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

ansible/playbooks/day1_deploy_llm_inference_multimodel.yml

@@ -0,0 +1,31 @@
+---
+# ------------------------------------------------------------------------------
+# FILE: playbooks/day1_deploy_llm_inference_multimodel.yml
+# DESCRIPTION: Day 1 playbook for the dual-model (aux + tool-calling) rollout
+#              on astro-orbiter. Builds on roles/llm-inference (CUDA/driver
+#              already done) — does not replace it.
+#
+# Usage:
+#   cd ~/git/homelab/ansible
+#   ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference_multimodel.yml
+#   # or scope to specific phases:
+#   ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference_multimodel.yml --tags discover
+#
+# KNOWN GAP (2026-08-05): Semaphore is currently broken; this is being run
+# via direct ansible-playbook as an accepted interim stopgap. Retarget
+# through Semaphore once it's repaired.
+#
+# Phases (see roles/llm-inference-multimodel/README.md for detail):
+#   0. discover  — read-only; confirm existing Gemma service management
+#   1. models    — idempotent GGUF downloads (Phi-4-14B, Mistral-Small-24B)
+#   2. systemd   — deploy both unit files, do NOT auto-start
+#   3. firewall  — scope ports 8000/8001, non-0.0.0.0 bind
+#   4. verify    — start both services, smoke test, VRAM check
+# ------------------------------------------------------------------------------
+
+- name: Deploy dual-model LLM inference stack on astro-orbiter
+  hosts: astro_orbiter
+  gather_facts: true
+
+  roles:
+    - role: llm-inference-multimodel