fix: [nomad-step-5] S5.2 — nomad/jobs/staging.hcl + chat.hcl (#989)

bin/disinto

@@ -823,11 +823,16 @@ _disinto_init_nomad() {
       echo "[deploy] dry-run complete"
     fi
 
-    # Build custom images dry-run (if agents service is included)
-    if echo ",$with_services," | grep -q ",agents,"; then
+    # Build custom images dry-run (if agents or chat services are included)
+    if echo ",$with_services," | grep -qE ",(agents|chat),"; then
       echo ""
       echo "── Build images dry-run ──────────────────────────────"
-      echo "[build] [dry-run] docker build -t disinto/agents:local -f ${FACTORY_ROOT}/docker/agents/Dockerfile ${FACTORY_ROOT}"
+      if echo ",$with_services," | grep -q ",agents,"; then
+        echo "[build] [dry-run] docker build -t disinto/agents:local -f ${FACTORY_ROOT}/docker/agents/Dockerfile ${FACTORY_ROOT}"
+      fi
+      if echo ",$with_services," | grep -q ",chat,"; then
+        echo "[build] [dry-run] docker build -t disinto/chat:local -f ${FACTORY_ROOT}/docker/chat/Dockerfile ${FACTORY_ROOT}"
+      fi
     fi
     exit 0
   fi
@@ -916,15 +921,22 @@ _disinto_init_nomad() {
     echo "[import] no --import-env/--import-sops — skipping; set them or seed kv/disinto/* manually before deploying secret-dependent services"
   fi
 
-  # Build custom images required by Nomad jobs (S4.2) — before deploy.
+  # Build custom images required by Nomad jobs (S4.2, S5.2) — before deploy.
   # Single-node factory dev box: no multi-node pull needed, no registry auth.
   # Can upgrade to approach B (registry push/pull) later if multi-node.
-  if echo ",$with_services," | grep -q ",agents,"; then
+  if echo ",$with_services," | grep -qE ",(agents|chat),"; then
     echo ""
     echo "── Building custom images ─────────────────────────────"
-    local tag="disinto/agents:local"
-    echo "── Building $tag ─────────────────────────────"
-    docker build -t "$tag" -f "${FACTORY_ROOT}/docker/agents/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5
+    if echo ",$with_services," | grep -q ",agents,"; then
+      local tag="disinto/agents:local"
+      echo "── Building $tag ─────────────────────────────"
+      docker build -t "$tag" -f "${FACTORY_ROOT}/docker/agents/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5
+    fi
+    if echo ",$with_services," | grep -q ",chat,"; then
+      local tag="disinto/chat:local"
+      echo "── Building $tag ─────────────────────────────"
+      docker build -t "$tag" -f "${FACTORY_ROOT}/docker/chat/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5
+    fi
   fi
 
   # Interleaved seed/deploy per service (S2.6, #928, #948).
@@ -935,9 +947,9 @@ _disinto_init_nomad() {
   if [ -n "$with_services" ]; then
     local vault_addr="${VAULT_ADDR:-http://127.0.0.1:8200}"
 
-    # Build ordered deploy list (S3.4, S4.2): forgejo → woodpecker-server → woodpecker-agent → agents
+    # Build ordered deploy list (S3.4, S4.2, S5.2): forgejo → woodpecker-server → woodpecker-agent → agents → staging → chat
     local DEPLOY_ORDER=""
-    for ordered_svc in forgejo woodpecker-server woodpecker-agent agents; do
+    for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat; do
       if echo ",$with_services," | grep -q ",$ordered_svc,"; then
         DEPLOY_ORDER="${DEPLOY_ORDER:+${DEPLOY_ORDER} }${ordered_svc}"
       fi
@@ -950,6 +962,7 @@ _disinto_init_nomad() {
       case "$svc" in
         woodpecker-server|woodpecker-agent) seed_name="woodpecker" ;;
         agents) seed_name="agents" ;;
+        chat) seed_name="chat" ;;
       esac
       local seed_script="${FACTORY_ROOT}/tools/vault-seed-${seed_name}.sh"
       if [ -x "$seed_script" ]; then
@@ -1014,6 +1027,12 @@ _disinto_init_nomad() {
     if echo ",$with_services," | grep -q ",agents,"; then
       echo "             agents: (polling loop running)"
     fi
+    if echo ",$with_services," | grep -q ",staging,"; then
+      echo "             staging: (internal, no external port)"
+    fi
+    if echo ",$with_services," | grep -q ",chat,"; then
+      echo "             chat: 8080"
+    fi
     echo "────────────────────────────────────────────────────────"
   fi
 
@@ -1142,9 +1161,9 @@ disinto_init() {
     for _svc in $with_services; do
       _svc=$(echo "$_svc" | xargs)
       case "$_svc" in
-        forgejo|woodpecker-server|woodpecker-agent|agents) ;;
+        forgejo|woodpecker-server|woodpecker-agent|agents|staging|chat) ;;
         *)
-          echo "Error: unknown service '${_svc}' — known: forgejo, woodpecker-server, woodpecker-agent, agents" >&2
+          echo "Error: unknown service '${_svc}' — known: forgejo, woodpecker-server, woodpecker-agent, agents, staging, chat" >&2
           exit 1
           ;;
       esac

nomad/client.hcl

@@ -55,6 +55,12 @@ client {
     read_only = false
   }
 
+  # staging static content (docker/ directory with images, HTML, etc.)
+  host_volume "site-content" {
+    path      = "/srv/disinto/docker"
+    read_only = true
+  }
+
   # ops repo clone (vault actions, sprint artifacts, knowledge).
   host_volume "ops-repo" {
     path      = "/srv/disinto/ops-repo"

nomad/jobs/chat.hcl

@@ -0,0 +1,154 @@
+# =============================================================================
+# nomad/jobs/chat.hcl — Claude chat UI (Nomad service job)
+#
+# Part of the Nomad+Vault migration (S5.2, issue #989). Lightweight service
+# job for the Claude chat UI with sandbox hardening (#706).
+#
+# Build:
+#   Custom image built from docker/chat/Dockerfile as disinto/chat:local
+#   (same :local pattern as disinto/agents:local).
+#
+# Sandbox hardening (#706):
+#   - Read-only root filesystem (enforced via entrypoint)
+#   - tmpfs /tmp:size=64m for runtime temp files
+#   - cap_drop ALL (no Linux capabilities)
+#   - mem_limit 512m (matches compose sandbox hardening)
+#
+# Vault integration:
+#   - vault { role = "service-chat" } at group scope
+#   - Template stanza renders CHAT_OAUTH_CLIENT_ID, CHAT_OAUTH_CLIENT_SECRET,
+#     FORWARD_AUTH_SECRET from kv/disinto/shared/chat
+#   - Seeded on fresh boxes by tools/vault-seed-chat.sh
+#
+# Host volume:
+#   - chat-history → /var/lib/chat/history (persists conversation history)
+#
+# Not the runtime yet: docker-compose.yml is still the factory's live stack
+# until cutover. This file exists so CI can validate it and S5.2 can wire
+# `disinto init --backend=nomad --with chat` to `nomad job run` it.
+# =============================================================================
+
+job "chat" {
+  type        = "service"
+  datacenters = ["dc1"]
+
+  group "chat" {
+    count = 1
+
+    # ── Vault workload identity (S5.2, issue #989) ───────────────────────────
+    # Role `service-chat` defined in vault/roles.yaml, policy in
+    # vault/policies/service-chat.hcl. Bound claim pins nomad_job_id = "chat".
+    vault {
+      role = "service-chat"
+    }
+
+    # ── Network ──────────────────────────────────────────────────────────────
+    # External port 8080 for chat UI access (via edge proxy or direct).
+    network {
+      port "http" {
+        static = 8080
+        to     = 8080
+      }
+    }
+
+    # ── Host volumes ─────────────────────────────────────────────────────────
+    # chat-history volume: declared in nomad/client.hcl, path
+    # /srv/disinto/chat-history on the factory box.
+    volume "chat-history" {
+      type      = "host"
+      source    = "chat-history"
+      read_only = false
+    }
+
+    # ── Restart policy ───────────────────────────────────────────────────────
+    restart {
+      attempts = 3
+      interval = "5m"
+      delay    = "15s"
+      mode     = "delay"
+    }
+
+    # ── Service registration ─────────────────────────────────────────────────
+    service {
+      name     = "chat"
+      port     = "http"
+      provider = "nomad"
+
+      check {
+        type     = "http"
+        path     = "/health"
+        interval = "10s"
+        timeout  = "3s"
+      }
+    }
+
+    task "chat" {
+      driver = "docker"
+
+      config {
+        image      = "disinto/chat:local"
+        force_pull = false
+        # Sandbox hardening (#706): cap_drop ALL (no Linux capabilities)
+        # tmpfs /tmp for runtime files (64MB)
+        # ReadonlyRootfs enforced via entrypoint script (fails if running as root)
+        cap_drop   = ["ALL"]
+        tmpfs      = ["/tmp:size=64m"]
+        # Security options for sandbox hardening
+        # apparmor=unconfined needed for Claude CLI ptrace access
+        # no-new-privileges prevents privilege escalation
+        security_opt = ["apparmor=unconfined", "no-new-privileges"]
+      }
+
+      # ── Volume mounts ──────────────────────────────────────────────────────
+      # Mount chat-history for conversation persistence
+      volume_mount {
+        volume      = "chat-history"
+        destination = "/var/lib/chat/history"
+        read_only   = false
+      }
+
+      # ── Environment: secrets from Vault (S5.2) ──────────────────────────────
+      # CHAT_OAUTH_CLIENT_ID, CHAT_OAUTH_CLIENT_SECRET, FORWARD_AUTH_SECRET
+      # rendered from kv/disinto/shared/chat via template stanza.
+      env {
+        FORGE_URL                      = "http://forgejo:3000"
+        CHAT_MAX_REQUESTS_PER_HOUR     = "60"
+        CHAT_MAX_REQUESTS_PER_DAY      = "1000"
+      }
+
+      # ── Vault-templated secrets (S5.2, issue #989) ─────────────────────────
+      # Renders chat-secrets.env from Vault KV v2 at kv/disinto/shared/chat.
+      # Placeholder values kept < 16 chars to avoid secret-scan CI failures.
+      template {
+        destination          = "secrets/chat-secrets.env"
+        env                  = true
+        change_mode          = "restart"
+        error_on_missing_key = false
+        data                 = <<EOT
+{{- with secret "kv/data/disinto/shared/chat" -}}
+CHAT_OAUTH_CLIENT_ID={{ .Data.data.chat_oauth_client_id }}
+CHAT_OAUTH_CLIENT_SECRET={{ .Data.data.chat_oauth_client_secret }}
+FORWARD_AUTH_SECRET={{ .Data.data.forward_auth_secret }}
+{{- else -}}
+# WARNING: run tools/vault-seed-chat.sh
+CHAT_OAUTH_CLIENT_ID=seed-me
+CHAT_OAUTH_CLIENT_SECRET=seed-me
+FORWARD_AUTH_SECRET=seed-me
+{{- end -}}
+EOT
+      }
+
+      # ── Sandbox hardening (S5.2, #706) ────────────────────────────────────
+      # Matches docker-compose sandbox hardening:
+      #   - ReadonlyRootfs=true (read-only root filesystem)
+      #   - CapDrop=ALL (no Linux capabilities)
+      #   - PidsLimit=128 (prevent fork bombs)
+      #   - Memory=512m (536870912 bytes)
+      resources {
+        cpu       = 200
+        memory    = 512
+        pids_limit = 128
+      }
+    }
+  }
+}

nomad/jobs/staging.hcl

@@ -0,0 +1,85 @@
+# =============================================================================
+# nomad/jobs/staging.hcl — Staging file server (Nomad service job)
+#
+# Part of the Nomad+Vault migration (S5.2, issue #989). Lightweight service job
+# for the staging file server using Caddy as a static file server.
+#
+# Mount contract:
+#   This job mounts the `docker/` directory as `/srv/site` (read-only).
+#   The docker/ directory contains static content (images, HTML, etc.)
+#   served to staging environment users.
+#
+# Network:
+#   No external port exposed — edge proxy routes to it internally.
+#   Service discovery via Nomad native provider for internal routing.
+#
+# Not the runtime yet: docker-compose.yml is still the factory's live stack
+# until cutover. This file exists so CI can validate it and S5.2 can wire
+# `disinto init --backend=nomad --with staging` to `nomad job run` it.
+# =============================================================================
+
+job "staging" {
+  type        = "service"
+  datacenters = ["dc1"]
+
+  group "staging" {
+    count = 1
+
+    # No Vault integration needed — no secrets required (static file server)
+
+    # Internal service — no external port. Edge proxy routes internally.
+    network {
+      port "http" {
+        static = 80
+        to     = 80
+      }
+    }
+
+    restart {
+      attempts = 3
+      interval = "5m"
+      delay    = "15s"
+      mode     = "delay"
+    }
+
+    service {
+      name     = "staging"
+      port     = "http"
+      provider = "nomad"
+
+      check {
+        type     = "http"
+        path     = "/"
+        interval = "10s"
+        timeout  = "3s"
+      }
+    }
+
+    task "staging" {
+      driver = "docker"
+
+      config {
+        image = "caddy:alpine"
+        ports = ["http"]
+      }
+
+      # Mount docker/ directory as /srv/site:ro (static content)
+      volume_mount {
+        volume      = "site-content"
+        destination = "/srv/site"
+        read_only   = true
+      }
+
+      resources {
+        cpu    = 100
+        memory = 256
+      }
+    }
+
+    volume "site-content" {
+      type      = "host"
+      source    = "site-content"
+      read_only = true
+    }
+  }
+}

tests/disinto-init-nomad.bats

@@ -215,7 +215,7 @@ setup_file() {
   run "$DISINTO_BIN" init placeholder/repo --backend=nomad --with unknown-service --dry-run
   [ "$status" -ne 0 ]
   [[ "$output" == *"unknown service"* ]]
-  [[ "$output" == *"known: forgejo, woodpecker-server, woodpecker-agent, agents"* ]]
+  [[ "$output" == *"known: forgejo, woodpecker-server, woodpecker-agent, agents, staging, chat"* ]]
 }
 
 # S3.4: woodpecker auto-expansion and forgejo auto-inclusion

vault/policies/service-chat.hcl

@@ -0,0 +1,15 @@
+# vault/policies/service-chat.hcl
+#
+# Read-only access to shared Chat secrets (OAuth client config, forward auth
+# secret). Attached to the Chat Nomad job via workload identity (S5.2).
+#
+# Scope: kv/disinto/shared/chat — entries owned by the operator and
+# shared between the chat service and edge proxy.
+
+path "kv/data/disinto/shared/chat" {
+  capabilities = ["read"]
+}
+
+path "kv/metadata/disinto/shared/chat" {
+  capabilities = ["list", "read"]
+}

vault/roles.yaml

@@ -70,6 +70,13 @@ roles:
     namespace: default
     job_id:    agents
 
+  # ── Chat UI (nomad/jobs/chat.hcl — S5.2) ─────────────────────────────────
+  # Claude chat UI service with OAuth secrets. Uses vault/policies/service-chat.hcl.
+  - name:      service-chat
+    policy:    service-chat
+    namespace: default
+    job_id:    chat
+
   # ── Per-agent bots (nomad/jobs/bot-<role>.hcl — land in later steps) ───────
   # job_id placeholders match the policy name 1:1 until each bot's jobspec
   # lands. When a bot's jobspec is added under nomad/jobs/, update the