auto-fix: harness-dashboard restarted — container was down, now healthy

This commit is contained in:
Abiba
2026-06-28 01:36:00 +00:00
parent 0ca3b65ad4
commit ac13ecaaf7
18 changed files with 4500 additions and 0 deletions
@@ -0,0 +1,143 @@
version: "3.8"
services:
redis:
image: redis:7-alpine
container_name: harness-redis
restart: unless-stopped
ports:
- "127.0.0.1:6379:6379"
volumes:
- redis-data:/data
command: redis-server --appendonly yes --maxmemory 256mb --maxmemory-policy allkeys-lru
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 10s
timeout: 3s
retries: 5
postgres:
image: postgres:16-alpine
container_name: harness-postgres
restart: unless-stopped
ports:
- "127.0.0.1:5432:5432"
environment:
- POSTGRES_DB=litellm
- POSTGRES_USER=litellm
- POSTGRES_PASSWORD=d9fc143e3dc1a7a8e672c359fea95c5e
volumes:
- pgdata:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U litellm"]
interval: 5s
timeout: 3s
retries: 5
router:
build: ./router
container_name: harness-router
restart: unless-stopped
ports:
- "127.0.0.1:9000:9000"
environment:
- REDIS_URL=redis://redis:6379
- GPU_MOE_URL=http://192.168.68.15:8080/v1
- GPU_DENSE_URL=http://192.168.68.8:8080/v1
- GPU_LIGHT_URL=http://192.168.68.110:8080/v1
- API_KEYS={"sk-syslog-local-master-key":{"tier":"enterprise","agent":"admin","deprecated":true},"sk-9e65b69a67-e54af421c1b09fb8bd4f75dacb38cb64":{"tier":"enterprise","agent":"admin"},"sk-syslog-abiba":{"tier":"enterprise","agent":"Abiba","deprecated":true},"sk-856ffb0bbb-e5aaf78b10054eca608f8fbcbd73a889":{"tier":"enterprise","agent":"Abiba"},"sk-syslog-mumuni":{"tier":"enterprise","agent":"Mumuni","deprecated":true},"sk-b57e6e042e-47573660114f3138c852c47f62da807e":{"tier":"enterprise","agent":"Mumuni"},"sk-syslog-tanko":{"tier":"enterprise","agent":"Tanko","deprecated":true},"sk-620a05e95a-e93d875476b650a4d1137249ead8eaa7":{"tier":"enterprise","agent":"Tanko"},"sk-syslog-koby":{"tier":"enterprise","agent":"Koby","deprecated":true},"sk-eb3e6fc1c0-de1bf2edf35a53cb3749a2400483fdee":{"tier":"enterprise","agent":"Koby"},"sk-syslog-kagenz0":{"tier":"enterprise","agent":"Kagenz0","deprecated":true},"sk-12b66b3392-b548aed9138aeb6f698e8e521650ed9b":{"tier":"enterprise","agent":"Kagenz0"},"sk-syslog-koonimo":{"tier":"enterprise","agent":"Koonimo","deprecated":true},"sk-680d06686c-00ee8bf9dc3c93b276af122d49a14dfe":{"tier":"enterprise","agent":"Koonimo"},"sk-starter-abc123":{"tier":"starter","agent":"test-starter","deprecated":true},"sk-55da55907a-1bd7ff344e26feda50e9ac2219697860":{"tier":"starter","agent":"test-starter"},"sk-professional-xyz789":{"tier":"professional","agent":"test-pro","deprecated":true},"sk-b5159863e6-8df3ae52fb958cfe76cc2888c8c8e676":{"tier":"professional","agent":"test-pro"}}
- ADMIN_KEY=sk-admin-ee09fffd04978b61a1569ac670c68814
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9000/health')"]
interval: 30s
timeout: 15s
retries: 3
depends_on:
redis:
condition: service_healthy
litellm:
image: docker.litellm.ai/berriai/litellm:1.90.0-rc.1
command: ["--config", "/app/config.yaml", "--port", "4000"]
container_name: harness-litellm
restart: unless-stopped
ports:
- "4001:4000"
volumes:
- ./litellm_config.yaml:/app/config.yaml
- /opt/combined-ca-bundle.pem:/etc/ssl/certs/ca-certificates.crt:ro
environment:
- LITELLM_MASTER_KEY=sk-litellm-7f96080dd99b15c36bd4b333b58a6796
- ROUTER_API_KEY=sk-9e65b69a67-e54af421c1b09fb8bd4f75dacb38cb64
- DATABASE_URL=postgresql://litellm:d9fc143e3dc1a7a8e672c359fea95c5e@postgres:5432/litellm
- STORE_MODEL_IN_DB=True
- LITELLM_UI_USERNAME=admin
- LITELLM_UI_PASSWORD=syslog-admin-2026
- UI_USERNAME=admin
- UI_PASSWORD=syslog-admin-2026
- OPENAI_API_KEY=not-used
- PROXY_BASE_URL=https://litellm.sysloggh.net
- DOCS_URL=/docs
- ANTHROPIC_API_KEY=not-used
- GENERIC_CLIENT_ID=FHd7bs9dP5gHad2Ki23iUL5kQvFa0GRaj3nlLnNU
- GENERIC_CLIENT_SECRET=aDkXQx82duqpxc98xxqp0quzzUf1mawsnOTqj7sx1acaS7rWSt02N5ksBCi92n8ZilRavigoYME6fLakP20Ixc9H2pxnSZFiOqQLb7BPi8UtsvfxmzXklD0HJIdbKFxe
- GENERIC_AUTHORIZATION_ENDPOINT=https://auth.sysloggh.net/application/o/authorize/
- GENERIC_TOKEN_ENDPOINT=https://auth.sysloggh.net/application/o/token/
- GENERIC_USERINFO_ENDPOINT=https://auth.sysloggh.net/application/o/userinfo/
- GENERIC_SCOPE=openid email profile
- GENERIC_ROLE_MAPPINGS_DEFAULT_ROLE=proxy_admin
- SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
extra_hosts:
- "host.docker.internal:host-gateway"
- "auth.sysloggh.net:192.168.68.11"
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:4000/health/liveliness')"]
interval: 15s
timeout: 5s
retries: 3
depends_on:
postgres:
condition: service_healthy
redis:
condition: service_healthy
nginx:
image: nginx:alpine
container_name: harness-nginx
restart: unless-stopped
ports:
- "80:80"
volumes:
- ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
- ./dashboard:/opt/inference-harness/dashboard:ro
extra_hosts:
- "auth.sysloggh.net:192.168.68.11"
healthcheck:
test: ["CMD", "curl", "-f", "http://127.0.0.1/health"]
interval: 30s
timeout: 15s
retries: 3
depends_on:
- litellm
- dashboard
dashboard:
build: ./dashboard
container_name: harness-dashboard
restart: unless-stopped
ports:
- "127.0.0.1:3000:3000"
environment:
- REDIS_URL=redis://redis:6379
- GPU_SIDECARS=192.168.68.15:8090,192.168.68.8:8090,192.168.68.110:8090
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3000/health')"]
interval: 15s
timeout: 5s
retries: 3
depends_on:
- redis
volumes:
redis-data:
pgdata: