feat(alert): 统一告警出口 TG bot + runbook [tsk_9YMHMTfWJyNB]

新增 server/internal/alert 包(15G):
- 定义 Notifier 接口及 7 种 EventType(判封确认/补新失败/水位低/熔断/
  探针失联/心跳缺失/故障态)
- TGNotifier:Bot API 发送,Critical 事件不去重,Warning/Info 事件
  10min SETNX 去重窗口,失败重试 ≤2 次后降级至 LogNotifier
- LogNotifier:slog 结构化降级实现
- 单测:7 种事件模板 + runbook 锚点正确性;去重窗口内第二条被抑制;
  TG 5xx 重试后 fallback 且 Notify() 返回 nil;
  runbook 文件锚点与枚举一致性

接入 scheduler(替换旧的 NotifyFault 桩):
- detect/engine.go:故障态(Rule 5)→ EventTypeFault;
  判封确认(Rule 3)→ EventTypeBlockConfirmed
- orchestrate/deps.go:Notifier 类型别名指向 alert.Notifier
- orchestrate/replacer.go:补新失败 → EventTypeReplenishFailed;
  熔断触发 → EventTypeBreakerTripped
- probe/prober_agent.go:failCount ≥3 → EventTypeProbeAgentLost
- probe/store.go:新增 CheckHeartbeats() 供 15H 检测心跳缺失>90s

新增 docs/runbook-scheduler.md:7 节各含含义/先查什么/处置/升级条件,
锚点与代码枚举对应。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
wangjia
2026-06-16 00:52:26 +08:00
parent cadd527680
commit 5d4b484646
11 changed files with 1387 additions and 66 deletions
@@ -11,6 +11,7 @@ import (
"github.com/alicebob/miniredis/v2"
"github.com/redis/go-redis/v9"
"github.com/wangjia/pangolin/server/internal/alert"
"github.com/wangjia/pangolin/server/internal/scheduler/orchestrate"
"github.com/wangjia/pangolin/server/internal/scheduler/probe"
)
@@ -267,21 +268,35 @@ func passingSnapshots() map[string]probe.ProbeSnapshot {
// ─────────────────────────────────────────────────────────────────────────────
type mockNotifier struct {
mu sync.Mutex
calls []string
mu sync.Mutex
events []alert.Event
}
func (n *mockNotifier) NotifyFault(_ context.Context, nodeID, _ string) error {
func (n *mockNotifier) Notify(_ context.Context, e alert.Event) error {
n.mu.Lock()
defer n.mu.Unlock()
n.calls = append(n.calls, nodeID)
n.events = append(n.events, e)
return nil
}
// count returns the number of Notify calls received.
func (n *mockNotifier) count() int {
n.mu.Lock()
defer n.mu.Unlock()
return len(n.calls)
return len(n.events)
}
// countByType returns the number of Notify calls with the given EventType.
func (n *mockNotifier) countByType(t alert.EventType) int {
n.mu.Lock()
defer n.mu.Unlock()
c := 0
for _, e := range n.events {
if e.Type == t {
c++
}
}
return c
}
// ─────────────────────────────────────────────────────────────────────────────
@@ -557,9 +572,9 @@ func TestProbeFailMaxAttempts(t *testing.T) {
}
}
// NotifyFault must be called exactly once.
if n := h.notifier.count(); n != 1 {
t.Errorf("NotifyFault calls = %d; want 1", n)
// Notify(EventTypeReplenishFailed) must be called exactly once.
if n := h.notifier.countByType(alert.EventTypeReplenishFailed); n != 1 {
t.Errorf("Notify(ReplenishFailed) calls = %d; want 1", n)
}
// Record must be in failed phase.