deploy xmem-go to aws

Author: ved015

.github/workflows/deploy-go.yml

@@ -0,0 +1,93 @@
+# Deploy xmem-go to the PRODUCTION AWS EC2 instance when Go code changes land on main.
+#
+# Mirrors the Python deploy workflow: SSHes into EC2, pulls latest main,
+# builds the Go binary on-server, and restarts the xmem-go systemd service.
+#
+# Re-uses the same EC2 secrets as the Python deploy workflow:
+#   EC2_HOST, EC2_USER, EC2_SSH_KEY, EC2_SSH_KEY_PASSPHRASE
+
+name: Deploy xmem-go
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'xmem-go/**'
+  workflow_dispatch:
+
+concurrency:
+  group: deploy-xmem-go
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment:
+      name: production
+      url: ${{ vars.PRODUCTION_URL }}
+    permissions:
+      contents: read
+      deployments: write
+
+    steps:
+      - name: Create deployment
+        uses: chrnorm/deployment-action@v2
+        id: deployment
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          environment: production
+
+      - name: Deploy over SSH
+        uses: appleboy/ssh-action@v1.2.2
+        with:
+          host: ${{ secrets.EC2_HOST }}
+          username: ${{ secrets.EC2_USER }}
+          key: ${{ secrets.EC2_SSH_KEY }}
+          passphrase: ${{ secrets.EC2_SSH_KEY_PASSPHRASE }}
+          command_timeout: 20m
+          script: |
+            set -euo pipefail
+            export PATH=$PATH:/usr/local/go/bin
+            cd "${{ secrets.EC2_DEPLOY_PATH }}"
+
+            echo "── Pulling latest main ──"
+            git fetch origin main
+            git checkout main
+            git pull origin main
+
+            echo "── Building xmem-go ──"
+            cd xmem-go
+            go build -o xmem-go ./cmd/xmem
+
+            echo "── Restarting xmem-go service ──"
+            sudo systemctl restart xmem-go
+
+            echo "── Waiting for health endpoint ──"
+            for i in $(seq 1 30); do
+              HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8002/health || true)
+              if [ "$HTTP_CODE" = "200" ]; then
+                echo "Health check passed (attempt $i)"
+                exit 0
+              fi
+              echo "Health check attempt $i: HTTP $HTTP_CODE — retrying in 10s"
+              sleep 10
+            done
+            echo "FATAL: Health check never returned 200 after 300s"
+            exit 1
+
+      - name: Deployment succeeded
+        if: success()
+        uses: chrnorm/deployment-status@v2
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          deployment-id: ${{ steps.deployment.outputs.deployment_id }}
+          state: success
+          environment-url: ${{ vars.PRODUCTION_URL }}
+
+      - name: Deployment failed
+        if: failure()
+        uses: chrnorm/deployment-status@v2
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          deployment-id: ${{ steps.deployment.outputs.deployment_id }}
+          state: failure

xmem-go/.env.example

@@ -1,6 +1,6 @@
 # XMem Go runs separately from the production Python service.
 API_HOST=0.0.0.0
-API_PORT=8081
+API_PORT=8002
 API_KEYS='["dev-xmem-go-key"]'
 CORS_ORIGINS='["http://localhost:3000","http://localhost:5173"]'
 RATE_LIMIT=60

xmem-go/.gitignore

@@ -3,4 +3,5 @@
 !.env.example
 coverage.out
 tmp/
+xmem-go
 

xmem-go/README.md

@@ -30,20 +30,20 @@ go test ./...
 go run ./cmd/xmem
 ```
 
-The server listens on `http://localhost:8081` by default. Use the dev API key from `.env.example`:
+The server listens on `http://localhost:8002` by default. Use the dev API key from `.env.example`:
 
 ```bash
-curl http://localhost:8081/health
+curl http://localhost:8002/health
 
-curl -X POST http://localhost:8081/v1/memory/ingest \
+curl -X POST http://localhost:8002/v1/memory/ingest \
   -H 'Authorization: Bearer dev-xmem-go-key' \
   -H 'Content-Type: application/json' \
   -d '{"user_query":"My name is Alice and I work at XMem.","user_id":"alice"}'
 
 # The ingest response returns a durable job_id immediately. Poll the returned
 # status_url until status is "succeeded" before retrieving the newly written memory.
 
-curl -X POST http://localhost:8081/v1/memory/retrieve \
+curl -X POST http://localhost:8002/v1/memory/retrieve \
   -H 'Authorization: Bearer dev-xmem-go-key' \
   -H 'Content-Type: application/json' \
   -d '{"query":"Where do I work?","user_id":"alice","top_k":5}'

xmem-go/docker/Dockerfile

@@ -8,6 +8,6 @@ FROM alpine:3.21
 WORKDIR /app
 COPY --from=build /out/xmem-go /app/xmem-go
 COPY .env.example /app/.env.example
-EXPOSE 8081
+EXPOSE 8002
 CMD ["/app/xmem-go"]