fix(deploy): inventory-aware orchestration and correct override paths

- orchestrate-deploy.sh: read nodes from inventory/topology.yaml instead of hardcoded list
- orchestrate-deploy.sh: LTE nodes (chelsty-infra, chelsty-ha) use ConnectTimeout=30, non-fatal on failure
- deploy-node.sh: service discovery falls back to services.yaml if no services.txt
- deploy-node.sh: override path corrected to hosts/<node>/runtime/<service>/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

scripts/deploy/deploy-node.sh

@@ -8,6 +8,7 @@ set -e
 REPO_PATH="${HOME}/homelab-codex-ws"
 RUNTIME_PATH="/opt/homelab"
 HOSTNAME=$(hostname | tr '[:lower:]' '[:upper:]')
+HOST_DIR="${REPO_PATH}/hosts/$(hostname | tr '[:upper:]' '[:lower:]')"
 
 echo "--- Starting Deployment on ${HOSTNAME} ---"
 
@@ -22,20 +23,33 @@ echo "Pulling latest changes..."
 git pull
 
 # 2. Identify Services
-# Based on our convention, we look for services assigned to this host
-# For now, we'll check if a 'services.txt' exists in the host folder
-SERVICE_LIST="${REPO_PATH}/hosts/$(hostname | tr '[:upper:]' '[:lower:]')/services.txt"
+SERVICES=()
+if [ -f "${HOST_DIR}/services.txt" ]; then
+    mapfile -t SERVICES < <(grep -v '^\s*#' "${HOST_DIR}/services.txt" | grep -v '^\s*$')
+elif [ -f "${HOST_DIR}/services.yaml" ]; then
+    SERVICES=($(python3 -c "
+import yaml, sys
+try:
+    with open('${HOST_DIR}/services.yaml', 'r') as f:
+        data = yaml.safe_load(f)
+        if data and 'services' in data:
+            if isinstance(data['services'], dict):
+                print(' '.join(data['services'].keys()))
+            elif isinstance(data['services'], list):
+                print(' '.join(data['services']))
+except Exception as e:
+    print(f'Error parsing YAML: {e}', file=sys.stderr)
+    sys.exit(1)
+"))
+fi
 
-if [ ! -f "$SERVICE_LIST" ]; then
-    echo "No services.txt found for ${HOSTNAME}. Skipping service deployment."
+if [ ${#SERVICES[@]} -eq 0 ]; then
+    echo "No services found for ${HOSTNAME}. Skipping service deployment."
     exit 0
 fi
 
 # 3. Deploy Services
-while IFS= read -r service || [ -n "$service" ]; do
-    [[ "$service" =~ ^#.*$ ]] && continue # Skip comments
-    [[ -z "$service" ]] && continue      # Skip empty lines
-
+for service in "${SERVICES[@]}"; do
     echo "Deploying service: ${service}..."
 
     COMPOSE_FILE="${REPO_PATH}/services/${service}/docker-compose.yml"
@@ -45,13 +59,10 @@ while IFS= read -r service || [ -n "$service" ]; do
         continue
     fi
 
-    # Target directory in runtime
     TARGET_DIR="${RUNTIME_PATH}/services/${service}"
     mkdir -p "$TARGET_DIR"
 
-    # We use the compose file from the repo directly
-    # but we can also handle overrides here
-    OVERRIDE_FILE="${RUNTIME_PATH}/config/${service}/docker-compose.override.yml"
+    OVERRIDE_FILE="${HOST_DIR}/runtime/${service}/docker-compose.override.yml"
 
     COMPOSE_CMD="docker compose -f ${COMPOSE_FILE}"
     if [ -f "$OVERRIDE_FILE" ]; then
@@ -60,7 +71,6 @@ while IFS= read -r service || [ -n "$service" ]; do
     fi
 
     $COMPOSE_CMD up -d --remove-orphans
-
-done < "$SERVICE_LIST"
+done
 
 echo "--- Deployment Complete ---"

scripts/deploy/orchestrate-deploy.sh

@@ -1,15 +1,30 @@
 #!/usr/bin/env bash
 # orchestrate-deploy.sh - To be run on SATURN
-# Triggers deployment on remote execution nodes.
+# Triggers deployment on remote execution nodes via inventory.
 
 set -e
 
-HOSTS=("solaria" "piha" "vps")
-USER="oskar" # Default user
+REPO_PATH="${HOME}/homelab-codex-ws"
+USER="oskar"
 
-for HOST in "${HOSTS[@]}"; do
+while IFS=' ' read -r HOST TAG; do
     echo ">>> Triggering deployment on ${HOST}..."
+    if [[ "$TAG" == "lte" ]]; then
+        ssh -o ConnectTimeout=30 "${USER}@${HOST}" "bash ~/homelab-codex-ws/scripts/deploy/deploy-node.sh" || \
+            echo "WARNING: Deployment on ${HOST} failed or timed out (LTE/intermittent node, skipping)"
+    else
         ssh "${USER}@${HOST}" "bash ~/homelab-codex-ws/scripts/deploy/deploy-node.sh"
-done
+    fi
+done < <(python3 -c "
+import yaml, sys
+with open('${REPO_PATH}/inventory/topology.yaml') as f:
+    data = yaml.safe_load(f)
+skip = {'saturn', 'solaria'}
+for name, info in (data.get('nodes') or {}).items():
+    if name in skip:
+        continue
+    uplink = ((info or {}).get('connectivity') or {}).get('uplink', '')
+    print(name, 'lte' if uplink == 'lte' else 'standard')
+")
 
 echo ">>> All deployments triggered."