chore: update versions

src/bifrost-gateway/.env.example

@@ -1,5 +1,13 @@
 # Bifrost Gateway Version
-BIFROST_VERSION=v1.3.48
+BIFROST_VERSION=v1.3.54
 
 # Port to bind to on the host machine
 BIFROST_PORT=28080
+
+# Telemetry
+PROMETHEUS_VERSION=v3.0.1
+PROMETHEUS_PORT=29090
+GRAFANA_VERSION=11.4.0
+GRAFANA_PORT=23000
+GRAFANA_ADMIN_USER=admin
+GRAFANA_ADMIN_PASSWORD=admin

src/bifrost-gateway/README.md

@@ -7,12 +7,39 @@ Bifrost is a lightweight, high-performance LLM gateway that supports multiple mo
 ## Services
 
 - `bifrost`: The LLM gateway service.
+- `prometheus`: Prometheus for metrics collection (enabled with `--profile telemetry`).
+- `grafana`: Grafana for visualization (enabled with `--profile telemetry`).
 
 ## Configuration
 
-- `BIFROST_VERSION`: The version of the Bifrost image, default is `v1.3.48`.
+- `BIFROST_VERSION`: The version of the Bifrost image, default is `v1.3.54`.
 - `BIFROST_PORT`: The port for the Bifrost service, default is `28080`.
 
+### Telemetry
+
+- `PROMETHEUS_VERSION`: Prometheus version, default `v3.0.1`.
+- `PROMETHEUS_PORT`: Prometheus port, default `29090`.
+- `GRAFANA_VERSION`: Grafana version, default `11.4.0`.
+- `GRAFANA_PORT`: Grafana port, default `23000`.
+- `GRAFANA_ADMIN_USER`: Grafana admin user, default `admin`.
+- `GRAFANA_ADMIN_PASSWORD`: Grafana admin password, default `admin`.
+
+## Usage
+
+Start the gateway:
+
+```bash
+docker compose up -d
+```
+
+Start with telemetry (Prometheus + Grafana):
+
+```bash
+docker compose --profile telemetry up -d
+```
+
 ## Volumes
 
 - `bifrost_data`: A volume for storing Bifrost data.
+- `prometheus_data`: A volume for storing Prometheus data.
+- `grafana_data`: A volume for storing Grafana data.

src/bifrost-gateway/README.zh.md

@@ -7,12 +7,39 @@ Bifrost 是一个轻量级、高性能的 LLM 网关，支持多种模型和提
 ## 服务
 
 - `bifrost`: LLM 网关服务。
+- `prometheus`: 用于指标收集的 Prometheus（通过 `--profile telemetry` 启用）。
+- `grafana`: 用于可视化的 Grafana（通过 `--profile telemetry` 启用）。
 
 ## 配置
 
-- `BIFROST_VERSION`: Bifrost 镜像的版本，默认为 `v1.3.48`。
+- `BIFROST_VERSION`: Bifrost 镜像的版本，默认为 `v1.3.54`。
 - `BIFROST_PORT`: Bifrost 服务的端口，默认为 `28080`。
 
+### 遥测 (Telemetry)
+
+- `PROMETHEUS_VERSION`: Prometheus 版本，默认为 `v3.0.1`。
+- `PROMETHEUS_PORT`: Prometheus 端口，默认为 `29090`。
+- `GRAFANA_VERSION`: Grafana 版本，默认为 `11.4.0`。
+- `GRAFANA_PORT`: Grafana 端口，默认为 `23000`。
+- `GRAFANA_ADMIN_USER`: Grafana 管理员用户，默认为 `admin`。
+- `GRAFANA_ADMIN_PASSWORD`: Grafana 管理员密码，默认为 `admin`。
+
+## 使用
+
+启动网关：
+
+```bash
+docker compose up -d
+```
+
+启动带有遥测功能（Prometheus + Grafana）的网关：
+
+```bash
+docker compose --profile telemetry up -d
+```
+
 ## 卷
 
 - `bifrost_data`: 用于存储 Bifrost 数据的卷。
+- `prometheus_data`: 用于存储 Prometheus 数据的卷。
+- `grafana_data`: 用于存储 Grafana 数据的卷。

src/bifrost-gateway/config/grafana/datasources.yml

@@ -0,0 +1,9 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    url: http://prometheus:9090
+    isDefault: true
+    access: proxy
+    editable: true

src/bifrost-gateway/config/prometheus.yml

@@ -0,0 +1,8 @@
+global:
+  scrape_interval: 15s
+
+scrape_configs:
+  - job_name: 'bifrost'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['bifrost:8080']

src/bifrost-gateway/docker-compose.yaml

@@ -9,7 +9,7 @@ x-defaults: &defaults
 services:
   bifrost:
     <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}maximhq/bifrost:${BIFROST_VERSION:-v1.3.48}
+    image: ${GLOBAL_REGISTRY:-}maximhq/bifrost:${BIFROST_VERSION:-v1.3.54}
     volumes:
       - bifrost_data:/app/data
     ports:
@@ -31,5 +31,64 @@ services:
       retries: 3
       start_period: 10s
 
+  prometheus:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}prom/prometheus:${PROMETHEUS_VERSION:-v3.8.1}
+    profiles: ["telemetry"]
+    volumes:
+      - ./config/prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
+    ports:
+      - "${PROMETHEUS_PORT:-29090}:9090"
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 10s
+    deploy:
+      resources:
+        limits:
+          cpus: ${PROMETHEUS_CPU_LIMIT:-0.50}
+          memory: ${PROMETHEUS_MEMORY_LIMIT:-512M}
+        reservations:
+          cpus: ${PROMETHEUS_CPU_RESERVATION:-0.10}
+          memory: ${PROMETHEUS_MEMORY_RESERVATION:-128M}
+
+  grafana:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}grafana/grafana:${GRAFANA_VERSION:-12.3.1}
+    profiles: ["telemetry"]
+    volumes:
+      - ./config/grafana/datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml
+      - grafana_data:/var/lib/grafana
+    environment:
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
+      - GF_USERS_ALLOW_SIGN_UP=false
+    ports:
+      - "${GRAFANA_PORT:-23000}:3000"
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/api/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 10s
+    deploy:
+      resources:
+        limits:
+          cpus: ${GRAFANA_CPU_LIMIT:-0.50}
+          memory: ${GRAFANA_MEMORY_LIMIT:-512M}
+        reservations:
+          cpus: ${GRAFANA_CPU_RESERVATION:-0.10}
+          memory: ${GRAFANA_MEMORY_RESERVATION:-128M}
+
 volumes:
   bifrost_data:
+  prometheus_data:
+  grafana_data: