Files
homelab/ansible/roles/llm-inference-multimodel/tasks/firewall.yml
2026-08-05 15:53:31 -05:00

65 lines
2.8 KiB
YAML

---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/tasks/firewall.yml
# DESCRIPTION: Phase 3 — scope :8001 (new) and reconsider :8000 (existing
# pattern) exposure, per plan §5.
#
# Current baseline pattern (0.0.0.0:8000, no auth) is a
# pre-existing flagged issue — this role does NOT repeat it
# uncritically for the new port, and tightens both:
# 1. Bind address: handled in systemd.yml templates via
# {{ llm_bind_address }} (default 10.1.71.130, NOT 0.0.0.0).
# 2. Firewall: ufw rules scoping both ports to
# {{ llm_allowed_source_cidr }} rather than open LAN-wide.
#
# Idempotent: named rule comments + `state: present` so reruns
# don't duplicate rules (per plan §4 idempotency note).
# ------------------------------------------------------------------------------
- name: Check whether ufw is installed/active
ansible.builtin.command:
cmd: ufw status
register: llm_ufw_status
changed_when: false
failed_when: false
become: true
- name: WARNING — ufw not active, firewall scoping cannot be applied
ansible.builtin.debug:
msg: >-
ufw does not appear to be active on this host (`ufw status` returned:
{{ llm_ufw_status.stdout | default('n/a') }}). Firewall scoping for
ports {{ llm_aux_port }}/{{ llm_toolcall_port }} was skipped. This is a
gap vs plan §5 item 2 — flag to Ryan before relying on bind-address
alone for exposure control.
when: "'Status: active' not in (llm_ufw_status.stdout | default(''))"
- name: Allow aux port ({{ llm_aux_port }}) from the Hermes source subnet
community.general.ufw:
rule: allow
port: "{{ llm_aux_port | string }}"
proto: tcp
src: "{{ llm_allowed_source_cidr }}"
comment: "llm-inference-multimodel: aux (Phi-4) — scoped to Hermes subnet"
become: true
when: "'Status: active' in (llm_ufw_status.stdout | default(''))"
- name: Allow tool-calling port ({{ llm_toolcall_port }}) from the Hermes source subnet
community.general.ufw:
rule: allow
port: "{{ llm_toolcall_port | string }}"
proto: tcp
src: "{{ llm_allowed_source_cidr }}"
comment: "llm-inference-multimodel: toolcall (Mistral-Small) — scoped to Hermes subnet"
become: true
when: "'Status: active' in (llm_ufw_status.stdout | default(''))"
- name: Report firewall scoping applied
ansible.builtin.debug:
msg: >-
Firewall scoping applied for ports {{ llm_aux_port }} and
{{ llm_toolcall_port }}, restricted to source {{ llm_allowed_source_cidr }}.
Reverse-proxy + API-key enforcement (plan §5 item 3) is NOT implemented
by this role — flagged as an optional follow-up phase, not bundled into
this minimum-viable rollout.