We built an agent that fixes production bugs. The hardest part was stopping it.

说明与用途

一个自动化的 on‑call 代理自动重现错误、编写最小修复并打开 PR，但在任何写入之前都需要人工批准，以通过严格的工具门控和仓库隔离确保安全。

问题

On-call engineers spend time manually reproducing bugs, writing tests, patching code, and opening PRs. Manual judgment is required to decide when to write to the repository, leading to either unsafe autonomous bots or slow human review.

结果

The agent reduced on‑call engineer effort by automating mechanical steps while maintaining safety through a verified tool‑call firewall, reproduction requirement, and fail‑closed policy. A critical bug in the glob matcher was discovered and fixed by moving the repair service to a separate repository, strengthening the perimeter.

工作流

• 1. Sentry fires an alert
• 2. Agent reads the issue and culprit frame
• 3. Agent reproduces the failure in a sandbox with a failing test
• 4. Agent writes the smallest patch that makes the test green
• 5. Agent calls a GitHub tool to create a pull request
• 6. TrueForge pauses the turn and presents the exact arguments to the operator
• 7. Operator reviews the diff and approves or rejects the write
• 8. If approved, the pull request is created; if rejected, the agent stops

证据

By the time you see that summary, the agent has already decided everything, and you are reading a description of the work written by the same thing that did the work.

来源

If you cannot reproduce the failure, say so plainly, explain what you tried, and stop — do not proceed to a fix.

来源

The agent is required to work six stages in order, and stage three is: reproduce the failure in the sandbox with a test that fails.

来源