From 998d0b0fcab6e5ce8788e36ad44b0163214ce426 Mon Sep 17 00:00:00 2001
From: Local Dev <dev@localhost>
Date: Fri, 9 Oct 2026 21:58:56 +0200
Subject: [PATCH] =?UTF-8?q?prometheus:=20add=20ClamAV=20sidecar=20?=
 =?UTF-8?q?=E2=80=94=20real=20uploads=20can=20scan=20now?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before this: service's /healthz always 503'd and the upload endpoint
rejected every submission with scan verdict=error, because clamd was not
installed anywhere reachable. Service worked for the seeded browse view
but no publisher could POST a listing.

Now: a `clamav` sibling container runs the official clamav/clamav:stable
image on an internal docker network only Prometheus can reach. The
Prometheus service connects via CLAMD_HOST=clamav. Signatures live in a
dedicated volume so restarts reuse the ~250 MB freshclam downloaded on
first start.

Two networks on the Prometheus container now:
  prometheus-internal   bridge, service + clamav only; clamd never exposed
  hephaestus            external hephaestus_default, so Hephaestus's Caddy
                        continues to route prometheus.x → prometheus:3700

depends_on with condition=service_healthy means Prometheus waits for
clamd's healthcheck to pass before starting. clamav's start_period is
5 min to accommodate the signature download; the healthcheck itself
is clamdcheck.sh / clamdscan --ping with a 10s timeout per probe.

Deploy on the VPS:
  cd ~/prometheus && git pull && cd deploy
  docker compose pull clamav   # first time, 500+ MB
  docker compose up -d         # Prometheus will wait for clamav healthy
---
 deploy/docker-compose.yml | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/deploy/docker-compose.yml b/deploy/docker-compose.yml
index e02cdf0..bb25e44 100644
--- a/deploy/docker-compose.yml
+++ b/deploy/docker-compose.yml
@@ -19,8 +19,13 @@ services:
       dockerfile: deploy/Dockerfile
     image: prometheus:latest
     restart: unless-stopped
+    depends_on:
+      clamav:
+        condition: service_healthy
     environment:
       BNS_NETWORK: chipnet
+      CLAMD_HOST: clamav
+      CLAMD_PORT: "3310"
       ADMIN_PUBLISHER: ${ADMIN_PUBLISHER:-}
       VIRUSTOTAL_API_KEY: ${VIRUSTOTAL_API_KEY:-}
       PAYMENT_REQUIRED: ${PAYMENT_REQUIRED:-}
@@ -30,6 +35,7 @@ services:
     volumes:
       - data:/data
     networks:
+      - prometheus-internal
       - hephaestus
     expose:
       - "3700"
@@ -38,12 +44,39 @@ services:
       interval: 30s
       timeout: 5s
       retries: 3
-      start_period: 10s
+      start_period: 60s
+
+  # ClamAV runs as a sibling container on an internal network — only
+  # Prometheus can reach it. First start downloads ~250 MB of signatures via
+  # freshclam into a volume; subsequent starts reuse it.
+  clamav:
+    image: clamav/clamav:stable
+    restart: unless-stopped
+    environment:
+      CLAMAV_NO_MILTERD: "true"
+    volumes:
+      - clamav-sigs:/var/lib/clamav
+    networks:
+      - prometheus-internal
+    expose:
+      - "3310"
+    healthcheck:
+      test: ["CMD-SHELL", "clamdcheck.sh || clamdscan --ping 2>/dev/null || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 10
+      # Signature download on first start can take a few minutes.
+      start_period: 5m
 
 volumes:
   data:
+  clamav-sigs:
 
 networks:
+  # Internal: only Prometheus + clamav. Clamd never exposed off this network.
+  prometheus-internal:
+    driver: bridge
+  # External: shared with Hephaestus so its Caddy can route prometheus.x.
   hephaestus:
     external: true
     name: hephaestus_default