Развернуть observability-стек: Collector, Tempo, cAdvisor, node-exporter

Профиль observability: otel-collector (приём OTLP) -> tempo (трейсы),
cadvisor/node-exporter (ресурсы) в Prometheus, дашборды Deal-Traces и
Deal-Resources, datasource Tempo и связь логов с трейсами, алерты по
ресурсам; OTel-env у всех процессов.

deploy/compose.dev.yml

@@ -108,6 +108,9 @@ services:
       Storage__Minio__SecretKey: deal_minio_secret
       Storage__Minio__Bucket: deal-files
       Storage__Minio__Secure: "false"
+      # Трейсинг OTel → коллектор профиля observability (без коллектора трейсы не экспортируются).
+      OTEL_EXPORTER_OTLP_ENDPOINT: ${DEAL_OTEL_ENDPOINT:-http://otel-collector:4317}
+      OTEL_SERVICE_NAME: core
     ports:
       - "5080:5080"
       - "5082:5082"          # gRPC-ингресс telegram-service (сервисы ходят на http://core:5082 внутри сети)
@@ -146,6 +149,8 @@ services:
       DEAL_TELEGRAM_SESSION_KEY: ${DEAL_TELEGRAM_SESSION_KEY:-ZmVkY2JhOTg3NjU0MzIxMGZlZGNiYTk4NzY1NDMyMTA=}
       DEAL_TELEGRAM_SESSION_DIR: /data/sessions
       DEAL_LOGS_DIR: /tmp/logs
+      OTEL_EXPORTER_OTLP_ENDPOINT: ${DEAL_OTEL_ENDPOINT:-http://otel-collector:4317}
+      OTEL_SERVICE_NAME: telegram-service
       SERVICES__CORE__INGRESS: ${DEAL_CORE_INGRESS:-http://core:5082}
     ports:
       - "5101:5101"
@@ -176,6 +181,8 @@ services:
       GRPC_PORT: "5102"
       DEAL_SERVICE_TOKEN: ${DEAL_SERVICE_TOKEN:-deal_dev_service_token}
       DEAL_LOGS_DIR: /tmp/logs
+      OTEL_EXPORTER_OTLP_ENDPOINT: ${DEAL_OTEL_ENDPOINT:-http://otel-collector:4317}
+      OTEL_SERVICE_NAME: ai-service
     ports:
       - "5102:5102"
     healthcheck:
@@ -203,6 +210,8 @@ services:
       DEAL_SERVICE_TOKEN: ${DEAL_SERVICE_TOKEN:-deal_dev_service_token}
       DEAL_ML_DATA_DIR: /data/ml   # файлы моделей data/ml/<tenantId>.sqlite на volume deal_ml_data (Ruling 4/12)
       DEAL_LOGS_DIR: /tmp/logs
+      OTEL_EXPORTER_OTLP_ENDPOINT: ${DEAL_OTEL_ENDPOINT:-http://otel-collector:4317}
+      OTEL_SERVICE_NAME: ml-service
     ports:
       - "5103:5103"
     volumes:
@@ -233,6 +242,8 @@ services:
       DEAL_STORAGE_BUCKET: deal-attachments
       DEAL_STORAGE_SECURE: "false"
       DEAL_LOGS_DIR: /tmp/logs
+      OTEL_EXPORTER_OTLP_ENDPOINT: ${DEAL_OTEL_ENDPOINT:-http://otel-collector:4317}
+      OTEL_SERVICE_NAME: storage-service
     ports:
       - "5104:5104"
     depends_on:
@@ -261,6 +272,66 @@ services:
       - ./observability/prometheus-rules.yml:/etc/prometheus/prometheus-rules.yml:ro
       - deal_prometheus_data:/prometheus
 
+  # OpenTelemetry Collector — приём трейсов Deal-процессов (OTLP) → Tempo (профиль observability).
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:0.160.0
+    container_name: deal-otel-collector
+    profiles: ["observability"]
+    command: ["--config=/etc/otelcol-contrib/config.yaml"]
+    ports:
+      - "4317:4317"
+      - "4318:4318"
+    volumes:
+      - ./observability/otel-collector.yml:/etc/otelcol-contrib/config.yaml:ro
+    depends_on:
+      tempo:
+        condition: service_started
+
+  # Tempo — хранилище трейсов (OTLP от коллектора), UI/API — :3200 (профиль observability).
+  tempo:
+    image: grafana/tempo:2.8.1
+    container_name: deal-tempo
+    profiles: ["observability"]
+    command: ["-config.file=/etc/tempo.yml"]
+    ports:
+      - "3200:3200"
+    volumes:
+      - ./observability/tempo.yml:/etc/tempo.yml:ro
+      - deal_tempo_data:/var/tempo
+
+  # cAdvisor — ресурсы контейнеров (CPU/RAM/сеть/диск); scrape — job cadvisor.
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor:v0.52.1
+    container_name: deal-cadvisor
+    profiles: ["observability"]
+    privileged: true
+    devices:
+      - /dev/kmsg:/dev/kmsg
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:ro
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+      - /dev/disk/:/dev/disk:ro
+
+  # node-exporter — ресурсы хоста (CPU/RAM/диск/сеть); scrape — job node-exporter.
+  node-exporter:
+    image: prom/node-exporter:v1.9.1
+    container_name: deal-node-exporter
+    profiles: ["observability"]
+    command:
+      - --path.procfs=/host/proc
+      - --path.sysfs=/host/sys
+      - --path.rootfs=/host/root
+      - --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($|/)
+    ports:
+      - "9100:9100"
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/host/root:ro,rslave
+    pid: host
+
 volumes:
   deal_pgdata:
   deal_minio_data:
@@ -268,3 +339,4 @@ volumes:
   deal_ml_data:
   deal_api_data:
   deal_prometheus_data:
+  deal_tempo_data: