Fix scoped deployment state and config ownership

scripts/deploy-remote.sh

@@ -127,15 +127,29 @@ state_revision() {
 }
 
 state_status() {
-    local service="$1" line value
+    local service="$1" line value=pending
     if [[ -r "$STATE_DIR/$service" ]]; then
         while IFS= read -r line; do
             case "$line" in
                 status=*) value="${line#status=}" ;;
             esac
         done < "$STATE_DIR/$service"
-        printf '%s' "${value:-pending}"
     fi
+    printf '%s' "$value"
+}
+
+register_changed_services() {
+    local base="$1" service recorded status
+    [[ -n "$base" ]] || return 0
+    while IFS= read -r service; do
+        [[ -n "$service" ]] || continue
+        recorded="$(state_revision "$service")"
+        status="$(state_status "$service")"
+        if [[ "$status" != deployed || "$recorded" != "$REVISION" ]]; then
+            mark_status "$service" pending
+        fi
+    done < <(python3 scripts/deploy-plan.py --target "$TARGET" --repo "$REMOTE_DIR" \
+        --base "$base" --head "$REVISION")
 }
 
 add_changed_services() {
@@ -150,13 +164,19 @@ add_changed_services() {
 }
 
 add_pending_services() {
-    local service recorded changed
+    local service recorded status changed
     for state_file in "$STATE_DIR"/*; do
         [[ -f "$state_file" ]] || continue
         service="${state_file##*/}"
         recorded="$(state_revision "$service")"
+        status="$(state_status "$service")"
+        if [[ "$status" != deployed ]]; then
+            # A pending service was intentionally skipped or its handler
+            # failed. Retry it even when the checkout has not advanced.
+            SERVICES+=("$service")
+            continue
+        fi
         [[ -n "$recorded" && "$recorded" != "$REVISION" ]] || continue
-        [[ "$(state_status "$service")" != deployed ]] || continue
         if [[ "$TARGET" == dankclaw && "$service" == frank-default-small ]]; then continue; fi
         if [[ "$TARGET" == dankserver && "$service" == frank-default-large ]]; then continue; fi
         if ! changed="$(python3 scripts/deploy-plan.py --target "$TARGET" \
@@ -171,12 +191,24 @@ add_pending_services() {
     done
 }
 
-copy_shared_config() {
-    run_privileged mkdir -p /opt/searxng/config /opt/prometheus/config /opt/loki/config /opt/alloy/config
+copy_searxng_config() {
+    run_privileged mkdir -p /opt/searxng/config
     run_privileged cp shared/searxng/settings.yml /opt/searxng/config/settings.yml
     run_privileged cp shared/searxng/limiter.toml /opt/searxng/config/limiter.toml
+}
+
+copy_prometheus_config() {
+    run_privileged mkdir -p /opt/prometheus/config
     run_privileged cp shared/prometheus/prometheus.yml /opt/prometheus/config/prometheus.yml
+}
+
+copy_loki_config() {
+    run_privileged mkdir -p /opt/loki/config
     run_privileged cp shared/loki/loki-config.yaml /opt/loki/config/loki-config.yaml
+}
+
+copy_alloy_config() {
+    run_privileged mkdir -p /opt/alloy/config
     run_privileged cp shared/alloy/config.alloy /opt/alloy/config/config.alloy
 }
 
@@ -221,7 +253,6 @@ deploy_caddy() {
         echo "caddy is owned by dankclaw; refusing to deploy it on $TARGET" >&2
         return 2
     fi
-    copy_shared_config
     render_caddyfile
     deploy_homepage
     local cfhash oldhash image
@@ -285,6 +316,15 @@ deploy_compose_service() {
                 comfyui|loki|alloy)
                     build_compose_image "$service"
                     ;;
+                prometheus)
+                    copy_prometheus_config
+                    ;;
+                loki)
+                    copy_loki_config
+                    ;;
+                alloy)
+                    copy_alloy_config
+                    ;;
             esac
             podman-compose -f dankclaw/compose.yaml up -d --no-deps "$service"
             ;;
@@ -331,7 +371,7 @@ install_quadlet() {
 }
 
 deploy_searxng() {
-    copy_shared_config
+    copy_searxng_config
     install_quadlet searxng dankclaw/searxng/quadlet searxng
     install_quadlet searxng-valkey dankclaw/searxng/quadlet searxng-valkey
     install_quadlet gluetun dankclaw/searxng/quadlet gluetun
@@ -450,6 +490,12 @@ deploy_service() {
     esac
 }
 
+if [[ -n "$FROM_REVISION" ]]; then
+    # Register every changed service before applying the requested scope. This
+    # preserves an explicit --service selection as pending work for the next
+    # ordinary deployment.
+    register_changed_services "$FROM_REVISION"
+fi
 if [[ "$PENDING" -eq 1 ]]; then
     add_changed_services "$FROM_REVISION"
     add_pending_services

scripts/deploy.sh

@@ -208,7 +208,8 @@ if [[ "$NEW_REVISION" != "$EXPECTED_REVISION" ]]; then
     echo "FAIL: target checkout is $NEW_REVISION, expected $EXPECTED_REVISION" >&2
     exit 1
 fi
-exec ./scripts/deploy-remote.sh "$TARGET" "$NEW_REVISION" "$@"
+exec ./scripts/deploy-remote.sh "$TARGET" "$NEW_REVISION" "$@" \
+    --from-revision "$OLD_REVISION"
 REMOTE_EOF
 
 echo "=== Deploy complete: $TARGET ==="

tests/deployment_scoping.bats

@@ -110,6 +110,15 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
     [ "$status" -eq 2 ]
 }
 
+@test "remote runner recognizes a pending service at the same revision" {
+    local state_dir="$(mktemp -d)"
+    printf 'revision=%s\nstatus=pending\n' "$(git rev-parse HEAD)" > "$state_dir/unknown-service"
+    run env DEPLOY_STATE_DIR="$state_dir" REMOTE_DIR="$REPO_ROOT" \
+        bash "$REMOTE_DEPLOY" dankclaw "$(git rev-parse HEAD)" --pending
+    [ "$status" -eq 2 ]
+    [[ "$output" == *"unknown-service"* || "$output" == *"not deployed"* ]]
+}
+
 @test "top-level deployer delegates to the service-scoped remote runner" {
     grep -q 'deploy-remote.sh' "$REPO_ROOT/scripts/deploy.sh"
     grep -qE 'SERVICE|service' "$REPO_ROOT/scripts/deploy.sh"