From 4e2db680494844d0d596d60daa4fda1f35af713f Mon Sep 17 00:00:00 2001
From: Brent Neale <BrentNeale1@users.noreply.github.com>
Date: Thu, 19 Feb 2026 15:53:54 +1000
Subject: [PATCH] Add Railway deployment config for 24/7 cloud paper trading

- Dockerfile: add templates copy, ENV PORT, update CMD to live engine
- Create src/live/health.py: threaded HTTP health server (/health, /state)
- Wire health server into src/live/run.py before engine loop
- Dashboard: add unauthenticated /health endpoint, use PORT env var
- Create railway.toml with Dockerfile builder and health check config
- docker-compose.yml: rename service to live-engine, add PORT env vars

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 Dockerfile         |  4 +++-
 docker-compose.yml | 10 +++++++--
 railway.toml       |  9 ++++++++
 src/dashboard.py   |  7 +++++-
 src/live/health.py | 53 ++++++++++++++++++++++++++++++++++++++++++++++
 src/live/run.py    |  3 +++
 6 files changed, 82 insertions(+), 4 deletions(-)
 create mode 100644 railway.toml
 create mode 100644 src/live/health.py

diff --git a/Dockerfile b/Dockerfile
index 2e5074c..eda6645 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -12,8 +12,10 @@ RUN pip install --no-cache-dir -r requirements.docker.txt
 COPY config/system.yaml config/system.yaml
 COPY src/ src/
 COPY sql/ sql/
+COPY templates/ templates/
 
 RUN mkdir -p logs models
 
 ENV PYTHONUNBUFFERED=1
-CMD ["python", "src/order_executor.py"]
+ENV PORT=8080
+CMD ["python", "src/live/run.py"]
diff --git a/docker-compose.yml b/docker-compose.yml
index b9211f8..760e3ff 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,13 +1,17 @@
 services:
-  fx-quant:
+  live-engine:
     build: .
-    container_name: fx-quant
+    container_name: fx-quant-engine
     env_file:
       - config/.env
+    environment:
+      - PORT=8080
     volumes:
       - ./config:/app/config
       - ./logs:/app/logs
       - ./models:/app/models
+    ports:
+      - "8080:8080"
     restart: unless-stopped
 
   dashboard:
@@ -16,6 +20,8 @@ services:
     command: python src/dashboard.py
     env_file:
       - config/.env
+    environment:
+      - PORT=5000
     volumes:
       - ./config:/app/config
       - ./logs:/app/logs:ro
diff --git a/railway.toml b/railway.toml
new file mode 100644
index 0000000..2eb66d9
--- /dev/null
+++ b/railway.toml
@@ -0,0 +1,9 @@
+[build]
+builder = "dockerfile"
+dockerfilePath = "Dockerfile"
+
+[deploy]
+healthcheckPath = "/health"
+healthcheckTimeout = 30
+restartPolicyType = "on_failure"
+restartPolicyMaxRetries = 5
diff --git a/src/dashboard.py b/src/dashboard.py
index 53357a0..8bc0088 100644
--- a/src/dashboard.py
+++ b/src/dashboard.py
@@ -161,6 +161,11 @@ def validate_config(cfg):
 # ---------------------------------------------------------------------------
 # Routes
 # ---------------------------------------------------------------------------
+@app.route("/health")
+def health():
+    return jsonify({"status": "ok"})
+
+
 @app.route("/")
 @requires_auth
 def index():
@@ -589,4 +594,4 @@ def _parse_int_list(s):
 # Main
 # ---------------------------------------------------------------------------
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5000, debug=False)
+    app.run(host="0.0.0.0", port=int(os.environ.get("PORT", 5000)), debug=False)
diff --git a/src/live/health.py b/src/live/health.py
new file mode 100644
index 0000000..a022add
--- /dev/null
+++ b/src/live/health.py
@@ -0,0 +1,53 @@
+"""
+Lightweight threaded HTTP health server for Railway liveness checks.
+
+Runs as a daemon thread so it never blocks the main trading engine loop.
+"""
+import json
+import os
+import time
+import threading
+from http.server import HTTPServer, BaseHTTPRequestHandler
+
+_start_time = time.time()
+
+STATE_FILE = os.path.join(
+    os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
+    "logs", "live_state.json",
+)
+
+
+class _HealthHandler(BaseHTTPRequestHandler):
+    def do_GET(self):
+        if self.path == "/health":
+            body = json.dumps({
+                "status": "ok",
+                "uptime_seconds": round(time.time() - _start_time, 1),
+            })
+            self._respond(200, body)
+        elif self.path == "/state":
+            try:
+                with open(STATE_FILE) as f:
+                    body = f.read()
+            except FileNotFoundError:
+                body = json.dumps({"error": "state file not found"})
+            self._respond(200, body)
+        else:
+            self._respond(404, json.dumps({"error": "not found"}))
+
+    def _respond(self, code: int, body: str):
+        self.send_response(code)
+        self.send_header("Content-Type", "application/json")
+        self.end_headers()
+        self.wfile.write(body.encode())
+
+    def log_message(self, format, *args):
+        pass  # suppress request logs to keep engine output clean
+
+
+def start_health_server():
+    port = int(os.environ.get("PORT", 8080))
+    server = HTTPServer(("0.0.0.0", port), _HealthHandler)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    print(f"Health server listening on :{port}")
diff --git a/src/live/run.py b/src/live/run.py
index 58e2589..78cae17 100644
--- a/src/live/run.py
+++ b/src/live/run.py
@@ -89,6 +89,9 @@ def build_slots(config: dict) -> list[StrategySlot]:
 
 
 def main():
+    from src.live.health import start_health_server
+    start_health_server()
+
     config = load_config()
     if not config:
         print("ERROR: No phase2 config found in config/system.yaml")