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>

server/internal/scheduler/detect/engine.go

@@ -9,32 +9,14 @@ import (
 
 	"github.com/redis/go-redis/v9"
 
+	"github.com/wangjia/pangolin/server/internal/alert"
 	"github.com/wangjia/pangolin/server/internal/idgen"
 )
 
-// ─────────────────────────────────────────────────────────────────────────────
-// Notifier — 15G interface stub
-// ─────────────────────────────────────────────────────────────────────────────
-
-// Notifier is the 15G event sink for fault notifications.
-// The real implementation (15G) sends a Telegram/alerting message; the stub
-// below writes to the structured logger and is used until 15G is ready.
-type Notifier interface {
-	NotifyFault(ctx context.Context, nodeID, reason string) error
-}
-
-// LogNotifier is a Notifier stub that logs via slog.
-// It is used when no real Notifier is wired up.
-type LogNotifier struct{}
-
-// NotifyFault implements Notifier.
-func (LogNotifier) NotifyFault(_ context.Context, nodeID, reason string) error {
-	slog.Warn("node fault detected — manual review required",
-		"node_id", nodeID,
-		"reason", reason,
-	)
-	return nil
-}
+// Notifier is the 15G alert outlet used by the detection engine.
+// It is satisfied by alert.Notifier (the real TG implementation) and by
+// alert.LogNotifier (the fallback / development stub).
+type Notifier = alert.Notifier
 
 // ─────────────────────────────────────────────────────────────────────────────
 // Redis key constants
@@ -91,7 +73,7 @@ func NewEngine(
 		cfg = &d
 	}
 	if notifier == nil {
-		notifier = LogNotifier{}
+		notifier = alert.LogNotifier{}
 	}
 	return &Engine{
 		probeStore: probeStore,
@@ -150,8 +132,11 @@ func (e *Engine) processNode(ctx context.Context, node NodeInfo) error {
 	// Streaks are left unchanged so that when the node recovers the engine
 	// resumes from its current position rather than re-triggering immediately.
 	if isFault(sig) {
-		reason := fmt.Sprintf("domestic_fail_isps=%d overseas_ok=false", sig.DomesticFailISPs)
-		if notifyErr := e.notifier.NotifyFault(ctx, node.ID, reason); notifyErr != nil {
+		ev := alert.NewEvent(alert.EventTypeFault, node.ID, map[string]string{
+			"domestic_fail_isps": fmt.Sprintf("%d", sig.DomesticFailISPs),
+			"overseas_ok":        "false",
+		})
+		if notifyErr := e.notifier.Notify(ctx, ev); notifyErr != nil {
 			slog.Error("detect: notify fault", "node_id", node.ID, "error", notifyErr)
 		}
 		return nil // do not persist streak changes
@@ -254,6 +239,14 @@ func (e *Engine) processSuspect(ctx context.Context, node NodeInfo, sig NodeSign
 				return e.streaks.Save(ctx, node.ID, sk)
 			}
 
+			// Emit 判封确认 alert (15G exit channel).
+			confirmedEv := alert.NewEvent(alert.EventTypeBlockConfirmed, node.ID, map[string]string{
+				"suspect_streak": fmt.Sprintf("%d", sk.SuspectStreak),
+			})
+			if notifyErr := e.notifier.Notify(ctx, confirmedEv); notifyErr != nil {
+				slog.Error("detect: notify block confirmed", "node_id", node.ID, "error", notifyErr)
+			}
+
 			// Immediately mark down — skip draining per lifecycle policy.
 			downDetail := map[string]any{
 				"from": "blocked_confirmed",

server/internal/scheduler/detect/engine_test.go

@@ -9,6 +9,7 @@ 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/detect"
 	"github.com/wangjia/pangolin/server/internal/scheduler/probe"
 )
@@ -29,16 +30,26 @@ func (m *mockSnapshotter) SnapshotsByNode(_ context.Context, nodeID string) (map
 	return nil, nil
 }
 
-// recordingNotifier records NotifyFault calls for assertion.
+// recordingNotifier records Notify calls for assertion.
 type recordingNotifier struct {
-	calls []string // nodeID values
+	events []alert.Event
 }
 
-func (r *recordingNotifier) NotifyFault(_ context.Context, nodeID, _ string) error {
-	r.calls = append(r.calls, nodeID)
+func (r *recordingNotifier) Notify(_ context.Context, e alert.Event) error {
+	r.events = append(r.events, e)
 	return nil
 }
 
+// hasFaultEvent returns true if any recorded event has type EventTypeFault.
+func (r *recordingNotifier) hasFaultEvent() bool {
+	for _, e := range r.events {
+		if e.Type == alert.EventTypeFault {
+			return true
+		}
+	}
+	return false
+}
+
 // newTestRedis creates an in-process Redis (miniredis) and returns a connected
 // client plus a cleanup function.  Tests must call cleanup() at the end.
 func newTestRedis(t *testing.T) (*redis.Client, *miniredis.Miniredis) {
@@ -345,11 +356,11 @@ func TestRules(t *testing.T) {
 			}
 
 			// Verify fault notification.
-			if tc.wantFaultNotified && len(notifier.calls) == 0 {
-				t.Error("expected NotifyFault to be called, but it was not")
+			if tc.wantFaultNotified && !notifier.hasFaultEvent() {
+				t.Error("expected fault Notify event to be recorded, but it was not")
 			}
-			if !tc.wantFaultNotified && len(notifier.calls) > 0 {
-				t.Errorf("unexpected NotifyFault calls: %v", notifier.calls)
+			if !tc.wantFaultNotified && notifier.hasFaultEvent() {
+				t.Errorf("unexpected fault Notify events: %v", notifier.events)
 			}
 		})
 	}
@@ -594,8 +605,8 @@ func TestFaultNoTransitionNoStreak(t *testing.T) {
 	if events := lc.Events(); len(events) != 0 {
 		t.Errorf("unexpected events: %v", events)
 	}
-	if len(notifier.calls) == 0 {
-		t.Error("expected NotifyFault to be called at least once")
+	if !notifier.hasFaultEvent() {
+		t.Error("expected fault Notify event to be recorded at least once")
 	}
 }