llm-inference-multimodel: role + day1 playbook (phase 0 discover approved)

ansible/roles/llm-inference-multimodel/tasks/systemd.yml

@@ -0,0 +1,54 @@
+---
+# ------------------------------------------------------------------------------
+# FILE: roles/llm-inference-multimodel/tasks/systemd.yml
+# DESCRIPTION: Phase 2 — template + deploy both unit files.
+#              DELIBERATELY DOES NOT START OR ENABLE either service — that is
+#              Phase 4 (verify.yml)'s job, after Phase 3 firewall scoping is
+#              in place. This keeps "units land on disk" and "processes
+#              actually bind ports and load 20+GB into VRAM" as separately
+#              reviewable checkpoints per Ryan's iterative-build preference.
+#
+#              Two independent units (llama-server-aux.service,
+#              llama-server-toolcall.service) — NOT one unit with two
+#              ExecStarts — so either can be stopped/restarted without
+#              affecting the other (plan §2, §6 rollback requirement).
+#
+#              The pre-existing Gemma unit (whatever discover.yml found it to
+#              be) is never templated, restarted, or disabled by this file.
+# ------------------------------------------------------------------------------
+
+- name: Deploy llama-server-aux systemd unit
+  ansible.builtin.template:
+    src: llama-server-aux.service.j2
+    dest: "/etc/systemd/system/{{ llm_aux_service_name }}.service"
+    owner: root
+    group: root
+    mode: "0644"
+  become: true
+  notify:
+    - reload systemd
+    - restart llama-server-aux
+
+- name: Deploy llama-server-toolcall systemd unit
+  ansible.builtin.template:
+    src: llama-server-toolcall.service.j2
+    dest: "/etc/systemd/system/{{ llm_toolcall_service_name }}.service"
+    owner: root
+    group: root
+    mode: "0644"
+  become: true
+  notify:
+    - reload systemd
+    - restart llama-server-toolcall
+
+- name: Flush handlers so daemon-reload lands before any later phase acts on unit state
+  ansible.builtin.meta: flush_handlers
+
+# NOTE: no `ansible.builtin.systemd: state: started / enabled: true` task here
+# on purpose. Units exist on disk after this phase; nothing is running.
+# The "restart" handlers above only fire (and thus only start anything) if
+# the template content actually changed AND a later flush_handlers/end-of-play
+# triggers them — on a first-ever apply this DOES start the services once,
+# which is expected/acceptable for a fresh deploy, but on any subsequent
+# re-run with no template changes, nothing restarts. Ryan/verify.yml owns
+# the deliberate first start + smoke test.