# Displace mistral-small-4 (heretic) on ana-ml2 GPU 0 and serve
# bjk110/Qwen3.5-122B-A10B-abliterated-NVFP4 (text-only) as the new `gen` model
# (operator 2026-06-19). Weights pre-staged at /tank/aimodels/qwen3.5-122b-a10b-nvfp4
# (incl. the repo's serving/entrypoint.sh + vllm_patches/ that the compose mounts).
#
# ⚠️ Downing mistral-small-4 takes down the Worldtree CHARACTER backend (vision-intact)
# until it's repointed — operator-acknowledged. REVERT = down qwen, up -d the heretic.
#
#   scripts/elway ana-ml2 --playbook playbooks/serve-qwen3.5-122b.yaml

vars:
  compose_dir: /opt/docker/compose/qwen3.5-122b
  heretic_dir: /opt/docker/compose/mistral-small-4-heretic
  model_dir: /tank/aimodels/qwen3.5-122b-a10b-nvfp4
  host_port: "8013"

steps:
  - name: Verify NVFP4 weights + the repo's patch/entrypoint are staged
    shell: |
      test -f {{ model_dir }}/model.safetensors.index.json \
        && test -f {{ model_dir }}/serving/entrypoint.sh \
        && test -f {{ model_dir }}/vllm_patches/patch_qwen35_moe_text.py
    changed_when: "false"

  - name: Ensure vLLM compile-cache dir exists (writable)
    shell: mkdir -p {{ model_dir }}/.cache/vllm
    creates: "{{ model_dir }}/.cache/vllm"

  - name: Ensure compose dir exists
    shell: mkdir -p {{ compose_dir }}
    creates: "{{ compose_dir }}"

  - name: Upload compose.yaml
    upload:
      src: stacks/qwen3.5-122b/compose.yaml
      dest: "{{ compose_dir }}/compose.yaml"
      mode: "0644"

  - name: Seed .env from template (only if absent)
    upload:
      src: stacks/qwen3.5-122b/.env.example
      dest: "{{ compose_dir }}/.env"
      mode: "0644"
    when: "[ ! -f {{ compose_dir }}/.env ]"

  - name: Displace — down mistral-small-4-heretic (frees GPU 0; no-op if down)
    shell: cd {{ heretic_dir }} && docker compose down

  - name: Bring up qwen3.5-122b
    shell: cd {{ compose_dir }} && docker compose up -d

  - name: Wait for vLLM /health (allow ~15 min for patch + NVFP4 MoE load + warmup)
    shell: |
      for i in $(seq 1 180); do
        curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
        sleep 5
      done
      exit 1
    changed_when: "false"

verify:
  - name: /health returns 200
    shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/health
    changed_when: "false"

  - name: served model id is qwen3.5-122-a10b
    shell: curl -sf http://localhost:{{ host_port }}/v1/models | grep -q qwen3.5-122-a10b
    changed_when: "false"

  - name: container running
    shell: docker inspect vllm-qwen35-122b --format '{{.State.Status}}' | grep -q running
    changed_when: "false"