.github/workflows/ci.yml

@@ -20,12 +20,39 @@ jobs:
   rust:
     runs-on: ubuntu-latest
     needs: gates
-    # Compile sqlx query! macros against the committed .sqlx cache (no DB needed);
+    # Compile sqlx query! macros against the committed .sqlx cache (no DB needed).
-    # DB-backed tests spin up their own postgres via testcontainers at runtime.
+    # Tests need a live Postgres — locally cm-testkit reads CM_TEST_DATABASE_URL
+    # from .cargo/config.toml pointing at scripts/test-server.sh's host container.
+    # The fleet act_runner uses the `host` executor (jobs run on morpheus/tank/
+    # architect natively, not inside a container), so we start a per-run postgres
+    # container and reach it via its bridge IP. GITHUB_RUN_ID scopes the name so
+    # concurrent jobs on the same runner don't collide.
     env:
       SQLX_OFFLINE: "true"
     steps:
       - uses: actions/checkout@v4
+      - name: Start postgres sidecar
+        run: |
+          set -euo pipefail
+          NAME="ci-pg-${GITHUB_RUN_ID}"
+          docker rm -f "$NAME" >/dev/null 2>&1 || true
+          docker run -d --name "$NAME" \
+            -e POSTGRES_PASSWORD=postgres \
+            -e POSTGRES_DB=postgres \
+            postgres:16-alpine >/dev/null
+          PG_IP=$(docker inspect -f '{{.NetworkSettings.IPAddress}}' "$NAME")
+          echo "PG_CONTAINER=$NAME" >> "$GITHUB_ENV"
+          echo "CM_TEST_DATABASE_URL=postgres://postgres:postgres@${PG_IP}:5432/postgres" >> "$GITHUB_ENV"
+          for i in $(seq 1 30); do
+            if docker exec "$NAME" pg_isready -U postgres -q >/dev/null 2>&1; then
+              echo "postgres ready at ${PG_IP} after ${i}s"
+              exit 0
+            fi
+            sleep 1
+          done
+          echo "postgres never became ready" >&2
+          docker logs "$NAME" >&2 || true
+          exit 1
       - uses: dtolnay/rust-toolchain@stable
         with:
           toolchain: 1.96.0
@@ -39,6 +66,9 @@ jobs:
         run: cargo test --workspace
       - name: Air-gapped installer verify path
         run: ./ci/test-install.sh
+      - name: Cleanup postgres sidecar
+        if: always()
+        run: docker rm -f "${PG_CONTAINER:-}" >/dev/null 2>&1 || true
 
   frontend:
     runs-on: ubuntu-latest
@@ -92,3 +122,53 @@ jobs:
         with:
           name: playwright-traces
           path: frontend/test-results/
+
+  # Rolling deploy: on green main only, build the three prod images, tag with
+  # :main-<sha> + :latest, push to the fleet registry (redclaw-web-01:5000 via
+  # its Tailscale IP — the fleet's daemons trust it in insecure-registries by
+  # IP, not by hostname). GW-04's clawmates-deploy.timer rolls forward within
+  # ~1 minute of the push. Skipped on PRs.
+  #
+  # `e2e` is intentionally NOT in `needs`: it launches its own postgres + dex
+  # via `docker run` on the host and then reaches them via 127.0.0.1, which
+  # fails from inside the act_runner container. Migrating e2e to a physical
+  # build node is a separate task; until then e2e is signal-only, not gating.
+  publish:
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    needs: [gates, rust, frontend]
+    env:
+      REGISTRY: 100.94.185.103:5000
+      NAMESPACE: clawmates
+    steps:
+      - uses: actions/checkout@v4
+      - name: Resolve short SHA
+        run: echo "SHA=${GITHUB_SHA::7}" >> "$GITHUB_ENV"
+      - name: Build images
+        run: |
+          set -euo pipefail
+          for svc in broker server frontend; do
+            docker build \
+              -t "${REGISTRY}/${NAMESPACE}/${svc}:main-${SHA}" \
+              -t "${REGISTRY}/${NAMESPACE}/${svc}:latest" \
+              -f "images/${svc}.Dockerfile" .
+          done
+      - name: Push images
+        run: |
+          set -euo pipefail
+          for svc in broker server frontend; do
+            docker push "${REGISTRY}/${NAMESPACE}/${svc}:main-${SHA}"
+            docker push "${REGISTRY}/${NAMESPACE}/${svc}:latest"
+          done
+      - name: Summary
+        run: |
+          {
+            echo "## Published images"
+            echo ""
+            for svc in broker server frontend; do
+              echo "- \`${REGISTRY}/${NAMESPACE}/${svc}:main-${SHA}\`"
+              echo "- \`${REGISTRY}/${NAMESPACE}/${svc}:latest\`"
+            done
+            echo ""
+            echo "GW-04 timer picks these up within ~1 minute."
+          } >> "$GITHUB_STEP_SUMMARY"

deploy/gw-04/clawmates-deploy.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=Clawmates rolling deploy (pull :latest, roll on drift)
+Wants=docker.service
+After=docker.service network-online.target
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/clawmates-deploy.sh
+StandardOutput=journal
+StandardError=journal
+Nice=10

deploy/gw-04/clawmates-deploy.sh

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+#
+# clawmates rolling deploy — polls the fleet registry for :latest of the three
+# prod images (broker, server, frontend). On drift, pulls the new image, retags
+# it under the un-prefixed name the running compose file uses, and rolls the
+# affected services with `docker compose up -d`.
+#
+# Install:
+#   sudo install -m 0755 clawmates-deploy.sh /usr/local/bin/clawmates-deploy.sh
+#   sudo install -m 0644 clawmates-deploy.service /etc/systemd/system/
+#   sudo install -m 0644 clawmates-deploy.timer   /etc/systemd/system/
+#   sudo systemctl daemon-reload
+#   sudo systemctl enable --now clawmates-deploy.timer
+#
+# Verify:
+#   systemctl list-timers clawmates-deploy.timer
+#   tail -f /var/log/clawmates-deploy.log
+#
+# The retag step (registry/clawmates/<svc>:latest → clawmates/<svc>:latest)
+# keeps the current /root/clawmates/docker-compose.yml working unchanged until
+# we're ready to migrate the compose file to registry-prefixed image names.
+
+set -euo pipefail
+
+REGISTRY="${REGISTRY:-100.94.185.103:5000}"
+NAMESPACE="${NAMESPACE:-clawmates}"
+COMPOSE_DIR="${COMPOSE_DIR:-/root/clawmates}"
+LOG="${LOG:-/var/log/clawmates-deploy.log}"
+SERVICES=(broker server frontend)
+
+log() { printf '%s %s\n' "$(date -Iseconds)" "$*" | tee -a "$LOG" >/dev/null; }
+
+changed=()
+for svc in "${SERVICES[@]}"; do
+  ref="${REGISTRY}/${NAMESPACE}/${svc}:latest"
+  local_ref="${NAMESPACE}/${svc}:latest"
+
+  before=$(docker inspect --format '{{.Id}}' "$ref" 2>/dev/null || echo "")
+  if ! docker pull -q "$ref" >/dev/null 2>&1; then
+    log "pull failed: $ref"
+    continue
+  fi
+  after=$(docker inspect --format '{{.Id}}' "$ref")
+
+  if [[ "$before" != "$after" ]]; then
+    log "new image for $svc: ${before:-<none>} -> $after"
+    changed+=("$svc")
+  fi
+
+  # Always keep the un-prefixed tag pointing at the fresh image, so a stale
+  # local retag can't wedge us.
+  docker tag "$ref" "$local_ref"
+done
+
+if [[ ${#changed[@]} -eq 0 ]]; then
+  exit 0
+fi
+
+log "rolling: ${changed[*]}"
+cd "$COMPOSE_DIR"
+docker compose up -d "${changed[@]}"
+log "roll complete: ${changed[*]}"

deploy/gw-04/clawmates-deploy.timer

@@ -0,0 +1,11 @@
+[Unit]
+Description=Clawmates rolling deploy — every minute
+
+[Timer]
+OnBootSec=2min
+OnUnitActiveSec=1min
+AccuracySec=15s
+Unit=clawmates-deploy.service
+
+[Install]
+WantedBy=timers.target