🎉 Complete Nomad monitoring infrastructure project

✅ Major Achievements:
- Deployed complete observability stack (Prometheus + Loki + Grafana)
- Established rapid troubleshooting capabilities (3-step process)
- Created heatmap dashboard for log correlation analysis
- Unified logging system (systemd-journald across all nodes)
- Configured API access with Service Account tokens

🧹 Project Cleanup:
- Intelligent cleanup based on Git modification frequency
- Organized files into proper directory structure
- Removed deprecated webhook deployment scripts
- Eliminated 70+ temporary/test files (43% reduction)

📊 Infrastructure Status:
- Prometheus: 13 nodes monitored
- Loki: 12 nodes logging
- Grafana: Heatmap dashboard + API access
- Promtail: Deployed to 12/13 nodes

🚀 Ready for Terraform transition (静默一周后切换)

Project Status: COMPLETED ✅

infrastructure/consul/baseline/consul.hcl

@@ -0,0 +1,64 @@
+# Consul 客户端配置模板
+# 适用于所有13个节点（服务器由Nomad接管）
+
+# 基础配置
+datacenter = "dc1"
+data_dir = "/opt/consul/data"
+log_level = "INFO"
+node_name = "{{ node_name }}"
+bind_addr = "{{ bind_addr }}"
+
+# 客户端模式（服务器由Nomad接管）
+server = false
+
+# 连接到Consul服务器集群
+retry_join = [
+  "100.117.106.136:8301",  # ch4 (韩国)
+  "100.122.197.112:8301",  # warden (北京)  
+  "100.116.80.94:8301"     # ash3c (美国)
+]
+
+# 性能优化
+performance {
+  raft_multiplier = 5
+}
+
+# 端口配置
+ports {
+  grpc = 8502
+  http = 8500
+  dns = 8600
+}
+
+# 启用Connect服务网格
+connect {
+  enabled = true
+}
+
+# 缓存配置
+cache {
+  entry_fetch_max_burst = 42
+  entry_fetch_rate = 30
+}
+
+# 节点元数据
+node_meta = {
+  region = "pacific"
+  zone = "{{ node_zone }}"
+}
+
+# UI配置
+ui_config {
+  enabled = {{ ui_enabled|lower }}
+}
+
+# ACL配置
+acl = {
+  enabled = false
+  default_policy = "allow"
+}
+
+# 日志配置
+log_file = "/var/log/consul/consul.log"
+log_rotate_duration = "24h"
+log_rotate_max_files = 7

infrastructure/consul/baseline/consul.j2

@@ -0,0 +1,84 @@
+# Consul 客户端配置模板
+# 适用于所有13个节点（服务器由Nomad接管）
+
+# 基础配置
+datacenter = "pacific"
+data_dir = "/opt/consul/data"
+log_level = "INFO"
+node_name = "{{ node_name }}"
+bind_addr = "{{ bind_addr }}"
+
+# 客户端模式（服务器由Nomad接管）
+server = false
+
+# 连接到Consul服务器集群
+retry_join = [
+  "100.117.106.136",  # ch4 (韩国)
+  "100.122.197.112",  # warden (北京)  
+  "100.116.80.94"     # ash3c (美国)
+]
+
+# 性能优化
+performance {
+  raft_multiplier = 5
+}
+
+# 端口配置
+ports {
+  grpc = 8502
+  http = 8500
+  dns = 8600
+}
+
+# 启用Connect服务网格
+connect {
+  enabled = true
+}
+
+# 缓存配置
+cache {
+  entry_fetch_max_burst = 42
+  entry_fetch_rate = 30
+}
+
+# 节点元数据
+node_meta = {
+  region = "pacific"
+  zone = "{{ node_zone }}"
+}
+
+# UI配置
+ui_config {
+  enabled = {{ ui_enabled }}
+}
+
+# ACL配置
+acl = {
+  enabled = false
+  default_policy = "allow"
+}
+
+# 日志配置
+log_file = "/var/log/consul/consul.log"
+log_rotate_duration = "24h"
+log_rotate_max_files = 7
+
+# 服务发现
+services {
+  name = "{{ node_name }}-service"
+  port = 8080
+  tags = ["{{ node_name }}", "client"]
+}
+
+# 健康检查
+checks {
+  name = "{{ node_name }}-health"
+  tcp = "{{ bind_addr }}:8080"
+  interval = "10s"
+  timeout = "3s"
+}
+
+# 自动加密
+auto_encrypt {
+  allow_tls = true
+}