chore(docker): add Dockerfile, compose stack, and observability configs

Author: reaatech

Dockerfile

@@ -0,0 +1,55 @@
+# Stage 1: Build
+FROM node:22-alpine AS builder
+
+WORKDIR /app
+
+# Copy package files
+COPY package.json package-lock.json ./
+
+# Install dependencies (full install for build)
+RUN npm ci && npm cache clean --force
+
+# Copy source
+COPY tsconfig.json ./
+COPY src ./src
+
+# Build
+RUN npm run build
+
+# Stage 2: Install production deps only
+FROM node:22-alpine AS prod-deps
+
+WORKDIR /app
+
+COPY package.json package-lock.json ./
+RUN npm ci --only=production && npm cache clean --force
+
+# Stage 3: Runtime
+FROM node:22-alpine AS runtime
+
+WORKDIR /app
+
+# Install dumb-init for proper signal handling
+RUN apk add --no-cache dumb-init
+
+# Create non-root user
+RUN addgroup -g 1001 -S nodejs && \
+    adduser -S nodejs -u 1001
+
+# Copy built artifacts and prod deps
+COPY --from=prod-deps --chown=nodejs:nodejs /app/node_modules ./node_modules
+COPY --from=builder --chown=nodejs:nodejs /app/dist ./dist
+COPY --from=builder --chown=nodejs:nodejs /app/package.json ./
+
+# Switch to non-root user
+USER nodejs
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+  CMD node dist/healthcheck.js || exit 1
+
+# Expose port for MCP server
+EXPOSE 3000
+
+# Default command
+CMD ["node", "dist/cli.js"]

docker-compose.yml

@@ -0,0 +1,78 @@
+version: '3.8'
+
+services:
+  # Main agent-eval-harness service
+  agent-eval-harness:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "3000:3000"
+    environment:
+      - NODE_ENV=development
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4318
+    volumes:
+      - ./trajectories:/app/trajectories
+      - ./results:/app/results
+      - ./golden:/app/golden
+    depends_on:
+      - otel-collector
+    command: ["node", "dist/cli.js", "serve", "--port", "3000", "--host", "0.0.0.0"]
+
+  # OpenTelemetry Collector
+  otel-collector:
+    image: otel/opentelemetry-collector:latest
+    ports:
+      - "4317:4317"  # OTLP gRPC
+      - "4318:4318"  # OTLP HTTP
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel/config.yaml
+    command: ["--config", "/etc/otel/config.yaml"]
+
+  # Jaeger for tracing visualization
+  jaeger:
+    image: jaegertracing/all-in-one:latest
+    ports:
+      - "16686:16686"  # Jaeger UI
+      - "14268:14268"  # Jaeger ingest
+    environment:
+      - COLLECTOR_OTLP_ENABLED=true
+
+  # TODO: Replace with actual mock LLM image
+  # mock-llm:
+  #   image: TODO
+  #   ports:
+  #     - "8080:8080"
+  #   environment:
+  #     - PORT=8080
+  #     - MOCK_RESPONSES=true
+
+  # Prometheus for metrics
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus/prometheus.yml
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/etc/prometheus/console_libraries'
+      - '--web.console.templates=/etc/prometheus/consoles'
+
+  # Grafana for dashboards
+  grafana:
+    image: grafana/grafana:latest
+    ports:
+      - "3001:3000"
+    environment:
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
+    volumes:
+      - grafana-data:/var/lib/grafana
+    depends_on:
+      - prometheus
+
+volumes:
+  grafana-data:

otel-collector-config.yaml

@@ -0,0 +1,31 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+    timeout: 5s
+    send_batch_size: 1024
+
+exporters:
+  logging:
+    loglevel: warn
+  otlp/jaeger:
+    endpoint: jaeger:4317
+    tls:
+      insecure: true
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [logging, otlp/jaeger]
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [logging]

prometheus.yaml

@@ -0,0 +1,8 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'agent-eval-harness'
+    static_configs:
+      - targets: ['agent-eval-harness:9464']