---
# ------------------------------------------------------------------------------
# Playbook: day2_swap_qwen38.yml
# Purpose:  Swap the primary production model on astro-orbiter router from
#           Qwen3.6-35B-A3B-UD-Q4_K_S to Qwen3.8-27B-Q4_K_M.
#           This is a GitOps-encoded record of the swap performed 2026-08-16
#           per Ryan's direction (kanban task t_f5f7e9ad).
#
# What this playbook does:
#   1. Renders the updated llama-server-router-preset.ini.j2 to
#      /opt/llama-server-router-preset.ini on astro-orbiter.
#   2. Reloads the llama-server-router service (SIGHUP / restart as needed).
#   3. Verifies the new model ID appears in /v1/models.
#
# Prerequisites:
#   - Qwen3.8-27B-Q4_K_M.gguf must be present in /opt/models on astro-orbiter.
#     (Downloaded out-of-band via wget during the swap task.)
#   - roles/llm-inference-multimodel/defaults/main.yml updated to reference
#     Qwen3.8-27B-Q4_K_M (done in this same commit).
#
# Run:
#   env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook \
#     -i inventory.yml \
#     playbooks/day2_swap_qwen38.yml
#
# Task reference: t_f5f7e9ad — War Machine, 2026-08-16
# ------------------------------------------------------------------------------
- name: Swap primary model to Qwen3.8-27B-Q4_K_M on astro-orbiter
  hosts: astro-orbiter
  become: true
  vars:
    llm_router_preset_enabled: true

  roles:
    - role: llm-inference-multimodel
      tags: [preset, systemd, verify]