feat: add tracing enrichment and prometheus exporter

deploy/prometheus/alert.rules.yml

@@ -0,0 +1,34 @@
+groups:
+  - name: takeoutsaas-app
+    interval: 30s
+    rules:
+      - alert: HighErrorRate
+        expr: |
+          sum(rate(http_server_request_duration_seconds_count{http_response_status_code=~"5.."}[5m]))
+            / sum(rate(http_server_request_duration_seconds_count[5m])) > 0.05
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "API 5xx 错误率过高"
+          description: "过去 5 分钟 5xx 占比超过 5%，请检查依赖或发布"
+
+      - alert: HighP95Latency
+        expr: |
+          histogram_quantile(0.95, sum(rate(http_server_request_duration_seconds_bucket[5m])) by (le, service_name))
+            > 1
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "API P95 延迟过高"
+          description: "过去 5 分钟 P95 超过 1s，请排查热点接口或依赖"
+
+      - alert: InstanceDown
+        expr: up{job=~"admin-api|mini-api|user-api"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "实例不可达"
+          description: "Prometheus 抓取失败，实例处于 down 状态"

deploy/prometheus/prometheus.yml

@@ -0,0 +1,28 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 30s
+
+rule_files:
+  - alert.rules.yml
+
+scrape_configs:
+  - job_name: admin-api
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["admin-api:8080"]
+        labels:
+          service: admin-api
+
+  - job_name: mini-api
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["mini-api:8080"]
+        labels:
+          service: mini-api
+
+  - job_name: user-api
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["user-api:8080"]
+        labels:
+          service: user-api