---
# ------------------------------------------------------------------------------
# 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
#
# EXECUTION CHANNEL (2026-08-12, War Machine): run via the Semaphore template
# "llm_inference_multimodel_stage_models" (scoped to --tags models). Do NOT
# run this via direct ansible-playbook or ad-hoc ssh/curl/systemctl — all
# homelab inference changes go through Ansible roles executed by Semaphore for
# audit/visibility. Phase 1 (models) is idempotent: it only downloads/stages a
# GGUF when missing or size-mismatched, and only restarts the router when a new
# GGUF is detected (normal re-runs that find the files correct touch nothing).
#
# 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