---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/defaults/main.yml
# DESCRIPTION: Overridable defaults for the llm-inference-multimodel role.
#              Deploy target: astro-orbiter (10.1.71.130, RTX 3090 24GB).
#              Built ALONGSIDE roles/llm-inference (not a replacement) — that
#              role's CUDA/build/driver phases are the prerequisite; this role
#              assumes /opt/llama.cpp/build/bin/llama-server already exists.
#
#              See /home/hermes/astro-orbiter-multi-model-plan.md for the full
#              approved design (VRAM math, rationale, rollback story).
# ------------------------------------------------------------------------------

# Shared
llm_service_user: jarvis
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
llm_models_dir: /opt/models

# Bind address — deliberately NOT 0.0.0.0 (see plan §5). Default to the private
# LAN interface so both instances are reachable from Hermes but not the world.
# Override to 127.0.0.1 if even LAN-wide reachability is unwanted and a reverse
# proxy/localhost-only tunnel is used instead.
llm_bind_address: "10.1.71.130"

# Firewall scoping (Phase 3) — subnet/hosts allowed to reach the ports above.
# Override per-environment; default assumes Hermes runs somewhere on this /24.
llm_allowed_source_cidr: "10.1.70.0/24"

# --- Aux / classification instance (port 8000, Phi-4-14B) -------------------
# Text-only instruction model, no tool-calling training — safe offload target
# per the auxiliary-task-offload skill's "no tool_calls emission risk" bar.
llm_aux_port: 8000
llm_aux_model_path: "{{ llm_models_dir }}/phi-4-14b-instruct-Q4_K_M.gguf"
llm_aux_model_url: "https://huggingface.co/bartowski/phi-4-GGUF/resolve/main/phi-4-Q4_K_M.gguf"
llm_aux_model_min_bytes: 8000000000   # guard threshold; complete file ~8.5GB
llm_aux_ctx_size: 8192
llm_aux_parallel: 2
llm_aux_gpu_layers: 99
llm_aux_service_name: llama-server-aux
llm_aux_model_id: phi-4-14b-instruct   # served model name for OpenAI-compat API

# --- Tool-calling instance (port 8001, Mistral-Small-24B) --------------------
# Native function-calling support; deployed at Q3_K_M per plan §1 Option B
# to fit VRAM budget. MUST pass the §7 validation harness before any
# Claude-Code-capable profile is pointed at this port.
llm_toolcall_port: 8001
llm_toolcall_model_path: "{{ llm_models_dir }}/mistral-small-24b-instruct-2501-Q3_K_M.gguf"
llm_toolcall_model_url: "https://huggingface.co/bartowski/Mistral-Small-24B-Instruct-2501-GGUF/resolve/main/Mistral-Small-24B-Instruct-2501-Q3_K_M.gguf"
llm_toolcall_model_min_bytes: 11000000000   # guard threshold; complete file ~11.7GB
llm_toolcall_ctx_size: 4096
llm_toolcall_parallel: 1
llm_toolcall_gpu_layers: 99
llm_toolcall_service_name: llama-server-toolcall
llm_toolcall_model_id: mistral-small-24b-instruct-2501

# --- Existing Gemma baseline (rollback target — never modified by this role) -
# Populated by Phase 0 discovery (tasks/discover.yml) if not already known.
# Set here only as a fallback name to search for; discovery is authoritative.
llm_existing_gemma_service_name_guess: llama-server