---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/tasks/main.yml
# DESCRIPTION: Entry point — imports one task file per phase.
#              Phases are additive; re-running the full playbook is always
#              safe (idempotent). Use --tags to run a specific phase subset:
#                --tags discover,models,systemd,firewall,verify
#
# IMPORTANT: Phase 2 (systemd) deploys but does NOT start either service.
#            Phase 4 (verify) is what starts + smoke-tests them. This lets
#            Ryan review "systemd units land, nothing running yet" as a
#            distinct, revertable checkpoint before anything touches the
#            live GPU/VRAM state.
# ------------------------------------------------------------------------------

# Phase 0 — Discover (read-only; confirm how the existing Gemma llama-server
# is actually managed today before assuming a systemd unit exists)
- import_tasks: discover.yml
  tags: [discover]

# Phase 1 — Models (idempotent GGUF download, size-check guard)
- import_tasks: models.yml
  tags: [models]

# Phase 2 — Systemd (template + deploy both unit files, do NOT auto-start)
- import_tasks: systemd.yml
  tags: [systemd]

# Phase 3 — Firewall (scope :8001 and reconsider :8000 exposure)
- import_tasks: firewall.yml
  tags: [firewall]

# Phase 4 — Verify (start both services, curl smoke test, nvidia-smi VRAM check)
- import_tasks: verify.yml
  tags: [verify]