
• 3. CI executes only the gates specified in the plan within the allocated budget
• 4. Flaky freeze runs outside the budget to quarantine unstable tests
• 5. If a gate times out, the patch fails and the agent is prompted to split the diff

证据

Classify each patch by risk, then assign a time budget and a gate set.

来源

A gate that times out fails the patch.

来源