fix(alerting): evaluate the replay-paused branch of DbReplicationLag, add ApiMemoryPressure; retarget grey-zone scenarios

DbReplicationLag の式は PromQL の or が左辺のサンプル（常に 0）を残すため
pg_is_wal_replay_paused の分岐が評価されず、第 1・2 回とも発火しなかった。2 つの
bool を加算して clamp する式に直す。api コンテナのメモリが limit の 80% を超えて
2 分続いたときの ApiMemoryPressure（第 2 層）を追加する。C-G2 の StressChaos は
size "80%"（ノード基準）で即 OOM になっていたため 200MB に、V-G1 の対象は
トラフィックを受けているインスタンス legacy:busy に変更する。slo.md に新ルールを追記。

vm/observability/grafana/provisioning/alerting/rules.yaml

@@ -57,8 +57,7 @@ groups:
       model:
         refId: A
         instant: true
-        expr: histogram_quantile(0.95, sum by (le) (rate(demo_http_request_duration_seconds_bucket{route=~"orders|price"}[5m])))
-          > bool 0.5
+        expr: histogram_quantile(0.95, sum by (le) (rate(demo_http_request_duration_seconds_bucket{route=~"orders|price"}[5m]))) > bool 0.5
     - refId: C
       datasourceUid: __expr__
       model:
@@ -89,8 +88,7 @@ groups:
       model:
         refId: A
         instant: true
-        expr: (sum(rate(demo_http_requests_total{status=~"5.."}[5m])) / sum(rate(demo_http_requests_total[5m])))
-          > bool 0.01
+        expr: (sum(rate(demo_http_requests_total{status=~"5.."}[5m])) / sum(rate(demo_http_requests_total[5m]))) > bool 0.01
     - refId: C
       datasourceUid: __expr__
       model:
@@ -112,8 +110,7 @@ groups:
       layer: '1'
       signature: pod_crashloop
     annotations:
-      summary: container restarted 3+ times in 5m (kubelet is handling; escalate after
-        5m)
+      summary: container restarted 3+ times in 5m (kubelet is handling; escalate after 5m)
     data:
     - refId: A
       relativeTimeRange:
@@ -123,8 +120,7 @@ groups:
       model:
         refId: A
         instant: true
-        expr: max by (pod) (increase(kube_pod_container_status_restarts_total{namespace="demo"}[5m]))
-          >= bool 3
+        expr: max by (pod) (increase(kube_pod_container_status_restarts_total{namespace="demo"}[5m])) >= bool 3
     - refId: C
       datasourceUid: __expr__
       model:
@@ -146,8 +142,7 @@ groups:
       layer: '1'
       signature: legacy_unhealthy
     annotations:
-      summary: fewer than 2 healthy legacy-api instances (MIG autohealing is handling;
-        escalate after 10m)
+      summary: fewer than 2 healthy legacy-api instances (MIG autohealing is handling; escalate after 10m)
     data:
     - refId: A
       relativeTimeRange:
@@ -158,7 +153,6 @@ groups:
         refId: A
         instant: true
         expr: count(up{job="legacy-api"} == 1) < bool 2
-        # no series until WP-15 ships Alloy on the legacy VMs: absent -> NoData -> OK (the `or vector(0)` form fired continuously)
     - refId: C
       datasourceUid: __expr__
       model:
@@ -189,8 +183,7 @@ groups:
       model:
         refId: A
         instant: true
-        expr: (max(pg_replication_lag_seconds) > bool 60) or (max(pg_is_wal_replay_paused)
-          == bool 1)
+        expr: clamp_max((max(pg_replication_lag_seconds) > bool 60) + (max(pg_is_wal_replay_paused) == bool 1), 1)
     - refId: C
       datasourceUid: __expr__
       model:
@@ -265,3 +258,35 @@ groups:
             type: gt
             params:
             - 0
+  - uid: api-memory-pressure
+    title: ApiMemoryPressure
+    condition: C
+    for: 2m
+    noDataState: OK
+    execErrState: Error
+    labels:
+      layer: '2'
+    annotations:
+      summary: an api container holds more than 80% of its memory limit for 2 minutes (grey zone; rollout restart after approval)
+    data:
+    - refId: A
+      relativeTimeRange:
+        from: 600
+        to: 0
+      datasourceUid: mimir
+      model:
+        refId: A
+        instant: true
+        expr: max by (pod) (container_memory_working_set_bytes{namespace="demo",container="api"}) / on (pod) max by (pod) (kube_pod_container_resource_limits{namespace="demo",container="api",resource="memory"})
+          > bool 0.8
+    - refId: C
+      datasourceUid: __expr__
+      model:
+        refId: C
+        type: threshold
+        expression: A
+        conditions:
+        - evaluator:
+            type: gt
+            params:
+            - 0