# config/llm.cloud.yaml
# Snipe — LLM config for the managed cloud instance (menagerie)
#
# Mounted read-only into the cloud API container at /app/config/llm.yaml
# (see compose.cloud.yml).  Personal fine-tunes and local-only backends
# (claude_code, copilot) are intentionally excluded here.
#
# CF Orchestrator routes both ollama and vllm allocations for VRAM-aware
# scheduling.  CF_ORCH_URL must be set in .env for allocations to resolve;
# if cf-orch is unreachable the backend falls back to its static base_url.
#
# Model choice for query builder: llama3.1:8b
#   - Reliable instruction following and JSON output
#   - No creative fine-tuning drift (unlike writer models in the pool)
#   - Fits comfortably in 8 GB VRAM alongside other services

backends:
  ollama:
    type: openai_compat
    base_url: http://host.docker.internal:11434/v1
    api_key: ollama
    model: llama3.1:8b
    enabled: true
    supports_images: false
    cf_orch:
      service: ollama
      ttl_s: 300

  anthropic:
    type: anthropic
    api_key_env: ANTHROPIC_API_KEY
    model: claude-haiku-4-5-20251001
    enabled: false
    supports_images: false

fallback_order:
  - ollama
  - anthropic