---
- name: "🔍 Resolve {{ application_id }} hosting node + container id"
ansible.builtin.include_tasks: "{{ lookup('path_absolute', 'roles/sys-svc-compose/tasks/utils/swarm/resolve_host_cid.yml') }}"
vars:
resolve_service_key: "{{ entity_name }}"
resolve_output_prefix: LITELLM
resolve_compose_cid: "{{ LITELLM_CONTAINER }}"
- name: "⏳ Wait until the gateway accepts connections on its own port"
ansible.builtin.shell: | # nocheck: container-exec-resolver runtime-resolved CID, delegated to the hosting node
container exec -i {{ LITELLM_LOCAL_CID | quote }} python3 -c 'import socket; socket.create_connection(("127.0.0.1", {{ LITELLM_PORT }}), 5).close()'
register: litellm_gateway_listening
retries: 60
delay: 5
until: litellm_gateway_listening.rc == 0
changed_when: false
delegate_to: "{{ LITELLM_HOST_NODE }}"
- name: "🔑 Ensure a virtual key exists per consumer"
ansible.builtin.shell: | # nocheck: container-exec-resolver runtime-resolved CID, delegated to the hosting node
container exec -i -e LITELLM_PORT={{ LITELLM_PORT | quote }} {{ LITELLM_LOCAL_CID | quote }} python3 -c {{ lookup('file', lookup('path_absolute', 'roles/svc-ai-litellm/files/python/ensure_keys.py')) | quote }}
args:
stdin: "{{ LITELLM_CONSUMER_KEYS | to_json }}"
register: litellm_keys_result
retries: 10
delay: 6
until: litellm_keys_result.rc == 0
changed_when: "'CHANGED' in litellm_keys_result.stdout"
no_log: "{{ MASK_CREDENTIALS_IN_LOGS | bool }}"
delegate_to: "{{ LITELLM_HOST_NODE }}"
- name: "🛡️ Prove the gateway is closed and revocation stays per consumer"
ansible.builtin.shell: | # nocheck: container-exec-resolver runtime-resolved CID, delegated to the hosting node
container exec -i -e LITELLM_PORT={{ LITELLM_PORT | quote }} {{ LITELLM_LOCAL_CID | quote }} python3 -c {{ lookup('file', lookup('path_absolute', 'roles/svc-ai-litellm/files/python/probe_auth.py')) | quote }}
args:
stdin: "{{ {'key': (LITELLM_CONSUMER_KEYS | first).key} | to_json }}"
register: litellm_auth_probe
retries: 5
delay: 10
until: litellm_auth_probe.rc == 0
changed_when: false
no_log: "{{ MASK_CREDENTIALS_IN_LOGS | bool }}"
delegate_to: "{{ LITELLM_HOST_NODE }}"
- name: "🔥 Warm the chat model so the first prompt is not a cold load"
ansible.builtin.shell: | # nocheck: container-exec-resolver runtime-resolved CID, delegated to the hosting node
container exec -i -e LITELLM_PORT={{ LITELLM_PORT | quote }} -e LITELLM_MODEL={{ LITELLM_CHAT_MODEL | quote }} {{ LITELLM_LOCAL_CID | quote }} python3 -c {{ lookup('file', lookup('path_absolute', 'roles/svc-ai-litellm/files/python/warm_model.py')) | quote }}
register: litellm_warm_result
retries: 5
delay: 10
until: litellm_warm_result.rc == 0
changed_when: false
delegate_to: "{{ LITELLM_HOST_NODE }}"
when: LITELLM_CHAT_MODEL_SERVED | bool
- name: "⏱️ Rank the served models on measured generation speed"
ansible.builtin.include_tasks: 02_speed.yml
when:
- LITELLM_ROUTER_ALIAS | length > 0
- LITELLM_CHAT_MODEL_SERVED | bool
