docs: add Coolify deployment guide and compose file (#444)

Co-authored-by: Jason Woltje <jason@diversecanvas.com> Co-committed-by: Jason Woltje <jason@diversecanvas.com>
2026-02-22 07:40:24 +00:00
parent 17144b1c42
commit 9901fba61e
2 changed files with 417 additions and 0 deletions
--- a/docker-compose.coolify.yml
+++ b/docker-compose.coolify.yml
@@ -0,0 +1,280 @@
+# ==============================================
+# Mosaic Stack — Coolify Core Deployment
+# ==============================================
+#
+# Core services only. For Matrix, speech, and other optional
+# services, deploy them as separate Coolify services or extend
+# this file.
+#
+# Usage (Coolify):
+#   1. New Resource -> Docker Compose
+#   2. Paste this file
+#   3. Set environment variables in Coolify UI
+#   4. Configure domains for web + api in Coolify UI
+#   5. Deploy
+#
+# NOTE: Traefik labels are NOT included here. Coolify manages
+# routing and TLS via its own proxy integration. Configure
+# domains in the Coolify service settings.
+#
+# ==============================================
+
+services:
+  # ======================
+  # PostgreSQL Database
+  # ======================
+  postgres:
+    image: git.mosaicstack.dev/mosaic/stack-postgres:${IMAGE_TAG:-latest}
+    restart: unless-stopped
+    environment:
+      - POSTGRES_USER=${POSTGRES_USER}
+      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
+      - POSTGRES_DB=${POSTGRES_DB}
+      - POSTGRES_SHARED_BUFFERS=${POSTGRES_SHARED_BUFFERS:-256MB}
+      - POSTGRES_EFFECTIVE_CACHE_SIZE=${POSTGRES_EFFECTIVE_CACHE_SIZE:-1GB}
+      - POSTGRES_MAX_CONNECTIONS=${POSTGRES_MAX_CONNECTIONS:-100}
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    networks:
+      - internal
+
+  # ======================
+  # Valkey Cache
+  # ======================
+  valkey:
+    image: valkey/valkey:8-alpine
+    restart: unless-stopped
+    command:
+      - valkey-server
+      - --maxmemory ${VALKEY_MAXMEMORY:-256mb}
+      - --maxmemory-policy noeviction
+      - --appendonly yes
+    volumes:
+      - valkey_data:/data
+    healthcheck:
+      test: ["CMD", "valkey-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 10s
+    networks:
+      - internal
+
+  # ======================
+  # Mosaic API
+  # ======================
+  api:
+    image: git.mosaicstack.dev/mosaic/stack-api:${IMAGE_TAG:-latest}
+    restart: unless-stopped
+    environment:
+      # Coolify domain assignment (magic variable — tells Coolify this service gets a domain on port 3001)
+      - SERVICE_FQDN_API_3001
+      - NODE_ENV=production
+      - PORT=${API_PORT:-3001}
+      - API_HOST=${API_HOST:-0.0.0.0}
+      # Database
+      - DATABASE_URL=postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
+      # Cache
+      - VALKEY_URL=redis://valkey:6379
+      # Auth (external Authentik — optional)
+      - OIDC_ENABLED=${OIDC_ENABLED:-false}
+      - OIDC_ISSUER=${OIDC_ISSUER:-}
+      - OIDC_CLIENT_ID=${OIDC_CLIENT_ID:-}
+      - OIDC_CLIENT_SECRET=${OIDC_CLIENT_SECRET:-}
+      - OIDC_REDIRECT_URI=${OIDC_REDIRECT_URI:-}
+      # JWT
+      - JWT_SECRET=${JWT_SECRET}
+      - JWT_EXPIRATION=${JWT_EXPIRATION:-24h}
+      # Better Auth
+      - BETTER_AUTH_SECRET=${BETTER_AUTH_SECRET}
+      - BETTER_AUTH_URL=${BETTER_AUTH_URL:-}
+      - CSRF_SECRET=${CSRF_SECRET}
+      - COOKIE_DOMAIN=${COOKIE_DOMAIN:-}
+      # Encryption
+      - ENCRYPTION_KEY=${ENCRYPTION_KEY}
+      # External services (optional — leave empty to disable)
+      - OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT:-}
+      - OLLAMA_MODEL=${OLLAMA_MODEL:-llama3.2}
+      - OPENBAO_ADDR=${OPENBAO_ADDR:-}
+      # Knowledge module
+      - KNOWLEDGE_CACHE_ENABLED=${KNOWLEDGE_CACHE_ENABLED:-true}
+      - KNOWLEDGE_CACHE_TTL=${KNOWLEDGE_CACHE_TTL:-300}
+      - SEMANTIC_SEARCH_SIMILARITY_THRESHOLD=${SEMANTIC_SEARCH_SIMILARITY_THRESHOLD:-0.5}
+      # Rate limiting
+      - RATE_LIMIT_TTL=${RATE_LIMIT_TTL:-60}
+      - RATE_LIMIT_GLOBAL_LIMIT=${RATE_LIMIT_GLOBAL_LIMIT:-100}
+      - RATE_LIMIT_STORAGE=${RATE_LIMIT_STORAGE:-redis}
+      # Speech services (disabled — not in core stack)
+      - STT_ENABLED=${STT_ENABLED:-false}
+      - TTS_ENABLED=${TTS_ENABLED:-false}
+      # Matrix bridge (disabled — not in core stack)
+      - MATRIX_ACCESS_TOKEN=${MATRIX_ACCESS_TOKEN:-}
+      # Telemetry (disabled by default)
+      - MOSAIC_TELEMETRY_ENABLED=${MOSAIC_TELEMETRY_ENABLED:-false}
+      - MOSAIC_TELEMETRY_SERVER_URL=${MOSAIC_TELEMETRY_SERVER_URL:-}
+      - MOSAIC_TELEMETRY_API_KEY=${MOSAIC_TELEMETRY_API_KEY:-}
+      - MOSAIC_TELEMETRY_INSTANCE_ID=${MOSAIC_TELEMETRY_INSTANCE_ID:-}
+      - MOSAIC_TELEMETRY_DRY_RUN=${MOSAIC_TELEMETRY_DRY_RUN:-false}
+      # Frontend URLs (for CORS and auth redirects)
+      - NEXT_PUBLIC_APP_URL=${NEXT_PUBLIC_APP_URL}
+      - NEXT_PUBLIC_API_URL=${NEXT_PUBLIC_API_URL}
+      - TRUSTED_ORIGINS=${TRUSTED_ORIGINS:-}
+    depends_on:
+      postgres:
+        condition: service_healthy
+      valkey:
+        condition: service_healthy
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          'node -e "require(''http'').get(''http://localhost:${API_PORT:-3001}/health'', (r) => {process.exit(r.statusCode === 200 ? 0 : 1)})"',
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    networks:
+      - internal
+
+  # ======================
+  # Mosaic Web
+  # ======================
+  web:
+    image: git.mosaicstack.dev/mosaic/stack-web:${IMAGE_TAG:-latest}
+    restart: unless-stopped
+    environment:
+      # Coolify domain assignment (magic variable — tells Coolify this service gets a domain on port 3000)
+      - SERVICE_FQDN_WEB_3000
+      - NODE_ENV=production
+      - PORT=${WEB_PORT:-3000}
+      - NEXT_PUBLIC_API_URL=${NEXT_PUBLIC_API_URL}
+      - NEXT_PUBLIC_APP_URL=${NEXT_PUBLIC_APP_URL}
+      - NEXT_PUBLIC_ORCHESTRATOR_URL=${NEXT_PUBLIC_ORCHESTRATOR_URL:-}
+      - NEXT_PUBLIC_AUTH_MODE=${NEXT_PUBLIC_AUTH_MODE:-real}
+      - ORCHESTRATOR_API_KEY=${ORCHESTRATOR_API_KEY:-}
+    depends_on:
+      api:
+        condition: service_healthy
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          'node -e "require(''http'').get(''http://localhost:${WEB_PORT:-3000}'', (r) => {process.exit(r.statusCode === 200 ? 0 : 1)})"',
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    networks:
+      - internal
+
+  # ======================
+  # Mosaic Coordinator
+  # ======================
+  coordinator:
+    image: git.mosaicstack.dev/mosaic/stack-coordinator:${IMAGE_TAG:-latest}
+    restart: unless-stopped
+    environment:
+      - GITEA_WEBHOOK_SECRET=${GITEA_WEBHOOK_SECRET:-}
+      - GITEA_URL=${GITEA_URL:-}
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+      - LOG_LEVEL=${LOG_LEVEL:-info}
+      - HOST=0.0.0.0
+      - PORT=8000
+      - COORDINATOR_POLL_INTERVAL=${COORDINATOR_POLL_INTERVAL:-5.0}
+      - COORDINATOR_MAX_CONCURRENT_AGENTS=${COORDINATOR_MAX_CONCURRENT_AGENTS:-10}
+      - COORDINATOR_ENABLED=${COORDINATOR_ENABLED:-true}
+      # Telemetry
+      - MOSAIC_TELEMETRY_ENABLED=${MOSAIC_TELEMETRY_ENABLED:-false}
+      - MOSAIC_TELEMETRY_SERVER_URL=${MOSAIC_TELEMETRY_SERVER_URL:-}
+      - MOSAIC_TELEMETRY_API_KEY=${MOSAIC_TELEMETRY_API_KEY:-}
+      - MOSAIC_TELEMETRY_INSTANCE_ID=${MOSAIC_TELEMETRY_INSTANCE_ID:-}
+      - MOSAIC_TELEMETRY_DRY_RUN=${MOSAIC_TELEMETRY_DRY_RUN:-false}
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "python",
+          "-c",
+          "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 5s
+    networks:
+      - internal
+
+  # ======================
+  # Mosaic Orchestrator
+  # ======================
+  orchestrator:
+    image: git.mosaicstack.dev/mosaic/stack-orchestrator:${IMAGE_TAG:-latest}
+    restart: unless-stopped
+    user: "1000:1000"
+    environment:
+      - NODE_ENV=production
+      - ORCHESTRATOR_PORT=3001
+      - AI_PROVIDER=${AI_PROVIDER:-ollama}
+      - OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT:-}
+      - OLLAMA_MODEL=${OLLAMA_MODEL:-llama3.2}
+      - VALKEY_URL=redis://valkey:6379
+      - VALKEY_HOST=valkey
+      - VALKEY_PORT=6379
+      - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
+      - ORCHESTRATOR_API_KEY=${ORCHESTRATOR_API_KEY:-}
+      - DOCKER_SOCKET=/var/run/docker.sock
+      - GIT_USER_NAME=Mosaic Orchestrator
+      - GIT_USER_EMAIL=orchestrator@mosaicstack.dev
+      - KILLSWITCH_ENABLED=true
+      - SANDBOX_ENABLED=true
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - orchestrator_workspace:/workspace
+    depends_on:
+      valkey:
+        condition: service_healthy
+      api:
+        condition: service_healthy
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          'node -e "require(''http'').get(''http://localhost:3001/health'', (r) => {process.exit(r.statusCode === 200 ? 0 : 1)})"',
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    networks:
+      - internal
+    security_opt:
+      - no-new-privileges:true
+    cap_drop:
+      - ALL
+    cap_add:
+      - NET_BIND_SERVICE
+    tmpfs:
+      - /tmp:noexec,nosuid,size=100m
+
+# ======================
+# Volumes
+# ======================
+volumes:
+  postgres_data:
+  valkey_data:
+  orchestrator_workspace:
+
+# ======================
+# Networks
+# ======================
+networks:
+  internal:
+    driver: bridge
--- a/docs/COOLIFY-DEPLOYMENT.md
+++ b/docs/COOLIFY-DEPLOYMENT.md
@@ -0,0 +1,137 @@
+# Mosaic Stack — Coolify Deployment
+
+## Overview
+
+Coolify deployment on VM `10.1.1.44` (Proxmox). Replaces the Docker Swarm deployment on w-docker0 (`10.1.1.45`).
+
+## Architecture
+
+```
+Internet → Cloudflare → Public IP (174.137.97.162)
+  → Main Traefik (10.1.1.43) — TCP TLS passthrough for *.woltje.com
+    → Coolify Traefik (10.1.1.44) — terminates TLS via Cloudflare DNS-01 wildcard certs
+      → Service containers
+```
+
+## Services (Core Stack)
+
+| Service      | Image                                           | Internal Port   | External Domain         |
+| ------------ | ----------------------------------------------- | --------------- | ----------------------- |
+| postgres     | `git.mosaicstack.dev/mosaic/stack-postgres`     | 5432            | —                       |
+| valkey       | `valkey/valkey:8-alpine`                        | 6379            | —                       |
+| api          | `git.mosaicstack.dev/mosaic/stack-api`          | 3001            | `api.mosaic.woltje.com` |
+| web          | `git.mosaicstack.dev/mosaic/stack-web`          | 3000            | `mosaic.woltje.com`     |
+| coordinator  | `git.mosaicstack.dev/mosaic/stack-coordinator`  | 8000            | —                       |
+| orchestrator | `git.mosaicstack.dev/mosaic/stack-orchestrator` | 3001 (internal) | —                       |
+
+Matrix (synapse, element-web) and speech services (speaches, kokoro-tts) are NOT included in the core stack. Deploy separately if needed.
+
+## Compose File
+
+`docker-compose.coolify.yml` in the repo root. This is the Coolify-compatible version of the deployment compose.
+
+Key differences from the Swarm compose (`docker-compose.swarm.portainer.yml`):
+
+- No `deploy:` blocks (Swarm-only)
+- No Traefik labels (Coolify manages routing)
+- Bridge network instead of overlay
+- `restart: unless-stopped` instead of Swarm restart policies
+- `SERVICE_FQDN_*` magic environment variables for Coolify domain assignment
+- List-style environment syntax (required for Coolify magic vars)
+
+## Coolify IDs
+
+| Resource    | UUID                       |
+| ----------- | -------------------------- |
+| Project     | `rs04g008kgkkw4s0wgsk40w4` |
+| Environment | `gko8csc804g8og0oosc8ccs8` |
+| Service     | `ug0ssok4g44wocok8kws8gg8` |
+| Server      | `as8kcogk08skskkcsok888g4` |
+
+### Application UUIDs
+
+| App          | UUID                        |
+| ------------ | --------------------------- |
+| postgres     | `jcw0ogskkw040os48ggkgkc8`  |
+| valkey       | `skssgwcggc0c8owoogcso8og`  |
+| api          | `mc40cgwwo8okwwoko84408k4k` |
+| web          | `c48gcwgc40ok44scscowc8cc`  |
+| coordinator  | `s8gwog4c44w08c8sgkcg04k8`  |
+| orchestrator | `uo4wkg88co0ckc4c4k44sowc`  |
+
+## Coolify API
+
+Base URL: `http://10.1.1.44:8000/api/v1`
+Auth: Bearer token from `credentials.json` → `coolify.app_token`
+
+### Patterns & Gotchas
+
+- **Compose must be base64-encoded** when sending via `docker_compose_raw` field
+- **`SERVICE_FQDN_*` magic vars**: Coolify reads these from the compose to auto-assign domains. Format: `SERVICE_FQDN_{NAME}_{PORT}` (e.g., `SERVICE_FQDN_API_3001`). Must use list-style env syntax (`- SERVICE_FQDN_API_3001`), NOT dict-style.
+- **FQDN updates on sub-applications**: Coolify API doesn't support updating FQDNs on compose service sub-apps via REST. Workaround: update directly in Coolify's PostgreSQL DB (`coolify-db` container, `service_applications` table).
+- **Environment variable management**: Use `PATCH /api/v1/services/{uuid}/envs` with `{ "key": "VAR_NAME", "value": "val", "is_preview": false }`
+- **Service start**: `POST /api/v1/services/{uuid}/start`
+- **Coolify uses PostgreSQL** (not SQLite) for its internal database — container `coolify-db`
+
+### DB Access (for workarounds)
+
+```bash
+ssh localadmin@10.1.1.44
+docker exec -it coolify-db psql -U coolify -d coolify
+
+-- Check service app FQDNs
+SELECT name, fqdn FROM service_applications WHERE service_id = (
+  SELECT id FROM services WHERE uuid = 'ug0ssok4g44wocok8kws8gg8'
+);
+```
+
+## Environment Variables
+
+All env vars are set via Coolify API and stored in `/data/coolify/services/{uuid}/.env` on the node.
+
+Critical vars that were missing initially:
+
+- `BETTER_AUTH_URL` — **Required** in production. API won't start without it. Set to `https://api.mosaic.woltje.com`.
+
+## Current State (2026-02-22)
+
+### Working
+
+- All 6 containers running and healthy
+- API health endpoint responds at `https://api.mosaic.woltje.com/health`
+- Database migrations completed
+- Inter-service networking (api→postgres, api→valkey) confirmed via health checks
+
+### Issues
+
+1. **DNS: `mosaic.woltje.com` points to wrong server**
+   - Resolves to `10.1.1.45` (old Swarm node) instead of through Cloudflare (`174.137.97.162`)
+   - `api.mosaic.woltje.com` resolves correctly through Cloudflare
+   - Fix: Update Cloudflare DNS A record for `mosaic.woltje.com`
+
+2. **Coordinator: OTLP exporter noise**
+   - Trying to export traces to `localhost:4318` which doesn't exist
+   - Container is healthy, errors are non-critical
+   - Fix: Set `MOSAIC_TELEMETRY_ENABLED=false` in Coolify env vars, or deploy an OTLP collector
+
+3. **Coolify managed lifecycle**
+   - CoolifyTask was failing when starting the service via API/UI
+   - Containers were started manually via `docker compose up -d` from the service directory
+   - Coolify recognizes the containers (correct naming convention) but may not properly manage restarts/redeploys
+   - Needs investigation: check Coolify task logs, verify compose processing
+
+4. **Full connectivity verification needed**
+   - web→api communication untested (blocked by DNS issue)
+   - Orchestrator→valkey and orchestrator→api connectivity unverified
+   - Coordinator webhook endpoint untested
+
+## SSH Access
+
+```bash
+ssh localadmin@10.1.1.44
+# Note: localadmin cannot sudo without TTY/password
+# Use docker to access files:
+docker run --rm -v /data/coolify/services:/srv alpine cat /srv/{uuid}/docker-compose.yml
+# Use docker exec for Coolify DB:
+docker exec -it coolify-db psql -U coolify -d coolify
+```