esh-pfi-infrastructure/playbooks/deploy-fish-cpp.yaml

# Deploy fish-cpp (Fish s2-pro via s2.cpp + GGML CUDA inference) to irv-ml1.
#
# Builds the image locally — multi-stage CUDA devel base (CMake + s2.cpp
# compile, ~10 min cold) → CUDA runtime base + binary + python shim.
# Pre-pulls rodrigomt/s2-pro-gguf weights (q6_k default, ~5 GB) into
# the bind-mounted weights dir.
#
# Usage:
#   scripts/elway irv-ml1 --playbook playbooks/deploy-fish-cpp.yaml
#
# Idempotent — every step is creates-/when-gated; rerun is safe.

vars:
  compose_dir: /opt/docker/compose/fish-cpp
  references_dir: /worktank/fish-cpp/references
  weights_dir: /worktank/fish-cpp/weights
  host_port: "8199"
  weights_repo: rodrigomt/s2-pro-gguf
  default_quant: s2-pro-q6_k.gguf

steps:
  # ── host-side dirs ──────────────────────────────────────────────────

  - name: Ensure /worktank/fish-cpp root exists (one-time, sudo)
    shell: mkdir -p /worktank/fish-cpp
    sudo: true
    creates: /worktank/fish-cpp

  - name: Chown /worktank/fish-cpp to lkraven
    shell: chown -R lkraven:lkraven /worktank/fish-cpp
    sudo: true
    when: "[ \"$(stat -c %U /worktank/fish-cpp)\" != \"lkraven\" ]"

  - name: Ensure references dir exists
    shell: mkdir -p {{ references_dir }}
    creates: "{{ references_dir }}"

  - name: Ensure weights dir exists
    shell: mkdir -p {{ weights_dir }}
    creates: "{{ weights_dir }}"

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

  # ── deploy build context ────────────────────────────────────────────
  # s2.cpp is built INSIDE the docker image, but the Dockerfile + shim
  # need to be present in the compose dir so `docker compose build`
  # can find them.

  - name: Upload compose.yaml
    upload:
      src: stacks/fish-cpp/compose.yaml
      dest: "{{ compose_dir }}/compose.yaml"
      mode: "0644"

  - name: Upload Dockerfile
    upload:
      src: stacks/fish-cpp/Dockerfile
      dest: "{{ compose_dir }}/Dockerfile"
      mode: "0644"

  - name: Upload server.py (FastAPI shim)
    upload:
      src: stacks/fish-cpp/server.py
      dest: "{{ compose_dir }}/server.py"
      mode: "0644"

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

  # ── pre-pull weights ────────────────────────────────────────────────
  # q6_k + tokenizer.json (~5 GB total). Same one-shot
  # python:3.12-slim + huggingface_hub.snapshot_download + hf_transfer
  # pattern we've used for fish-s2, voxtral, etc. Idempotent on rerun
  # via `creates:` on the model file.

  - name: Pre-pull rodrigomt/s2-pro-gguf weights (q6_k + tokenizer, ~5 GB)
    shell: |
      docker run --rm --user 1000:1000 \
        -e HOME=/tmp/h -e HF_HUB_ENABLE_HF_TRANSFER=1 \
        -v {{ weights_dir }}:/dest \
        python:3.12-slim sh -c 'set -e; mkdir -p /tmp/h /tmp/pip /tmp/site; PIP_CACHE_DIR=/tmp/pip pip install --quiet --target /tmp/site huggingface_hub hf_transfer; PYTHONPATH=/tmp/site python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id=\"{{ weights_repo }}\", local_dir=\"/dest\", allow_patterns=[\"{{ default_quant }}\",\"tokenizer.json\"])"'
    creates: "{{ weights_dir }}/{{ default_quant }}"

  # ── build + bring up ────────────────────────────────────────────────

  - name: docker compose build (~10 min first time; CUDA toolchain + s2.cpp compile)
    shell: |
      set -o pipefail
      cd {{ compose_dir }} && docker compose build 2>&1 \
        | grep -vE '^#[0-9]+ |^ => |^=> |Collecting|Downloading|Requirement|Using cached|Installing collected|Successfully (installed|built)|━'

  - name: docker compose up -d
    shell: cd {{ compose_dir }} && docker compose up -d

  - name: Wait for /v1/health to respond
    shell: |
      for i in $(seq 1 60); do
        curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/v1/health && exit 0
        sleep 5
      done
      exit 1
    changed_when: "false"

verify:
  - name: /v1/health returns 200 + reports model loaded
    shell: |
      curl -sf http://localhost:{{ host_port }}/v1/health \
        | python3 -c "import json,sys; d=json.load(sys.stdin); assert d.get('status')=='ok' and d.get('model')"
    changed_when: "false"

  - name: /v1/tts returns a real WAV (POST with text body)
    # `set -e` so curl/file/grep failures actually propagate. The
    # previous version put `rm -f` as the last command, which always
    # exits 0 — masking real failures (verify reported OK even when
    # nothing was running on host_port). Trap-based cleanup runs the
    # rm even on failure.
    shell: |
      set -e
      out=$(mktemp --suffix=.wav)
      trap 'rm -f "$out"' EXIT
      curl -sf -X POST http://localhost:{{ host_port }}/v1/tts \
        -H 'Content-Type: application/json' \
        -d '{"text":"Verify."}' \
        -o "$out" --max-time 60
      file -b "$out" | grep -q '^RIFF.*WAVE'
    changed_when: "false"

  - name: Container is running
    shell: docker inspect fish-cpp --format '{{.State.Status}}' | grep -q running
    changed_when: "false"