# LiteLLM config for inference.coop
# PRODUCTION config: Tinfoil (TEE-protected inference)
# LiteLLM talks plaintext OpenAI to a local Tinfoil proxy (127.0.0.1:3301),
# which verifies the enclave attestation and encrypts request/response bodies
# with EHBP (HPKE) before forwarding to the Tinfoil enclave. Provider key set
# via environment variable TINFOIL_API_KEY.

model_list:
  # DeepSeek V4.1 Flash — default model (replaces V4 Flash, deprecated 2026-09-15)
  - model_name: deepseek-v4-1-flash
    litellm_params:
      model: openai/deepseek-v4-1-flash
      api_base: http://127.0.0.1:3301/v1
      api_key: os.environ/TINFOIL_API_KEY

  # GPT-OSS 120B — lightweight fallback
  - model_name: gpt-oss-120b
    litellm_params:
      model: openai/gpt-oss-120b
      api_base: http://127.0.0.1:3301/v1
      api_key: os.environ/TINFOIL_API_KEY

  # GLM-5.3 Flash — fast, efficient MoE model
  - model_name: glm-5-3-flash
    litellm_params:
      model: openai/glm-5-3-flash
      api_base: http://127.0.0.1:3301/v1
      api_key: os.environ/TINFOIL_API_KEY

# Fallback: if DeepSeek is down, use GPT-OSS
router_settings:
  num_retries: 2
  timeout: 30
  fallbacks:
    - deepseek-v4-1-flash:
        - gpt-oss-120b

general_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
  database_url: os.environ/DATABASE_URL
  store_model_in_db: true

litellm_settings:
  salt_key: os.environ/LITELLM_SALT_KEY
  drop_params: true
  num_threads: 4
  request_timeout: 30