use nginx for handling and proxy request to API and Web UI #15
Conversation
📝 WalkthroughWalkthroughAdded an nginx reverse-proxy service to Docker Compose, removed host port mappings from Changes
Sequence DiagramsequenceDiagram
participant Client
participant nginx as nginx-proxy<br/>(port 80)
participant api as swetrix-api<br/>(port 5005)
participant app as swetrix<br/>(port 3000)
Client->>nginx: HTTP request (port 80)
rect rgba(200,220,240,0.5)
Note over nginx: Route decision
alt Path starts with /backend
nginx->>api: proxy_pass to swetrix-api:5005 (HTTP/1.1)
api-->>nginx: response
else Other paths (root)
nginx->>app: proxy_pass to swetrix:3000 (HTTP/1.1)
app-->>nginx: response
end
end
nginx-->>Client: HTTP response
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Fix all issues with AI Agents 🤖
In @nginx/config:
- Around line 6-12: The /api/ location block is missing several proxy headers
and operational directives; inside the location /api/ block add proxy_set_header
X-Forwarded-Proto $scheme and proxy_set_header Upgrade $http_upgrade along with
proxy_set_header Connection $connection_upgrade (and ensure you add the
top-level map $http_upgrade -> $connection_upgrade if WebSocket support is
required), and also add client_max_body_size with an appropriate limit plus
timeout directives proxy_connect_timeout, proxy_send_timeout, and
proxy_read_timeout to make the proxy resilient.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
nginx/config (1)
14-20: Add missing proxy headers and consider operational directives.The root location has the same gaps as the /api/ location:
Major concerns:
- X-Forwarded-Proto header missing (critical for HTTPS setups)
- Connection and Upgrade headers missing (required if the frontend uses WebSockets for real-time updates)
Recommended improvements:
- Add client_max_body_size directive
- Add timeout configurations for better reliability
🔎 Proposed enhancements
location / { proxy_pass http://swetrix:3000; proxy_http_version 1.1; proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; + proxy_set_header X-Forwarded-Proto $scheme; + proxy_set_header X-Forwarded-Host $host; + + # WebSocket support (if needed) + proxy_set_header Upgrade $http_upgrade; + proxy_set_header Connection $connection_upgrade; + + # Operational settings + client_max_body_size 10M; + proxy_connect_timeout 60s; + proxy_send_timeout 60s; + proxy_read_timeout 60s; }
🧹 Nitpick comments (2)
compose.yaml (2)
117-119: Replace deprecatedlinkswithdepends_on.The
linksdirective is deprecated in Docker Compose v2+. Usedepends_oninstead for service dependencies, which provides the same networking functionality with clearer semantics.🔎 Proposed refactor
nginx-proxy: image: nginx:1.29.4-alpine restart: always - links: - - "swetrix-api" - - "swetrix" + depends_on: + swetrix: + condition: service_healthy + swetrix-api: + condition: service_healthy ports: - "80:80"
114-123: Consider adding a health check for the nginx-proxy service.Adding a health check improves service orchestration and enables better monitoring of the reverse proxy.
🔎 Proposed enhancement
nginx-proxy: image: nginx:1.29.4-alpine restart: always links: - "swetrix-api" - "swetrix" ports: - "80:80" volumes: - ./nginx/config:/etc/nginx/conf.d/default.conf + healthcheck: + test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:80/ || exit 1"] + interval: 30s + timeout: 10s + retries: 3 + start_period: 10s
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
compose.yamlnginx/config
🔇 Additional comments (3)
nginx/config (1)
2-3: LGTM! Standard listen configuration.The IPv4 and IPv6 listen directives on port 80 are correctly configured for the single-domain architecture.
compose.yaml (2)
9-9: LGTM! API_URL correctly configured for single-domain setup.The hardcoded
/apivalue aligns with the nginx routing configuration that proxies/api/requests to the backend API service.
115-115: No action required. The image versionnginx:1.29.4-alpineis valid—nginx 1.29.4 (mainline) was released on December 9, 2025. If using a mainline release in production is a concern, consider pinning to the latest stable version (1.28.1 as of January 2026) instead, but the current version specification itself is not invalid.
|
wow that look fantastic! thanks for the PR, will be merged before the v5 release soon! |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@compose.yaml`:
- Line 9: The frontend is configured with API_URL=/backend but nginx only
proxies location /api/ to the API service, causing requests to /backend to hit
the frontend; fix by either changing API_URL to "/api" in the compose
environment (update the API_URL value) or add a matching nginx location block
(add location /backend { proxy_pass http://swetrix-api:5005/; } in nginx/config)
so that requests to /backend are forwarded to swetrix-api:5005.
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@compose.yaml`:
- Line 9: In the swetrix-fe container environment block in compose.yaml, replace
the unsupported environment key BASE_URL with API_URL so the frontend can locate
the backend (i.e., change the mapping from BASE_URL=${BASE_URL} to
API_URL=${BASE_URL} or set API_URL to the public Swetrix API base URL); update
the environment entry for the swetrix-fe service accordingly.
In `@README.md`:
- Around line 23-25: Replace the non-descriptive link text "here" that points to
https://docs.swetrix.com/selfhosting/configuring with a descriptive phrase like
"Self-hosting configuration guide" (or "Swetrix self-hosting configuration
guide") so the sentence "A table explaining what each value means can be found
here" becomes accessible and lint-compliant; update the markdown link text while
keeping the same URL and leave the surrounding sentences about BASE_URL and
docker unchanged to satisfy MD059.
🧹 Nitpick comments (1)
compose.yaml (1)
114-128: Consider mounting the nginx config read-only.
Prevents accidental writes in the container and signals intent.🔒 Suggested change
- - ./nginx/config:/etc/nginx/conf.d/default.conf + - ./nginx/config:/etc/nginx/conf.d/default.conf:ro
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@nginx/config`:
- Around line 19-27: The proxy headers use undefined variables
$connection_upgrade and $proxy_add_forwarded; fix by either (A) replacing the
non-standard Forwarded header (proxy_set_header Forwarded) with a supported
header or removing it and set Connection to a static value (e.g., "upgrade" when
appropriate), or (B, preferred) add a map for $http_upgrade to define
$connection_upgrade at the http level (via a map directive in the http block or
top of this conf.d include) and remove/replace $proxy_add_forwarded with a
constructed Forwarded value or omit it; update the proxy_set_header lines
(proxy_set_header Connection and proxy_set_header Forwarded) accordingly so
Connection uses the defined $connection_upgrade and Forwarded does not reference
$proxy_add_forwarded.
♻️ Duplicate comments (1)
nginx/config (1)
37-58: Same undefined variable issues apply here.The
$connection_upgradeand$proxy_add_forwardedissues flagged in the/backend/block apply equally to this location block. Apply the same fix to both locations.
🧹 Nitpick comments (1)
nginx/config (1)
29-35: Consider adding timeout and body size limits.The proxy buffering configuration looks good. However, for production resilience, consider adding:
client_max_body_sizeto limit upload sizes- Timeout directives to prevent hanging connections
♻️ Proposed additions
# Proxy buffering (prevents truncated responses for large files) proxy_buffering on; proxy_buffer_size 256k; proxy_buffers 32 512k; proxy_busy_buffers_size 4m; proxy_max_temp_file_size 1024m; + + # Operational limits + client_max_body_size 10m; + proxy_connect_timeout 60s; + proxy_send_timeout 60s; + proxy_read_timeout 60s; }
2 participants
This fix issue Swetrix/swetrix#460, by using nginx to proxy request then forward to either API or FE. It help Swetrix can be deploy on single domain with API is on
/api/instead of separate domainSummary by CodeRabbit
Chores
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.