observability

.qualops/.qualopsrc.json

@@ -23,4 +23,3 @@
     "maxInlineComments": 50
   }
 }
-

Dockerfile

@@ -24,9 +24,7 @@ RUN pnpm run build
 
 FROM node:22-bookworm-slim AS runtime
 WORKDIR /app
-ENV NODE_ENV=production \
-    PORT=3000 \
-    CONFIG_PATH=/etc/configurable-agent/config.yaml
+ENV NODE_ENV=production PORT=3000
 RUN corepack enable && corepack prepare pnpm@10.30.2 --activate
 COPY package.json pnpm-lock.yaml ./
 COPY pnpm-workspace.yaml* ./

docker-compose.yml

@@ -0,0 +1,51 @@
+services:
+  agent:
+    build:
+      context: .
+      dockerfile: ./Dockerfile
+    ports:
+      - "3000:3000"
+    environment:
+      - CONFIG_PATH=/app/example.config.yaml
+      - OTEL_EXPORTER_OTLP_ENDPOINT=http://tempo:4318
+      - OTEL_SERVICE_NAME=configurable-agent
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+    volumes:
+      - ./example.config.yaml:/app/example.config.yaml:ro
+    healthcheck:
+      test: ["CMD", "node", "-e", "fetch('http://localhost:3000/health').then(r => process.exit(r.ok ? 0 : 1)).catch(() => process.exit(1))"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+    depends_on:
+      - tempo
+
+  tempo:
+    image: grafana/tempo:2.6.1
+    command: ["-config.file=/etc/tempo.yaml"]
+    volumes:
+      - ./docker/tempo.yaml:/etc/tempo.yaml
+      - tempo_data:/var/tempo
+    ports:
+      - "3200:3200"   # HTTP API
+      - "4317:4317"   # OTLP gRPC
+      - "4318:4318"   # OTLP HTTP
+
+  grafana:
+    image: grafana/grafana:latest
+    volumes:
+      - ./docker/grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
+      - ./docker/grafana-provisioning.yaml:/etc/grafana/provisioning/dashboards/dashboard.yaml
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+      - GF_AUTH_DISABLE_LOGIN_FORM=true
+      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor
+    ports:
+      - "3001:3000"
+    depends_on:
+      - tempo
+
+volumes:
+  tempo_data:

docker/grafana-datasources.yaml

@@ -0,0 +1,20 @@
+apiVersion: 1
+
+datasources:
+  - name: Tempo
+    type: tempo
+    access: proxy
+    orgId: 1
+    url: http://tempo:3200
+    basicAuth: false
+    isDefault: true
+    version: 1
+    editable: false
+    apiVersion: 1
+    uid: tempo
+    jsonData:
+      httpMethod: GET
+      search:
+        hide: false
+      nodeGraph:
+        enabled: true

docker/grafana-provisioning.yaml

@@ -0,0 +1,11 @@
+apiVersion: 1
+
+providers:
+  - name: "default"
+    orgId: 1
+    folder: ""
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 10
+    options:
+      path: /var/lib/grafana/dashboards

docker/tempo.yaml

@@ -0,0 +1,26 @@
+server:
+  http_listen_port: 3200
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        http:
+          endpoint: 0.0.0.0:4318
+        grpc:
+          endpoint: 0.0.0.0:4317
+
+ingester:
+  max_block_duration: 5m
+
+compactor:
+  compaction:
+    block_retention: 1h
+
+storage:
+  trace:
+    backend: local
+    wal:
+      path: /var/tempo/wal
+    local:
+      path: /var/tempo/blocks

package.json

@@ -10,6 +10,7 @@
   "engines": {
     "node": ">=22"
   },
+  "packageManager": "pnpm@10.28.2",
   "scripts": {
     "dev": "tsx watch src/index.ts",
     "build": "tsc -p tsconfig.build.json && chmod +x dist/index.js",
@@ -28,6 +29,7 @@
     "@ai-sdk/openai": "^2.0.0",
     "@ai-sdk/openai-compatible": "^1.0.36",
     "@hono/node-server": "^1.14.0",
+    "@hono/otel": "1.1.2",
     "@opentelemetry/api": "^1.9.0",
     "@opentelemetry/auto-instrumentations-node": "^0.54.0",
     "@opentelemetry/exporter-trace-otlp-http": "^0.55.0",

src/api/server.ts

@@ -1,3 +1,4 @@
+import { httpInstrumentationMiddleware } from '@hono/otel';
 import type { ModelMessage, ToolSet } from 'ai';
 import { Hono } from 'hono';
 import { streamSSE } from 'hono/streaming';
@@ -20,6 +21,8 @@ export function buildServer(config: AgentConfig, options: BuildServerOptions) {
   const app = new Hono();
   const { tools } = options;
 
+  app.use('*', httpInstrumentationMiddleware());
+
   app.get('/health', (c) => c.json({ status: 'ok' }));
 
   app.get('/ready', (c) => {

src/modes/serve.ts

@@ -23,7 +23,7 @@ export async function runServe(): Promise<void> {
   let registry: Awaited<ReturnType<typeof buildMcpRegistry>>;
   try {
     registry = await buildMcpRegistry(config);
-    
+
     logger.info(
       { tools: Object.keys(registry.tools).length, servers: config.mcpTools.length },
       'mcp registry ready',

src/observability/tracing.ts

@@ -17,7 +17,13 @@ export function startTracing(): void {
       [SemanticResourceAttributes.SERVICE_VERSION]: process.env.OTEL_SERVICE_VERSION ?? '0.1.0',
     }),
     traceExporter: new OTLPTraceExporter(),
-    instrumentations: [getNodeAutoInstrumentations()],
+    instrumentations: [
+      getNodeAutoInstrumentations({
+        '@opentelemetry/instrumentation-http': {
+          requireParentforIncomingSpans: true,
+        },
+      }),
+    ],
   });
   sdk.start();
 }