feat(ansible): add swapfile + resource_limits roles; add CoulombCore to inventory

T01: roles/swapfile — idempotent 4GB swapfile, vm.swappiness=10, fstab entry
T02: roles/resource_limits — PAM nproc caps (512/1024), systemd user-1000.slice
     memory limits (1500M/512M); templated per-host via host_vars
- inventory/host_vars/CoulombCore.yml — host-specific vars for both roles
- inventory/servers.yaml — add CoulombCore with id_ops SSH key
- inventory_from_yaml.py — load host_vars files into Ansible hostvars
- playbooks/bootstrap.yaml — include swapfile + resource_limits roles
- workplans/WP-0004 — flag T04/T09/T10 needs_human, add CoulombCore-local convergence note

Codifies manual INC-002 hardening. See RAIL-HO-WP-0004-T01/T02.

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

ansible/inventory/host_vars/CoulombCore.yml

@@ -0,0 +1,14 @@
+# Host-specific variables for CoulombCore (92.205.130.254)
+# k3s single-node cluster host — HostEurope
+
+# Swapfile (T01)
+swap_size_gb: 4
+swap_swappiness: 10
+
+# Resource limits (T02) — prevents runaway agents (see INC-002)
+resource_limit_user: tegwick
+resource_limit_uid: 1000
+nproc_soft: 512
+nproc_hard: 1024
+user_memory_max: "1500M"
+user_memory_swap_max: "512M"

ansible/inventory_from_yaml.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-import json, yaml, subprocess, os, sys, pathlib
+import json, yaml, subprocess, os, sys, pathlib, glob
 
 def load_servers():
     with open(os.path.join(os.path.dirname(__file__), '..', 'inventory', 'servers.yaml')) as f:
@@ -17,6 +17,15 @@ def load_tf_outputs():
     except Exception:
         return {}
 
+def load_host_vars(name):
+    """Load host_vars/<name>.yml if it exists."""
+    script_dir = os.path.dirname(__file__)
+    path = os.path.join(script_dir, '..', 'inventory', 'host_vars', f'{name}.yml')
+    if os.path.exists(path):
+        with open(path) as f:
+            return yaml.safe_load(f) or {}
+    return {}
+
 def main():
     server_list = load_servers()
     tf = load_tf_outputs()
@@ -25,10 +34,14 @@ def main():
     for s in server_list:
         name = s['name']
         host_names.append(name)
-        hostvars[name] = {
+        hvars = {
             "ansible_host": tf.get(name) or s.get('ip'),
-            "ansible_user": s.get('ssh_user', 'admin')
+            "ansible_user": s.get('ssh_user', 'admin'),
         }
+        if s.get('ssh_key'):
+            hvars["ansible_ssh_private_key_file"] = s['ssh_key']
+        hvars.update(load_host_vars(name))
+        hostvars[name] = hvars
     inv = {
         "all": {"hosts": host_names},
         "_meta": {"hostvars": hostvars}

ansible/playbooks/bootstrap.yaml

@@ -7,4 +7,6 @@
     - role: base
     - role: sops_agent
     - role: custodian_agent   # injects ~/.ssh/id_custodian_agent.pub into authorized_keys
+    - role: swapfile          # provisions swap file (size + swappiness from host_vars)
+    - role: resource_limits   # nproc PAM caps + systemd user slice memory limits
     # - role: wireguard   # enable if you configure WireGuard variables

ansible/roles/resource_limits/handlers/main.yml

@@ -0,0 +1,4 @@
+---
+- name: Reload systemd daemon
+  ansible.builtin.systemd:
+    daemon_reload: true

ansible/roles/resource_limits/tasks/main.yml

@@ -0,0 +1,35 @@
+---
+# resource_limits role — PAM nproc caps + systemd user slice memory limits
+#
+# Variables (set per-host in host_vars):
+#   resource_limit_user:         username to limit (default: tegwick)
+#   resource_limit_uid:          UID for systemd user slice (default: 1000)
+#   nproc_soft:                  soft nproc limit (default: 512)
+#   nproc_hard:                  hard nproc limit (default: 1024)
+#   user_memory_max:             systemd MemoryMax (default: 1500M)
+#   user_memory_swap_max:        systemd MemorySwapMax (default: 512M)
+
+- name: Set PAM nproc limits
+  ansible.builtin.template:
+    src: nproc-limits.conf.j2
+    dest: /etc/security/limits.d/60-nproc-{{ resource_limit_user | default('tegwick') }}.conf
+    owner: root
+    group: root
+    mode: '0644'
+
+- name: Ensure systemd user slice override directory
+  ansible.builtin.file:
+    path: "/etc/systemd/system/user-{{ resource_limit_uid | default(1000) }}.slice.d"
+    state: directory
+    owner: root
+    group: root
+    mode: '0755'
+
+- name: Set systemd user slice memory limits
+  ansible.builtin.template:
+    src: user-slice-limits.conf.j2
+    dest: "/etc/systemd/system/user-{{ resource_limit_uid | default(1000) }}.slice.d/limits.conf"
+    owner: root
+    group: root
+    mode: '0644'
+  notify: Reload systemd daemon

ansible/roles/resource_limits/templates/nproc-limits.conf.j2

@@ -0,0 +1,6 @@
+# Managed by Ansible (resource_limits role)
+# Caps process count for {{ resource_limit_user | default('tegwick') }}
+# to prevent runaway agents from exhausting the kernel PID table.
+# See INC-002 (2026-03-26) for root cause context.
+{{ resource_limit_user | default('tegwick') }} soft nproc {{ nproc_soft | default(512) }}
+{{ resource_limit_user | default('tegwick') }} hard nproc {{ nproc_hard | default(1024) }}

ansible/roles/resource_limits/templates/user-slice-limits.conf.j2

@@ -0,0 +1,7 @@
+# Managed by Ansible (resource_limits role)
+# Caps memory for all processes in the user-{{ resource_limit_uid | default(1000) }}.slice.
+# Prevents a single user's agent workload from OOM-killing the entire node.
+# See INC-002 (2026-03-26) for root cause context.
+[Slice]
+MemoryMax={{ user_memory_max | default('1500M') }}
+MemorySwapMax={{ user_memory_swap_max | default('512M') }}

ansible/roles/swapfile/tasks/main.yml

@@ -0,0 +1,59 @@
+---
+# swapfile role — provisions a swap file of configurable size
+#
+# Variables (set per-host in host_vars):
+#   swap_size_gb:    size in gigabytes (default: 4)
+#   swap_swappiness: vm.swappiness value (default: 10)
+
+- name: Check if swapfile exists with correct size
+  ansible.builtin.stat:
+    path: /swapfile
+  register: swapfile_stat
+
+- name: Allocate swapfile (fallocate)
+  ansible.builtin.command:
+    cmd: "fallocate -l {{ (swap_size_gb | default(4)) | int }}G /swapfile"
+    creates: /swapfile
+  when: not swapfile_stat.stat.exists
+
+- name: Set swapfile permissions
+  ansible.builtin.file:
+    path: /swapfile
+    owner: root
+    group: root
+    mode: '0600'
+
+- name: Format swapfile
+  ansible.builtin.command:
+    cmd: mkswap /swapfile
+  when: not swapfile_stat.stat.exists
+
+- name: Enable swapfile
+  ansible.builtin.command:
+    cmd: swapon /swapfile
+  when: not swapfile_stat.stat.exists
+  ignore_errors: true  # already active is not an error
+
+- name: Ensure swapfile in /etc/fstab
+  ansible.builtin.lineinfile:
+    path: /etc/fstab
+    regexp: '^/swapfile'
+    line: '/swapfile none swap sw 0 0'
+    state: present
+
+- name: Set vm.swappiness at runtime
+  ansible.posix.sysctl:
+    name: vm.swappiness
+    value: "{{ swap_swappiness | default(10) }}"
+    state: present
+    reload: true
+
+- name: Persist vm.swappiness across reboots
+  ansible.builtin.copy:
+    dest: /etc/sysctl.d/60-swappiness.conf
+    owner: root
+    group: root
+    mode: '0644'
+    content: |
+      # Managed by Ansible (swapfile role)
+      vm.swappiness = {{ swap_swappiness | default(10) }}