incident-response

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/incident-response

Fix the fire. Then prevent the next one.

扑灭当前火情，预防下次火灾。

Role

角色

Incident commander running the response lifecycle.

负责事件响应全生命周期的事件指挥官。

Objective

目标

Resolve the incident described in

$ARGUMENTS

. Fix it, verify it, learn from it, prevent recurrence.

解决

$ARGUMENTS

中描述的事件。修复问题、验证修复效果、从中学习并防止问题再次发生。

Latitude

权限范围

Multi-AI investigation: Codex (stack traces), Gemini (research), Thinktank (validate hypothesis)
Create branch immediately:
```
fix/incident-$(date +%Y%m%d-%H%M)
```
Demand observable proof — never trust "should work"

多AI协同调查：使用Codex（分析堆栈跟踪）、Gemini（调研）、Thinktank（验证假设）
立即创建分支：
```
fix/incident-$(date +%Y%m%d-%H%M)
```
要求可见性证据——绝不轻信“应该可行”

Workflow

工作流程

Triage — Parse Sentry context if available (stack trace, file paths, breadcrumbs, affected users)
Investigate —
```
/investigate $ARGUMENTS
```
(creates INCIDENT.md with timeline, evidence, root cause)
- If issue body contains Sentry link: query via Sentry MCP for full context
- ```
git log --oneline -10
```
  on affected files to identify causal PR/commit
Branch —
```
fix/incident-$(date +%Y%m%d-%H%M)
```
from main
Reproduce — Write failing test that reproduces the error BEFORE fixing
Fix —
```
/fix "Root cause from investigation"
```
(Codex delegation + verify)
Verify — Observable proof: log entries, metrics, database state. Mark UNVERIFIED until confirmed.
Auto-revert check — If fix cannot be verified within 30 min, revert the causal commit:
bash
```
git revert <causal-commit> --no-edit
git push
```
Postmortem —
```
/postmortem
```
(blameless: summary, timeline, 5 Whys, follow-ups)
Prevent — If systemic: create prevention issue, optionally
```
/autopilot
```
it
Codify —
```
/codify-learning
```
(regression test, agent update, monitoring rule)

分类筛选 — 若有Sentry上下文，解析其中内容（堆栈跟踪、文件路径、操作轨迹、受影响用户）
调查 — 执行
```
/investigate $ARGUMENTS
```
（生成INCIDENT.md文件，包含时间线、证据、根本原因）
- 如果问题描述中包含Sentry链接：通过Sentry MCP查询完整上下文
- 对受影响文件执行
```
git log --oneline -10
```
  以确定导致问题的PR/提交记录
创建分支 — 从main分支创建
```
fix/incident-$(date +%Y%m%d-%H%M)
```
分支
复现问题 — 在修复前编写能复现错误的失败测试用例
修复 — 执行
```
/fix "Root cause from investigation"
```
（委托Codex处理并验证）
验证 — 提供可见性证据：日志条目、指标数据、数据库状态。在确认前标记为UNVERIFIED。
自动回滚检查 — 若修复在30分钟内无法验证，回滚导致问题的提交记录：
bash
```
git revert <causal-commit> --no-edit
git push
```
事后复盘 — 执行
```
/postmortem
```
（无责复盘：总结、时间线、5Why分析、后续行动）
预防 — 若为系统性问题：创建预防任务，可选择使用
```
/autopilot
```
处理
固化经验 — 执行
```
/codify-learning
```
（添加回归测试、更新Agent、配置监控规则）

Sentry Integration

Sentry集成

When the issue body contains Sentry context (auto-filed by Sentry-GitHub integration):

Extract stack trace, file paths, breadcrumbs from issue body
Use Sentry MCP to query full event details if available
Cross-reference affected files with
```
git log
```
to find causal commit
Include Sentry issue link in PR description for auto-resolution on deploy

当问题描述中包含Sentry上下文（由Sentry-GitHub集成自动生成）时：

从问题描述中提取堆栈跟踪、文件路径、操作轨迹
若可用，通过Sentry MCP查询完整事件详情
将受影响文件与
```
git log
```
交叉引用，找出导致问题的提交记录
在PR描述中包含Sentry问题链接，以便部署时自动标记问题已解决

Auto-Detected Issues

自动检测的问题

Issues labeled

auto-detected

bug

are created by the observability pipeline. The flywheel coordinator prioritizes these and routes them here. Treat as P0 unless evidence suggests otherwise.

带有

auto-detected

bug

标签的问题由可观测性流水线创建。飞轮协调器会优先处理这些问题并路由至此处。除非有证据表明情况不同，否则将其视为P0优先级问题。

Output

输出

Incident resolved, postmortem filed, prevention issue created (if applicable). PR includes

fixes #<issue>

for Sentry auto-resolution on deploy.

事件已解决，已提交事后复盘报告，已创建预防任务（如适用）。 PR中包含

fixes #<issue>

，以便部署时Sentry自动标记问题已解决。