main:重构指标系统并切换为 Redis 方案

变更内容：
- 重构指标系统实现，支持基于 Redis 的多实例指标管理。
- 替换原有的 Pushgateway 和 Redis Exporter 方案。
- 更新 Prometheus 配置，适配新的指标抓取方式。
- 添加 Redis 指标相关配置和告警规则文件。
- 更新 Dockerfile 和 docker-compose 文件，移除多余服务，精简配置。
- 编写 `metrics_unified.py` 模块及单元测试。
- 修复部分代码中的冗余和格式问题。

monitoring/alerts/rules.yaml

@@ -2,38 +2,52 @@ groups:
   - name: functional_scaffold_alerts
     interval: 30s
     rules:
+      # 高错误率告警
       - alert: HighErrorRate
         expr: rate(http_requests_total{status="error"}[5m]) > 0.05
         for: 5m
         labels:
           severity: warning
         annotations:
-          summary: "High error rate detected"
-          description: "Error rate is {{ $value }} requests/sec for {{ $labels.endpoint }}"
+          summary: "检测到高错误率"
+          description: "端点 {{ $labels.endpoint }} 的错误率为 {{ $value }} 请求/秒"
 
+      # 高延迟告警
       - alert: HighLatency
         expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1
         for: 5m
         labels:
           severity: warning
         annotations:
-          summary: "High latency detected"
-          description: "P95 latency is {{ $value }}s for {{ $labels.endpoint }}"
+          summary: "检测到高延迟"
+          description: "端点 {{ $labels.endpoint }} 的 P95 延迟为 {{ $value }}s"
 
+      # 服务不可用告警
       - alert: ServiceDown
         expr: up{job="functional-scaffold"} == 0
         for: 1m
         labels:
           severity: critical
         annotations:
-          summary: "Service is down"
-          description: "FunctionalScaffold service has been down for more than 1 minute"
+          summary: "服务不可用"
+          description: "FunctionalScaffold 服务已停止超过 1 分钟"
 
-      - alert: HighMemoryUsage
-        expr: container_memory_usage_bytes{container="functional-scaffold"} / container_spec_memory_limit_bytes{container="functional-scaffold"} > 0.9
+      # 算法执行失败率告警
+      - alert: HighAlgorithmFailureRate
+        expr: rate(algorithm_executions_total{status="error"}[5m]) / rate(algorithm_executions_total[5m]) > 0.1
         for: 5m
         labels:
           severity: warning
         annotations:
-          summary: "High memory usage"
-          description: "Memory usage is {{ $value | humanizePercentage }} of limit"
+          summary: "算法执行失败率过高"
+          description: "算法 {{ $labels.algorithm }} 的失败率超过 10%"
+
+      # 算法执行延迟告警
+      - alert: HighAlgorithmLatency
+        expr: histogram_quantile(0.95, rate(algorithm_execution_duration_seconds_bucket[5m])) > 5
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "算法执行延迟过高"
+          description: "算法 {{ $labels.algorithm }} 的 P95 延迟为 {{ $value }}s"

monitoring/prometheus.yml

@@ -8,27 +8,13 @@ global:
 
 # 抓取配置
 scrape_configs:
-  # 方案1：从 Pushgateway 抓取指标（推荐）
-  - job_name: 'pushgateway'
-    honor_labels: true
-    static_configs:
-      - targets: ['pushgateway:9091']
-    metric_relabel_configs:
-      # 保留 instance 标签
-      - source_labels: [instance]
-        target_label: instance
-        action: replace
-
-  # 方案2：从 Redis Exporter 抓取指标
-  - job_name: 'redis-exporter'
-    static_configs:
-      - targets: ['redis-exporter:8001']
-
-  # 直接从应用实例抓取（如果有多个实例，需要配置服务发现）
-  - job_name: 'app'
+  # 从应用实例抓取指标（Redis 统一指标方案）
+  # 应用通过 /metrics 端点从 Redis 读取并导出 Prometheus 格式指标
+  - job_name: 'functional-scaffold'
     static_configs:
       - targets: ['app:8000']
     metrics_path: '/metrics'
+    scrape_interval: 10s
 
   # Prometheus 自身监控
   - job_name: 'prometheus'
@@ -37,7 +23,7 @@ scrape_configs:
 
 # 告警规则文件
 rule_files:
-  - '/etc/prometheus/rules/*.yml'
+  - '/etc/prometheus/rules/*.yaml'
 
 # Alertmanager 配置（可选）
 # alerting: