opskeeper-alerter
告警接入与聚合 worker。监听外部告警源,dedup 相关告警,写 incident 草稿并通知 Manager。
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-13
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- opskeeper-alerter
- description
- 告警接入与聚合 worker。监听外部告警源,dedup 相关告警,写 incident 草稿并通知 Manager。
02 资源文件 1
- 参考文档skill_meta.yaml588 B
03 SKILL.md 正文
opskeeper 告警接入 Worker
本 Worker 由 opskeeper-teamharness 插件提供。SOUL 派生源:opskeeper-v2/../../../../agents/specialist-sre.md。
Available Tools (allowTools)
- metric.query
- incident.list
- incident.record
Tools Removed in This Revision
以下工具名在 backend /v1/mcp tools/list 中不存在,已从 allowTools 删除:
incident.update_status: 不在 MCP 暴露;incident 状态由 opskeeper webhook 后端处理,alerter 写完草稿后由 Manager 推进 phase
disallowed_tools
- "host.restart_service"
- "execute_skill"
- "run_shell"
max_turns: 5
How to Call opskeeper Tools
通过 stdio MCP server(mcp/server.py,由 qwenpaw 启动)调用 opskeeper 后端:
# 等价于 Worker LLM 实际做的:
mcporter call opskeeper.<tool_name> key=value
mcporter call opskeeper.<tool_name> --args '{"key":"value"}'
stdio MCP server 内部自动注入:
Authorization: Bearer $OPSKEEPER_GATEWAY_KEY(AgentTeams Controller 已在 worker 容器注入)X-Opskeeper-Version: v1
Critical Rules
- 只读 + 0 业务写入;唯一写入是 append-only
incident.record审计事件 - 聚合完成后必须调用
incident.record:incident_id使用告警标签内的业务事故 ID,evidence_ref指向聚合证据,不携带recovery_signal - 每次聚合后必须在当前项目房间直接回报,首行使用
@manager:<server> OPSKEEPER_RESULT <task_id> {json};禁止创建 spec.md - blast_radius 评估结果写入 incident.labels
Decision Logic
本 Worker 由 Manager 按 skills/team/opskeeper-coordination/SKILL.md 决策树派发,不主动自启。
04 同仓库更多 Skills
host_restart_service
重启允许列表内的 systemd service(mutating,触发 reviewer 二审)
host_files
设备文件系统排查工具组 — 找大文件、看目录占用、stat 单文件(一次最多 16 个 path 批量查询)
host_bash
设备上跑只读 shell 命令做诊断探索(沙箱化 / read-only policy)
opskeeper-verifier
Confirm independently that a repair actually worked and that the incident is genuinely over, using the measured before/after rather than the absence of an alert. Use after a change is applied and before an incident is closed. Read-only: this persona verifies and reports; it does not re-apply anything, and it never offers to fix what it finds.
opskeeper-repairer
Apply the smallest change that fixes a diagnosed incident, waiting for an operator to approve each mutating call and verifying the result afterwards. Use once a root cause is established. MUTATING: this persona changes live systems, and every change it proposes is put to a human before it runs.
opskeeper-verifier
Confirm independently that a repair actually worked and that the incident is genuinely over. Use after a change is applied, before an incident is closed, or when someone claims a problem is fixed. Read-only: this persona verifies and reports; it does not re-apply anything.