observability: fix alloy ui component, busybox healthchecks for loki/alloy

- alloy 1.x renamed the server component to ui; the old block failed the
  initial load and the container crash-looped
- grafana/loki is distroless and grafana/alloy lacks wget, so their
  healthchecks could never run; local images add a static busybox from
  alpine for that one command
- deploy.sh builds all three local images if missing
- tests: 3 new seams

dankclaw/alloy/Containerfile

@@ -0,0 +1,15 @@
+# Alloy + a static busybox.
+#
+# grafana/alloy has a shell but no wget/curl, so the compose healthcheck
+# cannot run anything inside the container. This image drops a static
+# busybox into it for the healthcheck command only. All Alloy behavior is
+# unchanged.
+#
+# Build on dankclaw:
+#   podman build -t franksdank/alloy:latest -f dankclaw/alloy/Containerfile .
+
+FROM docker.io/library/alpine:latest AS tools
+# busybox provides wget for the healthcheck.
+
+FROM docker.io/grafana/alloy:latest
+COPY --from=tools /bin/busybox /usr/local/bin/busybox

dankclaw/compose.yaml

@@ -149,7 +149,8 @@ services:
       retries: 3
 
   loki:
-    image: docker.io/grafana/loki:latest
+    # Local build: grafana/loki + static busybox (healthcheck).
+    image: franksdank/loki:latest
     container_name: loki
     restart: unless-stopped
     # Rootless: container root maps to the invoking user (dank), which
@@ -163,13 +164,14 @@ services:
       - /opt/loki/config:/etc/loki
       - /opt/loki/data:/loki
     healthcheck:
-      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3100/ready"]
+      test: ["CMD", "/usr/local/bin/busybox", "wget", "--spider", "-q", "http://localhost:3100/ready"]
       interval: 30s
       timeout: 10s
       retries: 3
 
   alloy:
-    image: docker.io/grafana/alloy:latest
+    # Local build: grafana/alloy + static busybox (healthcheck).
+    image: franksdank/alloy:latest
     container_name: alloy
     restart: unless-stopped
     volumes:
@@ -180,7 +182,7 @@ services:
     depends_on:
       - loki
     healthcheck:
-      test: ["CMD", "wget", "--spider", "-q", "http://localhost:12345/-/healthy"]
+      test: ["CMD", "/usr/local/bin/busybox", "wget", "--spider", "-q", "http://localhost:12345/-/healthy"]
       interval: 30s
       timeout: 10s
       retries: 3

dankclaw/loki/Containerfile

@@ -0,0 +1,15 @@
+# Loki + a static busybox.
+#
+# grafana/loki is distroless: no shell, no wget, so the compose healthcheck
+# cannot run anything inside the container. This image drops a static
+# busybox into it for the healthcheck command only. All Loki behavior is
+# unchanged.
+#
+# Build on dankclaw:
+#   podman build -t franksdank/loki:latest -f dankclaw/loki/Containerfile .
+
+FROM docker.io/library/alpine:latest AS tools
+# busybox provides wget for the healthcheck.
+
+FROM docker.io/grafana/loki:latest
+COPY --from=tools /bin/busybox /usr/local/bin/busybox

scripts/deploy.sh

@@ -139,10 +139,16 @@ fi
 
 if [ '${COMPOSE_UP[$TARGET]}' = '1' ]; then
   echo '[4/4] Restarting stack...'
-  if ! podman image exists franksdank/caddy-porkbun:latest; then
-    echo '  franksdank/caddy-porkbun image missing; building it (a few minutes)...'
-    podman build -t franksdank/caddy-porkbun:latest -f dankclaw/caddy/Containerfile .
-  fi
+  # Locally built images: caddy + porkbun module, and loki/alloy + a static
+  # busybox (their upstream images lack the wget the healthchecks need).
+  for dir in caddy loki alloy; do
+    img=franksdank/$dir
+    [ "$dir" = "caddy" ] && img=franksdank/caddy-porkbun
+    if ! podman image exists $img:latest; then
+      echo "  $img image missing; building it..."
+      podman build -t $img:latest -f dankclaw/$dir/Containerfile .
+    fi
+  done
   podman-compose -f '${COMPOSE[$TARGET]}' up -d
 else
   echo '[4/4] Skipping compose restart (stack runs as bare containers on this host)'

shared/alloy/config.alloy

@@ -6,9 +6,10 @@ logging {
 }
 
 // Local listener so the container healthcheck can probe us.
-server {
-  http_listen_addr = "0.0.0.0:12345"
-  grpc_listen_addr = "0.0.0.0:12346"
+// Alloy >= 1.0 renamed the server component to ui.
+ui {
+  host = "0.0.0.0"
+  port = 12345
 }
 
 // Ship logs to Loki (container name on the podman network).

tests/caddyfile.bats

@@ -136,3 +136,29 @@ CADDYFILE="$REPO_ROOT/dankclaw/Caddyfile"
         }
     done
 }
+
+# --- distroless healthchecks (loki/alloy carry a static busybox) ---
+
+@test "loki and alloy run from local images carrying a static busybox" {
+    local compose="$REPO_ROOT/dankclaw/compose.yaml"
+    grep -q 'image: franksdank/loki:latest' "$compose" || { echo "loki image not local"; return 1; }
+    grep -q 'image: franksdank/alloy:latest' "$compose" || { echo "alloy image not local"; return 1; }
+    local img
+    for img in loki alloy; do
+        local cf="$REPO_ROOT/dankclaw/$img/Containerfile"
+        [ -f "$cf" ] || { echo "missing $cf"; return 1; }
+        grep -q 'busybox' "$cf" || { echo "$cf does not install busybox"; return 1; }
+    done
+}
+
+@test "loki and alloy healthchecks use the busybox wget" {
+    local compose="$REPO_ROOT/dankclaw/compose.yaml"
+    local n
+    n=$(grep -c '/usr/local/bin/busybox' "$compose")
+    [ "$n" -ge 2 ] || { echo "expected >=2 busybox healthchecks, found $n"; return 1; }
+}
+
+@test "alloy config uses the ui component (the server component was renamed)" {
+    grep -qE '^ui \{' "$REPO_ROOT/shared/alloy/config.alloy"
+    ! grep -qE '^server \{' "$REPO_ROOT/shared/alloy/config.alloy"
+}