# ═══════════════════════════════════════════════════════════
# LiteLLM Proxy — Routing pour Effi
# Endpoint OpenAI-compatible sur :4000 (host network)
# ‎
# Backend unique : Jean (llama.cpp/ROCm sur PC gaming .11:8080)
# via jean-proxy :3012 + WOL auto si PC eteint.
# ‎
# CONTRAINTE VRAM : la RX 7800 XT a 16 Go. Le modele Qwen3.6-27B IQ4_XS
# occupe ~15.3 Go. Ollama ne peut PAS cohabiter (llama3.1-8b = ~5 Go
# supplémentaires -> OOM). On abandonne Ollama et on expose 3 profils
# du meme modele Qwen3.6, avec ou sans raisonnement (toggle natif
# chat_template_kwargs.enable_thinking):
#   - qwen3.6-reason : raisonnement ON  (tâches complexes, code, analyse)
#   - qwen3.6-fast   : raisonnement OFF (chat rapide, mail, extraction simple)
#   - qwen3.6-27b    : alias (= reason, défaut)
# ‎
# Latence observee (campagne de tests 2026-06-27) :
#   reason : TTFT 11-38s, 60-75 tok/s (le modele reflechit avant de repondre)
#   fast   : TTFT 0.4-1s, 60-75 tok/s (reponse quasi immediate)
# ═══════════════════════════════════════════════════════════

model_list:
  # ═════════════════════════════════════════════════════════
  # Profil 1 — Raisonnement ON (défaut, pour tâches complexes)
  # Le modele reflechit (jusqu'a 2048 tokens de reasoning_content)
  # avant de produire sa reponse. Bon pour code, analyse, RAG, rapports.
  # ═════════════════════════════════════════════════════════
  - model_name: qwen3.6-reason
    litellm_params:
      model: openai/qwen3.6-reason
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: true

  - model_name: qwen3.6-27b
    litellm_params:
      model: openai/qwen3.6-27b
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: true

  # ═════════════════════════════════════════════════════════
  # Profil 2 — Raisonnement OFF (chat rapide, ~5x moins de latence)
  # Reponse immediate (TTFT <1s) sans phase de reflexion.
  # Ideal pour : chat interactif, redaction de mail, extraction
  # structuree simple, Q/R directes.
  # ═════════════════════════════════════════════════════════
  - model_name: qwen3.6-fast
    litellm_params:
      model: openai/qwen3.6-fast
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: false

  # Alias court "qwen3.6" = fast par defaut (usage chat le plus courant)
  - model_name: qwen3.6
    litellm_params:
      model: openai/qwen3.6
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: false

  # ═════════════════════════════════════════════════════════
  # Backend Ollama — COMMENTE (contention VRAM, voir entete)
  # Pour reactiver si dispo (autre machine / GPU dedie), decommenter
  # et s'assurer que le GPU peut charger les deux modeles.
  # ═════════════════════════════════════════════════════════
  # - model_name: llama3.1-8b
  #   litellm_params:
  #     model: ollama/llama3.1:8b
  #     api_base: http://localhost:3011
  #     timeout: 600

litellm_settings:
  drop_params: false   # ne pas dropper: on veut passer chat_template_kwargs a Jean
  telemetry: false

general_settings:
  master_key: sk-effi-litellm-master