homelab/ansible/group_vars/all/semaphore.yml

---
# ============================================================================
# Semaphore configuration-as-code
# ============================================================================
# Drives a freshly-deployed Semaphore instance into its desired state via
# the Semaphore REST API. Idempotent: every object is checked first; only
# missing ones are created. Existing objects are left alone.
#
# Loaded from group_vars/all/semaphore.yml so that the configuration is
# version-controlled in the homelab repo and survives a wipe-and-redeploy
# of the Semaphore VM.
# ============================================================================

# ---------------------------------------------------------------------------
# API connection (defaults to the local Traefik-fronted service-name URL).
# Override semaphore_api_url to point at a specific instance if needed.
# ---------------------------------------------------------------------------
semaphore_api_url: "https://semaphore.local.mk-labs.cloud/api"
semaphore_api_validate_certs: true
semaphore_api_token: "{{ vault_semaphore_api_token }}"

# Feature flag — keeps day1_deploy_semaphore.yml deploy-only by default.
# Set true to also run the configuration pass.
semaphore_configure: false

# ---------------------------------------------------------------------------
# Declarative configuration of the Semaphore instance.
# ---------------------------------------------------------------------------
#
# Top-level shape:
#
#   semaphore_config:
#     project:        single dict — the lab uses one project ("mk-labs")
#     keys:           list of credentials Semaphore stores
#     repositories:   git repos Semaphore can clone
#     inventories:    Ansible inventories from those repos
#     environments:   env-var bundles
#     templates:      task templates that tie everything together
#
# Each list element has a unique "name" used as the natural identity key.
# ---------------------------------------------------------------------------

semaphore_config:
  project:
    name: mk-labs
    alert: false
    max_parallel_tasks: 0  # 0 = unlimited

  keys:
    # The ansible-vault password. login_password type with empty login
    # — only the password field is consumed by Semaphore at runtime.
    - name: ansible-vault-pass
      type: login_password
      login: ""
      password: "{{ vault_ansible_vault_password }}"

    # SSH key for the gitea deploy access (clone the homelab repo).
    - name: gitea-deploy
      type: ssh
      ssh_login: git
      ssh_private_key: "{{ vault_gitea_deploy_key }}"

    # SSH key for the universal automation account 'wed' — pre-baked in
    # every mk-labs VM template. This is the canonical user Semaphore
    # uses to reach the fleet.
    - name: wed-ssh
      type: ssh
      ssh_login: wed
      ssh_private_key: "{{ vault_wed_ssh_private_key }}"

    # SSH key Semaphore can use to reach the fleet as jarvis (admin
    # account provisioned by linux-baseline). Retained for jobs that
    # specifically need jarvis-level access; the default is wed-ssh.
    - name: jarvis-ssh
      type: ssh
      ssh_login: jarvis
      ssh_private_key: "{{ vault_jarvis_ssh_private_key }}"

  repositories:
    - name: homelab
      git_url: "ssh://git@gitea.mk-labs.cloud:2221/rblundon/homelab.git"
      git_branch: main
      ssh_key: gitea-deploy

  inventories:
    - name: production
      type: file
      inventory_file: ansible/inventory.yml
      repository: homelab
      # wed is the universal automation account pre-baked in every VM
      # template. Semaphore uses it for fleet-wide jobs.
      ssh_key: wed-ssh
      # become_key is Semaphore's sudo PASSWORD slot, not a second SSH
      # key. wed has passwordless sudo on every host, so reference the
      # built-in "None" key. (Semaphore rejects an SSH-type key here.)
      become_key: None

  environments:
    - name: default
      env:
        ANSIBLE_HOST_KEY_CHECKING: "False"
        ANSIBLE_FORCE_COLOR: "True"
        # Semaphore runs ansible-playbook from the cloned REPO ROOT (not
        # from the playbook's directory as I first assumed). Path is
        # therefore relative to repo root, not playbook dir.
        ANSIBLE_ROLES_PATH: "ansible/roles"
        # Collections are installed by the semaphore role into a host-side
        # directory bind-mounted into the container at this path.
        ANSIBLE_COLLECTIONS_PATH: "/opt/ansible-collections"

  templates:
    - name: "day0_linux_baseline"
      description: "Apply the mk-labs Linux baseline to one or more hosts."
      app: ansible
      playbook: ansible/playbooks/day0_linux_baseline.yml
      inventory: production
      repository: homelab
      environment: default
      vault_password: ansible-vault-pass
      arguments: '["--diff"]'
      survey_vars:
        - name: target
          title: "Target host or group"
          description: "Inventory target (e.g. figment, semaphore_server, all)"
          required: true
          type: TextVar
          default_value: "all"

    - name: "day1_deploy_semaphore"
      description: "Re-deploy Semaphore + PostgreSQL on figment."
      app: ansible
      playbook: ansible/playbooks/day1_deploy_semaphore.yml
      inventory: production
      repository: homelab
      environment: default
      vault_password: ansible-vault-pass
      arguments: '["--diff"]'

    - name: "day0_linux_baseline_check"
      description: "Dry-run the baseline — shows diffs, applies nothing."
      app: ansible
      playbook: ansible/playbooks/day0_linux_baseline.yml
      inventory: production
      repository: homelab
      environment: default
      vault_password: ansible-vault-pass
      arguments: '["--check","--diff"]'
      survey_vars:
        - name: target
          title: "Target host or group"
          description: "Inventory target (e.g. figment, semaphore_server, all)"
          required: true
          type: TextVar
          default_value: "all"

    - name: "llm_inference_multimodel_stage_models"
      description: >-
        Stage additional GGUF models into /opt/models on astro-orbiter via the
        llm-inference-multimodel role (--tags models only). Idempotent: skips
        files already present at the correct byte size. Notifies the
        llama-server-router restart handler ONLY when a new GGUF is actually
        downloaded. Does NOT touch Phase 4 (verify) or the legacy
        llama-server-qwen service. Safe to run repeatedly.
      app: ansible
      playbook: ansible/playbooks/day1_deploy_llm_inference_multimodel.yml
      inventory: production
      repository: homelab
      environment: default
      vault_password: ansible-vault-pass
      arguments: '["--tags","models","--diff"]'
      # Scoped to --tags models:
      #   Phase 0 (discover) -- skipped (no tag)
      #   Phase 1 (models)   -- RUN (idempotent GGUF staging via stage_model.yml)
      #   Phase 2 (systemd)  -- skipped
      #   Phase 3 (firewall) -- skipped
      #   Phase 4 (verify)   -- SKIPPED (collision risk: verify.yml would start
      #                         llama-server-qwen on :8002, conflicting with the
      #                         production llama-server-router.service. Excluded
      #                         here deliberately. See t_730f9584.)

    - name: "llm_router_update_unit"
      description: >-
        Re-render and reload the llama-server-router systemd unit on astro-orbiter,
        then restart the live service so new args (e.g. --models-max) take effect.
        Drives playbooks/day2_bump_router_models_max.yml. Added 2026-08-12 (t_33acbb2e):
        bump --models-max 1 -> 4 with full VRAM budget note in host_vars.
      app: ansible
      playbook: ansible/playbooks/day2_bump_router_models_max.yml
      inventory: production
      repository: homelab
      environment: default
      vault_password: ansible-vault-pass
      arguments: '["--diff"]'